From e5fc9e7a666e5964b60e05903b90aa832354b68c Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Fri, 12 Nov 2010 17:33:17 +0100
Subject: netfilter: nf_conntrack: don't always initialize ct->proto

ct->proto is big(60 bytes) due to structure ip_ct_tcp, and we don't need
to initialize the whole for all the other protocols. This patch moves
proto to the end of structure nf_conn, and pushes the initialization down
to the individual protocols.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index caf17db87dbc..abfff1e8e0d0 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -116,14 +116,14 @@ struct nf_conn {
 	u_int32_t secmark;
 #endif
 
-	/* Storage reserved for other modules: */
-	union nf_conntrack_proto proto;
-
 	/* Extensions */
 	struct nf_ct_ext *ext;
 #ifdef CONFIG_NET_NS
 	struct net *ct_net;
 #endif
+
+	/* Storage reserved for other modules, must be the last member */
+	union nf_conntrack_proto proto;
 };
 
 static inline struct nf_conn *
-- 
cgit v1.2.3


From 0f8e80044b26b4b30213a3fdffebd325cdc21362 Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Mon, 15 Nov 2010 11:51:06 +0100
Subject: netfilter: nf_conntrack: define ct_*_info as needed

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index abfff1e8e0d0..8a58901c96d3 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -50,11 +50,24 @@ union nf_conntrack_expect_proto {
 /* per conntrack: application helper private data */
 union nf_conntrack_help {
 	/* insert conntrack helper private data (master) here */
+#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE)
 	struct nf_ct_ftp_master ct_ftp_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_PPTP) || \
+    defined(CONFIG_NF_CONNTRACK_PPTP_MODULE)
 	struct nf_ct_pptp_master ct_pptp_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_H323) || \
+    defined(CONFIG_NF_CONNTRACK_H323_MODULE)
 	struct nf_ct_h323_master ct_h323_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_SANE) || \
+    defined(CONFIG_NF_CONNTRACK_SANE_MODULE)
 	struct nf_ct_sane_master ct_sane_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE)
 	struct nf_ct_sip_master ct_sip_info;
+#endif
 };
 
 #include <linux/types.h>
-- 
cgit v1.2.3


From 76a2d3bcfcc86e2a8044258515b86492a37631a3 Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Mon, 15 Nov 2010 11:59:03 +0100
Subject: netfilter: nf_nat: don't use atomic bit operation

As we own the conntrack and the others can't see it until we confirm it,
we don't need to use atomic bit operation on ct->status.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_nat_core.h | 4 ++--
 net/ipv4/netfilter/nf_nat_core.c    | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h
index 33602ab66190..5aec85c29979 100644
--- a/include/net/netfilter/nf_nat_core.h
+++ b/include/net/netfilter/nf_nat_core.h
@@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {
 	if (manip == IP_NAT_MANIP_SRC)
-		return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
+		return ct->status & IPS_SRC_NAT_DONE_BIT;
 	else
-		return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status);
+		return ct->status & IPS_DST_NAT_DONE_BIT;
 }
 
 struct nlattr;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index c04787ce1a71..ab877acb22a1 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -323,9 +323,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 
 	/* It's done. */
 	if (maniptype == IP_NAT_MANIP_DST)
-		set_bit(IPS_DST_NAT_DONE_BIT, &ct->status);
+		ct->status |= IPS_DST_NAT_DONE_BIT;
 	else
-		set_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
+		ct->status |= IPS_SRC_NAT_DONE_BIT;
 
 	return NF_ACCEPT;
 }
-- 
cgit v1.2.3


From e0e76c83becc7536e8371e560504d836d34fcf7d Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Mon, 15 Nov 2010 12:23:24 +0100
Subject: netfilter: ct_extend: define NF_CT_EXT_* as needed

Less IDs make nf_ct_ext smaller.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack_ecache.h | 8 ++++++++
 include/net/netfilter/nf_conntrack_extend.h | 6 ++++++
 include/net/netfilter/nf_nat.h              | 4 ++++
 3 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 96ba5f7dcab6..f596b60d6d75 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -23,12 +23,17 @@ struct nf_conntrack_ecache {
 static inline struct nf_conntrack_ecache *
 nf_ct_ecache_find(const struct nf_conn *ct)
 {
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE);
+#else
+	return NULL;
+#endif
 }
 
 static inline struct nf_conntrack_ecache *
 nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
 {
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *e;
 
@@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
 		e->expmask = expmask;
 	}
 	return e;
+#else
+	return NULL;
+#endif
 };
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 0772d296dfdb..1a9f96db3798 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -7,10 +7,16 @@
 
 enum nf_ct_ext_id {
 	NF_CT_EXT_HELPER,
+#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	NF_CT_EXT_NAT,
+#endif
 	NF_CT_EXT_ACCT,
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	NF_CT_EXT_ECACHE,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
 	NF_CT_EXT_ZONE,
+#endif
 	NF_CT_EXT_NUM,
 };
 
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index f5f09f032a90..e966092a36f1 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -84,7 +84,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
 
 static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct)
 {
+#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	return nf_ct_ext_find(ct, NF_CT_EXT_NAT);
+#else
+	return NULL;
+#endif
 }
 
 #else  /* !__KERNEL__: iptables wants this to compile. */
-- 
cgit v1.2.3


From 03c0e5bb34c9755ae4d955c97fba40b24e9c7fe7 Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Mon, 15 Nov 2010 12:27:27 +0100
Subject: netfilter: nf_nat: define nat_pptp_info as needed

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_nat.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index e966092a36f1..aff80b190c12 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat {
 /* per conntrack: nat application helper private data */
 union nf_conntrack_nat_help {
 	/* insert nat helper private data here */
+#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE)
 	struct nf_nat_pptp nat_pptp_info;
+#endif
 };
 
 struct nf_conn;
-- 
cgit v1.2.3


From 0e60ebe04c51807db972d03665651ae6b5c26d7e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 15 Nov 2010 18:17:21 +0100
Subject: netfilter: add __rcu annotations

Add some __rcu annotations and use helpers to reduce number of sparse
warnings (CONFIG_SPARSE_RCU_POINTER=y)

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h                    |  6 +++---
 include/net/netfilter/nf_conntrack_ecache.h  |  4 ++--
 include/net/netfilter/nf_conntrack_l3proto.h |  2 +-
 net/netfilter/core.c                         |  4 ++--
 net/netfilter/nf_conntrack_expect.c          |  6 +++---
 net/netfilter/nf_conntrack_proto.c           | 20 +++++++++++++++-----
 net/netfilter/nf_conntrack_standalone.c      |  9 ++++++---
 net/netfilter/nf_log.c                       |  6 ++++--
 net/netfilter/nf_queue.c                     | 18 ++++++++++++++----
 net/netfilter/nfnetlink_log.c                |  6 +++---
 10 files changed, 53 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 89341c32631a..928a35ec21c7 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -265,7 +265,7 @@ struct nf_afinfo {
 	int		route_key_size;
 };
 
-extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO];
+extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO];
 static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family)
 {
 	return rcu_dereference(nf_afinfo[family]);
@@ -355,9 +355,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 #endif /*CONFIG_NETFILTER*/
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *);
+extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu;
 extern void nf_ct_attach(struct sk_buff *, struct sk_buff *);
-extern void (*nf_ct_destroy)(struct nf_conntrack *);
+extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
 #else
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
 #endif
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index f596b60d6d75..8fdb04b8cce0 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -67,7 +67,7 @@ struct nf_ct_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_ct_event *item);
 };
 
-extern struct nf_ct_event_notifier *nf_conntrack_event_cb;
+extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
 extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
 extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
 
@@ -167,7 +167,7 @@ struct nf_exp_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_exp_event *item);
 };
 
-extern struct nf_exp_event_notifier *nf_expect_event_cb;
+extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
 extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
 extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
 
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index a7547611e8f1..e8010f445ae1 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -73,7 +73,7 @@ struct nf_conntrack_l3proto {
 	struct module *me;
 };
 
-extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX];
+extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX];
 
 /* Protocol registration. */
 extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto);
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 85dabb86be6f..5faec4fd8193 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -212,7 +212,7 @@ EXPORT_SYMBOL(skb_make_writable);
 /* This does not belong here, but locally generated errors need it if connection
    tracking in use: without this, connection may not be in hash table, and hence
    manufactured ICMP or RST packets will not be associated with it. */
-void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *);
+void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly;
 EXPORT_SYMBOL(ip_ct_attach);
 
 void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
@@ -229,7 +229,7 @@ void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(nf_ct_attach);
 
-void (*nf_ct_destroy)(struct nf_conntrack *);
+void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly;
 EXPORT_SYMBOL(nf_ct_destroy);
 
 void nf_conntrack_destroy(struct nf_conntrack *nfct)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 46e8966912b1..cab196cf428c 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -482,7 +482,7 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
 	struct hlist_node *n;
 
 	for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
-		n = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		n = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 		if (n)
 			return n;
 	}
@@ -495,11 +495,11 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_expect_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_next_rcu(head));
 	while (head == NULL) {
 		if (++st->bucket >= nf_ct_expect_hsize)
 			return NULL;
-		head = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		head = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 	}
 	return head;
 }
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index dc7bb74110df..03b56a0fff30 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -166,6 +166,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct nf_conntrack_l3proto *l3proto
 int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto)
 {
 	int ret = 0;
+	struct nf_conntrack_l3proto *old;
 
 	if (proto->l3proto >= AF_MAX)
 		return -EBUSY;
@@ -174,7 +175,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto)
 		return -EINVAL;
 
 	mutex_lock(&nf_ct_proto_mutex);
-	if (nf_ct_l3protos[proto->l3proto] != &nf_conntrack_l3proto_generic) {
+	old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
+					lockdep_is_held(&nf_ct_proto_mutex));
+	if (old != &nf_conntrack_l3proto_generic) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -201,7 +204,9 @@ void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto)
 	BUG_ON(proto->l3proto >= AF_MAX);
 
 	mutex_lock(&nf_ct_proto_mutex);
-	BUG_ON(nf_ct_l3protos[proto->l3proto] != proto);
+	BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
+					 lockdep_is_held(&nf_ct_proto_mutex)
+					 ) != proto);
 	rcu_assign_pointer(nf_ct_l3protos[proto->l3proto],
 			   &nf_conntrack_l3proto_generic);
 	nf_ct_l3proto_unregister_sysctl(proto);
@@ -299,8 +304,10 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto)
 		smp_wmb();
 
 		nf_ct_protos[l4proto->l3proto] = proto_array;
-	} else if (nf_ct_protos[l4proto->l3proto][l4proto->l4proto] !=
-					&nf_conntrack_l4proto_generic) {
+	} else if (rcu_dereference_protected(
+			nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
+			lockdep_is_held(&nf_ct_proto_mutex)
+			) != &nf_conntrack_l4proto_generic) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -331,7 +338,10 @@ void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto)
 	BUG_ON(l4proto->l3proto >= PF_MAX);
 
 	mutex_lock(&nf_ct_proto_mutex);
-	BUG_ON(nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != l4proto);
+	BUG_ON(rcu_dereference_protected(
+			nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
+			lockdep_is_held(&nf_ct_proto_mutex)
+			) != l4proto);
 	rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
 			   &nf_conntrack_l4proto_generic);
 	nf_ct_l4proto_unregister_sysctl(l4proto);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0fb65705b44b..328f1d2a51f8 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <linux/rculist_nulls.h>
 
 MODULE_LICENSE("GPL");
 
@@ -56,7 +57,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	for (st->bucket = 0;
 	     st->bucket < net->ct.htable_size;
 	     st->bucket++) {
-		n = rcu_dereference(net->ct.hash[st->bucket].first);
+		n = rcu_dereference(hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -69,13 +70,15 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
 			if (++st->bucket >= net->ct.htable_size)
 				return NULL;
 		}
-		head = rcu_dereference(net->ct.hash[st->bucket].first);
+		head = rcu_dereference(
+				hlist_nulls_first_rcu(
+					&net->ct.hash[st->bucket]));
 	}
 	return head;
 }
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index b07393eab88e..20c775cff2a8 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -161,7 +161,8 @@ static int seq_show(struct seq_file *s, void *v)
 	struct nf_logger *t;
 	int ret;
 
-	logger = nf_loggers[*pos];
+	logger = rcu_dereference_protected(nf_loggers[*pos],
+					   lockdep_is_held(&nf_log_mutex));
 
 	if (!logger)
 		ret = seq_printf(s, "%2lld NONE (", *pos);
@@ -249,7 +250,8 @@ static int nf_log_proc_dostring(ctl_table *table, int write,
 		mutex_unlock(&nf_log_mutex);
 	} else {
 		mutex_lock(&nf_log_mutex);
-		logger = nf_loggers[tindex];
+		logger = rcu_dereference_protected(nf_loggers[tindex],
+						   lockdep_is_held(&nf_log_mutex));
 		if (!logger)
 			table->data = "NONE";
 		else
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 74aebed5bd28..1876f7411561 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -27,14 +27,17 @@ static DEFINE_MUTEX(queue_handler_mutex);
 int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
 {
 	int ret;
+	const struct nf_queue_handler *old;
 
 	if (pf >= ARRAY_SIZE(queue_handler))
 		return -EINVAL;
 
 	mutex_lock(&queue_handler_mutex);
-	if (queue_handler[pf] == qh)
+	old = rcu_dereference_protected(queue_handler[pf],
+					lockdep_is_held(&queue_handler_mutex));
+	if (old == qh)
 		ret = -EEXIST;
-	else if (queue_handler[pf])
+	else if (old)
 		ret = -EBUSY;
 	else {
 		rcu_assign_pointer(queue_handler[pf], qh);
@@ -49,11 +52,15 @@ EXPORT_SYMBOL(nf_register_queue_handler);
 /* The caller must flush their queue before this */
 int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
 {
+	const struct nf_queue_handler *old;
+
 	if (pf >= ARRAY_SIZE(queue_handler))
 		return -EINVAL;
 
 	mutex_lock(&queue_handler_mutex);
-	if (queue_handler[pf] && queue_handler[pf] != qh) {
+	old = rcu_dereference_protected(queue_handler[pf],
+					lockdep_is_held(&queue_handler_mutex));
+	if (old && old != qh) {
 		mutex_unlock(&queue_handler_mutex);
 		return -EINVAL;
 	}
@@ -73,7 +80,10 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh)
 
 	mutex_lock(&queue_handler_mutex);
 	for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++)  {
-		if (queue_handler[pf] == qh)
+		if (rcu_dereference_protected(
+				queue_handler[pf],
+				lockdep_is_held(&queue_handler_mutex)
+				) == qh)
 			rcu_assign_pointer(queue_handler[pf], NULL);
 	}
 	mutex_unlock(&queue_handler_mutex);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 6a1572b0ab41..91592da504b9 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -874,19 +874,19 @@ static struct hlist_node *get_first(struct iter_state *st)
 
 	for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) {
 		if (!hlist_empty(&instance_table[st->bucket]))
-			return rcu_dereference_bh(instance_table[st->bucket].first);
+			return rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket]));
 	}
 	return NULL;
 }
 
 static struct hlist_node *get_next(struct iter_state *st, struct hlist_node *h)
 {
-	h = rcu_dereference_bh(h->next);
+	h = rcu_dereference_bh(hlist_next_rcu(h));
 	while (!h) {
 		if (++st->bucket >= INSTANCE_BUCKETS)
 			return NULL;
 
-		h = rcu_dereference_bh(instance_table[st->bucket].first);
+		h = rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket]));
 	}
 	return h;
 }
-- 
cgit v1.2.3


From e9e5eee8733739f13a204132b502494b3f494f3b Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Mon, 8 Nov 2010 20:05:57 +0900
Subject: IPVS: Add persistence engine to connection entry

The dest of a connection may not exist if it has been created as the result
of connection synchronisation. But in order for connection entries for
templates with persistence engine data created through connection
synchronisation to be valid access to the persistence engine pointer is
required.  So add the persistence engine to the connection itself.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 16 ++++++++++++++--
 net/netfilter/ipvs/ip_vs_conn.c | 19 ++++++++++---------
 net/netfilter/ipvs/ip_vs_ctl.c  |  4 ++--
 net/netfilter/ipvs/ip_vs_pe.c   | 14 ++++----------
 4 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b7bbd6c28cfa..be2b5690f892 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -422,6 +422,7 @@ struct ip_vs_conn {
 	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
 	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
 
+	const struct ip_vs_pe	*pe;
 	char			*pe_data;
 	__u8			pe_data_len;
 };
@@ -814,8 +815,19 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
 void ip_vs_unbind_pe(struct ip_vs_service *svc);
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
-extern struct ip_vs_pe *ip_vs_pe_get(const char *name);
-extern void ip_vs_pe_put(struct ip_vs_pe *pe);
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
+
+static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		__module_get(pe->module);
+}
+
+static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		module_put(pe->module);
+}
 
 /*
  *	IPVS protocol functions (from ip_vs_proto.c)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e9adecdc8ca4..64a9ca314100 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -176,8 +176,8 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 	ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
 			      NULL, 0, &p);
 
-	if (cp->dest && cp->dest->svc->pe) {
-		p.pe = cp->dest->svc->pe;
+	if (cp->pe) {
+		p.pe = cp->pe;
 		p.pe_data = cp->pe_data;
 		p.pe_data_len = cp->pe_data_len;
 	}
@@ -765,6 +765,7 @@ static void ip_vs_conn_expire(unsigned long data)
 		if (cp->flags & IP_VS_CONN_F_NFCT)
 			ip_vs_conn_drop_conntrack(cp);
 
+		ip_vs_pe_put(cp->pe);
 		kfree(cp->pe_data);
 		if (unlikely(cp->app != NULL))
 			ip_vs_unbind_app(cp);
@@ -826,7 +827,9 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 			&cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
-	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) {
+	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) {
+		ip_vs_pe_get(p->pe);
+		cp->pe = p->pe;
 		cp->pe_data = p->pe_data;
 		cp->pe_data_len = p->pe_data_len;
 	}
@@ -958,15 +961,13 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
 
-		if (cp->dest && cp->pe_data &&
-		    cp->dest->svc->pe->show_pe_data) {
+		if (cp->pe_data) {
 			pe_data[0] = ' ';
-			len = strlen(cp->dest->svc->pe->name);
-			memcpy(pe_data + 1, cp->dest->svc->pe->name, len);
+			len = strlen(cp->pe->name);
+			memcpy(pe_data + 1, cp->pe->name, len);
 			pe_data[len + 1] = ' ';
 			len += 2;
-			len += cp->dest->svc->pe->show_pe_data(cp,
-							       pe_data + len);
+			len += cp->pe->show_pe_data(cp, pe_data + len);
 		}
 		pe_data[len] = '\0';
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5f5daa30b0af..3e92558dfcc2 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1139,7 +1139,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u,
 	}
 
 	if (u->pe_name && *u->pe_name) {
-		pe = ip_vs_pe_get(u->pe_name);
+		pe = ip_vs_pe_getbyname(u->pe_name);
 		if (pe == NULL) {
 			pr_info("persistence engine module ip_vs_pe_%s "
 				"not found\n", u->pe_name);
@@ -1250,7 +1250,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	old_sched = sched;
 
 	if (u->pe_name && *u->pe_name) {
-		pe = ip_vs_pe_get(u->pe_name);
+		pe = ip_vs_pe_getbyname(u->pe_name);
 		if (pe == NULL) {
 			pr_info("persistence engine module ip_vs_pe_%s "
 				"not found\n", u->pe_name);
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index 3414af70ee12..e99f920b93d1 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -30,7 +30,7 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc)
 
 /* Get pe in the pe list by name */
 static struct ip_vs_pe *
-ip_vs_pe_getbyname(const char *pe_name)
+__ip_vs_pe_getbyname(const char *pe_name)
 {
 	struct ip_vs_pe *pe;
 
@@ -60,28 +60,22 @@ ip_vs_pe_getbyname(const char *pe_name)
 }
 
 /* Lookup pe and try to load it if it doesn't exist */
-struct ip_vs_pe *ip_vs_pe_get(const char *name)
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name)
 {
 	struct ip_vs_pe *pe;
 
 	/* Search for the pe by name */
-	pe = ip_vs_pe_getbyname(name);
+	pe = __ip_vs_pe_getbyname(name);
 
 	/* If pe not found, load the module and search again */
 	if (!pe) {
 		request_module("ip_vs_pe_%s", name);
-		pe = ip_vs_pe_getbyname(name);
+		pe = __ip_vs_pe_getbyname(name);
 	}
 
 	return pe;
 }
 
-void ip_vs_pe_put(struct ip_vs_pe *pe)
-{
-	if (pe && pe->module)
-		module_put(pe->module);
-}
-
 /* Register a pe in the pe list */
 int register_ip_vs_pe(struct ip_vs_pe *pe)
 {
-- 
cgit v1.2.3


From d494262b8a0f3507b62104a565849124abe29827 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Tue, 9 Nov 2010 09:33:15 +0900
Subject: IPVS: Make the cp argument to ip_vs_sync_conn() static

Acked-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 2 +-
 net/netfilter/ipvs/ip_vs_sync.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index be2b5690f892..d5a32e47f9d9 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -916,7 +916,7 @@ extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(const struct ip_vs_conn *cp);
 
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index ab85aedea17e..a4dccbc4f1bb 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -236,7 +236,7 @@ get_curr_sync_buff(unsigned long time)
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
  */
-void ip_vs_sync_conn(struct ip_vs_conn *cp)
+void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_sync_mesg *m;
 	struct ip_vs_sync_conn *s;
-- 
cgit v1.2.3


From 0e051e683ba4acb4e67c272c6a89707d974099d1 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Fri, 19 Nov 2010 14:25:07 +0100
Subject: IPVS: Backup, Prepare for transferring firewall marks (fwmark) to the
 backup daemon.

One struct will have fwmark added:
 * ip_vs_conn

ip_vs_conn_new() and ip_vs_find_dest()
will have an extra param - fwmark
The effects of that, is in this patch.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 6 ++++--
 net/netfilter/ipvs/ip_vs_conn.c | 5 +++--
 net/netfilter/ipvs/ip_vs_core.c | 8 ++++----
 net/netfilter/ipvs/ip_vs_ctl.c  | 4 ++--
 net/netfilter/ipvs/ip_vs_ftp.c  | 5 +++--
 net/netfilter/ipvs/ip_vs_sync.c | 4 ++--
 6 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d5a32e47f9d9..890f01c215e9 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -382,6 +382,7 @@ struct ip_vs_conn {
 	union nf_inet_addr       vaddr;          /* virtual address */
 	union nf_inet_addr       daddr;          /* destination address */
 	volatile __u32           flags;          /* status flags */
+	__u32                    fwmark;         /* Fire wall mark from skb */
 	__be16                   cport;
 	__be16                   vport;
 	__be16                   dport;
@@ -720,7 +721,7 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
 struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
 				  const union nf_inet_addr *daddr,
 				  __be16 dport, unsigned flags,
-				  struct ip_vs_dest *dest);
+				  struct ip_vs_dest *dest, __u32 fwmark);
 extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
 extern const char * ip_vs_state_name(__u16 proto, int state);
@@ -901,7 +902,8 @@ extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
 extern struct ip_vs_dest *
 ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
-		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol);
+		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol,
+		__u32 fwmark);
 extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 7615f9e3d955..66e4662925d5 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -613,7 +613,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	if ((cp) && (!cp->dest)) {
 		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
 				       &cp->vaddr, cp->vport,
-				       cp->protocol);
+				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
 		return dest;
 	} else
@@ -803,7 +803,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
 struct ip_vs_conn *
 ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	       const union nf_inet_addr *daddr, __be16 dport, unsigned flags,
-	       struct ip_vs_dest *dest)
+	       struct ip_vs_dest *dest, __u32 fwmark)
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol);
@@ -827,6 +827,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 			&cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
+	cp->fwmark         = fwmark;
 	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) {
 		ip_vs_pe_get(p->pe);
 		cp->pe = p->pe;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b4e51e9c5a04..e2bb3cd41c07 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -293,7 +293,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * and thus param.pe_data will be destroyed
 		 * when the template expires */
 		ct = ip_vs_conn_new(&param, &dest->addr, dport,
-				    IP_VS_CONN_F_TEMPLATE, dest);
+				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
 		if (ct == NULL) {
 			kfree(param.pe_data);
 			return NULL;
@@ -319,7 +319,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	 */
 	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0],
 			      &iph.daddr, ports[1], &param);
-	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest);
+	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
 		return NULL;
@@ -423,7 +423,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 				      pptr[0], &iph.daddr, pptr[1], &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
-				    flags, dest);
+				    flags, dest, skb->mark);
 		if (!cp)
 			return NULL;
 	}
@@ -489,7 +489,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 					      &iph.daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
-					    NULL);
+					    NULL, skb->mark);
 			if (!cp)
 				return NF_DROP;
 		}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 3e92558dfcc2..a5bd00279047 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -657,12 +657,12 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
-				   __be16 vport, __u16 protocol)
+				   __be16 vport, __u16 protocol, __u32 fwmark)
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_service *svc;
 
-	svc = ip_vs_service_get(af, 0, protocol, vaddr, vport);
+	svc = ip_vs_service_get(af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
 	dest = ip_vs_lookup_dest(svc, daddr, dport);
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 75455000ad1c..84aef65b37d1 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -208,7 +208,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			n_cp = ip_vs_conn_new(&p, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
 					      IP_VS_CONN_F_NFCT,
-					      cp->dest);
+					      cp->dest, skb->mark);
 			if (!n_cp)
 				return 0;
 
@@ -365,7 +365,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		if (!n_cp) {
 			n_cp = ip_vs_conn_new(&p, &cp->daddr,
 					      htons(ntohs(cp->dport)-1),
-					      IP_VS_CONN_F_NFCT, cp->dest);
+					      IP_VS_CONN_F_NFCT, cp->dest,
+					      skb->mark);
 			if (!n_cp)
 				return 0;
 
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3897d6bf3b29..47eed672dc08 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -404,7 +404,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 					       s->dport,
 					       (union nf_inet_addr *)&s->vaddr,
 					       s->vport,
-					       s->protocol);
+					       s->protocol, 0);
 			/*  Set the approprite ativity flag */
 			if (s->protocol == IPPROTO_TCP) {
 				if (state != IP_VS_TCP_S_ESTABLISHED)
@@ -419,7 +419,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			}
 			cp = ip_vs_conn_new(&param,
 					    (union nf_inet_addr *)&s->daddr,
-					    s->dport, flags, dest);
+					    s->dport, flags, dest, 0);
 			if (dest)
 				atomic_dec(&dest->refcnt);
 			if (!cp) {
-- 
cgit v1.2.3


From fe5e7a1efb664df0280f10377813d7099fb7eb0f Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Fri, 19 Nov 2010 14:25:12 +0100
Subject: IPVS: Backup, Adding Version 1 receive capability

Functionality improvements
 * flags  changed from 16 to 32 bits
 * fwmark added (32 bits)
 * timeout in sec. added (32 bits)
 * pe data added (Variable length)
 * IPv6 capabilities (3x16 bytes for addr.)
 * Version and type in every conn msg.

ip_vs_process_message() now handles Version 1 messages
and will call ip_vs_process_message_v0() for version 0 messages.

ip_vs_proc_conn() is common for both version, and handles the update of
connection hash.

ip_vs_conn_fill_param_sync()    - Version 1 messages only
ip_vs_conn_fill_param_sync_v0() - Version 0 messages only

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/linux/ip_vs.h           |   8 +
 include/net/ip_vs.h             |   1 +
 net/netfilter/ipvs/ip_vs_pe.c   |   5 +-
 net/netfilter/ipvs/ip_vs_sync.c | 549 +++++++++++++++++++++++++++++++---------
 4 files changed, 440 insertions(+), 123 deletions(-)

(limited to 'include')

diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h
index 5f43a3b2e3ad..4deb3834d62c 100644
--- a/include/linux/ip_vs.h
+++ b/include/linux/ip_vs.h
@@ -89,6 +89,14 @@
 #define IP_VS_CONN_F_TEMPLATE	0x1000		/* template, not connection */
 #define IP_VS_CONN_F_ONE_PACKET	0x2000		/* forward only one packet */
 
+#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \
+				  IP_VS_CONN_F_NOOUTPUT | \
+				  IP_VS_CONN_F_INACTIVE | \
+				  IP_VS_CONN_F_SEQ_MASK | \
+				  IP_VS_CONN_F_NO_CPORT | \
+				  IP_VS_CONN_F_TEMPLATE \
+				 )
+
 /* Flags that are not sent to backup server start from bit 16 */
 #define IP_VS_CONN_F_NFCT	(1 << 16)	/* use netfilter conntrack */
 
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 890f01c215e9..4069484df7bb 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -817,6 +817,7 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc);
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
 struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
+struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
 
 static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
 {
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index e99f920b93d1..5cf859ccb31b 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -29,12 +29,11 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc)
 }
 
 /* Get pe in the pe list by name */
-static struct ip_vs_pe *
-__ip_vs_pe_getbyname(const char *pe_name)
+struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
 {
 	struct ip_vs_pe *pe;
 
-	IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__,
+	IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__,
 		  pe_name);
 
 	spin_lock_bh(&ip_vs_pe_lock);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 566482f227fa..e071508901d1 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -35,6 +35,8 @@
 #include <linux/wait.h>
 #include <linux/kernel.h>
 
+#include <asm/unaligned.h>		/* Used for ntoh_seq and hton_seq */
+
 #include <net/ip.h>
 #include <net/sock.h>
 
@@ -286,6 +288,16 @@ static struct sockaddr_in mcast_addr = {
 	.sin_addr.s_addr	= cpu_to_be32(IP_VS_SYNC_GROUP),
 };
 
+/*
+ * Copy of struct ip_vs_seq
+ * From unaligned network order to aligned host order
+ */
+static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho)
+{
+	ho->init_seq       = get_unaligned_be32(&no->init_seq);
+	ho->delta          = get_unaligned_be32(&no->delta);
+	ho->previous_delta = get_unaligned_be32(&no->previous_delta);
+}
 
 static inline struct ip_vs_sync_buff *sb_dequeue(void)
 {
@@ -418,59 +430,186 @@ void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 		ip_vs_sync_conn(cp->control);
 }
 
+/*
+ *  fill_param used by version 1
+ */
 static inline int
-ip_vs_conn_fill_param_sync(int af, int protocol,
-			   const union nf_inet_addr *caddr, __be16 cport,
-			   const union nf_inet_addr *vaddr, __be16 vport,
-			   struct ip_vs_conn_param *p)
+ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
+			   struct ip_vs_conn_param *p,
+			   __u8 *pe_data, unsigned int pe_data_len,
+			   __u8 *pe_name, unsigned int pe_name_len)
 {
-	/* XXX: Need to take into account persistence engine */
-	ip_vs_conn_fill_param(af, protocol, caddr, cport, vaddr, vport, p);
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		ip_vs_conn_fill_param(af, sc->v6.protocol,
+				      (const union nf_inet_addr *)&sc->v6.caddr,
+				      sc->v6.cport,
+				      (const union nf_inet_addr *)&sc->v6.vaddr,
+				      sc->v6.vport, p);
+	else
+#endif
+		ip_vs_conn_fill_param(af, sc->v4.protocol,
+				      (const union nf_inet_addr *)&sc->v4.caddr,
+				      sc->v4.cport,
+				      (const union nf_inet_addr *)&sc->v4.vaddr,
+				      sc->v4.vport, p);
+	/* Handle pe data */
+	if (pe_data_len) {
+		if (pe_name_len) {
+			char buff[IP_VS_PENAME_MAXLEN+1];
+
+			memcpy(buff, pe_name, pe_name_len);
+			buff[pe_name_len]=0;
+			p->pe = __ip_vs_pe_getbyname(buff);
+			if (!p->pe) {
+				IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", buff);
+				return 1;
+			}
+		} else {
+			IP_VS_ERR_RL("BACKUP, Invalid PE parameters\n");
+			return 1;
+		}
+
+		p->pe_data = kmalloc(pe_data_len, GFP_ATOMIC);
+		if (!p->pe_data) {
+			if (p->pe->module)
+				module_put(p->pe->module);
+			return -ENOMEM;
+		}
+		memcpy(p->pe_data, pe_data, pe_data_len);
+		p->pe_data_len = pe_data_len;
+	}
 	return 0;
 }
 
 /*
- *      Process received multicast message and create the corresponding
- *      ip_vs_conn entries.
+ *  Connection Add / Update.
+ *  Common for version 0 and 1 reception of backup sync_conns.
+ *  Param: ...
+ *         timeout is in sec.
+ */
+static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
+			    unsigned state, unsigned protocol, unsigned type,
+			    const union nf_inet_addr *daddr, __be16 dport,
+			    unsigned long timeout, __u32 fwmark,
+			    struct ip_vs_sync_conn_options *opt,
+			    struct ip_vs_protocol *pp)
+{
+	struct ip_vs_dest *dest;
+	struct ip_vs_conn *cp;
+
+
+	if (!(flags & IP_VS_CONN_F_TEMPLATE))
+		cp = ip_vs_conn_in_get(param);
+	else
+		cp = ip_vs_ct_in_get(param);
+
+	if (cp && param->pe_data) 	/* Free pe_data */
+		kfree(param->pe_data);
+	if (!cp) {
+		/*
+		 * Find the appropriate destination for the connection.
+		 * If it is not found the connection will remain unbound
+		 * but still handled.
+		 */
+		dest = ip_vs_find_dest(type, daddr, dport, param->vaddr,
+				       param->vport, protocol, fwmark);
+
+		/*  Set the approprite ativity flag */
+		if (protocol == IPPROTO_TCP) {
+			if (state != IP_VS_TCP_S_ESTABLISHED)
+				flags |= IP_VS_CONN_F_INACTIVE;
+			else
+				flags &= ~IP_VS_CONN_F_INACTIVE;
+		} else if (protocol == IPPROTO_SCTP) {
+			if (state != IP_VS_SCTP_S_ESTABLISHED)
+				flags |= IP_VS_CONN_F_INACTIVE;
+			else
+				flags &= ~IP_VS_CONN_F_INACTIVE;
+		}
+		cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
+		if (dest)
+			atomic_dec(&dest->refcnt);
+		if (!cp) {
+			if (param->pe_data)
+				kfree(param->pe_data);
+			IP_VS_DBG(2, "BACKUP, add new conn. failed\n");
+			return;
+		}
+	} else if (!cp->dest) {
+		dest = ip_vs_try_bind_dest(cp);
+		if (dest)
+			atomic_dec(&dest->refcnt);
+	} else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
+		(cp->state != state)) {
+		/* update active/inactive flag for the connection */
+		dest = cp->dest;
+		if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
+			(state != IP_VS_TCP_S_ESTABLISHED)) {
+			atomic_dec(&dest->activeconns);
+			atomic_inc(&dest->inactconns);
+			cp->flags |= IP_VS_CONN_F_INACTIVE;
+		} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
+			(state == IP_VS_TCP_S_ESTABLISHED)) {
+			atomic_inc(&dest->activeconns);
+			atomic_dec(&dest->inactconns);
+			cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+		}
+	} else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) &&
+		(cp->state != state)) {
+		dest = cp->dest;
+		if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
+		(state != IP_VS_SCTP_S_ESTABLISHED)) {
+			atomic_dec(&dest->activeconns);
+			atomic_inc(&dest->inactconns);
+			cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+		}
+	}
+
+	if (opt)
+		memcpy(&cp->in_seq, opt, sizeof(*opt));
+	atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
+	cp->state = state;
+	cp->old_state = cp->state;
+	/*
+	 * For Ver 0 messages style
+	 *  - Not possible to recover the right timeout for templates
+	 *  - can not find the right fwmark
+	 *    virtual service. If needed, we can do it for
+	 *    non-fwmark persistent services.
+	 * Ver 1 messages style.
+	 *  - No problem.
+	 */
+	if (timeout) {
+		if (timeout > MAX_SCHEDULE_TIMEOUT / HZ)
+			timeout = MAX_SCHEDULE_TIMEOUT / HZ;
+		cp->timeout = timeout*HZ;
+	} else if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
+		cp->timeout = pp->timeout_table[state];
+	else
+		cp->timeout = (3*60*HZ);
+	ip_vs_conn_put(cp);
+}
+
+/*
+ *  Process received multicast message for Version 0
  */
-static void ip_vs_process_message(char *buffer, const size_t buflen)
+static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
 	struct ip_vs_sync_conn_v0 *s;
 	struct ip_vs_sync_conn_options *opt;
-	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
-	struct ip_vs_dest *dest;
 	struct ip_vs_conn_param param;
 	char *p;
 	int i;
 
-	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
-		IP_VS_ERR_RL("sync message header too short\n");
-		return;
-	}
-
-	/* Convert size back to host byte order */
-	m->size = ntohs(m->size);
-
-	if (buflen != m->size) {
-		IP_VS_ERR_RL("bogus sync message size\n");
-		return;
-	}
-
-	/* SyncID sanity check */
-	if (ip_vs_backup_syncid != 0 && m->syncid != ip_vs_backup_syncid) {
-		IP_VS_DBG(7, "Ignoring incoming msg with syncid = %d\n",
-			  m->syncid);
-		return;
-	}
-
 	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
 	for (i=0; i<m->nr_conns; i++) {
 		unsigned flags, state;
 
 		if (p + SIMPLE_CONN_SIZE > buffer+buflen) {
-			IP_VS_ERR_RL("bogus conn in sync message\n");
+			IP_VS_ERR_RL("BACKUP v0, bogus conn\n");
 			return;
 		}
 		s = (struct ip_vs_sync_conn_v0 *) p;
@@ -480,7 +619,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			opt = (struct ip_vs_sync_conn_options *)&s[1];
 			p += FULL_CONN_SIZE;
 			if (p > buffer+buflen) {
-				IP_VS_ERR_RL("bogus conn options in sync message\n");
+				IP_VS_ERR_RL("BACKUP v0, Dropping buffer bogus conn options\n");
 				return;
 			}
 		} else {
@@ -492,12 +631,12 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 		if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
 			pp = ip_vs_proto_get(s->protocol);
 			if (!pp) {
-				IP_VS_ERR_RL("Unsupported protocol %u in sync msg\n",
+				IP_VS_DBG(2, "BACKUP v0, Unsupported protocol %u\n",
 					s->protocol);
 				continue;
 			}
 			if (state >= pp->num_states) {
-				IP_VS_DBG(2, "Invalid %s state %u in sync msg\n",
+				IP_VS_DBG(2, "BACKUP v0, Invalid %s state %u\n",
 					pp->name, state);
 				continue;
 			}
@@ -505,103 +644,273 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			/* protocol in templates is not used for state/timeout */
 			pp = NULL;
 			if (state > 0) {
-				IP_VS_DBG(2, "Invalid template state %u in sync msg\n",
+				IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n",
 					state);
 				state = 0;
 			}
 		}
 
-		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
-					       (union nf_inet_addr *)&s->caddr,
-					       s->cport,
-					       (union nf_inet_addr *)&s->vaddr,
-					       s->vport, &param)) {
-			pr_err("ip_vs_conn_fill_param_sync failed");
-			return;
+		ip_vs_conn_fill_param(AF_INET, s->protocol,
+				      (const union nf_inet_addr *)&s->caddr,
+				      s->cport,
+				      (const union nf_inet_addr *)&s->vaddr,
+				      s->vport, &param);
+
+		/* Send timeout as Zero */
+		ip_vs_proc_conn(&param, flags, state, s->protocol, AF_INET,
+				(union nf_inet_addr *)&s->daddr, s->dport,
+				0, 0, opt, pp);
+	}
+}
+
+/*
+ * Handle options
+ */
+static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen,
+				    __u32 *opt_flags,
+				    struct ip_vs_sync_conn_options *opt)
+{
+	struct ip_vs_sync_conn_options *topt;
+
+	topt = (struct ip_vs_sync_conn_options *)p;
+
+	if (plen != sizeof(struct ip_vs_sync_conn_options)) {
+		IP_VS_DBG(2, "BACKUP, bogus conn options length\n");
+		return -EINVAL;
+	}
+	if (*opt_flags & IPVS_OPT_F_SEQ_DATA) {
+		IP_VS_DBG(2, "BACKUP, conn options found twice\n");
+		return -EINVAL;
+	}
+	ntoh_seq(&topt->in_seq, &opt->in_seq);
+	ntoh_seq(&topt->out_seq, &opt->out_seq);
+	*opt_flags |= IPVS_OPT_F_SEQ_DATA;
+	return 0;
+}
+
+static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len,
+			  __u8 **data, unsigned int maxlen,
+			  __u32 *opt_flags, __u32 flag)
+{
+	if (plen > maxlen) {
+		IP_VS_DBG(2, "BACKUP, bogus par.data len > %d\n", maxlen);
+		return -EINVAL;
+	}
+	if (*opt_flags & flag) {
+		IP_VS_DBG(2, "BACKUP, Par.data found twice 0x%x\n", flag);
+		return -EINVAL;
+	}
+	*data_len = plen;
+	*data = p;
+	*opt_flags |= flag;
+	return 0;
+}
+/*
+ *   Process a Version 1 sync. connection
+ */
+static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
+{
+	struct ip_vs_sync_conn_options opt;
+	union  ip_vs_sync_conn *s;
+	struct ip_vs_protocol *pp;
+	struct ip_vs_conn_param param;
+	__u32 flags;
+	unsigned int af, state, pe_data_len=0, pe_name_len=0;
+	__u8 *pe_data=NULL, *pe_name=NULL;
+	__u32 opt_flags=0;
+	int retc=0;
+
+	s = (union ip_vs_sync_conn *) p;
+
+	if (s->v6.type & STYPE_F_INET6) {
+#ifdef CONFIG_IP_VS_IPV6
+		af = AF_INET6;
+		p += sizeof(struct ip_vs_sync_v6);
+#else
+		IP_VS_DBG(3,"BACKUP, IPv6 msg received, and IPVS is not compiled for IPv6\n");
+		retc = 10;
+		goto out;
+#endif
+	} else if (!s->v4.type) {
+		af = AF_INET;
+		p += sizeof(struct ip_vs_sync_v4);
+	} else {
+		return -10;
+	}
+	if (p > msg_end)
+		return -20;
+
+	/* Process optional params check Type & Len. */
+	while (p < msg_end) {
+		int ptype;
+		int plen;
+
+		if (p+2 > msg_end)
+			return -30;
+		ptype = *(p++);
+		plen  = *(p++);
+
+		if (!plen || ((p + plen) > msg_end))
+			return -40;
+		/* Handle seq option  p = param data */
+		switch (ptype & ~IPVS_OPT_F_PARAM) {
+		case IPVS_OPT_SEQ_DATA:
+			if (ip_vs_proc_seqopt(p, plen, &opt_flags, &opt))
+				return -50;
+			break;
+
+		case IPVS_OPT_PE_DATA:
+			if (ip_vs_proc_str(p, plen, &pe_data_len, &pe_data,
+					   IP_VS_PEDATA_MAXLEN, &opt_flags,
+					   IPVS_OPT_F_PE_DATA))
+				return -60;
+			break;
+
+		case IPVS_OPT_PE_NAME:
+			if (ip_vs_proc_str(p, plen,&pe_name_len, &pe_name,
+					   IP_VS_PENAME_MAXLEN, &opt_flags,
+					   IPVS_OPT_F_PE_NAME))
+				return -70;
+			break;
+
+		default:
+			/* Param data mandatory ? */
+			if (!(ptype & IPVS_OPT_F_PARAM)) {
+				IP_VS_DBG(3, "BACKUP, Unknown mandatory param %d found\n",
+					  ptype & ~IPVS_OPT_F_PARAM);
+				retc = 20;
+				goto out;
+			}
 		}
-		if (!(flags & IP_VS_CONN_F_TEMPLATE))
-			cp = ip_vs_conn_in_get(&param);
-		else
-			cp = ip_vs_ct_in_get(&param);
-		if (!cp) {
-			/*
-			 * Find the appropriate destination for the connection.
-			 * If it is not found the connection will remain unbound
-			 * but still handled.
-			 */
-			dest = ip_vs_find_dest(AF_INET,
-					       (union nf_inet_addr *)&s->daddr,
-					       s->dport,
-					       (union nf_inet_addr *)&s->vaddr,
-					       s->vport,
-					       s->protocol, 0);
-			/*  Set the approprite ativity flag */
-			if (s->protocol == IPPROTO_TCP) {
-				if (state != IP_VS_TCP_S_ESTABLISHED)
-					flags |= IP_VS_CONN_F_INACTIVE;
-				else
-					flags &= ~IP_VS_CONN_F_INACTIVE;
-			} else if (s->protocol == IPPROTO_SCTP) {
-				if (state != IP_VS_SCTP_S_ESTABLISHED)
-					flags |= IP_VS_CONN_F_INACTIVE;
-				else
-					flags &= ~IP_VS_CONN_F_INACTIVE;
+		p += plen;  /* Next option */
+	}
+
+	/* Get flags and Mask off unsupported */
+	flags  = ntohl(s->v4.flags) & IP_VS_CONN_F_BACKUP_MASK;
+	flags |= IP_VS_CONN_F_SYNC;
+	state = ntohs(s->v4.state);
+
+	if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
+		pp = ip_vs_proto_get(s->v4.protocol);
+		if (!pp) {
+			IP_VS_DBG(3,"BACKUP, Unsupported protocol %u\n",
+				s->v4.protocol);
+			retc = 30;
+			goto out;
+		}
+		if (state >= pp->num_states) {
+			IP_VS_DBG(3, "BACKUP, Invalid %s state %u\n",
+				pp->name, state);
+			retc = 40;
+			goto out;
+		}
+	} else {
+		/* protocol in templates is not used for state/timeout */
+		pp = NULL;
+		if (state > 0) {
+			IP_VS_DBG(3, "BACKUP, Invalid template state %u\n",
+				state);
+			state = 0;
+		}
+	}
+	if (ip_vs_conn_fill_param_sync(af, s, &param,
+					pe_data, pe_data_len,
+					pe_name, pe_name_len)) {
+		retc = 50;
+		goto out;
+	}
+	/* If only IPv4, just silent skip IPv6 */
+	if (af == AF_INET)
+		ip_vs_proc_conn(&param, flags, state, s->v4.protocol, af,
+				(union nf_inet_addr *)&s->v4.daddr, s->v4.dport,
+				ntohl(s->v4.timeout), ntohl(s->v4.fwmark),
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
+				pp);
+#ifdef CONFIG_IP_VS_IPV6
+	else
+		ip_vs_proc_conn(&param, flags, state, s->v6.protocol, af,
+				(union nf_inet_addr *)&s->v6.daddr, s->v6.dport,
+				ntohl(s->v6.timeout), ntohl(s->v6.fwmark),
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
+				pp);
+#endif
+	return 0;
+	/* Error exit */
+out:
+	IP_VS_DBG(2, "BACKUP, Single msg dropped err:%d\n", retc);
+	return retc;
+
+}
+/*
+ *      Process received multicast message and create the corresponding
+ *      ip_vs_conn entries.
+ *      Handles Version 0 & 1
+ */
+static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
+{
+	struct ip_vs_sync_mesg_v2 *m2 = (struct ip_vs_sync_mesg_v2 *)buffer;
+	__u8 *p, *msg_end;
+	unsigned int i, nr_conns;
+
+	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
+		IP_VS_DBG(2, "BACKUP, message header too short\n");
+		return;
+	}
+	/* Convert size back to host byte order */
+	m2->size = ntohs(m2->size);
+
+	if (buflen != m2->size) {
+		IP_VS_DBG(2, "BACKUP, bogus message size\n");
+		return;
+	}
+	/* SyncID sanity check */
+	if (ip_vs_backup_syncid != 0 && m2->syncid != ip_vs_backup_syncid) {
+		IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid);
+		return;
+	}
+	/* Handle version 1  message */
+	if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0)
+	    && (m2->spare == 0)) {
+
+		msg_end = buffer + sizeof(struct ip_vs_sync_mesg_v2);
+		nr_conns = m2->nr_conns;
+
+		for (i=0; i<nr_conns; i++) {
+			union ip_vs_sync_conn *s;
+			unsigned size;
+			int retc;
+
+			p = msg_end;
+			if (p + sizeof(s->v4) > buffer+buflen) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n");
+				return;
 			}
-			cp = ip_vs_conn_new(&param,
-					    (union nf_inet_addr *)&s->daddr,
-					    s->dport, flags, dest, 0);
-			if (dest)
-				atomic_dec(&dest->refcnt);
-			if (!cp) {
-				pr_err("ip_vs_conn_new failed\n");
+			s = (union ip_vs_sync_conn *)p;
+			size = ntohs(s->v4.ver_size) & SVER_MASK;
+			msg_end = p + size;
+			/* Basic sanity checks */
+			if (msg_end  > buffer+buflen) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, msg > buffer\n");
 				return;
 			}
-		} else if (!cp->dest) {
-			dest = ip_vs_try_bind_dest(cp);
-			if (dest)
-				atomic_dec(&dest->refcnt);
-		} else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
-			   (cp->state != state)) {
-			/* update active/inactive flag for the connection */
-			dest = cp->dest;
-			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
-				(state != IP_VS_TCP_S_ESTABLISHED)) {
-				atomic_dec(&dest->activeconns);
-				atomic_inc(&dest->inactconns);
-				cp->flags |= IP_VS_CONN_F_INACTIVE;
-			} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
-				(state == IP_VS_TCP_S_ESTABLISHED)) {
-				atomic_inc(&dest->activeconns);
-				atomic_dec(&dest->inactconns);
-				cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+			if (ntohs(s->v4.ver_size) >> SVER_SHIFT) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, Unknown version %d\n",
+					      ntohs(s->v4.ver_size) >> SVER_SHIFT);
+				return;
 			}
-		} else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) &&
-			   (cp->state != state)) {
-			dest = cp->dest;
-			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
-			     (state != IP_VS_SCTP_S_ESTABLISHED)) {
-			    atomic_dec(&dest->activeconns);
-			    atomic_inc(&dest->inactconns);
-			    cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+			/* Process a single sync_conn */
+			if ((retc=ip_vs_proc_sync_conn(p, msg_end)) < 0) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n",
+					     retc);
+				return;
 			}
+			/* Make sure we have 32 bit alignment */
+			msg_end = p + ((size + 3) & ~3);
 		}
-
-		if (opt)
-			memcpy(&cp->in_seq, opt, sizeof(*opt));
-		atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
-		cp->state = state;
-		cp->old_state = cp->state;
-		/*
-		 * We can not recover the right timeout for templates
-		 * in all cases, we can not find the right fwmark
-		 * virtual service. If needed, we can do it for
-		 * non-fwmark persistent services.
-		 */
-		if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
-			cp->timeout = pp->timeout_table[state];
-		else
-			cp->timeout = (3*60*HZ);
-		ip_vs_conn_put(cp);
+	} else {
+		/* Old type of message */
+		ip_vs_process_message_v0(buffer, buflen);
+		return;
 	}
 }
 
-- 
cgit v1.2.3


From 986a075795339c5ea1122ce9290dfd5504252eb0 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Fri, 19 Nov 2010 14:25:13 +0100
Subject: IPVS: Backup, Change sending to Version 1 format

Enable sending and removal of version 0 sending
Affected functions,

ip_vs_sync_buff_create()
ip_vs_sync_conn()

ip_vs_core.c removal of IPv4 check.

*v5
 Just check cp->pe_data_len in ip_vs_sync_conn
 Check if padding needed before adding a new sync_conn
 to the buffer, i.e. avoid sending padding at the end.

*v4
 moved sanity check and pe_name_len after sloop.
 use cp->pe instead of cp->dest->svc->pe
 real length in each sync_conn, not padded length
 however total size of a sync_msg includes padding.

*v3
 Sending ip_vs_sync_conn_options in network order.
 Sending Templates for ONE_PACKET conn.
 Renaming of ip_vs_sync_mesg to ip_vs_sync_mesg_v0

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |   2 +-
 net/netfilter/ipvs/ip_vs_core.c |  13 ++-
 net/netfilter/ipvs/ip_vs_sync.c | 189 +++++++++++++++++++++++++++++++---------
 3 files changed, 156 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4069484df7bb..a715f3db179a 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -919,7 +919,7 @@ extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(const struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
 
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 3445da6e8c95..5287771d0647 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1560,9 +1560,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 *
 	 * Sync connection if it is about to close to
 	 * encorage the standby servers to update the connections timeout
+	 *
+	 * For ONE_PKT let ip_vs_sync_conn() do the filter work.
 	 */
-	pkts = atomic_add_return(1, &cp->in_pkts);
-	if (af == AF_INET && (ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		pkts = sysctl_ip_vs_sync_threshold[0];
+	else
+		pkts = atomic_add_return(1, &cp->in_pkts);
+
+	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
 			(pkts % sysctl_ip_vs_sync_threshold[1]
@@ -1577,8 +1583,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	/* Keep this block last: TCP and others with pp->num_states <= 1 */
-	else if (af == AF_INET &&
-	    (ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	else if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
 	      (pkts % sysctl_ip_vs_sync_threshold[1]
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index e071508901d1..df5abf0e25af 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -226,7 +226,7 @@ struct ip_vs_sync_thread_data {
 #define MAX_CONNS_PER_SYNCBUFF	255 /* nr_conns in ip_vs_sync_mesg is 8 bit */
 
 /* Version 0 header */
-struct ip_vs_sync_mesg {
+struct ip_vs_sync_mesg_v0 {
 	__u8                    nr_conns;
 	__u8                    syncid;
 	__u16                   size;
@@ -235,7 +235,7 @@ struct ip_vs_sync_mesg {
 };
 
 /* Version 1 header */
-struct ip_vs_sync_mesg_v2 {
+struct ip_vs_sync_mesg {
 	__u8			reserved;	/* must be zero */
 	__u8			syncid;
 	__u16			size;
@@ -299,6 +299,17 @@ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho)
 	ho->previous_delta = get_unaligned_be32(&no->previous_delta);
 }
 
+/*
+ * Copy of struct ip_vs_seq
+ * From Aligned host order to unaligned network order
+ */
+static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no)
+{
+	put_unaligned_be32(ho->init_seq, &no->init_seq);
+	put_unaligned_be32(ho->delta, &no->delta);
+	put_unaligned_be32(ho->previous_delta, &no->previous_delta);
+}
+
 static inline struct ip_vs_sync_buff *sb_dequeue(void)
 {
 	struct ip_vs_sync_buff *sb;
@@ -317,6 +328,9 @@ static inline struct ip_vs_sync_buff *sb_dequeue(void)
 	return sb;
 }
 
+/*
+ * Create a new sync buffer for Version 1 proto.
+ */
 static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
 {
 	struct ip_vs_sync_buff *sb;
@@ -328,11 +342,15 @@ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
 		kfree(sb);
 		return NULL;
 	}
-	sb->mesg->nr_conns = 0;
+	sb->mesg->reserved = 0;  /* old nr_conns i.e. must be zeo now */
+	sb->mesg->version = SYNC_PROTO_VER;
 	sb->mesg->syncid = ip_vs_master_syncid;
-	sb->mesg->size = 4;
-	sb->head = (unsigned char *)sb->mesg + 4;
+	sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
+	sb->mesg->nr_conns = 0;
+	sb->mesg->spare = 0;
+	sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg);
 	sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen;
+
 	sb->firstuse = jiffies;
 	return sb;
 }
@@ -373,18 +391,60 @@ get_curr_sync_buff(unsigned long time)
 	return sb;
 }
 
-
 /*
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
+ *      Sending Version 1 messages
  */
-void ip_vs_sync_conn(const struct ip_vs_conn *cp)
+void ip_vs_sync_conn(struct ip_vs_conn *cp)
 {
 	struct ip_vs_sync_mesg *m;
-	struct ip_vs_sync_conn_v0 *s;
-	int len;
+	union ip_vs_sync_conn *s;
+	__u8 *p;
+	unsigned int len, pe_name_len, pad;
+
+	/* Do not sync ONE PACKET */
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		goto control;
+sloop:
+	/* Sanity checks */
+	pe_name_len = 0;
+	if (cp->pe_data_len) {
+		if (!cp->pe_data || !cp->dest) {
+			IP_VS_ERR_RL("SYNC, connection pe_data invalid\n");
+			return;
+		}
+		pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN);
+	}
 
 	spin_lock(&curr_sb_lock);
+
+#ifdef CONFIG_IP_VS_IPV6
+	if (cp->af == AF_INET6)
+		len = sizeof(struct ip_vs_sync_v6);
+	else
+#endif
+		len = sizeof(struct ip_vs_sync_v4);
+
+	if (cp->flags & IP_VS_CONN_F_SEQ_MASK)
+		len += sizeof(struct ip_vs_sync_conn_options) + 2;
+
+	if (cp->pe_data_len)
+		len += cp->pe_data_len + 2;	/* + Param hdr field */
+	if (pe_name_len)
+		len += pe_name_len + 2;
+
+	/* check if there is a space for this one  */
+	pad = 0;
+	if (curr_sb) {
+		pad = (4 - (size_t)curr_sb->head) & 3;
+		if (curr_sb->head + len + pad > curr_sb->end) {
+			sb_queue_tail(curr_sb);
+			curr_sb = NULL;
+			pad = 0;
+		}
+	}
+
 	if (!curr_sb) {
 		if (!(curr_sb=ip_vs_sync_buff_create())) {
 			spin_unlock(&curr_sb_lock);
@@ -393,41 +453,84 @@ void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 		}
 	}
 
-	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
-		SIMPLE_CONN_SIZE;
 	m = curr_sb->mesg;
-	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
-
-	/* copy members */
-	s->protocol = cp->protocol;
-	s->cport = cp->cport;
-	s->vport = cp->vport;
-	s->dport = cp->dport;
-	s->caddr = cp->caddr.ip;
-	s->vaddr = cp->vaddr.ip;
-	s->daddr = cp->daddr.ip;
-	s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED);
-	s->state = htons(cp->state);
-	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
-		struct ip_vs_sync_conn_options *opt =
-			(struct ip_vs_sync_conn_options *)&s[1];
-		memcpy(opt, &cp->in_seq, sizeof(*opt));
-	}
-
+	p = curr_sb->head;
+	curr_sb->head += pad + len;
+	m->size += pad + len;
+	/* Add ev. padding from prev. sync_conn */
+	while (pad--)
+		*(p++) = 0;
+
+	s = (union ip_vs_sync_conn *)p;
+
+	/* Set message type  & copy members */
+	s->v4.type = (cp->af == AF_INET6 ? STYPE_F_INET6 : 0);
+	s->v4.ver_size = htons(len & SVER_MASK);	/* Version 0 */
+	s->v4.flags = htonl(cp->flags & ~IP_VS_CONN_F_HASHED);
+	s->v4.state = htons(cp->state);
+	s->v4.protocol = cp->protocol;
+	s->v4.cport = cp->cport;
+	s->v4.vport = cp->vport;
+	s->v4.dport = cp->dport;
+	s->v4.fwmark = htonl(cp->fwmark);
+	s->v4.timeout = htonl(cp->timeout / HZ);
 	m->nr_conns++;
-	m->size += len;
-	curr_sb->head += len;
 
-	/* check if there is a space for next one */
-	if (curr_sb->head+FULL_CONN_SIZE > curr_sb->end) {
-		sb_queue_tail(curr_sb);
-		curr_sb = NULL;
+#ifdef CONFIG_IP_VS_IPV6
+	if (cp->af == AF_INET6) {
+		p += sizeof(struct ip_vs_sync_v6);
+		ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6);
+		ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6);
+		ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6);
+	} else
+#endif
+	{
+		p += sizeof(struct ip_vs_sync_v4);	/* options ptr */
+		s->v4.caddr = cp->caddr.ip;
+		s->v4.vaddr = cp->vaddr.ip;
+		s->v4.daddr = cp->daddr.ip;
+	}
+	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
+		*(p++) = IPVS_OPT_SEQ_DATA;
+		*(p++) = sizeof(struct ip_vs_sync_conn_options);
+		hton_seq((struct ip_vs_seq *)p, &cp->in_seq);
+		p += sizeof(struct ip_vs_seq);
+		hton_seq((struct ip_vs_seq *)p, &cp->out_seq);
+		p += sizeof(struct ip_vs_seq);
 	}
+	/* Handle pe data */
+	if (cp->pe_data_len && cp->pe_data) {
+		*(p++) = IPVS_OPT_PE_DATA;
+		*(p++) = cp->pe_data_len;
+		memcpy(p, cp->pe_data, cp->pe_data_len);
+		p += cp->pe_data_len;
+		if (pe_name_len) {
+			/* Add PE_NAME */
+			*(p++) = IPVS_OPT_PE_NAME;
+			*(p++) = pe_name_len;
+			memcpy(p, cp->pe->name, pe_name_len);
+			p += pe_name_len;
+		}
+	}
+
 	spin_unlock(&curr_sb_lock);
 
+control:
 	/* synchronize its controller if it has */
-	if (cp->control)
-		ip_vs_sync_conn(cp->control);
+	cp = cp->control;
+	if (!cp)
+		return;
+	/*
+	 * Reduce sync rate for templates
+	 * i.e only increment in_pkts for Templates.
+	 */
+	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
+		int pkts = atomic_add_return(1, &cp->in_pkts);
+
+		if (pkts % sysctl_ip_vs_sync_threshold[1] != 1)
+			return;
+	}
+	goto sloop;
 }
 
 /*
@@ -596,7 +699,7 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
  */
 static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 {
-	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
+	struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer;
 	struct ip_vs_sync_conn_v0 *s;
 	struct ip_vs_sync_conn_options *opt;
 	struct ip_vs_protocol *pp;
@@ -604,7 +707,7 @@ static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 	char *p;
 	int i;
 
-	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
+	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0);
 	for (i=0; i<m->nr_conns; i++) {
 		unsigned flags, state;
 
@@ -848,11 +951,11 @@ out:
  */
 static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 {
-	struct ip_vs_sync_mesg_v2 *m2 = (struct ip_vs_sync_mesg_v2 *)buffer;
+	struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
 	__u8 *p, *msg_end;
-	unsigned int i, nr_conns;
+	int i, nr_conns;
 
-	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
+	if (buflen < sizeof(struct ip_vs_sync_mesg_v0)) {
 		IP_VS_DBG(2, "BACKUP, message header too short\n");
 		return;
 	}
@@ -872,7 +975,7 @@ static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 	if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0)
 	    && (m2->spare == 0)) {
 
-		msg_end = buffer + sizeof(struct ip_vs_sync_mesg_v2);
+		msg_end = buffer + sizeof(struct ip_vs_sync_mesg);
 		nr_conns = m2->nr_conns;
 
 		for (i=0; i<nr_conns; i++) {
-- 
cgit v1.2.3


From b880c1f077000956b9f475d5f3b6c5e45ff2e342 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Fri, 19 Nov 2010 14:25:14 +0100
Subject: IPVS: Backup, adding version 0 sending capabilities

This patch adds a sysclt net.ipv4.vs.sync_version
that can be used to send sync msg in version 0 or 1 format.

sync_version value is logical,
     Value 1 (default) New version
           0 Plain old version

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |   2 +
 net/netfilter/ipvs/ip_vs_ctl.c  |  28 ++++++++-
 net/netfilter/ipvs/ip_vs_sync.c | 134 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 163 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a715f3db179a..d858264217ba 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -883,7 +883,9 @@ extern int sysctl_ip_vs_conntrack;
 extern int sysctl_ip_vs_snat_reroute;
 extern struct ip_vs_stats ip_vs_stats;
 extern const struct ctl_path net_vs_ctl_path[];
+extern int sysctl_ip_vs_sync_ver;
 
+extern void ip_vs_sync_switch_mode(int mode);
 extern struct ip_vs_service *
 ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a5bd00279047..d12a13c497ba 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -92,7 +92,7 @@ int sysctl_ip_vs_nat_icmp_send = 0;
 int sysctl_ip_vs_conntrack;
 #endif
 int sysctl_ip_vs_snat_reroute = 1;
-
+int sysctl_ip_vs_sync_ver = 1;		/* Default version of sync proto */
 
 #ifdef CONFIG_IP_VS_DEBUG
 static int sysctl_ip_vs_debug_level = 0;
@@ -1536,6 +1536,25 @@ proc_do_sync_threshold(ctl_table *table, int write,
 	return rc;
 }
 
+static int
+proc_do_sync_mode(ctl_table *table, int write,
+		     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int *valp = table->data;
+	int val = *valp;
+	int rc;
+
+	rc = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (write && (*valp != val)) {
+		if ((*valp < 0) || (*valp > 1)) {
+			/* Restore the correct value */
+			*valp = val;
+		} else {
+			ip_vs_sync_switch_mode(val);
+		}
+	}
+	return rc;
+}
 
 /*
  *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
@@ -1602,6 +1621,13 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.procname	= "sync_version",
+		.data		= &sysctl_ip_vs_sync_ver,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_do_sync_mode,
+	},
 #if 0
 	{
 		.procname	= "timeout_established",
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index df5abf0e25af..c1c167ab73ee 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -5,6 +5,18 @@
  *              high-performance and highly available server based on a
  *              cluster of servers.
  *
+ * Version 1,   is capable of handling both version 0 and 1 messages.
+ *              Version 0 is the plain old format.
+ *              Note Version 0 receivers will just drop Ver 1 messages.
+ *              Version 1 is capable of handle IPv6, Persistence data,
+ *              time-outs, and firewall marks.
+ *              In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order.
+ *              Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0
+ *
+ * Definitions  Message: is a complete datagram
+ *              Sync_conn: is a part of a Message
+ *              Param Data is an option to a Sync_conn.
+ *
  * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
  *
  * ip_vs_sync:  sync connection info from master load balancer to backups
@@ -15,6 +27,8 @@
  *	Alexandre Cassen	:	Added SyncID support for incoming sync
  *					messages filtering.
  *	Justin Ossevoort	:	Fix endian problem on sync message size.
+ *	Hans Schillstrom	:	Added Version 1: i.e. IPv6,
+ *					Persistence support, fwmark and time-out.
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -391,6 +405,121 @@ get_curr_sync_buff(unsigned long time)
 	return sb;
 }
 
+/*
+ * Switch mode from sending version 0 or 1
+ *  - must handle sync_buf
+ */
+void ip_vs_sync_switch_mode(int mode) {
+
+	if (!ip_vs_sync_state & IP_VS_STATE_MASTER)
+		return;
+	if (mode == sysctl_ip_vs_sync_ver || !curr_sb)
+		return;
+
+	spin_lock_bh(&curr_sb_lock);
+	/* Buffer empty ? then let buf_create do the job  */
+	if ( curr_sb->mesg->size <=  sizeof(struct ip_vs_sync_mesg)) {
+		kfree(curr_sb);
+		curr_sb = NULL;
+	} else {
+		spin_lock_bh(&ip_vs_sync_lock);
+		if (ip_vs_sync_state & IP_VS_STATE_MASTER)
+			list_add_tail(&curr_sb->list, &ip_vs_sync_queue);
+		else
+			ip_vs_sync_buff_release(curr_sb);
+		spin_unlock_bh(&ip_vs_sync_lock);
+	}
+	spin_unlock_bh(&curr_sb_lock);
+}
+
+/*
+ * Create a new sync buffer for Version 0 proto.
+ */
+static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
+{
+	struct ip_vs_sync_buff *sb;
+	struct ip_vs_sync_mesg_v0 *mesg;
+
+	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
+		return NULL;
+
+	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
+		kfree(sb);
+		return NULL;
+	}
+	mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg;
+	mesg->nr_conns = 0;
+	mesg->syncid = ip_vs_master_syncid;
+	mesg->size = 4;
+	sb->head = (unsigned char *)mesg + 4;
+	sb->end = (unsigned char *)mesg + sync_send_mesg_maxlen;
+	sb->firstuse = jiffies;
+	return sb;
+}
+
+/*
+ *      Version 0 , could be switched in by sys_ctl.
+ *      Add an ip_vs_conn information into the current sync_buff.
+ */
+void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
+{
+	struct ip_vs_sync_mesg_v0 *m;
+	struct ip_vs_sync_conn_v0 *s;
+	int len;
+
+	if (unlikely(cp->af != AF_INET))
+		return;
+	/* Do not sync ONE PACKET */
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		return;
+
+	spin_lock(&curr_sb_lock);
+	if (!curr_sb) {
+		if (!(curr_sb=ip_vs_sync_buff_create_v0())) {
+			spin_unlock(&curr_sb_lock);
+			pr_err("ip_vs_sync_buff_create failed.\n");
+			return;
+		}
+	}
+
+	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
+		SIMPLE_CONN_SIZE;
+	m = (struct ip_vs_sync_mesg_v0 *)curr_sb->mesg;
+	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
+
+	/* copy members */
+	s->reserved = 0;
+	s->protocol = cp->protocol;
+	s->cport = cp->cport;
+	s->vport = cp->vport;
+	s->dport = cp->dport;
+	s->caddr = cp->caddr.ip;
+	s->vaddr = cp->vaddr.ip;
+	s->daddr = cp->daddr.ip;
+	s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED);
+	s->state = htons(cp->state);
+	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
+		struct ip_vs_sync_conn_options *opt =
+			(struct ip_vs_sync_conn_options *)&s[1];
+		memcpy(opt, &cp->in_seq, sizeof(*opt));
+	}
+
+	m->nr_conns++;
+	m->size += len;
+	curr_sb->head += len;
+
+	/* check if there is a space for next one */
+	if (curr_sb->head + FULL_CONN_SIZE > curr_sb->end) {
+		sb_queue_tail(curr_sb);
+		curr_sb = NULL;
+	}
+	spin_unlock(&curr_sb_lock);
+
+	/* synchronize its controller if it has */
+	if (cp->control)
+		ip_vs_sync_conn(cp->control);
+}
+
 /*
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
@@ -403,6 +532,11 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp)
 	__u8 *p;
 	unsigned int len, pe_name_len, pad;
 
+	/* Handle old version of the protocol */
+	if (sysctl_ip_vs_sync_ver == 0) {
+		ip_vs_sync_conn_v0(cp);
+		return;
+	}
 	/* Do not sync ONE PACKET */
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		goto control;
-- 
cgit v1.2.3


From f1c722295e029eace7960fc687efd5afd67dc555 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Wed, 15 Dec 2010 22:58:53 +0100
Subject: netfilter: xtables: use guarded types

We are supposed to use the kernel's own types in userspace exports.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_CT.h          | 10 +++++-----
 include/linux/netfilter/xt_TCPOPTSTRIP.h |  2 +-
 include/linux/netfilter/xt_TPROXY.h      |  8 ++++----
 include/linux/netfilter/xt_cluster.h     |  8 ++++----
 include/linux/netfilter/xt_quota.h       |  6 +++---
 include/linux/netfilter/xt_time.h        | 14 +++++++-------
 include/linux/netfilter/xt_u32.h         | 16 ++++++++--------
 7 files changed, 32 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h
index 1b564106891d..fbf4c5658554 100644
--- a/include/linux/netfilter/xt_CT.h
+++ b/include/linux/netfilter/xt_CT.h
@@ -4,11 +4,11 @@
 #define XT_CT_NOTRACK	0x1
 
 struct xt_ct_target_info {
-	u_int16_t	flags;
-	u_int16_t	zone;
-	u_int32_t	ct_events;
-	u_int32_t	exp_events;
-	char		helper[16];
+	__u16 flags;
+	__u16 zone;
+	__u32 ct_events;
+	__u32 exp_events;
+	char helper[16];
 
 	/* Used internally by the kernel */
 	struct nf_conn	*ct __attribute__((aligned(8)));
diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h
index 2db543214ff5..342ef14b1761 100644
--- a/include/linux/netfilter/xt_TCPOPTSTRIP.h
+++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h
@@ -7,7 +7,7 @@
 	(((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0)
 
 struct xt_tcpoptstrip_target_info {
-	u_int32_t strip_bmap[8];
+	__u32 strip_bmap[8];
 };
 
 #endif /* _XT_TCPOPTSTRIP_H */
diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h
index 3f3d69361289..8097e0b4c15e 100644
--- a/include/linux/netfilter/xt_TPROXY.h
+++ b/include/linux/netfilter/xt_TPROXY.h
@@ -5,15 +5,15 @@
  * redirection. We can get rid of that whenever we get support for
  * mutliple targets in the same rule. */
 struct xt_tproxy_target_info {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	__be32 laddr;
 	__be16 lport;
 };
 
 struct xt_tproxy_target_info_v1 {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	union nf_inet_addr laddr;
 	__be16 lport;
 };
diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h
index 886682656f09..66cfa3c782ac 100644
--- a/include/linux/netfilter/xt_cluster.h
+++ b/include/linux/netfilter/xt_cluster.h
@@ -6,10 +6,10 @@ enum xt_cluster_flags {
 };
 
 struct xt_cluster_match_info {
-	u_int32_t		total_nodes;
-	u_int32_t		node_mask;
-	u_int32_t		hash_seed;
-	u_int32_t		flags;
+	__u32 total_nodes;
+	__u32 node_mask;
+	__u32 hash_seed;
+	__u32 flags;
 };
 
 #define XT_CLUSTER_NODES_MAX	32
diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h
index b0d28c659ab7..8bda65f0bc92 100644
--- a/include/linux/netfilter/xt_quota.h
+++ b/include/linux/netfilter/xt_quota.h
@@ -9,9 +9,9 @@ enum xt_quota_flags {
 struct xt_quota_priv;
 
 struct xt_quota_info {
-	u_int32_t		flags;
-	u_int32_t		pad;
-	aligned_u64		quota;
+	__u32 flags;
+	__u32 pad;
+	aligned_u64 quota;
 
 	/* Used internally by the kernel */
 	struct xt_quota_priv	*master;
diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h
index 14b6df412c9f..b8bd4568efdb 100644
--- a/include/linux/netfilter/xt_time.h
+++ b/include/linux/netfilter/xt_time.h
@@ -2,13 +2,13 @@
 #define _XT_TIME_H 1
 
 struct xt_time_info {
-	u_int32_t date_start;
-	u_int32_t date_stop;
-	u_int32_t daytime_start;
-	u_int32_t daytime_stop;
-	u_int32_t monthdays_match;
-	u_int8_t weekdays_match;
-	u_int8_t flags;
+	__u32 date_start;
+	__u32 date_stop;
+	__u32 daytime_start;
+	__u32 daytime_stop;
+	__u32 monthdays_match;
+	__u8 weekdays_match;
+	__u8 flags;
 };
 
 enum {
diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h
index 9947f56cdbdd..e8c3d8722bae 100644
--- a/include/linux/netfilter/xt_u32.h
+++ b/include/linux/netfilter/xt_u32.h
@@ -9,13 +9,13 @@ enum xt_u32_ops {
 };
 
 struct xt_u32_location_element {
-	u_int32_t number;
-	u_int8_t nextop;
+	__u32 number;
+	__u8 nextop;
 };
 
 struct xt_u32_value_element {
-	u_int32_t min;
-	u_int32_t max;
+	__u32 min;
+	__u32 max;
 };
 
 /*
@@ -27,14 +27,14 @@ struct xt_u32_value_element {
 struct xt_u32_test {
 	struct xt_u32_location_element location[XT_U32_MAXSIZE+1];
 	struct xt_u32_value_element value[XT_U32_MAXSIZE+1];
-	u_int8_t nnums;
-	u_int8_t nvalues;
+	__u8 nnums;
+	__u8 nvalues;
 };
 
 struct xt_u32 {
 	struct xt_u32_test tests[XT_U32_MAXSIZE+1];
-	u_int8_t ntests;
-	u_int8_t invert;
+	__u8 ntests;
+	__u8 invert;
 };
 
 #endif /* _XT_U32_H */
-- 
cgit v1.2.3


From ae90bdeaeac6b964b7a1e853a90a19f358a9ac20 Mon Sep 17 00:00:00 2001
From: KOVACS Krisztian <hidden@balabit.hu>
Date: Wed, 15 Dec 2010 23:53:41 +0100
Subject: netfilter: fix compilation when conntrack is disabled but tproxy is
 enabled

The IPv6 tproxy patches split IPv6 defragmentation off of conntrack, but
failed to update the #ifdef stanzas guarding the defragmentation related
fields and code in skbuff and conntrack related code in nf_defrag_ipv6.c.

This patch adds the required #ifdefs so that IPv6 tproxy can truly be used
without connection tracking.

Original report:
http://marc.info/?l=linux-netdev&m=129010118516341&w=2

Reported-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/skbuff.h                         | 15 +++++++++++++++
 include/net/netfilter/ipv6/nf_conntrack_ipv6.h | 10 ----------
 include/net/netfilter/ipv6/nf_defrag_ipv6.h    | 10 ++++++++++
 net/core/skbuff.c                              |  2 ++
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      |  8 +++++++-
 5 files changed, 34 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e6ba898de61c..4f2db79a2abb 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -255,6 +255,11 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
+#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
+    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
+#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
+#endif
+
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
@@ -362,6 +367,8 @@ struct sk_buff {
 	void			(*destructor)(struct sk_buff *skb);
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct nf_conntrack	*nfct;
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	struct sk_buff		*nfct_reasm;
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
@@ -2051,6 +2058,8 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 	if (nfct)
 		atomic_inc(&nfct->use);
 }
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
 {
 	if (skb)
@@ -2079,6 +2088,8 @@ static inline void nf_reset(struct sk_buff *skb)
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	nf_conntrack_put_reasm(skb->nfct_reasm);
 	skb->nfct_reasm = NULL;
 #endif
@@ -2095,6 +2106,8 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 	dst->nfct = src->nfct;
 	nf_conntrack_get(src->nfct);
 	dst->nfctinfo = src->nfctinfo;
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	dst->nfct_reasm = src->nfct_reasm;
 	nf_conntrack_get_reasm(src->nfct_reasm);
 #endif
@@ -2108,6 +2121,8 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(dst->nfct);
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	nf_conntrack_put_reasm(dst->nfct_reasm);
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
index 1ee717eb5b09..a4c993685795 100644
--- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
@@ -7,16 +7,6 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6;
 
-extern int nf_ct_frag6_init(void);
-extern void nf_ct_frag6_cleanup(void);
-extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			       struct net_device *in,
-			       struct net_device *out,
-			       int (*okfn)(struct sk_buff *));
-
-struct inet_frags_ctl;
-
 #include <linux/sysctl.h>
 extern struct ctl_table nf_ct_ipv6_sysctl_table[];
 
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index 94dd54d76b48..fd79c9a1779d 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -3,4 +3,14 @@
 
 extern void nf_defrag_ipv6_enable(void);
 
+extern int nf_ct_frag6_init(void);
+extern void nf_ct_frag6_cleanup(void);
+extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
+extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
+			       struct net_device *in,
+			       struct net_device *out,
+			       int (*okfn)(struct sk_buff *));
+
+struct inet_frags_ctl;
+
 #endif /* _NF_DEFRAG_IPV6_H */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 104f8444754a..74ebf4b5258a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -380,6 +380,8 @@ static void skb_release_head_state(struct sk_buff *skb)
 	}
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb->nfct);
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	nf_conntrack_put_reasm(skb->nfct_reasm);
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 99abfb53bab9..97c5b21b9674 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -19,13 +19,15 @@
 
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_bridge.h>
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#endif
+#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 
 static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
@@ -33,8 +35,10 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 {
 	u16 zone = NF_CT_DEFAULT_ZONE;
 
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	if (skb->nfct)
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+#endif
 
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge &&
@@ -56,9 +60,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 {
 	struct sk_buff *reasm;
 
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	/* Previously seen (loopback)?	*/
 	if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
 		return NF_ACCEPT;
+#endif
 
 	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
 	/* queued */
-- 
cgit v1.2.3


From ca01d6dd2d7a2652000307520777538740efc286 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Tue, 28 Dec 2010 14:25:21 -0800
Subject: pstore: new filesystem interface to platform persistent storage

Some platforms have a small amount of non-volatile storage that
can be used to store information useful to diagnose the cause of
a system crash.  This is the generic part of a file system interface
that presents information from the crash as a series of files in
/dev/pstore.  Once the information has been seen, the underlying
storage is freed by deleting the files.

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 Documentation/ABI/testing/pstore          |  35 ++++
 Documentation/ABI/testing/sysfs-fs-pstore |   7 +
 fs/Kconfig                                |   1 +
 fs/Makefile                               |   1 +
 fs/pstore/Kconfig                         |  13 ++
 fs/pstore/Makefile                        |   7 +
 fs/pstore/inode.c                         | 280 ++++++++++++++++++++++++++++++
 fs/pstore/internal.h                      |   7 +
 fs/pstore/platform.c                      | 202 +++++++++++++++++++++
 include/linux/magic.h                     |   1 +
 include/linux/pstore.h                    |  60 +++++++
 11 files changed, 614 insertions(+)
 create mode 100644 Documentation/ABI/testing/pstore
 create mode 100644 Documentation/ABI/testing/sysfs-fs-pstore
 create mode 100644 fs/pstore/Kconfig
 create mode 100644 fs/pstore/Makefile
 create mode 100644 fs/pstore/inode.c
 create mode 100644 fs/pstore/internal.h
 create mode 100644 fs/pstore/platform.c
 create mode 100644 include/linux/pstore.h

(limited to 'include')

diff --git a/Documentation/ABI/testing/pstore b/Documentation/ABI/testing/pstore
new file mode 100644
index 000000000000..f1fb2a004264
--- /dev/null
+++ b/Documentation/ABI/testing/pstore
@@ -0,0 +1,35 @@
+Where:		/dev/pstore/...
+Date:		January 2011
+Kernel Version: 2.6.38
+Contact:	tony.luck@intel.com
+Description:	Generic interface to platform dependent persistent storage.
+
+		Platforms that provide a mechanism to preserve some data
+		across system reboots can register with this driver to
+		provide a generic interface to show records captured in
+		the dying moments.  In the case of a panic the last part
+		of the console log is captured, but other interesting
+		data can also be saved.
+
+		# mount -t pstore - /dev/pstore
+
+		$ ls -l /dev/pstore
+		total 0
+		-r--r--r-- 1 root root 7896 Nov 30 15:38 dmesg-erst-1
+
+		Different users of this interface will result in different
+		filename prefixes.  Currently two are defined:
+
+		"dmesg"	- saved console log
+		"mce"	- architecture dependent data from fatal h/w error
+
+		Once the information in a file has been read, removing
+		the file will signal to the underlying persistent storage
+		device that it can reclaim the space for later re-use.
+
+		$ rm /dev/pstore/dmesg-erst-1
+
+		The expectation is that all files in /dev/pstore
+		will be saved elsewhere and erased from persistent store
+		soon after boot to free up space ready for the next
+		catastrophe.
diff --git a/Documentation/ABI/testing/sysfs-fs-pstore b/Documentation/ABI/testing/sysfs-fs-pstore
new file mode 100644
index 000000000000..8e659d854805
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-fs-pstore
@@ -0,0 +1,7 @@
+What:		/sys/fs/pstore/kmsg_bytes
+Date:		January 2011
+Kernel Version: 2.6.38
+Contact:	"Tony Luck" <tony.luck@intel.com>
+Description:
+		Controls amount of console log that will be saved
+		to persistent store on oops/panic.
diff --git a/fs/Kconfig b/fs/Kconfig
index 771f457402d4..2bbe47fec1ec 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -188,6 +188,7 @@ source "fs/omfs/Kconfig"
 source "fs/hpfs/Kconfig"
 source "fs/qnx4/Kconfig"
 source "fs/romfs/Kconfig"
+source "fs/pstore/Kconfig"
 source "fs/sysv/Kconfig"
 source "fs/ufs/Kconfig"
 source "fs/exofs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index a7f7cef0c0c8..db71a5b21a4f 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -121,3 +121,4 @@ obj-$(CONFIG_BTRFS_FS)		+= btrfs/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
 obj-$(CONFIG_EXOFS_FS)          += exofs/
 obj-$(CONFIG_CEPH_FS)		+= ceph/
+obj-$(CONFIG_PSTORE)		+= pstore/
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
new file mode 100644
index 000000000000..867d0ac026ce
--- /dev/null
+++ b/fs/pstore/Kconfig
@@ -0,0 +1,13 @@
+config PSTORE
+	bool "Persistant store support"
+	default n
+	help
+	   This option enables generic access to platform level
+	   persistent storage via "pstore" filesystem that can
+	   be mounted as /dev/pstore.  Only useful if you have
+	   a platform level driver that registers with pstore to
+	   provide the data, so you probably should just go say "Y"
+	   (or "M") to a platform specific persistent store driver
+	   (e.g. ACPI_APEI on X86) which will select this for you.
+	   If you don't have a platform persistent store driver,
+	   say N.
diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile
new file mode 100644
index 000000000000..760f4bce7d1d
--- /dev/null
+++ b/fs/pstore/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the linux pstorefs routines.
+#
+
+obj-y += pstore.o
+
+pstore-objs += inode.o platform.o
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
new file mode 100644
index 000000000000..0e806aafe857
--- /dev/null
+++ b/fs/pstore/inode.c
@@ -0,0 +1,280 @@
+/*
+ * Persistent Storage - ramfs parts.
+ *
+ * Copyright (C) 2010 Intel Corporation <tony.luck@intel.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/mount.h>
+#include <linux/ramfs.h>
+#include <linux/sched.h>
+#include <linux/magic.h>
+#include <linux/pstore.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+#define	PSTORE_NAMELEN	64
+
+struct pstore_private {
+	u64	id;
+	int	(*erase)(u64);
+};
+
+#define pstore_get_inode ramfs_get_inode
+
+/*
+ * When a file is unlinked from our file system we call the
+ * platform driver to erase the record from persistent store.
+ */
+static int pstore_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct pstore_private *p = dentry->d_inode->i_private;
+
+	p->erase(p->id);
+	kfree(p);
+
+	return simple_unlink(dir, dentry);
+}
+
+static const struct inode_operations pstore_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.unlink		= pstore_unlink,
+};
+
+static const struct super_operations pstore_ops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= generic_delete_inode,
+	.show_options	= generic_show_options,
+};
+
+static struct super_block *pstore_sb;
+static struct vfsmount *pstore_mnt;
+
+int pstore_is_mounted(void)
+{
+	return pstore_mnt != NULL;
+}
+
+/*
+ * Set up a file structure as if we had opened this file and
+ * write our data to it.
+ */
+static int pstore_writefile(struct inode *inode, struct dentry *dentry,
+	char *data, size_t size)
+{
+	struct file f;
+	ssize_t n;
+	mm_segment_t old_fs = get_fs();
+
+	memset(&f, '0', sizeof f);
+	f.f_mapping = inode->i_mapping;
+	f.f_path.dentry = dentry;
+	f.f_path.mnt = pstore_mnt;
+	f.f_pos = 0;
+	f.f_op = inode->i_fop;
+	set_fs(KERNEL_DS);
+	n = do_sync_write(&f, data, size, &f.f_pos);
+	set_fs(old_fs);
+
+	fsnotify_modify(&f);
+
+	return n == size;
+}
+
+/*
+ * Make a regular file in the root directory of our file system.
+ * Load it up with "size" bytes of data from "buf".
+ * Set the mtime & ctime to the date that this record was originally stored.
+ */
+int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
+			      char *data, size_t size,
+			      struct timespec time, int (*erase)(u64))
+{
+	struct dentry		*root = pstore_sb->s_root;
+	struct dentry		*dentry;
+	struct inode		*inode;
+	int			rc;
+	char			name[PSTORE_NAMELEN];
+	struct pstore_private	*private;
+
+	rc = -ENOMEM;
+	inode = pstore_get_inode(pstore_sb, root->d_inode, S_IFREG | 0444, 0);
+	if (!inode)
+		goto fail;
+	inode->i_uid = inode->i_gid = 0;
+	private = kmalloc(sizeof *private, GFP_KERNEL);
+	if (!private)
+		goto fail_alloc;
+	private->id = id;
+	private->erase = erase;
+
+	switch (type) {
+	case PSTORE_TYPE_DMESG:
+		sprintf(name, "dmesg-%s-%lld", psname, id);
+		break;
+	case PSTORE_TYPE_MCE:
+		sprintf(name, "mce-%s-%lld", psname, id);
+		break;
+	case PSTORE_TYPE_UNKNOWN:
+		sprintf(name, "unknown-%s-%lld", psname, id);
+		break;
+	default:
+		sprintf(name, "type%d-%s-%lld", type, psname, id);
+		break;
+	}
+
+	mutex_lock(&root->d_inode->i_mutex);
+
+	rc = -ENOSPC;
+	dentry = d_alloc_name(root, name);
+	if (IS_ERR(dentry))
+		goto fail_lockedalloc;
+
+	d_add(dentry, inode);
+
+	mutex_unlock(&root->d_inode->i_mutex);
+
+	if (!pstore_writefile(inode, dentry, data, size))
+		goto fail_write;
+
+	inode->i_private = private;
+
+	if (time.tv_sec)
+		inode->i_mtime = inode->i_ctime = time;
+
+	return 0;
+
+fail_write:
+	kfree(private);
+	inode->i_nlink--;
+	mutex_lock(&root->d_inode->i_mutex);
+	d_delete(dentry);
+	dput(dentry);
+	mutex_unlock(&root->d_inode->i_mutex);
+	goto fail;
+
+fail_lockedalloc:
+	mutex_unlock(&root->d_inode->i_mutex);
+	kfree(private);
+fail_alloc:
+	iput(inode);
+
+fail:
+	return rc;
+}
+
+int pstore_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *inode = NULL;
+	struct dentry *root;
+	int err;
+
+	save_mount_options(sb, data);
+
+	pstore_sb = sb;
+
+	sb->s_maxbytes		= MAX_LFS_FILESIZE;
+	sb->s_blocksize		= PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits	= PAGE_CACHE_SHIFT;
+	sb->s_magic		= PSTOREFS_MAGIC;
+	sb->s_op		= &pstore_ops;
+	sb->s_time_gran		= 1;
+
+	inode = pstore_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	if (!inode) {
+		err = -ENOMEM;
+		goto fail;
+	}
+	/* override ramfs "dir" options so we catch unlink(2) */
+	inode->i_op = &pstore_dir_inode_operations;
+
+	root = d_alloc_root(inode);
+	sb->s_root = root;
+	if (!root) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	pstore_get_records();
+
+	return 0;
+fail:
+	iput(inode);
+	return err;
+}
+
+static int pstore_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	struct dentry *root;
+
+	root = mount_nodev(fs_type, flags, data, pstore_fill_super);
+	if (IS_ERR(root))
+		return -ENOMEM;
+
+	mnt->mnt_root = root;
+	mnt->mnt_sb = root->d_sb;
+	pstore_mnt = mnt;
+
+	return 0;
+}
+
+static void pstore_kill_sb(struct super_block *sb)
+{
+	kill_litter_super(sb);
+	pstore_sb = NULL;
+	pstore_mnt = NULL;
+}
+
+static struct file_system_type pstore_fs_type = {
+	.name		= "pstore",
+	.get_sb		= pstore_get_sb,
+	.kill_sb	= pstore_kill_sb,
+};
+
+static int __init init_pstore_fs(void)
+{
+	int ret = 0;
+	struct kobject *pstorefs_kobj;
+
+	pstorefs_kobj = kobject_create_and_add("pstore", fs_kobj);
+	if (!pstorefs_kobj)
+		return -ENOMEM;
+
+	sysfs_create_file(pstorefs_kobj, &pstore_kmsg_bytes_attr.attr);
+
+	ret = register_filesystem(&pstore_fs_type);
+
+	if (ret) {
+		sysfs_remove_file(pstorefs_kobj, &pstore_kmsg_bytes_attr.attr);
+		kobject_put(pstorefs_kobj);
+	}
+
+	return ret;
+}
+module_init(init_pstore_fs)
+
+MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
new file mode 100644
index 000000000000..76c26d2fab29
--- /dev/null
+++ b/fs/pstore/internal.h
@@ -0,0 +1,7 @@
+extern void	pstore_get_records(void);
+extern int	pstore_mkfile(enum pstore_type_id, char *psname, u64 id,
+			      char *data, size_t size,
+			      struct timespec time, int (*erase)(u64));
+extern int	pstore_is_mounted(void);
+
+extern struct kobj_attribute pstore_kmsg_bytes_attr;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
new file mode 100644
index 000000000000..705fdf8abf6e
--- /dev/null
+++ b/fs/pstore/platform.c
@@ -0,0 +1,202 @@
+/*
+ * Persistent Storage - platform driver interface parts.
+ *
+ * Copyright (C) 2010 Intel Corporation <tony.luck@intel.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/atomic.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/kmsg_dump.h>
+#include <linux/module.h>
+#include <linux/pstore.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+/*
+ * pstore_lock just protects "psinfo" during
+ * calls to pstore_register()
+ */
+static DEFINE_SPINLOCK(pstore_lock);
+static struct pstore_info *psinfo;
+
+/* How much of the console log to snapshot. /sys/fs/pstore/kmsg_bytes */
+static unsigned long kmsg_bytes = 10240;
+
+static ssize_t b_show(struct kobject *kobj,
+		      struct kobj_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%lu\n", kmsg_bytes);
+}
+
+static ssize_t b_store(struct kobject *kobj, struct kobj_attribute *attr,
+		       const char *buf, size_t count)
+{
+	return (sscanf(buf, "%lu", &kmsg_bytes) > 0) ? count : 0;
+}
+
+struct kobj_attribute pstore_kmsg_bytes_attr =
+	__ATTR(kmsg_bytes, S_IRUGO | S_IWUSR, b_show, b_store);
+
+/* Tag each group of saved records with a sequence number */
+static int	oopscount;
+
+/*
+ * callback from kmsg_dump. (s2,l2) has the most recently
+ * written bytes, older bytes are in (s1,l1). Save as much
+ * as we can from the end of the buffer.
+ */
+static void pstore_dump(struct kmsg_dumper *dumper,
+	    enum kmsg_dump_reason reason,
+	    const char *s1, unsigned long l1,
+	    const char *s2, unsigned long l2)
+{
+	unsigned long	s1_start, s2_start;
+	unsigned long	l1_cpy, l2_cpy;
+	unsigned long	size, total = 0;
+	char		*dst;
+	u64		id;
+	int		hsize, part = 1;
+
+	mutex_lock(&psinfo->buf_mutex);
+	oopscount++;
+	while (total < kmsg_bytes) {
+		dst = psinfo->buf;
+		hsize = sprintf(dst, "Oops#%d Part%d\n", oopscount, part++);
+		size = psinfo->bufsize - hsize;
+		dst += hsize;
+
+		l2_cpy = min(l2, size);
+		l1_cpy = min(l1, size - l2_cpy);
+
+		if (l1_cpy + l2_cpy == 0)
+			break;
+
+		s2_start = l2 - l2_cpy;
+		s1_start = l1 - l1_cpy;
+
+		memcpy(dst, s1 + s1_start, l1_cpy);
+		memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy);
+
+		id = psinfo->write(PSTORE_TYPE_DMESG, hsize + l1_cpy + l2_cpy);
+		if (pstore_is_mounted())
+			pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id,
+				      psinfo->buf, hsize + l1_cpy + l2_cpy,
+				      CURRENT_TIME, psinfo->erase);
+		l1 -= l1_cpy;
+		l2 -= l2_cpy;
+		total += l1_cpy + l2_cpy;
+	}
+	mutex_unlock(&psinfo->buf_mutex);
+}
+
+static struct kmsg_dumper pstore_dumper = {
+	.dump = pstore_dump,
+};
+
+/*
+ * platform specific persistent storage driver registers with
+ * us here. If pstore is already mounted, call the platform
+ * read function right away to populate the file system. If not
+ * then the pstore mount code will call us later to fill out
+ * the file system.
+ *
+ * Register with kmsg_dump to save last part of console log on panic.
+ */
+int pstore_register(struct pstore_info *psi)
+{
+	struct module *owner = psi->owner;
+
+	spin_lock(&pstore_lock);
+	if (psinfo) {
+		spin_unlock(&pstore_lock);
+		return -EBUSY;
+	}
+	psinfo = psi;
+	spin_unlock(&pstore_lock);
+
+	if (owner && !try_module_get(owner)) {
+		psinfo = NULL;
+		return -EINVAL;
+	}
+
+	if (pstore_is_mounted())
+		pstore_get_records();
+
+	kmsg_dump_register(&pstore_dumper);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pstore_register);
+
+/*
+ * Read all the records from the persistent store. Create and
+ * file files in our filesystem.
+ */
+void pstore_get_records(void)
+{
+	struct pstore_info *psi = psinfo;
+	size_t			size;
+	u64			id;
+	enum pstore_type_id	type;
+	struct timespec		time;
+	int			failed = 0;
+
+	if (!psi)
+		return;
+
+	mutex_lock(&psinfo->buf_mutex);
+	while ((size = psi->read(&id, &type, &time)) > 0) {
+		if (pstore_mkfile(type, psi->name, id, psi->buf, size,
+				  time, psi->erase))
+			failed++;
+	}
+	mutex_unlock(&psinfo->buf_mutex);
+
+	if (failed)
+		printk(KERN_WARNING "pstore: failed to load %d record(s) from '%s'\n",
+		       failed, psi->name);
+}
+
+/*
+ * Call platform driver to write a record to the
+ * persistent store.
+ */
+int pstore_write(enum pstore_type_id type, char *buf, size_t size)
+{
+	u64	id;
+
+	if (!psinfo)
+		return -ENODEV;
+
+	if (size > psinfo->bufsize)
+		return -EFBIG;
+
+	mutex_lock(&psinfo->buf_mutex);
+	memcpy(psinfo->buf, buf, size);
+	id = psinfo->write(type, size);
+	if (pstore_is_mounted())
+		pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id, psinfo->buf,
+			      size, CURRENT_TIME, psinfo->erase);
+	mutex_unlock(&psinfo->buf_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pstore_write);
diff --git a/include/linux/magic.h b/include/linux/magic.h
index ff690d05f129..e87fd5ac3e5e 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -26,6 +26,7 @@
 #define ISOFS_SUPER_MAGIC	0x9660
 #define JFFS2_SUPER_MAGIC	0x72b6
 #define ANON_INODE_FS_MAGIC	0x09041934
+#define PSTOREFS_MAGIC		0x6165676C
 
 #define MINIX_SUPER_MAGIC	0x137F		/* original minix fs */
 #define MINIX_SUPER_MAGIC2	0x138F		/* minix fs, 30 char names */
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
new file mode 100644
index 000000000000..41977737bb7d
--- /dev/null
+++ b/include/linux/pstore.h
@@ -0,0 +1,60 @@
+/*
+ * Persistent Storage - pstore.h
+ *
+ * Copyright (C) 2010 Intel Corporation <tony.luck@intel.com>
+ *
+ * This code is the generic layer to export data records from platform
+ * level persistent storage via a file system.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#ifndef _LINUX_PSTORE_H
+#define _LINUX_PSTORE_H
+
+/* types */
+enum pstore_type_id {
+	PSTORE_TYPE_DMESG	= 0,
+	PSTORE_TYPE_MCE		= 1,
+	PSTORE_TYPE_UNKNOWN	= 255
+};
+
+struct pstore_info {
+	struct module	*owner;
+	char		*name;
+	struct mutex	buf_mutex;	/* serialize access to 'buf' */
+	char		*buf;
+	size_t		bufsize;
+	size_t		(*read)(u64 *id, enum pstore_type_id *type,
+			struct timespec *time);
+	u64		(*write)(enum pstore_type_id type, size_t size);
+	int		(*erase)(u64 id);
+};
+
+#ifdef CONFIG_PSTORE
+extern int pstore_register(struct pstore_info *);
+extern int pstore_write(enum pstore_type_id type, char *buf, size_t size);
+#else
+static inline int
+pstore_register(struct pstore_info *psi)
+{
+	return -ENODEV;
+}
+static inline int
+pstore_write(enum pstore_type_id type, char *buf, size_t size)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /*_LINUX_PSTORE_H*/
-- 
cgit v1.2.3


From 61b1ab4583e275af216c8454b9256de680499b19 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:42 +0100
Subject: IPVS: netns, add basic init per netns.

Preparation for network name-space init, in this stage
some empty functions exists.

In most files there is a check if it is root ns i.e. init_net
if (!net_eq(net, &init_net))
        return ...
this will be removed by the last patch, when enabling name-space.

*v3
 ip_vs_conn.c merge error corrected.
 net_ipvs #ifdef removed as sugested by Jan Engelhardt

[ horms@verge.net.au: Removed whitespace-change-only hunks ]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              | 11 +++++++
 include/net/net_namespace.h      |  2 ++
 include/net/netns/ip_vs.h        | 25 ++++++++++++++++
 net/netfilter/ipvs/ip_vs_app.c   | 28 +++++++++++++++---
 net/netfilter/ipvs/ip_vs_conn.c  | 34 ++++++++++++++++++----
 net/netfilter/ipvs/ip_vs_core.c  | 63 ++++++++++++++++++++++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_ctl.c   | 49 +++++++++++++++++++++++++------
 net/netfilter/ipvs/ip_vs_est.c   | 20 ++++++++++++-
 net/netfilter/ipvs/ip_vs_ftp.c   | 34 +++++++++++++++++++---
 net/netfilter/ipvs/ip_vs_lblc.c  | 37 +++++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_lblcr.c | 38 +++++++++++++++++++++---
 net/netfilter/ipvs/ip_vs_proto.c | 19 ++++++++++++
 net/netfilter/ipvs/ip_vs_sync.c  | 27 +++++++++++++++++
 13 files changed, 354 insertions(+), 33 deletions(-)
 create mode 100644 include/net/netns/ip_vs.h

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d858264217ba..c1c2ece3ed94 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -28,6 +28,15 @@
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #endif
+#include <net/net_namespace.h>		/* Netw namespace */
+
+/*
+ * Generic access of ipvs struct
+ */
+static inline struct netns_ipvs *net_ipvs(struct net* net)
+{
+	return net->ipvs;
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -922,6 +931,8 @@ extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
 extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern int ip_vs_sync_init(void);
+extern void ip_vs_sync_cleanup(void);
 
 
 /*
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 1bf812b21fb7..b3b4a34cb2cc 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -20,6 +20,7 @@
 #include <net/netns/conntrack.h>
 #endif
 #include <net/netns/xfrm.h>
+#include <net/netns/ip_vs.h>
 
 struct proc_dir_entry;
 struct net_device;
@@ -94,6 +95,7 @@ struct net {
 #ifdef CONFIG_XFRM
 	struct netns_xfrm	xfrm;
 #endif
+	struct netns_ipvs	*ipvs;
 };
 
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
new file mode 100644
index 000000000000..12fe84087cec
--- /dev/null
+++ b/include/net/netns/ip_vs.h
@@ -0,0 +1,25 @@
+/*
+ *  IP Virtual Server
+ *  Data structure for network namspace
+ *
+ */
+
+#ifndef IP_VS_H_
+#define IP_VS_H_
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/list_nulls.h>
+#include <linux/ip_vs.h>
+#include <asm/atomic.h>
+#include <linux/in.h>
+
+struct ip_vs_stats;
+struct ip_vs_sync_buff;
+struct ctl_table_header;
+
+struct netns_ipvs {
+	int			gen;		/* Generation */
+};
+
+#endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index a475edee0912..40b09ccc4896 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -569,15 +569,35 @@ static const struct file_operations ip_vs_app_fops = {
 };
 #endif
 
-int __init ip_vs_app_init(void)
+static int __net_init __ip_vs_app_init(struct net *net)
 {
-	/* we will replace it with proc_net_ipvs_create() soon */
-	proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops);
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
 	return 0;
 }
 
+static void __net_exit __ip_vs_app_cleanup(struct net *net)
+{
+	proc_net_remove(net, "ip_vs_app");
+}
+
+static struct pernet_operations ip_vs_app_ops = {
+	.init = __ip_vs_app_init,
+	.exit = __ip_vs_app_cleanup,
+};
+
+int __init ip_vs_app_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_app_ops);
+	return rv;
+}
+
 
 void ip_vs_app_cleanup(void)
 {
-	proc_net_remove(&init_net, "ip_vs_app");
+	unregister_pernet_subsys(&ip_vs_app_ops);
 }
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 66e4662925d5..7c1b502f8d8d 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1201,11 +1201,36 @@ static void ip_vs_conn_flush(void)
 		goto flush_again;
 	}
 }
+/*
+ * per netns init and exit
+ */
+int __net_init __ip_vs_conn_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
 
+	proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
+	proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+	return 0;
+}
+
+static void __net_exit __ip_vs_conn_cleanup(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	proc_net_remove(net, "ip_vs_conn");
+	proc_net_remove(net, "ip_vs_conn_sync");
+}
+static struct pernet_operations ipvs_conn_ops = {
+	.init = __ip_vs_conn_init,
+	.exit = __ip_vs_conn_cleanup,
+};
 
 int __init ip_vs_conn_init(void)
 {
 	int idx;
+	int retc;
 
 	/* Compute size and mask */
 	ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
@@ -1243,24 +1268,21 @@ int __init ip_vs_conn_init(void)
 		rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
 	}
 
-	proc_net_fops_create(&init_net, "ip_vs_conn", 0, &ip_vs_conn_fops);
-	proc_net_fops_create(&init_net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+	retc = register_pernet_subsys(&ipvs_conn_ops);
 
 	/* calculate the random value for connection hash */
 	get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));
 
-	return 0;
+	return retc;
 }
 
-
 void ip_vs_conn_cleanup(void)
 {
+	unregister_pernet_subsys(&ipvs_conn_ops);
 	/* flush all the connection entries first */
 	ip_vs_conn_flush();
 
 	/* Release the empty cache */
 	kmem_cache_destroy(ip_vs_conn_cachep);
-	proc_net_remove(&init_net, "ip_vs_conn");
-	proc_net_remove(&init_net, "ip_vs_conn_sync");
 	vfree(ip_vs_conn_tab);
 }
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5287771d0647..206f40c548d7 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -41,6 +41,7 @@
 #include <net/icmp.h>                   /* for icmp_send */
 #include <net/route.h>
 #include <net/ip6_checksum.h>
+#include <net/netns/generic.h>		/* net_generic() */
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
@@ -68,6 +69,12 @@ EXPORT_SYMBOL(ip_vs_conn_put);
 EXPORT_SYMBOL(ip_vs_get_debug_level);
 #endif
 
+int ip_vs_net_id __read_mostly;
+#ifdef IP_VS_GENERIC_NETNS
+EXPORT_SYMBOL(ip_vs_net_id);
+#endif
+/* netns cnt used for uniqueness */
+static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);
 
 /* ID used in ICMP lookups */
 #define icmp_id(icmph)          (((icmph)->un).echo.id)
@@ -1813,6 +1820,44 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 #endif
 };
 
+/*
+ *	Initialize IP Virtual Server netns mem.
+ */
+static int __net_init __ip_vs_init(struct net *net)
+{
+	struct netns_ipvs *ipvs;
+
+	if (!net_eq(net, &init_net)) {
+		pr_err("The final patch for enabling netns is missing\n");
+		return -EPERM;
+	}
+	ipvs = net_generic(net, ip_vs_net_id);
+	if (ipvs == NULL) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	/* Counters used for creating unique names */
+	ipvs->gen = atomic_read(&ipvs_netns_cnt);
+	atomic_inc(&ipvs_netns_cnt);
+	net->ipvs = ipvs;
+	printk(KERN_INFO "IPVS: Creating netns size=%lu id=%d\n",
+			 sizeof(struct netns_ipvs), ipvs->gen);
+	return 0;
+}
+
+static void __net_exit __ip_vs_cleanup(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	IP_VS_DBG(10, "ipvs netns %d released\n", ipvs->gen);
+}
+
+static struct pernet_operations ipvs_core_ops = {
+	.init = __ip_vs_init,
+	.exit = __ip_vs_cleanup,
+	.id   = &ip_vs_net_id,
+	.size = sizeof(struct netns_ipvs),
+};
 
 /*
  *	Initialize IP Virtual Server
@@ -1821,8 +1866,11 @@ static int __init ip_vs_init(void)
 {
 	int ret;
 
-	ip_vs_estimator_init();
+	ret = register_pernet_subsys(&ipvs_core_ops);	/* Alloc ip_vs struct */
+	if (ret < 0)
+		return ret;
 
+	ip_vs_estimator_init();
 	ret = ip_vs_control_init();
 	if (ret < 0) {
 		pr_err("can't setup control.\n");
@@ -1843,15 +1891,23 @@ static int __init ip_vs_init(void)
 		goto cleanup_app;
 	}
 
+	ret = ip_vs_sync_init();
+	if (ret < 0) {
+		pr_err("can't setup sync data.\n");
+		goto cleanup_conn;
+	}
+
 	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	if (ret < 0) {
 		pr_err("can't register hooks.\n");
-		goto cleanup_conn;
+		goto cleanup_sync;
 	}
 
 	pr_info("ipvs loaded.\n");
 	return ret;
 
+cleanup_sync:
+	ip_vs_sync_cleanup();
   cleanup_conn:
 	ip_vs_conn_cleanup();
   cleanup_app:
@@ -1861,17 +1917,20 @@ static int __init ip_vs_init(void)
 	ip_vs_control_cleanup();
   cleanup_estimator:
 	ip_vs_estimator_cleanup();
+	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	return ret;
 }
 
 static void __exit ip_vs_cleanup(void)
 {
 	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+	ip_vs_sync_cleanup();
 	ip_vs_conn_cleanup();
 	ip_vs_app_cleanup();
 	ip_vs_protocol_cleanup();
 	ip_vs_control_cleanup();
 	ip_vs_estimator_cleanup();
+	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	pr_info("ipvs unloaded.\n");
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ca49e928f302..ceeef4352d34 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3406,6 +3406,42 @@ static void ip_vs_genl_unregister(void)
 
 /* End of Generic Netlink interface definitions */
 
+/*
+ * per netns intit/exit func.
+ */
+int __net_init __ip_vs_control_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
+	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
+	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+						  vs_vars);
+	if (sysctl_header == NULL)
+		goto err_reg;
+	ip_vs_new_estimator(&ip_vs_stats);
+	return 0;
+
+err_reg:
+	return -ENOMEM;
+}
+
+static void __net_exit __ip_vs_control_cleanup(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	ip_vs_kill_estimator(&ip_vs_stats);
+	unregister_net_sysctl_table(sysctl_header);
+	proc_net_remove(net, "ip_vs_stats");
+	proc_net_remove(net, "ip_vs");
+}
+
+static struct pernet_operations ipvs_control_ops = {
+	.init = __ip_vs_control_init,
+	.exit = __ip_vs_control_cleanup,
+};
 
 int __init ip_vs_control_init(void)
 {
@@ -3437,12 +3473,9 @@ int __init ip_vs_control_init(void)
 		return ret;
 	}
 
-	proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops);
-	proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops);
-
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars);
-
-	ip_vs_new_estimator(&ip_vs_stats);
+	ret = register_pernet_subsys(&ipvs_control_ops);
+	if (ret)
+		return ret;
 
 	/* Hook the defense timer */
 	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
@@ -3459,9 +3492,7 @@ void ip_vs_control_cleanup(void)
 	cancel_delayed_work_sync(&defense_work);
 	cancel_work_sync(&defense_work.work);
 	ip_vs_kill_estimator(&ip_vs_stats);
-	unregister_sysctl_table(sysctl_header);
-	proc_net_remove(&init_net, "ip_vs_stats");
-	proc_net_remove(&init_net, "ip_vs");
+	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
 	LeaveFunction(2);
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index ff28801962e0..7417a0c1408b 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -157,13 +157,31 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 	est->outbps = 0;
 }
 
+static int __net_init __ip_vs_estimator_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	return 0;
+}
+
+static struct pernet_operations ip_vs_app_ops = {
+	.init = __ip_vs_estimator_init,
+};
+
 int __init ip_vs_estimator_init(void)
 {
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_app_ops);
+	if (rv < 0)
+		return rv;
 	mod_timer(&est_timer, jiffies + 2 * HZ);
-	return 0;
+	return rv;
 }
 
 void ip_vs_estimator_cleanup(void)
 {
 	del_timer_sync(&est_timer);
+	unregister_pernet_subsys(&ip_vs_app_ops);
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 84aef65b37d1..0e762f322aa3 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -399,15 +399,17 @@ static struct ip_vs_app ip_vs_ftp = {
 	.pkt_in =	ip_vs_ftp_in,
 };
 
-
 /*
- *	ip_vs_ftp initialization
+ *	per netns ip_vs_ftp initialization
  */
-static int __init ip_vs_ftp_init(void)
+static int __net_init __ip_vs_ftp_init(struct net *net)
 {
 	int i, ret;
 	struct ip_vs_app *app = &ip_vs_ftp;
 
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
 	ret = register_ip_vs_app(app);
 	if (ret)
 		return ret;
@@ -427,14 +429,38 @@ static int __init ip_vs_ftp_init(void)
 
 	return ret;
 }
+/*
+ *	netns exit
+ */
+static void __ip_vs_ftp_exit(struct net *net)
+{
+	struct ip_vs_app *app = &ip_vs_ftp;
+
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	unregister_ip_vs_app(app);
+}
+
+static struct pernet_operations ip_vs_ftp_ops = {
+	.init = __ip_vs_ftp_init,
+	.exit = __ip_vs_ftp_exit,
+};
 
+int __init ip_vs_ftp_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_ftp_ops);
+	return rv;
+}
 
 /*
  *	ip_vs_ftp finish.
  */
 static void __exit ip_vs_ftp_exit(void)
 {
-	unregister_ip_vs_app(&ip_vs_ftp);
+	unregister_pernet_subsys(&ip_vs_ftp_ops);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 9323f8944199..84278fb4e055 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -543,23 +543,54 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
 	.schedule =		ip_vs_lblc_schedule,
 };
 
+/*
+ *  per netns init.
+ */
+static int __net_init __ip_vs_lblc_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+						  vs_vars_table);
+	if (!sysctl_header)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __net_exit __ip_vs_lblc_exit(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	unregister_net_sysctl_table(sysctl_header);
+}
+
+static struct pernet_operations ip_vs_lblc_ops = {
+	.init = __ip_vs_lblc_init,
+	.exit = __ip_vs_lblc_exit,
+};
 
 static int __init ip_vs_lblc_init(void)
 {
 	int ret;
 
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
+	ret = register_pernet_subsys(&ip_vs_lblc_ops);
+	if (ret)
+		return ret;
+
 	ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler);
 	if (ret)
-		unregister_sysctl_table(sysctl_header);
+		unregister_pernet_subsys(&ip_vs_lblc_ops);
 	return ret;
 }
 
 
 static void __exit ip_vs_lblc_cleanup(void)
 {
-	unregister_sysctl_table(sysctl_header);
 	unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
+	unregister_pernet_subsys(&ip_vs_lblc_ops);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index dbeed8ea421a..7c7396a6acbf 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -744,23 +744,53 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
 	.schedule =		ip_vs_lblcr_schedule,
 };
 
+/*
+ *  per netns init.
+ */
+static int __net_init __ip_vs_lblcr_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+						  vs_vars_table);
+	if (!sysctl_header)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __net_exit __ip_vs_lblcr_exit(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	unregister_net_sysctl_table(sysctl_header);
+}
+
+static struct pernet_operations ip_vs_lblcr_ops = {
+	.init = __ip_vs_lblcr_init,
+	.exit = __ip_vs_lblcr_exit,
+};
 
 static int __init ip_vs_lblcr_init(void)
 {
 	int ret;
 
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
+	ret = register_pernet_subsys(&ip_vs_lblcr_ops);
+	if (ret)
+		return ret;
+
 	ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
 	if (ret)
-		unregister_sysctl_table(sysctl_header);
+		unregister_pernet_subsys(&ip_vs_lblcr_ops);
 	return ret;
 }
 
-
 static void __exit ip_vs_lblcr_cleanup(void)
 {
-	unregister_sysctl_table(sysctl_header);
 	unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
+	unregister_pernet_subsys(&ip_vs_lblcr_ops);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index c53998390877..45392942d0e7 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -236,6 +236,23 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
 		ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg);
 }
 
+/*
+ * per network name-space init
+ */
+static int __net_init __ip_vs_protocol_init(struct net *net)
+{
+	return 0;
+}
+
+static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
+{
+	/* empty */
+}
+
+static struct pernet_operations ipvs_proto_ops = {
+	.init = __ip_vs_protocol_init,
+	.exit = __ip_vs_protocol_cleanup,
+};
 
 int __init ip_vs_protocol_init(void)
 {
@@ -265,6 +282,7 @@ int __init ip_vs_protocol_init(void)
 	REGISTER_PROTOCOL(&ip_vs_protocol_esp);
 #endif
 	pr_info("Registered protocols (%s)\n", &protocols[2]);
+	return register_pernet_subsys(&ipvs_proto_ops);
 
 	return 0;
 }
@@ -275,6 +293,7 @@ void ip_vs_protocol_cleanup(void)
 	struct ip_vs_protocol *pp;
 	int i;
 
+	unregister_pernet_subsys(&ipvs_proto_ops);
 	/* unregister all the ipvs protocols */
 	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
 		while ((pp = ip_vs_proto_table[i]) != NULL)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c1c167ab73ee..3668739a6d06 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1639,3 +1639,30 @@ int stop_sync_thread(int state)
 
 	return 0;
 }
+
+/*
+ * Initialize data struct for each netns
+ */
+static int __net_init __ip_vs_sync_init(struct net *net)
+{
+	return 0;
+}
+
+static void __ip_vs_sync_cleanup(struct net *net)
+{
+}
+static struct pernet_operations ipvs_sync_ops = {
+	.init = __ip_vs_sync_init,
+	.exit = __ip_vs_sync_cleanup,
+};
+
+
+int __init ip_vs_sync_init(void)
+{
+	return register_pernet_subsys(&ipvs_sync_ops);
+}
+
+void __exit ip_vs_sync_cleanup(void)
+{
+	unregister_pernet_subsys(&ipvs_sync_ops);
+}
-- 
cgit v1.2.3


From fc723250c9cb046cc19833a2b1c4309bbf59ac36 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:43 +0100
Subject: IPVS: netns to services part 1

Services hash tables got netns ptr a hash arg,
While Real Servers (rs) has been moved to ipvs struct.
Two new inline functions added to get net ptr from skb.

Since ip_vs is called from different contexts there is two
places to dig for the net ptr skb->dev or skb->sk
this is handled in skb_net() and skb_sknet()

Global functions, ip_vs_service_get() ip_vs_lookup_real_service()
etc have got  struct net *net as first param.
If possible get net ptr skb etc,
 - if not &init_net is used at this early stage of patching.

ip_vs_ctl.c  procfs not ready for netns yet.

*v3
 Comments by Julian
- __ip_vs_service_find and __ip_vs_svc_fwm_find are fast path,
  net_eq(svc->net, net) so the check is at the end now.
- net = skb_net(skb) in ip_vs_out moved after check for skb_dst.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |  64 +++++++++-
 include/net/netns/ip_vs.h             |   8 ++
 net/netfilter/ipvs/ip_vs_conn.c       |   2 +-
 net/netfilter/ipvs/ip_vs_core.c       |   4 +-
 net/netfilter/ipvs/ip_vs_ctl.c        | 232 +++++++++++++++++++---------------
 net/netfilter/ipvs/ip_vs_proto_sctp.c |   5 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |   7 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c  |   5 +-
 net/netfilter/ipvs/ip_vs_sync.c       |   2 +-
 9 files changed, 214 insertions(+), 115 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index c1c2ece3ed94..d551e0d8fd9a 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -37,6 +37,59 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
 {
 	return net->ipvs;
 }
+/*
+ * Get net ptr from skb in traffic cases
+ * use skb_sknet when call is from userland (ioctl or netlink)
+ */
+static inline struct net *skb_net(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/*
+	 * This is used for debug only.
+	 * Start with the most likely hit
+	 * End with BUG
+	 */
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	if (skb_dst(skb)->dev)
+		return dev_net(skb_dst(skb)->dev);
+	WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
+		      __func__, __LINE__);
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return dev_net(skb->dev ? : skb_dst(skb)->dev);
+#endif
+#else
+	return &init_net;
+#endif
+}
+
+static inline struct net *skb_sknet(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/* Start with the most likely hit */
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n",
+		       __func__, __LINE__);
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return sock_net(skb->sk);
+#endif
+#else
+	return &init_net;
+#endif
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -496,6 +549,7 @@ struct ip_vs_service {
 	unsigned		flags;	  /* service status flags */
 	unsigned		timeout;  /* persistent timeout in ticks */
 	__be32			netmask;  /* grouping granularity */
+	struct net		*net;
 
 	struct list_head	destinations;  /* real server d-linked list */
 	__u32			num_dests;     /* number of servers */
@@ -896,7 +950,7 @@ extern int sysctl_ip_vs_sync_ver;
 
 extern void ip_vs_sync_switch_mode(int mode);
 extern struct ip_vs_service *
-ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
 
 static inline void ip_vs_service_put(struct ip_vs_service *svc)
@@ -905,7 +959,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc)
 }
 
 extern struct ip_vs_dest *
-ip_vs_lookup_real_service(int af, __u16 protocol,
+ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 			  const union nf_inet_addr *daddr, __be16 dport);
 
 extern int ip_vs_use_count_inc(void);
@@ -913,9 +967,9 @@ extern void ip_vs_use_count_dec(void);
 extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
 extern struct ip_vs_dest *
-ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
-		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol,
-		__u32 fwmark);
+ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
+		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
+		__u16 protocol, __u32 fwmark);
 extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 12fe84087cec..5b87d22a39fb 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -20,6 +20,14 @@ struct ctl_table_header;
 
 struct netns_ipvs {
 	int			gen;		/* Generation */
+	/*
+	 *	Hash table: for real service lookups
+	 */
+	#define IP_VS_RTAB_BITS 4
+	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
+	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
+
+	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 7c1b502f8d8d..7a0e79e3ad0f 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -611,7 +611,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	if ((cp) && (!cp->dest)) {
-		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
+		dest = ip_vs_find_dest(&init_net, cp->af, &cp->daddr, cp->dport,
 				       &cp->vaddr, cp->vport,
 				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 206f40c548d7..d0616ea1eebf 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1031,6 +1031,7 @@ drop:
 static unsigned int
 ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_conn *cp;
@@ -1054,6 +1055,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (unlikely(!skb_dst(skb)))
 		return NF_ACCEPT;
 
+	net = skb_net(skb);
 	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
@@ -1119,7 +1121,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 					  sizeof(_ports), _ports);
 		if (pptr == NULL)
 			return NF_ACCEPT;	/* Not for me */
-		if (ip_vs_lookup_real_service(af, iph.protocol,
+		if (ip_vs_lookup_real_service(net, af, iph.protocol,
 					      &iph.saddr,
 					      pptr[0])) {
 			/*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ceeef4352d34..2d7c96bd2114 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -287,15 +287,6 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
 /* the service table hashed by fwmark */
 static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
 
-/*
- *	Hash table: for real service lookups
- */
-#define IP_VS_RTAB_BITS 4
-#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
-#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
-
-static struct list_head ip_vs_rtable[IP_VS_RTAB_SIZE];
-
 /*
  *	Trash for destinations
  */
@@ -311,9 +302,9 @@ static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0);
 /*
  *	Returns hash value for virtual service
  */
-static __inline__ unsigned
-ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr,
-		  __be16 port)
+static inline unsigned
+ip_vs_svc_hashkey(struct net *net, int af, unsigned proto,
+		  const union nf_inet_addr *addr, __be16 port)
 {
 	register unsigned porth = ntohs(port);
 	__be32 addr_fold = addr->ip;
@@ -323,6 +314,7 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr,
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
+	addr_fold ^= ((size_t)net>>8);
 
 	return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth)
 		& IP_VS_SVC_TAB_MASK;
@@ -331,13 +323,13 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr,
 /*
  *	Returns hash value of fwmark for virtual service lookup
  */
-static __inline__ unsigned ip_vs_svc_fwm_hashkey(__u32 fwmark)
+static inline unsigned ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark)
 {
-	return fwmark & IP_VS_SVC_TAB_MASK;
+	return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK;
 }
 
 /*
- *	Hashes a service in the ip_vs_svc_table by <proto,addr,port>
+ *	Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port>
  *	or in the ip_vs_svc_fwm_table by fwmark.
  *	Should be called with locked tables.
  */
@@ -353,16 +345,16 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc)
 
 	if (svc->fwmark == 0) {
 		/*
-		 *  Hash it by <protocol,addr,port> in ip_vs_svc_table
+		 *  Hash it by <netns,protocol,addr,port> in ip_vs_svc_table
 		 */
-		hash = ip_vs_svc_hashkey(svc->af, svc->protocol, &svc->addr,
-					 svc->port);
+		hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol,
+					 &svc->addr, svc->port);
 		list_add(&svc->s_list, &ip_vs_svc_table[hash]);
 	} else {
 		/*
-		 *  Hash it by fwmark in ip_vs_svc_fwm_table
+		 *  Hash it by fwmark in svc_fwm_table
 		 */
-		hash = ip_vs_svc_fwm_hashkey(svc->fwmark);
+		hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark);
 		list_add(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
 	}
 
@@ -374,7 +366,7 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc)
 
 
 /*
- *	Unhashes a service from ip_vs_svc_table/ip_vs_svc_fwm_table.
+ *	Unhashes a service from svc_table / svc_fwm_table.
  *	Should be called with locked tables.
  */
 static int ip_vs_svc_unhash(struct ip_vs_service *svc)
@@ -386,10 +378,10 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
 	}
 
 	if (svc->fwmark == 0) {
-		/* Remove it from the ip_vs_svc_table table */
+		/* Remove it from the svc_table table */
 		list_del(&svc->s_list);
 	} else {
-		/* Remove it from the ip_vs_svc_fwm_table table */
+		/* Remove it from the svc_fwm_table table */
 		list_del(&svc->f_list);
 	}
 
@@ -400,23 +392,24 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
 
 
 /*
- *	Get service by {proto,addr,port} in the service table.
+ *	Get service by {netns, proto,addr,port} in the service table.
  */
 static inline struct ip_vs_service *
-__ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr,
-		    __be16 vport)
+__ip_vs_service_find(struct net *net, int af, __u16 protocol,
+		     const union nf_inet_addr *vaddr, __be16 vport)
 {
 	unsigned hash;
 	struct ip_vs_service *svc;
 
 	/* Check for "full" addressed entries */
-	hash = ip_vs_svc_hashkey(af, protocol, vaddr, vport);
+	hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport);
 
 	list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){
 		if ((svc->af == af)
 		    && ip_vs_addr_equal(af, &svc->addr, vaddr)
 		    && (svc->port == vport)
-		    && (svc->protocol == protocol)) {
+		    && (svc->protocol == protocol)
+		    && net_eq(svc->net, net)) {
 			/* HIT */
 			return svc;
 		}
@@ -430,16 +423,17 @@ __ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr,
  *	Get service by {fwmark} in the service table.
  */
 static inline struct ip_vs_service *
-__ip_vs_svc_fwm_find(int af, __u32 fwmark)
+__ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark)
 {
 	unsigned hash;
 	struct ip_vs_service *svc;
 
 	/* Check for fwmark addressed entries */
-	hash = ip_vs_svc_fwm_hashkey(fwmark);
+	hash = ip_vs_svc_fwm_hashkey(net, fwmark);
 
 	list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) {
-		if (svc->fwmark == fwmark && svc->af == af) {
+		if (svc->fwmark == fwmark && svc->af == af
+		    && net_eq(svc->net, net)) {
 			/* HIT */
 			return svc;
 		}
@@ -449,7 +443,7 @@ __ip_vs_svc_fwm_find(int af, __u32 fwmark)
 }
 
 struct ip_vs_service *
-ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport)
 {
 	struct ip_vs_service *svc;
@@ -459,14 +453,15 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 	/*
 	 *	Check the table hashed by fwmark first
 	 */
-	if (fwmark && (svc = __ip_vs_svc_fwm_find(af, fwmark)))
+	svc = __ip_vs_svc_fwm_find(net, af, fwmark);
+	if (fwmark && svc)
 		goto out;
 
 	/*
 	 *	Check the table hashed by <protocol,addr,port>
 	 *	for "full" addressed entries
 	 */
-	svc = __ip_vs_service_find(af, protocol, vaddr, vport);
+	svc = __ip_vs_service_find(net, af, protocol, vaddr, vport);
 
 	if (svc == NULL
 	    && protocol == IPPROTO_TCP
@@ -476,7 +471,7 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 		 * Check if ftp service entry exists, the packet
 		 * might belong to FTP data connections.
 		 */
-		svc = __ip_vs_service_find(af, protocol, vaddr, FTPPORT);
+		svc = __ip_vs_service_find(net, af, protocol, vaddr, FTPPORT);
 	}
 
 	if (svc == NULL
@@ -484,7 +479,7 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 		/*
 		 * Check if the catch-all port (port zero) exists
 		 */
-		svc = __ip_vs_service_find(af, protocol, vaddr, 0);
+		svc = __ip_vs_service_find(net, af, protocol, vaddr, 0);
 	}
 
   out:
@@ -545,10 +540,10 @@ static inline unsigned ip_vs_rs_hashkey(int af,
 }
 
 /*
- *	Hashes ip_vs_dest in ip_vs_rtable by <proto,addr,port>.
+ *	Hashes ip_vs_dest in rs_table by <proto,addr,port>.
  *	should be called with locked tables.
  */
-static int ip_vs_rs_hash(struct ip_vs_dest *dest)
+static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
 {
 	unsigned hash;
 
@@ -562,19 +557,19 @@ static int ip_vs_rs_hash(struct ip_vs_dest *dest)
 	 */
 	hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port);
 
-	list_add(&dest->d_list, &ip_vs_rtable[hash]);
+	list_add(&dest->d_list, &ipvs->rs_table[hash]);
 
 	return 1;
 }
 
 /*
- *	UNhashes ip_vs_dest from ip_vs_rtable.
+ *	UNhashes ip_vs_dest from rs_table.
  *	should be called with locked tables.
  */
 static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
 {
 	/*
-	 * Remove it from the ip_vs_rtable table.
+	 * Remove it from the rs_table table.
 	 */
 	if (!list_empty(&dest->d_list)) {
 		list_del(&dest->d_list);
@@ -588,10 +583,11 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
  *	Lookup real service by <proto,addr,port> in the real service table.
  */
 struct ip_vs_dest *
-ip_vs_lookup_real_service(int af, __u16 protocol,
+ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 			  const union nf_inet_addr *daddr,
 			  __be16 dport)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	unsigned hash;
 	struct ip_vs_dest *dest;
 
@@ -602,7 +598,7 @@ ip_vs_lookup_real_service(int af, __u16 protocol,
 	hash = ip_vs_rs_hashkey(af, daddr, dport);
 
 	read_lock(&__ip_vs_rs_lock);
-	list_for_each_entry(dest, &ip_vs_rtable[hash], d_list) {
+	list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) {
 		if ((dest->af == af)
 		    && ip_vs_addr_equal(af, &dest->addr, daddr)
 		    && (dest->port == dport)
@@ -652,7 +648,8 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
  * ip_vs_lookup_real_service() looked promissing, but
  * seems not working as expected.
  */
-struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr,
+struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
+				   const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
 				   __be16 vport, __u16 protocol, __u32 fwmark)
@@ -660,7 +657,7 @@ struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr,
 	struct ip_vs_dest *dest;
 	struct ip_vs_service *svc;
 
-	svc = ip_vs_service_get(af, fwmark, protocol, vaddr, vport);
+	svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
 	dest = ip_vs_lookup_dest(svc, daddr, dport);
@@ -768,6 +765,7 @@ static void
 __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		    struct ip_vs_dest_user_kern *udest, int add)
 {
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 	int conn_flags;
 
 	/* set the weight and the flags */
@@ -780,11 +778,11 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		conn_flags |= IP_VS_CONN_F_NOOUTPUT;
 	} else {
 		/*
-		 *    Put the real service in ip_vs_rtable if not present.
+		 *    Put the real service in rs_table if not present.
 		 *    For now only for NAT!
 		 */
 		write_lock_bh(&__ip_vs_rs_lock);
-		ip_vs_rs_hash(dest);
+		ip_vs_rs_hash(ipvs, dest);
 		write_unlock_bh(&__ip_vs_rs_lock);
 	}
 	atomic_set(&dest->conn_flags, conn_flags);
@@ -1117,7 +1115,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
  *	Add a service into the service hash table
  */
 static int
-ip_vs_add_service(struct ip_vs_service_user_kern *u,
+ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		  struct ip_vs_service **svc_p)
 {
 	int ret = 0;
@@ -1172,6 +1170,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u,
 	svc->flags = u->flags;
 	svc->timeout = u->timeout * HZ;
 	svc->netmask = u->netmask;
+	svc->net = net;
 
 	INIT_LIST_HEAD(&svc->destinations);
 	rwlock_init(&svc->sched_lock);
@@ -1428,17 +1427,19 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
 /*
  *	Flush all the virtual services
  */
-static int ip_vs_flush(void)
+static int ip_vs_flush(struct net *net)
 {
 	int idx;
 	struct ip_vs_service *svc, *nxt;
 
 	/*
-	 * Flush the service table hashed by <protocol,addr,port>
+	 * Flush the service table hashed by <netns,protocol,addr,port>
 	 */
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
-		list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], s_list) {
-			ip_vs_unlink_service(svc);
+		list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx],
+					 s_list) {
+			if (net_eq(svc->net, net))
+				ip_vs_unlink_service(svc);
 		}
 	}
 
@@ -1448,7 +1449,8 @@ static int ip_vs_flush(void)
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry_safe(svc, nxt,
 					 &ip_vs_svc_fwm_table[idx], f_list) {
-			ip_vs_unlink_service(svc);
+			if (net_eq(svc->net, net))
+				ip_vs_unlink_service(svc);
 		}
 	}
 
@@ -1472,20 +1474,22 @@ static int ip_vs_zero_service(struct ip_vs_service *svc)
 	return 0;
 }
 
-static int ip_vs_zero_all(void)
+static int ip_vs_zero_all(struct net *net)
 {
 	int idx;
 	struct ip_vs_service *svc;
 
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
-			ip_vs_zero_service(svc);
+			if (net_eq(svc->net, net))
+				ip_vs_zero_service(svc);
 		}
 	}
 
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
-			ip_vs_zero_service(svc);
+			if (net_eq(svc->net, net))
+				ip_vs_zero_service(svc);
 		}
 	}
 
@@ -1763,6 +1767,7 @@ static struct ctl_table_header * sysctl_header;
 #ifdef CONFIG_PROC_FS
 
 struct ip_vs_iter {
+	struct seq_net_private p;  /* Do not move this, netns depends upon it*/
 	struct list_head *table;
 	int bucket;
 };
@@ -1789,6 +1794,7 @@ static inline const char *ip_vs_fwd_name(unsigned flags)
 /* Get the Nth entry in the two lists */
 static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
 {
+	struct net *net = seq_file_net(seq);
 	struct ip_vs_iter *iter = seq->private;
 	int idx;
 	struct ip_vs_service *svc;
@@ -1796,7 +1802,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
 	/* look in hash by protocol */
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
-			if (pos-- == 0){
+			if (net_eq(svc->net, net) && pos-- == 0) {
 				iter->table = ip_vs_svc_table;
 				iter->bucket = idx;
 				return svc;
@@ -1807,7 +1813,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
 	/* keep looking in fwmark */
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
-			if (pos-- == 0) {
+			if (net_eq(svc->net, net) && pos-- == 0) {
 				iter->table = ip_vs_svc_fwm_table;
 				iter->bucket = idx;
 				return svc;
@@ -1961,7 +1967,7 @@ static const struct seq_operations ip_vs_info_seq_ops = {
 
 static int ip_vs_info_open(struct inode *inode, struct file *file)
 {
-	return seq_open_private(file, &ip_vs_info_seq_ops,
+	return seq_open_net(inode, file, &ip_vs_info_seq_ops,
 			sizeof(struct ip_vs_iter));
 }
 
@@ -2011,7 +2017,7 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 
 static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, ip_vs_stats_show, NULL);
+	return single_open_net(inode, file, ip_vs_stats_show);
 }
 
 static const struct file_operations ip_vs_stats_fops = {
@@ -2113,6 +2119,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
 static int
 do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 {
+	struct net *net = sock_net(sk);
 	int ret;
 	unsigned char arg[MAX_ARG_LEN];
 	struct ip_vs_service_user *usvc_compat;
@@ -2147,7 +2154,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 
 	if (cmd == IP_VS_SO_SET_FLUSH) {
 		/* Flush the virtual service */
-		ret = ip_vs_flush();
+		ret = ip_vs_flush(net);
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
 		/* Set timeout values for (tcp tcpfin udp) */
@@ -2174,7 +2181,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	if (cmd == IP_VS_SO_SET_ZERO) {
 		/* if no service address is set, zero counters in all */
 		if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) {
-			ret = ip_vs_zero_all();
+			ret = ip_vs_zero_all(net);
 			goto out_unlock;
 		}
 	}
@@ -2191,10 +2198,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 
 	/* Lookup the exact service by <protocol, addr, port> or fwmark */
 	if (usvc.fwmark == 0)
-		svc = __ip_vs_service_find(usvc.af, usvc.protocol,
+		svc = __ip_vs_service_find(net, usvc.af, usvc.protocol,
 					   &usvc.addr, usvc.port);
 	else
-		svc = __ip_vs_svc_fwm_find(usvc.af, usvc.fwmark);
+		svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark);
 
 	if (cmd != IP_VS_SO_SET_ADD
 	    && (svc == NULL || svc->protocol != usvc.protocol)) {
@@ -2207,7 +2214,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		if (svc != NULL)
 			ret = -EEXIST;
 		else
-			ret = ip_vs_add_service(&usvc, &svc);
+			ret = ip_vs_add_service(net, &usvc, &svc);
 		break;
 	case IP_VS_SO_SET_EDIT:
 		ret = ip_vs_edit_service(svc, &usvc);
@@ -2267,7 +2274,8 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 }
 
 static inline int
-__ip_vs_get_service_entries(const struct ip_vs_get_services *get,
+__ip_vs_get_service_entries(struct net *net,
+			    const struct ip_vs_get_services *get,
 			    struct ip_vs_get_services __user *uptr)
 {
 	int idx, count=0;
@@ -2278,7 +2286,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
 			/* Only expose IPv4 entries to old interface */
-			if (svc->af != AF_INET)
+			if (svc->af != AF_INET || !net_eq(svc->net, net))
 				continue;
 
 			if (count >= get->num_services)
@@ -2297,7 +2305,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
 			/* Only expose IPv4 entries to old interface */
-			if (svc->af != AF_INET)
+			if (svc->af != AF_INET || !net_eq(svc->net, net))
 				continue;
 
 			if (count >= get->num_services)
@@ -2317,7 +2325,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
 }
 
 static inline int
-__ip_vs_get_dest_entries(const struct ip_vs_get_dests *get,
+__ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 			 struct ip_vs_get_dests __user *uptr)
 {
 	struct ip_vs_service *svc;
@@ -2325,9 +2333,9 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get,
 	int ret = 0;
 
 	if (get->fwmark)
-		svc = __ip_vs_svc_fwm_find(AF_INET, get->fwmark);
+		svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark);
 	else
-		svc = __ip_vs_service_find(AF_INET, get->protocol, &addr,
+		svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr,
 					   get->port);
 
 	if (svc) {
@@ -2401,7 +2409,9 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	unsigned char arg[128];
 	int ret = 0;
 	unsigned int copylen;
+	struct net *net = sock_net(sk);
 
+	BUG_ON(!net);
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
@@ -2463,7 +2473,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = __ip_vs_get_service_entries(get, user);
+		ret = __ip_vs_get_service_entries(net, get, user);
 	}
 	break;
 
@@ -2476,10 +2486,11 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		entry = (struct ip_vs_service_entry *)arg;
 		addr.ip = entry->addr;
 		if (entry->fwmark)
-			svc = __ip_vs_svc_fwm_find(AF_INET, entry->fwmark);
+			svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark);
 		else
-			svc = __ip_vs_service_find(AF_INET, entry->protocol,
-						   &addr, entry->port);
+			svc = __ip_vs_service_find(net, AF_INET,
+						   entry->protocol, &addr,
+						   entry->port);
 		if (svc) {
 			ip_vs_copy_service(entry, svc);
 			if (copy_to_user(user, entry, sizeof(*entry)) != 0)
@@ -2502,7 +2513,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = __ip_vs_get_dest_entries(get, user);
+		ret = __ip_vs_get_dest_entries(net, get, user);
 	}
 	break;
 
@@ -2722,11 +2733,12 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
 	int idx = 0, i;
 	int start = cb->args[0];
 	struct ip_vs_service *svc;
+	struct net *net = skb_sknet(skb);
 
 	mutex_lock(&__ip_vs_mutex);
 	for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
-			if (++idx <= start)
+			if (++idx <= start || !net_eq(svc->net, net))
 				continue;
 			if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
 				idx--;
@@ -2737,7 +2749,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
 
 	for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
-			if (++idx <= start)
+			if (++idx <= start || !net_eq(svc->net, net))
 				continue;
 			if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
 				idx--;
@@ -2753,7 +2765,8 @@ nla_put_failure:
 	return skb->len;
 }
 
-static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
+static int ip_vs_genl_parse_service(struct net *net,
+				    struct ip_vs_service_user_kern *usvc,
 				    struct nlattr *nla, int full_entry,
 				    struct ip_vs_service **ret_svc)
 {
@@ -2796,9 +2809,9 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
 	}
 
 	if (usvc->fwmark)
-		svc = __ip_vs_svc_fwm_find(usvc->af, usvc->fwmark);
+		svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark);
 	else
-		svc = __ip_vs_service_find(usvc->af, usvc->protocol,
+		svc = __ip_vs_service_find(net, usvc->af, usvc->protocol,
 					   &usvc->addr, usvc->port);
 	*ret_svc = svc;
 
@@ -2835,13 +2848,14 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
 	return 0;
 }
 
-static struct ip_vs_service *ip_vs_genl_find_service(struct nlattr *nla)
+static struct ip_vs_service *ip_vs_genl_find_service(struct net *net,
+						     struct nlattr *nla)
 {
 	struct ip_vs_service_user_kern usvc;
 	struct ip_vs_service *svc;
 	int ret;
 
-	ret = ip_vs_genl_parse_service(&usvc, nla, 0, &svc);
+	ret = ip_vs_genl_parse_service(net, &usvc, nla, 0, &svc);
 	return ret ? ERR_PTR(ret) : svc;
 }
 
@@ -2909,6 +2923,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 	struct ip_vs_service *svc;
 	struct ip_vs_dest *dest;
 	struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1];
+	struct net *net;
 
 	mutex_lock(&__ip_vs_mutex);
 
@@ -2917,7 +2932,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 			IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy))
 		goto out_err;
 
-	svc = ip_vs_genl_find_service(attrs[IPVS_CMD_ATTR_SERVICE]);
+	net = skb_sknet(skb);
+	svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]);
 	if (IS_ERR(svc) || svc == NULL)
 		goto out_err;
 
@@ -3102,13 +3118,15 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct ip_vs_dest_user_kern udest;
 	int ret = 0, cmd;
 	int need_full_svc = 0, need_full_dest = 0;
+	struct net *net;
 
+	net = skb_sknet(skb);
 	cmd = info->genlhdr->cmd;
 
 	mutex_lock(&__ip_vs_mutex);
 
 	if (cmd == IPVS_CMD_FLUSH) {
-		ret = ip_vs_flush();
+		ret = ip_vs_flush(net);
 		goto out;
 	} else if (cmd == IPVS_CMD_SET_CONFIG) {
 		ret = ip_vs_genl_set_config(info->attrs);
@@ -3133,7 +3151,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	} else if (cmd == IPVS_CMD_ZERO &&
 		   !info->attrs[IPVS_CMD_ATTR_SERVICE]) {
-		ret = ip_vs_zero_all();
+		ret = ip_vs_zero_all(net);
 		goto out;
 	}
 
@@ -3143,7 +3161,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE)
 		need_full_svc = 1;
 
-	ret = ip_vs_genl_parse_service(&usvc,
+	ret = ip_vs_genl_parse_service(net, &usvc,
 				       info->attrs[IPVS_CMD_ATTR_SERVICE],
 				       need_full_svc, &svc);
 	if (ret)
@@ -3173,7 +3191,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	switch (cmd) {
 	case IPVS_CMD_NEW_SERVICE:
 		if (svc == NULL)
-			ret = ip_vs_add_service(&usvc, &svc);
+			ret = ip_vs_add_service(net, &usvc, &svc);
 		else
 			ret = -EEXIST;
 		break;
@@ -3211,7 +3229,9 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *msg;
 	void *reply;
 	int ret, cmd, reply_cmd;
+	struct net *net;
 
+	net = skb_sknet(skb);
 	cmd = info->genlhdr->cmd;
 
 	if (cmd == IPVS_CMD_GET_SERVICE)
@@ -3240,7 +3260,8 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	{
 		struct ip_vs_service *svc;
 
-		svc = ip_vs_genl_find_service(info->attrs[IPVS_CMD_ATTR_SERVICE]);
+		svc = ip_vs_genl_find_service(net,
+					      info->attrs[IPVS_CMD_ATTR_SERVICE]);
 		if (IS_ERR(svc)) {
 			ret = PTR_ERR(svc);
 			goto out_err;
@@ -3411,9 +3432,15 @@ static void ip_vs_genl_unregister(void)
  */
 int __net_init __ip_vs_control_init(struct net *net)
 {
+	int idx;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
+	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
+		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
+
 	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
 	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
 	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
@@ -3445,43 +3472,48 @@ static struct pernet_operations ipvs_control_ops = {
 
 int __init ip_vs_control_init(void)
 {
-	int ret;
 	int idx;
+	int ret;
 
 	EnterFunction(2);
 
-	/* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */
+	/* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++)  {
 		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
 		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
 	}
-	for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++)  {
-		INIT_LIST_HEAD(&ip_vs_rtable[idx]);
+
+	ret = register_pernet_subsys(&ipvs_control_ops);
+	if (ret) {
+		pr_err("cannot register namespace.\n");
+		goto err;
 	}
-	smp_wmb();
+
+	smp_wmb();	/* Do we really need it now ? */
 
 	ret = nf_register_sockopt(&ip_vs_sockopts);
 	if (ret) {
 		pr_err("cannot register sockopt.\n");
-		return ret;
+		goto err_net;
 	}
 
 	ret = ip_vs_genl_register();
 	if (ret) {
 		pr_err("cannot register Generic Netlink interface.\n");
 		nf_unregister_sockopt(&ip_vs_sockopts);
-		return ret;
+		goto err_net;
 	}
 
-	ret = register_pernet_subsys(&ipvs_control_ops);
-	if (ret)
-		return ret;
-
 	/* Hook the defense timer */
 	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
 
 	LeaveFunction(2);
 	return 0;
+
+err_net:
+	unregister_pernet_subsys(&ipvs_control_ops);
+err:
+	return ret;
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index a315159983ad..521b827083fe 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -12,6 +12,7 @@ static int
 sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		   int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
@@ -27,9 +28,9 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 				 sizeof(_schunkh), &_schunkh);
 	if (sch == NULL)
 		return 0;
-
+	net = skb_net(skb);
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				     &iph.daddr, sh->dest))) {
 		int ignored;
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 1cdab12abfef..c175d3166263 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -31,6 +31,7 @@ static int
 tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	struct tcphdr _tcph, *th;
 	struct ip_vs_iphdr iph;
@@ -42,11 +43,11 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		*verdict = NF_DROP;
 		return 0;
 	}
-
+	net = skb_net(skb);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
 	if (th->syn &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr,
-				     th->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
+				     &iph.daddr, th->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop()) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index cd398de010cc..5ab54f648654 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -31,6 +31,7 @@ static int
 udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	struct udphdr _udph, *uh;
 	struct ip_vs_iphdr iph;
@@ -42,8 +43,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		*verdict = NF_DROP;
 		return 0;
 	}
-
-	svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	net = skb_net(skb);
+	svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				&iph.daddr, uh->dest);
 	if (svc) {
 		int ignored;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3668739a6d06..662aa2c22a05 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -749,7 +749,7 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
 		 * If it is not found the connection will remain unbound
 		 * but still handled.
 		 */
-		dest = ip_vs_find_dest(type, daddr, dport, param->vaddr,
+		dest = ip_vs_find_dest(&init_net, type, daddr, dport, param->vaddr,
 				       param->vport, protocol, fwmark);
 
 		/*  Set the approprite ativity flag */
-- 
cgit v1.2.3


From d0a1eef9c38218af20c809b2220a960b7ed81a36 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:44 +0100
Subject: IPVS: netns awarness to lblcr sheduler

var sysctl_ip_vs_lblcr_expiration moved to ipvs struct as
    sysctl_lblcr_expiration

procfs updated to handle this.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h        |  5 ++++
 net/netfilter/ipvs/ip_vs_lblcr.c | 54 ++++++++++++++++++++++++++--------------
 2 files changed, 41 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 5b87d22a39fb..51a92ee1b167 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -28,6 +28,11 @@ struct netns_ipvs {
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+
+	/* ip_vs_lblcr */
+	int			sysctl_lblcr_expiration;
+	struct ctl_table_header	*lblcr_ctl_header;
+	struct ctl_table	*lblcr_ctl_table;
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 7c7396a6acbf..61ae8cfcf0b4 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -70,8 +70,6 @@
  *    entries that haven't been touched for a day.
  */
 #define COUNT_FOR_FULL_EXPIRATION   30
-static int sysctl_ip_vs_lblcr_expiration = 24*60*60*HZ;
-
 
 /*
  *     for IPVS lblcr entry hash table
@@ -296,7 +294,7 @@ struct ip_vs_lblcr_table {
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblcr_expiration",
-		.data		= &sysctl_ip_vs_lblcr_expiration,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -304,8 +302,6 @@ static ctl_table vs_vars_table[] = {
 	{ }
 };
 
-static struct ctl_table_header * sysctl_header;
-
 static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
 {
 	list_del(&en->list);
@@ -425,14 +421,15 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
 	unsigned long now = jiffies;
 	int i, j;
 	struct ip_vs_lblcr_entry *en, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
 
 		write_lock(&svc->sched_lock);
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
-			if (time_after(en->lastuse+sysctl_ip_vs_lblcr_expiration,
-				       now))
+			if (time_after(en->lastuse
+					+ ipvs->sysctl_lblcr_expiration, now))
 				continue;
 
 			ip_vs_lblcr_free(en);
@@ -664,6 +661,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	read_lock(&svc->sched_lock);
 	en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr);
 	if (en) {
+		struct netns_ipvs *ipvs = net_ipvs(svc->net);
 		/* We only hold a read lock, but this is atomic */
 		en->lastuse = jiffies;
 
@@ -675,7 +673,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		/* More than one destination + enough time passed by, cleanup */
 		if (atomic_read(&en->set.size) > 1 &&
 				time_after(jiffies, en->set.lastmod +
-				sysctl_ip_vs_lblcr_expiration)) {
+				ipvs->sysctl_lblcr_expiration)) {
 			struct ip_vs_dest *m;
 
 			write_lock(&en->set.lock);
@@ -749,23 +747,43 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
  */
 static int __net_init __ip_vs_lblcr_init(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
-	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
-						  vs_vars_table);
-	if (!sysctl_header)
-		return -ENOMEM;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net)) {
+		ipvs->lblcr_ctl_table = kmemdup(vs_vars_table,
+						sizeof(vs_vars_table),
+						GFP_KERNEL);
+		if (ipvs->lblcr_ctl_table == NULL)
+			goto err_dup;
+	} else
+		ipvs->lblcr_ctl_table = vs_vars_table;
+	ipvs->sysctl_lblcr_expiration = 24*60*60*HZ;
+	ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
+
+	ipvs->lblcr_ctl_header =
+		register_net_sysctl_table(net, net_vs_ctl_path,
+					  ipvs->lblcr_ctl_table);
+	if (!ipvs->lblcr_ctl_header)
+		goto err_reg;
 
 	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblcr_ctl_table);
+
+err_dup:
+	return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_lblcr_exit(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	unregister_net_sysctl_table(ipvs->lblcr_ctl_header);
 
-	unregister_net_sysctl_table(sysctl_header);
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblcr_ctl_table);
 }
 
 static struct pernet_operations ip_vs_lblcr_ops = {
-- 
cgit v1.2.3


From b6e885ddb903e681b7cbb4e68ad775154660e1f4 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:45 +0100
Subject: IPVS: netns awarness to lblc sheduler

var sysctl_ip_vs_lblc_expiration moved to ipvs struct as
    sysctl_lblc_expiration

procfs updated to handle this.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h       |  4 ++++
 net/netfilter/ipvs/ip_vs_lblc.c | 50 ++++++++++++++++++++++++++++-------------
 2 files changed, 38 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 51a92ee1b167..d14581cc4fe0 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -29,6 +29,10 @@ struct netns_ipvs {
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 
+	/* ip_vs_lblc */
+	int			sysctl_lblc_expiration;
+	struct ctl_table_header	*lblc_ctl_header;
+	struct ctl_table	*lblc_ctl_table;
 	/* ip_vs_lblcr */
 	int			sysctl_lblcr_expiration;
 	struct ctl_table_header	*lblcr_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 84278fb4e055..d5bec3371871 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -70,7 +70,6 @@
  *    entries that haven't been touched for a day.
  */
 #define COUNT_FOR_FULL_EXPIRATION   30
-static int sysctl_ip_vs_lblc_expiration = 24*60*60*HZ;
 
 
 /*
@@ -117,7 +116,7 @@ struct ip_vs_lblc_table {
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblc_expiration",
-		.data		= &sysctl_ip_vs_lblc_expiration,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -125,8 +124,6 @@ static ctl_table vs_vars_table[] = {
 	{ }
 };
 
-static struct ctl_table_header * sysctl_header;
-
 static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
 {
 	list_del(&en->list);
@@ -248,6 +245,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 	struct ip_vs_lblc_entry *en, *nxt;
 	unsigned long now = jiffies;
 	int i, j;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLC_TAB_MASK;
@@ -255,7 +253,8 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 		write_lock(&svc->sched_lock);
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
 			if (time_before(now,
-					en->lastuse + sysctl_ip_vs_lblc_expiration))
+					en->lastuse +
+					ipvs->sysctl_lblc_expiration))
 				continue;
 
 			ip_vs_lblc_free(en);
@@ -548,23 +547,43 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
  */
 static int __net_init __ip_vs_lblc_init(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
-	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
-						  vs_vars_table);
-	if (!sysctl_header)
-		return -ENOMEM;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net)) {
+		ipvs->lblc_ctl_table = kmemdup(vs_vars_table,
+						sizeof(vs_vars_table),
+						GFP_KERNEL);
+		if (ipvs->lblc_ctl_table == NULL)
+			goto err_dup;
+	} else
+		ipvs->lblc_ctl_table = vs_vars_table;
+	ipvs->sysctl_lblc_expiration = 24*60*60*HZ;
+	ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
+
+	ipvs->lblc_ctl_header =
+		register_net_sysctl_table(net, net_vs_ctl_path,
+					  ipvs->lblc_ctl_table);
+	if (!ipvs->lblc_ctl_header)
+		goto err_reg;
 
 	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblc_ctl_table);
+
+err_dup:
+	return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_lblc_exit(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	unregister_net_sysctl_table(ipvs->lblc_ctl_header);
 
-	unregister_net_sysctl_table(sysctl_header);
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblc_ctl_table);
 }
 
 static struct pernet_operations ip_vs_lblc_ops = {
@@ -586,7 +605,6 @@ static int __init ip_vs_lblc_init(void)
 	return ret;
 }
 
-
 static void __exit ip_vs_lblc_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
-- 
cgit v1.2.3


From 252c64103237f1841088f0f29b4f084b1c774546 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:46 +0100
Subject: IPVS: netns, prepare protocol

Add support for protocol data per name-space.
in struct ip_vs_protocol, appcnt will be removed when all protos
are modified for network name-space.

This patch causes warnings of unused functions, they will be used
when next patch will be applied.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              | 20 +++++++++++-
 include/net/netns/ip_vs.h        |  3 ++
 net/netfilter/ipvs/ip_vs_proto.c | 66 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 88 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d551e0d8fd9a..88d4e40b538a 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -352,6 +352,7 @@ struct iphdr;
 struct ip_vs_conn;
 struct ip_vs_app;
 struct sk_buff;
+struct ip_vs_proto_data;
 
 struct ip_vs_protocol {
 	struct ip_vs_protocol	*next;
@@ -366,6 +367,10 @@ struct ip_vs_protocol {
 
 	void (*exit)(struct ip_vs_protocol *pp);
 
+	void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd);
+
+	void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);
+
 	int (*conn_schedule)(int af, struct sk_buff *skb,
 			     struct ip_vs_protocol *pp,
 			     int *verdict, struct ip_vs_conn **cpp);
@@ -417,7 +422,20 @@ struct ip_vs_protocol {
 	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
 };
 
-extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto);
+/*
+ * protocol data per netns
+ */
+struct ip_vs_proto_data {
+	struct ip_vs_proto_data	*next;
+	struct ip_vs_protocol	*pp;
+	int			*timeout_table;	/* protocol timeout table */
+	atomic_t		appcnt;		/* counter of proto app incs. */
+	struct tcp_states_t	*tcp_state_table;
+};
+
+extern struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
+extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
+						     unsigned short proto);
 
 struct ip_vs_conn_param {
 	const union nf_inet_addr	*caddr;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index d14581cc4fe0..6f4e089b8db2 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -28,6 +28,9 @@ struct netns_ipvs {
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+	/* ip_vs_proto */
+	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
+	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 45392942d0e7..576e29648c53 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -60,6 +60,31 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return 0;
 }
 
+/*
+ *	register an ipvs protocols netns related data
+ */
+static int
+register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	unsigned hash = IP_VS_PROTO_HASH(pp->protocol);
+	struct ip_vs_proto_data *pd =
+			kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC);
+
+	if (!pd) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	pd->pp = pp;	/* For speed issues */
+	pd->next = ipvs->proto_data_table[hash];
+	ipvs->proto_data_table[hash] = pd;
+	atomic_set(&pd->appcnt, 0);	/* Init app counter */
+
+	if (pp->init_netns != NULL)
+		pp->init_netns(net, pd);
+
+	return 0;
+}
 
 /*
  *	unregister an ipvs protocol
@@ -82,6 +107,29 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return -ESRCH;
 }
 
+/*
+ *	unregister an ipvs protocols netns data
+ */
+static int
+unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data **pd_p;
+	unsigned hash = IP_VS_PROTO_HASH(pd->pp->protocol);
+
+	pd_p = &ipvs->proto_data_table[hash];
+	for (; *pd_p; pd_p = &(*pd_p)->next) {
+		if (*pd_p == pd) {
+			*pd_p = pd->next;
+			if (pd->pp->exit_netns != NULL)
+				pd->pp->exit_netns(net, pd);
+			kfree(pd);
+			return 0;
+		}
+	}
+
+	return -ESRCH;
+}
 
 /*
  *	get ip_vs_protocol object by its proto.
@@ -100,6 +148,24 @@ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto)
 }
 EXPORT_SYMBOL(ip_vs_proto_get);
 
+/*
+ *	get ip_vs_protocol object data by netns and proto
+ */
+struct ip_vs_proto_data *
+ip_vs_proto_data_get(struct net *net, unsigned short proto)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd;
+	unsigned hash = IP_VS_PROTO_HASH(proto);
+
+	for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) {
+		if (pd->pp->protocol == proto)
+			return pd;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(ip_vs_proto_data_get);
 
 /*
  *	Propagate event for state change to all protocols
-- 
cgit v1.2.3


From 4a85b96c08ef84076f84e87280223a4301988ed9 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:47 +0100
Subject: IPVS: netns preparation for proto_tcp

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that is common for all protos and use all
ip_vs_proto_data

*v3
Removed unused function as sugested by Simon

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                  |  2 +-
 include/net/netns/ip_vs.h            |  8 +++
 net/netfilter/ipvs/ip_vs_ftp.c       |  8 ++-
 net/netfilter/ipvs/ip_vs_proto.c     | 13 ++++-
 net/netfilter/ipvs/ip_vs_proto_tcp.c | 97 +++++++++++++++++++-----------------
 5 files changed, 79 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 88d4e40b538a..3c45a00cdc3e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -807,7 +807,7 @@ extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
 extern const char * ip_vs_state_name(__u16 proto, int state);
 
-extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
+extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_check_template(struct ip_vs_conn *ct);
 extern void ip_vs_random_dropentry(void);
 extern int ip_vs_conn_init(void);
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 6f4e089b8db2..ac77363647ab 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -31,6 +31,14 @@ struct netns_ipvs {
 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
 	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
+	/* ip_vs_proto_tcp */
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	#define	TCP_APP_TAB_BITS	4
+	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
+	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
+	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
+	spinlock_t		tcp_app_lock;
+#endif
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 0e762f322aa3..b38ae941f677 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -157,6 +157,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	int ret = 0;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
+	struct net *net;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -257,8 +258,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		 * would be adjusted twice.
 		 */
 
+		net = skb_net(skb);
 		cp->app_data = NULL;
-		ip_vs_tcp_conn_listen(n_cp);
+		ip_vs_tcp_conn_listen(net, n_cp);
 		ip_vs_conn_put(n_cp);
 		return ret;
 	}
@@ -287,6 +289,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	union nf_inet_addr to;
 	__be16 port;
 	struct ip_vs_conn *n_cp;
+	struct net *net;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -378,7 +381,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	/*
 	 *	Move tunnel to listen state
 	 */
-	ip_vs_tcp_conn_listen(n_cp);
+	net = skb_net(skb);
+	ip_vs_tcp_conn_listen(net, n_cp);
 	ip_vs_conn_put(n_cp);
 
 	return 1;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 576e29648c53..320c6a65f370 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -307,12 +307,23 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
  */
 static int __net_init __ip_vs_protocol_init(struct net *net)
 {
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
+#endif
 	return 0;
 }
 
 static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
 {
-	/* empty */
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd;
+	int i;
+
+	/* unregister all the ipvs proto data for this netns */
+	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
+		while ((pd = ipvs->proto_data_table[i]) != NULL)
+			unregister_ip_vs_proto_netns(net, pd);
+	}
 }
 
 static struct pernet_operations ipvs_proto_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index c175d3166263..9d9df3d61093 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -9,8 +9,12 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
  *
+ *              Network name space (netns) aware.
+ *              Global data moved to netns i.e struct netns_ipvs
+ *              tcp_timeouts table has copy per netns in a hash table per
+ *              protocol ip_vs_proto_data and is handled by netns
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -345,7 +349,7 @@ static const int tcp_state_off[IP_VS_DIR_LAST] = {
 /*
  *	Timeout table[state]
  */
-static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = {
+static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = {
 	[IP_VS_TCP_S_NONE]		=	2*HZ,
 	[IP_VS_TCP_S_ESTABLISHED]	=	15*60*HZ,
 	[IP_VS_TCP_S_SYN_SENT]		=	2*60*HZ,
@@ -460,13 +464,6 @@ static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
 	tcp_state_table = (on? tcp_states_dos : tcp_states);
 }
 
-static int
-tcp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-	return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_TCP_S_LAST,
-				       tcp_state_name_table, sname, to);
-}
-
 static inline int tcp_state_idx(struct tcphdr *th)
 {
 	if (th->rst)
@@ -487,6 +484,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 	int state_idx;
 	int new_state = IP_VS_TCP_S_CLOSE;
 	int state_off = tcp_state_off[direction];
+	struct ip_vs_proto_data *pd;  /* Temp fix */
 
 	/*
 	 *    Update state offset to INPUT_ONLY if necessary
@@ -542,10 +540,13 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		}
 	}
 
-	cp->timeout = pp->timeout_table[cp->state = new_state];
+	pd = ip_vs_proto_data_get(&init_net, pp->protocol);
+	if (likely(pd))
+		cp->timeout = pd->timeout_table[cp->state = new_state];
+	else	/* What to do ? */
+		cp->timeout = tcp_timeouts[cp->state = new_state];
 }
 
-
 /*
  *	Handle state transitions
  */
@@ -573,17 +574,6 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction,
 	return 1;
 }
 
-
-/*
- *	Hash table for TCP application incarnations
- */
-#define	TCP_APP_TAB_BITS	4
-#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
-#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
-
-static struct list_head tcp_apps[TCP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(tcp_app_lock);
-
 static inline __u16 tcp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port)
@@ -597,21 +587,23 @@ static int tcp_register_app(struct ip_vs_app *inc)
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
 
 	hash = tcp_app_hashkey(port);
 
-	spin_lock_bh(&tcp_app_lock);
-	list_for_each_entry(i, &tcp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->tcp_app_lock);
+	list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &tcp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_tcp.appcnt);
+	list_add(&inc->p_list, &ipvs->tcp_apps[hash]);
+	atomic_inc(&pd->pp->appcnt);
 
   out:
-	spin_unlock_bh(&tcp_app_lock);
+	spin_unlock_bh(&ipvs->tcp_app_lock);
 	return ret;
 }
 
@@ -619,16 +611,20 @@ static int tcp_register_app(struct ip_vs_app *inc)
 static void
 tcp_unregister_app(struct ip_vs_app *inc)
 {
-	spin_lock_bh(&tcp_app_lock);
-	atomic_dec(&ip_vs_protocol_tcp.appcnt);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
+
+	spin_lock_bh(&ipvs->tcp_app_lock);
+	atomic_dec(&pd->pp->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&tcp_app_lock);
+	spin_unlock_bh(&ipvs->tcp_app_lock);
 }
 
 
 static int
 tcp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -640,12 +636,12 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = tcp_app_hashkey(cp->vport);
 
-	spin_lock(&tcp_app_lock);
-	list_for_each_entry(inc, &tcp_apps[hash], p_list) {
+	spin_lock(&ipvs->tcp_app_lock);
+	list_for_each_entry(inc, &ipvs->tcp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&tcp_app_lock);
+			spin_unlock(&ipvs->tcp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->"
 				      "%s:%u to app %s on port %u\n",
@@ -662,7 +658,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&tcp_app_lock);
+	spin_unlock(&ipvs->tcp_app_lock);
 
   out:
 	return result;
@@ -672,24 +668,34 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
 /*
  *	Set LISTEN timeout. (ip_vs_conn_put will setup timer)
  */
-void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp)
+void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp)
 {
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+
 	spin_lock(&cp->lock);
 	cp->state = IP_VS_TCP_S_LISTEN;
-	cp->timeout = ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_LISTEN];
+	cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN]
+			   : tcp_timeouts[IP_VS_TCP_S_LISTEN]);
 	spin_unlock(&cp->lock);
 }
 
-
-static void ip_vs_tcp_init(struct ip_vs_protocol *pp)
+/* ---------------------------------------------
+ *   timeouts is netns related now.
+ * ---------------------------------------------
+ */
+static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(tcp_apps);
-	pp->timeout_table = tcp_timeouts;
-}
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->tcp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
+							sizeof(tcp_timeouts));
+}
 
-static void ip_vs_tcp_exit(struct ip_vs_protocol *pp)
+static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
+	kfree(pd->timeout_table);
 }
 
 
@@ -699,8 +705,10 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
 	.num_states =		IP_VS_TCP_S_LAST,
 	.dont_defrag =		0,
 	.appcnt =		ATOMIC_INIT(0),
-	.init =			ip_vs_tcp_init,
-	.exit =			ip_vs_tcp_exit,
+	.init =			NULL,
+	.exit =			NULL,
+	.init_netns =		__ip_vs_tcp_init,
+	.exit_netns =		__ip_vs_tcp_exit,
 	.register_app =		tcp_register_app,
 	.unregister_app =	tcp_unregister_app,
 	.conn_schedule =	tcp_conn_schedule,
@@ -714,5 +722,4 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
 	.app_conn_bind =	tcp_app_conn_bind,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	tcp_timeout_change,
-	.set_state_timeout =	tcp_set_state_timeout,
 };
-- 
cgit v1.2.3


From 78b16bde104cc74bedbf462b0ebed2990f35ff6b Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:48 +0100
Subject: IPVS: netns preparation for proto_udp

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that is common for all protos and use ip_vs_proto_data

*v3
Removed unused function set_state_timeout()

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h            |  8 ++++
 net/netfilter/ipvs/ip_vs_proto.c     |  3 ++
 net/netfilter/ipvs/ip_vs_proto_udp.c | 86 ++++++++++++++++++------------------
 3 files changed, 54 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index ac77363647ab..62b1448d3795 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -39,6 +39,14 @@ struct netns_ipvs {
 	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
 	spinlock_t		tcp_app_lock;
 #endif
+	/* ip_vs_proto_udp */
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	#define	UDP_APP_TAB_BITS	4
+	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
+	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
+	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
+	spinlock_t		udp_app_lock;
+#endif
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 320c6a65f370..cdc414238fcb 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -309,6 +309,9 @@ static int __net_init __ip_vs_protocol_init(struct net *net)
 {
 #ifdef CONFIG_IP_VS_PROTO_TCP
 	register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_udp);
 #endif
 	return 0;
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 5ab54f648654..71a4721a8f8a 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -9,7 +9,8 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
+ *              Network name space (netns) aware.
  *
  */
 
@@ -345,19 +346,6 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
 	return 1;
 }
 
-
-/*
- *	Note: the caller guarantees that only one of register_app,
- *	unregister_app or app_conn_bind is called each time.
- */
-
-#define	UDP_APP_TAB_BITS	4
-#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
-#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
-
-static struct list_head udp_apps[UDP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(udp_app_lock);
-
 static inline __u16 udp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> UDP_APP_TAB_BITS) ^ (__force u16)port)
@@ -371,22 +359,24 @@ static int udp_register_app(struct ip_vs_app *inc)
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
 
 	hash = udp_app_hashkey(port);
 
 
-	spin_lock_bh(&udp_app_lock);
-	list_for_each_entry(i, &udp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->udp_app_lock);
+	list_for_each_entry(i, &ipvs->udp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &udp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_udp.appcnt);
+	list_add(&inc->p_list, &ipvs->udp_apps[hash]);
+	atomic_inc(&pd->pp->appcnt);
 
   out:
-	spin_unlock_bh(&udp_app_lock);
+	spin_unlock_bh(&ipvs->udp_app_lock);
 	return ret;
 }
 
@@ -394,15 +384,19 @@ static int udp_register_app(struct ip_vs_app *inc)
 static void
 udp_unregister_app(struct ip_vs_app *inc)
 {
-	spin_lock_bh(&udp_app_lock);
-	atomic_dec(&ip_vs_protocol_udp.appcnt);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+
+	spin_lock_bh(&ipvs->udp_app_lock);
+	atomic_dec(&pd->pp->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&udp_app_lock);
+	spin_unlock_bh(&ipvs->udp_app_lock);
 }
 
 
 static int udp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -414,12 +408,12 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = udp_app_hashkey(cp->vport);
 
-	spin_lock(&udp_app_lock);
-	list_for_each_entry(inc, &udp_apps[hash], p_list) {
+	spin_lock(&ipvs->udp_app_lock);
+	list_for_each_entry(inc, &ipvs->udp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&udp_app_lock);
+			spin_unlock(&ipvs->udp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->"
 				      "%s:%u to app %s on port %u\n",
@@ -436,14 +430,14 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&udp_app_lock);
+	spin_unlock(&ipvs->udp_app_lock);
 
   out:
 	return result;
 }
 
 
-static int udp_timeouts[IP_VS_UDP_S_LAST+1] = {
+static const int udp_timeouts[IP_VS_UDP_S_LAST+1] = {
 	[IP_VS_UDP_S_NORMAL]		=	5*60*HZ,
 	[IP_VS_UDP_S_LAST]		=	2*HZ,
 };
@@ -453,14 +447,6 @@ static const char *const udp_state_name_table[IP_VS_UDP_S_LAST+1] = {
 	[IP_VS_UDP_S_LAST]		=	"BUG!",
 };
 
-
-static int
-udp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-	return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_UDP_S_LAST,
-				       udp_state_name_table, sname, to);
-}
-
 static const char * udp_state_name(int state)
 {
 	if (state >= IP_VS_UDP_S_LAST)
@@ -473,18 +459,31 @@ udp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
 		     struct ip_vs_protocol *pp)
 {
-	cp->timeout = pp->timeout_table[IP_VS_UDP_S_NORMAL];
+	struct ip_vs_proto_data *pd;   /* Temp fix, pp will be replaced by pd */
+
+	pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
+	if (unlikely(!pd)) {
+		pr_err("UDP no ns data\n");
+		return 0;
+	}
+
+	cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL];
 	return 1;
 }
 
-static void udp_init(struct ip_vs_protocol *pp)
+static void __udp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(udp_apps);
-	pp->timeout_table = udp_timeouts;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->udp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts,
+							sizeof(udp_timeouts));
 }
 
-static void udp_exit(struct ip_vs_protocol *pp)
+static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
+	kfree(pd->timeout_table);
 }
 
 
@@ -493,8 +492,10 @@ struct ip_vs_protocol ip_vs_protocol_udp = {
 	.protocol =		IPPROTO_UDP,
 	.num_states =		IP_VS_UDP_S_LAST,
 	.dont_defrag =		0,
-	.init =			udp_init,
-	.exit =			udp_exit,
+	.init =			NULL,
+	.exit =			NULL,
+	.init_netns =		__udp_init,
+	.exit_netns =		__udp_exit,
 	.conn_schedule =	udp_conn_schedule,
 	.conn_in_get =		ip_vs_conn_in_get_proto,
 	.conn_out_get =		ip_vs_conn_out_get_proto,
@@ -508,5 +509,4 @@ struct ip_vs_protocol ip_vs_protocol_udp = {
 	.app_conn_bind =	udp_app_conn_bind,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	NULL,
-	.set_state_timeout =	udp_set_state_timeout,
 };
-- 
cgit v1.2.3


From 9d934878e7870fbbbd8eaed2e467552536877def Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:49 +0100
Subject: IPVS: netns preparation for proto_sctp

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that is common for all protos and use ip_vs_proto_data

*v3
 Removed unuset function set_state_timeout()

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h             |   9 +++
 net/netfilter/ipvs/ip_vs_proto.c      |   3 +
 net/netfilter/ipvs/ip_vs_proto_sctp.c | 121 ++++++++++++++++------------------
 3 files changed, 70 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 62b1448d3795..58bd3fd85a97 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -47,6 +47,15 @@ struct netns_ipvs {
 	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
 	spinlock_t		udp_app_lock;
 #endif
+	/* ip_vs_proto_sctp */
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	#define SCTP_APP_TAB_BITS	4
+	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
+	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
+	/* Hash table for SCTP application incarnations	 */
+	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
+	spinlock_t		sctp_app_lock;
+#endif
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index cdc414238fcb..001b2f825043 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -312,6 +312,9 @@ static int __net_init __ip_vs_protocol_init(struct net *net)
 #endif
 #ifdef CONFIG_IP_VS_PROTO_UDP
 	register_ip_vs_proto_netns(net, &ip_vs_protocol_udp);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp);
 #endif
 	return 0;
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 521b827083fe..f826dd1e4630 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -862,7 +862,7 @@ static struct ipvs_sctp_nextstate
 /*
  *      Timeout table[state]
  */
-static int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
+static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
 	[IP_VS_SCTP_S_NONE]         =     2 * HZ,
 	[IP_VS_SCTP_S_INIT_CLI]     =     1 * 60 * HZ,
 	[IP_VS_SCTP_S_INIT_SER]     =     1 * 60 * HZ,
@@ -906,18 +906,6 @@ static const char *sctp_state_name(int state)
 	return "?";
 }
 
-static void sctp_timeout_change(struct ip_vs_protocol *pp, int flags)
-{
-}
-
-static int
-sctp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-
-return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_SCTP_S_LAST,
-				sctp_state_name_table, sname, to);
-}
-
 static inline int
 set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		int direction, const struct sk_buff *skb)
@@ -926,6 +914,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 	unsigned char chunk_type;
 	int event, next_state;
 	int ihl;
+	struct ip_vs_proto_data *pd;
 
 #ifdef CONFIG_IP_VS_IPV6
 	ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
@@ -1001,10 +990,13 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 			}
 		}
 	}
+	pd = ip_vs_proto_data_get(&init_net, pp->protocol); /* tmp fix */
+	if (likely(pd))
+		cp->timeout = pd->timeout_table[cp->state = next_state];
+	else	/* What to do ? */
+		cp->timeout = sctp_timeouts[cp->state = next_state];
 
-	 cp->timeout = pp->timeout_table[cp->state = next_state];
-
-	 return 1;
+	return 1;
 }
 
 static int
@@ -1020,16 +1012,6 @@ sctp_state_transition(struct ip_vs_conn *cp, int direction,
 	return ret;
 }
 
-/*
- *      Hash table for SCTP application incarnations
- */
-#define SCTP_APP_TAB_BITS        4
-#define SCTP_APP_TAB_SIZE        (1 << SCTP_APP_TAB_BITS)
-#define SCTP_APP_TAB_MASK        (SCTP_APP_TAB_SIZE - 1)
-
-static struct list_head sctp_apps[SCTP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(sctp_app_lock);
-
 static inline __u16 sctp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> SCTP_APP_TAB_BITS) ^ (__force u16)port)
@@ -1042,34 +1024,40 @@ static int sctp_register_app(struct ip_vs_app *inc)
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
 
 	hash = sctp_app_hashkey(port);
 
-	spin_lock_bh(&sctp_app_lock);
-	list_for_each_entry(i, &sctp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->sctp_app_lock);
+	list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &sctp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_sctp.appcnt);
+	list_add(&inc->p_list, &ipvs->sctp_apps[hash]);
+	atomic_inc(&pd->pp->appcnt);
 out:
-	spin_unlock_bh(&sctp_app_lock);
+	spin_unlock_bh(&ipvs->sctp_app_lock);
 
 	return ret;
 }
 
 static void sctp_unregister_app(struct ip_vs_app *inc)
 {
-	spin_lock_bh(&sctp_app_lock);
-	atomic_dec(&ip_vs_protocol_sctp.appcnt);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
+
+	spin_lock_bh(&ipvs->sctp_app_lock);
+	atomic_dec(&pd->pp->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&sctp_app_lock);
+	spin_unlock_bh(&ipvs->sctp_app_lock);
 }
 
 static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -1080,12 +1068,12 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = sctp_app_hashkey(cp->vport);
 
-	spin_lock(&sctp_app_lock);
-	list_for_each_entry(inc, &sctp_apps[hash], p_list) {
+	spin_lock(&ipvs->sctp_app_lock);
+	list_for_each_entry(inc, &ipvs->sctp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&sctp_app_lock);
+			spin_unlock(&ipvs->sctp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->"
 					"%s:%u to app %s on port %u\n",
@@ -1101,43 +1089,50 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&sctp_app_lock);
+	spin_unlock(&ipvs->sctp_app_lock);
 out:
 	return result;
 }
 
-static void ip_vs_sctp_init(struct ip_vs_protocol *pp)
+/* ---------------------------------------------
+ *   timeouts is netns related now.
+ * ---------------------------------------------
+ */
+static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(sctp_apps);
-	pp->timeout_table = sctp_timeouts;
-}
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->tcp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts,
+							sizeof(sctp_timeouts));
+}
 
-static void ip_vs_sctp_exit(struct ip_vs_protocol *pp)
+static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
-
+	kfree(pd->timeout_table);
 }
 
 struct ip_vs_protocol ip_vs_protocol_sctp = {
-	.name = "SCTP",
-	.protocol = IPPROTO_SCTP,
-	.num_states = IP_VS_SCTP_S_LAST,
-	.dont_defrag = 0,
-	.appcnt = ATOMIC_INIT(0),
-	.init = ip_vs_sctp_init,
-	.exit = ip_vs_sctp_exit,
-	.register_app = sctp_register_app,
+	.name		= "SCTP",
+	.protocol	= IPPROTO_SCTP,
+	.num_states	= IP_VS_SCTP_S_LAST,
+	.dont_defrag	= 0,
+	.init		= NULL,
+	.exit		= NULL,
+	.init_netns	= __ip_vs_sctp_init,
+	.exit_netns	= __ip_vs_sctp_exit,
+	.register_app	= sctp_register_app,
 	.unregister_app = sctp_unregister_app,
-	.conn_schedule = sctp_conn_schedule,
-	.conn_in_get = ip_vs_conn_in_get_proto,
-	.conn_out_get = ip_vs_conn_out_get_proto,
-	.snat_handler = sctp_snat_handler,
-	.dnat_handler = sctp_dnat_handler,
-	.csum_check = sctp_csum_check,
-	.state_name = sctp_state_name,
+	.conn_schedule	= sctp_conn_schedule,
+	.conn_in_get	= ip_vs_conn_in_get_proto,
+	.conn_out_get	= ip_vs_conn_out_get_proto,
+	.snat_handler	= sctp_snat_handler,
+	.dnat_handler	= sctp_dnat_handler,
+	.csum_check	= sctp_csum_check,
+	.state_name	= sctp_state_name,
 	.state_transition = sctp_state_transition,
-	.app_conn_bind = sctp_app_conn_bind,
-	.debug_packet = ip_vs_tcpudp_debug_packet,
-	.timeout_change = sctp_timeout_change,
-	.set_state_timeout = sctp_set_state_timeout,
+	.app_conn_bind	= sctp_app_conn_bind,
+	.debug_packet	= ip_vs_tcpudp_debug_packet,
+	.timeout_change	= NULL,
 };
-- 
cgit v1.2.3


From 9330419d9aa4f97df412ac9be9fc0388c67dd315 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:51 +0100
Subject: IPVS: netns, use ip_vs_proto_data as param.

ip_vs_protocol *pp is replaced by ip_vs_proto_data *pd in
function call in ip_vs_protocol struct i.e. :,
 - timeout_change()
 - state_transition()

ip_vs_protocol_timeout_change() got ipvs as param, due to above
and a upcoming patch - defence work

Most of this changes are triggered by Julians comment:
"tcp_timeout_change should work with the new struct ip_vs_proto_data
        so that tcp_state_table will go to pd->state_table
        and set_tcp_state will get pd instead of pp"

*v3
Mostly comments from Julian
The pp -> pd conversion should start from functions like
ip_vs_out() that use pp = ip_vs_proto_get(iph.protocol),
now they should use ip_vs_proto_data_get(net, iph.protocol).
conn_in_get() and conn_out_get() unused param *pp, removed.

*v4
ip_vs_protocol_timeout_change() walk the proto_data path.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                     | 18 +++-----
 net/netfilter/ipvs/ip_vs_conn.c         |  2 -
 net/netfilter/ipvs/ip_vs_core.c         | 77 ++++++++++++++++++++-------------
 net/netfilter/ipvs/ip_vs_ctl.c          | 55 ++++++++++++++---------
 net/netfilter/ipvs/ip_vs_proto.c        | 21 ++++++---
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 10 ++---
 net/netfilter/ipvs/ip_vs_proto_sctp.c   | 16 +++----
 net/netfilter/ipvs/ip_vs_proto_tcp.c    | 27 +++++-------
 net/netfilter/ipvs/ip_vs_proto_udp.c    | 11 ++---
 net/netfilter/xt_ipvs.c                 |  2 +-
 10 files changed, 129 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 3c45a00cdc3e..464ea365ca07 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -372,13 +372,12 @@ struct ip_vs_protocol {
 	void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);
 
 	int (*conn_schedule)(int af, struct sk_buff *skb,
-			     struct ip_vs_protocol *pp,
+			     struct ip_vs_proto_data *pd,
 			     int *verdict, struct ip_vs_conn **cpp);
 
 	struct ip_vs_conn *
 	(*conn_in_get)(int af,
 		       const struct sk_buff *skb,
-		       struct ip_vs_protocol *pp,
 		       const struct ip_vs_iphdr *iph,
 		       unsigned int proto_off,
 		       int inverse);
@@ -386,7 +385,6 @@ struct ip_vs_protocol {
 	struct ip_vs_conn *
 	(*conn_out_get)(int af,
 			const struct sk_buff *skb,
-			struct ip_vs_protocol *pp,
 			const struct ip_vs_iphdr *iph,
 			unsigned int proto_off,
 			int inverse);
@@ -404,7 +402,7 @@ struct ip_vs_protocol {
 
 	int (*state_transition)(struct ip_vs_conn *cp, int direction,
 				const struct sk_buff *skb,
-				struct ip_vs_protocol *pp);
+				struct ip_vs_proto_data *pd);
 
 	int (*register_app)(struct ip_vs_app *inc);
 
@@ -417,9 +415,7 @@ struct ip_vs_protocol {
 			     int offset,
 			     const char *msg);
 
-	void (*timeout_change)(struct ip_vs_protocol *pp, int flags);
-
-	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
+	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
 };
 
 /*
@@ -778,7 +774,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
 struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-					    struct ip_vs_protocol *pp,
 					    const struct ip_vs_iphdr *iph,
 					    unsigned int proto_off,
 					    int inverse);
@@ -786,7 +781,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
 struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);
 
 struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-					     struct ip_vs_protocol *pp,
 					     const struct ip_vs_iphdr *iph,
 					     unsigned int proto_off,
 					     int inverse);
@@ -917,7 +911,7 @@ static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
  */
 extern int ip_vs_protocol_init(void);
 extern void ip_vs_protocol_cleanup(void);
-extern void ip_vs_protocol_timeout_change(int flags);
+extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
 extern int *ip_vs_create_timeout_table(int *table, int size);
 extern int
 ip_vs_set_state_timeout(int *table, int num, const char *const *names,
@@ -947,9 +941,9 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 extern struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_protocol *pp, int *ignored);
+	       struct ip_vs_proto_data *pd, int *ignored);
 extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-			struct ip_vs_protocol *pp);
+			struct ip_vs_proto_data *pd);
 
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 7a0e79e3ad0f..a7aba6a4697e 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -329,7 +329,6 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 
 struct ip_vs_conn *
 ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-			struct ip_vs_protocol *pp,
 			const struct ip_vs_iphdr *iph,
 			unsigned int proto_off, int inverse)
 {
@@ -428,7 +427,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 struct ip_vs_conn *
 ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-			 struct ip_vs_protocol *pp,
 			 const struct ip_vs_iphdr *iph,
 			 unsigned int proto_off, int inverse)
 {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d0616ea1eebf..9317affc5ea1 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -177,11 +177,11 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 static inline int
 ip_vs_set_state(struct ip_vs_conn *cp, int direction,
 		const struct sk_buff *skb,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_proto_data *pd)
 {
-	if (unlikely(!pp->state_transition))
+	if (unlikely(!pd->pp->state_transition))
 		return 0;
-	return pp->state_transition(cp, direction, skb, pp);
+	return pd->pp->state_transition(cp, direction, skb, pd);
 }
 
 static inline int
@@ -378,8 +378,9 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
  */
 struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_protocol *pp, int *ignored)
+	       struct ip_vs_proto_data *pd, int *ignored)
 {
+	struct ip_vs_protocol *pp = pd->pp;
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
@@ -408,7 +409,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 *    Do not schedule replies from local real server.
 	 */
 	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-	    (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) {
+	    (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) {
 		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
 			      "Not scheduling reply for existing connection");
 		__ip_vs_conn_put(cp);
@@ -479,11 +480,12 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
  *  no destination is available for a new connection.
  */
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_proto_data *pd)
 {
 	__be16 _ports[2], *pptr;
 	struct ip_vs_iphdr iph;
 	int unicast;
+
 	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 
 	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
@@ -530,10 +532,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_in_stats(cp, skb);
 
 		/* set state */
-		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
+		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 
 		/* transmit the first SYN packet */
-		ret = cp->packet_xmit(skb, cp, pp);
+		ret = cp->packet_xmit(skb, cp, pd->pp);
 		/* do not touch skb anymore */
 
 		atomic_inc(&cp->in_pkts);
@@ -840,7 +842,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -917,7 +919,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 
 	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -956,9 +958,11 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
  * Used for NAT and local client.
  */
 static unsigned int
-handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		struct ip_vs_conn *cp, int ihl)
 {
+	struct ip_vs_protocol *pp = pd->pp;
+
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
 	if (!skb_make_writable(skb, ihl))
@@ -1007,7 +1011,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
 
 	ip_vs_out_stats(cp, skb);
-	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
+	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
 	skb->ipvs_property = 1;
 	if (!(cp->flags & IP_VS_CONN_F_NFCT))
 		ip_vs_notrack(skb);
@@ -1034,6 +1038,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 
 	EnterFunction(11);
@@ -1079,9 +1084,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
-	pp = ip_vs_proto_get(iph.protocol);
-	if (unlikely(!pp))
+	pd = ip_vs_proto_data_get(net, iph.protocol);
+	if (unlikely(!pd))
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* reassemble IP fragments */
 #ifdef CONFIG_IP_VS_IPV6
@@ -1107,10 +1113,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0);
+	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pp, cp, iph.len);
+		return handle_response(af, skb, pd, cp, iph.len);
 	if (sysctl_ip_vs_nat_icmp_send &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
@@ -1236,12 +1242,14 @@ ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
 static int
 ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
+	struct net *net = NULL;
 	struct iphdr *iph;
 	struct icmphdr	_icmph, *ic;
 	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
 	struct ip_vs_iphdr ciph;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	unsigned int offset, ihl, verdict;
 	union nf_inet_addr snet;
 
@@ -1283,9 +1291,11 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
-	pp = ip_vs_proto_get(cih->protocol);
-	if (!pp)
+	net = skb_net(skb);
+	pd = ip_vs_proto_data_get(net, cih->protocol);
+	if (!pd)
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
 	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
@@ -1299,10 +1309,10 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp) {
 		/* The packet could also belong to a local client */
-		cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1);
+		cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 		if (cp) {
 			snet.ip = iph->saddr;
 			return handle_response_icmp(AF_INET, skb, &snet,
@@ -1346,6 +1356,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 static int
 ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
+	struct net *net = NULL;
 	struct ipv6hdr *iph;
 	struct icmp6hdr	_icmph, *ic;
 	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
@@ -1353,6 +1364,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	struct ip_vs_iphdr ciph;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	unsigned int offset, verdict;
 	union nf_inet_addr snet;
 	struct rt6_info *rt;
@@ -1395,9 +1407,11 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
-	pp = ip_vs_proto_get(cih->nexthdr);
-	if (!pp)
+	net = skb_net(skb);
+	pd = ip_vs_proto_data_get(net, cih->nexthdr);
+	if (!pd)
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
 	/* TODO: we don't support fragmentation at the moment anyways */
@@ -1411,10 +1425,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET6, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp) {
 		/* The packet could also belong to a local client */
-		cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1);
+		cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
 		if (cp) {
 			ipv6_addr_copy(&snet.in6, &iph->saddr);
 			return handle_response_icmp(AF_INET6, skb, &snet,
@@ -1457,8 +1471,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 static unsigned int
 ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, restart, pkts;
 
@@ -1514,20 +1530,21 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
+	net = skb_net(skb);
 	/* Protocol supported? */
-	pp = ip_vs_proto_get(iph.protocol);
-	if (unlikely(!pp))
+	pd = ip_vs_proto_data_get(net, iph.protocol);
+	if (unlikely(!pd))
 		return NF_ACCEPT;
-
+	pp = pd->pp;
 	/*
 	 * Check if the packet belongs to an existing connection entry
 	 */
-	cp = pp->conn_in_get(af, skb, pp, &iph, iph.len, 0);
+	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
 
 	if (unlikely(!cp)) {
 		int v;
 
-		if (!pp->conn_schedule(af, skb, pp, &v, &cp))
+		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
 			return v;
 	}
 
@@ -1555,7 +1572,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	ip_vs_in_stats(cp, skb);
-	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
+	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 	if (cp->packet_xmit)
 		ret = cp->packet_xmit(skb, cp, pp);
 		/* do not touch skb anymore */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 2d7c96bd2114..88474f1e828a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -38,6 +38,7 @@
 #include <linux/mutex.h>
 
 #include <net/net_namespace.h>
+#include <linux/nsproxy.h>
 #include <net/ip.h>
 #ifdef CONFIG_IP_VS_IPV6
 #include <net/ipv6.h>
@@ -125,7 +126,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr)
  *	update_defense_level is called from keventd and from sysctl,
  *	so it needs to protect itself from softirqs
  */
-static void update_defense_level(void)
+static void update_defense_level(struct netns_ipvs *ipvs)
 {
 	struct sysinfo i;
 	static int old_secure_tcp = 0;
@@ -239,7 +240,8 @@ static void update_defense_level(void)
 	}
 	old_secure_tcp = sysctl_ip_vs_secure_tcp;
 	if (to_change >= 0)
-		ip_vs_protocol_timeout_change(sysctl_ip_vs_secure_tcp>1);
+		ip_vs_protocol_timeout_change(ipvs,
+					     sysctl_ip_vs_secure_tcp > 1);
 	spin_unlock(&ip_vs_securetcp_lock);
 
 	local_bh_enable();
@@ -255,7 +257,10 @@ static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
 
 static void defense_work_handler(struct work_struct *work)
 {
-	update_defense_level();
+	struct net *net = &init_net;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	update_defense_level(ipvs);
 	if (atomic_read(&ip_vs_dropentry))
 		ip_vs_random_dropentry();
 
@@ -1502,6 +1507,7 @@ static int
 proc_do_defense_mode(ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct net *net = current->nsproxy->net_ns;
 	int *valp = table->data;
 	int val = *valp;
 	int rc;
@@ -1512,7 +1518,7 @@ proc_do_defense_mode(ctl_table *table, int write,
 			/* Restore the correct value */
 			*valp = val;
 		} else {
-			update_defense_level();
+			update_defense_level(net_ipvs(net));
 		}
 	}
 	return rc;
@@ -2033,8 +2039,10 @@ static const struct file_operations ip_vs_stats_fops = {
 /*
  *	Set timeout values for tcp tcpfin udp in the timeout_table.
  */
-static int ip_vs_set_timeout(struct ip_vs_timeout_user *u)
+static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u)
 {
+	struct ip_vs_proto_data *pd;
+
 	IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n",
 		  u->tcp_timeout,
 		  u->tcp_fin_timeout,
@@ -2042,19 +2050,22 @@ static int ip_vs_set_timeout(struct ip_vs_timeout_user *u)
 
 #ifdef CONFIG_IP_VS_PROTO_TCP
 	if (u->tcp_timeout) {
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED]
+		pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+		pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
 			= u->tcp_timeout * HZ;
 	}
 
 	if (u->tcp_fin_timeout) {
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT]
+		pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+		pd->timeout_table[IP_VS_TCP_S_FIN_WAIT]
 			= u->tcp_fin_timeout * HZ;
 	}
 #endif
 
 #ifdef CONFIG_IP_VS_PROTO_UDP
 	if (u->udp_timeout) {
-		ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL]
+		pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
+		pd->timeout_table[IP_VS_UDP_S_NORMAL]
 			= u->udp_timeout * HZ;
 	}
 #endif
@@ -2158,7 +2169,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
 		/* Set timeout values for (tcp tcpfin udp) */
-		ret = ip_vs_set_timeout((struct ip_vs_timeout_user *)arg);
+		ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg);
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_STARTDAEMON) {
 		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
@@ -2370,17 +2381,19 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 }
 
 static inline void
-__ip_vs_get_timeouts(struct ip_vs_timeout_user *u)
+__ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u)
 {
+	struct ip_vs_proto_data *pd;
+
 #ifdef CONFIG_IP_VS_PROTO_TCP
-	u->tcp_timeout =
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
-	u->tcp_fin_timeout =
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
+	pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+	u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
+	u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
 #endif
 #ifdef CONFIG_IP_VS_PROTO_UDP
+	pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
 	u->udp_timeout =
-		ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
+			pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
 #endif
 }
 
@@ -2521,7 +2534,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	{
 		struct ip_vs_timeout_user t;
 
-		__ip_vs_get_timeouts(&t);
+		__ip_vs_get_timeouts(net, &t);
 		if (copy_to_user(user, &t, sizeof(t)) != 0)
 			ret = -EFAULT;
 	}
@@ -3092,11 +3105,11 @@ static int ip_vs_genl_del_daemon(struct nlattr **attrs)
 	return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
 }
 
-static int ip_vs_genl_set_config(struct nlattr **attrs)
+static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
 {
 	struct ip_vs_timeout_user t;
 
-	__ip_vs_get_timeouts(&t);
+	__ip_vs_get_timeouts(net, &t);
 
 	if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP])
 		t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]);
@@ -3108,7 +3121,7 @@ static int ip_vs_genl_set_config(struct nlattr **attrs)
 	if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP])
 		t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]);
 
-	return ip_vs_set_timeout(&t);
+	return ip_vs_set_timeout(net, &t);
 }
 
 static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
@@ -3129,7 +3142,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		ret = ip_vs_flush(net);
 		goto out;
 	} else if (cmd == IPVS_CMD_SET_CONFIG) {
-		ret = ip_vs_genl_set_config(info->attrs);
+		ret = ip_vs_genl_set_config(net, info->attrs);
 		goto out;
 	} else if (cmd == IPVS_CMD_NEW_DAEMON ||
 		   cmd == IPVS_CMD_DEL_DAEMON) {
@@ -3281,7 +3294,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	{
 		struct ip_vs_timeout_user t;
 
-		__ip_vs_get_timeouts(&t);
+		__ip_vs_get_timeouts(net, &t);
 #ifdef CONFIG_IP_VS_PROTO_TCP
 		NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout);
 		NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN,
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 9f609d4d5d58..6ac986cdcff3 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -152,9 +152,8 @@ EXPORT_SYMBOL(ip_vs_proto_get);
  *	get ip_vs_protocol object data by netns and proto
  */
 struct ip_vs_proto_data *
-ip_vs_proto_data_get(struct net *net, unsigned short proto)
+__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
 {
-	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_proto_data *pd;
 	unsigned hash = IP_VS_PROTO_HASH(proto);
 
@@ -165,20 +164,28 @@ ip_vs_proto_data_get(struct net *net, unsigned short proto)
 
 	return NULL;
 }
+
+struct ip_vs_proto_data *
+ip_vs_proto_data_get(struct net *net, unsigned short proto)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	return __ipvs_proto_data_get(ipvs, proto);
+}
 EXPORT_SYMBOL(ip_vs_proto_data_get);
 
 /*
  *	Propagate event for state change to all protocols
  */
-void ip_vs_protocol_timeout_change(int flags)
+void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags)
 {
-	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	int i;
 
 	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
-		for (pp = ip_vs_proto_table[i]; pp; pp = pp->next) {
-			if (pp->timeout_change)
-				pp->timeout_change(pp, flags);
+		for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) {
+			if (pd->pp->timeout_change)
+				pd->pp->timeout_change(pd, flags);
 		}
 	}
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index b8b37fafc988..28039cbfcff4 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -55,7 +55,7 @@ ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
 }
 
 static struct ip_vs_conn *
-ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
+ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 		   const struct ip_vs_iphdr *iph, unsigned int proto_off,
 		   int inverse)
 {
@@ -72,7 +72,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet "
 			      "%s%s %s->%s\n",
 			      inverse ? "ICMP+" : "",
-			      pp->name,
+			      ip_vs_proto_get(iph->protocol)->name,
 			      IP_VS_DBG_ADDR(af, &iph->saddr),
 			      IP_VS_DBG_ADDR(af, &iph->daddr));
 	}
@@ -83,7 +83,6 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static struct ip_vs_conn *
 ah_esp_conn_out_get(int af, const struct sk_buff *skb,
-		    struct ip_vs_protocol *pp,
 		    const struct ip_vs_iphdr *iph,
 		    unsigned int proto_off,
 		    int inverse)
@@ -97,7 +96,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
 			      "%s%s %s->%s\n",
 			      inverse ? "ICMP+" : "",
-			      pp->name,
+			      ip_vs_proto_get(iph->protocol)->name,
 			      IP_VS_DBG_ADDR(af, &iph->saddr),
 			      IP_VS_DBG_ADDR(af, &iph->daddr));
 	}
@@ -107,7 +106,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 
 
 static int
-ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		     int *verdict, struct ip_vs_conn **cpp)
 {
 	/*
@@ -137,7 +136,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = {
 	.app_conn_bind =	NULL,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	NULL,		/* ISAKMP */
-	.set_state_timeout =	NULL,
 };
 #endif
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index f826dd1e4630..19bc37976ea7 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -9,7 +9,7 @@
 #include <net/ip_vs.h>
 
 static int
-sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		   int *verdict, struct ip_vs_conn **cpp)
 {
 	struct net *net;
@@ -47,10 +47,10 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pp);
+				*verdict = ip_vs_leave(svc, skb, pd);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -907,14 +907,13 @@ static const char *sctp_state_name(int state)
 }
 
 static inline int
-set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
+set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 		int direction, const struct sk_buff *skb)
 {
 	sctp_chunkhdr_t _sctpch, *sch;
 	unsigned char chunk_type;
 	int event, next_state;
 	int ihl;
-	struct ip_vs_proto_data *pd;
 
 #ifdef CONFIG_IP_VS_IPV6
 	ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
@@ -966,7 +965,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 		IP_VS_DBG_BUF(8, "%s %s  %s:%d->"
 				"%s:%d state: %s->%s conn->refcnt:%d\n",
-				pp->name,
+				pd->pp->name,
 				((direction == IP_VS_DIR_OUTPUT) ?
 				 "output " : "input "),
 				IP_VS_DBG_ADDR(cp->af, &cp->daddr),
@@ -990,7 +989,6 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 			}
 		}
 	}
-	pd = ip_vs_proto_data_get(&init_net, pp->protocol); /* tmp fix */
 	if (likely(pd))
 		cp->timeout = pd->timeout_table[cp->state = next_state];
 	else	/* What to do ? */
@@ -1001,12 +999,12 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 static int
 sctp_state_transition(struct ip_vs_conn *cp, int direction,
-		const struct sk_buff *skb, struct ip_vs_protocol *pp)
+		const struct sk_buff *skb, struct ip_vs_proto_data *pd)
 {
 	int ret = 0;
 
 	spin_lock(&cp->lock);
-	ret = set_sctp_state(pp, cp, direction, skb);
+	ret = set_sctp_state(pd, cp, direction, skb);
 	spin_unlock(&cp->lock);
 
 	return ret;
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 9d9df3d61093..d7c245532798 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -32,7 +32,7 @@
 #include <net/ip_vs.h>
 
 static int
-tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
 	struct net *net;
@@ -68,10 +68,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pp);
+				*verdict = ip_vs_leave(svc, skb, pd);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -448,10 +448,7 @@ static struct tcp_states_t tcp_states_dos [] = {
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
 };
 
-static struct tcp_states_t *tcp_state_table = tcp_states;
-
-
-static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
+static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags)
 {
 	int on = (flags & 1);		/* secure_tcp */
 
@@ -461,7 +458,7 @@ static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
 	** for most if not for all of the applications. Something
 	** like "capabilities" (flags) for each object.
 	*/
-	tcp_state_table = (on? tcp_states_dos : tcp_states);
+	pd->tcp_state_table = (on ? tcp_states_dos : tcp_states);
 }
 
 static inline int tcp_state_idx(struct tcphdr *th)
@@ -478,13 +475,12 @@ static inline int tcp_state_idx(struct tcphdr *th)
 }
 
 static inline void
-set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
+set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 	      int direction, struct tcphdr *th)
 {
 	int state_idx;
 	int new_state = IP_VS_TCP_S_CLOSE;
 	int state_off = tcp_state_off[direction];
-	struct ip_vs_proto_data *pd;  /* Temp fix */
 
 	/*
 	 *    Update state offset to INPUT_ONLY if necessary
@@ -502,7 +498,8 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		goto tcp_state_out;
 	}
 
-	new_state = tcp_state_table[state_off+state_idx].next_state[cp->state];
+	new_state =
+		pd->tcp_state_table[state_off+state_idx].next_state[cp->state];
 
   tcp_state_out:
 	if (new_state != cp->state) {
@@ -510,7 +507,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->"
 			      "%s:%d state: %s->%s conn->refcnt:%d\n",
-			      pp->name,
+			      pd->pp->name,
 			      ((state_off == TCP_DIR_OUTPUT) ?
 			       "output " : "input "),
 			      th->syn ? 'S' : '.',
@@ -540,7 +537,6 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		}
 	}
 
-	pd = ip_vs_proto_data_get(&init_net, pp->protocol);
 	if (likely(pd))
 		cp->timeout = pd->timeout_table[cp->state = new_state];
 	else	/* What to do ? */
@@ -553,7 +549,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 static int
 tcp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_proto_data *pd)
 {
 	struct tcphdr _tcph, *th;
 
@@ -568,7 +564,7 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction,
 		return 0;
 
 	spin_lock(&cp->lock);
-	set_tcp_state(pp, cp, direction, th);
+	set_tcp_state(pd, cp, direction, th);
 	spin_unlock(&cp->lock);
 
 	return 1;
@@ -691,6 +687,7 @@ static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
 	spin_lock_init(&ipvs->tcp_app_lock);
 	pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
 							sizeof(tcp_timeouts));
+	pd->tcp_state_table =  tcp_states;
 }
 
 static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 71a4721a8f8a..aa85df2f14a0 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -29,7 +29,7 @@
 #include <net/ip6_checksum.h>
 
 static int
-udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
 	struct net *net;
@@ -64,10 +64,10 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pp);
+				*verdict = ip_vs_leave(svc, skb, pd);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -457,11 +457,8 @@ static const char * udp_state_name(int state)
 static int
 udp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_proto_data *pd)
 {
-	struct ip_vs_proto_data *pd;   /* Temp fix, pp will be replaced by pd */
-
-	pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
 	if (unlikely(!pd)) {
 		pr_err("UDP no ns data\n");
 		return 0;
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
index 9127a3d8aa35..bb10b0717f1b 100644
--- a/net/netfilter/xt_ipvs.c
+++ b/net/netfilter/xt_ipvs.c
@@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */);
+	cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */);
 	if (unlikely(cp == NULL)) {
 		match = false;
 		goto out;
-- 
cgit v1.2.3


From 9bbac6a904d0816dae58b454692c54d6773cc20d Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:52 +0100
Subject: IPVS: netns, common protocol changes and use of appcnt.

appcnt and timeout_table moved from struct ip_vs_protocol to
ip_vs proto_data.

struct net *net added as first param to
 - register_app()
 - unregister_app()
 - app_conn_bind()
 - ip_vs_conn_new()

[horms@verge.net.au: removed cosmetic-change-only hunk]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |  2 --
 net/netfilter/ipvs/ip_vs_conn.c       |  6 ++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c |  4 +--
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |  5 ++--
 net/netfilter/ipvs/ip_vs_proto_udp.c  |  4 +--
 net/netfilter/ipvs/ip_vs_sync.c       | 55 +++++++++++++++++++----------------
 6 files changed, 39 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 464ea365ca07..cc6ae621a9b5 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -360,8 +360,6 @@ struct ip_vs_protocol {
 	u16			protocol;
 	u16			num_states;
 	int			dont_defrag;
-	atomic_t		appcnt;		/* counter of proto app incs */
-	int			*timeout_table;	/* protocol timeout table */
 
 	void (*init)(struct ip_vs_protocol *pp);
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a7aba6a4697e..b2024c942345 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -804,7 +804,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	       struct ip_vs_dest *dest, __u32 fwmark)
 {
 	struct ip_vs_conn *cp;
-	struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, p->protocol);
 
 	cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
 	if (cp == NULL) {
@@ -863,8 +863,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 #endif
 		ip_vs_bind_xmit(cp);
 
-	if (unlikely(pp && atomic_read(&pp->appcnt)))
-		ip_vs_bind_app(cp, pp);
+	if (unlikely(pd && atomic_read(&pd->appcnt)))
+		ip_vs_bind_app(cp, pd->pp);
 
 	/*
 	 * Allow conntrack to be preserved. By default, conntrack
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 19bc37976ea7..0f14f793318a 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1035,7 +1035,7 @@ static int sctp_register_app(struct ip_vs_app *inc)
 		}
 	}
 	list_add(&inc->p_list, &ipvs->sctp_apps[hash]);
-	atomic_inc(&pd->pp->appcnt);
+	atomic_inc(&pd->appcnt);
 out:
 	spin_unlock_bh(&ipvs->sctp_app_lock);
 
@@ -1048,7 +1048,7 @@ static void sctp_unregister_app(struct ip_vs_app *inc)
 	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
 
 	spin_lock_bh(&ipvs->sctp_app_lock);
-	atomic_dec(&pd->pp->appcnt);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
 	spin_unlock_bh(&ipvs->sctp_app_lock);
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index d7c245532798..290b3803d8ce 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -596,7 +596,7 @@ static int tcp_register_app(struct ip_vs_app *inc)
 		}
 	}
 	list_add(&inc->p_list, &ipvs->tcp_apps[hash]);
-	atomic_inc(&pd->pp->appcnt);
+	atomic_inc(&pd->appcnt);
 
   out:
 	spin_unlock_bh(&ipvs->tcp_app_lock);
@@ -611,7 +611,7 @@ tcp_unregister_app(struct ip_vs_app *inc)
 	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
 
 	spin_lock_bh(&ipvs->tcp_app_lock);
-	atomic_dec(&pd->pp->appcnt);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
 	spin_unlock_bh(&ipvs->tcp_app_lock);
 }
@@ -701,7 +701,6 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
 	.protocol =		IPPROTO_TCP,
 	.num_states =		IP_VS_TCP_S_LAST,
 	.dont_defrag =		0,
-	.appcnt =		ATOMIC_INIT(0),
 	.init =			NULL,
 	.exit =			NULL,
 	.init_netns =		__ip_vs_tcp_init,
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index aa85df2f14a0..3719837a8fdc 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -373,7 +373,7 @@ static int udp_register_app(struct ip_vs_app *inc)
 		}
 	}
 	list_add(&inc->p_list, &ipvs->udp_apps[hash]);
-	atomic_inc(&pd->pp->appcnt);
+	atomic_inc(&pd->appcnt);
 
   out:
 	spin_unlock_bh(&ipvs->udp_app_lock);
@@ -388,7 +388,7 @@ udp_unregister_app(struct ip_vs_app *inc)
 	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 
 	spin_lock_bh(&ipvs->udp_app_lock);
-	atomic_dec(&pd->pp->appcnt);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
 	spin_unlock_bh(&ipvs->udp_app_lock);
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 662aa2c22a05..6831e8fac8db 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -725,17 +725,16 @@ ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
  *  Param: ...
  *         timeout is in sec.
  */
-static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
-			    unsigned state, unsigned protocol, unsigned type,
+static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
+			    unsigned int flags, unsigned int state,
+			    unsigned int protocol, unsigned int type,
 			    const union nf_inet_addr *daddr, __be16 dport,
 			    unsigned long timeout, __u32 fwmark,
-			    struct ip_vs_sync_conn_options *opt,
-			    struct ip_vs_protocol *pp)
+			    struct ip_vs_sync_conn_options *opt)
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *cp;
 
-
 	if (!(flags & IP_VS_CONN_F_TEMPLATE))
 		cp = ip_vs_conn_in_get(param);
 	else
@@ -821,17 +820,23 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
 		if (timeout > MAX_SCHEDULE_TIMEOUT / HZ)
 			timeout = MAX_SCHEDULE_TIMEOUT / HZ;
 		cp->timeout = timeout*HZ;
-	} else if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
-		cp->timeout = pp->timeout_table[state];
-	else
-		cp->timeout = (3*60*HZ);
+	} else {
+		struct ip_vs_proto_data *pd;
+
+		pd = ip_vs_proto_data_get(net, protocol);
+		if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table)
+			cp->timeout = pd->timeout_table[state];
+		else
+			cp->timeout = (3*60*HZ);
+	}
 	ip_vs_conn_put(cp);
 }
 
 /*
  *  Process received multicast message for Version 0
  */
-static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
+static void ip_vs_process_message_v0(struct net *net, const char *buffer,
+				     const size_t buflen)
 {
 	struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer;
 	struct ip_vs_sync_conn_v0 *s;
@@ -879,7 +884,6 @@ static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 			}
 		} else {
 			/* protocol in templates is not used for state/timeout */
-			pp = NULL;
 			if (state > 0) {
 				IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n",
 					state);
@@ -894,9 +898,9 @@ static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 				      s->vport, &param);
 
 		/* Send timeout as Zero */
-		ip_vs_proc_conn(&param, flags, state, s->protocol, AF_INET,
+		ip_vs_proc_conn(net, &param, flags, state, s->protocol, AF_INET,
 				(union nf_inet_addr *)&s->daddr, s->dport,
-				0, 0, opt, pp);
+				0, 0, opt);
 	}
 }
 
@@ -945,7 +949,7 @@ static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len,
 /*
  *   Process a Version 1 sync. connection
  */
-static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
+static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end)
 {
 	struct ip_vs_sync_conn_options opt;
 	union  ip_vs_sync_conn *s;
@@ -1043,7 +1047,6 @@ static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
 		}
 	} else {
 		/* protocol in templates is not used for state/timeout */
-		pp = NULL;
 		if (state > 0) {
 			IP_VS_DBG(3, "BACKUP, Invalid template state %u\n",
 				state);
@@ -1058,18 +1061,18 @@ static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
 	}
 	/* If only IPv4, just silent skip IPv6 */
 	if (af == AF_INET)
-		ip_vs_proc_conn(&param, flags, state, s->v4.protocol, af,
+		ip_vs_proc_conn(net, &param, flags, state, s->v4.protocol, af,
 				(union nf_inet_addr *)&s->v4.daddr, s->v4.dport,
 				ntohl(s->v4.timeout), ntohl(s->v4.fwmark),
-				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
-				pp);
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
+				);
 #ifdef CONFIG_IP_VS_IPV6
 	else
-		ip_vs_proc_conn(&param, flags, state, s->v6.protocol, af,
+		ip_vs_proc_conn(net, &param, flags, state, s->v6.protocol, af,
 				(union nf_inet_addr *)&s->v6.daddr, s->v6.dport,
 				ntohl(s->v6.timeout), ntohl(s->v6.fwmark),
-				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
-				pp);
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
+				);
 #endif
 	return 0;
 	/* Error exit */
@@ -1083,7 +1086,8 @@ out:
  *      ip_vs_conn entries.
  *      Handles Version 0 & 1
  */
-static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
+static void ip_vs_process_message(struct net *net, __u8 *buffer,
+				  const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
 	__u8 *p, *msg_end;
@@ -1136,7 +1140,8 @@ static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 				return;
 			}
 			/* Process a single sync_conn */
-			if ((retc=ip_vs_proc_sync_conn(p, msg_end)) < 0) {
+			retc = ip_vs_proc_sync_conn(net, p, msg_end);
+			if (retc < 0) {
 				IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n",
 					     retc);
 				return;
@@ -1146,7 +1151,7 @@ static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 		}
 	} else {
 		/* Old type of message */
-		ip_vs_process_message_v0(buffer, buflen);
+		ip_vs_process_message_v0(net, buffer, buflen);
 		return;
 	}
 }
@@ -1500,7 +1505,7 @@ static int sync_thread_backup(void *data)
 			/* disable bottom half, because it accesses the data
 			   shared by softirq while getting/creating conns */
 			local_bh_disable();
-			ip_vs_process_message(tinfo->buf, len);
+			ip_vs_process_message(&init_net, tinfo->buf, len);
 			local_bh_enable();
 		}
 	}
-- 
cgit v1.2.3


From ab8a5e8408c3df2d654611bffc3aaf04f418b266 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:53 +0100
Subject: IPVS: netns awareness to ip_vs_app

All variables moved to struct ipvs,
most external changes fixed (i.e. init_net removed)

in ip_vs_protocol param struct net *net added to:
 - register_app()
 - unregister_app()
This affected almost all proto_xxx.c files

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   | 12 +++---
 include/net/netns/ip_vs.h             |  5 +++
 net/netfilter/ipvs/ip_vs_app.c        | 73 +++++++++++++++++++++--------------
 net/netfilter/ipvs/ip_vs_ftp.c        |  8 ++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c | 12 +++---
 net/netfilter/ipvs/ip_vs_proto_tcp.c  | 12 +++---
 net/netfilter/ipvs/ip_vs_proto_udp.c  | 12 +++---
 7 files changed, 76 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cc6ae621a9b5..0cdd8ce454c2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -402,9 +402,9 @@ struct ip_vs_protocol {
 				const struct sk_buff *skb,
 				struct ip_vs_proto_data *pd);
 
-	int (*register_app)(struct ip_vs_app *inc);
+	int (*register_app)(struct net *net, struct ip_vs_app *inc);
 
-	void (*unregister_app)(struct ip_vs_app *inc);
+	void (*unregister_app)(struct net *net, struct ip_vs_app *inc);
 
 	int (*app_conn_bind)(struct ip_vs_conn *cp);
 
@@ -871,12 +871,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
  *      (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
-extern int register_ip_vs_app(struct ip_vs_app *app);
-extern void unregister_ip_vs_app(struct ip_vs_app *app);
+extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app);
+extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
 extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
 extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
-extern int
-register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port);
+extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app,
+				  __u16 proto, __u16 port);
 extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
 extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 58bd3fd85a97..03f7fe1bede6 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -28,6 +28,11 @@ struct netns_ipvs {
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+	/* ip_vs_app */
+	struct list_head	app_list;
+	struct mutex		app_mutex;
+	struct lock_class_key	app_key;	/* mutex debuging */
+
 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
 	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 40b09ccc4896..286f46594e0e 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -43,11 +43,6 @@ EXPORT_SYMBOL(register_ip_vs_app);
 EXPORT_SYMBOL(unregister_ip_vs_app);
 EXPORT_SYMBOL(register_ip_vs_app_inc);
 
-/* ipvs application list head */
-static LIST_HEAD(ip_vs_app_list);
-static DEFINE_MUTEX(__ip_vs_app_mutex);
-
-
 /*
  *	Get an ip_vs_app object
  */
@@ -67,7 +62,8 @@ static inline void ip_vs_app_put(struct ip_vs_app *app)
  *	Allocate/initialize app incarnation and register it in proto apps.
  */
 static int
-ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
+ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
+		  __u16 port)
 {
 	struct ip_vs_protocol *pp;
 	struct ip_vs_app *inc;
@@ -98,7 +94,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
 		}
 	}
 
-	ret = pp->register_app(inc);
+	ret = pp->register_app(net, inc);
 	if (ret)
 		goto out;
 
@@ -119,7 +115,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
  *	Release app incarnation
  */
 static void
-ip_vs_app_inc_release(struct ip_vs_app *inc)
+ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_protocol *pp;
 
@@ -127,7 +123,7 @@ ip_vs_app_inc_release(struct ip_vs_app *inc)
 		return;
 
 	if (pp->unregister_app)
-		pp->unregister_app(inc);
+		pp->unregister_app(net, inc);
 
 	IP_VS_DBG(9, "%s App %s:%u unregistered\n",
 		  pp->name, inc->name, ntohs(inc->port));
@@ -168,15 +164,17 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc)
  *	Register an application incarnation in protocol applications
  */
 int
-register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port)
+register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
+		       __u16 port)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	int result;
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
-	result = ip_vs_app_inc_new(app, proto, port);
+	result = ip_vs_app_inc_new(net, app, proto, port);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	return result;
 }
@@ -185,16 +183,17 @@ register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port)
 /*
  *	ip_vs_app registration routine
  */
-int register_ip_vs_app(struct ip_vs_app *app)
+int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
-	list_add(&app->a_list, &ip_vs_app_list);
+	list_add(&app->a_list, &ipvs->app_list);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	return 0;
 }
@@ -204,19 +203,20 @@ int register_ip_vs_app(struct ip_vs_app *app)
  *	ip_vs_app unregistration routine
  *	We are sure there are no app incarnations attached to services
  */
-void unregister_ip_vs_app(struct ip_vs_app *app)
+void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_app *inc, *nxt;
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
 	list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
-		ip_vs_app_inc_release(inc);
+		ip_vs_app_inc_release(net, inc);
 	}
 
 	list_del(&app->a_list);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	/* decrease the module use count */
 	ip_vs_use_count_dec();
@@ -226,7 +226,8 @@ void unregister_ip_vs_app(struct ip_vs_app *app)
 /*
  *	Bind ip_vs_conn to its ip_vs_app (called by cp constructor)
  */
-int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp)
+int ip_vs_bind_app(struct ip_vs_conn *cp,
+		   struct ip_vs_protocol *pp)
 {
 	return pp->app_conn_bind(cp);
 }
@@ -481,11 +482,11 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
  *	/proc/net/ip_vs_app entry function
  */
 
-static struct ip_vs_app *ip_vs_app_idx(loff_t pos)
+static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos)
 {
 	struct ip_vs_app *app, *inc;
 
-	list_for_each_entry(app, &ip_vs_app_list, a_list) {
+	list_for_each_entry(app, &ipvs->app_list, a_list) {
 		list_for_each_entry(inc, &app->incs_list, a_list) {
 			if (pos-- == 0)
 				return inc;
@@ -497,19 +498,24 @@ static struct ip_vs_app *ip_vs_app_idx(loff_t pos)
 
 static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	mutex_lock(&__ip_vs_app_mutex);
+	struct net *net = seq_file_net(seq);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	mutex_lock(&ipvs->app_mutex);
 
-	return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN;
+	return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN;
 }
 
 static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_app *inc, *app;
 	struct list_head *e;
+	struct net *net = seq_file_net(seq);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
-		return ip_vs_app_idx(0);
+		return ip_vs_app_idx(ipvs, 0);
 
 	inc = v;
 	app = inc->app;
@@ -518,7 +524,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		return list_entry(e, struct ip_vs_app, a_list);
 
 	/* go on to next application */
-	for (e = app->a_list.next; e != &ip_vs_app_list; e = e->next) {
+	for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) {
 		app = list_entry(e, struct ip_vs_app, a_list);
 		list_for_each_entry(inc, &app->incs_list, a_list) {
 			return inc;
@@ -529,7 +535,9 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static void ip_vs_app_seq_stop(struct seq_file *seq, void *v)
 {
-	mutex_unlock(&__ip_vs_app_mutex);
+	struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq));
+
+	mutex_unlock(&ipvs->app_mutex);
 }
 
 static int ip_vs_app_seq_show(struct seq_file *seq, void *v)
@@ -557,7 +565,8 @@ static const struct seq_operations ip_vs_app_seq_ops = {
 
 static int ip_vs_app_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_app_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_app_seq_ops,
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations ip_vs_app_fops = {
@@ -571,9 +580,13 @@ static const struct file_operations ip_vs_app_fops = {
 
 static int __net_init __ip_vs_app_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
+	INIT_LIST_HEAD(&ipvs->app_list);
+	__mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key);
 	proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
 	return 0;
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b38ae941f677..77b0036dcb73 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -414,14 +414,14 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
-	ret = register_ip_vs_app(app);
+	ret = register_ip_vs_app(net, app);
 	if (ret)
 		return ret;
 
 	for (i=0; i<IP_VS_APP_MAX_PORTS; i++) {
 		if (!ports[i])
 			continue;
-		ret = register_ip_vs_app_inc(app, app->protocol, ports[i]);
+		ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]);
 		if (ret)
 			break;
 		pr_info("%s: loaded support on port[%d] = %d\n",
@@ -429,7 +429,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	}
 
 	if (ret)
-		unregister_ip_vs_app(app);
+		unregister_ip_vs_app(net, app);
 
 	return ret;
 }
@@ -443,7 +443,7 @@ static void __ip_vs_ftp_exit(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
-	unregister_ip_vs_app(app);
+	unregister_ip_vs_app(net, app);
 }
 
 static struct pernet_operations ip_vs_ftp_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 0f14f793318a..569e77bf08c4 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1016,14 +1016,14 @@ static inline __u16 sctp_app_hashkey(__be16 port)
 		& SCTP_APP_TAB_MASK;
 }
 
-static int sctp_register_app(struct ip_vs_app *inc)
+static int sctp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
 
 	hash = sctp_app_hashkey(port);
 
@@ -1042,10 +1042,10 @@ out:
 	return ret;
 }
 
-static void sctp_unregister_app(struct ip_vs_app *inc)
+static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
 
 	spin_lock_bh(&ipvs->sctp_app_lock);
 	atomic_dec(&pd->appcnt);
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 290b3803d8ce..757aaaf083bb 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -577,14 +577,14 @@ static inline __u16 tcp_app_hashkey(__be16 port)
 }
 
 
-static int tcp_register_app(struct ip_vs_app *inc)
+static int tcp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
 
 	hash = tcp_app_hashkey(port);
 
@@ -605,10 +605,10 @@ static int tcp_register_app(struct ip_vs_app *inc)
 
 
 static void
-tcp_unregister_app(struct ip_vs_app *inc)
+tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
 
 	spin_lock_bh(&ipvs->tcp_app_lock);
 	atomic_dec(&pd->appcnt);
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 3719837a8fdc..1dc394100fa8 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -353,14 +353,14 @@ static inline __u16 udp_app_hashkey(__be16 port)
 }
 
 
-static int udp_register_app(struct ip_vs_app *inc)
+static int udp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
 
 	hash = udp_app_hashkey(port);
 
@@ -382,10 +382,10 @@ static int udp_register_app(struct ip_vs_app *inc)
 
 
 static void
-udp_unregister_app(struct ip_vs_app *inc)
+udp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	spin_lock_bh(&ipvs->udp_app_lock);
 	atomic_dec(&pd->appcnt);
-- 
cgit v1.2.3


From 29c2026fd4980c144d9c746dc1565060f08e5796 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:54 +0100
Subject: IPVS: netns awareness to ip_vs_est

All variables moved to struct ipvs,
most external changes fixed (i.e. init_net removed)

*v3
 timer per ns instead of a common timer in estimator.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  4 +-
 include/net/netns/ip_vs.h      |  4 ++
 net/netfilter/ipvs/ip_vs_ctl.c | 20 +++++-----
 net/netfilter/ipvs/ip_vs_est.c | 86 +++++++++++++++++++++++-------------------
 4 files changed, 64 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 0cdd8ce454c2..c08927bb1728 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1004,8 +1004,8 @@ extern void ip_vs_sync_cleanup(void);
  */
 extern int ip_vs_estimator_init(void);
 extern void ip_vs_estimator_cleanup(void);
-extern void ip_vs_new_estimator(struct ip_vs_stats *stats);
-extern void ip_vs_kill_estimator(struct ip_vs_stats *stats);
+extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
 extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 
 /*
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 03f7fe1bede6..db0240198339 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -70,6 +70,10 @@ struct netns_ipvs {
 	int			sysctl_lblcr_expiration;
 	struct ctl_table_header	*lblcr_ctl_header;
 	struct ctl_table	*lblcr_ctl_table;
+	/* ip_vs_est */
+	struct list_head	est_list;	/* estimator list */
+	spinlock_t		est_lock;
+	struct timer_list	est_timer;	/* Estimation timer */
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 88474f1e828a..c89beb8eafbb 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -816,7 +816,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	spin_unlock(&dest->dst_lock);
 
 	if (add)
-		ip_vs_new_estimator(&dest->stats);
+		ip_vs_new_estimator(svc->net, &dest->stats);
 
 	write_lock_bh(&__ip_vs_svc_lock);
 
@@ -1009,9 +1009,9 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 /*
  *	Delete a destination (must be already unlinked from the service)
  */
-static void __ip_vs_del_dest(struct ip_vs_dest *dest)
+static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 {
-	ip_vs_kill_estimator(&dest->stats);
+	ip_vs_kill_estimator(net, &dest->stats);
 
 	/*
 	 *  Remove it from the d-linked list with the real services.
@@ -1080,6 +1080,7 @@ static int
 ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 {
 	struct ip_vs_dest *dest;
+	struct net *net = svc->net;
 	__be16 dport = udest->port;
 
 	EnterFunction(2);
@@ -1108,7 +1109,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	/*
 	 *	Delete the destination
 	 */
-	__ip_vs_del_dest(dest);
+	__ip_vs_del_dest(net, dest);
 
 	LeaveFunction(2);
 
@@ -1197,7 +1198,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	else if (svc->port == 0)
 		atomic_inc(&ip_vs_nullsvc_counter);
 
-	ip_vs_new_estimator(&svc->stats);
+	ip_vs_new_estimator(net, &svc->stats);
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
@@ -1345,7 +1346,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	if (svc->af == AF_INET)
 		ip_vs_num_services--;
 
-	ip_vs_kill_estimator(&svc->stats);
+	ip_vs_kill_estimator(svc->net, &svc->stats);
 
 	/* Unbind scheduler */
 	old_sched = svc->scheduler;
@@ -1368,7 +1369,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	 */
 	list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
 		__ip_vs_unlink_dest(svc, dest, 0);
-		__ip_vs_del_dest(dest);
+		__ip_vs_del_dest(svc->net, dest);
 	}
 
 	/*
@@ -3460,7 +3461,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 						  vs_vars);
 	if (sysctl_header == NULL)
 		goto err_reg;
-	ip_vs_new_estimator(&ip_vs_stats);
+	ip_vs_new_estimator(net, &ip_vs_stats);
 	return 0;
 
 err_reg:
@@ -3472,7 +3473,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
-	ip_vs_kill_estimator(&ip_vs_stats);
+	ip_vs_kill_estimator(net, &ip_vs_stats);
 	unregister_net_sysctl_table(sysctl_header);
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
@@ -3536,7 +3537,6 @@ void ip_vs_control_cleanup(void)
 	ip_vs_trash_cleanup();
 	cancel_delayed_work_sync(&defense_work);
 	cancel_work_sync(&defense_work.work);
-	ip_vs_kill_estimator(&ip_vs_stats);
 	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 7417a0c1408b..07d839bef537 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -8,8 +8,12 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
- *
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
+ *              Network name space (netns) aware.
+ *              Global data moved to netns i.e struct netns_ipvs
+ *              Affected data: est_list and est_lock.
+ *              estimation_timer() runs with timer per netns.
+ *              get_stats()) do the per cpu summing.
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -48,12 +52,6 @@
  */
 
 
-static void estimation_timer(unsigned long arg);
-
-static LIST_HEAD(est_list);
-static DEFINE_SPINLOCK(est_lock);
-static DEFINE_TIMER(est_timer, estimation_timer, 0, 0);
-
 static void estimation_timer(unsigned long arg)
 {
 	struct ip_vs_estimator *e;
@@ -62,9 +60,12 @@ static void estimation_timer(unsigned long arg)
 	u32 n_inpkts, n_outpkts;
 	u64 n_inbytes, n_outbytes;
 	u32 rate;
+	struct net *net = (struct net *)arg;
+	struct netns_ipvs *ipvs;
 
-	spin_lock(&est_lock);
-	list_for_each_entry(e, &est_list, list) {
+	ipvs = net_ipvs(net);
+	spin_lock(&ipvs->est_lock);
+	list_for_each_entry(e, &ipvs->est_list, list) {
 		s = container_of(e, struct ip_vs_stats, est);
 
 		spin_lock(&s->lock);
@@ -75,38 +76,39 @@ static void estimation_timer(unsigned long arg)
 		n_outbytes = s->ustats.outbytes;
 
 		/* scaled by 2^10, but divided 2 seconds */
-		rate = (n_conns - e->last_conns)<<9;
+		rate = (n_conns - e->last_conns) << 9;
 		e->last_conns = n_conns;
-		e->cps += ((long)rate - (long)e->cps)>>2;
-		s->ustats.cps = (e->cps+0x1FF)>>10;
+		e->cps += ((long)rate - (long)e->cps) >> 2;
+		s->ustats.cps = (e->cps + 0x1FF) >> 10;
 
-		rate = (n_inpkts - e->last_inpkts)<<9;
+		rate = (n_inpkts - e->last_inpkts) << 9;
 		e->last_inpkts = n_inpkts;
-		e->inpps += ((long)rate - (long)e->inpps)>>2;
-		s->ustats.inpps = (e->inpps+0x1FF)>>10;
+		e->inpps += ((long)rate - (long)e->inpps) >> 2;
+		s->ustats.inpps = (e->inpps + 0x1FF) >> 10;
 
-		rate = (n_outpkts - e->last_outpkts)<<9;
+		rate = (n_outpkts - e->last_outpkts) << 9;
 		e->last_outpkts = n_outpkts;
-		e->outpps += ((long)rate - (long)e->outpps)>>2;
-		s->ustats.outpps = (e->outpps+0x1FF)>>10;
+		e->outpps += ((long)rate - (long)e->outpps) >> 2;
+		s->ustats.outpps = (e->outpps + 0x1FF) >> 10;
 
-		rate = (n_inbytes - e->last_inbytes)<<4;
+		rate = (n_inbytes - e->last_inbytes) << 4;
 		e->last_inbytes = n_inbytes;
-		e->inbps += ((long)rate - (long)e->inbps)>>2;
-		s->ustats.inbps = (e->inbps+0xF)>>5;
+		e->inbps += ((long)rate - (long)e->inbps) >> 2;
+		s->ustats.inbps = (e->inbps + 0xF) >> 5;
 
-		rate = (n_outbytes - e->last_outbytes)<<4;
+		rate = (n_outbytes - e->last_outbytes) << 4;
 		e->last_outbytes = n_outbytes;
-		e->outbps += ((long)rate - (long)e->outbps)>>2;
-		s->ustats.outbps = (e->outbps+0xF)>>5;
+		e->outbps += ((long)rate - (long)e->outbps) >> 2;
+		s->ustats.outbps = (e->outbps + 0xF) >> 5;
 		spin_unlock(&s->lock);
 	}
-	spin_unlock(&est_lock);
-	mod_timer(&est_timer, jiffies + 2*HZ);
+	spin_unlock(&ipvs->est_lock);
+	mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
 }
 
-void ip_vs_new_estimator(struct ip_vs_stats *stats)
+void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
 
 	INIT_LIST_HEAD(&est->list);
@@ -126,18 +128,19 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats)
 	est->last_outbytes = stats->ustats.outbytes;
 	est->outbps = stats->ustats.outbps<<5;
 
-	spin_lock_bh(&est_lock);
-	list_add(&est->list, &est_list);
-	spin_unlock_bh(&est_lock);
+	spin_lock_bh(&ipvs->est_lock);
+	list_add(&est->list, &ipvs->est_list);
+	spin_unlock_bh(&ipvs->est_lock);
 }
 
-void ip_vs_kill_estimator(struct ip_vs_stats *stats)
+void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
 
-	spin_lock_bh(&est_lock);
+	spin_lock_bh(&ipvs->est_lock);
 	list_del(&est->list);
-	spin_unlock_bh(&est_lock);
+	spin_unlock_bh(&ipvs->est_lock);
 }
 
 void ip_vs_zero_estimator(struct ip_vs_stats *stats)
@@ -159,14 +162,25 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 
 static int __net_init __ip_vs_estimator_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
+	INIT_LIST_HEAD(&ipvs->est_list);
+	spin_lock_init(&ipvs->est_lock);
+	setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net);
+	mod_timer(&ipvs->est_timer, jiffies + 2 * HZ);
 	return 0;
 }
 
+static void __net_exit __ip_vs_estimator_exit(struct net *net)
+{
+	del_timer_sync(&net_ipvs(net)->est_timer);
+}
 static struct pernet_operations ip_vs_app_ops = {
 	.init = __ip_vs_estimator_init,
+	.exit = __ip_vs_estimator_exit,
 };
 
 int __init ip_vs_estimator_init(void)
@@ -174,14 +188,10 @@ int __init ip_vs_estimator_init(void)
 	int rv;
 
 	rv = register_pernet_subsys(&ip_vs_app_ops);
-	if (rv < 0)
-		return rv;
-	mod_timer(&est_timer, jiffies + 2 * HZ);
 	return rv;
 }
 
 void ip_vs_estimator_cleanup(void)
 {
-	del_timer_sync(&est_timer);
 	unregister_pernet_subsys(&ip_vs_app_ops);
 }
-- 
cgit v1.2.3


From f131315fa272d337dfca7dad2f033ff5296dad65 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:55 +0100
Subject: IPVS: netns awareness to ip_vs_sync

All global variables moved to struct ipvs,
most external changes fixed (i.e. init_net removed)
in sync_buf create  + 4 replaced by sizeof(struct..)

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  14 +-
 include/net/netns/ip_vs.h       |  16 ++
 net/netfilter/ipvs/ip_vs_core.c |  15 +-
 net/netfilter/ipvs/ip_vs_ctl.c  |  52 ++++---
 net/netfilter/ipvs/ip_vs_sync.c | 334 +++++++++++++++++++++-------------------
 5 files changed, 240 insertions(+), 191 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index c08927bb1728..4265b5e00c94 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -958,7 +958,7 @@ extern struct ip_vs_stats ip_vs_stats;
 extern const struct ctl_path net_vs_ctl_path[];
 extern int sysctl_ip_vs_sync_ver;
 
-extern void ip_vs_sync_switch_mode(int mode);
+extern void ip_vs_sync_switch_mode(struct net *net, int mode);
 extern struct ip_vs_service *
 ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
@@ -987,14 +987,10 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
  *      IPVS sync daemon data and function prototypes
  *      (from ip_vs_sync.c)
  */
-extern volatile int ip_vs_sync_state;
-extern volatile int ip_vs_master_syncid;
-extern volatile int ip_vs_backup_syncid;
-extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
-extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
+			     __u8 syncid);
+extern int stop_sync_thread(struct net *net, int state);
+extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_sync_init(void);
 extern void ip_vs_sync_cleanup(void);
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index db0240198339..aba78f3c8341 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -74,6 +74,22 @@ struct netns_ipvs {
 	struct list_head	est_list;	/* estimator list */
 	spinlock_t		est_lock;
 	struct timer_list	est_timer;	/* Estimation timer */
+	/* ip_vs_sync */
+	struct list_head	sync_queue;
+	spinlock_t		sync_lock;
+	struct ip_vs_sync_buff  *sync_buff;
+	spinlock_t		sync_buff_lock;
+	struct sockaddr_in	sync_mcast_addr;
+	struct task_struct	*master_thread;
+	struct task_struct	*backup_thread;
+	int			send_mesg_maxlen;
+	int			recv_mesg_maxlen;
+	volatile int		sync_state;
+	volatile int		master_syncid;
+	volatile int		backup_syncid;
+	/* multicast interface name */
+	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 9317affc5ea1..5531d569aa5e 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1471,12 +1471,13 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 static unsigned int
 ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 {
-	struct net *net = NULL;
+	struct net *net;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, restart, pkts;
+	struct netns_ipvs *ipvs;
 
 	/* Already marked as IPVS request or reply? */
 	if (skb->ipvs_property)
@@ -1556,7 +1557,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
-
+	net = skb_net(skb);
+	ipvs = net_ipvs(net);
 	/* Check the server status */
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
@@ -1589,12 +1591,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 *
 	 * For ONE_PKT let ip_vs_sync_conn() do the filter work.
 	 */
+
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		pkts = sysctl_ip_vs_sync_threshold[0];
 	else
 		pkts = atomic_add_return(1, &cp->in_pkts);
 
-	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
 			(pkts % sysctl_ip_vs_sync_threshold[1]
@@ -1603,13 +1606,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) {
-			ip_vs_sync_conn(cp);
+			ip_vs_sync_conn(net, cp);
 			goto out;
 		}
 	}
 
 	/* Keep this block last: TCP and others with pp->num_states <= 1 */
-	else if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
 	      (pkts % sysctl_ip_vs_sync_threshold[1]
@@ -1619,7 +1622,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	       (cp->state == IP_VS_TCP_S_CLOSE) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_TIME_WAIT)))))
-		ip_vs_sync_conn(cp);
+		ip_vs_sync_conn(net, cp);
 out:
 	cp->old_state = cp->state;
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c89beb8eafbb..03f86312b4bb 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1559,7 +1559,8 @@ proc_do_sync_mode(ctl_table *table, int write,
 			/* Restore the correct value */
 			*valp = val;
 		} else {
-			ip_vs_sync_switch_mode(val);
+			struct net *net = current->nsproxy->net_ns;
+			ip_vs_sync_switch_mode(net, val);
 		}
 	}
 	return rc;
@@ -2174,11 +2175,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_STARTDAEMON) {
 		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
-		ret = start_sync_thread(dm->state, dm->mcast_ifn, dm->syncid);
+		ret = start_sync_thread(net, dm->state, dm->mcast_ifn,
+					dm->syncid);
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_STOPDAEMON) {
 		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
-		ret = stop_sync_thread(dm->state);
+		ret = stop_sync_thread(net, dm->state);
 		goto out_unlock;
 	}
 
@@ -2424,6 +2426,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	int ret = 0;
 	unsigned int copylen;
 	struct net *net = sock_net(sk);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	BUG_ON(!net);
 	if (!capable(CAP_NET_ADMIN))
@@ -2546,15 +2549,17 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		struct ip_vs_daemon_user d[2];
 
 		memset(&d, 0, sizeof(d));
-		if (ip_vs_sync_state & IP_VS_STATE_MASTER) {
+		if (ipvs->sync_state & IP_VS_STATE_MASTER) {
 			d[0].state = IP_VS_STATE_MASTER;
-			strlcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn, sizeof(d[0].mcast_ifn));
-			d[0].syncid = ip_vs_master_syncid;
+			strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn,
+				sizeof(d[0].mcast_ifn));
+			d[0].syncid = ipvs->master_syncid;
 		}
-		if (ip_vs_sync_state & IP_VS_STATE_BACKUP) {
+		if (ipvs->sync_state & IP_VS_STATE_BACKUP) {
 			d[1].state = IP_VS_STATE_BACKUP;
-			strlcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn, sizeof(d[1].mcast_ifn));
-			d[1].syncid = ip_vs_backup_syncid;
+			strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn,
+				sizeof(d[1].mcast_ifn));
+			d[1].syncid = ipvs->backup_syncid;
 		}
 		if (copy_to_user(user, &d, sizeof(d)) != 0)
 			ret = -EFAULT;
@@ -3061,20 +3066,23 @@ nla_put_failure:
 static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
 				   struct netlink_callback *cb)
 {
+	struct net *net = skb_net(skb);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	mutex_lock(&__ip_vs_mutex);
-	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) {
+	if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) {
 		if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER,
-					   ip_vs_master_mcast_ifn,
-					   ip_vs_master_syncid, cb) < 0)
+					   ipvs->master_mcast_ifn,
+					   ipvs->master_syncid, cb) < 0)
 			goto nla_put_failure;
 
 		cb->args[0] = 1;
 	}
 
-	if ((ip_vs_sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) {
+	if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) {
 		if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP,
-					   ip_vs_backup_mcast_ifn,
-					   ip_vs_backup_syncid, cb) < 0)
+					   ipvs->backup_mcast_ifn,
+					   ipvs->backup_syncid, cb) < 0)
 			goto nla_put_failure;
 
 		cb->args[1] = 1;
@@ -3086,24 +3094,26 @@ nla_put_failure:
 	return skb->len;
 }
 
-static int ip_vs_genl_new_daemon(struct nlattr **attrs)
+static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs)
 {
 	if (!(attrs[IPVS_DAEMON_ATTR_STATE] &&
 	      attrs[IPVS_DAEMON_ATTR_MCAST_IFN] &&
 	      attrs[IPVS_DAEMON_ATTR_SYNC_ID]))
 		return -EINVAL;
 
-	return start_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]),
+	return start_sync_thread(net,
+				 nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]),
 				 nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]),
 				 nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID]));
 }
 
-static int ip_vs_genl_del_daemon(struct nlattr **attrs)
+static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs)
 {
 	if (!attrs[IPVS_DAEMON_ATTR_STATE])
 		return -EINVAL;
 
-	return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
+	return stop_sync_thread(net,
+				nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
 }
 
 static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
@@ -3159,9 +3169,9 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		if (cmd == IPVS_CMD_NEW_DAEMON)
-			ret = ip_vs_genl_new_daemon(daemon_attrs);
+			ret = ip_vs_genl_new_daemon(net, daemon_attrs);
 		else
-			ret = ip_vs_genl_del_daemon(daemon_attrs);
+			ret = ip_vs_genl_del_daemon(net, daemon_attrs);
 		goto out;
 	} else if (cmd == IPVS_CMD_ZERO &&
 		   !info->attrs[IPVS_CMD_ATTR_SERVICE]) {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 6831e8fac8db..c29e73d686fb 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -192,6 +192,7 @@ union ip_vs_sync_conn {
 #define IPVS_OPT_F_PARAM	(1 << (IPVS_OPT_PARAM-1))
 
 struct ip_vs_sync_thread_data {
+	struct net *net;
 	struct socket *sock;
 	char *buf;
 };
@@ -259,10 +260,6 @@ struct ip_vs_sync_mesg {
 	/* ip_vs_sync_conn entries start here */
 };
 
-/* the maximum length of sync (sending/receiving) message */
-static int sync_send_mesg_maxlen;
-static int sync_recv_mesg_maxlen;
-
 struct ip_vs_sync_buff {
 	struct list_head        list;
 	unsigned long           firstuse;
@@ -273,28 +270,6 @@ struct ip_vs_sync_buff {
 	unsigned char           *end;
 };
 
-
-/* the sync_buff list head and the lock */
-static LIST_HEAD(ip_vs_sync_queue);
-static DEFINE_SPINLOCK(ip_vs_sync_lock);
-
-/* current sync_buff for accepting new conn entries */
-static struct ip_vs_sync_buff   *curr_sb = NULL;
-static DEFINE_SPINLOCK(curr_sb_lock);
-
-/* ipvs sync daemon state */
-volatile int ip_vs_sync_state = IP_VS_STATE_NONE;
-volatile int ip_vs_master_syncid = 0;
-volatile int ip_vs_backup_syncid = 0;
-
-/* multicast interface name */
-char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-
-/* sync daemon tasks */
-static struct task_struct *sync_master_thread;
-static struct task_struct *sync_backup_thread;
-
 /* multicast addr */
 static struct sockaddr_in mcast_addr = {
 	.sin_family		= AF_INET,
@@ -324,20 +299,20 @@ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no)
 	put_unaligned_be32(ho->previous_delta, &no->previous_delta);
 }
 
-static inline struct ip_vs_sync_buff *sb_dequeue(void)
+static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs)
 {
 	struct ip_vs_sync_buff *sb;
 
-	spin_lock_bh(&ip_vs_sync_lock);
-	if (list_empty(&ip_vs_sync_queue)) {
+	spin_lock_bh(&ipvs->sync_lock);
+	if (list_empty(&ipvs->sync_queue)) {
 		sb = NULL;
 	} else {
-		sb = list_entry(ip_vs_sync_queue.next,
+		sb = list_entry(ipvs->sync_queue.next,
 				struct ip_vs_sync_buff,
 				list);
 		list_del(&sb->list);
 	}
-	spin_unlock_bh(&ip_vs_sync_lock);
+	spin_unlock_bh(&ipvs->sync_lock);
 
 	return sb;
 }
@@ -345,25 +320,27 @@ static inline struct ip_vs_sync_buff *sb_dequeue(void)
 /*
  * Create a new sync buffer for Version 1 proto.
  */
-static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
+static inline struct ip_vs_sync_buff *
+ip_vs_sync_buff_create(struct netns_ipvs *ipvs)
 {
 	struct ip_vs_sync_buff *sb;
 
 	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
 		return NULL;
 
-	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
+	sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC);
+	if (!sb->mesg) {
 		kfree(sb);
 		return NULL;
 	}
 	sb->mesg->reserved = 0;  /* old nr_conns i.e. must be zeo now */
 	sb->mesg->version = SYNC_PROTO_VER;
-	sb->mesg->syncid = ip_vs_master_syncid;
+	sb->mesg->syncid = ipvs->master_syncid;
 	sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
 	sb->mesg->nr_conns = 0;
 	sb->mesg->spare = 0;
 	sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg);
-	sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen;
+	sb->end = (unsigned char *)sb->mesg + ipvs->send_mesg_maxlen;
 
 	sb->firstuse = jiffies;
 	return sb;
@@ -375,14 +352,16 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb)
 	kfree(sb);
 }
 
-static inline void sb_queue_tail(struct ip_vs_sync_buff *sb)
+static inline void sb_queue_tail(struct netns_ipvs *ipvs)
 {
-	spin_lock(&ip_vs_sync_lock);
-	if (ip_vs_sync_state & IP_VS_STATE_MASTER)
-		list_add_tail(&sb->list, &ip_vs_sync_queue);
+	struct ip_vs_sync_buff *sb = ipvs->sync_buff;
+
+	spin_lock(&ipvs->sync_lock);
+	if (ipvs->sync_state & IP_VS_STATE_MASTER)
+		list_add_tail(&sb->list, &ipvs->sync_queue);
 	else
 		ip_vs_sync_buff_release(sb);
-	spin_unlock(&ip_vs_sync_lock);
+	spin_unlock(&ipvs->sync_lock);
 }
 
 /*
@@ -390,18 +369,18 @@ static inline void sb_queue_tail(struct ip_vs_sync_buff *sb)
  *	than the specified time or the specified time is zero.
  */
 static inline struct ip_vs_sync_buff *
-get_curr_sync_buff(unsigned long time)
+get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
 {
 	struct ip_vs_sync_buff *sb;
 
-	spin_lock_bh(&curr_sb_lock);
-	if (curr_sb && (time == 0 ||
-			time_before(jiffies - curr_sb->firstuse, time))) {
-		sb = curr_sb;
-		curr_sb = NULL;
+	spin_lock_bh(&ipvs->sync_buff_lock);
+	if (ipvs->sync_buff && (time == 0 ||
+	    time_before(jiffies - ipvs->sync_buff->firstuse, time))) {
+		sb = ipvs->sync_buff;
+		ipvs->sync_buff = NULL;
 	} else
 		sb = NULL;
-	spin_unlock_bh(&curr_sb_lock);
+	spin_unlock_bh(&ipvs->sync_buff_lock);
 	return sb;
 }
 
@@ -409,33 +388,37 @@ get_curr_sync_buff(unsigned long time)
  * Switch mode from sending version 0 or 1
  *  - must handle sync_buf
  */
-void ip_vs_sync_switch_mode(int mode) {
+void ip_vs_sync_switch_mode(struct net *net, int mode)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!ip_vs_sync_state & IP_VS_STATE_MASTER)
+	if (!ipvs->sync_state & IP_VS_STATE_MASTER)
 		return;
-	if (mode == sysctl_ip_vs_sync_ver || !curr_sb)
+	if (mode == sysctl_ip_vs_sync_ver || !ipvs->sync_buff)
 		return;
 
-	spin_lock_bh(&curr_sb_lock);
+	spin_lock_bh(&ipvs->sync_buff_lock);
 	/* Buffer empty ? then let buf_create do the job  */
-	if ( curr_sb->mesg->size <=  sizeof(struct ip_vs_sync_mesg)) {
-		kfree(curr_sb);
-		curr_sb = NULL;
+	if (ipvs->sync_buff->mesg->size <=  sizeof(struct ip_vs_sync_mesg)) {
+		kfree(ipvs->sync_buff);
+		ipvs->sync_buff = NULL;
 	} else {
-		spin_lock_bh(&ip_vs_sync_lock);
-		if (ip_vs_sync_state & IP_VS_STATE_MASTER)
-			list_add_tail(&curr_sb->list, &ip_vs_sync_queue);
+		spin_lock_bh(&ipvs->sync_lock);
+		if (ipvs->sync_state & IP_VS_STATE_MASTER)
+			list_add_tail(&ipvs->sync_buff->list,
+				      &ipvs->sync_queue);
 		else
-			ip_vs_sync_buff_release(curr_sb);
-		spin_unlock_bh(&ip_vs_sync_lock);
+			ip_vs_sync_buff_release(ipvs->sync_buff);
+		spin_unlock_bh(&ipvs->sync_lock);
 	}
-	spin_unlock_bh(&curr_sb_lock);
+	spin_unlock_bh(&ipvs->sync_buff_lock);
 }
 
 /*
  * Create a new sync buffer for Version 0 proto.
  */
-static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
+static inline struct ip_vs_sync_buff *
+ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs)
 {
 	struct ip_vs_sync_buff *sb;
 	struct ip_vs_sync_mesg_v0 *mesg;
@@ -443,16 +426,17 @@ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
 	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
 		return NULL;
 
-	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
+	sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC);
+	if (!sb->mesg) {
 		kfree(sb);
 		return NULL;
 	}
 	mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg;
 	mesg->nr_conns = 0;
-	mesg->syncid = ip_vs_master_syncid;
-	mesg->size = 4;
-	sb->head = (unsigned char *)mesg + 4;
-	sb->end = (unsigned char *)mesg + sync_send_mesg_maxlen;
+	mesg->syncid = ipvs->master_syncid;
+	mesg->size = sizeof(struct ip_vs_sync_mesg_v0);
+	sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0);
+	sb->end = (unsigned char *)mesg + ipvs->send_mesg_maxlen;
 	sb->firstuse = jiffies;
 	return sb;
 }
@@ -461,8 +445,9 @@ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
  *      Version 0 , could be switched in by sys_ctl.
  *      Add an ip_vs_conn information into the current sync_buff.
  */
-void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
+void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_sync_mesg_v0 *m;
 	struct ip_vs_sync_conn_v0 *s;
 	int len;
@@ -473,10 +458,12 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		return;
 
-	spin_lock(&curr_sb_lock);
-	if (!curr_sb) {
-		if (!(curr_sb=ip_vs_sync_buff_create_v0())) {
-			spin_unlock(&curr_sb_lock);
+	spin_lock(&ipvs->sync_buff_lock);
+	if (!ipvs->sync_buff) {
+		ipvs->sync_buff =
+			ip_vs_sync_buff_create_v0(ipvs);
+		if (!ipvs->sync_buff) {
+			spin_unlock(&ipvs->sync_buff_lock);
 			pr_err("ip_vs_sync_buff_create failed.\n");
 			return;
 		}
@@ -484,8 +471,8 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
 
 	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
 		SIMPLE_CONN_SIZE;
-	m = (struct ip_vs_sync_mesg_v0 *)curr_sb->mesg;
-	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
+	m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg;
+	s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head;
 
 	/* copy members */
 	s->reserved = 0;
@@ -506,18 +493,18 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
 
 	m->nr_conns++;
 	m->size += len;
-	curr_sb->head += len;
+	ipvs->sync_buff->head += len;
 
 	/* check if there is a space for next one */
-	if (curr_sb->head + FULL_CONN_SIZE > curr_sb->end) {
-		sb_queue_tail(curr_sb);
-		curr_sb = NULL;
+	if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) {
+		sb_queue_tail(ipvs);
+		ipvs->sync_buff = NULL;
 	}
-	spin_unlock(&curr_sb_lock);
+	spin_unlock(&ipvs->sync_buff_lock);
 
 	/* synchronize its controller if it has */
 	if (cp->control)
-		ip_vs_sync_conn(cp->control);
+		ip_vs_sync_conn(net, cp->control);
 }
 
 /*
@@ -525,8 +512,9 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
  *      Called by ip_vs_in.
  *      Sending Version 1 messages
  */
-void ip_vs_sync_conn(struct ip_vs_conn *cp)
+void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_sync_mesg *m;
 	union ip_vs_sync_conn *s;
 	__u8 *p;
@@ -534,7 +522,7 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp)
 
 	/* Handle old version of the protocol */
 	if (sysctl_ip_vs_sync_ver == 0) {
-		ip_vs_sync_conn_v0(cp);
+		ip_vs_sync_conn_v0(net, cp);
 		return;
 	}
 	/* Do not sync ONE PACKET */
@@ -551,7 +539,7 @@ sloop:
 		pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN);
 	}
 
-	spin_lock(&curr_sb_lock);
+	spin_lock(&ipvs->sync_buff_lock);
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6)
@@ -570,26 +558,27 @@ sloop:
 
 	/* check if there is a space for this one  */
 	pad = 0;
-	if (curr_sb) {
-		pad = (4 - (size_t)curr_sb->head) & 3;
-		if (curr_sb->head + len + pad > curr_sb->end) {
-			sb_queue_tail(curr_sb);
-			curr_sb = NULL;
+	if (ipvs->sync_buff) {
+		pad = (4 - (size_t)ipvs->sync_buff->head) & 3;
+		if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) {
+			sb_queue_tail(ipvs);
+			ipvs->sync_buff = NULL;
 			pad = 0;
 		}
 	}
 
-	if (!curr_sb) {
-		if (!(curr_sb=ip_vs_sync_buff_create())) {
-			spin_unlock(&curr_sb_lock);
+	if (!ipvs->sync_buff) {
+		ipvs->sync_buff = ip_vs_sync_buff_create(ipvs);
+		if (!ipvs->sync_buff) {
+			spin_unlock(&ipvs->sync_buff_lock);
 			pr_err("ip_vs_sync_buff_create failed.\n");
 			return;
 		}
 	}
 
-	m = curr_sb->mesg;
-	p = curr_sb->head;
-	curr_sb->head += pad + len;
+	m = ipvs->sync_buff->mesg;
+	p = ipvs->sync_buff->head;
+	ipvs->sync_buff->head += pad + len;
 	m->size += pad + len;
 	/* Add ev. padding from prev. sync_conn */
 	while (pad--)
@@ -647,7 +636,7 @@ sloop:
 		}
 	}
 
-	spin_unlock(&curr_sb_lock);
+	spin_unlock(&ipvs->sync_buff_lock);
 
 control:
 	/* synchronize its controller if it has */
@@ -699,7 +688,8 @@ ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
 			buff[pe_name_len]=0;
 			p->pe = __ip_vs_pe_getbyname(buff);
 			if (!p->pe) {
-				IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", buff);
+				IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n",
+					     buff);
 				return 1;
 			}
 		} else {
@@ -748,7 +738,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 		 * If it is not found the connection will remain unbound
 		 * but still handled.
 		 */
-		dest = ip_vs_find_dest(&init_net, type, daddr, dport, param->vaddr,
+		dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
 				       param->vport, protocol, fwmark);
 
 		/*  Set the approprite ativity flag */
@@ -1089,6 +1079,7 @@ out:
 static void ip_vs_process_message(struct net *net, __u8 *buffer,
 				  const size_t buflen)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
 	__u8 *p, *msg_end;
 	int i, nr_conns;
@@ -1105,7 +1096,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer,
 		return;
 	}
 	/* SyncID sanity check */
-	if (ip_vs_backup_syncid != 0 && m2->syncid != ip_vs_backup_syncid) {
+	if (ipvs->backup_syncid != 0 && m2->syncid != ipvs->backup_syncid) {
 		IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid);
 		return;
 	}
@@ -1190,8 +1181,10 @@ static int set_mcast_if(struct sock *sk, char *ifname)
 {
 	struct net_device *dev;
 	struct inet_sock *inet = inet_sk(sk);
+	struct net *net = sock_net(sk);
 
-	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
+	dev = __dev_get_by_name(net, ifname);
+	if (!dev)
 		return -ENODEV;
 
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
@@ -1210,30 +1203,33 @@ static int set_mcast_if(struct sock *sk, char *ifname)
  *	Set the maximum length of sync message according to the
  *	specified interface's MTU.
  */
-static int set_sync_mesg_maxlen(int sync_state)
+static int set_sync_mesg_maxlen(struct net *net, int sync_state)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct net_device *dev;
 	int num;
 
 	if (sync_state == IP_VS_STATE_MASTER) {
-		if ((dev = __dev_get_by_name(&init_net, ip_vs_master_mcast_ifn)) == NULL)
+		dev = __dev_get_by_name(net, ipvs->master_mcast_ifn);
+		if (!dev)
 			return -ENODEV;
 
 		num = (dev->mtu - sizeof(struct iphdr) -
 		       sizeof(struct udphdr) -
 		       SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE;
-		sync_send_mesg_maxlen = SYNC_MESG_HEADER_LEN +
+		ipvs->send_mesg_maxlen = SYNC_MESG_HEADER_LEN +
 			SIMPLE_CONN_SIZE * min(num, MAX_CONNS_PER_SYNCBUFF);
 		IP_VS_DBG(7, "setting the maximum length of sync sending "
-			  "message %d.\n", sync_send_mesg_maxlen);
+			  "message %d.\n", ipvs->send_mesg_maxlen);
 	} else if (sync_state == IP_VS_STATE_BACKUP) {
-		if ((dev = __dev_get_by_name(&init_net, ip_vs_backup_mcast_ifn)) == NULL)
+		dev = __dev_get_by_name(net, ipvs->backup_mcast_ifn);
+		if (!dev)
 			return -ENODEV;
 
-		sync_recv_mesg_maxlen = dev->mtu -
+		ipvs->recv_mesg_maxlen = dev->mtu -
 			sizeof(struct iphdr) - sizeof(struct udphdr);
 		IP_VS_DBG(7, "setting the maximum length of sync receiving "
-			  "message %d.\n", sync_recv_mesg_maxlen);
+			  "message %d.\n", ipvs->recv_mesg_maxlen);
 	}
 
 	return 0;
@@ -1248,6 +1244,7 @@ static int set_sync_mesg_maxlen(int sync_state)
 static int
 join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 {
+	struct net *net = sock_net(sk);
 	struct ip_mreqn mreq;
 	struct net_device *dev;
 	int ret;
@@ -1255,7 +1252,8 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 	memset(&mreq, 0, sizeof(mreq));
 	memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
 
-	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
+	dev = __dev_get_by_name(net, ifname);
+	if (!dev)
 		return -ENODEV;
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
@@ -1272,11 +1270,13 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 
 static int bind_mcastif_addr(struct socket *sock, char *ifname)
 {
+	struct net *net = sock_net(sock->sk);
 	struct net_device *dev;
 	__be32 addr;
 	struct sockaddr_in sin;
 
-	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
+	dev = __dev_get_by_name(net, ifname);
+	if (!dev)
 		return -ENODEV;
 
 	addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
@@ -1298,8 +1298,9 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname)
 /*
  *      Set up sending multicast socket over UDP
  */
-static struct socket * make_send_sock(void)
+static struct socket *make_send_sock(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct socket *sock;
 	int result;
 
@@ -1310,7 +1311,7 @@ static struct socket * make_send_sock(void)
 		return ERR_PTR(result);
 	}
 
-	result = set_mcast_if(sock->sk, ip_vs_master_mcast_ifn);
+	result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error setting outbound mcast interface\n");
 		goto error;
@@ -1319,7 +1320,7 @@ static struct socket * make_send_sock(void)
 	set_mcast_loop(sock->sk, 0);
 	set_mcast_ttl(sock->sk, 1);
 
-	result = bind_mcastif_addr(sock, ip_vs_master_mcast_ifn);
+	result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error binding address of the mcast interface\n");
 		goto error;
@@ -1343,8 +1344,9 @@ static struct socket * make_send_sock(void)
 /*
  *      Set up receiving multicast socket over UDP
  */
-static struct socket * make_receive_sock(void)
+static struct socket *make_receive_sock(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct socket *sock;
 	int result;
 
@@ -1368,7 +1370,7 @@ static struct socket * make_receive_sock(void)
 	/* join the multicast group */
 	result = join_mcast_group(sock->sk,
 			(struct in_addr *) &mcast_addr.sin_addr,
-			ip_vs_backup_mcast_ifn);
+			ipvs->backup_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error joining to the multicast group\n");
 		goto error;
@@ -1439,20 +1441,21 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
 static int sync_thread_master(void *data)
 {
 	struct ip_vs_sync_thread_data *tinfo = data;
+	struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
 	struct ip_vs_sync_buff *sb;
 
 	pr_info("sync thread started: state = MASTER, mcast_ifn = %s, "
 		"syncid = %d\n",
-		ip_vs_master_mcast_ifn, ip_vs_master_syncid);
+		ipvs->master_mcast_ifn, ipvs->master_syncid);
 
 	while (!kthread_should_stop()) {
-		while ((sb = sb_dequeue())) {
+		while ((sb = sb_dequeue(ipvs))) {
 			ip_vs_send_sync_msg(tinfo->sock, sb->mesg);
 			ip_vs_sync_buff_release(sb);
 		}
 
-		/* check if entries stay in curr_sb for 2 seconds */
-		sb = get_curr_sync_buff(2 * HZ);
+		/* check if entries stay in ipvs->sync_buff for 2 seconds */
+		sb = get_curr_sync_buff(ipvs, 2 * HZ);
 		if (sb) {
 			ip_vs_send_sync_msg(tinfo->sock, sb->mesg);
 			ip_vs_sync_buff_release(sb);
@@ -1462,14 +1465,13 @@ static int sync_thread_master(void *data)
 	}
 
 	/* clean up the sync_buff queue */
-	while ((sb=sb_dequeue())) {
+	while ((sb = sb_dequeue(ipvs)))
 		ip_vs_sync_buff_release(sb);
-	}
 
 	/* clean up the current sync_buff */
-	if ((sb = get_curr_sync_buff(0))) {
+	sb = get_curr_sync_buff(ipvs, 0);
+	if (sb)
 		ip_vs_sync_buff_release(sb);
-	}
 
 	/* release the sending multicast socket */
 	sock_release(tinfo->sock);
@@ -1482,11 +1484,12 @@ static int sync_thread_master(void *data)
 static int sync_thread_backup(void *data)
 {
 	struct ip_vs_sync_thread_data *tinfo = data;
+	struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
 	int len;
 
 	pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
 		"syncid = %d\n",
-		ip_vs_backup_mcast_ifn, ip_vs_backup_syncid);
+		ipvs->backup_mcast_ifn, ipvs->backup_syncid);
 
 	while (!kthread_should_stop()) {
 		wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
@@ -1496,7 +1499,7 @@ static int sync_thread_backup(void *data)
 		/* do we have data now? */
 		while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) {
 			len = ip_vs_receive(tinfo->sock, tinfo->buf,
-					sync_recv_mesg_maxlen);
+					ipvs->recv_mesg_maxlen);
 			if (len <= 0) {
 				pr_err("receiving message error\n");
 				break;
@@ -1505,7 +1508,7 @@ static int sync_thread_backup(void *data)
 			/* disable bottom half, because it accesses the data
 			   shared by softirq while getting/creating conns */
 			local_bh_disable();
-			ip_vs_process_message(&init_net, tinfo->buf, len);
+			ip_vs_process_message(tinfo->net, tinfo->buf, len);
 			local_bh_enable();
 		}
 	}
@@ -1519,11 +1522,12 @@ static int sync_thread_backup(void *data)
 }
 
 
-int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
+int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
 {
 	struct ip_vs_sync_thread_data *tinfo;
 	struct task_struct **realtask, *task;
 	struct socket *sock;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	char *name, *buf = NULL;
 	int (*threadfn)(void *data);
 	int result = -ENOMEM;
@@ -1533,27 +1537,27 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 		  sizeof(struct ip_vs_sync_conn_v0));
 
 	if (state == IP_VS_STATE_MASTER) {
-		if (sync_master_thread)
+		if (ipvs->master_thread)
 			return -EEXIST;
 
-		strlcpy(ip_vs_master_mcast_ifn, mcast_ifn,
-			sizeof(ip_vs_master_mcast_ifn));
-		ip_vs_master_syncid = syncid;
-		realtask = &sync_master_thread;
-		name = "ipvs_syncmaster";
+		strlcpy(ipvs->master_mcast_ifn, mcast_ifn,
+			sizeof(ipvs->master_mcast_ifn));
+		ipvs->master_syncid = syncid;
+		realtask = &ipvs->master_thread;
+		name = "ipvs_master:%d";
 		threadfn = sync_thread_master;
-		sock = make_send_sock();
+		sock = make_send_sock(net);
 	} else if (state == IP_VS_STATE_BACKUP) {
-		if (sync_backup_thread)
+		if (ipvs->backup_thread)
 			return -EEXIST;
 
-		strlcpy(ip_vs_backup_mcast_ifn, mcast_ifn,
-			sizeof(ip_vs_backup_mcast_ifn));
-		ip_vs_backup_syncid = syncid;
-		realtask = &sync_backup_thread;
-		name = "ipvs_syncbackup";
+		strlcpy(ipvs->backup_mcast_ifn, mcast_ifn,
+			sizeof(ipvs->backup_mcast_ifn));
+		ipvs->backup_syncid = syncid;
+		realtask = &ipvs->backup_thread;
+		name = "ipvs_backup:%d";
 		threadfn = sync_thread_backup;
-		sock = make_receive_sock();
+		sock = make_receive_sock(net);
 	} else {
 		return -EINVAL;
 	}
@@ -1563,9 +1567,9 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 		goto out;
 	}
 
-	set_sync_mesg_maxlen(state);
+	set_sync_mesg_maxlen(net, state);
 	if (state == IP_VS_STATE_BACKUP) {
-		buf = kmalloc(sync_recv_mesg_maxlen, GFP_KERNEL);
+		buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL);
 		if (!buf)
 			goto outsocket;
 	}
@@ -1574,10 +1578,11 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 	if (!tinfo)
 		goto outbuf;
 
+	tinfo->net = net;
 	tinfo->sock = sock;
 	tinfo->buf = buf;
 
-	task = kthread_run(threadfn, tinfo, name);
+	task = kthread_run(threadfn, tinfo, name, ipvs->gen);
 	if (IS_ERR(task)) {
 		result = PTR_ERR(task);
 		goto outtinfo;
@@ -1585,7 +1590,7 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 
 	/* mark as active */
 	*realtask = task;
-	ip_vs_sync_state |= state;
+	ipvs->sync_state |= state;
 
 	/* increase the module use count */
 	ip_vs_use_count_inc();
@@ -1603,16 +1608,18 @@ out:
 }
 
 
-int stop_sync_thread(int state)
+int stop_sync_thread(struct net *net, int state)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
 
 	if (state == IP_VS_STATE_MASTER) {
-		if (!sync_master_thread)
+		if (!ipvs->master_thread)
 			return -ESRCH;
 
 		pr_info("stopping master sync thread %d ...\n",
-			task_pid_nr(sync_master_thread));
+			task_pid_nr(ipvs->master_thread));
 
 		/*
 		 * The lock synchronizes with sb_queue_tail(), so that we don't
@@ -1620,21 +1627,21 @@ int stop_sync_thread(int state)
 		 * progress of stopping the master sync daemon.
 		 */
 
-		spin_lock_bh(&ip_vs_sync_lock);
-		ip_vs_sync_state &= ~IP_VS_STATE_MASTER;
-		spin_unlock_bh(&ip_vs_sync_lock);
-		kthread_stop(sync_master_thread);
-		sync_master_thread = NULL;
+		spin_lock_bh(&ipvs->sync_lock);
+		ipvs->sync_state &= ~IP_VS_STATE_MASTER;
+		spin_unlock_bh(&ipvs->sync_lock);
+		kthread_stop(ipvs->master_thread);
+		ipvs->master_thread = NULL;
 	} else if (state == IP_VS_STATE_BACKUP) {
-		if (!sync_backup_thread)
+		if (!ipvs->backup_thread)
 			return -ESRCH;
 
 		pr_info("stopping backup sync thread %d ...\n",
-			task_pid_nr(sync_backup_thread));
+			task_pid_nr(ipvs->backup_thread));
 
-		ip_vs_sync_state &= ~IP_VS_STATE_BACKUP;
-		kthread_stop(sync_backup_thread);
-		sync_backup_thread = NULL;
+		ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
+		kthread_stop(ipvs->backup_thread);
+		ipvs->backup_thread = NULL;
 	} else {
 		return -EINVAL;
 	}
@@ -1650,12 +1657,29 @@ int stop_sync_thread(int state)
  */
 static int __net_init __ip_vs_sync_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	INIT_LIST_HEAD(&ipvs->sync_queue);
+	spin_lock_init(&ipvs->sync_lock);
+	spin_lock_init(&ipvs->sync_buff_lock);
+
+	ipvs->sync_mcast_addr.sin_family = AF_INET;
+	ipvs->sync_mcast_addr.sin_port = cpu_to_be16(IP_VS_SYNC_PORT);
+	ipvs->sync_mcast_addr.sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP);
 	return 0;
 }
 
 static void __ip_vs_sync_cleanup(struct net *net)
 {
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+	stop_sync_thread(net, IP_VS_STATE_MASTER);
+	stop_sync_thread(net, IP_VS_STATE_BACKUP);
 }
+
 static struct pernet_operations ipvs_sync_ops = {
 	.init = __ip_vs_sync_init,
 	.exit = __ip_vs_sync_cleanup,
-- 
cgit v1.2.3


From b17fc9963f837ef1acfe36e193108fb16ed58647 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:56 +0100
Subject: IPVS: netns, ip_vs_stats and its procfs

The statistic counter locks for every packet are now removed,
and that statistic is now per CPU, i.e. no locks needed.
However summing is made in ip_vs_est into ip_vs_stats struct
which is moved to ipvs struc.

procfs, ip_vs_stats now have a "per cpu" count and a grand total.
A new function seq_file_single_net() in ip_vs.h created for handling of
single_open_net() since it does not place net ptr in a struct, like others.

/var/lib/lxc # cat /proc/net/ip_vs_stats_percpu
       Total Incoming Outgoing         Incoming         Outgoing
CPU    Conns  Packets  Packets            Bytes            Bytes
  0        0        3        1               9D               34
  1        0        1        2               49               70
  2        0        1        2               34               76
  3        1        2        2               70               74
  ~        1        7        7              18A              18E

     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s
           0        0        0                0                0

*v3
ip_vs_stats reamains as before, instead ip_vs_stats_percpu is added.
u64 seq lock added

*v4
Bug correction inbytes and outbytes as own vars..
per_cpu counter for all stats now as suggested by Julian.

[horms@verge.net.au: removed whitespace-change-only hunk]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  51 ++++++++++++++-
 include/net/netns/ip_vs.h       |   4 ++
 net/netfilter/ipvs/ip_vs_core.c |  89 ++++++++++++++------------
 net/netfilter/ipvs/ip_vs_ctl.c  | 134 ++++++++++++++++++++++++++++++++++------
 net/netfilter/ipvs/ip_vs_est.c  |  39 ++++++++++++
 5 files changed, 256 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4265b5e00c94..605d5db81a39 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -90,6 +90,18 @@ static inline struct net *skb_sknet(struct sk_buff *skb)
 	return &init_net;
 #endif
 }
+/*
+ * This one needed for single_open_net since net is stored directly in
+ * private not as a struct i.e. seq_file_net cant be used.
+ */
+static inline struct net *seq_file_single_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+	return (struct net *)seq->private;
+#else
+	return &init_net;
+#endif
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -320,6 +332,23 @@ struct ip_vs_seq {
 						   before last resized pkt */
 };
 
+/*
+ * counters per cpu
+ */
+struct ip_vs_counters {
+	__u32		conns;		/* connections scheduled */
+	__u32		inpkts;		/* incoming packets */
+	__u32		outpkts;	/* outgoing packets */
+	__u64		inbytes;	/* incoming bytes */
+	__u64		outbytes;	/* outgoing bytes */
+};
+/*
+ * Stats per cpu
+ */
+struct ip_vs_cpu_stats {
+	struct ip_vs_counters   ustats;
+	struct u64_stats_sync   syncp;
+};
 
 /*
  *	IPVS statistics objects
@@ -341,12 +370,28 @@ struct ip_vs_estimator {
 };
 
 struct ip_vs_stats {
-	struct ip_vs_stats_user	ustats;         /* statistics */
+	struct ip_vs_stats_user	ustats;		/* statistics */
 	struct ip_vs_estimator	est;		/* estimator */
-
-	spinlock_t              lock;           /* spin lock */
+	struct ip_vs_cpu_stats	*cpustats;	/* per cpu counters */
+	spinlock_t		lock;		/* spin lock */
 };
 
+/*
+ * Helper Macros for per cpu
+ * ipvs->tot_stats->ustats.count
+ */
+#define IPVS_STAT_INC(ipvs, count)	\
+	__this_cpu_inc((ipvs)->ustats->count)
+
+#define IPVS_STAT_ADD(ipvs, count, value) \
+	do {\
+		write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \
+				     raw_smp_processor_id())); \
+		__this_cpu_add((ipvs)->ustats->count, value); \
+		write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \
+				   raw_smp_processor_id())); \
+	} while (0)
+
 struct dst_entry;
 struct iphdr;
 struct ip_vs_conn;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index aba78f3c8341..bd1dad872178 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -61,6 +61,10 @@ struct netns_ipvs {
 	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
 	spinlock_t		sctp_app_lock;
 #endif
+	/* ip_vs_ctl */
+	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
+	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
+	seqcount_t			*ustats_seq; /* u64 read retry */
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5531d569aa5e..7e6a2a046bf5 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -115,21 +115,28 @@ static inline void
 ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 {
 	struct ip_vs_dest *dest = cp->dest;
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
-		spin_lock(&dest->stats.lock);
-		dest->stats.ustats.inpkts++;
-		dest->stats.ustats.inbytes += skb->len;
-		spin_unlock(&dest->stats.lock);
-
-		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.ustats.inpkts++;
-		dest->svc->stats.ustats.inbytes += skb->len;
-		spin_unlock(&dest->svc->stats.lock);
-
-		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.ustats.inpkts++;
-		ip_vs_stats.ustats.inbytes += skb->len;
-		spin_unlock(&ip_vs_stats.lock);
+		struct ip_vs_cpu_stats *s;
+
+		s = this_cpu_ptr(dest->stats.cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(dest->svc->stats.cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(ipvs->cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
 	}
 }
 
@@ -138,21 +145,28 @@ static inline void
 ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 {
 	struct ip_vs_dest *dest = cp->dest;
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
-		spin_lock(&dest->stats.lock);
-		dest->stats.ustats.outpkts++;
-		dest->stats.ustats.outbytes += skb->len;
-		spin_unlock(&dest->stats.lock);
-
-		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.ustats.outpkts++;
-		dest->svc->stats.ustats.outbytes += skb->len;
-		spin_unlock(&dest->svc->stats.lock);
-
-		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.ustats.outpkts++;
-		ip_vs_stats.ustats.outbytes += skb->len;
-		spin_unlock(&ip_vs_stats.lock);
+		struct ip_vs_cpu_stats *s;
+
+		s = this_cpu_ptr(dest->stats.cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(dest->svc->stats.cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(ipvs->cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
 	}
 }
 
@@ -160,17 +174,17 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 static inline void
 ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 {
-	spin_lock(&cp->dest->stats.lock);
-	cp->dest->stats.ustats.conns++;
-	spin_unlock(&cp->dest->stats.lock);
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
+	struct ip_vs_cpu_stats *s;
 
-	spin_lock(&svc->stats.lock);
-	svc->stats.ustats.conns++;
-	spin_unlock(&svc->stats.lock);
+	s = this_cpu_ptr(cp->dest->stats.cpustats);
+	s->ustats.conns++;
 
-	spin_lock(&ip_vs_stats.lock);
-	ip_vs_stats.ustats.conns++;
-	spin_unlock(&ip_vs_stats.lock);
+	s = this_cpu_ptr(svc->stats.cpustats);
+	s->ustats.conns++;
+
+	s = this_cpu_ptr(ipvs->cpustats);
+	s->ustats.conns++;
 }
 
 
@@ -1841,7 +1855,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	},
 #endif
 };
-
 /*
  *	Initialize IP Virtual Server netns mem.
  */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 03f86312b4bb..cbd58c60e1bf 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -257,8 +257,7 @@ static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
 
 static void defense_work_handler(struct work_struct *work)
 {
-	struct net *net = &init_net;
-	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 
 	update_defense_level(ipvs);
 	if (atomic_read(&ip_vs_dropentry))
@@ -519,6 +518,7 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest)
 			      svc->fwmark,
 			      IP_VS_DBG_ADDR(svc->af, &svc->addr),
 			      ntohs(svc->port), atomic_read(&svc->usecnt));
+		free_percpu(svc->stats.cpustats);
 		kfree(svc);
 	}
 }
@@ -722,6 +722,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 			list_del(&dest->n_list);
 			ip_vs_dst_reset(dest);
 			__ip_vs_unbind_svc(dest);
+			free_percpu(dest->stats.cpustats);
 			kfree(dest);
 		}
 	}
@@ -747,6 +748,7 @@ static void ip_vs_trash_cleanup(void)
 		list_del(&dest->n_list);
 		ip_vs_dst_reset(dest);
 		__ip_vs_unbind_svc(dest);
+		free_percpu(dest->stats.cpustats);
 		kfree(dest);
 	}
 }
@@ -868,6 +870,11 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 		pr_err("%s(): no memory.\n", __func__);
 		return -ENOMEM;
 	}
+	dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!dest->stats.cpustats) {
+		pr_err("%s() alloc_percpu failed\n", __func__);
+		goto err_alloc;
+	}
 
 	dest->af = svc->af;
 	dest->protocol = svc->protocol;
@@ -891,6 +898,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 
 	LeaveFunction(2);
 	return 0;
+
+err_alloc:
+	kfree(dest);
+	return -ENOMEM;
 }
 
 
@@ -1037,6 +1048,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 		   and only one user context can update virtual service at a
 		   time, so the operation here is OK */
 		atomic_dec(&dest->svc->refcnt);
+		free_percpu(dest->stats.cpustats);
 		kfree(dest);
 	} else {
 		IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, "
@@ -1163,6 +1175,11 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		ret = -ENOMEM;
 		goto out_err;
 	}
+	svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!svc->stats.cpustats) {
+		pr_err("%s() alloc_percpu failed\n", __func__);
+		goto out_err;
+	}
 
 	/* I'm the first user of the service */
 	atomic_set(&svc->usecnt, 0);
@@ -1212,6 +1229,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	*svc_p = svc;
 	return 0;
 
+
  out_err:
 	if (svc != NULL) {
 		ip_vs_unbind_scheduler(svc);
@@ -1220,6 +1238,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 			ip_vs_app_inc_put(svc->inc);
 			local_bh_enable();
 		}
+		if (svc->stats.cpustats)
+			free_percpu(svc->stats.cpustats);
 		kfree(svc);
 	}
 	ip_vs_scheduler_put(sched);
@@ -1388,6 +1408,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 			      svc->fwmark,
 			      IP_VS_DBG_ADDR(svc->af, &svc->addr),
 			      ntohs(svc->port), atomic_read(&svc->usecnt));
+		free_percpu(svc->stats.cpustats);
 		kfree(svc);
 	}
 
@@ -1499,7 +1520,7 @@ static int ip_vs_zero_all(struct net *net)
 		}
 	}
 
-	ip_vs_zero_stats(&ip_vs_stats);
+	ip_vs_zero_stats(net_ipvs(net)->tot_stats);
 	return 0;
 }
 
@@ -1989,13 +2010,11 @@ static const struct file_operations ip_vs_info_fops = {
 
 #endif
 
-struct ip_vs_stats ip_vs_stats = {
-	.lock = __SPIN_LOCK_UNLOCKED(ip_vs_stats.lock),
-};
-
 #ifdef CONFIG_PROC_FS
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
+	struct net *net = seq_file_single_net(seq);
+	struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -2003,22 +2022,22 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 	seq_printf(seq,
 		   "   Conns  Packets  Packets            Bytes            Bytes\n");
 
-	spin_lock_bh(&ip_vs_stats.lock);
-	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.ustats.conns,
-		   ip_vs_stats.ustats.inpkts, ip_vs_stats.ustats.outpkts,
-		   (unsigned long long) ip_vs_stats.ustats.inbytes,
-		   (unsigned long long) ip_vs_stats.ustats.outbytes);
+	spin_lock_bh(&tot_stats->lock);
+	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns,
+		   tot_stats->ustats.inpkts, tot_stats->ustats.outpkts,
+		   (unsigned long long) tot_stats->ustats.inbytes,
+		   (unsigned long long) tot_stats->ustats.outbytes);
 
 /*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		   " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
 	seq_printf(seq,"%8X %8X %8X %16X %16X\n",
-			ip_vs_stats.ustats.cps,
-			ip_vs_stats.ustats.inpps,
-			ip_vs_stats.ustats.outpps,
-			ip_vs_stats.ustats.inbps,
-			ip_vs_stats.ustats.outbps);
-	spin_unlock_bh(&ip_vs_stats.lock);
+			tot_stats->ustats.cps,
+			tot_stats->ustats.inpps,
+			tot_stats->ustats.outpps,
+			tot_stats->ustats.inbps,
+			tot_stats->ustats.outbps);
+	spin_unlock_bh(&tot_stats->lock);
 
 	return 0;
 }
@@ -2036,6 +2055,59 @@ static const struct file_operations ip_vs_stats_fops = {
 	.release = single_release,
 };
 
+static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
+{
+	struct net *net = seq_file_single_net(seq);
+	struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+	int i;
+
+/*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
+	seq_puts(seq,
+		 "       Total Incoming Outgoing         Incoming         Outgoing\n");
+	seq_printf(seq,
+		   "CPU    Conns  Packets  Packets            Bytes            Bytes\n");
+
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i);
+		seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
+			    i, u->ustats.conns, u->ustats.inpkts,
+			    u->ustats.outpkts, (__u64)u->ustats.inbytes,
+			    (__u64)u->ustats.outbytes);
+	}
+
+	spin_lock_bh(&tot_stats->lock);
+	seq_printf(seq, "  ~ %8X %8X %8X %16LX %16LX\n\n",
+		   tot_stats->ustats.conns, tot_stats->ustats.inpkts,
+		   tot_stats->ustats.outpkts,
+		   (unsigned long long) tot_stats->ustats.inbytes,
+		   (unsigned long long) tot_stats->ustats.outbytes);
+
+/*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
+	seq_puts(seq,
+		   "     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
+	seq_printf(seq, "    %8X %8X %8X %16X %16X\n",
+			tot_stats->ustats.cps,
+			tot_stats->ustats.inpps,
+			tot_stats->ustats.outpps,
+			tot_stats->ustats.inbps,
+			tot_stats->ustats.outbps);
+	spin_unlock_bh(&tot_stats->lock);
+
+	return 0;
+}
+
+static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open_net(inode, file, ip_vs_stats_percpu_show);
+}
+
+static const struct file_operations ip_vs_stats_percpu_fops = {
+	.owner = THIS_MODULE,
+	.open = ip_vs_stats_percpu_seq_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
 #endif
 
 /*
@@ -3461,32 +3533,54 @@ int __net_init __ip_vs_control_init(struct net *net)
 
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
+	/* procfs stats */
+	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
+	if (ipvs->tot_stats == NULL) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!ipvs->cpustats) {
+		pr_err("%s() alloc_percpu failed\n", __func__);
+		goto err_alloc;
+	}
+	spin_lock_init(&ipvs->tot_stats->lock);
 
 	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
 		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
 
 	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
 	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
+	proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
+			     &ip_vs_stats_percpu_fops);
 	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
 						  vs_vars);
 	if (sysctl_header == NULL)
 		goto err_reg;
-	ip_vs_new_estimator(net, &ip_vs_stats);
+	ip_vs_new_estimator(net, ipvs->tot_stats);
 	return 0;
 
 err_reg:
+	free_percpu(ipvs->cpustats);
+err_alloc:
+	kfree(ipvs->tot_stats);
 	return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_control_cleanup(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
-	ip_vs_kill_estimator(net, &ip_vs_stats);
+	ip_vs_kill_estimator(net, ipvs->tot_stats);
 	unregister_net_sysctl_table(sysctl_header);
+	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
+	free_percpu(ipvs->cpustats);
+	kfree(ipvs->tot_stats);
 }
 
 static struct pernet_operations ipvs_control_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 07d839bef537..d13616b138cd 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -52,6 +52,43 @@
  */
 
 
+/*
+ * Make a summary from each cpu
+ */
+static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
+				 struct ip_vs_cpu_stats *stats)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i);
+		unsigned int start;
+		__u64 inbytes, outbytes;
+		if (i) {
+			sum->conns += s->ustats.conns;
+			sum->inpkts += s->ustats.inpkts;
+			sum->outpkts += s->ustats.outpkts;
+			do {
+				start = u64_stats_fetch_begin_bh(&s->syncp);
+				inbytes = s->ustats.inbytes;
+				outbytes = s->ustats.outbytes;
+			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+			sum->inbytes += inbytes;
+			sum->outbytes += outbytes;
+		} else {
+			sum->conns = s->ustats.conns;
+			sum->inpkts = s->ustats.inpkts;
+			sum->outpkts = s->ustats.outpkts;
+			do {
+				start = u64_stats_fetch_begin_bh(&s->syncp);
+				sum->inbytes = s->ustats.inbytes;
+				sum->outbytes = s->ustats.outbytes;
+			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+		}
+	}
+}
+
+
 static void estimation_timer(unsigned long arg)
 {
 	struct ip_vs_estimator *e;
@@ -64,10 +101,12 @@ static void estimation_timer(unsigned long arg)
 	struct netns_ipvs *ipvs;
 
 	ipvs = net_ipvs(net);
+	ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats);
 	spin_lock(&ipvs->est_lock);
 	list_for_each_entry(e, &ipvs->est_list, list) {
 		s = container_of(e, struct ip_vs_stats, est);
 
+		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
 		spin_lock(&s->lock);
 		n_conns = s->ustats.conns;
 		n_inpkts = s->ustats.inpkts;
-- 
cgit v1.2.3


From 6e67e586e7289c144d5a189d6e0fa7141d025746 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:57 +0100
Subject: IPVS: netns, connection hash got net as param.

Connection hash table is now name space aware.
i.e. net ptr >> 8 is xor:ed to the hash,
and this is the first param to be compared.
The net struct is 0xa40 in size ( a little bit smaller for 32 bit arch:s)
and cache-line aligned, so a ptr >> 5 might be a more clever solution ?

All lookups where net is compared uses net_eq() which returns 1 when netns
is disabled, and the compiler seems to do something clever in that case.

ip_vs_conn_fill_param() have *net as first param now.

Three new inlines added to keep conn struct smaller
when names space is disabled.
- ip_vs_conn_net()
- ip_vs_conn_net_set()
- ip_vs_conn_net_eq()

*v3
  moved net compare to the end in "fast path"

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                     |  53 +++++++++++----
 include/net/netns/ip_vs.h               |   2 +
 net/netfilter/ipvs/ip_vs_conn.c         | 112 ++++++++++++++++++++------------
 net/netfilter/ipvs/ip_vs_core.c         |  15 +++--
 net/netfilter/ipvs/ip_vs_ftp.c          |  14 ++--
 net/netfilter/ipvs/ip_vs_nfct.c         |   6 +-
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c |  15 +++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c   |   2 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c    |   2 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c    |   2 +-
 net/netfilter/ipvs/ip_vs_sync.c         |  13 ++--
 11 files changed, 153 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 605d5db81a39..f82c0ffdee74 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -477,6 +477,7 @@ extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
 						     unsigned short proto);
 
 struct ip_vs_conn_param {
+	struct net			*net;
 	const union nf_inet_addr	*caddr;
 	const union nf_inet_addr	*vaddr;
 	__be16				cport;
@@ -494,17 +495,19 @@ struct ip_vs_conn_param {
  */
 struct ip_vs_conn {
 	struct list_head        c_list;         /* hashed list heads */
-
+#ifdef CONFIG_NET_NS
+	struct net              *net;           /* Name space */
+#endif
 	/* Protocol, addresses and port numbers */
-	u16                      af;		/* address family */
-	union nf_inet_addr       caddr;          /* client address */
-	union nf_inet_addr       vaddr;          /* virtual address */
-	union nf_inet_addr       daddr;          /* destination address */
-	volatile __u32           flags;          /* status flags */
-	__u32                    fwmark;         /* Fire wall mark from skb */
-	__be16                   cport;
-	__be16                   vport;
-	__be16                   dport;
+	u16                     af;             /* address family */
+	__be16                  cport;
+	__be16                  vport;
+	__be16                  dport;
+	__u32                   fwmark;         /* Fire wall mark from skb */
+	union nf_inet_addr      caddr;          /* client address */
+	union nf_inet_addr      vaddr;          /* virtual address */
+	union nf_inet_addr      daddr;          /* destination address */
+	volatile __u32          flags;          /* status flags */
 	__u16                   protocol;       /* Which protocol (TCP/UDP) */
 
 	/* counter and timer */
@@ -547,6 +550,33 @@ struct ip_vs_conn {
 	__u8			pe_data_len;
 };
 
+/*
+ *  To save some memory in conn table when name space is disabled.
+ */
+static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
+{
+#ifdef CONFIG_NET_NS
+	return cp->net;
+#else
+	return &init_net;
+#endif
+}
+static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
+{
+#ifdef CONFIG_NET_NS
+	cp->net = net;
+#endif
+}
+
+static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp,
+				    struct net *net)
+{
+#ifdef CONFIG_NET_NS
+	return cp->net == net;
+#else
+	return 1;
+#endif
+}
 
 /*
  *	Extended internal versions of struct ip_vs_service_user and
@@ -796,13 +826,14 @@ enum {
 	IP_VS_DIR_LAST,
 };
 
-static inline void ip_vs_conn_fill_param(int af, int protocol,
+static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
 					 const union nf_inet_addr *caddr,
 					 __be16 cport,
 					 const union nf_inet_addr *vaddr,
 					 __be16 vport,
 					 struct ip_vs_conn_param *p)
 {
+	p->net = net;
 	p->af = af;
 	p->protocol = protocol;
 	p->caddr = caddr;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index bd1dad872178..1acfb334e69b 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -66,6 +66,8 @@ struct netns_ipvs {
 	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
 	seqcount_t			*ustats_seq; /* u64 read retry */
 
+	/* ip_vs_conn */
+	atomic_t		conn_count;         /*  connection counter */
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
 	struct ctl_table_header	*lblc_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index b2024c942345..0d5e4feabc1b 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -64,9 +64,6 @@ static struct list_head *ip_vs_conn_tab __read_mostly;
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
 
-/*  counter for current IPVS connections */
-static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);
-
 /*  counter for no client port connections */
 static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);
 
@@ -76,7 +73,7 @@ static unsigned int ip_vs_conn_rnd __read_mostly;
 /*
  *  Fine locking granularity for big connection hash table
  */
-#define CT_LOCKARRAY_BITS  4
+#define CT_LOCKARRAY_BITS  5
 #define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
 #define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)
 
@@ -133,19 +130,19 @@ static inline void ct_write_unlock_bh(unsigned key)
 /*
  *	Returns hash value for IPVS connection entry
  */
-static unsigned int ip_vs_conn_hashkey(int af, unsigned proto,
+static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto,
 				       const union nf_inet_addr *addr,
 				       __be16 port)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
-				    (__force u32)port, proto, ip_vs_conn_rnd)
-			& ip_vs_conn_tab_mask;
+		return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
+				    (__force u32)port, proto, ip_vs_conn_rnd) ^
+			((size_t)net>>8)) & ip_vs_conn_tab_mask;
 #endif
-	return jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
-			    ip_vs_conn_rnd)
-		& ip_vs_conn_tab_mask;
+	return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
+			    ip_vs_conn_rnd) ^
+		((size_t)net>>8)) & ip_vs_conn_tab_mask;
 }
 
 static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
@@ -166,15 +163,15 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
 		port = p->vport;
 	}
 
-	return ip_vs_conn_hashkey(p->af, p->protocol, addr, port);
+	return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port);
 }
 
 static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_conn_param p;
 
-	ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
-			      NULL, 0, &p);
+	ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol,
+			      &cp->caddr, cp->cport, NULL, 0, &p);
 
 	if (cp->pe) {
 		p.pe = cp->pe;
@@ -186,7 +183,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 }
 
 /*
- *	Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port.
+ *	Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port.
  *	returns bool success.
  */
 static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
@@ -269,11 +266,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
+		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
-		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
-		    p->protocol == cp->protocol) {
+		    p->protocol == cp->protocol &&
+		    ip_vs_conn_net_eq(cp, p->net)) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ct_read_unlock(hash);
@@ -313,17 +311,18 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 			    struct ip_vs_conn_param *p)
 {
 	__be16 _ports[2], *pptr;
+	struct net *net = skb_net(skb);
 
 	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
 	if (pptr == NULL)
 		return 1;
 
 	if (likely(!inverse))
-		ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0],
-				      &iph->daddr, pptr[1], p);
+		ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr,
+				      pptr[0], &iph->daddr, pptr[1], p);
 	else
-		ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1],
-				      &iph->saddr, pptr[0], p);
+		ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr,
+				      pptr[1], &iph->saddr, pptr[0], p);
 	return 0;
 }
 
@@ -352,6 +351,8 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 	ct_read_lock(hash);
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+		if (!ip_vs_conn_net_eq(cp, p->net))
+			continue;
 		if (p->pe_data && p->pe->ct_match) {
 			if (p->pe == cp->pe && p->pe->ct_match(p, cp))
 				goto out;
@@ -403,10 +404,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
+		    p->vport == cp->cport && p->cport == cp->dport &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
-		    p->vport == cp->cport && p->cport == cp->dport &&
-		    p->protocol == cp->protocol) {
+		    p->protocol == cp->protocol &&
+		    ip_vs_conn_net_eq(cp, p->net)) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ret = cp;
@@ -609,8 +611,8 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	if ((cp) && (!cp->dest)) {
-		dest = ip_vs_find_dest(&init_net, cp->af, &cp->daddr, cp->dport,
-				       &cp->vaddr, cp->vport,
+		dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
+				       cp->dport, &cp->vaddr, cp->vport,
 				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
 		return dest;
@@ -728,6 +730,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 static void ip_vs_conn_expire(unsigned long data)
 {
 	struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 
 	cp->timeout = 60*HZ;
 
@@ -770,7 +773,7 @@ static void ip_vs_conn_expire(unsigned long data)
 		ip_vs_unbind_dest(cp);
 		if (cp->flags & IP_VS_CONN_F_NO_CPORT)
 			atomic_dec(&ip_vs_conn_no_cport_cnt);
-		atomic_dec(&ip_vs_conn_count);
+		atomic_dec(&ipvs->conn_count);
 
 		kmem_cache_free(ip_vs_conn_cachep, cp);
 		return;
@@ -804,7 +807,9 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	       struct ip_vs_dest *dest, __u32 fwmark)
 {
 	struct ip_vs_conn *cp;
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, p->protocol);
+	struct netns_ipvs *ipvs = net_ipvs(p->net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net,
+							   p->protocol);
 
 	cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
 	if (cp == NULL) {
@@ -814,6 +819,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 
 	INIT_LIST_HEAD(&cp->c_list);
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
+	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_copy(p->af, &cp->caddr, p->caddr);
@@ -844,7 +850,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	atomic_set(&cp->n_control, 0);
 	atomic_set(&cp->in_pkts, 0);
 
-	atomic_inc(&ip_vs_conn_count);
+	atomic_inc(&ipvs->conn_count);
 	if (flags & IP_VS_CONN_F_NO_CPORT)
 		atomic_inc(&ip_vs_conn_no_cport_cnt);
 
@@ -886,17 +892,22 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
  *	/proc/net/ip_vs_conn entries
  */
 #ifdef CONFIG_PROC_FS
+struct ip_vs_iter_state {
+	struct seq_net_private p;
+	struct list_head *l;
+};
 
 static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 {
 	int idx;
 	struct ip_vs_conn *cp;
+	struct ip_vs_iter_state *iter = seq->private;
 
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		ct_read_lock_bh(idx);
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
 			if (pos-- == 0) {
-				seq->private = &ip_vs_conn_tab[idx];
+				iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 			}
 		}
@@ -908,14 +919,17 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 
 static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	seq->private = NULL;
+	struct ip_vs_iter_state *iter = seq->private;
+
+	iter->l = NULL;
 	return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN;
 }
 
 static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_conn *cp = v;
-	struct list_head *e, *l = seq->private;
+	struct ip_vs_iter_state *iter = seq->private;
+	struct list_head *e, *l = iter->l;
 	int idx;
 
 	++*pos;
@@ -932,18 +946,19 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	while (++idx < ip_vs_conn_tab_size) {
 		ct_read_lock_bh(idx);
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-			seq->private = &ip_vs_conn_tab[idx];
+			iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 		}
 		ct_read_unlock_bh(idx);
 	}
-	seq->private = NULL;
+	iter->l = NULL;
 	return NULL;
 }
 
 static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
 {
-	struct list_head *l = seq->private;
+	struct ip_vs_iter_state *iter = seq->private;
+	struct list_head *l = iter->l;
 
 	if (l)
 		ct_read_unlock_bh(l - ip_vs_conn_tab);
@@ -957,9 +972,12 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Expires PEName PEData\n");
 	else {
 		const struct ip_vs_conn *cp = v;
+		struct net *net = seq_file_net(seq);
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
 
+		if (!ip_vs_conn_net_eq(cp, net))
+			return 0;
 		if (cp->pe_data) {
 			pe_data[0] = ' ';
 			len = strlen(cp->pe->name);
@@ -1004,7 +1022,8 @@ static const struct seq_operations ip_vs_conn_seq_ops = {
 
 static int ip_vs_conn_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_conn_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_conn_seq_ops,
+			    sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_fops = {
@@ -1031,6 +1050,10 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Origin Expires\n");
 	else {
 		const struct ip_vs_conn *cp = v;
+		struct net *net = seq_file_net(seq);
+
+		if (!ip_vs_conn_net_eq(cp, net))
+			return 0;
 
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
@@ -1067,7 +1090,8 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = {
 
 static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_conn_sync_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops,
+			    sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_sync_fops = {
@@ -1168,10 +1192,11 @@ void ip_vs_random_dropentry(void)
 /*
  *      Flush all the connection entries in the ip_vs_conn_tab
  */
-static void ip_vs_conn_flush(void)
+static void ip_vs_conn_flush(struct net *net)
 {
 	int idx;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
   flush_again:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
@@ -1181,7 +1206,8 @@ static void ip_vs_conn_flush(void)
 		ct_write_lock_bh(idx);
 
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-
+			if (!ip_vs_conn_net_eq(cp, net))
+				continue;
 			IP_VS_DBG(4, "del connection\n");
 			ip_vs_conn_expire_now(cp);
 			if (cp->control) {
@@ -1194,7 +1220,7 @@ static void ip_vs_conn_flush(void)
 
 	/* the counter may be not NULL, because maybe some conn entries
 	   are run by slow timer handler or unhashed but still referred */
-	if (atomic_read(&ip_vs_conn_count) != 0) {
+	if (atomic_read(&ipvs->conn_count) != 0) {
 		schedule();
 		goto flush_again;
 	}
@@ -1204,8 +1230,11 @@ static void ip_vs_conn_flush(void)
  */
 int __net_init __ip_vs_conn_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
+	atomic_set(&ipvs->conn_count, 0);
 
 	proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
 	proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
@@ -1217,6 +1246,8 @@ static void __net_exit __ip_vs_conn_cleanup(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
+	/* flush all the connection entries first */
+	ip_vs_conn_flush(net);
 	proc_net_remove(net, "ip_vs_conn");
 	proc_net_remove(net, "ip_vs_conn_sync");
 }
@@ -1277,9 +1308,6 @@ int __init ip_vs_conn_init(void)
 void ip_vs_conn_cleanup(void)
 {
 	unregister_pernet_subsys(&ipvs_conn_ops);
-	/* flush all the connection entries first */
-	ip_vs_conn_flush();
-
 	/* Release the empty cache */
 	kmem_cache_destroy(ip_vs_conn_cachep);
 	vfree(ip_vs_conn_tab);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 7e6a2a046bf5..7205b49c56c1 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -205,7 +205,8 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 			      const union nf_inet_addr *vaddr, __be16 vport,
 			      struct ip_vs_conn_param *p)
 {
-	ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
+	ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
+			      vport, p);
 	p->pe = svc->pe;
 	if (p->pe && p->pe->fill_param)
 		return p->pe->fill_param(p, skb);
@@ -348,8 +349,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	/*
 	 *    Create a new connection according to the template
 	 */
-	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, src_port,
-			      &iph.daddr, dst_port, &param);
+	ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
+			      src_port, &iph.daddr, dst_port, &param);
 
 	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
@@ -464,8 +465,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 */
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr,
-				      pptr[0], &iph.daddr, pptr[1], &p);
+
+		ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
+				      &iph.saddr, pptr[0], &iph.daddr, pptr[1],
+				      &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
@@ -532,7 +535,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(svc->af, iph.protocol,
+			ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
 					      &iph.saddr, pptr[0],
 					      &iph.daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 77b0036dcb73..6a04f9ab9d0d 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -198,13 +198,15 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		 */
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(AF_INET, iph->protocol,
-					      &from, port, &cp->caddr, 0, &p);
+			ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+					      iph->protocol, &from, port,
+					      &cp->caddr, 0, &p);
 			n_cp = ip_vs_conn_out_get(&p);
 		}
 		if (!n_cp) {
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr,
+			ip_vs_conn_fill_param(ip_vs_conn_net(cp),
+					      AF_INET, IPPROTO_TCP, &cp->caddr,
 					      0, &cp->vaddr, port, &p);
 			n_cp = ip_vs_conn_new(&p, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
@@ -361,9 +363,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port,
-				      &cp->vaddr, htons(ntohs(cp->vport)-1),
-				      &p);
+		ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+				      iph->protocol, &to, port, &cp->vaddr,
+				      htons(ntohs(cp->vport)-1), &p);
 		n_cp = ip_vs_conn_in_get(&p);
 		if (!n_cp) {
 			n_cp = ip_vs_conn_new(&p, &cp->daddr,
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index 4680647cd450..f454c80df0a7 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -141,6 +141,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 	struct nf_conntrack_tuple *orig, new_reply;
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = nf_ct_net(ct);
 
 	if (exp->tuple.src.l3num != PF_INET)
 		return;
@@ -155,7 +156,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 
 	/* RS->CLIENT */
 	orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
-	ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum,
+	ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum,
 			      &orig->src.u3, orig->src.u.tcp.port,
 			      &orig->dst.u3, orig->dst.u.tcp.port, &p);
 	cp = ip_vs_conn_out_get(&p);
@@ -268,7 +269,8 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 		" for conn " FMT_CONN "\n",
 		__func__, ARG_TUPLE(&tuple), ARG_CONN(cp));
 
-	h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple);
+	h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE,
+				  &tuple);
 	if (h) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		/* Show what happens instead of calling nf_ct_kill() */
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index 28039cbfcff4..5b8eb8b12c3e 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -41,15 +41,16 @@ struct isakmp_hdr {
 #define PORT_ISAKMP	500
 
 static void
-ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
-			     int inverse, struct ip_vs_conn_param *p)
+ah_esp_conn_fill_param_proto(struct net *net, int af,
+			     const struct ip_vs_iphdr *iph, int inverse,
+			     struct ip_vs_conn_param *p)
 {
 	if (likely(!inverse))
-		ip_vs_conn_fill_param(af, IPPROTO_UDP,
+		ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
 				      &iph->saddr, htons(PORT_ISAKMP),
 				      &iph->daddr, htons(PORT_ISAKMP), p);
 	else
-		ip_vs_conn_fill_param(af, IPPROTO_UDP,
+		ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
 				      &iph->daddr, htons(PORT_ISAKMP),
 				      &iph->saddr, htons(PORT_ISAKMP), p);
 }
@@ -61,8 +62,9 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = skb_net(skb);
 
-	ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+	ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
 	cp = ip_vs_conn_in_get(&p);
 	if (!cp) {
 		/*
@@ -89,8 +91,9 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = skb_net(skb);
 
-	ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+	ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
 	cp = ip_vs_conn_out_get(&p);
 	if (!cp) {
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 569e77bf08c4..550365a690c7 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1055,7 +1055,7 @@ static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
 
 static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 757aaaf083bb..d8b3f9f15826 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -620,7 +620,7 @@ tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
 static int
 tcp_app_conn_bind(struct ip_vs_conn *cp)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 1dc394100fa8..581157bbded5 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -396,7 +396,7 @@ udp_unregister_app(struct net *net, struct ip_vs_app *inc)
 
 static int udp_app_conn_bind(struct ip_vs_conn *cp)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c29e73d686fb..f85e47daecc3 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -660,21 +660,21 @@ control:
  *  fill_param used by version 1
  */
 static inline int
-ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
+ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
 			   struct ip_vs_conn_param *p,
 			   __u8 *pe_data, unsigned int pe_data_len,
 			   __u8 *pe_name, unsigned int pe_name_len)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		ip_vs_conn_fill_param(af, sc->v6.protocol,
+		ip_vs_conn_fill_param(net, af, sc->v6.protocol,
 				      (const union nf_inet_addr *)&sc->v6.caddr,
 				      sc->v6.cport,
 				      (const union nf_inet_addr *)&sc->v6.vaddr,
 				      sc->v6.vport, p);
 	else
 #endif
-		ip_vs_conn_fill_param(af, sc->v4.protocol,
+		ip_vs_conn_fill_param(net, af, sc->v4.protocol,
 				      (const union nf_inet_addr *)&sc->v4.caddr,
 				      sc->v4.cport,
 				      (const union nf_inet_addr *)&sc->v4.vaddr,
@@ -881,7 +881,7 @@ static void ip_vs_process_message_v0(struct net *net, const char *buffer,
 			}
 		}
 
-		ip_vs_conn_fill_param(AF_INET, s->protocol,
+		ip_vs_conn_fill_param(net, AF_INET, s->protocol,
 				      (const union nf_inet_addr *)&s->caddr,
 				      s->cport,
 				      (const union nf_inet_addr *)&s->vaddr,
@@ -1043,9 +1043,8 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end)
 			state = 0;
 		}
 	}
-	if (ip_vs_conn_fill_param_sync(af, s, &param,
-					pe_data, pe_data_len,
-					pe_name, pe_name_len)) {
+	if (ip_vs_conn_fill_param_sync(net, af, s, &param, pe_data,
+				       pe_data_len, pe_name, pe_name_len)) {
 		retc = 50;
 		goto out;
 	}
-- 
cgit v1.2.3


From a0840e2e165a370ca24a59545e564e9881a55891 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:58 +0100
Subject: IPVS: netns, ip_vs_ctl local vars moved to ipvs struct.

Moving global vars to ipvs struct, except for svc table lock.
Next patch for ctl will be drop-rate handling.

*v3
__ip_vs_mutex remains global
 ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |  27 ++--
 include/net/netns/ip_vs.h             |  37 ++++-
 net/netfilter/ipvs/ip_vs_conn.c       |   7 +-
 net/netfilter/ipvs/ip_vs_core.c       |  34 ++--
 net/netfilter/ipvs/ip_vs_ctl.c        | 291 ++++++++++++++++++----------------
 net/netfilter/ipvs/ip_vs_proto_sctp.c |   2 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |   2 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c  |   2 +-
 net/netfilter/ipvs/ip_vs_sync.c       |   9 +-
 9 files changed, 230 insertions(+), 181 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index f82c0ffdee74..af9acf44e40a 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -41,7 +41,7 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
  * Get net ptr from skb in traffic cases
  * use skb_sknet when call is from userland (ioctl or netlink)
  */
-static inline struct net *skb_net(struct sk_buff *skb)
+static inline struct net *skb_net(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_NS
 #ifdef CONFIG_IP_VS_DEBUG
@@ -69,7 +69,7 @@ static inline struct net *skb_net(struct sk_buff *skb)
 #endif
 }
 
-static inline struct net *skb_sknet(struct sk_buff *skb)
+static inline struct net *skb_sknet(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_NS
 #ifdef CONFIG_IP_VS_DEBUG
@@ -1023,13 +1023,6 @@ extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 /*
  *      IPVS control data and functions (from ip_vs_ctl.c)
  */
-extern int sysctl_ip_vs_cache_bypass;
-extern int sysctl_ip_vs_expire_nodest_conn;
-extern int sysctl_ip_vs_expire_quiescent_template;
-extern int sysctl_ip_vs_sync_threshold[2];
-extern int sysctl_ip_vs_nat_icmp_send;
-extern int sysctl_ip_vs_conntrack;
-extern int sysctl_ip_vs_snat_reroute;
 extern struct ip_vs_stats ip_vs_stats;
 extern const struct ctl_path net_vs_ctl_path[];
 extern int sysctl_ip_vs_sync_ver;
@@ -1119,11 +1112,13 @@ extern int ip_vs_icmp_xmit_v6
 extern int ip_vs_drop_rate;
 extern int ip_vs_drop_counter;
 
-static __inline__ int ip_vs_todrop(void)
+static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 {
-	if (!ip_vs_drop_rate) return 0;
-	if (--ip_vs_drop_counter > 0) return 0;
-	ip_vs_drop_counter = ip_vs_drop_rate;
+	if (!ipvs->drop_rate)
+		return 0;
+	if (--ipvs->drop_counter > 0)
+		return 0;
+	ipvs->drop_counter = ipvs->drop_rate;
 	return 1;
 }
 
@@ -1211,9 +1206,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
  *      Netfilter connection tracking
  *      (from ip_vs_nfct.c)
  */
-static inline int ip_vs_conntrack_enabled(void)
+static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
-	return sysctl_ip_vs_conntrack;
+	return ipvs->sysctl_conntrack;
 }
 
 extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
@@ -1226,7 +1221,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);
 
 #else
 
-static inline int ip_vs_conntrack_enabled(void)
+static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
 	return 0;
 }
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 1acfb334e69b..c4b1abf258e4 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -61,13 +61,46 @@ struct netns_ipvs {
 	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
 	spinlock_t		sctp_app_lock;
 #endif
+	/* ip_vs_conn */
+	atomic_t		conn_count;      /*  connection counter */
+
 	/* ip_vs_ctl */
 	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
 	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
 	seqcount_t			*ustats_seq; /* u64 read retry */
 
-	/* ip_vs_conn */
-	atomic_t		conn_count;         /*  connection counter */
+	int			num_services;    /* no of virtual services */
+	/* 1/rate drop and drop-entry variables */
+	int			drop_rate;
+	int			drop_counter;
+	atomic_t		dropentry;
+	/* locks in ctl.c */
+	spinlock_t		dropentry_lock;  /* drop entry handling */
+	spinlock_t		droppacket_lock; /* drop packet handling */
+	spinlock_t		securetcp_lock;  /* state and timeout tables */
+	rwlock_t		rs_lock;         /* real services table */
+	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
+	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* sys-ctl struct */
+	struct ctl_table_header	*sysctl_hdr;
+	struct ctl_table	*sysctl_tbl;
+	/* sysctl variables */
+	int			sysctl_amemthresh;
+	int			sysctl_am_droprate;
+	int			sysctl_drop_entry;
+	int			sysctl_drop_packet;
+	int			sysctl_secure_tcp;
+#ifdef CONFIG_IP_VS_NFCT
+	int			sysctl_conntrack;
+#endif
+	int			sysctl_snat_reroute;
+	int			sysctl_sync_ver;
+	int			sysctl_cache_bypass;
+	int			sysctl_expire_nodest_conn;
+	int			sysctl_expire_quiescent_template;
+	int			sysctl_sync_threshold[2];
+	int			sysctl_nat_icmp_send;
+
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
 	struct ctl_table_header	*lblc_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 0d5e4feabc1b..5ba205a4d79c 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -686,13 +686,14 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 int ip_vs_check_template(struct ip_vs_conn *ct)
 {
 	struct ip_vs_dest *dest = ct->dest;
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct));
 
 	/*
 	 * Checking the dest server status.
 	 */
 	if ((dest == NULL) ||
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
-	    (sysctl_ip_vs_expire_quiescent_template &&
+	    (ipvs->sysctl_expire_quiescent_template &&
 	     (atomic_read(&dest->weight) == 0))) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
 			      "protocol %s s:%s:%d v:%s:%d "
@@ -879,7 +880,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	 * IP_VS_CONN_F_ONE_PACKET too.
 	 */
 
-	if (ip_vs_conntrack_enabled())
+	if (ip_vs_conntrack_enabled(ipvs))
 		cp->flags |= IP_VS_CONN_F_NFCT;
 
 	/* Hash it in the ip_vs_conn_tab finally */
@@ -1198,7 +1199,7 @@ static void ip_vs_conn_flush(struct net *net)
 	struct ip_vs_conn *cp;
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-  flush_again:
+flush_again:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		/*
 		 *  Lock is actually needed in this loop.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 7205b49c56c1..a7c59a722af3 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -499,6 +499,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		struct ip_vs_proto_data *pd)
 {
+	struct netns_ipvs *ipvs;
 	__be16 _ports[2], *pptr;
 	struct ip_vs_iphdr iph;
 	int unicast;
@@ -521,7 +522,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
 	   and the destination is a non-local unicast, then create
 	   a cache_bypass connection entry */
-	if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) {
+	ipvs = net_ipvs(skb_net(skb));
+	if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
 		int ret, cs;
 		struct ip_vs_conn *cp;
 		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
@@ -733,6 +735,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 				struct ip_vs_protocol *pp,
 				unsigned int offset, unsigned int ihl)
 {
+	struct netns_ipvs *ipvs;
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != 0) {
@@ -754,6 +757,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	if (!skb_make_writable(skb, offset))
 		goto out;
 
+	ipvs = net_ipvs(skb_net(skb));
+
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
 		ip_vs_nat_icmp_v6(skb, pp, cp, 1);
@@ -763,11 +768,11 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
 			goto out;
 	} else
 #endif
-		if ((sysctl_ip_vs_snat_reroute ||
+		if ((ipvs->sysctl_snat_reroute ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			goto out;
@@ -979,6 +984,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		struct ip_vs_conn *cp, int ihl)
 {
 	struct ip_vs_protocol *pp = pd->pp;
+	struct netns_ipvs *ipvs;
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
@@ -1014,13 +1020,15 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	 * if it came from this machine itself.  So re-compute
 	 * the routing information.
 	 */
+	ipvs = net_ipvs(skb_net(skb));
+
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
 			goto drop;
 	} else
 #endif
-		if ((sysctl_ip_vs_snat_reroute ||
+		if ((ipvs->sysctl_snat_reroute ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			goto drop;
@@ -1057,6 +1065,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs;
 
 	EnterFunction(11);
 
@@ -1131,10 +1140,11 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	 * Check if the packet belongs to an existing entry
 	 */
 	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
+	ipvs = net_ipvs(net);
 
 	if (likely(cp))
 		return handle_response(af, skb, pd, cp, iph.len);
-	if (sysctl_ip_vs_nat_icmp_send &&
+	if (ipvs->sysctl_nat_icmp_send &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
 	     pp->protocol == IPPROTO_SCTP)) {
@@ -1580,7 +1590,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
 
-		if (sysctl_ip_vs_expire_nodest_conn) {
+		if (ipvs->sysctl_expire_nodest_conn) {
 			/* try to expire the connection immediately */
 			ip_vs_conn_expire_now(cp);
 		}
@@ -1610,15 +1620,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 */
 
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
-		pkts = sysctl_ip_vs_sync_threshold[0];
+		pkts = ipvs->sysctl_sync_threshold[0];
 	else
 		pkts = atomic_add_return(1, &cp->in_pkts);
 
 	if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
-			(pkts % sysctl_ip_vs_sync_threshold[1]
-			 == sysctl_ip_vs_sync_threshold[0])) ||
+			(pkts % ipvs->sysctl_sync_threshold[1]
+			 == ipvs->sysctl_sync_threshold[0])) ||
 				(cp->old_state != cp->state &&
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
@@ -1632,8 +1642,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
-	      (pkts % sysctl_ip_vs_sync_threshold[1]
-	       == sysctl_ip_vs_sync_threshold[0])) ||
+	      (pkts % ipvs->sysctl_sync_threshold[1]
+	       == ipvs->sysctl_sync_threshold[0])) ||
 	     ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
 	      ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE) ||
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index cbd58c60e1bf..183ac18bded5 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -58,42 +58,7 @@ static DEFINE_MUTEX(__ip_vs_mutex);
 /* lock for service table */
 static DEFINE_RWLOCK(__ip_vs_svc_lock);
 
-/* lock for table with the real services */
-static DEFINE_RWLOCK(__ip_vs_rs_lock);
-
-/* lock for state and timeout tables */
-static DEFINE_SPINLOCK(ip_vs_securetcp_lock);
-
-/* lock for drop entry handling */
-static DEFINE_SPINLOCK(__ip_vs_dropentry_lock);
-
-/* lock for drop packet handling */
-static DEFINE_SPINLOCK(__ip_vs_droppacket_lock);
-
-/* 1/rate drop and drop-entry variables */
-int ip_vs_drop_rate = 0;
-int ip_vs_drop_counter = 0;
-static atomic_t ip_vs_dropentry = ATOMIC_INIT(0);
-
-/* number of virtual services */
-static int ip_vs_num_services = 0;
-
 /* sysctl variables */
-static int sysctl_ip_vs_drop_entry = 0;
-static int sysctl_ip_vs_drop_packet = 0;
-static int sysctl_ip_vs_secure_tcp = 0;
-static int sysctl_ip_vs_amemthresh = 1024;
-static int sysctl_ip_vs_am_droprate = 10;
-int sysctl_ip_vs_cache_bypass = 0;
-int sysctl_ip_vs_expire_nodest_conn = 0;
-int sysctl_ip_vs_expire_quiescent_template = 0;
-int sysctl_ip_vs_sync_threshold[2] = { 3, 50 };
-int sysctl_ip_vs_nat_icmp_send = 0;
-#ifdef CONFIG_IP_VS_NFCT
-int sysctl_ip_vs_conntrack;
-#endif
-int sysctl_ip_vs_snat_reroute = 1;
-int sysctl_ip_vs_sync_ver = 1;		/* Default version of sync proto */
 
 #ifdef CONFIG_IP_VS_DEBUG
 static int sysctl_ip_vs_debug_level = 0;
@@ -142,73 +107,73 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 	/* si_swapinfo(&i); */
 	/* availmem = availmem - (i.totalswap - i.freeswap); */
 
-	nomem = (availmem < sysctl_ip_vs_amemthresh);
+	nomem = (availmem < ipvs->sysctl_amemthresh);
 
 	local_bh_disable();
 
 	/* drop_entry */
-	spin_lock(&__ip_vs_dropentry_lock);
-	switch (sysctl_ip_vs_drop_entry) {
+	spin_lock(&ipvs->dropentry_lock);
+	switch (ipvs->sysctl_drop_entry) {
 	case 0:
-		atomic_set(&ip_vs_dropentry, 0);
+		atomic_set(&ipvs->dropentry, 0);
 		break;
 	case 1:
 		if (nomem) {
-			atomic_set(&ip_vs_dropentry, 1);
-			sysctl_ip_vs_drop_entry = 2;
+			atomic_set(&ipvs->dropentry, 1);
+			ipvs->sysctl_drop_entry = 2;
 		} else {
-			atomic_set(&ip_vs_dropentry, 0);
+			atomic_set(&ipvs->dropentry, 0);
 		}
 		break;
 	case 2:
 		if (nomem) {
-			atomic_set(&ip_vs_dropentry, 1);
+			atomic_set(&ipvs->dropentry, 1);
 		} else {
-			atomic_set(&ip_vs_dropentry, 0);
-			sysctl_ip_vs_drop_entry = 1;
+			atomic_set(&ipvs->dropentry, 0);
+			ipvs->sysctl_drop_entry = 1;
 		};
 		break;
 	case 3:
-		atomic_set(&ip_vs_dropentry, 1);
+		atomic_set(&ipvs->dropentry, 1);
 		break;
 	}
-	spin_unlock(&__ip_vs_dropentry_lock);
+	spin_unlock(&ipvs->dropentry_lock);
 
 	/* drop_packet */
-	spin_lock(&__ip_vs_droppacket_lock);
-	switch (sysctl_ip_vs_drop_packet) {
+	spin_lock(&ipvs->droppacket_lock);
+	switch (ipvs->sysctl_drop_packet) {
 	case 0:
-		ip_vs_drop_rate = 0;
+		ipvs->drop_rate = 0;
 		break;
 	case 1:
 		if (nomem) {
-			ip_vs_drop_rate = ip_vs_drop_counter
-				= sysctl_ip_vs_amemthresh /
-				(sysctl_ip_vs_amemthresh-availmem);
-			sysctl_ip_vs_drop_packet = 2;
+			ipvs->drop_rate = ipvs->drop_counter
+				= ipvs->sysctl_amemthresh /
+				(ipvs->sysctl_amemthresh-availmem);
+			ipvs->sysctl_drop_packet = 2;
 		} else {
-			ip_vs_drop_rate = 0;
+			ipvs->drop_rate = 0;
 		}
 		break;
 	case 2:
 		if (nomem) {
-			ip_vs_drop_rate = ip_vs_drop_counter
-				= sysctl_ip_vs_amemthresh /
-				(sysctl_ip_vs_amemthresh-availmem);
+			ipvs->drop_rate = ipvs->drop_counter
+				= ipvs->sysctl_amemthresh /
+				(ipvs->sysctl_amemthresh-availmem);
 		} else {
-			ip_vs_drop_rate = 0;
-			sysctl_ip_vs_drop_packet = 1;
+			ipvs->drop_rate = 0;
+			ipvs->sysctl_drop_packet = 1;
 		}
 		break;
 	case 3:
-		ip_vs_drop_rate = sysctl_ip_vs_am_droprate;
+		ipvs->drop_rate = ipvs->sysctl_am_droprate;
 		break;
 	}
-	spin_unlock(&__ip_vs_droppacket_lock);
+	spin_unlock(&ipvs->droppacket_lock);
 
 	/* secure_tcp */
-	spin_lock(&ip_vs_securetcp_lock);
-	switch (sysctl_ip_vs_secure_tcp) {
+	spin_lock(&ipvs->securetcp_lock);
+	switch (ipvs->sysctl_secure_tcp) {
 	case 0:
 		if (old_secure_tcp >= 2)
 			to_change = 0;
@@ -217,7 +182,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		if (nomem) {
 			if (old_secure_tcp < 2)
 				to_change = 1;
-			sysctl_ip_vs_secure_tcp = 2;
+			ipvs->sysctl_secure_tcp = 2;
 		} else {
 			if (old_secure_tcp >= 2)
 				to_change = 0;
@@ -230,7 +195,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		} else {
 			if (old_secure_tcp >= 2)
 				to_change = 0;
-			sysctl_ip_vs_secure_tcp = 1;
+			ipvs->sysctl_secure_tcp = 1;
 		}
 		break;
 	case 3:
@@ -238,11 +203,11 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 			to_change = 1;
 		break;
 	}
-	old_secure_tcp = sysctl_ip_vs_secure_tcp;
+	old_secure_tcp = ipvs->sysctl_secure_tcp;
 	if (to_change >= 0)
 		ip_vs_protocol_timeout_change(ipvs,
-					     sysctl_ip_vs_secure_tcp > 1);
-	spin_unlock(&ip_vs_securetcp_lock);
+					      ipvs->sysctl_secure_tcp > 1);
+	spin_unlock(&ipvs->securetcp_lock);
 
 	local_bh_enable();
 }
@@ -260,7 +225,7 @@ static void defense_work_handler(struct work_struct *work)
 	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 
 	update_defense_level(ipvs);
-	if (atomic_read(&ip_vs_dropentry))
+	if (atomic_read(&ipvs->dropentry))
 		ip_vs_random_dropentry();
 
 	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
@@ -602,7 +567,7 @@ ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 	 */
 	hash = ip_vs_rs_hashkey(af, daddr, dport);
 
-	read_lock(&__ip_vs_rs_lock);
+	read_lock(&ipvs->rs_lock);
 	list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) {
 		if ((dest->af == af)
 		    && ip_vs_addr_equal(af, &dest->addr, daddr)
@@ -610,11 +575,11 @@ ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 		    && ((dest->protocol == protocol) ||
 			dest->vfwmark)) {
 			/* HIT */
-			read_unlock(&__ip_vs_rs_lock);
+			read_unlock(&ipvs->rs_lock);
 			return dest;
 		}
 	}
-	read_unlock(&__ip_vs_rs_lock);
+	read_unlock(&ipvs->rs_lock);
 
 	return NULL;
 }
@@ -788,9 +753,9 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		 *    Put the real service in rs_table if not present.
 		 *    For now only for NAT!
 		 */
-		write_lock_bh(&__ip_vs_rs_lock);
+		write_lock_bh(&ipvs->rs_lock);
 		ip_vs_rs_hash(ipvs, dest);
-		write_unlock_bh(&__ip_vs_rs_lock);
+		write_unlock_bh(&ipvs->rs_lock);
 	}
 	atomic_set(&dest->conn_flags, conn_flags);
 
@@ -1022,14 +987,16 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
  */
 static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	ip_vs_kill_estimator(net, &dest->stats);
 
 	/*
 	 *  Remove it from the d-linked list with the real services.
 	 */
-	write_lock_bh(&__ip_vs_rs_lock);
+	write_lock_bh(&ipvs->rs_lock);
 	ip_vs_rs_unhash(dest);
-	write_unlock_bh(&__ip_vs_rs_lock);
+	write_unlock_bh(&ipvs->rs_lock);
 
 	/*
 	 *  Decrease the refcnt of the dest, and free the dest
@@ -1092,7 +1059,6 @@ static int
 ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 {
 	struct ip_vs_dest *dest;
-	struct net *net = svc->net;
 	__be16 dport = udest->port;
 
 	EnterFunction(2);
@@ -1121,7 +1087,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	/*
 	 *	Delete the destination
 	 */
-	__ip_vs_del_dest(net, dest);
+	__ip_vs_del_dest(svc->net, dest);
 
 	LeaveFunction(2);
 
@@ -1140,6 +1106,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	struct ip_vs_scheduler *sched = NULL;
 	struct ip_vs_pe *pe = NULL;
 	struct ip_vs_service *svc = NULL;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	/* increase the module use count */
 	ip_vs_use_count_inc();
@@ -1219,7 +1186,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
-		ip_vs_num_services++;
+		ipvs->num_services++;
 
 	/* Hash the service into the service table */
 	write_lock_bh(&__ip_vs_svc_lock);
@@ -1359,12 +1326,13 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	struct ip_vs_dest *dest, *nxt;
 	struct ip_vs_scheduler *old_sched;
 	struct ip_vs_pe *old_pe;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	pr_info("%s: enter\n", __func__);
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
-		ip_vs_num_services--;
+		ipvs->num_services--;
 
 	ip_vs_kill_estimator(svc->net, &svc->stats);
 
@@ -1589,42 +1557,31 @@ proc_do_sync_mode(ctl_table *table, int write,
 
 /*
  *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
+ *	Do not change order or insert new entries without
+ *	align with netns init in __ip_vs_control_init()
  */
 
 static struct ctl_table vs_vars[] = {
 	{
 		.procname	= "amemthresh",
-		.data		= &sysctl_ip_vs_amemthresh,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#ifdef CONFIG_IP_VS_DEBUG
-	{
-		.procname	= "debug_level",
-		.data		= &sysctl_ip_vs_debug_level,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#endif
 	{
 		.procname	= "am_droprate",
-		.data		= &sysctl_ip_vs_am_droprate,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
 	{
 		.procname	= "drop_entry",
-		.data		= &sysctl_ip_vs_drop_entry,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_do_defense_mode,
 	},
 	{
 		.procname	= "drop_packet",
-		.data		= &sysctl_ip_vs_drop_packet,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_do_defense_mode,
@@ -1632,7 +1589,6 @@ static struct ctl_table vs_vars[] = {
 #ifdef CONFIG_IP_VS_NFCT
 	{
 		.procname	= "conntrack",
-		.data		= &sysctl_ip_vs_conntrack,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
@@ -1640,25 +1596,62 @@ static struct ctl_table vs_vars[] = {
 #endif
 	{
 		.procname	= "secure_tcp",
-		.data		= &sysctl_ip_vs_secure_tcp,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_do_defense_mode,
 	},
 	{
 		.procname	= "snat_reroute",
-		.data		= &sysctl_ip_vs_snat_reroute,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
 	{
 		.procname	= "sync_version",
-		.data		= &sysctl_ip_vs_sync_ver,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_do_sync_mode,
 	},
+	{
+		.procname	= "cache_bypass",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "expire_nodest_conn",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "expire_quiescent_template",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sync_threshold",
+		.maxlen		=
+			sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold),
+		.mode		= 0644,
+		.proc_handler	= proc_do_sync_threshold,
+	},
+	{
+		.procname	= "nat_icmp_send",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#ifdef CONFIG_IP_VS_DEBUG
+	{
+		.procname	= "debug_level",
+		.data		= &sysctl_ip_vs_debug_level,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
 #if 0
 	{
 		.procname	= "timeout_established",
@@ -1745,41 +1738,6 @@ static struct ctl_table vs_vars[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 #endif
-	{
-		.procname	= "cache_bypass",
-		.data		= &sysctl_ip_vs_cache_bypass,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "expire_nodest_conn",
-		.data		= &sysctl_ip_vs_expire_nodest_conn,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "expire_quiescent_template",
-		.data		= &sysctl_ip_vs_expire_quiescent_template,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "sync_threshold",
-		.data		= &sysctl_ip_vs_sync_threshold,
-		.maxlen		= sizeof(sysctl_ip_vs_sync_threshold),
-		.mode		= 0644,
-		.proc_handler	= proc_do_sync_threshold,
-	},
-	{
-		.procname	= "nat_icmp_send",
-		.data		= &sysctl_ip_vs_nat_icmp_send,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{ }
 };
 
@@ -1791,8 +1749,6 @@ const struct ctl_path net_vs_ctl_path[] = {
 };
 EXPORT_SYMBOL_GPL(net_vs_ctl_path);
 
-static struct ctl_table_header * sysctl_header;
-
 #ifdef CONFIG_PROC_FS
 
 struct ip_vs_iter {
@@ -2543,7 +2499,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		struct ip_vs_getinfo info;
 		info.version = IP_VS_VERSION_CODE;
 		info.size = ip_vs_conn_tab_size;
-		info.num_services = ip_vs_num_services;
+		info.num_services = ipvs->num_services;
 		if (copy_to_user(user, &info, sizeof(info)) != 0)
 			ret = -EFAULT;
 	}
@@ -3014,7 +2970,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 	struct ip_vs_service *svc;
 	struct ip_vs_dest *dest;
 	struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1];
-	struct net *net;
+	struct net *net = skb_sknet(skb);
 
 	mutex_lock(&__ip_vs_mutex);
 
@@ -3023,7 +2979,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 			IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy))
 		goto out_err;
 
-	net = skb_sknet(skb);
+
 	svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]);
 	if (IS_ERR(svc) || svc == NULL)
 		goto out_err;
@@ -3215,8 +3171,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	int ret = 0, cmd;
 	int need_full_svc = 0, need_full_dest = 0;
 	struct net *net;
+	struct netns_ipvs *ipvs;
 
 	net = skb_sknet(skb);
+	ipvs = net_ipvs(net);
 	cmd = info->genlhdr->cmd;
 
 	mutex_lock(&__ip_vs_mutex);
@@ -3326,8 +3284,10 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	void *reply;
 	int ret, cmd, reply_cmd;
 	struct net *net;
+	struct netns_ipvs *ipvs;
 
 	net = skb_sknet(skb);
+	ipvs = net_ipvs(net);
 	cmd = info->genlhdr->cmd;
 
 	if (cmd == IPVS_CMD_GET_SERVICE)
@@ -3530,9 +3490,21 @@ int __net_init __ip_vs_control_init(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ctl_table *tbl;
 
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
+
+	atomic_set(&ipvs->dropentry, 0);
+	spin_lock_init(&ipvs->dropentry_lock);
+	spin_lock_init(&ipvs->droppacket_lock);
+	spin_lock_init(&ipvs->securetcp_lock);
+	ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock);
+
+	/* Initialize rs_table */
+	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
+		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
+
 	/* procfs stats */
 	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
 	if (ipvs->tot_stats == NULL) {
@@ -3553,14 +3525,51 @@ int __net_init __ip_vs_control_init(struct net *net)
 	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
 	proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
 			     &ip_vs_stats_percpu_fops);
-	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+
+	if (!net_eq(net, &init_net)) {
+		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
+		if (tbl == NULL)
+			goto err_dup;
+	} else
+		tbl = vs_vars;
+	/* Initialize sysctl defaults */
+	idx = 0;
+	ipvs->sysctl_amemthresh = 1024;
+	tbl[idx++].data = &ipvs->sysctl_amemthresh;
+	ipvs->sysctl_am_droprate = 10;
+	tbl[idx++].data = &ipvs->sysctl_am_droprate;
+	tbl[idx++].data = &ipvs->sysctl_drop_entry;
+	tbl[idx++].data = &ipvs->sysctl_drop_packet;
+#ifdef CONFIG_IP_VS_NFCT
+	tbl[idx++].data = &ipvs->sysctl_conntrack;
+#endif
+	tbl[idx++].data = &ipvs->sysctl_secure_tcp;
+	ipvs->sysctl_snat_reroute = 1;
+	tbl[idx++].data = &ipvs->sysctl_snat_reroute;
+	ipvs->sysctl_sync_ver = 1;
+	tbl[idx++].data = &ipvs->sysctl_sync_ver;
+	tbl[idx++].data = &ipvs->sysctl_cache_bypass;
+	tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
+	tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
+	ipvs->sysctl_sync_threshold[0] = 3;
+	ipvs->sysctl_sync_threshold[1] = 50;
+	tbl[idx].data = &ipvs->sysctl_sync_threshold;
+	tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
+	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
+
+
+	ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path,
 						  vs_vars);
-	if (sysctl_header == NULL)
+	if (ipvs->sysctl_hdr == NULL)
 		goto err_reg;
 	ip_vs_new_estimator(net, ipvs->tot_stats);
+	ipvs->sysctl_tbl = tbl;
 	return 0;
 
 err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(tbl);
+err_dup:
 	free_percpu(ipvs->cpustats);
 err_alloc:
 	kfree(ipvs->tot_stats);
@@ -3575,7 +3584,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 		return;
 
 	ip_vs_kill_estimator(net, ipvs->tot_stats);
-	unregister_net_sysctl_table(sysctl_header);
+	unregister_net_sysctl_table(ipvs->sysctl_hdr);
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 550365a690c7..fb2d04ac5d4e 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -34,7 +34,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 				     &iph.daddr, sh->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index d8b3f9f15826..c0cc341b840d 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -54,7 +54,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 				     &iph.daddr, th->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 581157bbded5..f1282cbe6fe3 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -50,7 +50,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	if (svc) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f85e47daecc3..b1780562c42b 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -394,7 +394,7 @@ void ip_vs_sync_switch_mode(struct net *net, int mode)
 
 	if (!ipvs->sync_state & IP_VS_STATE_MASTER)
 		return;
-	if (mode == sysctl_ip_vs_sync_ver || !ipvs->sync_buff)
+	if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff)
 		return;
 
 	spin_lock_bh(&ipvs->sync_buff_lock);
@@ -521,7 +521,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
 	unsigned int len, pe_name_len, pad;
 
 	/* Handle old version of the protocol */
-	if (sysctl_ip_vs_sync_ver == 0) {
+	if (ipvs->sysctl_sync_ver == 0) {
 		ip_vs_sync_conn_v0(net, cp);
 		return;
 	}
@@ -650,7 +650,7 @@ control:
 	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
 		int pkts = atomic_add_return(1, &cp->in_pkts);
 
-		if (pkts % sysctl_ip_vs_sync_threshold[1] != 1)
+		if (pkts % ipvs->sysctl_sync_threshold[1] != 1)
 			return;
 	}
 	goto sloop;
@@ -724,6 +724,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	if (!(flags & IP_VS_CONN_F_TEMPLATE))
 		cp = ip_vs_conn_in_get(param);
@@ -794,7 +795,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 
 	if (opt)
 		memcpy(&cp->in_seq, opt, sizeof(*opt));
-	atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
+	atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]);
 	cp->state = state;
 	cp->old_state = cp->state;
 	/*
-- 
cgit v1.2.3


From f6340ee0c6b9498ec918a7bb2f44e20abb8b2833 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:44:59 +0100
Subject: IPVS: netns, defense work timer.

This patch makes defense work timer per name-space,
A net ptr had to be added to the ipvs struct,
since it's needed by defense_work_handler.

[ horms@verge.net.au: Use cancel_delayed_work_sync() instead of
	              cancel_rearming_delayed_work(). Found during
		      merge conflict resoliution ]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  2 +-
 include/net/netns/ip_vs.h       |  3 +++
 net/netfilter/ipvs/ip_vs_conn.c |  5 +++--
 net/netfilter/ipvs/ip_vs_core.c |  1 +
 net/netfilter/ipvs/ip_vs_ctl.c  | 20 +++++++++-----------
 5 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index af9acf44e40a..fbe660f95873 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -877,7 +877,7 @@ extern const char * ip_vs_state_name(__u16 proto, int state);
 
 extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_check_template(struct ip_vs_conn *ct);
-extern void ip_vs_random_dropentry(void);
+extern void ip_vs_random_dropentry(struct net *net);
 extern int ip_vs_conn_init(void);
 extern void ip_vs_conn_cleanup(void);
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index c4b1abf258e4..41332619142c 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -71,6 +71,7 @@ struct netns_ipvs {
 
 	int			num_services;    /* no of virtual services */
 	/* 1/rate drop and drop-entry variables */
+	struct delayed_work	defense_work;   /* Work handler */
 	int			drop_rate;
 	int			drop_counter;
 	atomic_t		dropentry;
@@ -129,6 +130,8 @@ struct netns_ipvs {
 	/* multicast interface name */
 	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	/* net name space ptr */
+	struct net		*net;            /* Needed by timer routines */
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 5ba205a4d79c..28bdaf7c02f4 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1138,7 +1138,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp)
 }
 
 /* Called from keventd and must protect itself from softirqs */
-void ip_vs_random_dropentry(void)
+void ip_vs_random_dropentry(struct net *net)
 {
 	int idx;
 	struct ip_vs_conn *cp;
@@ -1158,7 +1158,8 @@ void ip_vs_random_dropentry(void)
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
 				/* connection template */
 				continue;
-
+			if (!ip_vs_conn_net_eq(cp, net))
+				continue;
 			if (cp->protocol == IPPROTO_TCP) {
 				switch(cp->state) {
 				case IP_VS_TCP_S_SYN_RECV:
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index a7c59a722af3..bdda346a4f30 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1884,6 +1884,7 @@ static int __net_init __ip_vs_init(struct net *net)
 		pr_err("%s(): no memory.\n", __func__);
 		return -ENOMEM;
 	}
+	ipvs->net = net;
 	/* Counters used for creating unique names */
 	ipvs->gen = atomic_read(&ipvs_netns_cnt);
 	atomic_inc(&ipvs_netns_cnt);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 183ac18bded5..6a963d44df48 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -217,18 +217,16 @@ static void update_defense_level(struct netns_ipvs *ipvs)
  *	Timer for checking the defense
  */
 #define DEFENSE_TIMER_PERIOD	1*HZ
-static void defense_work_handler(struct work_struct *work);
-static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
 
 static void defense_work_handler(struct work_struct *work)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs =
+		container_of(work, struct netns_ipvs, defense_work.work);
 
 	update_defense_level(ipvs);
 	if (atomic_read(&ipvs->dropentry))
-		ip_vs_random_dropentry();
-
-	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
+		ip_vs_random_dropentry(ipvs->net);
+	schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
 }
 
 int
@@ -3564,6 +3562,9 @@ int __net_init __ip_vs_control_init(struct net *net)
 		goto err_reg;
 	ip_vs_new_estimator(net, ipvs->tot_stats);
 	ipvs->sysctl_tbl = tbl;
+	/* Schedule defense work */
+	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
+	schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
 	return 0;
 
 err_reg:
@@ -3588,6 +3589,8 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
+	cancel_delayed_work_sync(&ipvs->defense_work);
+	cancel_work_sync(&ipvs->defense_work.work);
 	free_percpu(ipvs->cpustats);
 	kfree(ipvs->tot_stats);
 }
@@ -3631,9 +3634,6 @@ int __init ip_vs_control_init(void)
 		goto err_net;
 	}
 
-	/* Hook the defense timer */
-	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
-
 	LeaveFunction(2);
 	return 0;
 
@@ -3648,8 +3648,6 @@ void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
 	ip_vs_trash_cleanup();
-	cancel_delayed_work_sync(&defense_work);
-	cancel_work_sync(&defense_work.work);
 	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
-- 
cgit v1.2.3


From f2431e6e9255461eb1476340a89ad32ad4b38b03 Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:45:00 +0100
Subject: IPVS: netns, trash handling

trash list per namspace,
and reordering of some params in dst struct.

[ horms@verge.net.au: Use cancel_delayed_work_sync() instead of
	              cancel_rearming_delayed_work(). Found during
		      merge conflict resoliution ]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  4 ++--
 include/net/netns/ip_vs.h      |  3 +++
 net/netfilter/ipvs/ip_vs_ctl.c | 23 +++++++++++------------
 3 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index fbe660f95873..b23bea62f708 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -662,8 +662,8 @@ struct ip_vs_dest {
 	struct list_head	d_list;   /* for table with all the dests */
 
 	u16			af;		/* address family */
-	union nf_inet_addr	addr;		/* IP address of the server */
 	__be16			port;		/* port number of the server */
+	union nf_inet_addr	addr;		/* IP address of the server */
 	volatile unsigned	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
@@ -690,8 +690,8 @@ struct ip_vs_dest {
 	/* for virtual service */
 	struct ip_vs_service	*svc;		/* service it belongs to */
 	__u16			protocol;	/* which protocol (TCP/UDP) */
-	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__be16			vport;		/* virtual port number */
+	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__u32			vfwmark;	/* firewall mark of service */
 };
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 41332619142c..67ca1cf55af8 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -82,6 +82,9 @@ struct netns_ipvs {
 	rwlock_t		rs_lock;         /* real services table */
 	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
 	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* Trash for destinations */
+	struct list_head	dest_trash;
+
 	/* sys-ctl struct */
 	struct ctl_table_header	*sysctl_hdr;
 	struct ctl_table	*sysctl_tbl;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 6a963d44df48..442edf4be644 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -254,11 +254,6 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
 /* the service table hashed by fwmark */
 static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
 
-/*
- *	Trash for destinations
- */
-static LIST_HEAD(ip_vs_dest_trash);
-
 /*
  *	FTP & NULL virtual service counters
  */
@@ -650,11 +645,12 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 		     __be16 dport)
 {
 	struct ip_vs_dest *dest, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	/*
 	 * Find the destination in trash
 	 */
-	list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) {
+	list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
 		IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
 			      "dest->refcnt=%d\n",
 			      dest->vfwmark,
@@ -703,11 +699,12 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
  *  are expired, and the refcnt of each destination in the trash must
  *  be 1, so we simply release them here.
  */
-static void ip_vs_trash_cleanup(void)
+static void ip_vs_trash_cleanup(struct net *net)
 {
 	struct ip_vs_dest *dest, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) {
+	list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
 		list_del(&dest->n_list);
 		ip_vs_dst_reset(dest);
 		__ip_vs_unbind_svc(dest);
@@ -1021,7 +1018,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
 			      atomic_read(&dest->refcnt));
-		list_add(&dest->n_list, &ip_vs_dest_trash);
+		list_add(&dest->n_list, &ipvs->dest_trash);
 		atomic_inc(&dest->refcnt);
 	}
 }
@@ -3503,6 +3500,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
 		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
 
+	INIT_LIST_HEAD(&ipvs->dest_trash);
+
 	/* procfs stats */
 	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
 	if (ipvs->tot_stats == NULL) {
@@ -3584,13 +3583,14 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
+	ip_vs_trash_cleanup(net);
 	ip_vs_kill_estimator(net, ipvs->tot_stats);
+	cancel_delayed_work_sync(&ipvs->defense_work);
+	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
-	cancel_delayed_work_sync(&ipvs->defense_work);
-	cancel_work_sync(&ipvs->defense_work.work);
 	free_percpu(ipvs->cpustats);
 	kfree(ipvs->tot_stats);
 }
@@ -3647,7 +3647,6 @@ err:
 void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
-	ip_vs_trash_cleanup();
 	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
-- 
cgit v1.2.3


From 763f8d0ed4f1ce38b35cc0e05482b7799b82789b Mon Sep 17 00:00:00 2001
From: Hans Schillstrom <hans.schillstrom@ericsson.com>
Date: Mon, 3 Jan 2011 14:45:01 +0100
Subject: IPVS: netns, svc counters moved in ip_vs_ctl,c

Last two global vars to be moved,
ip_vs_ftpsvc_counter and ip_vs_nullsvc_counter.

[horms@verge.net.au: removed whitespace-change-only hunk]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h      |  3 +++
 net/netfilter/ipvs/ip_vs_ctl.c | 21 +++++++++------------
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 67ca1cf55af8..259ebac904bf 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -84,6 +84,9 @@ struct netns_ipvs {
 	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
 	/* Trash for destinations */
 	struct list_head	dest_trash;
+	/* Service counters */
+	atomic_t		ftpsvc_counter;
+	atomic_t		nullsvc_counter;
 
 	/* sys-ctl struct */
 	struct ctl_table_header	*sysctl_hdr;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 442edf4be644..65f5de405ad2 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -254,12 +254,6 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
 /* the service table hashed by fwmark */
 static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
 
-/*
- *	FTP & NULL virtual service counters
- */
-static atomic_t ip_vs_ftpsvc_counter = ATOMIC_INIT(0);
-static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0);
-
 
 /*
  *	Returns hash value for virtual service
@@ -409,6 +403,7 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport)
 {
 	struct ip_vs_service *svc;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	read_lock(&__ip_vs_svc_lock);
 
@@ -427,7 +422,7 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 
 	if (svc == NULL
 	    && protocol == IPPROTO_TCP
-	    && atomic_read(&ip_vs_ftpsvc_counter)
+	    && atomic_read(&ipvs->ftpsvc_counter)
 	    && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) {
 		/*
 		 * Check if ftp service entry exists, the packet
@@ -437,7 +432,7 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 	}
 
 	if (svc == NULL
-	    && atomic_read(&ip_vs_nullsvc_counter)) {
+	    && atomic_read(&ipvs->nullsvc_counter)) {
 		/*
 		 * Check if the catch-all port (port zero) exists
 		 */
@@ -1173,9 +1168,9 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 
 	/* Update the virtual service counters */
 	if (svc->port == FTPPORT)
-		atomic_inc(&ip_vs_ftpsvc_counter);
+		atomic_inc(&ipvs->ftpsvc_counter);
 	else if (svc->port == 0)
-		atomic_inc(&ip_vs_nullsvc_counter);
+		atomic_inc(&ipvs->nullsvc_counter);
 
 	ip_vs_new_estimator(net, &svc->stats);
 
@@ -1359,9 +1354,9 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	 *    Update the virtual service counters
 	 */
 	if (svc->port == FTPPORT)
-		atomic_dec(&ip_vs_ftpsvc_counter);
+		atomic_dec(&ipvs->ftpsvc_counter);
 	else if (svc->port == 0)
-		atomic_dec(&ip_vs_nullsvc_counter);
+		atomic_dec(&ipvs->nullsvc_counter);
 
 	/*
 	 *    Free the service if nobody refers to it
@@ -3501,6 +3496,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
 
 	INIT_LIST_HEAD(&ipvs->dest_trash);
+	atomic_set(&ipvs->ftpsvc_counter, 0);
+	atomic_set(&ipvs->nullsvc_counter, 0);
 
 	/* procfs stats */
 	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
-- 
cgit v1.2.3


From 5df15196a2bbf16ca4c6a797ec00ff36d0d5c179 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Sun, 26 Dec 2010 10:22:22 +0100
Subject: netfilter: xt_comment: drop unneeded unsigned qualifier

Since a string is stored, and not something like a MAC address that
would rely on (un)signedness, drop the qualifier.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/xt_comment.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h
index eacfedc6b5d0..0ea5e79f5bd7 100644
--- a/include/linux/netfilter/xt_comment.h
+++ b/include/linux/netfilter/xt_comment.h
@@ -4,7 +4,7 @@
 #define XT_MAX_COMMENT_LEN 256
 
 struct xt_comment_info {
-	unsigned char comment[XT_MAX_COMMENT_LEN];
+	char comment[XT_MAX_COMMENT_LEN];
 };
 
 #endif /* XT_COMMENT_H */
-- 
cgit v1.2.3


From b017900aac4a158b9bf7ffdcb8a369a91115b3e4 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Wed, 15 Dec 2010 09:46:26 +0100
Subject: netfilter: xt_conntrack: support matching on port ranges

Add a new revision 3 that contains port ranges for all of origsrc,
origdst, replsrc and repldst. The high ports are appended to the
original v2 data structure to allow sharing most of the code with
v1 and v2. Use of the revision specific port matching function is
made dependant on par->match->revision.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/xt_conntrack.h | 15 +++++++
 net/netfilter/xt_conntrack.c           | 75 +++++++++++++++++++++++++++++++++-
 2 files changed, 88 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h
index 54f47a2f6152..74b904d8f99c 100644
--- a/include/linux/netfilter/xt_conntrack.h
+++ b/include/linux/netfilter/xt_conntrack.h
@@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 {
 	__u16 state_mask, status_mask;
 };
 
+struct xt_conntrack_mtinfo3 {
+	union nf_inet_addr origsrc_addr, origsrc_mask;
+	union nf_inet_addr origdst_addr, origdst_mask;
+	union nf_inet_addr replsrc_addr, replsrc_mask;
+	union nf_inet_addr repldst_addr, repldst_mask;
+	__u32 expires_min, expires_max;
+	__u16 l4proto;
+	__u16 origsrc_port, origdst_port;
+	__u16 replsrc_port, repldst_port;
+	__u16 match_flags, invert_flags;
+	__u16 state_mask, status_mask;
+	__u16 origsrc_port_high, origdst_port_high;
+	__u16 replsrc_port_high, repldst_port_high;
+};
+
 #endif /*_XT_CONNTRACK_H*/
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index e536710ad916..4ef1b63ad73f 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -112,6 +112,54 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info,
 	return true;
 }
 
+static inline bool
+port_match(u16 min, u16 max, u16 port, bool invert)
+{
+	return (port >= min && port <= max) ^ invert;
+}
+
+static inline bool
+ct_proto_port_check_v3(const struct xt_conntrack_mtinfo3 *info,
+		       const struct nf_conn *ct)
+{
+	const struct nf_conntrack_tuple *tuple;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+	if ((info->match_flags & XT_CONNTRACK_PROTO) &&
+	    (nf_ct_protonum(ct) == info->l4proto) ^
+	    !(info->invert_flags & XT_CONNTRACK_PROTO))
+		return false;
+
+	/* Shortcut to match all recognized protocols by using ->src.all. */
+	if ((info->match_flags & XT_CONNTRACK_ORIGSRC_PORT) &&
+	    !port_match(info->origsrc_port, info->origsrc_port_high,
+			ntohs(tuple->src.u.all),
+			info->invert_flags & XT_CONNTRACK_ORIGSRC_PORT))
+		return false;
+
+	if ((info->match_flags & XT_CONNTRACK_ORIGDST_PORT) &&
+	    !port_match(info->origdst_port, info->origdst_port_high,
+			ntohs(tuple->dst.u.all),
+			info->invert_flags & XT_CONNTRACK_ORIGDST_PORT))
+		return false;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+
+	if ((info->match_flags & XT_CONNTRACK_REPLSRC_PORT) &&
+	    !port_match(info->replsrc_port, info->replsrc_port_high,
+			ntohs(tuple->src.u.all),
+			info->invert_flags & XT_CONNTRACK_REPLSRC_PORT))
+		return false;
+
+	if ((info->match_flags & XT_CONNTRACK_REPLDST_PORT) &&
+	    !port_match(info->repldst_port, info->repldst_port_high,
+			ntohs(tuple->dst.u.all),
+			info->invert_flags & XT_CONNTRACK_REPLDST_PORT))
+		return false;
+
+	return true;
+}
+
 static bool
 conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
              u16 state_mask, u16 status_mask)
@@ -170,8 +218,13 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
 		    !(info->invert_flags & XT_CONNTRACK_REPLDST))
 			return false;
 
-	if (!ct_proto_port_check(info, ct))
-		return false;
+	if (par->match->revision != 3) {
+		if (!ct_proto_port_check(info, ct))
+			return false;
+	} else {
+		if (!ct_proto_port_check_v3(par->matchinfo, ct))
+			return false;
+	}
 
 	if ((info->match_flags & XT_CONNTRACK_STATUS) &&
 	    (!!(status_mask & ct->status) ^
@@ -207,6 +260,14 @@ conntrack_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
 }
 
+static bool
+conntrack_mt_v3(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_conntrack_mtinfo3 *info = par->matchinfo;
+
+	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
+}
+
 static int conntrack_mt_check(const struct xt_mtchk_param *par)
 {
 	int ret;
@@ -244,6 +305,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
 		.destroy    = conntrack_mt_destroy,
 		.me         = THIS_MODULE,
 	},
+	{
+		.name       = "conntrack",
+		.revision   = 3,
+		.family     = NFPROTO_UNSPEC,
+		.matchsize  = sizeof(struct xt_conntrack_mtinfo3),
+		.match      = conntrack_mt_v3,
+		.checkentry = conntrack_mt_check,
+		.destroy    = conntrack_mt_destroy,
+		.me         = THIS_MODULE,
+	},
 };
 
 static int __init conntrack_mt_init(void)
-- 
cgit v1.2.3


From 255d0dc34068a976550ce555e153c0bfcfec7cc6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 18 Dec 2010 18:35:15 +0100
Subject: netfilter: x_table: speedup compat operations

One iptables invocation with 135000 rules takes 35 seconds of cpu time
on a recent server, using a 32bit distro and a 64bit kernel.

We eventually trigger NMI/RCU watchdog.

INFO: rcu_sched_state detected stall on CPU 3 (t=6000 jiffies)

COMPAT mode has quadratic behavior and consume 16 bytes of memory per
rule.

Switch the xt_compat algos to use an array instead of list, and use a
binary search to locate an offset in the sorted array.

This halves memory need (8 bytes per rule), and removes quadratic
behavior [ O(N*N) -> O(N*log2(N)) ]

Time of iptables goes from 35 s to 150 ms.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h |  3 +-
 net/bridge/netfilter/ebtables.c    |  1 +
 net/ipv4/netfilter/arp_tables.c    |  2 +
 net/ipv4/netfilter/ip_tables.c     |  2 +
 net/ipv6/netfilter/ip6_tables.c    |  2 +
 net/netfilter/x_tables.c           | 82 ++++++++++++++++++++++----------------
 6 files changed, 57 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 742bec051440..0f04d985b41c 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -611,8 +611,9 @@ struct _compat_xt_align {
 extern void xt_compat_lock(u_int8_t af);
 extern void xt_compat_unlock(u_int8_t af);
 
-extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta);
+extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
 extern void xt_compat_flush_offsets(u_int8_t af);
+extern void xt_compat_init_offsets(u_int8_t af, unsigned int number);
 extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
 
 extern int xt_compat_match_offset(const struct xt_match *match);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 16df0532d4b9..5f1825df9dca 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1764,6 +1764,7 @@ static int compat_table_info(const struct ebt_table_info *info,
 
 	newinfo->entries_size = size;
 
+	xt_compat_init_offsets(AF_INET, info->nentries);
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);
 }
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 3fac340a28d5..47e5178b998b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -883,6 +883,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(NFPROTO_ARP, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1350,6 +1351,7 @@ static int translate_compat_table(const char *name,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
+	xt_compat_init_offsets(NFPROTO_ARP, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a846d633b3b6..c5a75d70970f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1080,6 +1080,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1681,6 +1682,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
+	xt_compat_init_offsets(AF_INET, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 455582384ece..0c9973a657fb 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1093,6 +1093,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET6, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1696,6 +1697,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
+	xt_compat_init_offsets(AF_INET6, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 80463507420e..ee5de3af510a 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -38,9 +38,8 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
 #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))
 
 struct compat_delta {
-	struct compat_delta *next;
-	unsigned int offset;
-	int delta;
+	unsigned int offset; /* offset in kernel */
+	int delta; /* delta in 32bit user land */
 };
 
 struct xt_af {
@@ -49,7 +48,9 @@ struct xt_af {
 	struct list_head target;
 #ifdef CONFIG_COMPAT
 	struct mutex compat_mutex;
-	struct compat_delta *compat_offsets;
+	struct compat_delta *compat_tab;
+	unsigned int number; /* number of slots in compat_tab[] */
+	unsigned int cur; /* number of used slots in compat_tab[] */
 #endif
 };
 
@@ -414,54 +415,67 @@ int xt_check_match(struct xt_mtchk_param *par,
 EXPORT_SYMBOL_GPL(xt_check_match);
 
 #ifdef CONFIG_COMPAT
-int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta)
+int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
 {
-	struct compat_delta *tmp;
+	struct xt_af *xp = &xt[af];
 
-	tmp = kmalloc(sizeof(struct compat_delta), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
+	if (!xp->compat_tab) {
+		if (!xp->number)
+			return -EINVAL;
+		xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number);
+		if (!xp->compat_tab)
+			return -ENOMEM;
+		xp->cur = 0;
+	}
 
-	tmp->offset = offset;
-	tmp->delta = delta;
+	if (xp->cur >= xp->number)
+		return -EINVAL;
 
-	if (xt[af].compat_offsets) {
-		tmp->next = xt[af].compat_offsets->next;
-		xt[af].compat_offsets->next = tmp;
-	} else {
-		xt[af].compat_offsets = tmp;
-		tmp->next = NULL;
-	}
+	if (xp->cur)
+		delta += xp->compat_tab[xp->cur - 1].delta;
+	xp->compat_tab[xp->cur].offset = offset;
+	xp->compat_tab[xp->cur].delta = delta;
+	xp->cur++;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_add_offset);
 
 void xt_compat_flush_offsets(u_int8_t af)
 {
-	struct compat_delta *tmp, *next;
-
-	if (xt[af].compat_offsets) {
-		for (tmp = xt[af].compat_offsets; tmp; tmp = next) {
-			next = tmp->next;
-			kfree(tmp);
-		}
-		xt[af].compat_offsets = NULL;
+	if (xt[af].compat_tab) {
+		vfree(xt[af].compat_tab);
+		xt[af].compat_tab = NULL;
+		xt[af].number = 0;
 	}
 }
 EXPORT_SYMBOL_GPL(xt_compat_flush_offsets);
 
 int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
 {
-	struct compat_delta *tmp;
-	int delta;
-
-	for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next)
-		if (tmp->offset < offset)
-			delta += tmp->delta;
-	return delta;
+	struct compat_delta *tmp = xt[af].compat_tab;
+	int mid, left = 0, right = xt[af].cur - 1;
+
+	while (left <= right) {
+		mid = (left + right) >> 1;
+		if (offset > tmp[mid].offset)
+			left = mid + 1;
+		else if (offset < tmp[mid].offset)
+			right = mid - 1;
+		else
+			return mid ? tmp[mid - 1].delta : 0;
+	}
+	WARN_ON_ONCE(1);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_calc_jump);
 
+void xt_compat_init_offsets(u_int8_t af, unsigned int number)
+{
+	xt[af].number = number;
+	xt[af].cur = 0;
+}
+EXPORT_SYMBOL(xt_compat_init_offsets);
+
 int xt_compat_match_offset(const struct xt_match *match)
 {
 	u_int16_t csize = match->compatsize ? : match->matchsize;
@@ -1337,7 +1351,7 @@ static int __init xt_init(void)
 		mutex_init(&xt[i].mutex);
 #ifdef CONFIG_COMPAT
 		mutex_init(&xt[i].compat_mutex);
-		xt[i].compat_offsets = NULL;
+		xt[i].compat_tab = NULL;
 #endif
 		INIT_LIST_HEAD(&xt[i].target);
 		INIT_LIST_HEAD(&xt[i].match);
-- 
cgit v1.2.3


From 6faee60a4e82075853a437831768cc9e2e563e4e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 20 Dec 2010 15:57:47 +0100
Subject: netfilter: ebt_ip6: allow matching on ipv6-icmp types/codes

To avoid adding a new match revision icmp type/code are stored
in the sport/dport area.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Holger Eitzenberger <holger@eitzenberger.org>
Reviewed-by: Bart De Schuymer<bdschuym@pandora.be>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge/ebt_ip6.h | 15 ++++++++---
 net/bridge/netfilter/ebt_ip6.c           | 46 +++++++++++++++++++++++---------
 2 files changed, 46 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h
index e5de98701519..22af18a3c16b 100644
--- a/include/linux/netfilter_bridge/ebt_ip6.h
+++ b/include/linux/netfilter_bridge/ebt_ip6.h
@@ -18,8 +18,11 @@
 #define EBT_IP6_PROTO 0x08
 #define EBT_IP6_SPORT 0x10
 #define EBT_IP6_DPORT 0x20
+#define EBT_IP6_ICMP6 0x40
+
 #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\
-		      EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT)
+		      EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \
+		      EBT_IP6_ICMP6)
 #define EBT_IP6_MATCH "ip6"
 
 /* the same values are used for the invflags */
@@ -32,8 +35,14 @@ struct ebt_ip6_info {
 	uint8_t  protocol;
 	uint8_t  bitmask;
 	uint8_t  invflags;
-	uint16_t sport[2];
-	uint16_t dport[2];
+	union {
+		uint16_t sport[2];
+		uint8_t icmpv6_type[2];
+	};
+	union {
+		uint16_t dport[2];
+		uint8_t icmpv6_code[2];
+	};
 };
 
 #endif
diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c
index 50a46afc2bcc..2ed0056a39a8 100644
--- a/net/bridge/netfilter/ebt_ip6.c
+++ b/net/bridge/netfilter/ebt_ip6.c
@@ -22,9 +22,15 @@
 #include <linux/netfilter_bridge/ebtables.h>
 #include <linux/netfilter_bridge/ebt_ip6.h>
 
-struct tcpudphdr {
-	__be16 src;
-	__be16 dst;
+union pkthdr {
+	struct {
+		__be16 src;
+		__be16 dst;
+	} tcpudphdr;
+	struct {
+		u8 type;
+		u8 code;
+	} icmphdr;
 };
 
 static bool
@@ -33,8 +39,8 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	const struct ebt_ip6_info *info = par->matchinfo;
 	const struct ipv6hdr *ih6;
 	struct ipv6hdr _ip6h;
-	const struct tcpudphdr *pptr;
-	struct tcpudphdr _ports;
+	const union pkthdr *pptr;
+	union pkthdr _pkthdr;
 
 	ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
 	if (ih6 == NULL)
@@ -56,26 +62,34 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			return false;
 		if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
 			return false;
-		if (!(info->bitmask & EBT_IP6_DPORT) &&
-		    !(info->bitmask & EBT_IP6_SPORT))
+		if (!(info->bitmask & ( EBT_IP6_DPORT |
+					EBT_IP6_SPORT | EBT_IP6_ICMP6)))
 			return true;
-		pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports),
-					  &_ports);
+
+		/* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */
+		pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr),
+					  &_pkthdr);
 		if (pptr == NULL)
 			return false;
 		if (info->bitmask & EBT_IP6_DPORT) {
-			u32 dst = ntohs(pptr->dst);
+			u16 dst = ntohs(pptr->tcpudphdr.dst);
 			if (FWINV(dst < info->dport[0] ||
 				  dst > info->dport[1], EBT_IP6_DPORT))
 				return false;
 		}
 		if (info->bitmask & EBT_IP6_SPORT) {
-			u32 src = ntohs(pptr->src);
+			u16 src = ntohs(pptr->tcpudphdr.src);
 			if (FWINV(src < info->sport[0] ||
 				  src > info->sport[1], EBT_IP6_SPORT))
 			return false;
 		}
-		return true;
+		if ((info->bitmask & EBT_IP6_ICMP6) &&
+		     FWINV(pptr->icmphdr.type < info->icmpv6_type[0] ||
+			   pptr->icmphdr.type > info->icmpv6_type[1] ||
+			   pptr->icmphdr.code < info->icmpv6_code[0] ||
+			   pptr->icmphdr.code > info->icmpv6_code[1],
+							EBT_IP6_ICMP6))
+			return false;
 	}
 	return true;
 }
@@ -103,6 +117,14 @@ static int ebt_ip6_mt_check(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1])
 		return -EINVAL;
+	if (info->bitmask & EBT_IP6_ICMP6) {
+		if ((info->invflags & EBT_IP6_PROTO) ||
+		     info->protocol != IPPROTO_ICMPV6)
+			return -EINVAL;
+		if (info->icmpv6_type[0] > info->icmpv6_type[1] ||
+		    info->icmpv6_code[0] > info->icmpv6_code[1])
+			return -EINVAL;
+	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From c7066f70d9610df0b9406cc635fc09e86136e714 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 14 Jan 2011 13:36:42 +0100
Subject: netfilter: fix Kconfig dependencies

Fix dependencies of netfilter realm match: it depends on NET_CLS_ROUTE,
which itself depends on NET_SCHED; this dependency is missing from netfilter.

Since matching on realms is also useful without having NET_SCHED enabled and
the option really only controls whether the tclassid member is included in
route and dst entries, rename the config option to IP_ROUTE_CLASSID and move
it outside of traffic scheduling context to get rid of the NET_SCHED dependeny.

Reported-by: Vladis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/dst.h        |  2 +-
 include/net/ip_fib.h     |  6 +++---
 net/ipv4/Kconfig         |  4 +++-
 net/ipv4/fib_rules.c     | 10 +++++-----
 net/ipv4/fib_semantics.c | 14 +++++++-------
 net/ipv4/ip_input.c      |  2 +-
 net/ipv4/route.c         | 26 +++++++++++++-------------
 net/netfilter/Kconfig    |  2 +-
 net/sched/Kconfig        |  5 +----
 net/sched/cls_flow.c     |  2 +-
 net/sched/em_meta.c      |  2 +-
 11 files changed, 37 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index a5bd72646d65..6baba836ad8b 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -72,7 +72,7 @@ struct dst_entry {
 
 	u32			metrics[RTAX_MAX];
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			tclassid;
 #else
 	__u32			__pad2;
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 07bdb5e9e8ac..65d1fcdbc63b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -55,7 +55,7 @@ struct fib_nh {
 	int			nh_weight;
 	int			nh_power;
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			nh_tclassid;
 #endif
 	int			nh_oif;
@@ -201,7 +201,7 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp,
 extern int __net_init fib4_rules_init(struct net *net);
 extern void __net_exit fib4_rules_exit(struct net *net);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 extern u32 fib_rules_tclass(struct fib_result *res);
 #endif
 
@@ -235,7 +235,7 @@ extern struct fib_table *fib_hash_table(u32 id);
 
 static inline void fib_combine_itag(u32 *itag, struct fib_result *res)
 {
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	u32 rtag;
 #endif
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 9e95d7fb6d5a..dcb2e18f6f8e 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -140,6 +140,9 @@ config IP_ROUTE_VERBOSE
 	  handled by the klogd daemon which is responsible for kernel messages
 	  ("man klogd").
 
+config IP_ROUTE_CLASSID
+	bool
+
 config IP_PNP
 	bool "IP: kernel level autoconfiguration"
 	help
@@ -655,4 +658,3 @@ config TCP_MD5SIG
 	  on the Internet.
 
 	  If unsure, say N.
-
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 7981a24f5c7b..9cefe72029cf 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -41,12 +41,12 @@ struct fib4_rule {
 	__be32			srcmask;
 	__be32			dst;
 	__be32			dstmask;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	u32			tclassid;
 #endif
 };
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 u32 fib_rules_tclass(struct fib_result *res)
 {
 	return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0;
@@ -165,7 +165,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (frh->dst_len)
 		rule4->dst = nla_get_be32(tb[FRA_DST]);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW])
 		rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
 #endif
@@ -195,7 +195,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->tos && (rule4->tos != frh->tos))
 		return 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
 		return 0;
 #endif
@@ -224,7 +224,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	if (rule4->src_len)
 		NLA_PUT_BE32(skb, FRA_SRC, rule4->src);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rule4->tclassid)
 		NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid);
 #endif
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3e0da3ef6116..a72c62d03106 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -200,7 +200,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		    nh->nh_weight != onh->nh_weight ||
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		    nh->nh_tclassid != onh->nh_tclassid ||
 #endif
 		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD))
@@ -422,7 +422,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
 #endif
@@ -476,7 +476,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla && nla_get_be32(nla) != nh->nh_gw)
 				return 1;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
 				return 1;
@@ -783,7 +783,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 			goto err_inval;
 		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
 			goto err_inval;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
 			goto err_inval;
 #endif
@@ -796,7 +796,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 		nh->nh_oif = cfg->fc_oif;
 		nh->nh_gw = cfg->fc_gw;
 		nh->nh_flags = cfg->fc_flags;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		nh->nh_tclassid = cfg->fc_flow;
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1006,7 +1006,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 
 		if (fi->fib_nh->nh_oif)
 			NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid)
 			NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
 #endif
@@ -1031,7 +1031,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 
 			if (nh->nh_gw)
 				NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			if (nh->nh_tclassid)
 				NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
 #endif
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d859bcc26cb7..d7b2b0987a3b 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -340,7 +340,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 		}
 	}
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (unlikely(skb_dst(skb)->tclassid)) {
 		struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
 		u32 idx = skb_dst(skb)->tclassid;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 66610ea3c87b..f70ae1bccb8a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -511,7 +511,7 @@ static const struct file_operations rt_cpu_seq_fops = {
 	.release = seq_release,
 };
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 static int rt_acct_proc_show(struct seq_file *m, void *v)
 {
 	struct ip_rt_acct *dst, *src;
@@ -564,14 +564,14 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
 	if (!pde)
 		goto err2;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
 	if (!pde)
 		goto err3;
 #endif
 	return 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 err3:
 	remove_proc_entry("rt_cache", net->proc_net_stat);
 #endif
@@ -585,7 +585,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net)
 {
 	remove_proc_entry("rt_cache", net->proc_net_stat);
 	remove_proc_entry("rt_cache", net->proc_net);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	remove_proc_entry("rt_acct", net->proc_net);
 #endif
 }
@@ -1784,7 +1784,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 	memcpy(addr, &src, 4);
 }
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 static void set_class_tag(struct rtable *rt, u32 tag)
 {
 	if (!(rt->dst.tclassid & 0xFFFF))
@@ -1811,7 +1811,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 			    rt->dst.dev->mtu > 576)
 				rt->dst.metrics[RTAX_MTU-1] = 576;
 		}
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
 #endif
 	} else
@@ -1827,7 +1827,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 	if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40)
 		rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	set_class_tag(rt, fib_rules_tclass(res));
 #endif
@@ -1883,7 +1883,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->fl.mark    = skb->mark;
 	rth->fl.fl4_src	= saddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_iif	=
@@ -2202,7 +2202,7 @@ local_input:
 	rth->fl.mark    = skb->mark;
 	rth->fl.fl4_src	= saddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_iif	=
@@ -2820,7 +2820,7 @@ static int rt_fill_info(struct net *net,
 	}
 	if (rt->dst.dev)
 		NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rt->dst.tclassid)
 		NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
 #endif
@@ -3245,9 +3245,9 @@ static __net_initdata struct pernet_operations rt_genid_ops = {
 };
 
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
-#endif /* CONFIG_NET_CLS_ROUTE */
+#endif /* CONFIG_IP_ROUTE_CLASSID */
 
 static __initdata unsigned long rhash_entries;
 static int __init set_rhash_entries(char *str)
@@ -3263,7 +3263,7 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
 		panic("IP: failed to allocate ip_rt_acct\n");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 1534f2b44caf..1b79353a5d29 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -886,7 +886,7 @@ config NETFILTER_XT_MATCH_RATEEST
 config NETFILTER_XT_MATCH_REALM
 	tristate  '"realm" match support'
 	depends on NETFILTER_ADVANCED
-	select NET_CLS_ROUTE
+	select IP_ROUTE_CLASSID
 	help
 	  This option adds a `realm' match, which allows you to use the realm
 	  key from the routing subsystem inside iptables.
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a36270a994d7..4b753ef70bb7 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -243,7 +243,7 @@ config NET_CLS_TCINDEX
 
 config NET_CLS_ROUTE4
 	tristate "Routing decision (ROUTE)"
-	select NET_CLS_ROUTE
+	select IP_ROUTE_CLASSID
 	select NET_CLS
 	---help---
 	  If you say Y here, you will be able to classify packets
@@ -252,9 +252,6 @@ config NET_CLS_ROUTE4
 	  To compile this code as a module, choose M here: the
 	  module will be called cls_route.
 
-config NET_CLS_ROUTE
-	bool
-
 config NET_CLS_FW
 	tristate "Netfilter mark (FW)"
 	select NET_CLS
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 5b271a18bc3a..a3b293d22c66 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -276,7 +276,7 @@ fallback:
 
 static u32 flow_get_rtclassid(const struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (skb_dst(skb))
 		return skb_dst(skb)->tclassid;
 #endif
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 34da5e29ea1a..0d66e58f26d8 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -255,7 +255,7 @@ META_COLLECTOR(int_rtclassid)
 	if (unlikely(skb_dst(skb) == NULL))
 		*err = -1;
 	else
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		dst->value = skb_dst(skb)->tclassid;
 #else
 		dst->value = 0;
-- 
cgit v1.2.3


From d862a6622e9db508d4b28cc7c5bc28bd548cc24e Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 14 Jan 2011 15:45:56 +0100
Subject: netfilter: nf_conntrack: use is_vmalloc_addr()

Use is_vmalloc_addr() in nf_ct_free_hashtable() and get rid of
the vmalloc flags to indicate that a hash table has been allocated
using vmalloc().

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h |  4 ++--
 include/net/netns/conntrack.h        |  2 --
 include/net/netns/ipv4.h             |  1 -
 net/ipv4/netfilter/nf_nat_core.c     |  6 ++----
 net/netfilter/nf_conntrack_core.c    | 26 +++++++++-----------------
 net/netfilter/nf_conntrack_expect.c  |  9 +++------
 net/netfilter/nf_conntrack_helper.c  | 10 +++-------
 7 files changed, 19 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 2bc344c98215..d0d13378991e 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -202,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto);
  * Allocate a hashtable of hlist_head (if nulls == 0),
  * or hlist_nulls_head (if nulls == 1)
  */
-extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls);
+extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls);
 
-extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size);
+extern void nf_ct_free_hashtable(void *hash, unsigned int size);
 
 extern struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(struct net *net, u16 zone,
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index d4958d4c6574..5cf8a8c141aa 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -28,8 +28,6 @@ struct netns_ct {
 	struct ctl_table_header	*acct_sysctl_header;
 	struct ctl_table_header	*event_sysctl_header;
 #endif
-	int			hash_vmalloc;
-	int			expect_vmalloc;
 	char			*slabname;
 };
 #endif
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index d68c3f121774..e2e2ef57eca2 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -43,7 +43,6 @@ struct netns_ipv4 {
 	struct xt_table		*nat_table;
 	struct hlist_head	*nat_bysource;
 	unsigned int		nat_htable_size;
-	int			nat_vmalloced;
 #endif
 
 	int sysctl_icmp_echo_ignore_all;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index eb55835a02c3..6972ceee99c6 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -682,8 +682,7 @@ static int __net_init nf_nat_net_init(struct net *net)
 {
 	/* Leave them the same for the moment. */
 	net->ipv4.nat_htable_size = net->ct.htable_size;
-	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size,
-						       &net->ipv4.nat_vmalloced, 0);
+	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0);
 	if (!net->ipv4.nat_bysource)
 		return -ENOMEM;
 	return 0;
@@ -705,8 +704,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	nf_ct_iterate_cleanup(net, &clean_nat, NULL);
 	synchronize_rcu();
-	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced,
-			     net->ipv4.nat_htable_size);
+	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size);
 }
 
 static struct pernet_operations nf_nat_net_ops = {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e95ac42ef673..dc2ff2cd0a7e 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1202,9 +1202,9 @@ static int kill_all(struct nf_conn *i, void *data)
 	return 1;
 }
 
-void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
+void nf_ct_free_hashtable(void *hash, unsigned int size)
 {
-	if (vmalloced)
+	if (is_vmalloc_addr(hash))
 		vfree(hash);
 	else
 		free_pages((unsigned long)hash,
@@ -1271,8 +1271,7 @@ static void nf_conntrack_cleanup_net(struct net *net)
 		goto i_see_dead_people;
 	}
 
-	nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
-			     net->ct.htable_size);
+	nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 	nf_conntrack_ecache_fini(net);
 	nf_conntrack_acct_fini(net);
 	nf_conntrack_expect_fini(net);
@@ -1301,21 +1300,18 @@ void nf_conntrack_cleanup(struct net *net)
 	}
 }
 
-void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls)
+void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
 {
 	struct hlist_nulls_head *hash;
 	unsigned int nr_slots, i;
 	size_t sz;
 
-	*vmalloced = 0;
-
 	BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
 	nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
 	sz = nr_slots * sizeof(struct hlist_nulls_head);
 	hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
 					get_order(sz));
 	if (!hash) {
-		*vmalloced = 1;
 		printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
 		hash = __vmalloc(sz, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
 				 PAGE_KERNEL);
@@ -1331,7 +1327,7 @@ EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable);
 
 int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 {
-	int i, bucket, vmalloced, old_vmalloced;
+	int i, bucket;
 	unsigned int hashsize, old_size;
 	struct hlist_nulls_head *hash, *old_hash;
 	struct nf_conntrack_tuple_hash *h;
@@ -1348,7 +1344,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	if (!hashsize)
 		return -EINVAL;
 
-	hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1);
+	hash = nf_ct_alloc_hashtable(&hashsize, 1);
 	if (!hash)
 		return -ENOMEM;
 
@@ -1370,15 +1366,13 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 		}
 	}
 	old_size = init_net.ct.htable_size;
-	old_vmalloced = init_net.ct.hash_vmalloc;
 	old_hash = init_net.ct.hash;
 
 	init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
-	init_net.ct.hash_vmalloc = vmalloced;
 	init_net.ct.hash = hash;
 	spin_unlock_bh(&nf_conntrack_lock);
 
-	nf_ct_free_hashtable(old_hash, old_vmalloced, old_size);
+	nf_ct_free_hashtable(old_hash, old_size);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
@@ -1491,8 +1485,7 @@ static int nf_conntrack_init_net(struct net *net)
 	}
 
 	net->ct.htable_size = nf_conntrack_htable_size;
-	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size,
-					     &net->ct.hash_vmalloc, 1);
+	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
 	if (!net->ct.hash) {
 		ret = -ENOMEM;
 		printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
@@ -1515,8 +1508,7 @@ err_ecache:
 err_acct:
 	nf_conntrack_expect_fini(net);
 err_expect:
-	nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
-			     net->ct.htable_size);
+	nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 err_hash:
 	kmem_cache_destroy(net->ct.nf_conntrack_cachep);
 err_cache:
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4a9ed23180df..cd1e8e0970f2 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -639,8 +639,7 @@ int nf_conntrack_expect_init(struct net *net)
 	}
 
 	net->ct.expect_count = 0;
-	net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize,
-						  &net->ct.expect_vmalloc, 0);
+	net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
 	if (net->ct.expect_hash == NULL)
 		goto err1;
 
@@ -662,8 +661,7 @@ err3:
 	if (net_eq(net, &init_net))
 		kmem_cache_destroy(nf_ct_expect_cachep);
 err2:
-	nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc,
-			     nf_ct_expect_hsize);
+	nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
 err1:
 	return err;
 }
@@ -675,6 +673,5 @@ void nf_conntrack_expect_fini(struct net *net)
 		rcu_barrier(); /* Wait for call_rcu() before destroy */
 		kmem_cache_destroy(nf_ct_expect_cachep);
 	}
-	nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc,
-			     nf_ct_expect_hsize);
+	nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
 }
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 767bbe98a0f0..1bdfea357955 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -33,7 +33,6 @@ static DEFINE_MUTEX(nf_ct_helper_mutex);
 static struct hlist_head *nf_ct_helper_hash __read_mostly;
 static unsigned int nf_ct_helper_hsize __read_mostly;
 static unsigned int nf_ct_helper_count __read_mostly;
-static int nf_ct_helper_vmalloc;
 
 
 /* Stupid hash, but collision free for the default registrations of the
@@ -267,8 +266,7 @@ int nf_conntrack_helper_init(void)
 	int err;
 
 	nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
-	nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize,
-						  &nf_ct_helper_vmalloc, 0);
+	nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0);
 	if (!nf_ct_helper_hash)
 		return -ENOMEM;
 
@@ -279,14 +277,12 @@ int nf_conntrack_helper_init(void)
 	return 0;
 
 err1:
-	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc,
-			     nf_ct_helper_hsize);
+	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize);
 	return err;
 }
 
 void nf_conntrack_helper_fini(void)
 {
 	nf_ct_extend_unregister(&helper_extend);
-	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc,
-			     nf_ct_helper_hsize);
+	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize);
 }
-- 
cgit v1.2.3


From 43f393caec0362abe03c72799d3f342af3973070 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@infradead.org>
Date: Sun, 16 Jan 2011 18:10:28 +0100
Subject: netfilter: audit target to record accepted/dropped packets

This patch adds a new netfilter target which creates audit records
for packets traversing a certain chain.

It can be used to record packets which are rejected administraively
as follows:

  -N AUDIT_DROP
  -A AUDIT_DROP -j AUDIT --type DROP
  -A AUDIT_DROP -j DROP

a rule which would typically drop or reject a packet would then
invoke the new chain to record packets before dropping them.

  -j AUDIT_DROP

The module is protocol independant and works for iptables, ip6tables
and ebtables.

The following information is logged:
 - netfilter hook
 - packet length
 - incomming/outgoing interface
 - MAC src/dst/proto for ethernet packets
 - src/dst/protocol address for IPv4/IPv6
 - src/dst port for TCP/UDP/UDPLITE
 - icmp type/code

Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Thomas Graf <tgraf@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/audit.h              |   1 +
 include/linux/netfilter/Kbuild     |   1 +
 include/linux/netfilter/xt_AUDIT.h |  30 ++++++
 net/netfilter/Kconfig              |  10 ++
 net/netfilter/Makefile             |   1 +
 net/netfilter/xt_AUDIT.c           | 204 +++++++++++++++++++++++++++++++++++++
 6 files changed, 247 insertions(+)
 create mode 100644 include/linux/netfilter/xt_AUDIT.h
 create mode 100644 net/netfilter/xt_AUDIT.c

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 8b5c0620abf9..ae227dfcf9c6 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -103,6 +103,7 @@
 #define AUDIT_BPRM_FCAPS	1321	/* Information about fcaps increasing perms */
 #define AUDIT_CAPSET		1322	/* Record showing argument to sys_capset */
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
+#define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9d40effe7ca7..9f11fbc377e2 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -9,6 +9,7 @@ header-y += nfnetlink_conntrack.h
 header-y += nfnetlink_log.h
 header-y += nfnetlink_queue.h
 header-y += x_tables.h
+header-y += xt_AUDIT.h
 header-y += xt_CHECKSUM.h
 header-y += xt_CLASSIFY.h
 header-y += xt_CONNMARK.h
diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h
new file mode 100644
index 000000000000..38751d2ea52b
--- /dev/null
+++ b/include/linux/netfilter/xt_AUDIT.h
@@ -0,0 +1,30 @@
+/*
+ * Header file for iptables xt_AUDIT target
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _XT_AUDIT_TARGET_H
+#define _XT_AUDIT_TARGET_H
+
+#include <linux/types.h>
+
+enum {
+	XT_AUDIT_TYPE_ACCEPT = 0,
+	XT_AUDIT_TYPE_DROP,
+	XT_AUDIT_TYPE_REJECT,
+	__XT_AUDIT_TYPE_MAX,
+};
+
+#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1)
+
+struct xt_audit_info {
+	__u8 type; /* XT_AUDIT_TYPE_* */
+};
+
+#endif /* _XT_AUDIT_TARGET_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 1b79353a5d29..93918f022555 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -326,6 +326,16 @@ config NETFILTER_XT_CONNMARK
 
 comment "Xtables targets"
 
+config NETFILTER_XT_TARGET_AUDIT
+	tristate "AUDIT target support"
+	depends on AUDIT
+	depends on NETFILTER_ADVANCED
+	---help---
+	  This option adds a 'AUDIT' target, which can be used to create
+	  audit records for packets dropped/accepted.
+
+	  To compileit as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_TARGET_CHECKSUM
 	tristate "CHECKSUM target support"
 	depends on IP_NF_MANGLE || IP6_NF_MANGLE
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 441050f31111..401d574bdfd2 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
 
 # targets
+obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
new file mode 100644
index 000000000000..81802d27346e
--- /dev/null
+++ b/net/netfilter/xt_AUDIT.c
@@ -0,0 +1,204 @@
+/*
+ * Creates audit record for dropped/accepted packets
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/audit.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_arp.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_AUDIT.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Thomas Graf <tgraf@redhat.com>");
+MODULE_DESCRIPTION("Xtables: creates audit records for dropped/accepted packets");
+MODULE_ALIAS("ipt_AUDIT");
+MODULE_ALIAS("ip6t_AUDIT");
+MODULE_ALIAS("ebt_AUDIT");
+MODULE_ALIAS("arpt_AUDIT");
+
+static void audit_proto(struct audit_buffer *ab, struct sk_buff *skb,
+			unsigned int proto, unsigned int offset)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE: {
+		const __be16 *pptr;
+		__be16 _ports[2];
+
+		pptr = skb_header_pointer(skb, offset, sizeof(_ports), _ports);
+		if (pptr == NULL) {
+			audit_log_format(ab, " truncated=1");
+			return;
+		}
+
+		audit_log_format(ab, " sport=%hu dport=%hu",
+				 ntohs(pptr[0]), ntohs(pptr[1]));
+		}
+		break;
+
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6: {
+		const u8 *iptr;
+		u8 _ih[2];
+
+		iptr = skb_header_pointer(skb, offset, sizeof(_ih), &_ih);
+		if (iptr == NULL) {
+			audit_log_format(ab, " truncated=1");
+			return;
+		}
+
+		audit_log_format(ab, " icmptype=%hhu icmpcode=%hhu",
+				 iptr[0], iptr[1]);
+
+		}
+		break;
+	}
+}
+
+static void audit_ip4(struct audit_buffer *ab, struct sk_buff *skb)
+{
+	struct iphdr _iph;
+	const struct iphdr *ih;
+
+	ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+	if (!ih) {
+		audit_log_format(ab, " truncated=1");
+		return;
+	}
+
+	audit_log_format(ab, " saddr=%pI4 daddr=%pI4 ipid=%hu proto=%hhu",
+		&ih->saddr, &ih->daddr, ntohs(ih->id), ih->protocol);
+
+	if (ntohs(ih->frag_off) & IP_OFFSET) {
+		audit_log_format(ab, " frag=1");
+		return;
+	}
+
+	audit_proto(ab, skb, ih->protocol, ih->ihl * 4);
+}
+
+static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
+{
+	struct ipv6hdr _ip6h;
+	const struct ipv6hdr *ih;
+	u8 nexthdr;
+	int offset;
+
+	ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h);
+	if (!ih) {
+		audit_log_format(ab, " truncated=1");
+		return;
+	}
+
+	nexthdr = ih->nexthdr;
+	offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h),
+				  &nexthdr);
+
+	audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu",
+			 &ih->saddr, &ih->daddr, nexthdr);
+
+	if (offset)
+		audit_proto(ab, skb, nexthdr, offset);
+}
+
+static unsigned int
+audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct xt_audit_info *info = par->targinfo;
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT);
+	if (ab == NULL)
+		goto errout;
+
+	audit_log_format(ab, "action=%hhu hook=%u len=%u inif=%s outif=%s",
+			 info->type, par->hooknum, skb->len,
+			 par->in ? par->in->name : "?",
+			 par->out ? par->out->name : "?");
+
+	if (skb->mark)
+		audit_log_format(ab, " mark=%#x", skb->mark);
+
+	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
+		audit_log_format(ab, " smac=%pM dmac=%pM macproto=0x%04x",
+				 eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+				 ntohs(eth_hdr(skb)->h_proto));
+
+		if (par->family == NFPROTO_BRIDGE) {
+			switch (eth_hdr(skb)->h_proto) {
+			case __constant_htons(ETH_P_IP):
+				audit_ip4(ab, skb);
+				break;
+
+			case __constant_htons(ETH_P_IPV6):
+				audit_ip6(ab, skb);
+				break;
+			}
+		}
+	}
+
+	switch (par->family) {
+	case NFPROTO_IPV4:
+		audit_ip4(ab, skb);
+		break;
+
+	case NFPROTO_IPV6:
+		audit_ip6(ab, skb);
+		break;
+	}
+
+	audit_log_end(ab);
+
+errout:
+	return XT_CONTINUE;
+}
+
+static int audit_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_audit_info *info = par->targinfo;
+
+	if (info->type > XT_AUDIT_TYPE_MAX) {
+		pr_info("Audit type out of range (valid range: 0..%hhu)\n",
+			XT_AUDIT_TYPE_MAX);
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static struct xt_target audit_tg_reg __read_mostly = {
+	.name		= "AUDIT",
+	.family		= NFPROTO_UNSPEC,
+	.target		= audit_tg,
+	.targetsize	= sizeof(struct xt_audit_info),
+	.checkentry	= audit_tg_check,
+	.me		= THIS_MODULE,
+};
+
+static int __init audit_tg_init(void)
+{
+	return xt_register_target(&audit_tg_reg);
+}
+
+static void __exit audit_tg_exit(void)
+{
+	xt_unregister_target(&audit_tg_reg);
+}
+
+module_init(audit_tg_init);
+module_exit(audit_tg_exit);
-- 
cgit v1.2.3


From fbabf31e4d482149b5e2704eb0287cf9117bdcf3 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@infradead.org>
Date: Sun, 16 Jan 2011 18:12:59 +0100
Subject: netfilter: create audit records for x_tables replaces

The setsockopt() syscall to replace tables is already recorded
in the audit logs. This patch stores additional information
such as table name and netfilter protocol.

Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Thomas Graf <tgraf@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/audit.h    |  1 +
 net/netfilter/x_tables.c | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index ae227dfcf9c6..32b5c62a5042 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -104,6 +104,7 @@
 #define AUDIT_CAPSET		1322	/* Record showing argument to sys_capset */
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
 #define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
+#define AUDIT_NETFILTER_CFG	1325	/* Netfilter chain modifications */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index ee5de3af510a..fbc2b72091e0 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/audit.h>
 #include <net/net_namespace.h>
 
 #include <linux/netfilter/x_tables.h>
@@ -834,6 +835,21 @@ xt_replace_table(struct xt_table *table,
 	 */
 	local_bh_enable();
 
+#ifdef CONFIG_AUDIT
+	if (audit_enabled) {
+		struct audit_buffer *ab;
+
+		ab = audit_log_start(current->audit_context, GFP_KERNEL,
+				     AUDIT_NETFILTER_CFG);
+		if (ab) {
+			audit_log_format(ab, "table=%s family=%u entries=%u",
+					 table->name, table->af,
+					 private->number);
+			audit_log_end(ab);
+		}
+	}
+#endif
+
 	return private;
 }
 EXPORT_SYMBOL_GPL(xt_replace_table);
-- 
cgit v1.2.3


From 7898e1f8e9eb1bee88c92d636e0ab93f2cbe31c6 Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Mon, 17 Jan 2011 08:05:27 -0800
Subject: Subject: [PATCH] Smack: mmap controls for library containment

  In the embedded world there are often situations
  where libraries are updated from a variety of sources,
  for a variety of reasons, and with any number of
  security characteristics. These differences
  might include privilege required for a given library
  provided interface to function properly, as occurs
  from time to time in graphics libraries. There are
  also cases where it is important to limit use of
  libraries based on the provider of the library and
  the security aware application may make choices
  based on that criteria.

  These issues are addressed by providing an additional
  Smack label that may optionally be assigned to an object,
  the SMACK64MMAP attribute. An mmap operation is allowed
  if there is no such attribute.

  If there is a SMACK64MMAP attribute the mmap is permitted
  only if a subject with that label has all of the access
  permitted a subject with the current task label.

  Security aware applications may from time to time
  wish to reduce their "privilege" to avoid accidental use
  of privilege. One case where this arises is the
  environment in which multiple sources provide libraries
  to perform the same functions. An application may know
  that it should eschew services made available from a
  particular vendor, or of a particular version.

  In support of this a secondary list of Smack rules has
  been added that is local to the task. This list is
  consulted only in the case where the global list has
  approved access. It can only further restrict access.
  Unlike the global last, if no entry is found on the
  local list access is granted. An application can add
  entries to its own list by writing to /smack/load-self.

  The changes appear large as they involve refactoring
  the list handling to accomodate there being more
  than one rule list.

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
---
 include/linux/xattr.h         |   2 +
 security/smack/smack.h        |   9 +-
 security/smack/smack_access.c |  52 ++++--
 security/smack/smack_lsm.c    | 269 +++++++++++++++++++++++++-----
 security/smack/smackfs.c      | 370 +++++++++++++++++++++++++++++-------------
 5 files changed, 524 insertions(+), 178 deletions(-)

(limited to 'include')

diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index e6131ef98d8f..6050783005bd 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -42,11 +42,13 @@
 #define XATTR_SMACK_IPOUT "SMACK64IPOUT"
 #define XATTR_SMACK_EXEC "SMACK64EXEC"
 #define XATTR_SMACK_TRANSMUTE "SMACK64TRANSMUTE"
+#define XATTR_SMACK_MMAP "SMACK64MMAP"
 #define XATTR_NAME_SMACK XATTR_SECURITY_PREFIX XATTR_SMACK_SUFFIX
 #define XATTR_NAME_SMACKIPIN	XATTR_SECURITY_PREFIX XATTR_SMACK_IPIN
 #define XATTR_NAME_SMACKIPOUT	XATTR_SECURITY_PREFIX XATTR_SMACK_IPOUT
 #define XATTR_NAME_SMACKEXEC	XATTR_SECURITY_PREFIX XATTR_SMACK_EXEC
 #define XATTR_NAME_SMACKTRANSMUTE XATTR_SECURITY_PREFIX XATTR_SMACK_TRANSMUTE
+#define XATTR_NAME_SMACKMMAP XATTR_SECURITY_PREFIX XATTR_SMACK_MMAP
 
 #define XATTR_CAPS_SUFFIX "capability"
 #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX
diff --git a/security/smack/smack.h b/security/smack/smack.h
index 129c4eb8ffb1..e365d455ceb6 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -52,13 +52,16 @@ struct socket_smack {
 struct inode_smack {
 	char		*smk_inode;	/* label of the fso */
 	char		*smk_task;	/* label of the task */
+	char		*smk_mmap;	/* label of the mmap domain */
 	struct mutex	smk_lock;	/* initialization lock */
 	int		smk_flags;	/* smack inode flags */
 };
 
 struct task_smack {
-	char		*smk_task;	/* label used for access control */
-	char		*smk_forked;	/* label when forked */
+	char			*smk_task;	/* label for access control */
+	char			*smk_forked;	/* label when forked */
+	struct list_head	smk_rules;	/* per task access rules */
+	struct mutex		smk_rules_lock;	/* lock for the rules */
 };
 
 #define	SMK_INODE_INSTANT	0x01	/* inode is instantiated */
@@ -202,7 +205,7 @@ struct inode_smack *new_inode_smack(char *);
 /*
  * These functions are in smack_access.c
  */
-int smk_access_entry(char *, char *);
+int smk_access_entry(char *, char *, struct list_head *);
 int smk_access(char *, char *, int, struct smk_audit_info *);
 int smk_curacc(char *, u32, struct smk_audit_info *);
 int smack_to_cipso(const char *, struct smack_cipso *);
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index 7ba8478f599e..86453db4333d 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -70,10 +70,11 @@ int log_policy = SMACK_AUDIT_DENIED;
  * smk_access_entry - look up matching access rule
  * @subject_label: a pointer to the subject's Smack label
  * @object_label: a pointer to the object's Smack label
+ * @rule_list: the list of rules to search
  *
  * This function looks up the subject/object pair in the
- * access rule list and returns pointer to the matching rule if found,
- * NULL otherwise.
+ * access rule list and returns the access mode. If no
+ * entry is found returns -ENOENT.
  *
  * NOTE:
  * Even though Smack labels are usually shared on smack_list
@@ -85,13 +86,13 @@ int log_policy = SMACK_AUDIT_DENIED;
  * will be on the list, so checking the pointers may be a worthwhile
  * optimization.
  */
-int smk_access_entry(char *subject_label, char *object_label)
+int smk_access_entry(char *subject_label, char *object_label,
+			struct list_head *rule_list)
 {
-	u32 may = MAY_NOT;
+	int may = -ENOENT;
 	struct smack_rule *srp;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(srp, &smack_rule_list, list) {
+	list_for_each_entry_rcu(srp, rule_list, list) {
 		if (srp->smk_subject == subject_label ||
 		    strcmp(srp->smk_subject, subject_label) == 0) {
 			if (srp->smk_object == object_label ||
@@ -101,7 +102,6 @@ int smk_access_entry(char *subject_label, char *object_label)
 			}
 		}
 	}
-	rcu_read_unlock();
 
 	return may;
 }
@@ -129,7 +129,7 @@ int smk_access_entry(char *subject_label, char *object_label)
 int smk_access(char *subject_label, char *object_label, int request,
 	       struct smk_audit_info *a)
 {
-	u32 may = MAY_NOT;
+	int may = MAY_NOT;
 	int rc = 0;
 
 	/*
@@ -181,13 +181,14 @@ int smk_access(char *subject_label, char *object_label, int request,
 	 * Beyond here an explicit relationship is required.
 	 * If the requested access is contained in the available
 	 * access (e.g. read is included in readwrite) it's
-	 * good.
-	 */
-	may = smk_access_entry(subject_label, object_label);
-	/*
-	 * This is a bit map operation.
+	 * good. A negative response from smk_access_entry()
+	 * indicates there is no entry for this pair.
 	 */
-	if ((request & may) == request)
+	rcu_read_lock();
+	may = smk_access_entry(subject_label, object_label, &smack_rule_list);
+	rcu_read_unlock();
+
+	if (may > 0 && (request & may) == request)
 		goto out_audit;
 
 	rc = -EACCES;
@@ -212,12 +213,27 @@ out_audit:
  */
 int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
 {
+	struct task_smack *tsp = current_security();
+	char *sp = smk_of_task(tsp);
+	int may;
 	int rc;
-	char *sp = smk_of_current();
 
+	/*
+	 * Check the global rule list
+	 */
 	rc = smk_access(sp, obj_label, mode, NULL);
-	if (rc == 0)
-		goto out_audit;
+	if (rc == 0) {
+		/*
+		 * If there is an entry in the task's rule list
+		 * it can further restrict access.
+		 */
+		may = smk_access_entry(sp, obj_label, &tsp->smk_rules);
+		if (may < 0)
+			goto out_audit;
+		if ((mode & may) == mode)
+			goto out_audit;
+		rc = -EACCES;
+	}
 
 	/*
 	 * Return if a specific label has been designated as the
@@ -228,7 +244,7 @@ int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
 		goto out_audit;
 
 	if (capable(CAP_MAC_OVERRIDE))
-		return 0;
+		rc = 0;
 
 out_audit:
 #ifdef CONFIG_AUDIT
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 533bf3255d7f..123a499ded37 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -84,6 +84,56 @@ struct inode_smack *new_inode_smack(char *smack)
 	return isp;
 }
 
+/**
+ * new_task_smack - allocate a task security blob
+ * @smack: a pointer to the Smack label to use in the blob
+ *
+ * Returns the new blob or NULL if there's no memory available
+ */
+static struct task_smack *new_task_smack(char *task, char *forked, gfp_t gfp)
+{
+	struct task_smack *tsp;
+
+	tsp = kzalloc(sizeof(struct task_smack), gfp);
+	if (tsp == NULL)
+		return NULL;
+
+	tsp->smk_task = task;
+	tsp->smk_forked = forked;
+	INIT_LIST_HEAD(&tsp->smk_rules);
+	mutex_init(&tsp->smk_rules_lock);
+
+	return tsp;
+}
+
+/**
+ * smk_copy_rules - copy a rule set
+ * @nhead - new rules header pointer
+ * @ohead - old rules header pointer
+ *
+ * Returns 0 on success, -ENOMEM on error
+ */
+static int smk_copy_rules(struct list_head *nhead, struct list_head *ohead,
+				gfp_t gfp)
+{
+	struct smack_rule *nrp;
+	struct smack_rule *orp;
+	int rc = 0;
+
+	INIT_LIST_HEAD(nhead);
+
+	list_for_each_entry_rcu(orp, ohead, list) {
+		nrp = kzalloc(sizeof(struct smack_rule), gfp);
+		if (nrp == NULL) {
+			rc = -ENOMEM;
+			break;
+		}
+		*nrp = *orp;
+		list_add_rcu(&nrp->list, nhead);
+	}
+	return rc;
+}
+
 /*
  * LSM hooks.
  * We he, that is fun!
@@ -102,23 +152,17 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
 {
 	int rc;
 	struct smk_audit_info ad;
-	char *sp, *tsp;
+	char *tsp;
 
 	rc = cap_ptrace_access_check(ctp, mode);
 	if (rc != 0)
 		return rc;
 
-	sp = smk_of_current();
 	tsp = smk_of_task(task_security(ctp));
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, ctp);
 
-	/* we won't log here, because rc can be overriden */
-	rc = smk_access(sp, tsp, MAY_READWRITE, NULL);
-	if (rc != 0 && capable(CAP_MAC_OVERRIDE))
-		rc = 0;
-
-	smack_log(sp, tsp, MAY_READWRITE, rc, &ad);
+	rc = smk_curacc(tsp, MAY_READWRITE, &ad);
 	return rc;
 }
 
@@ -134,23 +178,17 @@ static int smack_ptrace_traceme(struct task_struct *ptp)
 {
 	int rc;
 	struct smk_audit_info ad;
-	char *sp, *tsp;
+	char *tsp;
 
 	rc = cap_ptrace_traceme(ptp);
 	if (rc != 0)
 		return rc;
 
+	tsp = smk_of_task(task_security(ptp));
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, ptp);
 
-	sp = smk_of_current();
-	tsp = smk_of_task(task_security(ptp));
-	/* we won't log here, because rc can be overriden */
-	rc = smk_access(tsp, sp, MAY_READWRITE, NULL);
-	if (rc != 0 && has_capability(ptp, CAP_MAC_OVERRIDE))
-		rc = 0;
-
-	smack_log(tsp, sp, MAY_READWRITE, rc, &ad);
+	rc = smk_curacc(tsp, MAY_READWRITE, &ad);
 	return rc;
 }
 
@@ -474,7 +512,7 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 {
 	char *isp = smk_of_inode(inode);
 	char *dsp = smk_of_inode(dir);
-	u32 may;
+	int may;
 
 	if (name) {
 		*name = kstrdup(XATTR_SMACK_SUFFIX, GFP_KERNEL);
@@ -483,14 +521,17 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 	}
 
 	if (value) {
-		may = smk_access_entry(smk_of_current(), dsp);
+		rcu_read_lock();
+		may = smk_access_entry(smk_of_current(), dsp, &smack_rule_list);
+		rcu_read_unlock();
 
 		/*
 		 * If the access rule allows transmutation and
 		 * the directory requests transmutation then
 		 * by all means transmute.
 		 */
-		if (((may & MAY_TRANSMUTE) != 0) && smk_inode_transmutable(dir))
+		if (may > 0 && ((may & MAY_TRANSMUTE) != 0) &&
+		    smk_inode_transmutable(dir))
 			isp = dsp;
 
 		*value = kstrdup(isp, GFP_KERNEL);
@@ -716,7 +757,8 @@ static int smack_inode_setxattr(struct dentry *dentry, const char *name,
 	if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
 	    strcmp(name, XATTR_NAME_SMACKIPIN) == 0 ||
 	    strcmp(name, XATTR_NAME_SMACKIPOUT) == 0 ||
-	    strcmp(name, XATTR_NAME_SMACKEXEC) == 0) {
+	    strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
 		if (!capable(CAP_MAC_ADMIN))
 			rc = -EPERM;
 		/*
@@ -773,6 +815,12 @@ static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
 			isp->smk_task = nsp;
 		else
 			isp->smk_task = smack_known_invalid.smk_known;
+	} else if (strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
+		nsp = smk_import(value, size);
+		if (nsp != NULL)
+			isp->smk_mmap = nsp;
+		else
+			isp->smk_mmap = smack_known_invalid.smk_known;
 	} else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0)
 		isp->smk_flags |= SMK_INODE_TRANSMUTE;
 
@@ -815,7 +863,8 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 	    strcmp(name, XATTR_NAME_SMACKIPIN) == 0 ||
 	    strcmp(name, XATTR_NAME_SMACKIPOUT) == 0 ||
 	    strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
-	    strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) {
+	    strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKMMAP)) {
 		if (!capable(CAP_MAC_ADMIN))
 			rc = -EPERM;
 	} else
@@ -829,6 +878,7 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 	if (rc == 0) {
 		isp = dentry->d_inode->i_security;
 		isp->smk_task = NULL;
+		isp->smk_mmap = NULL;
 	}
 
 	return rc;
@@ -1059,6 +1109,113 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd,
 	return rc;
 }
 
+/**
+ * smk_mmap_list_check - the mmap check
+ * @sub: subject label
+ * @obj: object label
+ * @access: access mode
+ * @local: the task specific rule list
+ *
+ * Returns 0 if acces is permitted, -EACCES otherwise
+ */
+static int smk_mmap_list_check(char *sub, char *obj, int access,
+				struct list_head *local)
+{
+	int may;
+
+	/*
+	 * If there is not a global rule that
+	 * allows access say no.
+	 */
+	may = smk_access_entry(sub, obj, &smack_rule_list);
+	if (may == -ENOENT || (may & access) != access)
+		return -EACCES;
+	/*
+	 * If there is a task local rule that
+	 * denies access say no.
+	 */
+	may = smk_access_entry(sub, obj, local);
+	if (may != -ENOENT && (may & access) != access)
+		return -EACCES;
+
+	return 0;
+}
+
+/**
+ * smack_file_mmap :
+ * Check permissions for a mmap operation.  The @file may be NULL, e.g.
+ * if mapping anonymous memory.
+ * @file contains the file structure for file to map (may be NULL).
+ * @reqprot contains the protection requested by the application.
+ * @prot contains the protection that will be applied by the kernel.
+ * @flags contains the operational flags.
+ * Return 0 if permission is granted.
+ */
+static int smack_file_mmap(struct file *file,
+			   unsigned long reqprot, unsigned long prot,
+			   unsigned long flags, unsigned long addr,
+			   unsigned long addr_only)
+{
+	struct smack_rule *srp;
+	struct task_smack *tsp;
+	char *sp;
+	char *msmack;
+	struct inode_smack *isp;
+	struct dentry *dp;
+	int rc;
+
+	/* do DAC check on address space usage */
+	rc = cap_file_mmap(file, reqprot, prot, flags, addr, addr_only);
+	if (rc || addr_only)
+		return rc;
+
+	if (file == NULL || file->f_dentry == NULL)
+		return 0;
+
+	dp = file->f_dentry;
+
+	if (dp->d_inode == NULL)
+		return 0;
+
+	isp = dp->d_inode->i_security;
+	if (isp->smk_mmap == NULL)
+		return 0;
+	msmack = isp->smk_mmap;
+
+	tsp = current_security();
+	sp = smk_of_current();
+	rc = 0;
+
+	rcu_read_lock();
+	/*
+	 * For each Smack rule associated with the subject
+	 * label verify that the SMACK64MMAP also has access
+	 * to that rule's object label.
+	 *
+	 * Because neither of the labels comes
+	 * from the networking code it is sufficient
+	 * to compare pointers.
+	 */
+	list_for_each_entry_rcu(srp, &smack_rule_list, list) {
+		if (srp->smk_subject != sp)
+			continue;
+		/*
+		 * Matching labels always allows access.
+		 */
+		if (msmack == srp->smk_object)
+			continue;
+
+		rc = smk_mmap_list_check(msmack, srp->smk_object,
+					 srp->smk_access, &tsp->smk_rules);
+		if (rc != 0)
+			break;
+	}
+
+	rcu_read_unlock();
+
+	return rc;
+}
+
 /**
  * smack_file_set_fowner - set the file security blob value
  * @file: object in question
@@ -1095,6 +1252,7 @@ static int smack_file_send_sigiotask(struct task_struct *tsk,
 	 * struct fown_struct is never outside the context of a struct file
 	 */
 	file = container_of(fown, struct file, f_owner);
+
 	/* we don't log here as rc can be overriden */
 	rc = smk_access(file->f_security, tsp, MAY_WRITE, NULL);
 	if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE))
@@ -1145,9 +1303,14 @@ static int smack_file_receive(struct file *file)
  */
 static int smack_cred_alloc_blank(struct cred *cred, gfp_t gfp)
 {
-	cred->security = kzalloc(sizeof(struct task_smack), gfp);
-	if (cred->security == NULL)
+	struct task_smack *tsp;
+
+	tsp = new_task_smack(NULL, NULL, gfp);
+	if (tsp == NULL)
 		return -ENOMEM;
+
+	cred->security = tsp;
+
 	return 0;
 }
 
@@ -1156,13 +1319,24 @@ static int smack_cred_alloc_blank(struct cred *cred, gfp_t gfp)
  * smack_cred_free - "free" task-level security credentials
  * @cred: the credentials in question
  *
- * Smack isn't using copies of blobs. Everyone
- * points to an immutable list. The blobs never go away.
- * There is no leak here.
  */
 static void smack_cred_free(struct cred *cred)
 {
-	kfree(cred->security);
+	struct task_smack *tsp = cred->security;
+	struct smack_rule *rp;
+	struct list_head *l;
+	struct list_head *n;
+
+	if (tsp == NULL)
+		return;
+	cred->security = NULL;
+
+	list_for_each_safe(l, n, &tsp->smk_rules) {
+		rp = list_entry(l, struct smack_rule, list);
+		list_del(&rp->list);
+		kfree(rp);
+	}
+	kfree(tsp);
 }
 
 /**
@@ -1178,13 +1352,16 @@ static int smack_cred_prepare(struct cred *new, const struct cred *old,
 {
 	struct task_smack *old_tsp = old->security;
 	struct task_smack *new_tsp;
+	int rc;
 
-	new_tsp = kzalloc(sizeof(struct task_smack), gfp);
+	new_tsp = new_task_smack(old_tsp->smk_task, old_tsp->smk_task, gfp);
 	if (new_tsp == NULL)
 		return -ENOMEM;
 
-	new_tsp->smk_task = old_tsp->smk_task;
-	new_tsp->smk_forked = old_tsp->smk_task;
+	rc = smk_copy_rules(&new_tsp->smk_rules, &old_tsp->smk_rules, gfp);
+	if (rc != 0)
+		return rc;
+
 	new->security = new_tsp;
 	return 0;
 }
@@ -1203,6 +1380,11 @@ static void smack_cred_transfer(struct cred *new, const struct cred *old)
 
 	new_tsp->smk_task = old_tsp->smk_task;
 	new_tsp->smk_forked = old_tsp->smk_task;
+	mutex_init(&new_tsp->smk_rules_lock);
+	INIT_LIST_HEAD(&new_tsp->smk_rules);
+
+
+	/* cbs copy rule list */
 }
 
 /**
@@ -2419,6 +2601,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 			}
 		}
 		isp->smk_task = smk_fetch(XATTR_NAME_SMACKEXEC, inode, dp);
+		isp->smk_mmap = smk_fetch(XATTR_NAME_SMACKMMAP, inode, dp);
 
 		dput(dp);
 		break;
@@ -2478,6 +2661,7 @@ static int smack_getprocattr(struct task_struct *p, char *name, char **value)
 static int smack_setprocattr(struct task_struct *p, char *name,
 			     void *value, size_t size)
 {
+	int rc;
 	struct task_smack *tsp;
 	struct task_smack *oldtsp;
 	struct cred *new;
@@ -2513,13 +2697,16 @@ static int smack_setprocattr(struct task_struct *p, char *name,
 	new = prepare_creds();
 	if (new == NULL)
 		return -ENOMEM;
-	tsp = kzalloc(sizeof(struct task_smack), GFP_KERNEL);
+
+	tsp = new_task_smack(newsmack, oldtsp->smk_forked, GFP_KERNEL);
 	if (tsp == NULL) {
 		kfree(new);
 		return -ENOMEM;
 	}
-	tsp->smk_task = newsmack;
-	tsp->smk_forked = oldtsp->smk_forked;
+	rc = smk_copy_rules(&tsp->smk_rules, &oldtsp->smk_rules, GFP_KERNEL);
+	if (rc != 0)
+		return rc;
+
 	new->security = tsp;
 	commit_creds(new);
 	return size;
@@ -3221,6 +3408,7 @@ struct security_operations smack_ops = {
 	.file_ioctl = 			smack_file_ioctl,
 	.file_lock = 			smack_file_lock,
 	.file_fcntl = 			smack_file_fcntl,
+	.file_mmap =			smack_file_mmap,
 	.file_set_fowner = 		smack_file_set_fowner,
 	.file_send_sigiotask = 		smack_file_send_sigiotask,
 	.file_receive = 		smack_file_receive,
@@ -3334,23 +3522,20 @@ static __init int smack_init(void)
 	struct cred *cred;
 	struct task_smack *tsp;
 
-	tsp = kzalloc(sizeof(struct task_smack), GFP_KERNEL);
+	if (!security_module_enable(&smack_ops))
+		return 0;
+
+	tsp = new_task_smack(smack_known_floor.smk_known,
+				smack_known_floor.smk_known, GFP_KERNEL);
 	if (tsp == NULL)
 		return -ENOMEM;
 
-	if (!security_module_enable(&smack_ops)) {
-		kfree(tsp);
-		return 0;
-	}
-
 	printk(KERN_INFO "Smack:  Initializing.\n");
 
 	/*
 	 * Set the security state for the initial task.
 	 */
 	cred = (struct cred *) current->cred;
-	tsp->smk_forked = smack_known_floor.smk_known;
-	tsp->smk_task = smack_known_floor.smk_known;
 	cred->security = tsp;
 
 	/* initialize the smack_know_list */
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 362d5eda948b..90d1bbaaa6f3 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -43,6 +43,7 @@ enum smk_inos {
 	SMK_NETLBLADDR	= 8,	/* single label hosts */
 	SMK_ONLYCAP	= 9,	/* the only "capable" label */
 	SMK_LOGGING	= 10,	/* logging */
+	SMK_LOAD_SELF	= 11,	/* task specific rules */
 };
 
 /*
@@ -135,104 +136,30 @@ static void smk_netlabel_audit_set(struct netlbl_audit *nap)
 #define SMK_NETLBLADDRMIN	9
 #define SMK_NETLBLADDRMAX	42
 
-/*
- * Seq_file read operations for /smack/load
- */
-
-static void *load_seq_start(struct seq_file *s, loff_t *pos)
-{
-	if (*pos == SEQ_READ_FINISHED)
-		return NULL;
-	if (list_empty(&smack_rule_list))
-		return NULL;
-	return smack_rule_list.next;
-}
-
-static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
-{
-	struct list_head *list = v;
-
-	if (list_is_last(list, &smack_rule_list)) {
-		*pos = SEQ_READ_FINISHED;
-		return NULL;
-	}
-	return list->next;
-}
-
-static int load_seq_show(struct seq_file *s, void *v)
-{
-	struct list_head *list = v;
-	struct smack_rule *srp =
-		 list_entry(list, struct smack_rule, list);
-
-	seq_printf(s, "%s %s", (char *)srp->smk_subject,
-		   (char *)srp->smk_object);
-
-	seq_putc(s, ' ');
-
-	if (srp->smk_access & MAY_READ)
-		seq_putc(s, 'r');
-	if (srp->smk_access & MAY_WRITE)
-		seq_putc(s, 'w');
-	if (srp->smk_access & MAY_EXEC)
-		seq_putc(s, 'x');
-	if (srp->smk_access & MAY_APPEND)
-		seq_putc(s, 'a');
-	if (srp->smk_access & MAY_TRANSMUTE)
-		seq_putc(s, 't');
-	if (srp->smk_access == 0)
-		seq_putc(s, '-');
-
-	seq_putc(s, '\n');
-
-	return 0;
-}
-
-static void load_seq_stop(struct seq_file *s, void *v)
-{
-	/* No-op */
-}
-
-static const struct seq_operations load_seq_ops = {
-	.start = load_seq_start,
-	.next  = load_seq_next,
-	.show  = load_seq_show,
-	.stop  = load_seq_stop,
-};
-
-/**
- * smk_open_load - open() for /smack/load
- * @inode: inode structure representing file
- * @file: "load" file pointer
- *
- * For reading, use load_seq_* seq_file reading operations.
- */
-static int smk_open_load(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &load_seq_ops);
-}
-
 /**
  * smk_set_access - add a rule to the rule list
  * @srp: the new rule to add
+ * @rule_list: the list of rules
+ * @rule_lock: the rule list lock
  *
  * Looks through the current subject/object/access list for
  * the subject/object pair and replaces the access that was
  * there. If the pair isn't found add it with the specified
  * access.
  *
+ * Returns 1 if a rule was found to exist already, 0 if it is new
  * Returns 0 if nothing goes wrong or -ENOMEM if it fails
  * during the allocation of the new pair to add.
  */
-static int smk_set_access(struct smack_rule *srp)
+static int smk_set_access(struct smack_rule *srp, struct list_head *rule_list,
+				struct mutex *rule_lock)
 {
 	struct smack_rule *sp;
-	int ret = 0;
-	int found;
-	mutex_lock(&smack_list_lock);
+	int found = 0;
 
-	found = 0;
-	list_for_each_entry_rcu(sp, &smack_rule_list, list) {
+	mutex_lock(rule_lock);
+
+	list_for_each_entry_rcu(sp, rule_list, list) {
 		if (sp->smk_subject == srp->smk_subject &&
 		    sp->smk_object == srp->smk_object) {
 			found = 1;
@@ -241,19 +168,21 @@ static int smk_set_access(struct smack_rule *srp)
 		}
 	}
 	if (found == 0)
-		list_add_rcu(&srp->list, &smack_rule_list);
+		list_add_rcu(&srp->list, rule_list);
 
-	mutex_unlock(&smack_list_lock);
+	mutex_unlock(rule_lock);
 
-	return ret;
+	return found;
 }
 
 /**
- * smk_write_load - write() for /smack/load
+ * smk_write_load_list - write() for any /smack/load
  * @file: file pointer, not actually used
  * @buf: where to get the data from
  * @count: bytes sent
  * @ppos: where to start - must be 0
+ * @rule_list: the list of rules to write to
+ * @rule_lock: lock for the rule list
  *
  * Get one smack access rule from above.
  * The format is exactly:
@@ -263,21 +192,19 @@ static int smk_set_access(struct smack_rule *srp)
  *
  * writes must be SMK_LABELLEN+SMK_LABELLEN+SMK_ACCESSLEN bytes.
  */
-static ssize_t smk_write_load(struct file *file, const char __user *buf,
-			      size_t count, loff_t *ppos)
+static ssize_t smk_write_load_list(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos,
+				struct list_head *rule_list,
+				struct mutex *rule_lock)
 {
 	struct smack_rule *rule;
 	char *data;
 	int rc = -EINVAL;
 
 	/*
-	 * Must have privilege.
 	 * No partial writes.
 	 * Enough data must be present.
 	 */
-	if (!capable(CAP_MAC_ADMIN))
-		return -EPERM;
-
 	if (*ppos != 0)
 		return -EINVAL;
 	/*
@@ -372,11 +299,13 @@ static ssize_t smk_write_load(struct file *file, const char __user *buf,
 		goto out_free_rule;
 	}
 
-	rc = smk_set_access(rule);
-
-	if (!rc)
-		rc = count;
-	goto out;
+	rc = count;
+	/*
+	 * smk_set_access returns true if there was already a rule
+	 * for the subject/object pair, and false if it was new.
+	 */
+	if (!smk_set_access(rule, rule_list, rule_lock))
+		goto out;
 
 out_free_rule:
 	kfree(rule);
@@ -385,6 +314,108 @@ out:
 	return rc;
 }
 
+
+/*
+ * Seq_file read operations for /smack/load
+ */
+
+static void *load_seq_start(struct seq_file *s, loff_t *pos)
+{
+	if (*pos == SEQ_READ_FINISHED)
+		return NULL;
+	if (list_empty(&smack_rule_list))
+		return NULL;
+	return smack_rule_list.next;
+}
+
+static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct list_head *list = v;
+
+	if (list_is_last(list, &smack_rule_list)) {
+		*pos = SEQ_READ_FINISHED;
+		return NULL;
+	}
+	return list->next;
+}
+
+static int load_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_rule *srp =
+		 list_entry(list, struct smack_rule, list);
+
+	seq_printf(s, "%s %s", (char *)srp->smk_subject,
+		   (char *)srp->smk_object);
+
+	seq_putc(s, ' ');
+
+	if (srp->smk_access & MAY_READ)
+		seq_putc(s, 'r');
+	if (srp->smk_access & MAY_WRITE)
+		seq_putc(s, 'w');
+	if (srp->smk_access & MAY_EXEC)
+		seq_putc(s, 'x');
+	if (srp->smk_access & MAY_APPEND)
+		seq_putc(s, 'a');
+	if (srp->smk_access & MAY_TRANSMUTE)
+		seq_putc(s, 't');
+	if (srp->smk_access == 0)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+
+	return 0;
+}
+
+static void load_seq_stop(struct seq_file *s, void *v)
+{
+	/* No-op */
+}
+
+static const struct seq_operations load_seq_ops = {
+	.start = load_seq_start,
+	.next  = load_seq_next,
+	.show  = load_seq_show,
+	.stop  = load_seq_stop,
+};
+
+/**
+ * smk_open_load - open() for /smack/load
+ * @inode: inode structure representing file
+ * @file: "load" file pointer
+ *
+ * For reading, use load_seq_* seq_file reading operations.
+ */
+static int smk_open_load(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &load_seq_ops);
+}
+
+/**
+ * smk_write_load - write() for /smack/load
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_load(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+
+	/*
+	 * Must have privilege.
+	 * No partial writes.
+	 * Enough data must be present.
+	 */
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	return smk_write_load_list(file, buf, count, ppos, &smack_rule_list,
+					&smack_list_lock);
+}
+
 static const struct file_operations smk_load_ops = {
 	.open           = smk_open_load,
 	.read		= seq_read,
@@ -1288,6 +1319,112 @@ static const struct file_operations smk_logging_ops = {
 	.write		= smk_write_logging,
 	.llseek		= default_llseek,
 };
+
+/*
+ * Seq_file read operations for /smack/load-self
+ */
+
+static void *load_self_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct task_smack *tsp = current_security();
+
+	if (*pos == SEQ_READ_FINISHED)
+		return NULL;
+	if (list_empty(&tsp->smk_rules))
+		return NULL;
+	return tsp->smk_rules.next;
+}
+
+static void *load_self_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct task_smack *tsp = current_security();
+	struct list_head *list = v;
+
+	if (list_is_last(list, &tsp->smk_rules)) {
+		*pos = SEQ_READ_FINISHED;
+		return NULL;
+	}
+	return list->next;
+}
+
+static int load_self_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_rule *srp =
+		 list_entry(list, struct smack_rule, list);
+
+	seq_printf(s, "%s %s", (char *)srp->smk_subject,
+		   (char *)srp->smk_object);
+
+	seq_putc(s, ' ');
+
+	if (srp->smk_access & MAY_READ)
+		seq_putc(s, 'r');
+	if (srp->smk_access & MAY_WRITE)
+		seq_putc(s, 'w');
+	if (srp->smk_access & MAY_EXEC)
+		seq_putc(s, 'x');
+	if (srp->smk_access & MAY_APPEND)
+		seq_putc(s, 'a');
+	if (srp->smk_access & MAY_TRANSMUTE)
+		seq_putc(s, 't');
+	if (srp->smk_access == 0)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+
+	return 0;
+}
+
+static void load_self_seq_stop(struct seq_file *s, void *v)
+{
+	/* No-op */
+}
+
+static const struct seq_operations load_self_seq_ops = {
+	.start = load_self_seq_start,
+	.next  = load_self_seq_next,
+	.show  = load_self_seq_show,
+	.stop  = load_self_seq_stop,
+};
+
+
+/**
+ * smk_open_load_self - open() for /smack/load-self
+ * @inode: inode structure representing file
+ * @file: "load" file pointer
+ *
+ * For reading, use load_seq_* seq_file reading operations.
+ */
+static int smk_open_load_self(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &load_self_seq_ops);
+}
+
+/**
+ * smk_write_load_self - write() for /smack/load-self
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_load_self(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct task_smack *tsp = current_security();
+
+	return smk_write_load_list(file, buf, count, ppos, &tsp->smk_rules,
+					&tsp->smk_rules_lock);
+}
+
+static const struct file_operations smk_load_self_ops = {
+	.open           = smk_open_load_self,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_load_self,
+	.release        = seq_release,
+};
 /**
  * smk_fill_super - fill the /smackfs superblock
  * @sb: the empty superblock
@@ -1304,23 +1441,26 @@ static int smk_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *root_inode;
 
 	static struct tree_descr smack_files[] = {
-		[SMK_LOAD]	=
-			{"load", &smk_load_ops, S_IRUGO|S_IWUSR},
-		[SMK_CIPSO]	=
-			{"cipso", &smk_cipso_ops, S_IRUGO|S_IWUSR},
-		[SMK_DOI]	=
-			{"doi", &smk_doi_ops, S_IRUGO|S_IWUSR},
-		[SMK_DIRECT]	=
-			{"direct", &smk_direct_ops, S_IRUGO|S_IWUSR},
-		[SMK_AMBIENT]	=
-			{"ambient", &smk_ambient_ops, S_IRUGO|S_IWUSR},
-		[SMK_NETLBLADDR] =
-			{"netlabel", &smk_netlbladdr_ops, S_IRUGO|S_IWUSR},
-		[SMK_ONLYCAP]	=
-			{"onlycap", &smk_onlycap_ops, S_IRUGO|S_IWUSR},
-		[SMK_LOGGING]	=
-			{"logging", &smk_logging_ops, S_IRUGO|S_IWUSR},
-		/* last one */ {""}
+		[SMK_LOAD] = {
+			"load", &smk_load_ops, S_IRUGO|S_IWUSR},
+		[SMK_CIPSO] = {
+			"cipso", &smk_cipso_ops, S_IRUGO|S_IWUSR},
+		[SMK_DOI] = {
+			"doi", &smk_doi_ops, S_IRUGO|S_IWUSR},
+		[SMK_DIRECT] = {
+			"direct", &smk_direct_ops, S_IRUGO|S_IWUSR},
+		[SMK_AMBIENT] = {
+			"ambient", &smk_ambient_ops, S_IRUGO|S_IWUSR},
+		[SMK_NETLBLADDR] = {
+			"netlabel", &smk_netlbladdr_ops, S_IRUGO|S_IWUSR},
+		[SMK_ONLYCAP] = {
+			"onlycap", &smk_onlycap_ops, S_IRUGO|S_IWUSR},
+		[SMK_LOGGING] = {
+			"logging", &smk_logging_ops, S_IRUGO|S_IWUSR},
+		[SMK_LOAD_SELF] = {
+			"load-self", &smk_load_self_ops, S_IRUGO|S_IWUGO},
+		/* last one */
+			{""}
 	};
 
 	rc = simple_fill_super(sb, SMACK_MAGIC, smack_files);
-- 
cgit v1.2.3


From 0260c1dccc6a1018f8cf2c4778dffb47fc5d1c4c Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Tue, 18 Jan 2011 07:33:09 +0100
Subject: netfilter: xtables: use __uXX guarded types for userspace exports

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter_bridge/ebt_802_3.h     | 24 ++++++++++++------------
 include/linux/netfilter_bridge/ebt_among.h     |  2 +-
 include/linux/netfilter_bridge/ebt_arp.h       |  4 ++--
 include/linux/netfilter_bridge/ebt_ip.h        | 12 ++++++------
 include/linux/netfilter_bridge/ebt_ip6.h       | 16 ++++++++--------
 include/linux/netfilter_bridge/ebt_limit.h     |  8 ++++----
 include/linux/netfilter_bridge/ebt_log.h       |  6 +++---
 include/linux/netfilter_bridge/ebt_mark_m.h    |  4 ++--
 include/linux/netfilter_bridge/ebt_nflog.h     | 10 +++++-----
 include/linux/netfilter_bridge/ebt_pkttype.h   |  4 ++--
 include/linux/netfilter_bridge/ebt_stp.h       | 24 ++++++++++++------------
 include/linux/netfilter_bridge/ebt_ulog.h      |  2 +-
 include/linux/netfilter_bridge/ebt_vlan.h      |  8 ++++----
 include/linux/netfilter_ipv4/ipt_CLUSTERIP.h   | 14 +++++++-------
 include/linux/netfilter_ipv4/ipt_ECN.h         |  6 +++---
 include/linux/netfilter_ipv4/ipt_SAME.h        |  6 +++---
 include/linux/netfilter_ipv4/ipt_TTL.h         |  4 ++--
 include/linux/netfilter_ipv4/ipt_addrtype.h    | 14 +++++++-------
 include/linux/netfilter_ipv4/ipt_ah.h          |  4 ++--
 include/linux/netfilter_ipv4/ipt_ecn.h         |  8 ++++----
 include/linux/netfilter_ipv4/ipt_ttl.h         |  4 ++--
 include/linux/netfilter_ipv6/ip6t_HL.h         |  4 ++--
 include/linux/netfilter_ipv6/ip6t_REJECT.h     |  2 +-
 include/linux/netfilter_ipv6/ip6t_ah.h         |  8 ++++----
 include/linux/netfilter_ipv6/ip6t_frag.h       |  8 ++++----
 include/linux/netfilter_ipv6/ip6t_hl.h         |  4 ++--
 include/linux/netfilter_ipv6/ip6t_ipv6header.h |  6 +++---
 include/linux/netfilter_ipv6/ip6t_mh.h         |  4 ++--
 include/linux/netfilter_ipv6/ip6t_opts.h       | 10 +++++-----
 include/linux/netfilter_ipv6/ip6t_rt.h         | 12 ++++++------
 30 files changed, 121 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h
index c73ef0b18bdc..c427764f4444 100644
--- a/include/linux/netfilter_bridge/ebt_802_3.h
+++ b/include/linux/netfilter_bridge/ebt_802_3.h
@@ -24,24 +24,24 @@
 
 /* ui has one byte ctrl, ni has two */
 struct hdr_ui {
-	uint8_t dsap;
-	uint8_t ssap;
-	uint8_t ctrl;
-	uint8_t orig[3];
+	__u8 dsap;
+	__u8 ssap;
+	__u8 ctrl;
+	__u8 orig[3];
 	__be16 type;
 };
 
 struct hdr_ni {
-	uint8_t dsap;
-	uint8_t ssap;
+	__u8 dsap;
+	__u8 ssap;
 	__be16 ctrl;
-	uint8_t  orig[3];
+	__u8  orig[3];
 	__be16 type;
 };
 
 struct ebt_802_3_hdr {
-	uint8_t  daddr[6];
-	uint8_t  saddr[6];
+	__u8  daddr[6];
+	__u8  saddr[6];
 	__be16 len;
 	union {
 		struct hdr_ui ui;
@@ -59,10 +59,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb)
 #endif
 
 struct ebt_802_3_info {
-	uint8_t  sap;
+	__u8  sap;
 	__be16 type;
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  bitmask;
+	__u8  invflags;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h
index 0009558609a7..686c9619dbc0 100644
--- a/include/linux/netfilter_bridge/ebt_among.h
+++ b/include/linux/netfilter_bridge/ebt_among.h
@@ -30,7 +30,7 @@
  */
 
 struct ebt_mac_wormhash_tuple {
-	uint32_t cmp[2];
+	__u32 cmp[2];
 	__be32 ip;
 };
 
diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h
index cbf4843b6b0f..e62b5af95869 100644
--- a/include/linux/netfilter_bridge/ebt_arp.h
+++ b/include/linux/netfilter_bridge/ebt_arp.h
@@ -27,8 +27,8 @@ struct ebt_arp_info
 	unsigned char smmsk[ETH_ALEN];
 	unsigned char dmaddr[ETH_ALEN];
 	unsigned char dmmsk[ETH_ALEN];
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  bitmask;
+	__u8  invflags;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h
index 6a708fb92241..d99de58da2c7 100644
--- a/include/linux/netfilter_bridge/ebt_ip.h
+++ b/include/linux/netfilter_bridge/ebt_ip.h
@@ -31,12 +31,12 @@ struct ebt_ip_info {
 	__be32 daddr;
 	__be32 smsk;
 	__be32 dmsk;
-	uint8_t  tos;
-	uint8_t  protocol;
-	uint8_t  bitmask;
-	uint8_t  invflags;
-	uint16_t sport[2];
-	uint16_t dport[2];
+	__u8  tos;
+	__u8  protocol;
+	__u8  bitmask;
+	__u8  invflags;
+	__u16 sport[2];
+	__u16 dport[2];
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h
index 22af18a3c16b..998e9d5a6b60 100644
--- a/include/linux/netfilter_bridge/ebt_ip6.h
+++ b/include/linux/netfilter_bridge/ebt_ip6.h
@@ -31,17 +31,17 @@ struct ebt_ip6_info {
 	struct in6_addr daddr;
 	struct in6_addr smsk;
 	struct in6_addr dmsk;
-	uint8_t  tclass;
-	uint8_t  protocol;
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  tclass;
+	__u8  protocol;
+	__u8  bitmask;
+	__u8  invflags;
 	union {
-		uint16_t sport[2];
-		uint8_t icmpv6_type[2];
+		__u16 sport[2];
+		__u8 icmpv6_type[2];
 	};
 	union {
-		uint16_t dport[2];
-		uint8_t icmpv6_code[2];
+		__u16 dport[2];
+		__u8 icmpv6_code[2];
 	};
 };
 
diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h
index 4bf76b751676..721d51ffa513 100644
--- a/include/linux/netfilter_bridge/ebt_limit.h
+++ b/include/linux/netfilter_bridge/ebt_limit.h
@@ -10,13 +10,13 @@
    seconds, or one every 59 hours. */
 
 struct ebt_limit_info {
-	u_int32_t avg;    /* Average secs between packets * scale */
-	u_int32_t burst;  /* Period multiplier for upper limit. */
+	__u32 avg;    /* Average secs between packets * scale */
+	__u32 burst;  /* Period multiplier for upper limit. */
 
 	/* Used internally by the kernel */
 	unsigned long prev;
-	u_int32_t credit;
-	u_int32_t credit_cap, cost;
+	__u32 credit;
+	__u32 credit_cap, cost;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h
index cc2cdfb764bc..564beb4946ea 100644
--- a/include/linux/netfilter_bridge/ebt_log.h
+++ b/include/linux/netfilter_bridge/ebt_log.h
@@ -10,9 +10,9 @@
 #define EBT_LOG_WATCHER "log"
 
 struct ebt_log_info {
-	uint8_t loglevel;
-	uint8_t prefix[EBT_LOG_PREFIX_SIZE];
-	uint32_t bitmask;
+	__u8 loglevel;
+	__u8 prefix[EBT_LOG_PREFIX_SIZE];
+	__u32 bitmask;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h
index 9ceb10ec0ed6..97b96c4b8db4 100644
--- a/include/linux/netfilter_bridge/ebt_mark_m.h
+++ b/include/linux/netfilter_bridge/ebt_mark_m.h
@@ -6,8 +6,8 @@
 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR)
 struct ebt_mark_m_info {
 	unsigned long mark, mask;
-	uint8_t invert;
-	uint8_t bitmask;
+	__u8 invert;
+	__u8 bitmask;
 };
 #define EBT_MARK_MATCH "mark_m"
 
diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h
index 052817849b83..477315bc3537 100644
--- a/include/linux/netfilter_bridge/ebt_nflog.h
+++ b/include/linux/netfilter_bridge/ebt_nflog.h
@@ -10,11 +10,11 @@
 #define EBT_NFLOG_DEFAULT_THRESHOLD	1
 
 struct ebt_nflog_info {
-	u_int32_t len;
-	u_int16_t group;
-	u_int16_t threshold;
-	u_int16_t flags;
-	u_int16_t pad;
+	__u32 len;
+	__u16 group;
+	__u16 threshold;
+	__u16 flags;
+	__u16 pad;
 	char prefix[EBT_NFLOG_PREFIX_SIZE];
 };
 
diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h
index 51a799840931..7c0fb0fdcf14 100644
--- a/include/linux/netfilter_bridge/ebt_pkttype.h
+++ b/include/linux/netfilter_bridge/ebt_pkttype.h
@@ -2,8 +2,8 @@
 #define __LINUX_BRIDGE_EBT_PKTTYPE_H
 
 struct ebt_pkttype_info {
-	uint8_t pkt_type;
-	uint8_t invert;
+	__u8 pkt_type;
+	__u8 invert;
 };
 #define EBT_PKTTYPE_MATCH "pkttype"
 
diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h
index e503a0aa2728..13a0bd49a92a 100644
--- a/include/linux/netfilter_bridge/ebt_stp.h
+++ b/include/linux/netfilter_bridge/ebt_stp.h
@@ -21,24 +21,24 @@
 #define EBT_STP_MATCH "stp"
 
 struct ebt_stp_config_info {
-	uint8_t flags;
-	uint16_t root_priol, root_priou;
+	__u8 flags;
+	__u16 root_priol, root_priou;
 	char root_addr[6], root_addrmsk[6];
-	uint32_t root_costl, root_costu;
-	uint16_t sender_priol, sender_priou;
+	__u32 root_costl, root_costu;
+	__u16 sender_priol, sender_priou;
 	char sender_addr[6], sender_addrmsk[6];
-	uint16_t portl, portu;
-	uint16_t msg_agel, msg_ageu;
-	uint16_t max_agel, max_ageu;
-	uint16_t hello_timel, hello_timeu;
-	uint16_t forward_delayl, forward_delayu;
+	__u16 portl, portu;
+	__u16 msg_agel, msg_ageu;
+	__u16 max_agel, max_ageu;
+	__u16 hello_timel, hello_timeu;
+	__u16 forward_delayl, forward_delayu;
 };
 
 struct ebt_stp_info {
-	uint8_t type;
+	__u8 type;
 	struct ebt_stp_config_info config;
-	uint16_t bitmask;
-	uint16_t invflags;
+	__u16 bitmask;
+	__u16 invflags;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h
index b677e2671541..de35a51a7e46 100644
--- a/include/linux/netfilter_bridge/ebt_ulog.h
+++ b/include/linux/netfilter_bridge/ebt_ulog.h
@@ -10,7 +10,7 @@
 #define EBT_ULOG_VERSION 1
 
 struct ebt_ulog_info {
-	uint32_t nlgroup;
+	__u32 nlgroup;
 	unsigned int cprange;
 	unsigned int qthreshold;
 	char prefix[EBT_ULOG_PREFIX_LEN];
diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h
index 1d98be4031e7..48dffc1dad36 100644
--- a/include/linux/netfilter_bridge/ebt_vlan.h
+++ b/include/linux/netfilter_bridge/ebt_vlan.h
@@ -8,12 +8,12 @@
 #define EBT_VLAN_MATCH "vlan"
 
 struct ebt_vlan_info {
-	uint16_t id;		/* VLAN ID {1-4095} */
-	uint8_t prio;		/* VLAN User Priority {0-7} */
+	__u16 id;		/* VLAN ID {1-4095} */
+	__u8 prio;		/* VLAN User Priority {0-7} */
 	__be16 encap;		/* VLAN Encapsulated frame code {0-65535} */
-	uint8_t bitmask;		/* Args bitmask bit 1=1 - ID arg,
+	__u8 bitmask;		/* Args bitmask bit 1=1 - ID arg,
 				   bit 2=1 User-Priority arg, bit 3=1 encap*/
-	uint8_t invflags;		/* Inverse bitmask  bit 1=1 - inversed ID arg, 
+	__u8 invflags;		/* Inverse bitmask  bit 1=1 - inversed ID arg, 
 				   bit 2=1 - inversed Pirority arg */
 };
 
diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
index e5a3687c8a72..3114f06939ef 100644
--- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
+++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
@@ -17,15 +17,15 @@ struct clusterip_config;
 
 struct ipt_clusterip_tgt_info {
 
-	u_int32_t flags;
+	__u32 flags;
 
 	/* only relevant for new ones */
-	u_int8_t clustermac[6];
-	u_int16_t num_total_nodes;
-	u_int16_t num_local_nodes;
-	u_int16_t local_nodes[CLUSTERIP_MAX_NODES];
-	u_int32_t hash_mode;
-	u_int32_t hash_initval;
+	__u8 clustermac[6];
+	__u16 num_total_nodes;
+	__u16 num_local_nodes;
+	__u16 local_nodes[CLUSTERIP_MAX_NODES];
+	__u32 hash_mode;
+	__u32 hash_initval;
 
 	/* Used internally by the kernel */
 	struct clusterip_config *config;
diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h
index 7ca45918ab8e..c6e3e01b75e0 100644
--- a/include/linux/netfilter_ipv4/ipt_ECN.h
+++ b/include/linux/netfilter_ipv4/ipt_ECN.h
@@ -19,11 +19,11 @@
 #define IPT_ECN_OP_MASK		0xce
 
 struct ipt_ECN_info {
-	u_int8_t operation;	/* bitset of operations */
-	u_int8_t ip_ect;	/* ECT codepoint of IPv4 header, pre-shifted */
+	__u8 operation;	/* bitset of operations */
+	__u8 ip_ect;	/* ECT codepoint of IPv4 header, pre-shifted */
 	union {
 		struct {
-			u_int8_t ece:1, cwr:1; /* TCP ECT bits */
+			__u8 ece:1, cwr:1; /* TCP ECT bits */
 		} tcp;
 	} proto;
 };
diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h
index 2529660c5b38..fa0ebeca5d95 100644
--- a/include/linux/netfilter_ipv4/ipt_SAME.h
+++ b/include/linux/netfilter_ipv4/ipt_SAME.h
@@ -7,9 +7,9 @@
 
 struct ipt_same_info {
 	unsigned char info;
-	u_int32_t rangesize;
-	u_int32_t ipnum;
-	u_int32_t *iparray;
+	__u32 rangesize;
+	__u32 ipnum;
+	__u32 *iparray;
 
 	/* hangs off end. */
 	struct nf_nat_range range[IPT_SAME_MAX_RANGE];
diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h
index ee6611edc112..f6250e422d5e 100644
--- a/include/linux/netfilter_ipv4/ipt_TTL.h
+++ b/include/linux/netfilter_ipv4/ipt_TTL.h
@@ -13,8 +13,8 @@ enum {
 #define IPT_TTL_MAXMODE	IPT_TTL_DEC
 
 struct ipt_TTL_info {
-	u_int8_t	mode;
-	u_int8_t	ttl;
+	__u8	mode;
+	__u8	ttl;
 };
 
 
diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h
index 446de6aef983..f29c3cfcc240 100644
--- a/include/linux/netfilter_ipv4/ipt_addrtype.h
+++ b/include/linux/netfilter_ipv4/ipt_addrtype.h
@@ -9,17 +9,17 @@ enum {
 };
 
 struct ipt_addrtype_info_v1 {
-	u_int16_t	source;		/* source-type mask */
-	u_int16_t	dest;		/* dest-type mask */
-	u_int32_t	flags;
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	flags;
 };
 
 /* revision 0 */
 struct ipt_addrtype_info {
-	u_int16_t	source;		/* source-type mask */
-	u_int16_t	dest;		/* dest-type mask */
-	u_int32_t	invert_source;
-	u_int32_t	invert_dest;
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	invert_source;
+	__u32	invert_dest;
 };
 
 #endif
diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h
index 2e555b4d05e3..8fea283ee62a 100644
--- a/include/linux/netfilter_ipv4/ipt_ah.h
+++ b/include/linux/netfilter_ipv4/ipt_ah.h
@@ -2,8 +2,8 @@
 #define _IPT_AH_H
 
 struct ipt_ah {
-	u_int32_t spis[2];			/* Security Parameter Index */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 spis[2];			/* Security Parameter Index */
+	__u8  invflags;			/* Inverse flags */
 };
 
 
diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h
index 9945baa4ccd7..78b98aa8784d 100644
--- a/include/linux/netfilter_ipv4/ipt_ecn.h
+++ b/include/linux/netfilter_ipv4/ipt_ecn.h
@@ -20,12 +20,12 @@
 
 /* match info */
 struct ipt_ecn_info {
-	u_int8_t operation;
-	u_int8_t invert;
-	u_int8_t ip_ect;
+	__u8 operation;
+	__u8 invert;
+	__u8 ip_ect;
 	union {
 		struct {
-			u_int8_t ect;
+			__u8 ect;
 		} tcp;
 	} proto;
 };
diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h
index ee24fd86a3aa..93d9a06689a3 100644
--- a/include/linux/netfilter_ipv4/ipt_ttl.h
+++ b/include/linux/netfilter_ipv4/ipt_ttl.h
@@ -13,8 +13,8 @@ enum {
 
 
 struct ipt_ttl_info {
-	u_int8_t	mode;
-	u_int8_t	ttl;
+	__u8	mode;
+	__u8	ttl;
 };
 
 
diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h
index afb7813d45ab..81cdaf0480e3 100644
--- a/include/linux/netfilter_ipv6/ip6t_HL.h
+++ b/include/linux/netfilter_ipv6/ip6t_HL.h
@@ -14,8 +14,8 @@ enum {
 #define IP6T_HL_MAXMODE	IP6T_HL_DEC
 
 struct ip6t_HL_info {
-	u_int8_t	mode;
-	u_int8_t	hop_limit;
+	__u8	mode;
+	__u8	hop_limit;
 };
 
 
diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h
index 6be6504162bb..b999aa4e5969 100644
--- a/include/linux/netfilter_ipv6/ip6t_REJECT.h
+++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h
@@ -12,7 +12,7 @@ enum ip6t_reject_with {
 };
 
 struct ip6t_reject_info {
-	u_int32_t	with;	/* reject type */
+	__u32	with;	/* reject type */
 };
 
 #endif /*_IP6T_REJECT_H*/
diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h
index 17a745cfb2c7..a602c165edd1 100644
--- a/include/linux/netfilter_ipv6/ip6t_ah.h
+++ b/include/linux/netfilter_ipv6/ip6t_ah.h
@@ -2,10 +2,10 @@
 #define _IP6T_AH_H
 
 struct ip6t_ah {
-	u_int32_t spis[2];			/* Security Parameter Index */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  hdrres;			/* Test of the Reserved Filed */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 spis[2];			/* Security Parameter Index */
+	__u32 hdrlen;			/* Header Length */
+	__u8  hdrres;			/* Test of the Reserved Filed */
+	__u8  invflags;			/* Inverse flags */
 };
 
 #define IP6T_AH_SPI 0x01
diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h
index 3724d0850920..538b31ef5e3d 100644
--- a/include/linux/netfilter_ipv6/ip6t_frag.h
+++ b/include/linux/netfilter_ipv6/ip6t_frag.h
@@ -2,10 +2,10 @@
 #define _IP6T_FRAG_H
 
 struct ip6t_frag {
-	u_int32_t ids[2];			/* Security Parameter Index */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  flags;			/*  */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 ids[2];			/* Security Parameter Index */
+	__u32 hdrlen;			/* Header Length */
+	__u8  flags;			/*  */
+	__u8  invflags;			/* Inverse flags */
 };
 
 #define IP6T_FRAG_IDS 		0x01
diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h
index 5ef91b8319a8..c6fddcb971da 100644
--- a/include/linux/netfilter_ipv6/ip6t_hl.h
+++ b/include/linux/netfilter_ipv6/ip6t_hl.h
@@ -14,8 +14,8 @@ enum {
 
 
 struct ip6t_hl_info {
-	u_int8_t	mode;
-	u_int8_t	hop_limit;
+	__u8	mode;
+	__u8	hop_limit;
 };
 
 
diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h
index 01dfd445596a..73d53bd3ff62 100644
--- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h
+++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h
@@ -9,9 +9,9 @@ on whether they contain certain headers */
 #define __IPV6HEADER_H
 
 struct ip6t_ipv6header_info {
-	u_int8_t matchflags;
-	u_int8_t invflags;
-	u_int8_t modeflag;
+	__u8 matchflags;
+	__u8 invflags;
+	__u8 modeflag;
 };
 
 #define MASK_HOPOPTS    128
diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h
index 18549bca2d1f..98c8cf685eea 100644
--- a/include/linux/netfilter_ipv6/ip6t_mh.h
+++ b/include/linux/netfilter_ipv6/ip6t_mh.h
@@ -3,8 +3,8 @@
 
 /* MH matching stuff */
 struct ip6t_mh {
-	u_int8_t types[2];	/* MH type range */
-	u_int8_t invflags;	/* Inverse flags */
+	__u8 types[2];	/* MH type range */
+	__u8 invflags;	/* Inverse flags */
 };
 
 /* Values for "invflags" field in struct ip6t_mh. */
diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h
index 62d89bcd9f9c..405d309cd741 100644
--- a/include/linux/netfilter_ipv6/ip6t_opts.h
+++ b/include/linux/netfilter_ipv6/ip6t_opts.h
@@ -4,11 +4,11 @@
 #define IP6T_OPTS_OPTSNR 16
 
 struct ip6t_opts {
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t flags;				/*  */
-	u_int8_t invflags;			/* Inverse flags */
-	u_int16_t opts[IP6T_OPTS_OPTSNR];	/* opts */
-	u_int8_t optsnr;			/* Nr of OPts */
+	__u32 hdrlen;			/* Header Length */
+	__u8 flags;				/*  */
+	__u8 invflags;			/* Inverse flags */
+	__u16 opts[IP6T_OPTS_OPTSNR];	/* opts */
+	__u8 optsnr;			/* Nr of OPts */
 };
 
 #define IP6T_OPTS_LEN 		0x01
diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h
index ab91bfd2cd00..e8dad20acd37 100644
--- a/include/linux/netfilter_ipv6/ip6t_rt.h
+++ b/include/linux/netfilter_ipv6/ip6t_rt.h
@@ -6,13 +6,13 @@
 #define IP6T_RT_HOPS 16
 
 struct ip6t_rt {
-	u_int32_t rt_type;			/* Routing Type */
-	u_int32_t segsleft[2];			/* Segments Left */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  flags;			/*  */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 rt_type;			/* Routing Type */
+	__u32 segsleft[2];			/* Segments Left */
+	__u32 hdrlen;			/* Header Length */
+	__u8  flags;			/*  */
+	__u8  invflags;			/* Inverse flags */
 	struct in6_addr addrs[IP6T_RT_HOPS];	/* Hops */
-	u_int8_t addrnr;			/* Nr of Addresses */
+	__u8 addrnr;			/* Nr of Addresses */
 };
 
 #define IP6T_RT_TYP 		0x01
-- 
cgit v1.2.3


From 0b8ad876275c74e4bfb6ec3150793f3c0ecfcee2 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Tue, 18 Jan 2011 11:23:06 +0100
Subject: netfilter: xtables: add missing header files to export list

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/Kbuild | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9f11fbc377e2..fc4e0aa805a2 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -56,6 +56,8 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
+header-y += xt_secmark.h
+header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
 header-y += xt_string.h
-- 
cgit v1.2.3


From a7c2f4d7daf9bbea362763fa7353b1862a2487ad Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Tue, 18 Jan 2011 15:02:48 +0100
Subject: netfilter: nf_nat: fix conversion to non-atomic bit ops

My previous patch (netfilter: nf_nat: don't use atomic bit operation)
made a mistake when converting atomic_set to a normal bit 'or'.
IPS_*_BIT should be replaced with IPS_*.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Cc: Tim Gardner <tim.gardner@canonical.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_nat_core.h | 4 ++--
 net/ipv4/netfilter/nf_nat_core.c    | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h
index 5aec85c29979..3dc7b98effeb 100644
--- a/include/net/netfilter/nf_nat_core.h
+++ b/include/net/netfilter/nf_nat_core.h
@@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {
 	if (manip == IP_NAT_MANIP_SRC)
-		return ct->status & IPS_SRC_NAT_DONE_BIT;
+		return ct->status & IPS_SRC_NAT_DONE;
 	else
-		return ct->status & IPS_DST_NAT_DONE_BIT;
+		return ct->status & IPS_DST_NAT_DONE;
 }
 
 struct nlattr;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 6972ceee99c6..3002c0492fb0 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -323,9 +323,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 
 	/* It's done. */
 	if (maniptype == IP_NAT_MANIP_DST)
-		ct->status |= IPS_DST_NAT_DONE_BIT;
+		ct->status |= IPS_DST_NAT_DONE;
 	else
-		ct->status |= IPS_SRC_NAT_DONE_BIT;
+		ct->status |= IPS_SRC_NAT_DONE;
 
 	return NF_ACCEPT;
 }
-- 
cgit v1.2.3


From f615df76ed862b7d3927ec5f55b805ca19be29d9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Jan 2011 15:52:14 +0100
Subject: netfilter: reduce NF_VERDICT_MASK to 0xff

NF_VERDICT_MASK is currently 0xffff. This is because the upper
16 bits are used to store errno (for NF_DROP) or the queue number
(NF_QUEUE verdict).

As there are up to 0xffff different queues available, there is no more
room to store additional flags.

At the moment there are only 6 different verdicts, i.e. we can reduce
NF_VERDICT_MASK to 0xff to allow storing additional flags in the 0xff00 space.

NF_VERDICT_BITS would then be reduced to 8, but because the value is
exported to userspace, this might cause breakage; e.g.:

e.g. 'queuenr = (1 << NF_VERDICT_BITS) | NF_QUEUE'  would now break.

Thus, remove NF_VERDICT_BITS usage in the kernel and move the old value
to the 'userspace compat' section.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h | 20 +++++++++++++++-----
 net/netfilter/core.c      |  4 ++--
 net/netfilter/nf_queue.c  |  2 +-
 3 files changed, 18 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 0ab7ca787b22..78b73cc10216 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -24,16 +24,19 @@
 #define NF_MAX_VERDICT NF_STOP
 
 /* we overload the higher bits for encoding auxiliary data such as the queue
- * number. Not nice, but better than additional function arguments. */
-#define NF_VERDICT_MASK 0x0000ffff
-#define NF_VERDICT_BITS 16
+ * number or errno values. Not nice, but better than additional function
+ * arguments. */
+#define NF_VERDICT_MASK 0x000000ff
+
+/* extra verdict flags have mask 0x0000ff00 */
 
+/* queue number (NF_QUEUE) or errno (NF_DROP) */
 #define NF_VERDICT_QMASK 0xffff0000
 #define NF_VERDICT_QBITS 16
 
-#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE)
+#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE)
 
-#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP)
+#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP)
 
 /* only for userspace compatibility */
 #ifndef __KERNEL__
@@ -41,6 +44,9 @@
    <= 0x2000 is used for protocol-flags. */
 #define NFC_UNKNOWN 0x4000
 #define NFC_ALTERED 0x8000
+
+/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */
+#define NF_VERDICT_BITS 16
 #endif
 
 enum nf_inet_hooks {
@@ -72,6 +78,10 @@ union nf_inet_addr {
 
 #ifdef __KERNEL__
 #ifdef CONFIG_NETFILTER
+static inline int NF_DROP_GETERR(int verdict)
+{
+	return -(verdict >> NF_VERDICT_QBITS);
+}
 
 static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1,
 				   const union nf_inet_addr *a2)
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 0c5b796ef527..4d88e45b978e 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -175,12 +175,12 @@ next_hook:
 		ret = 1;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
 		kfree_skb(skb);
-		ret = -(verdict >> NF_VERDICT_BITS);
+		ret = NF_DROP_GETERR(verdict);
 		if (ret == 0)
 			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
 		ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
-			       verdict >> NF_VERDICT_BITS);
+			       verdict >> NF_VERDICT_QBITS);
 		if (ret < 0) {
 			if (ret == -ECANCELED)
 				goto next_hook;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5c4b730a2e68..ce1150d4a3f2 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -299,7 +299,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	case NF_QUEUE:
 		err = __nf_queue(skb, elem, entry->pf, entry->hook,
 				 entry->indev, entry->outdev, entry->okfn,
-				 verdict >> NF_VERDICT_BITS);
+				 verdict >> NF_VERDICT_QBITS);
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
-- 
cgit v1.2.3


From 94b27cc36123069966616670c3653cd6873babe9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 18 Jan 2011 16:08:30 +0100
Subject: netfilter: allow NFQUEUE bypass if no listener is available

If an skb is to be NF_QUEUE'd, but no program has opened the queue, the
packet is dropped.

This adds a v2 target revision of xt_NFQUEUE that allows packets to
continue through the ruleset instead.

Because the actual queueing happens outside of the target context, the
'bypass' flag has to be communicated back to the netfilter core.

Unfortunately the only choice to do this without adding a new function
argument is to use the target function return value (i.e. the verdict).

In the NF_QUEUE case, the upper 16bit already contain the queue number
to use.  The previous patch reduced NF_VERDICT_MASK to 0xff, i.e.
we now have extra room for a new flag.

If a hook issued a NF_QUEUE verdict, then the netfilter core will
continue packet processing if the queueing hook
returns -ESRCH (== "this queue does not exist") and the new
NF_VERDICT_FLAG_QUEUE_BYPASS flag is set in the verdict value.

Note: If the queue exists, but userspace does not consume packets fast
enough, the skb will still be dropped.

Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h            |  1 +
 include/linux/netfilter/xt_NFQUEUE.h |  6 ++++++
 net/netfilter/core.c                 |  3 +++
 net/netfilter/nf_queue.c             |  7 ++++++-
 net/netfilter/xt_NFQUEUE.c           | 28 +++++++++++++++++++++++++---
 5 files changed, 41 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 78b73cc10216..eeec00abb664 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -29,6 +29,7 @@
 #define NF_VERDICT_MASK 0x000000ff
 
 /* extra verdict flags have mask 0x0000ff00 */
+#define NF_VERDICT_FLAG_QUEUE_BYPASS	0x00008000
 
 /* queue number (NF_QUEUE) or errno (NF_DROP) */
 #define NF_VERDICT_QMASK 0xffff0000
diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h
index 2584f4a777de..9eafdbbb401c 100644
--- a/include/linux/netfilter/xt_NFQUEUE.h
+++ b/include/linux/netfilter/xt_NFQUEUE.h
@@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 {
 	__u16 queues_total;
 };
 
+struct xt_NFQ_info_v2 {
+	__u16 queuenum;
+	__u16 queues_total;
+	__u16 bypass;
+};
+
 #endif /* _XT_NFQ_TARGET_H */
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 4d88e45b978e..1e00bf7d27c5 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -184,6 +184,9 @@ next_hook:
 		if (ret < 0) {
 			if (ret == -ECANCELED)
 				goto next_hook;
+			if (ret == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
 			kfree_skb(skb);
 		}
 		ret = 0;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index ce1150d4a3f2..5ab22e2bbd7d 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -138,8 +138,10 @@ static int __nf_queue(struct sk_buff *skb,
 	rcu_read_lock();
 
 	qh = rcu_dereference(queue_handler[pf]);
-	if (!qh)
+	if (!qh) {
+		status = -ESRCH;
 		goto err_unlock;
+	}
 
 	afinfo = nf_get_afinfo(pf);
 	if (!afinfo)
@@ -303,6 +305,9 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
+			if (err == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
 			kfree_skb(skb);
 		}
 		break;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 39627706aac6..d4f4b5d66b20 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -83,9 +83,20 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	return NF_QUEUE_NR(queue);
 }
 
-static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
+static unsigned int
+nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct xt_NFQ_info_v1 *info = par->targinfo;
+	const struct xt_NFQ_info_v2 *info = par->targinfo;
+	unsigned int ret = nfqueue_tg_v1(skb, par);
+
+	if (info->bypass)
+		ret |= NF_VERDICT_FLAG_QUEUE_BYPASS;
+	return ret;
+}
+
+static int nfqueue_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_NFQ_info_v2 *info = par->targinfo;
 	u32 maxid;
 
 	if (unlikely(!rnd_inited)) {
@@ -102,6 +113,8 @@ static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
 		       info->queues_total, maxid);
 		return -ERANGE;
 	}
+	if (par->target->revision == 2 && info->bypass > 1)
+		return -EINVAL;
 	return 0;
 }
 
@@ -117,11 +130,20 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = {
 		.name		= "NFQUEUE",
 		.revision	= 1,
 		.family		= NFPROTO_UNSPEC,
-		.checkentry	= nfqueue_tg_v1_check,
+		.checkentry	= nfqueue_tg_check,
 		.target		= nfqueue_tg_v1,
 		.targetsize	= sizeof(struct xt_NFQ_info_v1),
 		.me		= THIS_MODULE,
 	},
+	{
+		.name		= "NFQUEUE",
+		.revision	= 2,
+		.family		= NFPROTO_UNSPEC,
+		.checkentry	= nfqueue_tg_check,
+		.target		= nfqueue_tg_v2,
+		.targetsize	= sizeof(struct xt_NFQ_info_v2),
+		.me		= THIS_MODULE,
+	},
 };
 
 static int __init nfqueue_tg_init(void)
-- 
cgit v1.2.3


From 93557f53e1fbd9e2b6574ab0a9b5852628fde9e3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 18 Jan 2011 18:12:24 +0100
Subject: netfilter: nf_conntrack: nf_conntrack snmp helper

Adding support for SNMP broadcast connection tracking. The SNMP
broadcast requests are now paired with the SNMP responses.
Thus allowing using SNMP broadcasts with firewall enabled.

Please refer to the following conversation:
http://marc.info/?l=netfilter-devel&m=125992205006600&w=2

Patrick McHardy wrote:
> > The best solution would be to add generic broadcast tracking, the
> > use of expectations for this is a bit of abuse.
> > The second best choice I guess would be to move the help() function
> > to a shared module and generalize it so it can be used for both.
This patch implements the "second best choice".

Since the netbios-ns conntrack module uses the same helper
functionality as the snmp, only one helper function is added
for both snmp and netbios-ns modules into the new object -
nf_conntrack_broadcast.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nf_conntrack_snmp.h |  9 ++++
 include/net/netfilter/nf_conntrack_helper.h |  6 +++
 net/ipv4/netfilter/Kconfig                  |  3 +-
 net/ipv4/netfilter/nf_nat_snmp_basic.c      |  9 ++--
 net/netfilter/Kconfig                       | 19 +++++++
 net/netfilter/Makefile                      |  2 +
 net/netfilter/nf_conntrack_broadcast.c      | 82 +++++++++++++++++++++++++++++
 net/netfilter/nf_conntrack_netbios_ns.c     | 74 ++++----------------------
 net/netfilter/nf_conntrack_snmp.c           | 77 +++++++++++++++++++++++++++
 9 files changed, 211 insertions(+), 70 deletions(-)
 create mode 100644 include/linux/netfilter/nf_conntrack_snmp.h
 create mode 100644 net/netfilter/nf_conntrack_broadcast.c
 create mode 100644 net/netfilter/nf_conntrack_snmp.c

(limited to 'include')

diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h
new file mode 100644
index 000000000000..064bc63a5346
--- /dev/null
+++ b/include/linux/netfilter/nf_conntrack_snmp.h
@@ -0,0 +1,9 @@
+#ifndef _NF_CONNTRACK_SNMP_H
+#define _NF_CONNTRACK_SNMP_H
+
+extern int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo);
+
+#endif /* _NF_CONNTRACK_SNMP_H */
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 32c305dbdab6..f1c1311adc2c 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
 extern int nf_conntrack_helper_init(void);
 extern void nf_conntrack_helper_fini(void);
 
+extern int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				       unsigned int protoff,
+				       struct nf_conn *ct,
+				       enum ip_conntrack_info ctinfo,
+				       unsigned int timeout);
+
 #endif /*_NF_CONNTRACK_HELPER_H*/
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index babd1a2bae5f..f926a310075d 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -206,8 +206,9 @@ config IP_NF_TARGET_REDIRECT
 
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
-	depends on NF_NAT
+	depends on NF_CONNTRACK_SNMP && NF_NAT
 	depends on NETFILTER_ADVANCED
+	default NF_NAT && NF_CONNTRACK_SNMP
 	---help---
 
 	  This module implements an Application Layer Gateway (ALG) for
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index ee5f419d0a56..8812a02078ab 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -54,6 +54,7 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_nat_helper.h>
+#include <linux/netfilter/nf_conntrack_snmp.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
@@ -1310,9 +1311,9 @@ static int __init nf_nat_snmp_basic_init(void)
 {
 	int ret = 0;
 
-	ret = nf_conntrack_helper_register(&snmp_helper);
-	if (ret < 0)
-		return ret;
+	BUG_ON(nf_nat_snmp_hook != NULL);
+	rcu_assign_pointer(nf_nat_snmp_hook, help);
+
 	ret = nf_conntrack_helper_register(&snmp_trap_helper);
 	if (ret < 0) {
 		nf_conntrack_helper_unregister(&snmp_helper);
@@ -1323,7 +1324,7 @@ static int __init nf_nat_snmp_basic_init(void)
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
-	nf_conntrack_helper_unregister(&snmp_helper);
+	rcu_assign_pointer(nf_nat_snmp_hook, NULL);
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index e2480bddbfd5..939b504604c2 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -185,9 +185,13 @@ config NF_CONNTRACK_IRC
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_BROADCAST
+	tristate
+
 config NF_CONNTRACK_NETBIOS_NS
 	tristate "NetBIOS name service protocol support"
 	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
 	help
 	  NetBIOS name service requests are sent as broadcast messages from an
 	  unprivileged port and responded to with unicast messages to the
@@ -204,6 +208,21 @@ config NF_CONNTRACK_NETBIOS_NS
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_SNMP
+	tristate "SNMP service protocol support"
+	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
+	help
+	  SNMP service requests are sent as broadcast messages from an
+	  unprivileged port and responded to with unicast messages to the
+	  same port. This make them hard to firewall properly because connection
+	  tracking doesn't deal with broadcasts. This helper tracks locally
+	  originating SNMP service requests and the corresponding
+	  responses. It relies on correct IP address configuration, specifically
+	  netmask and broadcast address.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NF_CONNTRACK_PPTP
 	tristate "PPtP protocol support"
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 401d574bdfd2..2c2628de9d3f 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -28,7 +28,9 @@ obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o
 obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
 obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o
 obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o
+obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o
 obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o
+obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o
 obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o
 obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
new file mode 100644
index 000000000000..4e99cca61612
--- /dev/null
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -0,0 +1,82 @@
+/*
+ *      broadcast connection tracking helper
+ *
+ *      (c) 2005 Patrick McHardy <kaber@trash.net>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <net/route.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+
+int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo,
+				unsigned int timeout)
+{
+	struct nf_conntrack_expect *exp;
+	struct iphdr *iph = ip_hdr(skb);
+	struct rtable *rt = skb_rtable(skb);
+	struct in_device *in_dev;
+	struct nf_conn_help *help = nfct_help(ct);
+	__be32 mask = 0;
+
+	/* we're only interested in locally generated packets */
+	if (skb->sk == NULL)
+		goto out;
+	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
+		goto out;
+	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
+		goto out;
+
+	rcu_read_lock();
+	in_dev = __in_dev_get_rcu(rt->dst.dev);
+	if (in_dev != NULL) {
+		for_primary_ifa(in_dev) {
+			if (ifa->ifa_broadcast == iph->daddr) {
+				mask = ifa->ifa_mask;
+				break;
+			}
+		} endfor_ifa(in_dev);
+	}
+	rcu_read_unlock();
+
+	if (mask == 0)
+		goto out;
+
+	exp = nf_ct_expect_alloc(ct);
+	if (exp == NULL)
+		goto out;
+
+	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+	exp->tuple.src.u.udp.port = help->helper->tuple.src.u.udp.port;
+
+	exp->mask.src.u3.ip       = mask;
+	exp->mask.src.u.udp.port  = htons(0xFFFF);
+
+	exp->expectfn             = NULL;
+	exp->flags                = NF_CT_EXPECT_PERMANENT;
+	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
+	exp->helper               = NULL;
+
+	nf_ct_expect_related(exp);
+	nf_ct_expect_put(exp);
+
+	nf_ct_refresh(ct, skb, timeout * HZ);
+out:
+	return NF_ACCEPT;
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help);
+
+MODULE_LICENSE("GPL");
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index aadde018a072..4c8f30a3d6d2 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -18,14 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/if_addr.h>
 #include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <net/route.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
@@ -40,75 +33,26 @@ MODULE_ALIAS("ip_conntrack_netbios_ns");
 MODULE_ALIAS_NFCT_HELPER("netbios_ns");
 
 static unsigned int timeout __read_mostly = 3;
-module_param(timeout, uint, 0400);
+module_param(timeout, uint, S_IRUSR);
 MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
 
-static int help(struct sk_buff *skb, unsigned int protoff,
-		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
-{
-	struct nf_conntrack_expect *exp;
-	struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt = skb_rtable(skb);
-	struct in_device *in_dev;
-	__be32 mask = 0;
-
-	/* we're only interested in locally generated packets */
-	if (skb->sk == NULL)
-		goto out;
-	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
-		goto out;
-	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
-		goto out;
-
-	rcu_read_lock();
-	in_dev = __in_dev_get_rcu(rt->dst.dev);
-	if (in_dev != NULL) {
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_broadcast == iph->daddr) {
-				mask = ifa->ifa_mask;
-				break;
-			}
-		} endfor_ifa(in_dev);
-	}
-	rcu_read_unlock();
-
-	if (mask == 0)
-		goto out;
-
-	exp = nf_ct_expect_alloc(ct);
-	if (exp == NULL)
-		goto out;
-
-	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
-	exp->tuple.src.u.udp.port = htons(NMBD_PORT);
-
-	exp->mask.src.u3.ip       = mask;
-	exp->mask.src.u.udp.port  = htons(0xFFFF);
-
-	exp->expectfn             = NULL;
-	exp->flags                = NF_CT_EXPECT_PERMANENT;
-	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
-	exp->helper               = NULL;
-
-	nf_ct_expect_related(exp);
-	nf_ct_expect_put(exp);
-
-	nf_ct_refresh(ct, skb, timeout * HZ);
-out:
-	return NF_ACCEPT;
-}
-
 static struct nf_conntrack_expect_policy exp_policy = {
 	.max_expected	= 1,
 };
 
+static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff,
+		   struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	return nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+}
+
 static struct nf_conntrack_helper helper __read_mostly = {
 	.name			= "netbios-ns",
-	.tuple.src.l3num	= AF_INET,
+	.tuple.src.l3num	= NFPROTO_IPV4,
 	.tuple.src.u.udp.port	= cpu_to_be16(NMBD_PORT),
 	.tuple.dst.protonum	= IPPROTO_UDP,
 	.me			= THIS_MODULE,
-	.help			= help,
+	.help			= netbios_ns_help,
 	.expect_policy		= &exp_policy,
 };
 
diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c
new file mode 100644
index 000000000000..6e545e26289e
--- /dev/null
+++ b/net/netfilter/nf_conntrack_snmp.c
@@ -0,0 +1,77 @@
+/*
+ *      SNMP service broadcast connection tracking helper
+ *
+ *      (c) 2011 Jiri Olsa <jolsa@redhat.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/in.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+
+#define SNMP_PORT	161
+
+MODULE_AUTHOR("Jiri Olsa <jolsa@redhat.com>");
+MODULE_DESCRIPTION("SNMP service broadcast connection tracking helper");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFCT_HELPER("snmp");
+
+static unsigned int timeout __read_mostly = 30;
+module_param(timeout, uint, S_IRUSR);
+MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
+
+int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+			unsigned int protoff,
+			struct nf_conn *ct,
+			enum ip_conntrack_info ctinfo);
+EXPORT_SYMBOL_GPL(nf_nat_snmp_hook);
+
+static int snmp_conntrack_help(struct sk_buff *skb, unsigned int protoff,
+		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	typeof(nf_nat_snmp_hook) nf_nat_snmp;
+
+	nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+
+	nf_nat_snmp = rcu_dereference(nf_nat_snmp_hook);
+	if (nf_nat_snmp && ct->status & IPS_NAT_MASK)
+		return nf_nat_snmp(skb, protoff, ct, ctinfo);
+
+	return NF_ACCEPT;
+}
+
+static struct nf_conntrack_expect_policy exp_policy = {
+	.max_expected	= 1,
+};
+
+static struct nf_conntrack_helper helper __read_mostly = {
+	.name			= "snmp",
+	.tuple.src.l3num	= NFPROTO_IPV4,
+	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
+	.tuple.dst.protonum	= IPPROTO_UDP,
+	.me			= THIS_MODULE,
+	.help			= snmp_conntrack_help,
+	.expect_policy		= &exp_policy,
+};
+
+static int __init nf_conntrack_snmp_init(void)
+{
+	exp_policy.timeout = timeout;
+	return nf_conntrack_helper_register(&helper);
+}
+
+static void __exit nf_conntrack_snmp_fini(void)
+{
+	nf_conntrack_helper_unregister(&helper);
+}
+
+module_init(nf_conntrack_snmp_init);
+module_exit(nf_conntrack_snmp_fini);
-- 
cgit v1.2.3


From 80f8f1027b99660897bdeaeae73002185d829906 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 18 Jan 2011 07:46:52 +0000
Subject: net: filter: dont block softirqs in sk_run_filter()

Packet filter (BPF) doesnt need to disable softirqs, being fully
re-entrant and lock-less.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 2 +-
 net/core/filter.c      | 6 +++---
 net/packet/af_packet.c | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index d884d268c704..ba6465bf7c7a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1189,7 +1189,7 @@ extern void sk_filter_release_rcu(struct rcu_head *rcu);
 static inline void sk_filter_release(struct sk_filter *fp)
 {
 	if (atomic_dec_and_test(&fp->refcnt))
-		call_rcu_bh(&fp->rcu, sk_filter_release_rcu);
+		call_rcu(&fp->rcu, sk_filter_release_rcu);
 }
 
 static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
diff --git a/net/core/filter.c b/net/core/filter.c
index afc58374ca96..232b1873bb28 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -142,14 +142,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	rcu_read_lock_bh();
-	filter = rcu_dereference_bh(sk->sk_filter);
+	rcu_read_lock();
+	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
 		unsigned int pkt_len = sk_run_filter(skb, filter->insns);
 
 		err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return err;
 }
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 91cb1d71f018..c3fc7b70a879 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -523,11 +523,11 @@ static inline unsigned int run_filter(const struct sk_buff *skb,
 {
 	struct sk_filter *filter;
 
-	rcu_read_lock_bh();
-	filter = rcu_dereference_bh(sk->sk_filter);
+	rcu_read_lock();
+	filter = rcu_dereference(sk->sk_filter);
 	if (filter != NULL)
 		res = sk_run_filter(skb, filter->insns);
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	return res;
 }
-- 
cgit v1.2.3


From a992ca2a0498edd22a88ac8c41570f536de29c9e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 19 Jan 2011 16:00:07 +0100
Subject: netfilter: nf_conntrack_tstamp: add flow-based timestamp extension

This patch adds flow-based timestamping for conntracks. This
conntrack extension is disabled by default. Basically, we use
two 64-bits variables to store the creation timestamp once the
conntrack has been confirmed and the other to store the deletion
time. This extension is disabled by default, to enable it, you
have to:

echo 1 > /proc/sys/net/netfilter/nf_conntrack_timestamp

This patch allows to save memory for user-space flow-based
loogers such as ulogd2. In short, ulogd2 does not need to
keep a hashtable with the conntrack in user-space to know
when they were created and destroyed, instead we use the
kernel timestamp. If we want to have a sane IPFIX implementation
in user-space, this nanosecs resolution timestamps are also
useful. Other custom user-space applications can benefit from
this via libnetfilter_conntrack.

This patch modifies the /proc output to display the delta time
in seconds since the flow start. You can also obtain the
flow-start date by means of the conntrack-tools.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nfnetlink_conntrack.h  |   9 ++
 include/net/netfilter/nf_conntrack_extend.h    |   4 +
 include/net/netfilter/nf_conntrack_timestamp.h |  53 +++++++++++
 include/net/netns/conntrack.h                  |   2 +
 net/netfilter/Kconfig                          |  11 +++
 net/netfilter/Makefile                         |   1 +
 net/netfilter/nf_conntrack_core.c              |  26 ++++++
 net/netfilter/nf_conntrack_netlink.c           |  46 +++++++++-
 net/netfilter/nf_conntrack_standalone.c        |  41 +++++++++
 net/netfilter/nf_conntrack_timestamp.c         | 120 +++++++++++++++++++++++++
 10 files changed, 312 insertions(+), 1 deletion(-)
 create mode 100644 include/net/netfilter/nf_conntrack_timestamp.h
 create mode 100644 net/netfilter/nf_conntrack_timestamp.c

(limited to 'include')

diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index 19711e3ffd42..debf1aefd753 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -42,6 +42,7 @@ enum ctattr_type {
 	CTA_SECMARK,		/* obsolete */
 	CTA_ZONE,
 	CTA_SECCTX,
+	CTA_TIMESTAMP,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -127,6 +128,14 @@ enum ctattr_counters {
 };
 #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1)
 
+enum ctattr_tstamp {
+	CTA_TIMESTAMP_UNSPEC,
+	CTA_TIMESTAMP_START,
+	CTA_TIMESTAMP_STOP,
+	__CTA_TIMESTAMP_MAX
+};
+#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1)
+
 enum ctattr_nat {
 	CTA_NAT_UNSPEC,
 	CTA_NAT_MINIP,
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 1a9f96db3798..2dcf31703acb 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -16,6 +16,9 @@ enum nf_ct_ext_id {
 #endif
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	NF_CT_EXT_ZONE,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	NF_CT_EXT_TSTAMP,
 #endif
 	NF_CT_EXT_NUM,
 };
@@ -25,6 +28,7 @@ enum nf_ct_ext_id {
 #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
+#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp
 
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h
new file mode 100644
index 000000000000..f17dcb664e29
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_timestamp.h
@@ -0,0 +1,53 @@
+#ifndef _NF_CONNTRACK_TSTAMP_H
+#define _NF_CONNTRACK_TSTAMP_H
+
+#include <net/net_namespace.h>
+#include <linux/netfilter/nf_conntrack_common.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+
+struct nf_conn_tstamp {
+	u_int64_t start;
+	u_int64_t stop;
+};
+
+static inline
+struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP);
+#else
+	return NULL;
+#endif
+}
+
+static inline
+struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	struct net *net = nf_ct_net(ct);
+
+	if (!net->ct.sysctl_tstamp)
+		return NULL;
+
+	return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp);
+#else
+	return NULL;
+#endif
+};
+
+static inline bool nf_ct_tstamp_enabled(struct net *net)
+{
+	return net->ct.sysctl_tstamp != 0;
+}
+
+static inline void nf_ct_set_tstamp(struct net *net, bool enable)
+{
+	net->ct.sysctl_tstamp = enable;
+}
+
+extern int nf_conntrack_tstamp_init(struct net *net);
+extern void nf_conntrack_tstamp_fini(struct net *net);
+
+#endif /* _NF_CONNTRACK_TSTAMP_H */
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 5cf8a8c141aa..341eb089349e 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -21,11 +21,13 @@ struct netns_ct {
 	int			sysctl_events;
 	unsigned int		sysctl_events_retry_timeout;
 	int			sysctl_acct;
+	int			sysctl_tstamp;
 	int			sysctl_checksum;
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
 	struct ctl_table_header	*acct_sysctl_header;
+	struct ctl_table_header	*tstamp_sysctl_header;
 	struct ctl_table_header	*event_sysctl_header;
 #endif
 	char			*slabname;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 939b504604c2..faf7412ea453 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -85,6 +85,17 @@ config NF_CONNTRACK_EVENTS
 
 	  If unsure, say `N'.
 
+config NF_CONNTRACK_TIMESTAMP
+	bool  'Connection tracking timestamping'
+	depends on NETFILTER_ADVANCED
+	help
+	  This option enables support for connection tracking timestamping.
+	  This allows you to store the flow start-time and to obtain
+	  the flow-stop time (once it has been destroyed) via Connection
+	  tracking events.
+
+	  If unsure, say `N'.
+
 config NF_CT_PROTO_DCCP
 	tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)'
 	depends on EXPERIMENTAL
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 2c2628de9d3f..9ae6878a85b1 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,6 +1,7 @@
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
 
 nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o
+nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f47ac67e1bfe..1909311c392a 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -43,6 +43,7 @@
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
 
@@ -282,6 +283,11 @@ EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
 static void death_by_timeout(unsigned long ul_conntrack)
 {
 	struct nf_conn *ct = (void *)ul_conntrack;
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp && tstamp->stop == 0)
+		tstamp->stop = ktime_to_ns(ktime_get_real());
 
 	if (!test_bit(IPS_DYING_BIT, &ct->status) &&
 	    unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
@@ -419,6 +425,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
+	struct nf_conn_tstamp *tstamp;
 	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
@@ -488,6 +495,14 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	atomic_inc(&ct->ct_general.use);
 	ct->status |= IPS_CONFIRMED;
 
+	/* set conntrack timestamp, if enabled. */
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp) {
+		if (skb->tstamp.tv64 == 0)
+			__net_timestamp((struct sk_buff *)skb);
+
+		tstamp->start = ktime_to_ns(skb->tstamp);
+	}
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
 	 * guarantee that no other CPU can find the conntrack before the above
@@ -746,6 +761,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 
 	ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
 	nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
@@ -1186,6 +1202,11 @@ struct __nf_ct_flush_report {
 static int kill_report(struct nf_conn *i, void *data)
 {
 	struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(i);
+	if (tstamp && tstamp->stop == 0)
+		tstamp->stop = ktime_to_ns(ktime_get_real());
 
 	/* If we fail to deliver the event, death_by_timeout() will retry */
 	if (nf_conntrack_event_report(IPCT_DESTROY, i,
@@ -1497,6 +1518,9 @@ static int nf_conntrack_init_net(struct net *net)
 	ret = nf_conntrack_acct_init(net);
 	if (ret < 0)
 		goto err_acct;
+	ret = nf_conntrack_tstamp_init(net);
+	if (ret < 0)
+		goto err_tstamp;
 	ret = nf_conntrack_ecache_init(net);
 	if (ret < 0)
 		goto err_ecache;
@@ -1504,6 +1528,8 @@ static int nf_conntrack_init_net(struct net *net)
 	return 0;
 
 err_ecache:
+	nf_conntrack_tstamp_fini(net);
+err_tstamp:
 	nf_conntrack_acct_fini(net);
 err_acct:
 	nf_conntrack_expect_fini(net);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9eabaa6f28a8..715d56c85475 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -42,6 +42,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_protocol.h>
@@ -230,6 +231,33 @@ nla_put_failure:
 	return -1;
 }
 
+static int
+ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct)
+{
+	struct nlattr *nest_count;
+	const struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (!tstamp)
+		return 0;
+
+	nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED);
+	if (!nest_count)
+		goto nla_put_failure;
+
+	NLA_PUT_BE64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start));
+	if (tstamp->stop != 0) {
+		NLA_PUT_BE64(skb, CTA_TIMESTAMP_STOP,
+			     cpu_to_be64(tstamp->stop));
+	}
+	nla_nest_end(skb, nest_count);
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
 #ifdef CONFIG_NF_CONNTRACK_MARK
 static inline int
 ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct)
@@ -404,6 +432,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	    ctnetlink_dump_timeout(skb, ct) < 0 ||
 	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
 	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+	    ctnetlink_dump_timestamp(skb, ct) < 0 ||
 	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_mark(skb, ct) < 0 ||
@@ -470,6 +499,18 @@ ctnetlink_secctx_size(const struct nf_conn *ct)
 #endif
 }
 
+static inline size_t
+ctnetlink_timestamp_size(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP))
+		return 0;
+	return nla_total_size(0) + 2 * nla_total_size(sizeof(uint64_t));
+#else
+	return 0;
+#endif
+}
+
 static inline size_t
 ctnetlink_nlmsg_size(const struct nf_conn *ct)
 {
@@ -481,6 +522,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
 	       + ctnetlink_counters_size(ct)
+	       + ctnetlink_timestamp_size(ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
 	       + nla_total_size(0) /* CTA_PROTOINFO */
 	       + nla_total_size(0) /* CTA_HELP */
@@ -571,7 +613,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 
 	if (events & (1 << IPCT_DESTROY)) {
 		if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
-		    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)
+		    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+		    ctnetlink_dump_timestamp(skb, ct) < 0)
 			goto nla_put_failure;
 	} else {
 		if (ctnetlink_dump_timeout(skb, ct) < 0)
@@ -1360,6 +1403,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 	nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
 	/* we must add conntrack extensions before confirmation. */
 	ct->status |= IPS_CONFIRMED;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 8257bf643593..69107fd78d3e 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #include <linux/rculist_nulls.h>
 
 MODULE_LICENSE("GPL");
@@ -46,6 +47,7 @@ EXPORT_SYMBOL_GPL(print_tuple);
 struct ct_iter_state {
 	struct seq_net_private p;
 	unsigned int bucket;
+	u_int64_t time_now;
 };
 
 static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
@@ -96,6 +98,9 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
 static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
+	struct ct_iter_state *st = seq->private;
+
+	st->time_now = ktime_to_ns(ktime_get_real());
 	rcu_read_lock();
 	return ct_get_idx(seq, *pos);
 }
@@ -135,6 +140,39 @@ static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 }
 #endif
 
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+static u_int64_t ct_delta_time(u_int64_t time_now, const struct nf_conn *ct)
+{
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp) {
+		u_int64_t delta_time = time_now - tstamp->start;
+		return delta_time > 0 ? div_s64(delta_time, NSEC_PER_SEC) : 0;
+	}
+	return -1;
+}
+
+static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+{
+	struct ct_iter_state *st = s->private;
+	u_int64_t delta_time;
+
+	delta_time = ct_delta_time(st->time_now, ct);
+	if (delta_time < 0)
+		return 0;
+
+	return seq_printf(s, "delta-time=%llu ",
+			  (unsigned long long)delta_time);
+}
+#else
+static inline int
+ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+{
+	return 0;
+}
+#endif
+
 /* return 0 on success, 1 in case of error */
 static int ct_seq_show(struct seq_file *s, void *v)
 {
@@ -203,6 +241,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		goto release;
 #endif
 
+	if (ct_show_delta_time(s, ct))
+		goto release;
+
 	if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
 		goto release;
 
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
new file mode 100644
index 000000000000..af7dd31af0a1
--- /dev/null
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -0,0 +1,120 @@
+/*
+ * (C) 2010 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation (or any later at your option).
+ */
+
+#include <linux/netfilter.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
+
+static int nf_ct_tstamp __read_mostly;
+
+module_param_named(tstamp, nf_ct_tstamp, bool, 0644);
+MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping.");
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table tstamp_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_timestamp",
+		.data		= &init_net.ct.sysctl_tstamp,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{}
+};
+#endif /* CONFIG_SYSCTL */
+
+static struct nf_ct_ext_type tstamp_extend __read_mostly = {
+	.len	= sizeof(struct nf_conn_tstamp),
+	.align	= __alignof__(struct nf_conn_tstamp),
+	.id	= NF_CT_EXT_TSTAMP,
+};
+
+#ifdef CONFIG_SYSCTL
+static int nf_conntrack_tstamp_init_sysctl(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = kmemdup(tstamp_sysctl_table, sizeof(tstamp_sysctl_table),
+			GFP_KERNEL);
+	if (!table)
+		goto out;
+
+	table[0].data = &net->ct.sysctl_tstamp;
+
+	net->ct.tstamp_sysctl_header = register_net_sysctl_table(net,
+			nf_net_netfilter_sysctl_path, table);
+	if (!net->ct.tstamp_sysctl_header) {
+		printk(KERN_ERR "nf_ct_tstamp: can't register to sysctl.\n");
+		goto out_register;
+	}
+	return 0;
+
+out_register:
+	kfree(table);
+out:
+	return -ENOMEM;
+}
+
+static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->ct.tstamp_sysctl_header->ctl_table_arg;
+	unregister_net_sysctl_table(net->ct.tstamp_sysctl_header);
+	kfree(table);
+}
+#else
+static int nf_conntrack_tstamp_init_sysctl(struct net *net)
+{
+	return 0;
+}
+
+static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
+{
+}
+#endif
+
+int nf_conntrack_tstamp_init(struct net *net)
+{
+	int ret;
+
+	net->ct.sysctl_tstamp = nf_ct_tstamp;
+
+	if (net_eq(net, &init_net)) {
+		ret = nf_ct_extend_register(&tstamp_extend);
+		if (ret < 0) {
+			printk(KERN_ERR "nf_ct_tstamp: Unable to register "
+					"extension\n");
+			goto out_extend_register;
+		}
+	}
+
+	ret = nf_conntrack_tstamp_init_sysctl(net);
+	if (ret < 0)
+		goto out_sysctl;
+
+	return 0;
+
+out_sysctl:
+	if (net_eq(net, &init_net))
+		nf_ct_extend_unregister(&tstamp_extend);
+out_extend_register:
+	return ret;
+}
+
+void nf_conntrack_tstamp_fini(struct net *net)
+{
+	nf_conntrack_tstamp_fini_sysctl(net);
+	if (net_eq(net, &init_net))
+		nf_ct_extend_unregister(&tstamp_extend);
+}
-- 
cgit v1.2.3


From df6ba5d80d6c9b51471d5fa046c3c06988e5f62a Mon Sep 17 00:00:00 2001
From: Luciano Coelho <coelho@ti.com>
Date: Wed, 12 Jan 2011 15:26:30 +0200
Subject: mac80211: add hw configuration for max ampdu buffer size

Some devices don't support the maximum AMDPU buffer size of 64, so we
need to add an option to configure this in the hardware configuration.
This value will be used in the ADDBA response instead of the value
suggested in the request, if the latter is greater than the max
supported.

Signed-off-by: Luciano Coelho <coelho@ti.com>
Tested-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/mac80211.h | 8 ++++++++
 net/mac80211/agg-rx.c  | 3 +++
 net/mac80211/main.c    | 1 +
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 62c0ce2d1dc8..d024fc563e7b 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1147,6 +1147,13 @@ enum ieee80211_hw_flags {
  * @napi_weight: weight used for NAPI polling.  You must specify an
  *	appropriate value here if a napi_poll operation is provided
  *	by your driver.
+
+ * @max_rx_aggregation_subframes: maximum buffer size (number of
+ *	sub-frames) to be used for A-MPDU block ack receiver
+ *	aggregation.
+ *	This is only relevant if the device has restrictions on the
+ *	number of subframes, if it relies on mac80211 to do reordering
+ *	it shouldn't be set.
  */
 struct ieee80211_hw {
 	struct ieee80211_conf conf;
@@ -1165,6 +1172,7 @@ struct ieee80211_hw {
 	u8 max_rates;
 	u8 max_report_rates;
 	u8 max_rate_tries;
+	u8 max_rx_aggregation_subframes;
 };
 
 /**
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index f138b195d657..002db5e86eb6 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -239,6 +239,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local,
 		buf_size = buf_size << sband->ht_cap.ampdu_factor;
 	}
 
+	/* make sure the size doesn't exceed the maximum supported by the hw */
+	if (buf_size > local->hw.max_rx_aggregation_subframes)
+		buf_size = local->hw.max_rx_aggregation_subframes;
 
 	/* examine state machine */
 	mutex_lock(&sta->ampdu_mlme.mtx);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 485d36bc9a46..1c507c6972e6 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -552,6 +552,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
 	local->hw.queues = 1;
 	local->hw.max_rates = 1;
 	local->hw.max_report_rates = 0;
+	local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
 	local->hw.conf.long_frame_max_tx_count = wiphy->retry_long;
 	local->hw.conf.short_frame_max_tx_count = wiphy->retry_short;
 	local->user_power_level = -1;
-- 
cgit v1.2.3


From 0b01f030d38e00650e2db42da083d8647aad40a5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 18 Jan 2011 13:51:05 +0100
Subject: mac80211: track receiver's aggregation reorder buffer size

The aggregation code currently doesn't implement the
buffer size negotiation. It will always request a max
buffer size (which is fine, if a little pointless, as
the mac80211 code doesn't know and might just use 0
instead), but if the peer requests a smaller size it
isn't possible to honour this request.

In order to fix this, look at the buffer size in the
addBA response frame, keep track of it and pass it to
the driver in the ampdu_action callback when called
with the IEEE80211_AMPDU_TX_OPERATIONAL action. That
way the driver can limit the number of subframes in
aggregates appropriately.

Note that this doesn't fix any drivers apart from the
addition of the new argument -- they all need to be
updated separately to use this variable!

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/ath/ar9170/main.c        |  3 ++-
 drivers/net/wireless/ath/ath9k/htc_drv_main.c |  2 +-
 drivers/net/wireless/ath/ath9k/main.c         |  2 +-
 drivers/net/wireless/ath/carl9170/main.c      |  2 +-
 drivers/net/wireless/iwlwifi/iwl-agn.c        |  3 ++-
 drivers/net/wireless/iwlwifi/iwl-agn.h        |  3 ++-
 drivers/net/wireless/mac80211_hwsim.c         |  3 ++-
 drivers/net/wireless/mwl8k.c                  |  3 ++-
 drivers/net/wireless/rt2x00/rt2800lib.c       |  3 ++-
 drivers/net/wireless/rt2x00/rt2800lib.h       |  3 ++-
 drivers/net/wireless/rtlwifi/core.c           |  3 ++-
 include/net/mac80211.h                        |  7 ++++++-
 net/mac80211/agg-rx.c                         |  4 ++--
 net/mac80211/agg-tx.c                         | 20 +++++++++++++++++---
 net/mac80211/driver-ops.h                     |  6 +++---
 net/mac80211/driver-trace.h                   | 11 +++++++----
 net/mac80211/sta_info.h                       |  2 ++
 17 files changed, 56 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c
index 32bf79e6a320..a9111e1161fd 100644
--- a/drivers/net/wireless/ath/ar9170/main.c
+++ b/drivers/net/wireless/ath/ar9170/main.c
@@ -1945,7 +1945,8 @@ static int ar9170_conf_tx(struct ieee80211_hw *hw, u16 queue,
 static int ar9170_ampdu_action(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif,
 			       enum ieee80211_ampdu_mlme_action action,
-			       struct ieee80211_sta *sta, u16 tid, u16 *ssn)
+			       struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			       u8 buf_size)
 {
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 187af5b4440d..f14f37d29f45 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1549,7 +1549,7 @@ static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  enum ieee80211_ampdu_mlme_action action,
 				  struct ieee80211_sta *sta,
-				  u16 tid, u16 *ssn)
+				  u16 tid, u16 *ssn, u8 buf_size)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
 	struct ath9k_htc_sta *ista;
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 174c016ef89d..c03184e7bffe 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -2165,7 +2165,7 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif,
 			      enum ieee80211_ampdu_mlme_action action,
 			      struct ieee80211_sta *sta,
-			      u16 tid, u16 *ssn)
+			      u16 tid, u16 *ssn, u8 buf_size)
 {
 	struct ath_wiphy *aphy = hw->priv;
 	struct ath_softc *sc = aphy->sc;
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index 870df8c42622..ecfb80b059d1 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -1279,7 +1279,7 @@ static int carl9170_op_ampdu_action(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    enum ieee80211_ampdu_mlme_action action,
 				    struct ieee80211_sta *sta,
-				    u16 tid, u16 *ssn)
+				    u16 tid, u16 *ssn, u8 buf_size)
 {
 	struct ar9170 *ar = hw->priv;
 	struct carl9170_sta_info *sta_info = (void *) sta->drv_priv;
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 36335b1b54d4..8b045a401d62 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -3393,7 +3393,8 @@ int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 			    struct ieee80211_vif *vif,
 			    enum ieee80211_ampdu_mlme_action action,
-			    struct ieee80211_sta *sta, u16 tid, u16 *ssn)
+			    struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			    u8 buf_size)
 {
 	struct iwl_priv *priv = hw->priv;
 	int ret = -EINVAL;
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h
index da303585f801..822221a97e80 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.h
@@ -349,7 +349,8 @@ void iwlagn_mac_update_tkip_key(struct ieee80211_hw *hw,
 int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 			    struct ieee80211_vif *vif,
 			    enum ieee80211_ampdu_mlme_action action,
-			    struct ieee80211_sta *sta, u16 tid, u16 *ssn);
+			    struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			    u8 buf_size);
 int iwlagn_mac_sta_add(struct ieee80211_hw *hw,
 		       struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 454f045ddff3..5d39b2840584 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -943,7 +943,8 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw,
 static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
 				       enum ieee80211_ampdu_mlme_action action,
-				       struct ieee80211_sta *sta, u16 tid, u16 *ssn)
+				       struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+				       u8 buf_size)
 {
 	switch (action) {
 	case IEEE80211_AMPDU_TX_START:
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 809f2bf27958..106b427d0064 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -4356,7 +4356,8 @@ static int mwl8k_get_survey(struct ieee80211_hw *hw, int idx,
 static int
 mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		   enum ieee80211_ampdu_mlme_action action,
-		   struct ieee80211_sta *sta, u16 tid, u16 *ssn)
+		   struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+		   u8 buf_size)
 {
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index a25be625ee90..f8ba01cbc6dd 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -3533,7 +3533,8 @@ EXPORT_SYMBOL_GPL(rt2800_get_tsf);
 
 int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 *ssn)
+			struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			u8 buf_size)
 {
 	int ret = 0;
 
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.h b/drivers/net/wireless/rt2x00/rt2800lib.h
index e3c995a9dec4..3efafb78ff77 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.h
+++ b/drivers/net/wireless/rt2x00/rt2800lib.h
@@ -198,7 +198,8 @@ int rt2800_conf_tx(struct ieee80211_hw *hw, u16 queue_idx,
 u64 rt2800_get_tsf(struct ieee80211_hw *hw);
 int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 *ssn);
+			struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			u8 buf_size);
 int rt2800_get_survey(struct ieee80211_hw *hw, int idx,
 		      struct survey_info *survey);
 
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index d6a924a05654..25d2d667ffba 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -748,7 +748,8 @@ static void rtl_op_sta_notify(struct ieee80211_hw *hw,
 static int rtl_op_ampdu_action(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif,
 			       enum ieee80211_ampdu_mlme_action action,
-			       struct ieee80211_sta *sta, u16 tid, u16 * ssn)
+			       struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			       u8 buf_size)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d024fc563e7b..5afe341b4010 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1731,6 +1731,10 @@ enum ieee80211_ampdu_mlme_action {
  * 	ieee80211_ampdu_mlme_action. Starting sequence number (@ssn)
  * 	is the first frame we expect to perform the action on. Notice
  * 	that TX/RX_STOP can pass NULL for this parameter.
+ *	The @buf_size parameter is only valid when the action is set to
+ *	%IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder
+ *	buffer size (number of subframes) for this session -- aggregates
+ *	containing more subframes than this may not be transmitted to the peer.
  *	Returns a negative error code on failure.
  *	The callback can sleep.
  *
@@ -1833,7 +1837,8 @@ struct ieee80211_ops {
 	int (*ampdu_action)(struct ieee80211_hw *hw,
 			    struct ieee80211_vif *vif,
 			    enum ieee80211_ampdu_mlme_action action,
-			    struct ieee80211_sta *sta, u16 tid, u16 *ssn);
+			    struct ieee80211_sta *sta, u16 tid, u16 *ssn,
+			    u8 buf_size);
 	int (*get_survey)(struct ieee80211_hw *hw, int idx,
 		struct survey_info *survey);
 	void (*rfkill_poll)(struct ieee80211_hw *hw);
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 002db5e86eb6..1f51f4162426 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -76,7 +76,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
 #endif /* CONFIG_MAC80211_HT_DEBUG */
 
 	if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP,
-			     &sta->sta, tid, NULL))
+			     &sta->sta, tid, NULL, 0))
 		printk(KERN_DEBUG "HW problem - can not stop rx "
 				"aggregation for tid %d\n", tid);
 
@@ -297,7 +297,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local,
 	}
 
 	ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START,
-			       &sta->sta, tid, &start_seq_num);
+			       &sta->sta, tid, &start_seq_num, 0);
 #ifdef CONFIG_MAC80211_HT_DEBUG
 	printk(KERN_DEBUG "Rx A-MPDU request on tid %d result %d\n", tid, ret);
 #endif /* CONFIG_MAC80211_HT_DEBUG */
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 9cc472c6a6a5..42f7c9007331 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -190,7 +190,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 
 	ret = drv_ampdu_action(local, sta->sdata,
 			       IEEE80211_AMPDU_TX_STOP,
-			       &sta->sta, tid, NULL);
+			       &sta->sta, tid, NULL, 0);
 
 	/* HW shall not deny going back to legacy */
 	if (WARN_ON(ret)) {
@@ -311,7 +311,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	start_seq_num = sta->tid_seq[tid] >> 4;
 
 	ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START,
-			       &sta->sta, tid, &start_seq_num);
+			       &sta->sta, tid, &start_seq_num, 0);
 	if (ret) {
 #ifdef CONFIG_MAC80211_HT_DEBUG
 		printk(KERN_DEBUG "BA request denied - HW unavailable for"
@@ -487,7 +487,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
 
 	drv_ampdu_action(local, sta->sdata,
 			 IEEE80211_AMPDU_TX_OPERATIONAL,
-			 &sta->sta, tid, NULL);
+			 &sta->sta, tid, NULL,
+			 sta->ampdu_mlme.tid_tx[tid]->buf_size);
 
 	/*
 	 * synchronize with TX path, while splicing the TX path
@@ -742,9 +743,11 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
 {
 	struct tid_ampdu_tx *tid_tx;
 	u16 capab, tid;
+	u8 buf_size;
 
 	capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab);
 	tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
+	buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6;
 
 	mutex_lock(&sta->ampdu_mlme.mtx);
 
@@ -767,12 +770,23 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
 
 	if (le16_to_cpu(mgmt->u.action.u.addba_resp.status)
 			== WLAN_STATUS_SUCCESS) {
+		/*
+		 * IEEE 802.11-2007 7.3.1.14:
+		 * In an ADDBA Response frame, when the Status Code field
+		 * is set to 0, the Buffer Size subfield is set to a value
+		 * of at least 1.
+		 */
+		if (!buf_size)
+			goto out;
+
 		if (test_and_set_bit(HT_AGG_STATE_RESPONSE_RECEIVED,
 				     &tid_tx->state)) {
 			/* ignore duplicate response */
 			goto out;
 		}
 
+		tid_tx->buf_size = buf_size;
+
 		if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state))
 			ieee80211_agg_tx_operational(local, sta, tid);
 
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 98d589960a49..78af32d4bc58 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -382,17 +382,17 @@ static inline int drv_ampdu_action(struct ieee80211_local *local,
 				   struct ieee80211_sub_if_data *sdata,
 				   enum ieee80211_ampdu_mlme_action action,
 				   struct ieee80211_sta *sta, u16 tid,
-				   u16 *ssn)
+				   u16 *ssn, u8 buf_size)
 {
 	int ret = -EOPNOTSUPP;
 
 	might_sleep();
 
-	trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn);
+	trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size);
 
 	if (local->ops->ampdu_action)
 		ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action,
-					       sta, tid, ssn);
+					       sta, tid, ssn, buf_size);
 
 	trace_drv_return_int(local, ret);
 
diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h
index 49c84218b2f4..fbabbc2f181a 100644
--- a/net/mac80211/driver-trace.h
+++ b/net/mac80211/driver-trace.h
@@ -784,9 +784,9 @@ TRACE_EVENT(drv_ampdu_action,
 		 struct ieee80211_sub_if_data *sdata,
 		 enum ieee80211_ampdu_mlme_action action,
 		 struct ieee80211_sta *sta, u16 tid,
-		 u16 *ssn),
+		 u16 *ssn, u8 buf_size),
 
-	TP_ARGS(local, sdata, action, sta, tid, ssn),
+	TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
@@ -794,6 +794,7 @@ TRACE_EVENT(drv_ampdu_action,
 		__field(u32, action)
 		__field(u16, tid)
 		__field(u16, ssn)
+		__field(u8, buf_size)
 		VIF_ENTRY
 	),
 
@@ -804,11 +805,13 @@ TRACE_EVENT(drv_ampdu_action,
 		__entry->action = action;
 		__entry->tid = tid;
 		__entry->ssn = ssn ? *ssn : 0;
+		__entry->buf_size = buf_size;
 	),
 
 	TP_printk(
-		LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d",
-		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, __entry->tid
+		LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action,
+		__entry->tid, __entry->buf_size
 	)
 );
 
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index bbdd2a86a94b..ca0b69060ef7 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -82,6 +82,7 @@ enum ieee80211_sta_info_flags {
  * @state: session state (see above)
  * @stop_initiator: initiator of a session stop
  * @tx_stop: TX DelBA frame when stopping
+ * @buf_size: reorder buffer size at receiver
  *
  * This structure's lifetime is managed by RCU, assignments to
  * the array holding it must hold the aggregation mutex.
@@ -101,6 +102,7 @@ struct tid_ampdu_tx {
 	u8 dialog_token;
 	u8 stop_initiator;
 	bool tx_stop;
+	u8 buf_size;
 };
 
 /**
-- 
cgit v1.2.3


From 5dd36bc933e8be84f8369ac64505a2938f9ce036 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 18 Jan 2011 13:52:23 +0100
Subject: mac80211: allow advertising correct maximum aggregate size

Currently, mac80211 always advertises that it may send
up to 64 subframes in an aggregate. This is fine, since
it's the max, but might as well be set to zero instead
since it doesn't have any information.

However, drivers might have that information, so allow
them to set a variable giving it, which will then be
used. The default of zero will be fine since to the
peer that means we don't know and it will just use its
own limit for the buffer size.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/mac80211.h | 5 +++++
 net/mac80211/agg-tx.c  | 3 ++-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 5afe341b4010..d6b0045788ce 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1154,6 +1154,10 @@ enum ieee80211_hw_flags {
  *	This is only relevant if the device has restrictions on the
  *	number of subframes, if it relies on mac80211 to do reordering
  *	it shouldn't be set.
+ *
+ * @max_tx_aggregation_subframes: maximum number of subframes in an
+ *	aggregate an HT driver will transmit, used by the peer as a
+ *	hint to size its reorder buffer.
  */
 struct ieee80211_hw {
 	struct ieee80211_conf conf;
@@ -1173,6 +1177,7 @@ struct ieee80211_hw {
 	u8 max_report_rates;
 	u8 max_rate_tries;
 	u8 max_rx_aggregation_subframes;
+	u8 max_tx_aggregation_subframes;
 };
 
 /**
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 42f7c9007331..63d852cb4ca2 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -342,7 +342,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	/* send AddBA request */
 	ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
 				     tid_tx->dialog_token, start_seq_num,
-				     0x40, tid_tx->timeout);
+				     local->hw.max_tx_aggregation_subframes,
+				     tid_tx->timeout);
 }
 
 int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
-- 
cgit v1.2.3


From cc4fc022571376412986e27e08b0765e9cb2aafb Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Tue, 18 Jan 2011 17:32:40 +0100
Subject: netfilter: xtables: connlimit revision 1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds destination address-based selection. The old "inverse"
member is overloaded (memory-wise) with a new "flags" variable,
similar to how J.Park did it with xt_string rev 1. Since revision 0
userspace only sets flag 0x1, no great changes are made to explicitly
test for different revisions.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 Documentation/feature-removal-schedule.txt |  7 +++++
 include/linux/netfilter/xt_connlimit.h     | 12 ++++++++
 net/netfilter/xt_connlimit.c               | 44 ++++++++++++++++++++----------
 3 files changed, 49 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 22f10818c2b3..45cc8044dad6 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -576,3 +576,10 @@ Why:	The functions have been superceded by cancel_delayed_work_sync()
 Who:	Tejun Heo <tj@kernel.org>
 
 ----------------------------
+
+What:	xt_connlimit rev 0
+When:	2012
+Who:	Jan Engelhardt <jengelh@medozas.de>
+Files:	net/netfilter/xt_connlimit.c
+
+----------------------------
diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h
index 7e3284bcbd2b..8884efc605c7 100644
--- a/include/linux/netfilter/xt_connlimit.h
+++ b/include/linux/netfilter/xt_connlimit.h
@@ -3,6 +3,11 @@
 
 struct xt_connlimit_data;
 
+enum {
+	XT_CONNLIMIT_INVERT = 1 << 0,
+	XT_CONNLIMIT_DADDR  = 1 << 1,
+};
+
 struct xt_connlimit_info {
 	union {
 		union nf_inet_addr mask;
@@ -14,6 +19,13 @@ struct xt_connlimit_info {
 #endif
 	};
 	unsigned int limit, inverse;
+	union {
+		/* revision 0 */
+		unsigned int inverse;
+
+		/* revision 1 */
+		__u32 flags;
+	};
 
 	/* Used internally by the kernel */
 	struct xt_connlimit_data *data __attribute__((aligned(8)));
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 452bc16af56c..7fd3fd51f274 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -193,10 +193,12 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 	if (par->family == NFPROTO_IPV6) {
 		const struct ipv6hdr *iph = ipv6_hdr(skb);
-		memcpy(&addr.ip6, &iph->saddr, sizeof(iph->saddr));
+		memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ?
+		       &iph->daddr : &iph->saddr, sizeof(addr.ip6));
 	} else {
 		const struct iphdr *iph = ip_hdr(skb);
-		addr.ip = iph->saddr;
+		addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ?
+			  iph->daddr : iph->saddr;
 	}
 
 	spin_lock_bh(&info->data->lock);
@@ -208,7 +210,8 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		/* kmalloc failed, drop it entirely */
 		goto hotdrop;
 
-	return (connections > info->limit) ^ info->inverse;
+	return (connections > info->limit) ^
+	       !!(info->flags & XT_CONNLIMIT_INVERT);
 
  hotdrop:
 	par->hotdrop = true;
@@ -266,25 +269,38 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
 	kfree(info->data);
 }
 
-static struct xt_match connlimit_mt_reg __read_mostly = {
-	.name       = "connlimit",
-	.revision   = 0,
-	.family     = NFPROTO_UNSPEC,
-	.checkentry = connlimit_mt_check,
-	.match      = connlimit_mt,
-	.matchsize  = sizeof(struct xt_connlimit_info),
-	.destroy    = connlimit_mt_destroy,
-	.me         = THIS_MODULE,
+static struct xt_match connlimit_mt_reg[] __read_mostly = {
+	{
+		.name       = "connlimit",
+		.revision   = 0,
+		.family     = NFPROTO_UNSPEC,
+		.checkentry = connlimit_mt_check,
+		.match      = connlimit_mt,
+		.matchsize  = sizeof(struct xt_connlimit_info),
+		.destroy    = connlimit_mt_destroy,
+		.me         = THIS_MODULE,
+	},
+	{
+		.name       = "connlimit",
+		.revision   = 1,
+		.family     = NFPROTO_UNSPEC,
+		.checkentry = connlimit_mt_check,
+		.match      = connlimit_mt,
+		.matchsize  = sizeof(struct xt_connlimit_info),
+		.destroy    = connlimit_mt_destroy,
+		.me         = THIS_MODULE,
+	},
 };
 
 static int __init connlimit_mt_init(void)
 {
-	return xt_register_match(&connlimit_mt_reg);
+	return xt_register_matches(connlimit_mt_reg,
+	       ARRAY_SIZE(connlimit_mt_reg));
 }
 
 static void __exit connlimit_mt_exit(void)
 {
-	xt_unregister_match(&connlimit_mt_reg);
+	xt_unregister_matches(connlimit_mt_reg, ARRAY_SIZE(connlimit_mt_reg));
 }
 
 module_init(connlimit_mt_init);
-- 
cgit v1.2.3


From cbda10fa97d72c7a1923be4426171aa90e8c6dab Mon Sep 17 00:00:00 2001
From: Vlad Dogaru <ddvlad@rosedu.org>
Date: Thu, 13 Jan 2011 23:38:30 +0000
Subject: net_device: add support for network device groups

Net devices can now be grouped, enabling simpler manipulation from
userspace. This patch adds a group field to the net_device structure, as
well as rtnetlink support to query and modify it.

Signed-off-by: Vlad Dogaru <ddvlad@rosedu.org>
Acked-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_link.h   |  1 +
 include/linux/netdevice.h |  7 +++++++
 net/core/dev.c            | 12 ++++++++++++
 net/core/rtnetlink.c      |  6 ++++++
 4 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 6485d2a89bec..f4a2e6b1b864 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -135,6 +135,7 @@ enum {
 	IFLA_VF_PORTS,
 	IFLA_PORT_SELF,
 	IFLA_AF_SPEC,
+	IFLA_GROUP,		/* Group the device belongs to */
 	__IFLA_MAX
 };
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d971346b0340..68a4627b74f5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -75,6 +75,9 @@ struct wireless_dev;
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+/* Initial net device group. All devices belong to group 0 by default. */
+#define INIT_NETDEV_GROUP	0
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -1153,6 +1156,9 @@ struct net_device {
 
 	/* phy device may attach itself for hardware timestamping */
 	struct phy_device *phydev;
+
+	/* group the device belongs to */
+	int group;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -1844,6 +1850,7 @@ extern int		dev_set_alias(struct net_device *, const char *, size_t);
 extern int		dev_change_net_namespace(struct net_device *,
 						 struct net *, const char *);
 extern int		dev_set_mtu(struct net_device *, int);
+extern void		dev_set_group(struct net_device *, int);
 extern int		dev_set_mac_address(struct net_device *,
 					    struct sockaddr *);
 extern int		dev_hard_start_xmit(struct sk_buff *skb,
diff --git a/net/core/dev.c b/net/core/dev.c
index 7741507429f4..2b85d4ae981f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4571,6 +4571,17 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 }
 EXPORT_SYMBOL(dev_set_mtu);
 
+/**
+ *	dev_set_group - Change group this device belongs to
+ *	@dev: device
+ *	@new_group: group this device should belong to
+ */
+void dev_set_group(struct net_device *dev, int new_group)
+{
+	dev->group = new_group;
+}
+EXPORT_SYMBOL(dev_set_group);
+
 /**
  *	dev_set_mac_address - Change Media Access Control Address
  *	@dev: device
@@ -5678,6 +5689,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->priv_flags = IFF_XMIT_DST_RELEASE;
 	setup(dev);
 	strcpy(dev->name, name);
+	dev->group = INIT_NETDEV_GROUP;
 	return dev;
 
 free_pcpu:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a5f7535aab5b..09062b07bf7f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -868,6 +868,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		   netif_running(dev) ? dev->operstate : IF_OPER_DOWN);
 	NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode);
 	NLA_PUT_U32(skb, IFLA_MTU, dev->mtu);
+	NLA_PUT_U32(skb, IFLA_GROUP, dev->group);
 
 	if (dev->ifindex != dev->iflink)
 		NLA_PUT_U32(skb, IFLA_LINK, dev->iflink);
@@ -1265,6 +1266,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		modified = 1;
 	}
 
+	if (tb[IFLA_GROUP]) {
+		dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
+		modified = 1;
+	}
+
 	/*
 	 * Interface selected by interface index but interface
 	 * name provided implies that a name change has been
-- 
cgit v1.2.3


From 4f57c087de9b46182545676d2c594120a20f2e58 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.r.fastabend@intel.com>
Date: Mon, 17 Jan 2011 08:06:04 +0000
Subject: net: implement mechanism for HW based QOS

This patch provides a mechanism for lower layer devices to
steer traffic using skb->priority to tx queues. This allows
for hardware based QOS schemes to use the default qdisc without
incurring the penalties related to global state and the qdisc
lock. While reliably receiving skbs on the correct tx ring
to avoid head of line blocking resulting from shuffling in
the LLD. Finally, all the goodness from txq caching and xps/rps
can still be leveraged.

Many drivers and hardware exist with the ability to implement
QOS schemes in the hardware but currently these drivers tend
to rely on firmware to reroute specific traffic, a driver
specific select_queue or the queue_mapping action in the
qdisc.

By using select_queue for this drivers need to be updated for
each and every traffic type and we lose the goodness of much
of the upstream work. Firmware solutions are inherently
inflexible. And finally if admins are expected to build a
qdisc and filter rules to steer traffic this requires knowledge
of how the hardware is currently configured. The number of tx
queues and the queue offsets may change depending on resources.
Also this approach incurs all the overhead of a qdisc with filters.

With the mechanism in this patch users can set skb priority using
expected methods ie setsockopt() or the stack can set the priority
directly. Then the skb will be steered to the correct tx queues
aligned with hardware QOS traffic classes. In the normal case with
single traffic class and all queues in this class everything
works as is until the LLD enables multiple tcs.

To steer the skb we mask out the lower 4 bits of the priority
and allow the hardware to configure upto 15 distinct classes
of traffic. This is expected to be sufficient for most applications
at any rate it is more then the 8021Q spec designates and is
equal to the number of prio bands currently implemented in
the default qdisc.

This in conjunction with a userspace application such as
lldpad can be used to implement 8021Q transmission selection
algorithms one of these algorithms being the extended transmission
selection algorithm currently being used for DCB.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 68 +++++++++++++++++++++++++++++++++++++++++++++++
 net/core/dev.c            | 55 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 122 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 68a4627b74f5..371fa8839d51 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -646,6 +646,14 @@ struct xps_dev_maps {
     (nr_cpu_ids * sizeof(struct xps_map *)))
 #endif /* CONFIG_XPS */
 
+#define TC_MAX_QUEUE	16
+#define TC_BITMASK	15
+/* HW offloaded queuing disciplines txq count and offset maps */
+struct netdev_tc_txq {
+	u16 count;
+	u16 offset;
+};
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -756,6 +764,11 @@ struct xps_dev_maps {
  * int (*ndo_set_vf_port)(struct net_device *dev, int vf,
  *			  struct nlattr *port[]);
  * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
+ * int (*ndo_setup_tc)(struct net_device *dev, u8 tc)
+ * 	Called to setup 'tc' number of traffic classes in the net device. This
+ * 	is always called from the stack with the rtnl lock held and netif tx
+ * 	queues stopped. This allows the netdevice to perform queue management
+ * 	safely.
  */
 #define HAVE_NET_DEVICE_OPS
 struct net_device_ops {
@@ -814,6 +827,7 @@ struct net_device_ops {
 						   struct nlattr *port[]);
 	int			(*ndo_get_vf_port)(struct net_device *dev,
 						   int vf, struct sk_buff *skb);
+	int			(*ndo_setup_tc)(struct net_device *dev, u8 tc);
 #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
 	int			(*ndo_fcoe_enable)(struct net_device *dev);
 	int			(*ndo_fcoe_disable)(struct net_device *dev);
@@ -1146,6 +1160,9 @@ struct net_device {
 	/* Data Center Bridging netlink ops */
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
+	u8 num_tc;
+	struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
+	u8 prio_tc_map[TC_BITMASK + 1];
 
 #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
 	/* max exchange id for FCoE LRO by ddp */
@@ -1164,6 +1181,57 @@ struct net_device {
 
 #define	NETDEV_ALIGN		32
 
+static inline
+int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
+{
+	return dev->prio_tc_map[prio & TC_BITMASK];
+}
+
+static inline
+int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
+{
+	if (tc >= dev->num_tc)
+		return -EINVAL;
+
+	dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK;
+	return 0;
+}
+
+static inline
+void netdev_reset_tc(struct net_device *dev)
+{
+	dev->num_tc = 0;
+	memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
+	memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
+}
+
+static inline
+int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
+{
+	if (tc >= dev->num_tc)
+		return -EINVAL;
+
+	dev->tc_to_txq[tc].count = count;
+	dev->tc_to_txq[tc].offset = offset;
+	return 0;
+}
+
+static inline
+int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
+{
+	if (num_tc > TC_MAX_QUEUE)
+		return -EINVAL;
+
+	dev->num_tc = num_tc;
+	return 0;
+}
+
+static inline
+int netdev_get_num_tc(struct net_device *dev)
+{
+	return dev->num_tc;
+}
+
 static inline
 struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
 					 unsigned int index)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b85d4ae981f..8b1d886ed23b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1593,6 +1593,48 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 	rcu_read_unlock();
 }
 
+/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
+ * @dev: Network device
+ * @txq: number of queues available
+ *
+ * If real_num_tx_queues is changed the tc mappings may no longer be
+ * valid. To resolve this verify the tc mapping remains valid and if
+ * not NULL the mapping. With no priorities mapping to this
+ * offset/count pair it will no longer be used. In the worst case TC0
+ * is invalid nothing can be done so disable priority mappings. If is
+ * expected that drivers will fix this mapping if they can before
+ * calling netif_set_real_num_tx_queues.
+ */
+void netif_setup_tc(struct net_device *dev, unsigned int txq)
+{
+	int i;
+	struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
+
+	/* If TC0 is invalidated disable TC mapping */
+	if (tc->offset + tc->count > txq) {
+		pr_warning("Number of in use tx queues changed "
+			   "invalidating tc mappings. Priority "
+			   "traffic classification disabled!\n");
+		dev->num_tc = 0;
+		return;
+	}
+
+	/* Invalidated prio to tc mappings set to TC0 */
+	for (i = 1; i < TC_BITMASK + 1; i++) {
+		int q = netdev_get_prio_tc_map(dev, i);
+
+		tc = &dev->tc_to_txq[q];
+		if (tc->offset + tc->count > txq) {
+			pr_warning("Number of in use tx queues "
+				   "changed. Priority %i to tc "
+				   "mapping %i is no longer valid "
+				   "setting map to 0\n",
+				   i, q);
+			netdev_set_prio_tc_map(dev, i, 0);
+		}
+	}
+}
+
 /*
  * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
  * greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
@@ -1612,6 +1654,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 		if (rc)
 			return rc;
 
+		if (dev->num_tc)
+			netif_setup_tc(dev, txq);
+
 		if (txq < dev->real_num_tx_queues)
 			qdisc_reset_all_tx_gt(dev, txq);
 	}
@@ -2161,6 +2206,8 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 		  unsigned int num_tx_queues)
 {
 	u32 hash;
+	u16 qoffset = 0;
+	u16 qcount = num_tx_queues;
 
 	if (skb_rx_queue_recorded(skb)) {
 		hash = skb_get_rx_queue(skb);
@@ -2169,13 +2216,19 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 		return hash;
 	}
 
+	if (dev->num_tc) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+		qoffset = dev->tc_to_txq[tc].offset;
+		qcount = dev->tc_to_txq[tc].count;
+	}
+
 	if (skb->sk && skb->sk->sk_hash)
 		hash = skb->sk->sk_hash;
 	else
 		hash = (__force u16) skb->protocol ^ skb->rxhash;
 	hash = jhash_1word(hash, hashrnd);
 
-	return (u16) (((u64) hash * num_tx_queues) >> 32);
+	return (u16) (((u64) hash * qcount) >> 32) + qoffset;
 }
 EXPORT_SYMBOL(__skb_tx_hash);
 
-- 
cgit v1.2.3


From b8970f0bfc78103cb74c66055de7379b15097840 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.r.fastabend@intel.com>
Date: Mon, 17 Jan 2011 08:06:09 +0000
Subject: net_sched: implement a root container qdisc sch_mqprio

This implements a mqprio queueing discipline that by default creates
a pfifo_fast qdisc per tx queue and provides the needed configuration
interface.

Using the mqprio qdisc the number of tcs currently in use along
with the range of queues alloted to each class can be configured. By
default skbs are mapped to traffic classes using the skb priority.
This mapping is configurable.

Configurable parameters,

struct tc_mqprio_qopt {
	__u8    num_tc;
	__u8    prio_tc_map[TC_BITMASK + 1];
	__u8    hw;
	__u16   count[TC_MAX_QUEUE];
	__u16   offset[TC_MAX_QUEUE];
};

Here the count/offset pairing give the queue alignment and the
prio_tc_map gives the mapping from skb->priority to tc.

The hw bit determines if the hardware should configure the count
and offset values. If the hardware bit is set then the operation
will fail if the hardware does not implement the ndo_setup_tc
operation. This is to avoid undetermined states where the hardware
may or may not control the queue mapping. Also minimal bounds
checking is done on the count/offset to verify a queue does not
exceed num_tx_queues and that queue ranges do not overlap. Otherwise
it is left to user policy or hardware configuration to create
useful mappings.

It is expected that hardware QOS schemes can be implemented by
creating appropriate mappings of queues in ndo_tc_setup().

One expected use case is drivers will use the ndo_setup_tc to map
queue ranges onto 802.1Q traffic classes. This provides a generic
mechanism to map network traffic onto these traffic classes and
removes the need for lower layer drivers to know specifics about
traffic types.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/pkt_sched.h |  12 ++
 net/sched/Kconfig         |  12 ++
 net/sched/Makefile        |   1 +
 net/sched/sch_generic.c   |   4 +
 net/sched/sch_mqprio.c    | 417 ++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 446 insertions(+)
 create mode 100644 net/sched/sch_mqprio.c

(limited to 'include')

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index 2cfa4bc8dea6..776cd93d5f7b 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -481,4 +481,16 @@ struct tc_drr_stats {
 	__u32	deficit;
 };
 
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+struct tc_mqprio_qopt {
+	__u8	num_tc;
+	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
+	__u8	hw;
+	__u16	count[TC_QOPT_MAX_QUEUE];
+	__u16	offset[TC_QOPT_MAX_QUEUE];
+};
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index f04d4a484d53..73431d4aa6ef 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -205,6 +205,18 @@ config NET_SCH_DRR
 
 	  If unsure, say N.
 
+config NET_SCH_MQPRIO
+	tristate "Multi-queue priority scheduler (MQPRIO)"
+	help
+	  Say Y here if you want to use the Multi-queue Priority scheduler.
+	  This scheduler allows QOS to be offloaded on NICs that have support
+	  for offloading QOS schedulers.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called sch_mqprio.
+
+	  If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 960f5dba6304..26ce681a2c60 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_NET_SCH_MULTIQ)	+= sch_multiq.o
 obj-$(CONFIG_NET_SCH_ATM)	+= sch_atm.o
 obj-$(CONFIG_NET_SCH_NETEM)	+= sch_netem.o
 obj-$(CONFIG_NET_SCH_DRR)	+= sch_drr.o
+obj-$(CONFIG_NET_SCH_MQPRIO)	+= sch_mqprio.o
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
 obj-$(CONFIG_NET_CLS_FW)	+= cls_fw.o
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 34dc598440a2..723b27849a50 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -540,6 +540,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.dump		=	pfifo_fast_dump,
 	.owner		=	THIS_MODULE,
 };
+EXPORT_SYMBOL(pfifo_fast_ops);
 
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  struct Qdisc_ops *ops)
@@ -674,6 +675,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 
 	return oqdisc;
 }
+EXPORT_SYMBOL(dev_graft_qdisc);
 
 static void attach_one_default_qdisc(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
@@ -761,6 +763,7 @@ void dev_activate(struct net_device *dev)
 		dev_watchdog_up(dev);
 	}
 }
+EXPORT_SYMBOL(dev_activate);
 
 static void dev_deactivate_queue(struct net_device *dev,
 				 struct netdev_queue *dev_queue,
@@ -840,6 +843,7 @@ void dev_deactivate(struct net_device *dev)
 	list_add(&dev->unreg_list, &single);
 	dev_deactivate_many(&single);
 }
+EXPORT_SYMBOL(dev_deactivate);
 
 static void dev_init_scheduler_queue(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
new file mode 100644
index 000000000000..8620c65f480a
--- /dev/null
+++ b/net/sched/sch_mqprio.c
@@ -0,0 +1,417 @@
+/*
+ * net/sched/sch_mqprio.c
+ *
+ * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/sch_generic.h>
+
+struct mqprio_sched {
+	struct Qdisc		**qdiscs;
+	int hw_owned;
+};
+
+static void mqprio_destroy(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	unsigned int ntx;
+
+	if (!priv->qdiscs)
+		return;
+
+	for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
+		qdisc_destroy(priv->qdiscs[ntx]);
+
+	if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc)
+		dev->netdev_ops->ndo_setup_tc(dev, 0);
+	else
+		netdev_set_num_tc(dev, 0);
+
+	kfree(priv->qdiscs);
+}
+
+static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
+{
+	int i, j;
+
+	/* Verify num_tc is not out of max range */
+	if (qopt->num_tc > TC_MAX_QUEUE)
+		return -EINVAL;
+
+	/* Verify priority mapping uses valid tcs */
+	for (i = 0; i < TC_BITMASK + 1; i++) {
+		if (qopt->prio_tc_map[i] >= qopt->num_tc)
+			return -EINVAL;
+	}
+
+	/* net_device does not support requested operation */
+	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
+		return -EINVAL;
+
+	/* if hw owned qcount and qoffset are taken from LLD so
+	 * no reason to verify them here
+	 */
+	if (qopt->hw)
+		return 0;
+
+	for (i = 0; i < qopt->num_tc; i++) {
+		unsigned int last = qopt->offset[i] + qopt->count[i];
+
+		/* Verify the queue count is in tx range being equal to the
+		 * real_num_tx_queues indicates the last queue is in use.
+		 */
+		if (qopt->offset[i] >= dev->real_num_tx_queues ||
+		    !qopt->count[i] ||
+		    last > dev->real_num_tx_queues)
+			return -EINVAL;
+
+		/* Verify that the offset and counts do not overlap */
+		for (j = i + 1; j < qopt->num_tc; j++) {
+			if (last > qopt->offset[j])
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct netdev_queue *dev_queue;
+	struct Qdisc *qdisc;
+	int i, err = -EOPNOTSUPP;
+	struct tc_mqprio_qopt *qopt = NULL;
+
+	BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
+	BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK);
+
+	if (sch->parent != TC_H_ROOT)
+		return -EOPNOTSUPP;
+
+	if (!netif_is_multiqueue(dev))
+		return -EOPNOTSUPP;
+
+	if (nla_len(opt) < sizeof(*qopt))
+		return -EINVAL;
+
+	qopt = nla_data(opt);
+	if (mqprio_parse_opt(dev, qopt))
+		return -EINVAL;
+
+	/* pre-allocate qdisc, attachment can't fail */
+	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
+			       GFP_KERNEL);
+	if (priv->qdiscs == NULL) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		dev_queue = netdev_get_tx_queue(dev, i);
+		qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops,
+					  TC_H_MAKE(TC_H_MAJ(sch->handle),
+						    TC_H_MIN(i + 1)));
+		if (qdisc == NULL) {
+			err = -ENOMEM;
+			goto err;
+		}
+		qdisc->flags |= TCQ_F_CAN_BYPASS;
+		priv->qdiscs[i] = qdisc;
+	}
+
+	/* If the mqprio options indicate that hardware should own
+	 * the queue mapping then run ndo_setup_tc otherwise use the
+	 * supplied and verified mapping
+	 */
+	if (qopt->hw) {
+		priv->hw_owned = 1;
+		err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc);
+		if (err)
+			goto err;
+	} else {
+		netdev_set_num_tc(dev, qopt->num_tc);
+		for (i = 0; i < qopt->num_tc; i++)
+			netdev_set_tc_queue(dev, i,
+					    qopt->count[i], qopt->offset[i]);
+	}
+
+	/* Always use supplied priority mappings */
+	for (i = 0; i < TC_BITMASK + 1; i++)
+		netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]);
+
+	sch->flags |= TCQ_F_MQROOT;
+	return 0;
+
+err:
+	mqprio_destroy(sch);
+	return err;
+}
+
+static void mqprio_attach(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct Qdisc *qdisc;
+	unsigned int ntx;
+
+	/* Attach underlying qdisc */
+	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
+		qdisc = priv->qdiscs[ntx];
+		qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+		if (qdisc)
+			qdisc_destroy(qdisc);
+	}
+	kfree(priv->qdiscs);
+	priv->qdiscs = NULL;
+}
+
+static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
+					     unsigned long cl)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx = cl - 1 - netdev_get_num_tc(dev);
+
+	if (ntx >= dev->num_tx_queues)
+		return NULL;
+	return netdev_get_tx_queue(dev, ntx);
+}
+
+static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
+		    struct Qdisc **old)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+	if (!dev_queue)
+		return -EINVAL;
+
+	if (dev->flags & IFF_UP)
+		dev_deactivate(dev);
+
+	*old = dev_graft_qdisc(dev_queue, new);
+
+	if (dev->flags & IFF_UP)
+		dev_activate(dev);
+
+	return 0;
+}
+
+static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tc_mqprio_qopt opt;
+	struct Qdisc *qdisc;
+	unsigned int i;
+
+	sch->q.qlen = 0;
+	memset(&sch->bstats, 0, sizeof(sch->bstats));
+	memset(&sch->qstats, 0, sizeof(sch->qstats));
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+		spin_lock_bh(qdisc_lock(qdisc));
+		sch->q.qlen		+= qdisc->q.qlen;
+		sch->bstats.bytes	+= qdisc->bstats.bytes;
+		sch->bstats.packets	+= qdisc->bstats.packets;
+		sch->qstats.qlen	+= qdisc->qstats.qlen;
+		sch->qstats.backlog	+= qdisc->qstats.backlog;
+		sch->qstats.drops	+= qdisc->qstats.drops;
+		sch->qstats.requeues	+= qdisc->qstats.requeues;
+		sch->qstats.overlimits	+= qdisc->qstats.overlimits;
+		spin_unlock_bh(qdisc_lock(qdisc));
+	}
+
+	opt.num_tc = netdev_get_num_tc(dev);
+	memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
+	opt.hw = priv->hw_owned;
+
+	for (i = 0; i < netdev_get_num_tc(dev); i++) {
+		opt.count[i] = dev->tc_to_txq[i].count;
+		opt.offset[i] = dev->tc_to_txq[i].offset;
+	}
+
+	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+
+	return skb->len;
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl)
+{
+	struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+	if (!dev_queue)
+		return NULL;
+
+	return dev_queue->qdisc_sleeping;
+}
+
+static unsigned long mqprio_get(struct Qdisc *sch, u32 classid)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx = TC_H_MIN(classid);
+
+	if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev))
+		return 0;
+	return ntx;
+}
+
+static void mqprio_put(struct Qdisc *sch, unsigned long cl)
+{
+}
+
+static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl,
+			 struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct net_device *dev = qdisc_dev(sch);
+
+	if (cl <= netdev_get_num_tc(dev)) {
+		tcm->tcm_parent = TC_H_ROOT;
+		tcm->tcm_info = 0;
+	} else {
+		int i;
+		struct netdev_queue *dev_queue;
+
+		dev_queue = mqprio_queue_get(sch, cl);
+		tcm->tcm_parent = 0;
+		for (i = 0; i < netdev_get_num_tc(dev); i++) {
+			struct netdev_tc_txq tc = dev->tc_to_txq[i];
+			int q_idx = cl - netdev_get_num_tc(dev);
+
+			if (q_idx > tc.offset &&
+			    q_idx <= tc.offset + tc.count) {
+				tcm->tcm_parent =
+					TC_H_MAKE(TC_H_MAJ(sch->handle),
+						  TC_H_MIN(i + 1));
+				break;
+			}
+		}
+		tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
+	}
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+			       struct gnet_dump *d)
+{
+	struct net_device *dev = qdisc_dev(sch);
+
+	if (cl <= netdev_get_num_tc(dev)) {
+		int i;
+		struct Qdisc *qdisc;
+		struct gnet_stats_queue qstats = {0};
+		struct gnet_stats_basic_packed bstats = {0};
+		struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1];
+
+		/* Drop lock here it will be reclaimed before touching
+		 * statistics this is required because the d->lock we
+		 * hold here is the look on dev_queue->qdisc_sleeping
+		 * also acquired below.
+		 */
+		spin_unlock_bh(d->lock);
+
+		for (i = tc.offset; i < tc.offset + tc.count; i++) {
+			qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+			spin_lock_bh(qdisc_lock(qdisc));
+			bstats.bytes      += qdisc->bstats.bytes;
+			bstats.packets    += qdisc->bstats.packets;
+			qstats.qlen       += qdisc->qstats.qlen;
+			qstats.backlog    += qdisc->qstats.backlog;
+			qstats.drops      += qdisc->qstats.drops;
+			qstats.requeues   += qdisc->qstats.requeues;
+			qstats.overlimits += qdisc->qstats.overlimits;
+			spin_unlock_bh(qdisc_lock(qdisc));
+		}
+		/* Reclaim root sleeping lock before completing stats */
+		spin_lock_bh(d->lock);
+		if (gnet_stats_copy_basic(d, &bstats) < 0 ||
+		    gnet_stats_copy_queue(d, &qstats) < 0)
+			return -1;
+	} else {
+		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
+
+		sch = dev_queue->qdisc_sleeping;
+		sch->qstats.qlen = sch->q.qlen;
+		if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+		    gnet_stats_copy_queue(d, &sch->qstats) < 0)
+			return -1;
+	}
+	return 0;
+}
+
+static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned long ntx;
+
+	if (arg->stop)
+		return;
+
+	/* Walk hierarchy with a virtual class per tc */
+	arg->count = arg->skip;
+	for (ntx = arg->skip;
+	     ntx < dev->num_tx_queues + netdev_get_num_tc(dev);
+	     ntx++) {
+		if (arg->fn(sch, ntx + 1, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+		arg->count++;
+	}
+}
+
+static const struct Qdisc_class_ops mqprio_class_ops = {
+	.graft		= mqprio_graft,
+	.leaf		= mqprio_leaf,
+	.get		= mqprio_get,
+	.put		= mqprio_put,
+	.walk		= mqprio_walk,
+	.dump		= mqprio_dump_class,
+	.dump_stats	= mqprio_dump_class_stats,
+};
+
+struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
+	.cl_ops		= &mqprio_class_ops,
+	.id		= "mqprio",
+	.priv_size	= sizeof(struct mqprio_sched),
+	.init		= mqprio_init,
+	.destroy	= mqprio_destroy,
+	.attach		= mqprio_attach,
+	.dump		= mqprio_dump,
+	.owner		= THIS_MODULE,
+};
+
+static int __init mqprio_module_init(void)
+{
+	return register_qdisc(&mqprio_qdisc_ops);
+}
+
+static void __exit mqprio_module_exit(void)
+{
+	unregister_qdisc(&mqprio_qdisc_ops);
+}
+
+module_init(mqprio_module_init);
+module_exit(mqprio_module_exit);
+
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 5d8449286456659cdd0998e62d80df2d9e77e9e3 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Thu, 20 Jan 2011 08:48:15 +0100
Subject: netfilter: xtables: remove extraneous header that slipped in

Commit 0b8ad87 (netfilter: xtables: add missing header files to export
list) erroneously added this.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/Kbuild | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index fc4e0aa805a2..89c0d1e20d72 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -56,7 +56,6 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
-header-y += xt_secmark.h
 header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
-- 
cgit v1.2.3


From ba12b130a65840005770135a69199cb9adaf8c8f Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Thu, 20 Jan 2011 14:01:12 +0100
Subject: netfilter: xtables: remove duplicate member

Accidentally missed removing the old out-of-union "inverse" member,
which caused the struct size to change which then gives size mismatch
warnings when using an old iptables.

It is interesting to see that gcc did not warn about this before.
(Filed http://gcc.gnu.org/bugzilla/show_bug.cgi?id=47376 )

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/xt_connlimit.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h
index 8884efc605c7..ab1d3b57fff7 100644
--- a/include/linux/netfilter/xt_connlimit.h
+++ b/include/linux/netfilter/xt_connlimit.h
@@ -18,7 +18,7 @@ struct xt_connlimit_info {
 		};
 #endif
 	};
-	unsigned int limit, inverse;
+	unsigned int limit;
 	union {
 		/* revision 0 */
 		unsigned int inverse;
-- 
cgit v1.2.3


From 06988b06935da7a210887e9d3f50f46f2faa4953 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Thu, 20 Jan 2011 17:50:17 +0100
Subject: netfilter: xtables: add missing header inclusions for headers_check

Resolve these warnings on `make headers_check`:

usr/include/linux/netfilter/xt_CT.h:7: found __[us]{8,16,32,64} type
without #include <linux/types.h>
...

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/xt_CT.h                | 2 ++
 include/linux/netfilter/xt_TCPOPTSTRIP.h       | 2 ++
 include/linux/netfilter/xt_TPROXY.h            | 2 ++
 include/linux/netfilter/xt_cluster.h           | 2 ++
 include/linux/netfilter/xt_connlimit.h         | 2 ++
 include/linux/netfilter/xt_quota.h             | 2 ++
 include/linux/netfilter/xt_socket.h            | 2 ++
 include/linux/netfilter/xt_time.h              | 2 ++
 include/linux/netfilter/xt_u32.h               | 2 ++
 include/linux/netfilter_bridge/ebt_802_3.h     | 2 ++
 include/linux/netfilter_bridge/ebt_among.h     | 2 ++
 include/linux/netfilter_bridge/ebt_arp.h       | 2 ++
 include/linux/netfilter_bridge/ebt_ip.h        | 2 ++
 include/linux/netfilter_bridge/ebt_ip6.h       | 2 ++
 include/linux/netfilter_bridge/ebt_limit.h     | 2 ++
 include/linux/netfilter_bridge/ebt_log.h       | 2 ++
 include/linux/netfilter_bridge/ebt_mark_m.h    | 2 ++
 include/linux/netfilter_bridge/ebt_nflog.h     | 2 ++
 include/linux/netfilter_bridge/ebt_pkttype.h   | 2 ++
 include/linux/netfilter_bridge/ebt_stp.h       | 2 ++
 include/linux/netfilter_bridge/ebt_ulog.h      | 2 ++
 include/linux/netfilter_bridge/ebt_vlan.h      | 2 ++
 include/linux/netfilter_ipv4/ipt_CLUSTERIP.h   | 2 ++
 include/linux/netfilter_ipv4/ipt_ECN.h         | 2 ++
 include/linux/netfilter_ipv4/ipt_SAME.h        | 2 ++
 include/linux/netfilter_ipv4/ipt_TTL.h         | 2 ++
 include/linux/netfilter_ipv4/ipt_addrtype.h    | 2 ++
 include/linux/netfilter_ipv4/ipt_ah.h          | 2 ++
 include/linux/netfilter_ipv4/ipt_ecn.h         | 2 ++
 include/linux/netfilter_ipv4/ipt_ttl.h         | 2 ++
 include/linux/netfilter_ipv6/ip6t_HL.h         | 2 ++
 include/linux/netfilter_ipv6/ip6t_REJECT.h     | 2 ++
 include/linux/netfilter_ipv6/ip6t_ah.h         | 2 ++
 include/linux/netfilter_ipv6/ip6t_frag.h       | 2 ++
 include/linux/netfilter_ipv6/ip6t_hl.h         | 2 ++
 include/linux/netfilter_ipv6/ip6t_ipv6header.h | 2 ++
 include/linux/netfilter_ipv6/ip6t_mh.h         | 2 ++
 include/linux/netfilter_ipv6/ip6t_opts.h       | 2 ++
 include/linux/netfilter_ipv6/ip6t_rt.h         | 1 +
 39 files changed, 77 insertions(+)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h
index fbf4c5658554..b56e76811c04 100644
--- a/include/linux/netfilter/xt_CT.h
+++ b/include/linux/netfilter/xt_CT.h
@@ -1,6 +1,8 @@
 #ifndef _XT_CT_H
 #define _XT_CT_H
 
+#include <linux/types.h>
+
 #define XT_CT_NOTRACK	0x1
 
 struct xt_ct_target_info {
diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h
index 342ef14b1761..7157318499c2 100644
--- a/include/linux/netfilter/xt_TCPOPTSTRIP.h
+++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h
@@ -1,6 +1,8 @@
 #ifndef _XT_TCPOPTSTRIP_H
 #define _XT_TCPOPTSTRIP_H
 
+#include <linux/types.h>
+
 #define tcpoptstrip_set_bit(bmap, idx) \
 	(bmap[(idx) >> 5] |= 1U << (idx & 31))
 #define tcpoptstrip_test_bit(bmap, idx) \
diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h
index 8097e0b4c15e..902043c2073f 100644
--- a/include/linux/netfilter/xt_TPROXY.h
+++ b/include/linux/netfilter/xt_TPROXY.h
@@ -1,6 +1,8 @@
 #ifndef _XT_TPROXY_H
 #define _XT_TPROXY_H
 
+#include <linux/types.h>
+
 /* TPROXY target is capable of marking the packet to perform
  * redirection. We can get rid of that whenever we get support for
  * mutliple targets in the same rule. */
diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h
index 66cfa3c782ac..9b883c8fbf54 100644
--- a/include/linux/netfilter/xt_cluster.h
+++ b/include/linux/netfilter/xt_cluster.h
@@ -1,6 +1,8 @@
 #ifndef _XT_CLUSTER_MATCH_H
 #define _XT_CLUSTER_MATCH_H
 
+#include <linux/types.h>
+
 enum xt_cluster_flags {
 	XT_CLUSTER_F_INV	= (1 << 0)
 };
diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h
index ab1d3b57fff7..0ca66e97acbc 100644
--- a/include/linux/netfilter/xt_connlimit.h
+++ b/include/linux/netfilter/xt_connlimit.h
@@ -1,6 +1,8 @@
 #ifndef _XT_CONNLIMIT_H
 #define _XT_CONNLIMIT_H
 
+#include <linux/types.h>
+
 struct xt_connlimit_data;
 
 enum {
diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h
index 8bda65f0bc92..ca6e03e47a17 100644
--- a/include/linux/netfilter/xt_quota.h
+++ b/include/linux/netfilter/xt_quota.h
@@ -1,6 +1,8 @@
 #ifndef _XT_QUOTA_H
 #define _XT_QUOTA_H
 
+#include <linux/types.h>
+
 enum xt_quota_flags {
 	XT_QUOTA_INVERT		= 0x1,
 };
diff --git a/include/linux/netfilter/xt_socket.h b/include/linux/netfilter/xt_socket.h
index 6f475b8ff34b..26d7217bd4f1 100644
--- a/include/linux/netfilter/xt_socket.h
+++ b/include/linux/netfilter/xt_socket.h
@@ -1,6 +1,8 @@
 #ifndef _XT_SOCKET_H
 #define _XT_SOCKET_H
 
+#include <linux/types.h>
+
 enum {
 	XT_SOCKET_TRANSPARENT = 1 << 0,
 };
diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h
index b8bd4568efdb..7c37fac576c4 100644
--- a/include/linux/netfilter/xt_time.h
+++ b/include/linux/netfilter/xt_time.h
@@ -1,6 +1,8 @@
 #ifndef _XT_TIME_H
 #define _XT_TIME_H 1
 
+#include <linux/types.h>
+
 struct xt_time_info {
 	__u32 date_start;
 	__u32 date_stop;
diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h
index e8c3d8722bae..04d1bfea03c2 100644
--- a/include/linux/netfilter/xt_u32.h
+++ b/include/linux/netfilter/xt_u32.h
@@ -1,6 +1,8 @@
 #ifndef _XT_U32_H
 #define _XT_U32_H 1
 
+#include <linux/types.h>
+
 enum xt_u32_ops {
 	XT_U32_AND,
 	XT_U32_LEFTSH,
diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h
index c427764f4444..be5be1577a56 100644
--- a/include/linux/netfilter_bridge/ebt_802_3.h
+++ b/include/linux/netfilter_bridge/ebt_802_3.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_802_3_H
 #define __LINUX_BRIDGE_EBT_802_3_H
 
+#include <linux/types.h>
+
 #define EBT_802_3_SAP 0x01
 #define EBT_802_3_TYPE 0x02
 
diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h
index 686c9619dbc0..bd4e3ad0b706 100644
--- a/include/linux/netfilter_bridge/ebt_among.h
+++ b/include/linux/netfilter_bridge/ebt_among.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_AMONG_H
 #define __LINUX_BRIDGE_EBT_AMONG_H
 
+#include <linux/types.h>
+
 #define EBT_AMONG_DST 0x01
 #define EBT_AMONG_SRC 0x02
 
diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h
index e62b5af95869..522f3e427f49 100644
--- a/include/linux/netfilter_bridge/ebt_arp.h
+++ b/include/linux/netfilter_bridge/ebt_arp.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_ARP_H
 #define __LINUX_BRIDGE_EBT_ARP_H
 
+#include <linux/types.h>
+
 #define EBT_ARP_OPCODE 0x01
 #define EBT_ARP_HTYPE 0x02
 #define EBT_ARP_PTYPE 0x04
diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h
index d99de58da2c7..c4bbc41b0ea4 100644
--- a/include/linux/netfilter_bridge/ebt_ip.h
+++ b/include/linux/netfilter_bridge/ebt_ip.h
@@ -15,6 +15,8 @@
 #ifndef __LINUX_BRIDGE_EBT_IP_H
 #define __LINUX_BRIDGE_EBT_IP_H
 
+#include <linux/types.h>
+
 #define EBT_IP_SOURCE 0x01
 #define EBT_IP_DEST 0x02
 #define EBT_IP_TOS 0x04
diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h
index 998e9d5a6b60..42b889682721 100644
--- a/include/linux/netfilter_bridge/ebt_ip6.h
+++ b/include/linux/netfilter_bridge/ebt_ip6.h
@@ -12,6 +12,8 @@
 #ifndef __LINUX_BRIDGE_EBT_IP6_H
 #define __LINUX_BRIDGE_EBT_IP6_H
 
+#include <linux/types.h>
+
 #define EBT_IP6_SOURCE 0x01
 #define EBT_IP6_DEST 0x02
 #define EBT_IP6_TCLASS 0x04
diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h
index 721d51ffa513..66d80b30ba0e 100644
--- a/include/linux/netfilter_bridge/ebt_limit.h
+++ b/include/linux/netfilter_bridge/ebt_limit.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_LIMIT_H
 #define __LINUX_BRIDGE_EBT_LIMIT_H
 
+#include <linux/types.h>
+
 #define EBT_LIMIT_MATCH "limit"
 
 /* timings are in milliseconds. */
diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h
index 564beb4946ea..7e7f1d1fe494 100644
--- a/include/linux/netfilter_bridge/ebt_log.h
+++ b/include/linux/netfilter_bridge/ebt_log.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_LOG_H
 #define __LINUX_BRIDGE_EBT_LOG_H
 
+#include <linux/types.h>
+
 #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */
 #define EBT_LOG_ARP 0x02
 #define EBT_LOG_NFLOG 0x04
diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h
index 97b96c4b8db4..410f9e5a71d4 100644
--- a/include/linux/netfilter_bridge/ebt_mark_m.h
+++ b/include/linux/netfilter_bridge/ebt_mark_m.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_MARK_M_H
 #define __LINUX_BRIDGE_EBT_MARK_M_H
 
+#include <linux/types.h>
+
 #define EBT_MARK_AND 0x01
 #define EBT_MARK_OR 0x02
 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR)
diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h
index 477315bc3537..df829fce9125 100644
--- a/include/linux/netfilter_bridge/ebt_nflog.h
+++ b/include/linux/netfilter_bridge/ebt_nflog.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_NFLOG_H
 #define __LINUX_BRIDGE_EBT_NFLOG_H
 
+#include <linux/types.h>
+
 #define EBT_NFLOG_MASK 0x0
 
 #define EBT_NFLOG_PREFIX_SIZE 64
diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h
index 7c0fb0fdcf14..c241badcd036 100644
--- a/include/linux/netfilter_bridge/ebt_pkttype.h
+++ b/include/linux/netfilter_bridge/ebt_pkttype.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_PKTTYPE_H
 #define __LINUX_BRIDGE_EBT_PKTTYPE_H
 
+#include <linux/types.h>
+
 struct ebt_pkttype_info {
 	__u8 pkt_type;
 	__u8 invert;
diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h
index 13a0bd49a92a..1025b9f5fb7d 100644
--- a/include/linux/netfilter_bridge/ebt_stp.h
+++ b/include/linux/netfilter_bridge/ebt_stp.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_STP_H
 #define __LINUX_BRIDGE_EBT_STP_H
 
+#include <linux/types.h>
+
 #define EBT_STP_TYPE		0x0001
 
 #define EBT_STP_FLAGS		0x0002
diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h
index de35a51a7e46..89a6becb5269 100644
--- a/include/linux/netfilter_bridge/ebt_ulog.h
+++ b/include/linux/netfilter_bridge/ebt_ulog.h
@@ -1,6 +1,8 @@
 #ifndef _EBT_ULOG_H
 #define _EBT_ULOG_H
 
+#include <linux/types.h>
+
 #define EBT_ULOG_DEFAULT_NLGROUP 0
 #define EBT_ULOG_DEFAULT_QTHRESHOLD 1
 #define EBT_ULOG_MAXNLGROUPS 32 /* hardcoded netlink max */
diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h
index 48dffc1dad36..967d1d5cf98d 100644
--- a/include/linux/netfilter_bridge/ebt_vlan.h
+++ b/include/linux/netfilter_bridge/ebt_vlan.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_BRIDGE_EBT_VLAN_H
 #define __LINUX_BRIDGE_EBT_VLAN_H
 
+#include <linux/types.h>
+
 #define EBT_VLAN_ID	0x01
 #define EBT_VLAN_PRIO	0x02
 #define EBT_VLAN_ENCAP	0x04
diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
index 3114f06939ef..c6a204c97047 100644
--- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
+++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
@@ -1,6 +1,8 @@
 #ifndef _IPT_CLUSTERIP_H_target
 #define _IPT_CLUSTERIP_H_target
 
+#include <linux/types.h>
+
 enum clusterip_hashmode {
     CLUSTERIP_HASHMODE_SIP = 0,
     CLUSTERIP_HASHMODE_SIP_SPT,
diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h
index c6e3e01b75e0..bb88d5315a4d 100644
--- a/include/linux/netfilter_ipv4/ipt_ECN.h
+++ b/include/linux/netfilter_ipv4/ipt_ECN.h
@@ -8,6 +8,8 @@
 */
 #ifndef _IPT_ECN_TARGET_H
 #define _IPT_ECN_TARGET_H
+
+#include <linux/types.h>
 #include <linux/netfilter/xt_DSCP.h>
 
 #define IPT_ECN_IP_MASK	(~XT_DSCP_MASK)
diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h
index fa0ebeca5d95..5bca78267afd 100644
--- a/include/linux/netfilter_ipv4/ipt_SAME.h
+++ b/include/linux/netfilter_ipv4/ipt_SAME.h
@@ -1,6 +1,8 @@
 #ifndef _IPT_SAME_H
 #define _IPT_SAME_H
 
+#include <linux/types.h>
+
 #define IPT_SAME_MAX_RANGE	10
 
 #define IPT_SAME_NODST		0x01
diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h
index f6250e422d5e..f6ac169d92f9 100644
--- a/include/linux/netfilter_ipv4/ipt_TTL.h
+++ b/include/linux/netfilter_ipv4/ipt_TTL.h
@@ -4,6 +4,8 @@
 #ifndef _IPT_TTL_H
 #define _IPT_TTL_H
 
+#include <linux/types.h>
+
 enum {
 	IPT_TTL_SET = 0,
 	IPT_TTL_INC,
diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h
index f29c3cfcc240..0da42237c8da 100644
--- a/include/linux/netfilter_ipv4/ipt_addrtype.h
+++ b/include/linux/netfilter_ipv4/ipt_addrtype.h
@@ -1,6 +1,8 @@
 #ifndef _IPT_ADDRTYPE_H
 #define _IPT_ADDRTYPE_H
 
+#include <linux/types.h>
+
 enum {
 	IPT_ADDRTYPE_INVERT_SOURCE	= 0x0001,
 	IPT_ADDRTYPE_INVERT_DEST	= 0x0002,
diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h
index 8fea283ee62a..4e02bb0119e3 100644
--- a/include/linux/netfilter_ipv4/ipt_ah.h
+++ b/include/linux/netfilter_ipv4/ipt_ah.h
@@ -1,6 +1,8 @@
 #ifndef _IPT_AH_H
 #define _IPT_AH_H
 
+#include <linux/types.h>
+
 struct ipt_ah {
 	__u32 spis[2];			/* Security Parameter Index */
 	__u8  invflags;			/* Inverse flags */
diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h
index 78b98aa8784d..eabf95fb7d3e 100644
--- a/include/linux/netfilter_ipv4/ipt_ecn.h
+++ b/include/linux/netfilter_ipv4/ipt_ecn.h
@@ -8,6 +8,8 @@
 */
 #ifndef _IPT_ECN_H
 #define _IPT_ECN_H
+
+#include <linux/types.h>
 #include <linux/netfilter/xt_dscp.h>
 
 #define IPT_ECN_IP_MASK	(~XT_DSCP_MASK)
diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h
index 93d9a06689a3..37bee4442486 100644
--- a/include/linux/netfilter_ipv4/ipt_ttl.h
+++ b/include/linux/netfilter_ipv4/ipt_ttl.h
@@ -4,6 +4,8 @@
 #ifndef _IPT_TTL_H
 #define _IPT_TTL_H
 
+#include <linux/types.h>
+
 enum {
 	IPT_TTL_EQ = 0,		/* equals */
 	IPT_TTL_NE,		/* not equals */
diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h
index 81cdaf0480e3..ebd8ead1bb63 100644
--- a/include/linux/netfilter_ipv6/ip6t_HL.h
+++ b/include/linux/netfilter_ipv6/ip6t_HL.h
@@ -5,6 +5,8 @@
 #ifndef _IP6T_HL_H
 #define _IP6T_HL_H
 
+#include <linux/types.h>
+
 enum {
 	IP6T_HL_SET = 0,
 	IP6T_HL_INC,
diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h
index b999aa4e5969..205ed62e4605 100644
--- a/include/linux/netfilter_ipv6/ip6t_REJECT.h
+++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h
@@ -1,6 +1,8 @@
 #ifndef _IP6T_REJECT_H
 #define _IP6T_REJECT_H
 
+#include <linux/types.h>
+
 enum ip6t_reject_with {
 	IP6T_ICMP6_NO_ROUTE,
 	IP6T_ICMP6_ADM_PROHIBITED,
diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h
index a602c165edd1..5da2b65cb3ad 100644
--- a/include/linux/netfilter_ipv6/ip6t_ah.h
+++ b/include/linux/netfilter_ipv6/ip6t_ah.h
@@ -1,6 +1,8 @@
 #ifndef _IP6T_AH_H
 #define _IP6T_AH_H
 
+#include <linux/types.h>
+
 struct ip6t_ah {
 	__u32 spis[2];			/* Security Parameter Index */
 	__u32 hdrlen;			/* Header Length */
diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h
index 538b31ef5e3d..b47f61b9e082 100644
--- a/include/linux/netfilter_ipv6/ip6t_frag.h
+++ b/include/linux/netfilter_ipv6/ip6t_frag.h
@@ -1,6 +1,8 @@
 #ifndef _IP6T_FRAG_H
 #define _IP6T_FRAG_H
 
+#include <linux/types.h>
+
 struct ip6t_frag {
 	__u32 ids[2];			/* Security Parameter Index */
 	__u32 hdrlen;			/* Header Length */
diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h
index c6fddcb971da..6e76dbc6c19a 100644
--- a/include/linux/netfilter_ipv6/ip6t_hl.h
+++ b/include/linux/netfilter_ipv6/ip6t_hl.h
@@ -5,6 +5,8 @@
 #ifndef _IP6T_HL_H
 #define _IP6T_HL_H
 
+#include <linux/types.h>
+
 enum {
 	IP6T_HL_EQ = 0,		/* equals */
 	IP6T_HL_NE,		/* not equals */
diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h
index 73d53bd3ff62..efae3a20c214 100644
--- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h
+++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h
@@ -8,6 +8,8 @@ on whether they contain certain headers */
 #ifndef __IPV6HEADER_H
 #define __IPV6HEADER_H
 
+#include <linux/types.h>
+
 struct ip6t_ipv6header_info {
 	__u8 matchflags;
 	__u8 invflags;
diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h
index 98c8cf685eea..a7729a5025cd 100644
--- a/include/linux/netfilter_ipv6/ip6t_mh.h
+++ b/include/linux/netfilter_ipv6/ip6t_mh.h
@@ -1,6 +1,8 @@
 #ifndef _IP6T_MH_H
 #define _IP6T_MH_H
 
+#include <linux/types.h>
+
 /* MH matching stuff */
 struct ip6t_mh {
 	__u8 types[2];	/* MH type range */
diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h
index 405d309cd741..17d419a811fd 100644
--- a/include/linux/netfilter_ipv6/ip6t_opts.h
+++ b/include/linux/netfilter_ipv6/ip6t_opts.h
@@ -1,6 +1,8 @@
 #ifndef _IP6T_OPTS_H
 #define _IP6T_OPTS_H
 
+#include <linux/types.h>
+
 #define IP6T_OPTS_OPTSNR 16
 
 struct ip6t_opts {
diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h
index e8dad20acd37..7605a5ff81cd 100644
--- a/include/linux/netfilter_ipv6/ip6t_rt.h
+++ b/include/linux/netfilter_ipv6/ip6t_rt.h
@@ -1,6 +1,7 @@
 #ifndef _IP6T_RT_H
 #define _IP6T_RT_H
 
+#include <linux/types.h>
 /*#include <linux/in6.h>*/
 
 #define IP6T_RT_HOPS 16
-- 
cgit v1.2.3


From 2f1e3176723d74ea2dd975e5be0ef6bb4fed2e2e Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 20 Jan 2011 20:46:52 +0100
Subject: netfilter: nf_conntrack: fix linker error with
 NF_CONNTRACK_TIMESTAMP=n

net/built-in.o: In function `nf_conntrack_init_net':
net/netfilter/nf_conntrack_core.c:1521:
	undefined reference to `nf_conntrack_tstamp_init'
net/netfilter/nf_conntrack_core.c:1531:
	undefined reference to `nf_conntrack_tstamp_fini'

Add dummy inline functions for the =n case to fix this.

Reported-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack_timestamp.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h
index f17dcb664e29..fc9c82b1f06b 100644
--- a/include/net/netfilter/nf_conntrack_timestamp.h
+++ b/include/net/netfilter/nf_conntrack_timestamp.h
@@ -47,7 +47,19 @@ static inline void nf_ct_set_tstamp(struct net *net, bool enable)
 	net->ct.sysctl_tstamp = enable;
 }
 
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
 extern int nf_conntrack_tstamp_init(struct net *net);
 extern void nf_conntrack_tstamp_fini(struct net *net);
+#else
+static inline int nf_conntrack_tstamp_init(struct net *net)
+{
+	return 0;
+}
+
+static inline void nf_conntrack_tstamp_fini(struct net *net)
+{
+	return;
+}
+#endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */
 
 #endif /* _NF_CONNTRACK_TSTAMP_H */
-- 
cgit v1.2.3


From a0a5b676401ee97a295dd9fcd7a374e883d48a8a Mon Sep 17 00:00:00 2001
From: Ky Srinivasan <ksrinivasan@novell.com>
Date: Thu, 16 Dec 2010 18:35:00 -0700
Subject: Connector: Add an index to support key/value pair (KVP) functionality

Added a connector index to support key value/pair (KVP) functionality
for Linux guests hosted on a HyperV platform.

Signed-off-by: K. Y. Srinivasan <ksrinivasan@novell.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/connector.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/connector.h b/include/linux/connector.h
index 7e8ca75d2dad..2e9759cdd275 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -42,8 +42,9 @@
 #define CN_VAL_DM_USERSPACE_LOG		0x1
 #define CN_IDX_DRBD			0x8
 #define CN_VAL_DRBD			0x1
+#define CN_KVP_IDX			0x9	/* HyperV KVP */
 
-#define CN_NETLINK_USERS		8
+#define CN_NETLINK_USERS		9
 
 /*
  * Maximum connector's message size.
-- 
cgit v1.2.3


From fd245a4adb5288eac37250875f237c40a20a1944 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 20 Jan 2011 05:27:16 +0000
Subject: net_sched: move TCQ_F_THROTTLED flag

In commit 371121057607e (net: QDISC_STATE_RUNNING dont need atomic bit
ops) I moved QDISC_STATE_RUNNING flag to __state container, located in
the cache line containing qdisc lock and often dirtied fields.

I now move TCQ_F_THROTTLED bit too, so that we let first cache line read
mostly, and shared by all cpus. This should speedup HTB/CBQ for example.

Not using test_bit()/__clear_bit()/__test_and_set_bit allows to use an
"unsigned int" for __state container, reducing by 8 bytes Qdisc size.

Introduce helpers to hide implementation details.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Patrick McHardy <kaber@trash.net>
CC: Jesper Dangaard Brouer <hawk@diku.dk>
CC: Jarek Poplawski <jarkao2@gmail.com>
CC: Jamal Hadi Salim <hadi@cyberus.ca>
CC: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 38 ++++++++++++++++++++++++++++----------
 net/sched/sch_api.c       |  6 +++---
 net/sched/sch_cbq.c       |  6 +++---
 net/sched/sch_hfsc.c      |  2 +-
 net/sched/sch_htb.c       |  4 ++--
 net/sched/sch_netem.c     |  2 +-
 net/sched/sch_tbf.c       |  2 +-
 7 files changed, 39 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e9eee99d8b1f..f6345f55041c 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -31,7 +31,8 @@ enum qdisc_state_t {
  * following bits are only changed while qdisc lock is held
  */
 enum qdisc___state_t {
-	__QDISC___STATE_RUNNING,
+	__QDISC___STATE_RUNNING = 1,
+	__QDISC___STATE_THROTTLED = 2,
 };
 
 struct qdisc_size_table {
@@ -46,10 +47,9 @@ struct Qdisc {
 	struct sk_buff *	(*dequeue)(struct Qdisc *dev);
 	unsigned		flags;
 #define TCQ_F_BUILTIN		1
-#define TCQ_F_THROTTLED		2
-#define TCQ_F_INGRESS		4
-#define TCQ_F_CAN_BYPASS	8
-#define TCQ_F_MQROOT		16
+#define TCQ_F_INGRESS		2
+#define TCQ_F_CAN_BYPASS	4
+#define TCQ_F_MQROOT		8
 #define TCQ_F_WARN_NONWC	(1 << 16)
 	int			padded;
 	struct Qdisc_ops	*ops;
@@ -78,25 +78,43 @@ struct Qdisc {
 	unsigned long		state;
 	struct sk_buff_head	q;
 	struct gnet_stats_basic_packed bstats;
-	unsigned long		__state;
+	unsigned int		__state;
 	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	spinlock_t		busylock;
 };
 
-static inline bool qdisc_is_running(struct Qdisc *qdisc)
+static inline bool qdisc_is_running(const struct Qdisc *qdisc)
 {
-	return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state);
+	return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false;
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
-	return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state);
+	if (qdisc_is_running(qdisc))
+		return false;
+	qdisc->__state |= __QDISC___STATE_RUNNING;
+	return true;
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
-	__clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state);
+	qdisc->__state &= ~__QDISC___STATE_RUNNING;
+}
+
+static inline bool qdisc_is_throttled(const struct Qdisc *qdisc)
+{
+	return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false;
+}
+
+static inline void qdisc_throttled(struct Qdisc *qdisc)
+{
+	qdisc->__state |= __QDISC___STATE_THROTTLED;
+}
+
+static inline void qdisc_unthrottled(struct Qdisc *qdisc)
+{
+	qdisc->__state &= ~__QDISC___STATE_THROTTLED;
 }
 
 struct Qdisc_class_ops {
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 36ac0ec81ce0..374fcbef80e8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -473,7 +473,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 	struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
 						 timer);
 
-	wd->qdisc->flags &= ~TCQ_F_THROTTLED;
+	qdisc_unthrottled(wd->qdisc);
 	__netif_schedule(qdisc_root(wd->qdisc));
 
 	return HRTIMER_NORESTART;
@@ -495,7 +495,7 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires)
 		     &qdisc_root_sleeping(wd->qdisc)->state))
 		return;
 
-	wd->qdisc->flags |= TCQ_F_THROTTLED;
+	qdisc_throttled(wd->qdisc);
 	time = ktime_set(0, 0);
 	time = ktime_add_ns(time, PSCHED_TICKS2NS(expires));
 	hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS);
@@ -505,7 +505,7 @@ EXPORT_SYMBOL(qdisc_watchdog_schedule);
 void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
 {
 	hrtimer_cancel(&wd->timer);
-	wd->qdisc->flags &= ~TCQ_F_THROTTLED;
+	qdisc_unthrottled(wd->qdisc);
 }
 EXPORT_SYMBOL(qdisc_watchdog_cancel);
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 4aaf44c95c52..25ed522b2891 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -351,7 +351,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
 {
 	int toplevel = q->toplevel;
 
-	if (toplevel > cl->level && !(cl->q->flags & TCQ_F_THROTTLED)) {
+	if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) {
 		psched_time_t now;
 		psched_tdiff_t incr;
 
@@ -625,7 +625,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer)
 		hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS);
 	}
 
-	sch->flags &= ~TCQ_F_THROTTLED;
+	qdisc_unthrottled(sch);
 	__netif_schedule(qdisc_root(sch));
 	return HRTIMER_NORESTART;
 }
@@ -974,7 +974,7 @@ cbq_dequeue(struct Qdisc *sch)
 		skb = cbq_dequeue_1(sch);
 		if (skb) {
 			sch->q.qlen--;
-			sch->flags &= ~TCQ_F_THROTTLED;
+			qdisc_unthrottled(sch);
 			return skb;
 		}
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index dea4009615f9..b632d9251913 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1664,7 +1664,7 @@ hfsc_dequeue(struct Qdisc *sch)
 		set_passive(cl);
 	}
 
-	sch->flags &= ~TCQ_F_THROTTLED;
+	qdisc_unthrottled(sch);
 	sch->q.qlen--;
 
 	return skb;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 3e86fd3a1b78..39db75cd8c17 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -865,7 +865,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 	/* try to dequeue direct packets as high prio (!) to minimize cpu work */
 	skb = __skb_dequeue(&q->direct_queue);
 	if (skb != NULL) {
-		sch->flags &= ~TCQ_F_THROTTLED;
+		qdisc_unthrottled(sch);
 		sch->q.qlen--;
 		return skb;
 	}
@@ -901,7 +901,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 			skb = htb_dequeue_tree(q, prio, level);
 			if (likely(skb != NULL)) {
 				sch->q.qlen--;
-				sch->flags &= ~TCQ_F_THROTTLED;
+				qdisc_unthrottled(sch);
 				goto fin;
 			}
 		}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index c2bbbe60d544..c26ef3614f7e 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -266,7 +266,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
 
-	if (sch->flags & TCQ_F_THROTTLED)
+	if (qdisc_is_throttled(sch))
 		return NULL;
 
 	skb = q->qdisc->ops->peek(q->qdisc);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 475edfb69c22..86c016696977 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -185,7 +185,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 			q->tokens = toks;
 			q->ptokens = ptoks;
 			sch->q.qlen--;
-			sch->flags &= ~TCQ_F_THROTTLED;
+			qdisc_unthrottled(sch);
 			return skb;
 		}
 
-- 
cgit v1.2.3


From a2da570d62fcb9e8816f6920e1ec02c706b289fa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 20 Jan 2011 03:48:19 +0000
Subject: net_sched: RCU conversion of stab

This patch converts stab qdisc management to RCU, so that we can perform
the qdisc_calculate_pkt_len() call before getting qdisc lock.

This shortens the lock's held time in __dev_xmit_skb().

This permits more qdiscs to get TCQ_F_CAN_BYPASS status, avoiding lot of
cache misses and so reducing latencies.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Patrick McHardy <kaber@trash.net>
CC: Jesper Dangaard Brouer <hawk@diku.dk>
CC: Jarek Poplawski <jarkao2@gmail.com>
CC: Jamal Hadi Salim <hadi@cyberus.ca>
CC: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 21 +++++++++++++++------
 net/core/dev.c            |  8 +++++---
 net/sched/sch_api.c       | 26 +++++++++++++++++---------
 net/sched/sch_generic.c   |  2 +-
 4 files changed, 38 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f6345f55041c..d531baa2506a 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -36,6 +36,7 @@ enum qdisc___state_t {
 };
 
 struct qdisc_size_table {
+	struct rcu_head		rcu;
 	struct list_head	list;
 	struct tc_sizespec	szopts;
 	int			refcnt;
@@ -53,7 +54,7 @@ struct Qdisc {
 #define TCQ_F_WARN_NONWC	(1 << 16)
 	int			padded;
 	struct Qdisc_ops	*ops;
-	struct qdisc_size_table	*stab;
+	struct qdisc_size_table	__rcu *stab;
 	struct list_head	list;
 	u32			handle;
 	u32			parent;
@@ -349,8 +350,8 @@ extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 				 struct Qdisc_ops *ops);
 extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
 				       struct Qdisc_ops *ops, u32 parentid);
-extern void qdisc_calculate_pkt_len(struct sk_buff *skb,
-				   struct qdisc_size_table *stab);
+extern void __qdisc_calculate_pkt_len(struct sk_buff *skb,
+				      const struct qdisc_size_table *stab);
 extern void tcf_destroy(struct tcf_proto *tp);
 extern void tcf_destroy_chain(struct tcf_proto **fl);
 
@@ -429,12 +430,20 @@ enum net_xmit_qdisc_t {
 #define net_xmit_drop_count(e)	(1)
 #endif
 
-static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static inline void qdisc_calculate_pkt_len(struct sk_buff *skb,
+					   const struct Qdisc *sch)
 {
 #ifdef CONFIG_NET_SCHED
-	if (sch->stab)
-		qdisc_calculate_pkt_len(skb, sch->stab);
+	struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab);
+
+	if (stab)
+		__qdisc_calculate_pkt_len(skb, stab);
 #endif
+}
+
+static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	qdisc_calculate_pkt_len(skb, sch);
 	return sch->enqueue(skb, sch);
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index a4ccd47f3196..2730352d2ccc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2325,15 +2325,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				 struct netdev_queue *txq)
 {
 	spinlock_t *root_lock = qdisc_lock(q);
-	bool contended = qdisc_is_running(q);
+	bool contended;
 	int rc;
 
+	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	qdisc_calculate_pkt_len(skb, q);
 	/*
 	 * Heuristic to force contended enqueues to serialize on a
 	 * separate lock before trying to get qdisc main lock.
 	 * This permits __QDISC_STATE_RUNNING owner to get the lock more often
 	 * and dequeue packets faster.
 	 */
+	contended = qdisc_is_running(q);
 	if (unlikely(contended))
 		spin_lock(&q->busylock);
 
@@ -2351,7 +2354,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
 			skb_dst_force(skb);
 
-		qdisc_skb_cb(skb)->pkt_len = skb->len;
 		qdisc_bstats_update(q, skb);
 
 		if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
@@ -2366,7 +2368,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		rc = NET_XMIT_SUCCESS;
 	} else {
 		skb_dst_force(skb);
-		rc = qdisc_enqueue_root(skb, q);
+		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 374fcbef80e8..150741579408 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -398,6 +398,11 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt)
 	return stab;
 }
 
+static void stab_kfree_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct qdisc_size_table, rcu));
+}
+
 void qdisc_put_stab(struct qdisc_size_table *tab)
 {
 	if (!tab)
@@ -407,7 +412,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab)
 
 	if (--tab->refcnt == 0) {
 		list_del(&tab->list);
-		kfree(tab);
+		call_rcu_bh(&tab->rcu, stab_kfree_rcu);
 	}
 
 	spin_unlock(&qdisc_stab_lock);
@@ -430,7 +435,7 @@ nla_put_failure:
 	return -1;
 }
 
-void qdisc_calculate_pkt_len(struct sk_buff *skb, struct qdisc_size_table *stab)
+void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab)
 {
 	int pkt_len, slot;
 
@@ -456,7 +461,7 @@ out:
 		pkt_len = 1;
 	qdisc_skb_cb(skb)->pkt_len = pkt_len;
 }
-EXPORT_SYMBOL(qdisc_calculate_pkt_len);
+EXPORT_SYMBOL(__qdisc_calculate_pkt_len);
 
 void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
 {
@@ -835,7 +840,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 				err = PTR_ERR(stab);
 				goto err_out4;
 			}
-			sch->stab = stab;
+			rcu_assign_pointer(sch->stab, stab);
 		}
 		if (tca[TCA_RATE]) {
 			spinlock_t *root_lock;
@@ -875,7 +880,7 @@ err_out4:
 	 * Any broken qdiscs that would require a ops->reset() here?
 	 * The qdisc was never in action so it shouldn't be necessary.
 	 */
-	qdisc_put_stab(sch->stab);
+	qdisc_put_stab(rtnl_dereference(sch->stab));
 	if (ops->destroy)
 		ops->destroy(sch);
 	goto err_out3;
@@ -883,7 +888,7 @@ err_out4:
 
 static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
 {
-	struct qdisc_size_table *stab = NULL;
+	struct qdisc_size_table *ostab, *stab = NULL;
 	int err = 0;
 
 	if (tca[TCA_OPTIONS]) {
@@ -900,8 +905,9 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
 			return PTR_ERR(stab);
 	}
 
-	qdisc_put_stab(sch->stab);
-	sch->stab = stab;
+	ostab = rtnl_dereference(sch->stab);
+	rcu_assign_pointer(sch->stab, stab);
+	qdisc_put_stab(ostab);
 
 	if (tca[TCA_RATE]) {
 		/* NB: ignores errors from replace_estimator
@@ -1180,6 +1186,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
 	struct gnet_dump d;
+	struct qdisc_size_table *stab;
 
 	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
 	tcm = NLMSG_DATA(nlh);
@@ -1195,7 +1202,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 		goto nla_put_failure;
 	q->qstats.qlen = q->q.qlen;
 
-	if (q->stab && qdisc_dump_stab(skb, q->stab) < 0)
+	stab = rtnl_dereference(q->stab);
+	if (stab && qdisc_dump_stab(skb, stab) < 0)
 		goto nla_put_failure;
 
 	if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2f1cb62130da..cc17e794c41e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -632,7 +632,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
 #ifdef CONFIG_NET_SCHED
 	qdisc_list_del(qdisc);
 
-	qdisc_put_stab(qdisc->stab);
+	qdisc_put_stab(rtnl_dereference(qdisc->stab));
 #endif
 	gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
 	if (ops->reset)
-- 
cgit v1.2.3


From d18046b3cd989c06d2ad8d615e57c3cf63c63b67 Mon Sep 17 00:00:00 2001
From: Shan Wei <shanwei@cn.fujitsu.com>
Date: Wed, 19 Jan 2011 23:12:54 +0000
Subject: dccp: clean up unused DCCP_STATE_MASK definition

Remove unused DCCP_STATE_MASK macro.

Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Acked-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dccp.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 010e2d87ed75..d638e85dc501 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -279,8 +279,6 @@ enum dccp_state {
 	DCCP_MAX_STATES
 };
 
-#define DCCP_STATE_MASK 0x1f
-
 enum {
 	DCCPF_OPEN	      = TCPF_ESTABLISHED,
 	DCCPF_REQUESTING      = TCPF_SYN_SENT,
-- 
cgit v1.2.3


From 686a2955531312dab77bb6f1e8602787d85e47d8 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 20 Jan 2011 22:47:32 -0800
Subject: net: Add safe reverse SKB queue walkers.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bf221d65d9ad..6e946da9d1d6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1801,6 +1801,15 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
 		     prefetch(skb->prev), (skb != (struct sk_buff *)(queue));	\
 		     skb = skb->prev)
 
+#define skb_queue_reverse_walk_safe(queue, skb, tmp)				\
+		for (skb = (queue)->prev, tmp = skb->prev;			\
+		     skb != (struct sk_buff *)(queue);				\
+		     skb = tmp, tmp = skb->prev)
+
+#define skb_queue_reverse_walk_from_safe(queue, skb, tmp)			\
+		for (tmp = skb->prev;						\
+		     skb != (struct sk_buff *)(queue);				\
+		     skb = tmp, tmp = skb->prev)
 
 static inline bool skb_has_frag_list(const struct sk_buff *skb)
 {
-- 
cgit v1.2.3


From c9e358dfc4a8cb2227172ef77908c2e0ee17bcb9 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Fri, 21 Jan 2011 09:24:48 -0700
Subject: driver-core: remove conditionals around devicetree pointers

Having conditional around the of_match_table and the of_node pointers
turns out to make driver code use ugly #ifdef blocks.  Drop the
conditionals and remove the #ifdef blocks from the affected drivers.

Also tidy up minor whitespace issues within the same hunks.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/i2c/busses/i2c-ocores.c | 14 +++-----------
 drivers/i2c/i2c-core.c          |  2 --
 drivers/mmc/host/mmc_spi.c      |  4 ----
 drivers/net/ethoc.c             |  8 +-------
 drivers/spi/pxa2xx_spi.c        |  2 --
 drivers/spi/pxa2xx_spi_pci.c    |  2 --
 drivers/spi/xilinx_spi.c        |  6 ------
 include/linux/device.h          |  7 ++-----
 include/linux/i2c.h             |  2 --
 include/linux/of.h              |  4 ++--
 10 files changed, 8 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c
index ef3bcb1ce864..c2ef5ce1f1ff 100644
--- a/drivers/i2c/busses/i2c-ocores.c
+++ b/drivers/i2c/busses/i2c-ocores.c
@@ -330,9 +330,7 @@ static int __devinit ocores_i2c_probe(struct platform_device *pdev)
 	i2c->adap = ocores_adapter;
 	i2c_set_adapdata(&i2c->adap, i2c);
 	i2c->adap.dev.parent = &pdev->dev;
-#ifdef CONFIG_OF
 	i2c->adap.dev.of_node = pdev->dev.of_node;
-#endif
 
 	/* add i2c adapter to i2c tree */
 	ret = i2c_add_adapter(&i2c->adap);
@@ -390,15 +388,11 @@ static int ocores_i2c_resume(struct platform_device *pdev)
 #define ocores_i2c_resume	NULL
 #endif
 
-#ifdef CONFIG_OF
 static struct of_device_id ocores_i2c_match[] = {
-        {
-                .compatible = "opencores,i2c-ocores",
-        },
-        {},
+	{ .compatible = "opencores,i2c-ocores", },
+	{},
 };
 MODULE_DEVICE_TABLE(of, ocores_i2c_match);
-#endif
 
 /* work with hotplug and coldplug */
 MODULE_ALIAS("platform:ocores-i2c");
@@ -411,9 +405,7 @@ static struct platform_driver ocores_i2c_driver = {
 	.driver  = {
 		.owner = THIS_MODULE,
 		.name = "ocores-i2c",
-#ifdef CONFIG_OF
-                .of_match_table = ocores_i2c_match,
-#endif
+		.of_match_table = ocores_i2c_match,
 	},
 };
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index f0bd5bcdf563..045ba6efea48 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -537,9 +537,7 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 	client->dev.parent = &client->adapter->dev;
 	client->dev.bus = &i2c_bus_type;
 	client->dev.type = &i2c_client_type;
-#ifdef CONFIG_OF
 	client->dev.of_node = info->of_node;
-#endif
 
 	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
 		     client->addr);
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index fd877f633dd2..2f7fc0c5146f 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1516,21 +1516,17 @@ static int __devexit mmc_spi_remove(struct spi_device *spi)
 	return 0;
 }
 
-#if defined(CONFIG_OF)
 static struct of_device_id mmc_spi_of_match_table[] __devinitdata = {
 	{ .compatible = "mmc-spi-slot", },
 	{},
 };
-#endif
 
 static struct spi_driver mmc_spi_driver = {
 	.driver = {
 		.name =		"mmc_spi",
 		.bus =		&spi_bus_type,
 		.owner =	THIS_MODULE,
-#if defined(CONFIG_OF)
 		.of_match_table = mmc_spi_of_match_table,
-#endif
 	},
 	.probe =	mmc_spi_probe,
 	.remove =	__devexit_p(mmc_spi_remove),
diff --git a/drivers/net/ethoc.c b/drivers/net/ethoc.c
index b79d7e1555d5..db0290f05bdf 100644
--- a/drivers/net/ethoc.c
+++ b/drivers/net/ethoc.c
@@ -1163,15 +1163,11 @@ static int ethoc_resume(struct platform_device *pdev)
 # define ethoc_resume  NULL
 #endif
 
-#ifdef CONFIG_OF
 static struct of_device_id ethoc_match[] = {
-	{
-		.compatible = "opencores,ethoc",
-	},
+	{ .compatible = "opencores,ethoc", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ethoc_match);
-#endif
 
 static struct platform_driver ethoc_driver = {
 	.probe   = ethoc_probe,
@@ -1181,9 +1177,7 @@ static struct platform_driver ethoc_driver = {
 	.driver  = {
 		.name = "ethoc",
 		.owner = THIS_MODULE,
-#ifdef CONFIG_OF
 		.of_match_table = ethoc_match,
-#endif
 	},
 };
 
diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c
index 95928833855b..a429b01d0285 100644
--- a/drivers/spi/pxa2xx_spi.c
+++ b/drivers/spi/pxa2xx_spi.c
@@ -1557,9 +1557,7 @@ static int __devinit pxa2xx_spi_probe(struct platform_device *pdev)
 	drv_data->ssp = ssp;
 
 	master->dev.parent = &pdev->dev;
-#ifdef CONFIG_OF
 	master->dev.of_node = pdev->dev.of_node;
-#endif
 	/* the spi->mode bits understood by this driver: */
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 
diff --git a/drivers/spi/pxa2xx_spi_pci.c b/drivers/spi/pxa2xx_spi_pci.c
index 351d8a375b57..b6589bb3a6c3 100644
--- a/drivers/spi/pxa2xx_spi_pci.c
+++ b/drivers/spi/pxa2xx_spi_pci.c
@@ -98,9 +98,7 @@ static int __devinit ce4100_spi_probe(struct pci_dev *dev,
 	pdev->dev.parent = &dev->dev;
 	pdev->dev.platform_data = &spi_info->spi_pdata;
 
-#ifdef CONFIG_OF
 	pdev->dev.of_node = dev->dev.of_node;
-#endif
 	pdev->dev.release = plat_dev_release;
 
 	spi_pdata->num_chipselect = dev->devfn;
diff --git a/drivers/spi/xilinx_spi.c b/drivers/spi/xilinx_spi.c
index 7adaef62a991..4d2c75df886c 100644
--- a/drivers/spi/xilinx_spi.c
+++ b/drivers/spi/xilinx_spi.c
@@ -351,14 +351,12 @@ static irqreturn_t xilinx_spi_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id xilinx_spi_of_match[] = {
 	{ .compatible = "xlnx,xps-spi-2.00.a", },
 	{ .compatible = "xlnx,xps-spi-2.00.b", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, xilinx_spi_of_match);
-#endif
 
 struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
 	u32 irq, s16 bus_num, int num_cs, int little_endian, int bits_per_word)
@@ -394,9 +392,7 @@ struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
 
 	master->bus_num = bus_num;
 	master->num_chipselect = num_cs;
-#ifdef CONFIG_OF
 	master->dev.of_node = dev->of_node;
-#endif
 
 	xspi->mem = *mem;
 	xspi->irq = irq;
@@ -539,9 +535,7 @@ static struct platform_driver xilinx_spi_driver = {
 	.driver = {
 		.name = XILINX_SPI_NAME,
 		.owner = THIS_MODULE,
-#ifdef CONFIG_OF
 		.of_match_table = xilinx_spi_of_match,
-#endif
 	},
 };
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 1bf5cf0b4513..ca5d25225aab 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -128,9 +128,7 @@ struct device_driver {
 
 	bool suppress_bind_attrs;	/* disables bind/unbind via sysfs */
 
-#if defined(CONFIG_OF)
 	const struct of_device_id	*of_match_table;
-#endif
 
 	int (*probe) (struct device *dev);
 	int (*remove) (struct device *dev);
@@ -441,9 +439,8 @@ struct device {
 					     override */
 	/* arch specific additions */
 	struct dev_archdata	archdata;
-#ifdef CONFIG_OF
-	struct device_node	*of_node;
-#endif
+
+	struct device_node	*of_node; /* associated device tree node */
 
 	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 903576df88dc..06a8d9c7de98 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -258,9 +258,7 @@ struct i2c_board_info {
 	unsigned short	addr;
 	void		*platform_data;
 	struct dev_archdata	*archdata;
-#ifdef CONFIG_OF
 	struct device_node *of_node;
-#endif
 	int		irq;
 };
 
diff --git a/include/linux/of.h b/include/linux/of.h
index cad7cf0ab278..d9dd664a6a9c 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -23,8 +23,6 @@
 
 #include <asm/byteorder.h>
 
-#ifdef CONFIG_OF
-
 typedef u32 phandle;
 typedef u32 ihandle;
 
@@ -65,6 +63,8 @@ struct device_node {
 #endif
 };
 
+#ifdef CONFIG_OF
+
 /* Pointer for first entry in chain of all nodes. */
 extern struct device_node *allnodes;
 extern struct device_node *of_chosen;
-- 
cgit v1.2.3


From 59eb21a6504731fc16db4cf9463065dd61093e08 Mon Sep 17 00:00:00 2001
From: Bruno Randolf <br1@einfach.org>
Date: Mon, 17 Jan 2011 13:37:28 +0900
Subject: cfg80211: Extend channel to frequency mapping for 802.11j

Extend channel to frequency mapping for 802.11j Japan 4.9GHz band, according to
IEEE802.11 section 17.3.8.3.2 and Annex J. Because there are now overlapping
channel numbers in the 2GHz and 5GHz band we can't map from channel to
frequency without knowing the band. This is no problem as in most contexts we
know the band. In places where we don't know the band (and WEXT compatibility)
we assume the 2GHz band for channels below 14.

This patch does not implement all channel to frequency mappings defined in
802.11, it's just an extension for 802.11j 20MHz channels. 5MHz and 10MHz
channels as well as 802.11y channels have been omitted.

The following drivers have been updated to reflect the API changes:
iwl-3945, iwl-agn, iwmc3200wifi, libertas, mwl8k, rt2x00, wl1251, wl12xx.
The drivers have been compile-tested only.

Signed-off-by: Bruno Randolf <br1@einfach.org>
Signed-off-by: Brian Prodoehl <bprodoehl@gmail.com>
Acked-by: Luciano Coelho <coelho@ti.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/iwlwifi/iwl-3945.c      |  5 ++--
 drivers/net/wireless/iwlwifi/iwl-agn-lib.c   |  5 ++--
 drivers/net/wireless/iwlwifi/iwl-core.c      |  3 ++-
 drivers/net/wireless/iwmc3200wifi/cfg80211.c |  3 ++-
 drivers/net/wireless/iwmc3200wifi/rx.c       |  7 ++++--
 drivers/net/wireless/libertas/cfg.c          |  6 +++--
 drivers/net/wireless/mwl8k.c                 |  6 +++--
 drivers/net/wireless/rt2x00/rt2x00dev.c      |  5 +++-
 drivers/net/wireless/wl1251/rx.c             |  3 ++-
 drivers/net/wireless/wl12xx/rx.c             |  2 +-
 include/net/cfg80211.h                       |  3 ++-
 net/mac80211/ibss.c                          |  3 ++-
 net/mac80211/mesh.c                          |  2 +-
 net/mac80211/mlme.c                          |  8 ++++---
 net/mac80211/scan.c                          |  3 ++-
 net/wireless/reg.c                           |  6 ++---
 net/wireless/util.c                          | 36 +++++++++++++++++-----------
 net/wireless/wext-compat.c                   |  5 +++-
 18 files changed, 71 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.c b/drivers/net/wireless/iwlwifi/iwl-3945.c
index a9b852be4509..1d9dcd7e3b82 100644
--- a/drivers/net/wireless/iwlwifi/iwl-3945.c
+++ b/drivers/net/wireless/iwlwifi/iwl-3945.c
@@ -594,10 +594,11 @@ static void iwl3945_rx_reply_rx(struct iwl_priv *priv,
 
 	rx_status.flag = 0;
 	rx_status.mactime = le64_to_cpu(rx_end->timestamp);
-	rx_status.freq =
-		ieee80211_channel_to_frequency(le16_to_cpu(rx_hdr->channel));
 	rx_status.band = (rx_hdr->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
 				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
+	rx_status.freq =
+		ieee80211_channel_to_frequency(le16_to_cpu(rx_hdr->channel),
+					       rx_status.band);
 
 	rx_status.rate_idx = iwl3945_hwrate_to_plcp_idx(rx_hdr->rate);
 	if (rx_status.band == IEEE80211_BAND_5GHZ)
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
index 29dcda0bde65..c7d03874b380 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
@@ -1162,10 +1162,11 @@ void iwlagn_rx_reply_rx(struct iwl_priv *priv,
 
 	/* rx_status carries information about the packet to mac80211 */
 	rx_status.mactime = le64_to_cpu(phy_res->timestamp);
-	rx_status.freq =
-		ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel));
 	rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
 				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
+	rx_status.freq =
+		ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel),
+					       rx_status.band);
 	rx_status.rate_idx =
 		iwlagn_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band);
 	rx_status.flag = 0;
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c
index efbde1f1a8bf..a8d4a936a2e7 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.c
+++ b/drivers/net/wireless/iwlwifi/iwl-core.c
@@ -227,7 +227,8 @@ int iwlcore_init_geos(struct iwl_priv *priv)
 		geo_ch = &sband->channels[sband->n_channels++];
 
 		geo_ch->center_freq =
-				ieee80211_channel_to_frequency(ch->channel);
+				ieee80211_channel_to_frequency(ch->channel,
+							       sband->band);
 		geo_ch->max_power = ch->max_power_avg;
 		geo_ch->max_antenna_gain = 0xff;
 		geo_ch->hw_value = ch->channel;
diff --git a/drivers/net/wireless/iwmc3200wifi/cfg80211.c b/drivers/net/wireless/iwmc3200wifi/cfg80211.c
index 5a4982271e96..ed57e4402800 100644
--- a/drivers/net/wireless/iwmc3200wifi/cfg80211.c
+++ b/drivers/net/wireless/iwmc3200wifi/cfg80211.c
@@ -287,7 +287,8 @@ int iwm_cfg80211_inform_bss(struct iwm_priv *iwm)
 			return -EINVAL;
 		}
 
-		freq = ieee80211_channel_to_frequency(umac_bss->channel);
+		freq = ieee80211_channel_to_frequency(umac_bss->channel,
+						      band->band);
 		channel = ieee80211_get_channel(wiphy, freq);
 		signal = umac_bss->rssi * 100;
 
diff --git a/drivers/net/wireless/iwmc3200wifi/rx.c b/drivers/net/wireless/iwmc3200wifi/rx.c
index a944893ae3ca..9a57cf6a488f 100644
--- a/drivers/net/wireless/iwmc3200wifi/rx.c
+++ b/drivers/net/wireless/iwmc3200wifi/rx.c
@@ -543,7 +543,10 @@ static int iwm_mlme_assoc_complete(struct iwm_priv *iwm, u8 *buf,
 	switch (le32_to_cpu(complete->status)) {
 	case UMAC_ASSOC_COMPLETE_SUCCESS:
 		chan = ieee80211_get_channel(wiphy,
-			ieee80211_channel_to_frequency(complete->channel));
+			ieee80211_channel_to_frequency(complete->channel,
+				complete->band == UMAC_BAND_2GHZ ?
+					IEEE80211_BAND_2GHZ :
+					IEEE80211_BAND_5GHZ));
 		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) {
 			/* Associated to a unallowed channel, disassociate. */
 			__iwm_invalidate_mlme_profile(iwm);
@@ -841,7 +844,7 @@ static int iwm_mlme_update_bss_table(struct iwm_priv *iwm, u8 *buf,
 		goto err;
 	}
 
-	freq = ieee80211_channel_to_frequency(umac_bss->channel);
+	freq = ieee80211_channel_to_frequency(umac_bss->channel, band->band);
 	channel = ieee80211_get_channel(wiphy, freq);
 	signal = umac_bss->rssi * 100;
 
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 698a1f7694ed..30ef0351bfc4 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -607,7 +607,8 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy,
 		/* No channel, no luck */
 		if (chan_no != -1) {
 			struct wiphy *wiphy = priv->wdev->wiphy;
-			int freq = ieee80211_channel_to_frequency(chan_no);
+			int freq = ieee80211_channel_to_frequency(chan_no,
+							IEEE80211_BAND_2GHZ);
 			struct ieee80211_channel *channel =
 				ieee80211_get_channel(wiphy, freq);
 
@@ -1597,7 +1598,8 @@ static int lbs_get_survey(struct wiphy *wiphy, struct net_device *dev,
 	lbs_deb_enter(LBS_DEB_CFG80211);
 
 	survey->channel = ieee80211_get_channel(wiphy,
-		ieee80211_channel_to_frequency(priv->channel));
+		ieee80211_channel_to_frequency(priv->channel,
+					       IEEE80211_BAND_2GHZ));
 
 	ret = lbs_get_rssi(priv, &signal, &noise);
 	if (ret == 0) {
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 106b427d0064..af4f2c64f242 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -906,7 +906,8 @@ mwl8k_rxd_8366_ap_process(void *_rxd, struct ieee80211_rx_status *status,
 	} else {
 		status->band = IEEE80211_BAND_2GHZ;
 	}
-	status->freq = ieee80211_channel_to_frequency(rxd->channel);
+	status->freq = ieee80211_channel_to_frequency(rxd->channel,
+						      status->band);
 
 	*qos = rxd->qos_control;
 
@@ -1013,7 +1014,8 @@ mwl8k_rxd_sta_process(void *_rxd, struct ieee80211_rx_status *status,
 	} else {
 		status->band = IEEE80211_BAND_2GHZ;
 	}
-	status->freq = ieee80211_channel_to_frequency(rxd->channel);
+	status->freq = ieee80211_channel_to_frequency(rxd->channel,
+						      status->band);
 
 	*qos = rxd->qos_control;
 	if ((rxd->rx_ctrl & MWL8K_STA_RX_CTRL_DECRYPT_ERROR) &&
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 9597a03242cc..31b7db05abd9 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -649,7 +649,10 @@ static void rt2x00lib_channel(struct ieee80211_channel *entry,
 			      const int channel, const int tx_power,
 			      const int value)
 {
-	entry->center_freq = ieee80211_channel_to_frequency(channel);
+	/* XXX: this assumption about the band is wrong for 802.11j */
+	entry->band = channel <= 14 ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
+	entry->center_freq = ieee80211_channel_to_frequency(channel,
+							    entry->band);
 	entry->hw_value = value;
 	entry->max_power = tx_power;
 	entry->max_antenna_gain = 0xff;
diff --git a/drivers/net/wireless/wl1251/rx.c b/drivers/net/wireless/wl1251/rx.c
index efa53607d5c9..86eef456d7b2 100644
--- a/drivers/net/wireless/wl1251/rx.c
+++ b/drivers/net/wireless/wl1251/rx.c
@@ -78,7 +78,8 @@ static void wl1251_rx_status(struct wl1251 *wl,
 	 */
 	wl->noise = desc->rssi - desc->snr / 2;
 
-	status->freq = ieee80211_channel_to_frequency(desc->channel);
+	status->freq = ieee80211_channel_to_frequency(desc->channel,
+						      status->band);
 
 	status->flag |= RX_FLAG_TSFT;
 
diff --git a/drivers/net/wireless/wl12xx/rx.c b/drivers/net/wireless/wl12xx/rx.c
index 682304c30b81..ec8d843d41cf 100644
--- a/drivers/net/wireless/wl12xx/rx.c
+++ b/drivers/net/wireless/wl12xx/rx.c
@@ -76,7 +76,7 @@ static void wl1271_rx_status(struct wl1271 *wl,
 	 */
 	wl->noise = desc->rssi - (desc->snr >> 1);
 
-	status->freq = ieee80211_channel_to_frequency(desc->channel);
+	status->freq = ieee80211_channel_to_frequency(desc->channel, desc_band);
 
 	if (desc->flags & WL1271_RX_DESC_ENCRYPT_MASK) {
 		status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1322695beb52..679a0494b5f2 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1790,8 +1790,9 @@ static inline void *wdev_priv(struct wireless_dev *wdev)
 /**
  * ieee80211_channel_to_frequency - convert channel number to frequency
  * @chan: channel number
+ * @band: band, necessary due to channel number overlap
  */
-extern int ieee80211_channel_to_frequency(int chan);
+extern int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band);
 
 /**
  * ieee80211_frequency_to_channel - convert frequency to channel number
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 53c7077ffd4f..775fb63471c4 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -270,7 +270,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	enum ieee80211_band band = rx_status->band;
 
 	if (elems->ds_params && elems->ds_params_len == 1)
-		freq = ieee80211_channel_to_frequency(elems->ds_params[0]);
+		freq = ieee80211_channel_to_frequency(elems->ds_params[0],
+						      band);
 	else
 		freq = rx_status->freq;
 
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 2563fd1ea998..2a57cc02c618 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -574,7 +574,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 			       &elems);
 
 	if (elems.ds_params && elems.ds_params_len == 1)
-		freq = ieee80211_channel_to_frequency(elems.ds_params[0]);
+		freq = ieee80211_channel_to_frequency(elems.ds_params[0], band);
 	else
 		freq = rx_status->freq;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index eecbb1fcd2ab..32210695b8b6 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -176,7 +176,7 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
 
 	/* check that channel matches the right operating channel */
 	if (local->hw.conf.channel->center_freq !=
-	    ieee80211_channel_to_frequency(hti->control_chan))
+	    ieee80211_channel_to_frequency(hti->control_chan, sband->band))
 		enable_ht = false;
 
 	if (enable_ht) {
@@ -429,7 +429,8 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		container_of((void *)bss, struct cfg80211_bss, priv);
 	struct ieee80211_channel *new_ch;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-	int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num);
+	int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num,
+						      cbss->channel->band);
 
 	ASSERT_MGD_MTX(ifmgd);
 
@@ -1519,7 +1520,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (elems->ds_params && elems->ds_params_len == 1)
-		freq = ieee80211_channel_to_frequency(elems->ds_params[0]);
+		freq = ieee80211_channel_to_frequency(elems->ds_params[0],
+						      rx_status->band);
 	else
 		freq = rx_status->freq;
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index fb274db77e3c..1ef73be76b25 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -196,7 +196,8 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
 	ieee802_11_parse_elems(elements, skb->len - baselen, &elems);
 
 	if (elems.ds_params && elems.ds_params_len == 1)
-		freq = ieee80211_channel_to_frequency(elems.ds_params[0]);
+		freq = ieee80211_channel_to_frequency(elems.ds_params[0],
+						      rx_status->band);
 	else
 		freq = rx_status->freq;
 
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 37693b6ef23a..c565689f0b9f 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1801,9 +1801,9 @@ void regulatory_hint_disconnect(void)
 
 static bool freq_is_chan_12_13_14(u16 freq)
 {
-	if (freq == ieee80211_channel_to_frequency(12) ||
-	    freq == ieee80211_channel_to_frequency(13) ||
-	    freq == ieee80211_channel_to_frequency(14))
+	if (freq == ieee80211_channel_to_frequency(12, IEEE80211_BAND_2GHZ) ||
+	    freq == ieee80211_channel_to_frequency(13, IEEE80211_BAND_2GHZ) ||
+	    freq == ieee80211_channel_to_frequency(14, IEEE80211_BAND_2GHZ))
 		return true;
 	return false;
 }
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 7620ae2fcf18..4ed065d8bb51 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -29,29 +29,37 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband,
 }
 EXPORT_SYMBOL(ieee80211_get_response_rate);
 
-int ieee80211_channel_to_frequency(int chan)
+int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band)
 {
-	if (chan < 14)
-		return 2407 + chan * 5;
-
-	if (chan == 14)
-		return 2484;
-
-	/* FIXME: 802.11j 17.3.8.3.2 */
-	return (chan + 1000) * 5;
+	/* see 802.11 17.3.8.3.2 and Annex J
+	 * there are overlapping channel numbers in 5GHz and 2GHz bands */
+	if (band == IEEE80211_BAND_5GHZ) {
+		if (chan >= 182 && chan <= 196)
+			return 4000 + chan * 5;
+		else
+			return 5000 + chan * 5;
+	} else { /* IEEE80211_BAND_2GHZ */
+		if (chan == 14)
+			return 2484;
+		else if (chan < 14)
+			return 2407 + chan * 5;
+		else
+			return 0; /* not supported */
+	}
 }
 EXPORT_SYMBOL(ieee80211_channel_to_frequency);
 
 int ieee80211_frequency_to_channel(int freq)
 {
+	/* see 802.11 17.3.8.3.2 and Annex J */
 	if (freq == 2484)
 		return 14;
-
-	if (freq < 2484)
+	else if (freq < 2484)
 		return (freq - 2407) / 5;
-
-	/* FIXME: 802.11j 17.3.8.3.2 */
-	return freq/5 - 1000;
+	else if (freq >= 4910 && freq <= 4980)
+		return (freq - 4000) / 5;
+	else
+		return (freq - 5000) / 5;
 }
 EXPORT_SYMBOL(ieee80211_frequency_to_channel);
 
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 3e5dbd4e4cd5..7f1f4ec49041 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -267,9 +267,12 @@ int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq)
 	 * -EINVAL for impossible things.
 	 */
 	if (freq->e == 0) {
+		enum ieee80211_band band = IEEE80211_BAND_2GHZ;
 		if (freq->m < 0)
 			return 0;
-		return ieee80211_channel_to_frequency(freq->m);
+		if (freq->m > 14)
+			band = IEEE80211_BAND_5GHZ;
+		return ieee80211_channel_to_frequency(freq->m, band);
 	} else {
 		int i, div = 1000000;
 		for (i = 0; i < freq->e; i++)
-- 
cgit v1.2.3


From cd7eab44e9946c28d595abe3e9a43e945bc49141 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 19 Jan 2011 21:01:44 +0000
Subject: genirq: Add IRQ affinity notifiers

When initiating I/O on a multiqueue and multi-IRQ device, we may want
to select a queue for which the response will be handled on the same
or a nearby CPU.  This requires a reverse-map of IRQ affinity.  Add a
notification mechanism to support this.

This is based closely on work by Thomas Gleixner <tglx@linutronix.de>.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Cc: linux-net-drivers@solarflare.com
Cc: Tom Herbert <therbert@google.com>
Cc: David Miller <davem@davemloft.net>
LKML-Reference: <1295470904.11126.84.camel@bwh-desktop>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/interrupt.h | 33 ++++++++++++++++++-
 include/linux/irqdesc.h   |  3 ++
 kernel/irq/manage.c       | 82 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 117 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 55e0d4253e49..63c5ad78e37c 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -14,6 +14,8 @@
 #include <linux/smp.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
+#include <linux/kref.h>
+#include <linux/workqueue.h>
 
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
@@ -240,6 +242,35 @@ extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
 extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+
+/**
+ * struct irq_affinity_notify - context for notification of IRQ affinity changes
+ * @irq:		Interrupt to which notification applies
+ * @kref:		Reference count, for internal use
+ * @work:		Work item, for internal use
+ * @notify:		Function to be called on change.  This will be
+ *			called in process context.
+ * @release:		Function to be called on release.  This will be
+ *			called in process context.  Once registered, the
+ *			structure must only be freed when this function is
+ *			called or later.
+ */
+struct irq_affinity_notify {
+	unsigned int irq;
+	struct kref kref;
+	struct work_struct work;
+	void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
+	void (*release)(struct kref *ref);
+};
+
+extern int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
+
+static inline void irq_run_affinity_notifiers(void)
+{
+	flush_scheduled_work();
+}
+
 #else /* CONFIG_SMP */
 
 static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
@@ -255,7 +286,7 @@ static inline int irq_can_set_affinity(unsigned int irq)
 static inline int irq_select_affinity(unsigned int irq)  { return 0; }
 
 static inline int irq_set_affinity_hint(unsigned int irq,
-                                        const struct cpumask *m)
+					const struct cpumask *m)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index c1a95b7b58de..bfef56dadddb 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -8,6 +8,7 @@
  * For now it's included from <linux/irq.h>
  */
 
+struct irq_affinity_notify;
 struct proc_dir_entry;
 struct timer_rand_state;
 /**
@@ -24,6 +25,7 @@ struct timer_rand_state;
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
  * @lock:		locking for SMP
+ * @affinity_notify:	context for notification of affinity changes
  * @pending_mask:	pending rebalanced interrupts
  * @threads_active:	number of irqaction threads currently running
  * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
@@ -70,6 +72,7 @@ struct irq_desc {
 	raw_spinlock_t		lock;
 #ifdef CONFIG_SMP
 	const struct cpumask	*affinity_hint;
+	struct irq_affinity_notify *affinity_notify;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_var_t		pending_mask;
 #endif
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0caa59f747dd..0587c5ceaed8 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -134,6 +134,10 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 		irq_set_thread_affinity(desc);
 	}
 #endif
+	if (desc->affinity_notify) {
+		kref_get(&desc->affinity_notify->kref);
+		schedule_work(&desc->affinity_notify->work);
+	}
 	desc->status |= IRQ_AFFINITY_SET;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
@@ -155,6 +159,79 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 }
 EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
 
+static void irq_affinity_notify(struct work_struct *work)
+{
+	struct irq_affinity_notify *notify =
+		container_of(work, struct irq_affinity_notify, work);
+	struct irq_desc *desc = irq_to_desc(notify->irq);
+	cpumask_var_t cpumask;
+	unsigned long flags;
+
+	if (!desc)
+		goto out;
+
+	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		goto out;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	if (desc->status & IRQ_MOVE_PENDING)
+		cpumask_copy(cpumask, desc->pending_mask);
+	else
+#endif
+		cpumask_copy(cpumask, desc->affinity);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	notify->notify(notify, cpumask);
+
+	free_cpumask_var(cpumask);
+out:
+	kref_put(&notify->kref, notify->release);
+}
+
+/**
+ *	irq_set_affinity_notifier - control notification of IRQ affinity changes
+ *	@irq:		Interrupt for which to enable/disable notification
+ *	@notify:	Context for notification, or %NULL to disable
+ *			notification.  Function pointers must be initialised;
+ *			the other fields will be initialised by this function.
+ *
+ *	Must be called in process context.  Notification may only be enabled
+ *	after the IRQ is allocated and must be disabled before the IRQ is
+ *	freed using free_irq().
+ */
+int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_affinity_notify *old_notify;
+	unsigned long flags;
+
+	/* The release function is promised process context */
+	might_sleep();
+
+	if (!desc)
+		return -EINVAL;
+
+	/* Complete initialisation of *notify */
+	if (notify) {
+		notify->irq = irq;
+		kref_init(&notify->kref);
+		INIT_WORK(&notify->work, irq_affinity_notify);
+	}
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	old_notify = desc->affinity_notify;
+	desc->affinity_notify = notify;
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	if (old_notify)
+		kref_put(&old_notify->kref, old_notify->release);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
+
 #ifndef CONFIG_AUTO_IRQ_AFFINITY
 /*
  * Generic version of the affinity autoselector.
@@ -1004,6 +1081,11 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (!desc)
 		return;
 
+#ifdef CONFIG_SMP
+	if (WARN_ON(desc->affinity_notify))
+		desc->affinity_notify = NULL;
+#endif
+
 	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
 	chip_bus_sync_unlock(desc);
-- 
cgit v1.2.3


From c39649c331c70952700f99832b03f87e9d7f5b4b Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 19 Jan 2011 11:03:25 +0000
Subject: lib: cpu_rmap: CPU affinity reverse-mapping

When initiating I/O on a multiqueue and multi-IRQ device, we may want
to select a queue for which the response will be handled on the same
or a nearby CPU.  This requires a reverse-map of IRQ affinity.  Add
library functions to support a generic reverse-mapping from CPUs to
objects with affinity and the specific case where the objects are
IRQs.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cpu_rmap.h |  73 +++++++++++++
 lib/Kconfig              |   4 +
 lib/Makefile             |   2 +
 lib/cpu_rmap.c           | 269 +++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 348 insertions(+)
 create mode 100644 include/linux/cpu_rmap.h
 create mode 100644 lib/cpu_rmap.c

(limited to 'include')

diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
new file mode 100644
index 000000000000..473771a528c0
--- /dev/null
+++ b/include/linux/cpu_rmap.h
@@ -0,0 +1,73 @@
+/*
+ * cpu_rmap.c: CPU affinity reverse-map support
+ * Copyright 2011 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/cpumask.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+
+/**
+ * struct cpu_rmap - CPU affinity reverse-map
+ * @size: Number of objects to be reverse-mapped
+ * @used: Number of objects added
+ * @obj: Pointer to array of object pointers
+ * @near: For each CPU, the index and distance to the nearest object,
+ *      based on affinity masks
+ */
+struct cpu_rmap {
+	u16		size, used;
+	void		**obj;
+	struct {
+		u16	index;
+		u16	dist;
+	}		near[0];
+};
+#define CPU_RMAP_DIST_INF 0xffff
+
+extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
+
+/**
+ * free_cpu_rmap - free CPU affinity reverse-map
+ * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL
+ */
+static inline void free_cpu_rmap(struct cpu_rmap *rmap)
+{
+	kfree(rmap);
+}
+
+extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
+extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
+			   const struct cpumask *affinity);
+
+static inline u16 cpu_rmap_lookup_index(struct cpu_rmap *rmap, unsigned int cpu)
+{
+	return rmap->near[cpu].index;
+}
+
+static inline void *cpu_rmap_lookup_obj(struct cpu_rmap *rmap, unsigned int cpu)
+{
+	return rmap->obj[rmap->near[cpu].index];
+}
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+
+/**
+ * alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs
+ * @size: Number of objects to be mapped
+ *
+ * Must be called in process context.
+ */
+static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size)
+{
+	return alloc_cpu_rmap(size, GFP_KERNEL);
+}
+extern void free_irq_cpu_rmap(struct cpu_rmap *rmap);
+
+extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq);
+
+#endif
diff --git a/lib/Kconfig b/lib/Kconfig
index 0ee67e08ad3e..8334342e0d05 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -201,6 +201,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
        bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
        depends on EXPERIMENTAL && BROKEN
 
+config CPU_RMAP
+	bool
+	depends on SMP
+
 #
 # Netlink attribute parsing support is select'ed if needed
 #
diff --git a/lib/Makefile b/lib/Makefile
index cbb774f7d41d..b73ba01a818a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -110,6 +110,8 @@ obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
 
 obj-$(CONFIG_AVERAGE) += average.o
 
+obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
new file mode 100644
index 000000000000..987acfafeb83
--- /dev/null
+++ b/lib/cpu_rmap.c
@@ -0,0 +1,269 @@
+/*
+ * cpu_rmap.c: CPU affinity reverse-map support
+ * Copyright 2011 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/cpu_rmap.h>
+#ifdef CONFIG_GENERIC_HARDIRQS
+#include <linux/interrupt.h>
+#endif
+#include <linux/module.h>
+
+/*
+ * These functions maintain a mapping from CPUs to some ordered set of
+ * objects with CPU affinities.  This can be seen as a reverse-map of
+ * CPU affinity.  However, we do not assume that the object affinities
+ * cover all CPUs in the system.  For those CPUs not directly covered
+ * by object affinities, we attempt to find a nearest object based on
+ * CPU topology.
+ */
+
+/**
+ * alloc_cpu_rmap - allocate CPU affinity reverse-map
+ * @size: Number of objects to be mapped
+ * @flags: Allocation flags e.g. %GFP_KERNEL
+ */
+struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
+{
+	struct cpu_rmap *rmap;
+	unsigned int cpu;
+	size_t obj_offset;
+
+	/* This is a silly number of objects, and we use u16 indices. */
+	if (size > 0xffff)
+		return NULL;
+
+	/* Offset of object pointer array from base structure */
+	obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]),
+			   sizeof(void *));
+
+	rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags);
+	if (!rmap)
+		return NULL;
+
+	rmap->obj = (void **)((char *)rmap + obj_offset);
+
+	/* Initially assign CPUs to objects on a rota, since we have
+	 * no idea where the objects are.  Use infinite distance, so
+	 * any object with known distance is preferable.  Include the
+	 * CPUs that are not present/online, since we definitely want
+	 * any newly-hotplugged CPUs to have some object assigned.
+	 */
+	for_each_possible_cpu(cpu) {
+		rmap->near[cpu].index = cpu % size;
+		rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
+	}
+
+	rmap->size = size;
+	return rmap;
+}
+EXPORT_SYMBOL(alloc_cpu_rmap);
+
+/* Reevaluate nearest object for given CPU, comparing with the given
+ * neighbours at the given distance.
+ */
+static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu,
+				const struct cpumask *mask, u16 dist)
+{
+	int neigh;
+
+	for_each_cpu(neigh, mask) {
+		if (rmap->near[cpu].dist > dist &&
+		    rmap->near[neigh].dist <= dist) {
+			rmap->near[cpu].index = rmap->near[neigh].index;
+			rmap->near[cpu].dist = dist;
+			return true;
+		}
+	}
+	return false;
+}
+
+#ifdef DEBUG
+static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
+{
+	unsigned index;
+	unsigned int cpu;
+
+	pr_info("cpu_rmap %p, %s:\n", rmap, prefix);
+
+	for_each_possible_cpu(cpu) {
+		index = rmap->near[cpu].index;
+		pr_info("cpu %d -> obj %u (distance %u)\n",
+			cpu, index, rmap->near[cpu].dist);
+	}
+}
+#else
+static inline void
+debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
+{
+}
+#endif
+
+/**
+ * cpu_rmap_add - add object to a rmap
+ * @rmap: CPU rmap allocated with alloc_cpu_rmap()
+ * @obj: Object to add to rmap
+ *
+ * Return index of object.
+ */
+int cpu_rmap_add(struct cpu_rmap *rmap, void *obj)
+{
+	u16 index;
+
+	BUG_ON(rmap->used >= rmap->size);
+	index = rmap->used++;
+	rmap->obj[index] = obj;
+	return index;
+}
+EXPORT_SYMBOL(cpu_rmap_add);
+
+/**
+ * cpu_rmap_update - update CPU rmap following a change of object affinity
+ * @rmap: CPU rmap to update
+ * @index: Index of object whose affinity changed
+ * @affinity: New CPU affinity of object
+ */
+int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
+		    const struct cpumask *affinity)
+{
+	cpumask_var_t update_mask;
+	unsigned int cpu;
+
+	if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL)))
+		return -ENOMEM;
+
+	/* Invalidate distance for all CPUs for which this used to be
+	 * the nearest object.  Mark those CPUs for update.
+	 */
+	for_each_online_cpu(cpu) {
+		if (rmap->near[cpu].index == index) {
+			rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
+			cpumask_set_cpu(cpu, update_mask);
+		}
+	}
+
+	debug_print_rmap(rmap, "after invalidating old distances");
+
+	/* Set distance to 0 for all CPUs in the new affinity mask.
+	 * Mark all CPUs within their NUMA nodes for update.
+	 */
+	for_each_cpu(cpu, affinity) {
+		rmap->near[cpu].index = index;
+		rmap->near[cpu].dist = 0;
+		cpumask_or(update_mask, update_mask,
+			   cpumask_of_node(cpu_to_node(cpu)));
+	}
+
+	debug_print_rmap(rmap, "after updating neighbours");
+
+	/* Update distances based on topology */
+	for_each_cpu(cpu, update_mask) {
+		if (cpu_rmap_copy_neigh(rmap, cpu,
+					topology_thread_cpumask(cpu), 1))
+			continue;
+		if (cpu_rmap_copy_neigh(rmap, cpu,
+					topology_core_cpumask(cpu), 2))
+			continue;
+		if (cpu_rmap_copy_neigh(rmap, cpu,
+					cpumask_of_node(cpu_to_node(cpu)), 3))
+			continue;
+		/* We could continue into NUMA node distances, but for now
+		 * we give up.
+		 */
+	}
+
+	debug_print_rmap(rmap, "after copying neighbours");
+
+	free_cpumask_var(update_mask);
+	return 0;
+}
+EXPORT_SYMBOL(cpu_rmap_update);
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+
+/* Glue between IRQ affinity notifiers and CPU rmaps */
+
+struct irq_glue {
+	struct irq_affinity_notify notify;
+	struct cpu_rmap *rmap;
+	u16 index;
+};
+
+/**
+ * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
+ * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
+ *
+ * Must be called in process context, before freeing the IRQs, and
+ * without holding any locks required by global workqueue items.
+ */
+void free_irq_cpu_rmap(struct cpu_rmap *rmap)
+{
+	struct irq_glue *glue;
+	u16 index;
+
+	if (!rmap)
+		return;
+
+	for (index = 0; index < rmap->used; index++) {
+		glue = rmap->obj[index];
+		irq_set_affinity_notifier(glue->notify.irq, NULL);
+	}
+	irq_run_affinity_notifiers();
+
+	kfree(rmap);
+}
+EXPORT_SYMBOL(free_irq_cpu_rmap);
+
+static void
+irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
+{
+	struct irq_glue *glue =
+		container_of(notify, struct irq_glue, notify);
+	int rc;
+
+	rc = cpu_rmap_update(glue->rmap, glue->index, mask);
+	if (rc)
+		pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
+}
+
+static void irq_cpu_rmap_release(struct kref *ref)
+{
+	struct irq_glue *glue =
+		container_of(ref, struct irq_glue, notify.kref);
+	kfree(glue);
+}
+
+/**
+ * irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map
+ * @rmap: The reverse-map
+ * @irq: The IRQ number
+ *
+ * This adds an IRQ affinity notifier that will update the reverse-map
+ * automatically.
+ *
+ * Must be called in process context, after the IRQ is allocated but
+ * before it is bound with request_irq().
+ */
+int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
+{
+	struct irq_glue *glue = kzalloc(sizeof(*glue), GFP_KERNEL);
+	int rc;
+
+	if (!glue)
+		return -ENOMEM;
+	glue->notify.notify = irq_cpu_rmap_notify;
+	glue->notify.release = irq_cpu_rmap_release;
+	glue->rmap = rmap;
+	glue->index = cpu_rmap_add(rmap, glue);
+	rc = irq_set_affinity_notifier(irq, &glue->notify);
+	if (rc)
+		kfree(glue);
+	return rc;
+}
+EXPORT_SYMBOL(irq_cpu_rmap_add);
+
+#endif /* CONFIG_GENERIC_HARDIRQS */
-- 
cgit v1.2.3


From c445477d74ab3779d1386ab797fbb9b628eb9f64 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 19 Jan 2011 11:03:53 +0000
Subject: net: RPS: Enable hardware acceleration of RFS

Allow drivers for multiqueue hardware with flow filter tables to
accelerate RFS.  The driver must:

1. Set net_device::rx_cpu_rmap to a cpu_rmap of the RX completion
IRQs (in queue order).  This will provide a mapping from CPUs to the
queues for which completions are handled nearest to them.

2. Implement net_device_ops::ndo_rx_flow_steer.  This operation adds
or replaces a filter steering the given flow to the given RX queue, if
possible.

3. Periodically remove filters for which rps_may_expire_flow() returns
true.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 33 ++++++++++++++--
 net/Kconfig               |  6 +++
 net/core/dev.c            | 97 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 127 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 371fa8839d51..a335f2022690 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -554,14 +554,16 @@ struct rps_map {
 #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16)))
 
 /*
- * The rps_dev_flow structure contains the mapping of a flow to a CPU and the
- * tail pointer for that CPU's input queue at the time of last enqueue.
+ * The rps_dev_flow structure contains the mapping of a flow to a CPU, the
+ * tail pointer for that CPU's input queue at the time of last enqueue, and
+ * a hardware filter index.
  */
 struct rps_dev_flow {
 	u16 cpu;
-	u16 fill;
+	u16 filter;
 	unsigned int last_qtail;
 };
+#define RPS_NO_FILTER 0xffff
 
 /*
  * The rps_dev_flow_table structure contains a table of flow mappings.
@@ -611,6 +613,11 @@ static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
 
 extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
 
+#ifdef CONFIG_RFS_ACCEL
+extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
+				u32 flow_id, u16 filter_id);
+#endif
+
 /* This structure contains an instance of an RX queue. */
 struct netdev_rx_queue {
 	struct rps_map __rcu		*rps_map;
@@ -769,6 +776,13 @@ struct netdev_tc_txq {
  * 	is always called from the stack with the rtnl lock held and netif tx
  * 	queues stopped. This allows the netdevice to perform queue management
  * 	safely.
+ *
+ *	RFS acceleration.
+ * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
+ *			    u16 rxq_index, u32 flow_id);
+ *	Set hardware filter for RFS.  rxq_index is the target queue index;
+ *	flow_id is a flow ID to be passed to rps_may_expire_flow() later.
+ *	Return the filter ID on success, or a negative error code.
  */
 #define HAVE_NET_DEVICE_OPS
 struct net_device_ops {
@@ -842,6 +856,12 @@ struct net_device_ops {
 	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
 						    u64 *wwn, int type);
 #endif
+#ifdef CONFIG_RFS_ACCEL
+	int			(*ndo_rx_flow_steer)(struct net_device *dev,
+						     const struct sk_buff *skb,
+						     u16 rxq_index,
+						     u32 flow_id);
+#endif
 };
 
 /*
@@ -1056,6 +1076,13 @@ struct net_device {
 
 	/* Number of RX queues currently active in device */
 	unsigned int		real_num_rx_queues;
+
+#ifdef CONFIG_RFS_ACCEL
+	/* CPU reverse-mapping for RX completion interrupts, indexed
+	 * by RX queue number.  Assigned by driver.  This must only be
+	 * set if the ndo_rx_flow_steer operation is defined. */
+	struct cpu_rmap		*rx_cpu_rmap;
+#endif
 #endif
 
 	rx_handler_func_t __rcu	*rx_handler;
diff --git a/net/Kconfig b/net/Kconfig
index 72840626284b..79cabf1ee68b 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -221,6 +221,12 @@ config RPS
 	depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
 	default y
 
+config RFS_ACCEL
+	boolean
+	depends on RPS && GENERIC_HARDIRQS
+	select CPU_RMAP
+	default y
+
 config XPS
 	boolean
 	depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
diff --git a/net/core/dev.c b/net/core/dev.c
index d162ba8d622d..aa761472f9e2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -132,6 +132,7 @@
 #include <trace/events/skb.h>
 #include <linux/pci.h>
 #include <linux/inetdevice.h>
+#include <linux/cpu_rmap.h>
 
 #include "net-sysfs.h"
 
@@ -2588,6 +2589,53 @@ EXPORT_SYMBOL(__skb_get_rxhash);
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
 
+static struct rps_dev_flow *
+set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
+	    struct rps_dev_flow *rflow, u16 next_cpu)
+{
+	u16 tcpu;
+
+	tcpu = rflow->cpu = next_cpu;
+	if (tcpu != RPS_NO_CPU) {
+#ifdef CONFIG_RFS_ACCEL
+		struct netdev_rx_queue *rxqueue;
+		struct rps_dev_flow_table *flow_table;
+		struct rps_dev_flow *old_rflow;
+		u32 flow_id;
+		u16 rxq_index;
+		int rc;
+
+		/* Should we steer this flow to a different hardware queue? */
+		if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap)
+			goto out;
+		rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu);
+		if (rxq_index == skb_get_rx_queue(skb))
+			goto out;
+
+		rxqueue = dev->_rx + rxq_index;
+		flow_table = rcu_dereference(rxqueue->rps_flow_table);
+		if (!flow_table)
+			goto out;
+		flow_id = skb->rxhash & flow_table->mask;
+		rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
+							rxq_index, flow_id);
+		if (rc < 0)
+			goto out;
+		old_rflow = rflow;
+		rflow = &flow_table->flows[flow_id];
+		rflow->cpu = next_cpu;
+		rflow->filter = rc;
+		if (old_rflow->filter == rflow->filter)
+			old_rflow->filter = RPS_NO_FILTER;
+	out:
+#endif
+		rflow->last_qtail =
+			per_cpu(softnet_data, tcpu).input_queue_head;
+	}
+
+	return rflow;
+}
+
 /*
  * get_rps_cpu is called from netif_receive_skb and returns the target
  * CPU from the RPS map of the receiving queue for a given skb.
@@ -2658,12 +2706,9 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		if (unlikely(tcpu != next_cpu) &&
 		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
-		      rflow->last_qtail)) >= 0)) {
-			tcpu = rflow->cpu = next_cpu;
-			if (tcpu != RPS_NO_CPU)
-				rflow->last_qtail = per_cpu(softnet_data,
-				    tcpu).input_queue_head;
-		}
+		      rflow->last_qtail)) >= 0))
+			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+
 		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
 			*rflowp = rflow;
 			cpu = tcpu;
@@ -2684,6 +2729,46 @@ done:
 	return cpu;
 }
 
+#ifdef CONFIG_RFS_ACCEL
+
+/**
+ * rps_may_expire_flow - check whether an RFS hardware filter may be removed
+ * @dev: Device on which the filter was set
+ * @rxq_index: RX queue index
+ * @flow_id: Flow ID passed to ndo_rx_flow_steer()
+ * @filter_id: Filter ID returned by ndo_rx_flow_steer()
+ *
+ * Drivers that implement ndo_rx_flow_steer() should periodically call
+ * this function for each installed filter and remove the filters for
+ * which it returns %true.
+ */
+bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
+			 u32 flow_id, u16 filter_id)
+{
+	struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index;
+	struct rps_dev_flow_table *flow_table;
+	struct rps_dev_flow *rflow;
+	bool expire = true;
+	int cpu;
+
+	rcu_read_lock();
+	flow_table = rcu_dereference(rxqueue->rps_flow_table);
+	if (flow_table && flow_id <= flow_table->mask) {
+		rflow = &flow_table->flows[flow_id];
+		cpu = ACCESS_ONCE(rflow->cpu);
+		if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
+		    ((int)(per_cpu(softnet_data, cpu).input_queue_head -
+			   rflow->last_qtail) <
+		     (int)(10 * flow_table->mask)))
+			expire = false;
+	}
+	rcu_read_unlock();
+	return expire;
+}
+EXPORT_SYMBOL(rps_may_expire_flow);
+
+#endif /* CONFIG_RFS_ACCEL */
+
 /* Called from hardirq (IPI) context */
 static void rps_trigger_softirq(void *data)
 {
-- 
cgit v1.2.3


From 04ed3e741d0f133e02bed7fa5c98edba128f90e7 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Mon, 24 Jan 2011 15:32:47 -0800
Subject: net: change netdev->features to u32
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Quoting Ben Hutchings: we presumably won't be defining features that
can only be enabled on 64-bit architectures.

Occurences found by `grep -r` on net/, drivers/net, include/

[ Move features and vlan_features next to each other in
  struct netdev, as per Eric Dumazet's suggestion -DaveM ]

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bnx2.c              |  2 +-
 drivers/net/bonding/bond_main.c |  4 ++--
 drivers/net/myri10ge/myri10ge.c |  4 ++--
 drivers/net/sfc/ethtool.c       |  4 ++--
 drivers/net/sfc/net_driver.h    |  2 +-
 drivers/net/tun.c               |  2 +-
 include/linux/netdevice.h       | 24 ++++++++++++------------
 include/linux/skbuff.h          |  2 +-
 include/net/protocol.h          |  4 ++--
 include/net/tcp.h               |  2 +-
 include/net/udp.h               |  2 +-
 net/8021q/vlan.c                |  2 +-
 net/bridge/br_if.c              |  2 +-
 net/bridge/br_private.h         |  2 +-
 net/core/dev.c                  | 15 +++++++--------
 net/core/ethtool.c              |  2 +-
 net/core/net-sysfs.c            |  2 +-
 net/core/skbuff.c               |  4 ++--
 net/ipv4/af_inet.c              |  2 +-
 net/ipv4/tcp.c                  |  2 +-
 net/ipv4/udp.c                  |  2 +-
 net/ipv6/af_inet6.c             |  2 +-
 net/ipv6/udp.c                  |  2 +-
 23 files changed, 45 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index df99edf3464a..cab96fa4cd3a 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -8312,7 +8312,7 @@ static const struct net_device_ops bnx2_netdev_ops = {
 #endif
 };
 
-static void inline vlan_features_add(struct net_device *dev, unsigned long flags)
+static void inline vlan_features_add(struct net_device *dev, u32 flags)
 {
 	dev->vlan_features |= flags;
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 163e0b06eaa5..7047b406b8ba 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1372,8 +1372,8 @@ static int bond_compute_features(struct bonding *bond)
 {
 	struct slave *slave;
 	struct net_device *bond_dev = bond->dev;
-	unsigned long features = bond_dev->features;
-	unsigned long vlan_features = 0;
+	u32 features = bond_dev->features;
+	u32 vlan_features = 0;
 	unsigned short max_hard_header_len = max((u16)ETH_HLEN,
 						bond_dev->hard_header_len);
 	int i;
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index ea5cfe2c3a04..a7f2eed9a08a 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -253,7 +253,7 @@ struct myri10ge_priv {
 	unsigned long serial_number;
 	int vendor_specific_offset;
 	int fw_multicast_support;
-	unsigned long features;
+	u32 features;
 	u32 max_tso6;
 	u32 read_dma;
 	u32 write_dma;
@@ -1776,7 +1776,7 @@ static int myri10ge_set_rx_csum(struct net_device *netdev, u32 csum_enabled)
 static int myri10ge_set_tso(struct net_device *netdev, u32 tso_enabled)
 {
 	struct myri10ge_priv *mgp = netdev_priv(netdev);
-	unsigned long flags = mgp->features & (NETIF_F_TSO6 | NETIF_F_TSO);
+	u32 flags = mgp->features & (NETIF_F_TSO6 | NETIF_F_TSO);
 
 	if (tso_enabled)
 		netdev->features |= flags;
diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c
index 0e8bb19ed60d..713969accdbd 100644
--- a/drivers/net/sfc/ethtool.c
+++ b/drivers/net/sfc/ethtool.c
@@ -502,7 +502,7 @@ static void efx_ethtool_get_stats(struct net_device *net_dev,
 static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable)
 {
 	struct efx_nic *efx __attribute__ ((unused)) = netdev_priv(net_dev);
-	unsigned long features;
+	u32 features;
 
 	features = NETIF_F_TSO;
 	if (efx->type->offload_features & NETIF_F_V6_CSUM)
@@ -519,7 +519,7 @@ static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable)
 static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	unsigned long features = efx->type->offload_features & NETIF_F_ALL_CSUM;
+	u32 features = efx->type->offload_features & NETIF_F_ALL_CSUM;
 
 	if (enable)
 		net_dev->features |= features;
diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index 28df8665256a..c65270241d2d 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -906,7 +906,7 @@ struct efx_nic_type {
 	unsigned int phys_addr_channels;
 	unsigned int tx_dc_base;
 	unsigned int rx_dc_base;
-	unsigned long offload_features;
+	u32 offload_features;
 	u32 reset_world_flags;
 };
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b100bd50a0d7..55786a0efc41 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1142,7 +1142,7 @@ static int tun_get_iff(struct net *net, struct tun_struct *tun,
  * privs required. */
 static int set_offload(struct net_device *dev, unsigned long arg)
 {
-	unsigned int old_features, features;
+	u32 old_features, features;
 
 	old_features = dev->features;
 	/* Unset features, set them as we chew on the arg. */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a335f2022690..0de3c59720fa 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -914,7 +914,11 @@ struct net_device {
 	struct list_head	unreg_list;
 
 	/* Net device features */
-	unsigned long		features;
+	u32			features;
+
+	/* VLAN feature mask */
+	u32			vlan_features;
+
 #define NETIF_F_SG		1	/* Scatter/gather IO. */
 #define NETIF_F_IP_CSUM		2	/* Can checksum TCP/UDP over IPv4. */
 #define NETIF_F_NO_CSUM		4	/* Does not require checksum. F.e. loopack. */
@@ -1176,9 +1180,6 @@ struct net_device {
 	/* rtnetlink link ops */
 	const struct rtnl_link_ops *rtnl_link_ops;
 
-	/* VLAN feature mask */
-	unsigned long vlan_features;
-
 	/* for setting kernel sock attribute on TCP connection setup */
 #define GSO_MAX_SIZE		65536
 	unsigned int		gso_max_size;
@@ -1401,7 +1402,7 @@ struct packet_type {
 					 struct packet_type *,
 					 struct net_device *);
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
-						int features);
+						u32 features);
 	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
@@ -2370,7 +2371,7 @@ extern int		netdev_tstamp_prequeue;
 extern int		weight_p;
 extern int		netdev_set_master(struct net_device *dev, struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb);
-extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features);
+extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features);
 #ifdef CONFIG_BUG
 extern void netdev_rx_csum_fault(struct net_device *dev);
 #else
@@ -2397,22 +2398,21 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l
 
 extern void linkwatch_run_queue(void);
 
-unsigned long netdev_increment_features(unsigned long all, unsigned long one,
-					unsigned long mask);
-unsigned long netdev_fix_features(unsigned long features, const char *name);
+u32 netdev_increment_features(u32 all, u32 one, u32 mask);
+u32 netdev_fix_features(u32 features, const char *name);
 
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
-int netif_skb_features(struct sk_buff *skb);
+u32 netif_skb_features(struct sk_buff *skb);
 
-static inline int net_gso_ok(int features, int gso_type)
+static inline int net_gso_ok(u32 features, int gso_type)
 {
 	int feature = gso_type << NETIF_F_GSO_SHIFT;
 	return (features & feature) == feature;
 }
 
-static inline int skb_gso_ok(struct sk_buff *skb, int features)
+static inline int skb_gso_ok(struct sk_buff *skb, u32 features)
 {
 	return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
 	       (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6e946da9d1d6..31f02d0b46a7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1877,7 +1877,7 @@ extern void	       skb_split(struct sk_buff *skb,
 extern int	       skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
 				 int shiftlen);
 
-extern struct sk_buff *skb_segment(struct sk_buff *skb, int features);
+extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features);
 
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 				       int len, void *buffer)
diff --git a/include/net/protocol.h b/include/net/protocol.h
index dc07495bce4c..6f7eb800974a 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -38,7 +38,7 @@ struct net_protocol {
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff	       *(*gso_segment)(struct sk_buff *skb,
-					       int features);
+					       u32 features);
 	struct sk_buff	      **(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb);
@@ -57,7 +57,7 @@ struct inet6_protocol {
 
 	int	(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff *(*gso_segment)(struct sk_buff *skb,
-				       int features);
+				       u32 features);
 	struct sk_buff **(*gro_receive)(struct sk_buff **head,
 					struct sk_buff *skb);
 	int	(*gro_complete)(struct sk_buff *skb);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 38509f047382..917911165e3b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1404,7 +1404,7 @@ extern struct request_sock_ops tcp6_request_sock_ops;
 extern void tcp_v4_destroy_sock(struct sock *sk);
 
 extern int tcp_v4_gso_send_check(struct sk_buff *skb);
-extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features);
 extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
 					struct sk_buff *skb);
 extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
diff --git a/include/net/udp.h b/include/net/udp.h
index bb967dd59bf7..e82f3a8c0f8f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -245,5 +245,5 @@ extern void udp4_proc_exit(void);
 extern void udp_init(void);
 
 extern int udp4_ufo_send_check(struct sk_buff *skb);
-extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features);
+extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features);
 #endif	/* _UDP_H */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 6e64f7c6a2e9..7850412f52b7 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -327,7 +327,7 @@ static void vlan_sync_address(struct net_device *dev,
 static void vlan_transfer_features(struct net_device *dev,
 				   struct net_device *vlandev)
 {
-	unsigned long old_features = vlandev->features;
+	u32 old_features = vlandev->features;
 
 	vlandev->features &= ~dev->vlan_features;
 	vlandev->features |= dev->features & dev->vlan_features;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index d9d1e2bac1d6..52ce4a30f8b3 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -365,7 +365,7 @@ int br_min_mtu(const struct net_bridge *br)
 void br_features_recompute(struct net_bridge *br)
 {
 	struct net_bridge_port *p;
-	unsigned long features, mask;
+	u32 features, mask;
 
 	features = mask = br->feature_mask;
 	if (list_empty(&br->port_list))
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 84aac7734bfc..9f22898c5359 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -182,7 +182,7 @@ struct net_bridge
 	struct br_cpu_netstats __percpu *stats;
 	spinlock_t			hash_lock;
 	struct hlist_head		hash[BR_HASH_SIZE];
-	unsigned long			feature_mask;
+	u32				feature_mask;
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct rtable 			fake_rtable;
 	bool				nf_call_iptables;
diff --git a/net/core/dev.c b/net/core/dev.c
index ad3741898584..7103f89fde0c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1858,7 +1858,7 @@ EXPORT_SYMBOL(skb_checksum_help);
  *	It may return NULL if the skb requires no segmentation.  This is
  *	only possible when GSO is used for verifying header integrity.
  */
-struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features)
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_type *ptype;
@@ -2046,7 +2046,7 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol)
 		 protocol == htons(ETH_P_FCOE)));
 }
 
-static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features)
+static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features)
 {
 	if (!can_checksum_protocol(features, protocol)) {
 		features &= ~NETIF_F_ALL_CSUM;
@@ -2058,10 +2058,10 @@ static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features
 	return features;
 }
 
-int netif_skb_features(struct sk_buff *skb)
+u32 netif_skb_features(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
-	int features = skb->dev->features;
+	u32 features = skb->dev->features;
 
 	if (protocol == htons(ETH_P_8021Q)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
@@ -2106,7 +2106,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 	int rc = NETDEV_TX_OK;
 
 	if (likely(!skb->next)) {
-		int features;
+		u32 features;
 
 		/*
 		 * If device doesnt need skb->dst, release it right now while
@@ -5213,7 +5213,7 @@ static void rollback_registered(struct net_device *dev)
 	rollback_registered_many(&single);
 }
 
-unsigned long netdev_fix_features(unsigned long features, const char *name)
+u32 netdev_fix_features(u32 features, const char *name)
 {
 	/* Fix illegal checksum combinations */
 	if ((features & NETIF_F_HW_CSUM) &&
@@ -6143,8 +6143,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
  *	@one to the master device with current feature set @all.  Will not
  *	enable anything that is off in @mask. Returns the new feature set.
  */
-unsigned long netdev_increment_features(unsigned long all, unsigned long one,
-					unsigned long mask)
+u32 netdev_increment_features(u32 all, u32 one, u32 mask)
 {
 	/* If device needs checksumming, downgrade to it. */
 	if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 17741782a345..bd1af99e1122 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1458,7 +1458,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	void __user *useraddr = ifr->ifr_data;
 	u32 ethcmd;
 	int rc;
-	unsigned long old_features;
+	u32 old_features;
 
 	if (!dev || !netif_device_present(dev))
 		return -ENODEV;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index e23c01be5a5b..81367ccf3306 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -99,7 +99,7 @@ NETDEVICE_SHOW(addr_assign_type, fmt_dec);
 NETDEVICE_SHOW(addr_len, fmt_dec);
 NETDEVICE_SHOW(iflink, fmt_dec);
 NETDEVICE_SHOW(ifindex, fmt_dec);
-NETDEVICE_SHOW(features, fmt_long_hex);
+NETDEVICE_SHOW(features, fmt_hex);
 NETDEVICE_SHOW(type, fmt_dec);
 NETDEVICE_SHOW(link_mode, fmt_dec);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d31bb36ae0dc..436c4c439240 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2497,7 +2497,7 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum);
  *	a pointer to the first in a list of new skbs for the segments.
  *	In case of error it returns ERR_PTR(err).
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, int features)
+struct sk_buff *skb_segment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
@@ -2507,7 +2507,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 	unsigned int offset = doffset;
 	unsigned int headroom;
 	unsigned int len;
-	int sg = features & NETIF_F_SG;
+	int sg = !!(features & NETIF_F_SG);
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	int err = -ENOMEM;
 	int i = 0;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f2b61107df6c..e5e2d9d64abb 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1215,7 +1215,7 @@ out:
 	return err;
 }
 
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct iphdr *iph;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6c11eece262c..f9867d2dbef4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2653,7 +2653,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct tcphdr *th;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8157b17959ee..d37baaa1dbe3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2199,7 +2199,7 @@ int udp4_ufo_send_check(struct sk_buff *skb)
 	return 0;
 }
 
-struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features)
+struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 978e80e2c4a8..3194aa909872 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -772,7 +772,7 @@ out:
 	return err;
 }
 
-static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features)
+static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct ipv6hdr *ipv6h;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9a009c66c8a3..a419a787eb69 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1299,7 +1299,7 @@ static int udp6_ufo_send_check(struct sk_buff *skb)
 	return 0;
 }
 
-static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
-- 
cgit v1.2.3


From acd1130e8793fb150fb522da8ec51675839eb4b1 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Mon, 24 Jan 2011 15:45:15 -0800
Subject: net: reduce and unify printk level in netdev_fix_features()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reduce printk() levels to KERN_INFO in netdev_fix_features() as this will
be used by ethtool and might spam dmesg unnecessarily.

This converts the function to use netdev_info() instead of plain printk().

As a side effect, bonding and bridge devices will now log dropped features
on every slave device change.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c |  4 ++--
 include/linux/netdevice.h       |  2 +-
 net/bridge/br_if.c              |  2 +-
 net/core/dev.c                  | 33 ++++++++++++---------------------
 4 files changed, 16 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7047b406b8ba..1df9f0ea9184 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1400,8 +1400,8 @@ static int bond_compute_features(struct bonding *bond)
 
 done:
 	features |= (bond_dev->features & BOND_VLAN_FEATURES);
-	bond_dev->features = netdev_fix_features(features, NULL);
-	bond_dev->vlan_features = netdev_fix_features(vlan_features, NULL);
+	bond_dev->features = netdev_fix_features(bond_dev, features);
+	bond_dev->vlan_features = netdev_fix_features(bond_dev, vlan_features);
 	bond_dev->hard_header_len = max_hard_header_len;
 
 	return 0;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0de3c59720fa..8858422c5c5d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2399,7 +2399,7 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l
 extern void linkwatch_run_queue(void);
 
 u32 netdev_increment_features(u32 all, u32 one, u32 mask);
-u32 netdev_fix_features(u32 features, const char *name);
+u32 netdev_fix_features(struct net_device *dev, u32 features);
 
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 52ce4a30f8b3..2a6801d8b728 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -379,7 +379,7 @@ void br_features_recompute(struct net_bridge *br)
 	}
 
 done:
-	br->dev->features = netdev_fix_features(features, NULL);
+	br->dev->features = netdev_fix_features(br->dev, features);
 }
 
 /* called with RTNL */
diff --git a/net/core/dev.c b/net/core/dev.c
index 7103f89fde0c..1b4c07fe295f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5213,58 +5213,49 @@ static void rollback_registered(struct net_device *dev)
 	rollback_registered_many(&single);
 }
 
-u32 netdev_fix_features(u32 features, const char *name)
+u32 netdev_fix_features(struct net_device *dev, u32 features)
 {
 	/* Fix illegal checksum combinations */
 	if ((features & NETIF_F_HW_CSUM) &&
 	    (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
-		if (name)
-			printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n",
-				name);
+		netdev_info(dev, "mixed HW and IP checksum settings.\n");
 		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
 	}
 
 	if ((features & NETIF_F_NO_CSUM) &&
 	    (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
-		if (name)
-			printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n",
-				name);
+		netdev_info(dev, "mixed no checksumming and other settings.\n");
 		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
 	}
 
 	/* Fix illegal SG+CSUM combinations. */
 	if ((features & NETIF_F_SG) &&
 	    !(features & NETIF_F_ALL_CSUM)) {
-		if (name)
-			printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no "
-			       "checksum feature.\n", name);
+		netdev_info(dev,
+			    "Dropping NETIF_F_SG since no checksum feature.\n");
 		features &= ~NETIF_F_SG;
 	}
 
 	/* TSO requires that SG is present as well. */
 	if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) {
-		if (name)
-			printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no "
-			       "SG feature.\n", name);
+		netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n");
 		features &= ~NETIF_F_TSO;
 	}
 
+	/* UFO needs SG and checksumming */
 	if (features & NETIF_F_UFO) {
 		/* maybe split UFO into V4 and V6? */
 		if (!((features & NETIF_F_GEN_CSUM) ||
 		    (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
 			    == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
-			if (name)
-				printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
-				       "since no checksum offload features.\n",
-				       name);
+			netdev_info(dev,
+				"Dropping NETIF_F_UFO since no checksum offload features.\n");
 			features &= ~NETIF_F_UFO;
 		}
 
 		if (!(features & NETIF_F_SG)) {
-			if (name)
-				printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
-				       "since no NETIF_F_SG feature.\n", name);
+			netdev_info(dev,
+				"Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n");
 			features &= ~NETIF_F_UFO;
 		}
 	}
@@ -5407,7 +5398,7 @@ int register_netdevice(struct net_device *dev)
 	if (dev->iflink == -1)
 		dev->iflink = dev->ifindex;
 
-	dev->features = netdev_fix_features(dev->features, dev->name);
+	dev->features = netdev_fix_features(dev, dev->features);
 
 	/* Enable software GSO if SG is supported. */
 	if (dev->features & NETIF_F_SG)
-- 
cgit v1.2.3


From 19df0c2fef010e94e90df514aaf4e73f6b80145c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Jan 2011 14:26:50 +0100
Subject: percpu: align percpu readmostly subsection to cacheline

Currently percpu readmostly subsection may share cachelines with other
percpu subsections which may result in unnecessary cacheline bounce
and performance degradation.

This patch adds @cacheline parameter to PERCPU() and PERCPU_VADDR()
linker macros, makes each arch linker scripts specify its cacheline
size and use it to align percpu subsections.

This is based on Shaohua's x86 only patch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Shaohua Li <shaohua.li@intel.com>
---
 arch/alpha/kernel/vmlinux.lds.S    |  2 +-
 arch/arm/kernel/vmlinux.lds.S      |  2 +-
 arch/blackfin/kernel/vmlinux.lds.S |  2 +-
 arch/cris/kernel/vmlinux.lds.S     |  2 +-
 arch/frv/kernel/vmlinux.lds.S      |  2 +-
 arch/ia64/kernel/vmlinux.lds.S     |  2 +-
 arch/m32r/kernel/vmlinux.lds.S     |  2 +-
 arch/mips/kernel/vmlinux.lds.S     |  2 +-
 arch/mn10300/kernel/vmlinux.lds.S  |  2 +-
 arch/parisc/kernel/vmlinux.lds.S   |  2 +-
 arch/powerpc/kernel/vmlinux.lds.S  |  2 +-
 arch/s390/kernel/vmlinux.lds.S     |  2 +-
 arch/sh/kernel/vmlinux.lds.S       |  2 +-
 arch/sparc/kernel/vmlinux.lds.S    |  2 +-
 arch/tile/kernel/vmlinux.lds.S     |  2 +-
 arch/um/include/asm/common.lds.S   |  2 +-
 arch/x86/kernel/vmlinux.lds.S      |  4 ++--
 arch/xtensa/kernel/vmlinux.lds.S   |  2 +-
 include/asm-generic/vmlinux.lds.h  | 35 ++++++++++++++++++++++-------------
 19 files changed, 41 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 003ef4c02585..173518f8c8bb 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -38,7 +38,7 @@ SECTIONS
 	__init_begin = ALIGN(PAGE_SIZE);
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
-	PERCPU(PAGE_SIZE)
+	PERCPU(64, PAGE_SIZE)
 	/* Align to THREAD_SIZE rather than PAGE_SIZE here so any padding page
 	   needed for the THREAD_SIZE aligned init_task gets freed after init */
 	. = ALIGN(THREAD_SIZE);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 86b66f3f2031..cf78a03bf810 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -70,7 +70,7 @@ SECTIONS
 #endif
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(32, PAGE_SIZE)
 
 #ifndef CONFIG_XIP_KERNEL
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 4122678529c0..c40d07f708e8 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -136,7 +136,7 @@ SECTIONS
 
 	. = ALIGN(16);
 	INIT_DATA_SECTION(16)
-	PERCPU(4)
+	PERCPU(32, 4)
 
 	.exit.data :
 	{
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 442218980db0..c62e1346f47c 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -107,7 +107,7 @@ SECTIONS
 #endif
 	__vmlinux_end = .;		/* Last address of the physical file. */
 #ifdef CONFIG_ETRAX_ARCH_V32
-	PERCPU(PAGE_SIZE)
+	PERCPU(32, PAGE_SIZE)
 
 	.init.ramfs : {
 		INIT_RAM_FS
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index 8b973f3cc90e..0daae8af5787 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/arch/frv/kernel/vmlinux.lds.S
@@ -37,7 +37,7 @@ SECTIONS
   _einittext = .;
 
   INIT_DATA_SECTION(8)
-  PERCPU(4096)
+  PERCPU(L1_CACHE_BYTES, 4096)
 
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 5a4d044dcb1c..787de4a77d82 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -198,7 +198,7 @@ SECTIONS {
 
 	/* Per-cpu data: */
 	. = ALIGN(PERCPU_PAGE_SIZE);
-	PERCPU_VADDR(PERCPU_ADDR, :percpu)
+	PERCPU_VADDR(SMP_CACHE_BYTES, PERCPU_ADDR, :percpu)
 	__phys_per_cpu_start = __per_cpu_load;
 	/*
 	 * ensure percpu data fits
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index 7da94eaa082b..c194d64cdbb9 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -53,7 +53,7 @@ SECTIONS
   __init_begin = .;
   INIT_TEXT_SECTION(PAGE_SIZE)
   INIT_DATA_SECTION(16)
-  PERCPU(PAGE_SIZE)
+  PERCPU(32, PAGE_SIZE)
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 570607b376b5..832afbb87588 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -115,7 +115,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(1 << CONFIG_MIPS_L1_CACHE_SHIFT, PAGE_SIZE)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index febbeee7f2f5..968bcd2cb022 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -70,7 +70,7 @@ SECTIONS
 	.exit.text : { EXIT_TEXT; }
 	.exit.data : { EXIT_DATA; }
 
-  PERCPU(PAGE_SIZE)
+  PERCPU(32, PAGE_SIZE)
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index d64a6bbec2aa..8f1e4efd143e 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -145,7 +145,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8a0deefac08d..b9150f07d266 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -160,7 +160,7 @@ SECTIONS
 		INIT_RAM_FS
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
 
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index a68ac10213b2..1bc18cdb525b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -77,7 +77,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(0x100, PAGE_SIZE)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 7f8a709c3ada..af4d46187a79 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -66,7 +66,7 @@ SECTIONS
 		__machvec_end = .;
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
 
 	/*
 	 * .exit.text is discarded at runtime, not link time, to deal with
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 0c1e6783657f..92b557afe535 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -108,7 +108,7 @@ SECTIONS
 		__sun4v_2insn_patch_end = .;
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(SMP_CACHE_BYTES, PAGE_SIZE)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S
index 25fdc0c1839a..c6ce378e0678 100644
--- a/arch/tile/kernel/vmlinux.lds.S
+++ b/arch/tile/kernel/vmlinux.lds.S
@@ -63,7 +63,7 @@ SECTIONS
     *(.init.page)
   } :data =0
   INIT_DATA_SECTION(16)
-  PERCPU(PAGE_SIZE)
+  PERCPU(L2_CACHE_BYTES, PAGE_SIZE)
   . = ALIGN(PAGE_SIZE);
   VMLINUX_SYMBOL(_einitdata) = .;
 
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index ac55b9efa1ce..34bede8aad4a 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -42,7 +42,7 @@
 	INIT_SETUP(0)
   }
 
-  PERCPU(32)
+  PERCPU(32, 32)
 	
   .initcall.init : {
 	INIT_CALLS
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bf4700755184..cef446f8ac78 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -230,7 +230,7 @@ SECTIONS
 	 * output PHDR, so the next output section - .init.text - should
 	 * start another segment - init.
 	 */
-	PERCPU_VADDR(0, :percpu)
+	PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
 #endif
 
 	INIT_TEXT_SECTION(PAGE_SIZE)
@@ -305,7 +305,7 @@ SECTIONS
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(THREAD_SIZE)
+	PERCPU(INTERNODE_CACHE_BYTES, THREAD_SIZE)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 9b526154c9ba..a2820065927e 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -155,7 +155,7 @@ SECTIONS
     INIT_RAM_FS
   }
 
-  PERCPU(PAGE_SIZE)
+  PERCPU(XCHAL_ICACHE_LINESIZE, PAGE_SIZE)
 
   /* We need this dummy segment here */
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 6ebb81030d2d..439df587c12c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -15,7 +15,7 @@
  *	HEAD_TEXT_SECTION
  *	INIT_TEXT_SECTION(PAGE_SIZE)
  *	INIT_DATA_SECTION(...)
- *	PERCPU(PAGE_SIZE)
+ *	PERCPU(CACHELINE_SIZE, PAGE_SIZE)
  *	__init_end = .;
  *
  *	_stext = .;
@@ -683,13 +683,18 @@
 
 /**
  * PERCPU_VADDR - define output section for percpu area
+ * @cacheline: cacheline size
  * @vaddr: explicit base address (optional)
  * @phdr: destination PHDR (optional)
  *
- * Macro which expands to output section for percpu area.  If @vaddr
- * is not blank, it specifies explicit base address and all percpu
- * symbols will be offset from the given address.  If blank, @vaddr
- * always equals @laddr + LOAD_OFFSET.
+ * Macro which expands to output section for percpu area.
+ *
+ * @cacheline is used to align subsections to avoid false cacheline
+ * sharing between subsections for different purposes.
+ *
+ * If @vaddr is not blank, it specifies explicit base address and all
+ * percpu symbols will be offset from the given address.  If blank,
+ * @vaddr always equals @laddr + LOAD_OFFSET.
  *
  * @phdr defines the output PHDR to use if not blank.  Be warned that
  * output PHDR is sticky.  If @phdr is specified, the next output
@@ -700,7 +705,7 @@
  * If there is no need to put the percpu section at a predetermined
  * address, use PERCPU().
  */
-#define PERCPU_VADDR(vaddr, phdr)					\
+#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
 	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
 	.data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
 				- LOAD_OFFSET) {			\
@@ -708,7 +713,9 @@
 		*(.data..percpu..first)					\
 		. = ALIGN(PAGE_SIZE);					\
 		*(.data..percpu..page_aligned)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu..readmostly)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu)					\
 		*(.data..percpu..shared_aligned)			\
 		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
@@ -717,18 +724,18 @@
 
 /**
  * PERCPU - define output section for percpu area, simple version
+ * @cacheline: cacheline size
  * @align: required alignment
  *
- * Align to @align and outputs output section for percpu area.  This
- * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * Align to @align and outputs output section for percpu area.  This macro
+ * doesn't manipulate @vaddr or @phdr and __per_cpu_load and
  * __per_cpu_start will be identical.
  *
- * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
- * that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32
- * configuration.
+ * This macro is equivalent to ALIGN(@align); PERCPU_VADDR(@cacheline,,)
+ * except that __per_cpu_load is defined as a relative symbol against
+ * .data..percpu which is required for relocatable x86_32 configuration.
  */
-#define PERCPU(align)							\
+#define PERCPU(cacheline, align)					\
 	. = ALIGN(align);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
@@ -736,7 +743,9 @@
 		*(.data..percpu..first)					\
 		. = ALIGN(PAGE_SIZE);					\
 		*(.data..percpu..page_aligned)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu..readmostly)				\
+		. = ALIGN(cacheline);					\
 		*(.data..percpu)					\
 		*(.data..percpu..shared_aligned)			\
 		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
-- 
cgit v1.2.3


From 41b2610c3443e6c4760e61fc10eef73f96f9f6a5 Mon Sep 17 00:00:00 2001
From: Hans Rosenfeld <hans.rosenfeld@amd.com>
Date: Mon, 24 Jan 2011 16:05:42 +0100
Subject: x86, amd: Extend AMD northbridge caching code to support "Link
 Control" devices

"Link Control" devices (NB function 4) will be used by L3 cache
partitioning on family 0x15.

Signed-off-by: Hans Rosenfeld <hans.rosenfeld@amd.com>
Cc: <andreas.herrmann3@amd.com>
LKML-Reference: <1295881543-572552-4-git-send-email-hans.rosenfeld@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/amd_nb.h |  1 +
 arch/x86/kernel/amd_nb.c      | 11 +++++++++--
 include/linux/pci_ids.h       |  1 +
 3 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 64dc82ee19f0..3e7070071d73 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -26,6 +26,7 @@ extern void amd_get_nodes(struct bootnode *nodes);
 
 struct amd_northbridge {
 	struct pci_dev *misc;
+	struct pci_dev *link;
 };
 
 struct amd_northbridge_info {
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index a4f394c8e055..4ae9a961c33c 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,11 @@ struct pci_device_id amd_nb_misc_ids[] = {
 };
 EXPORT_SYMBOL(amd_nb_misc_ids);
 
+static struct pci_device_id amd_nb_link_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_LINK) },
+	{}
+};
+
 const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
 	{ 0x00, 0x18, 0x20 },
 	{ 0xff, 0x00, 0x20 },
@@ -45,7 +50,7 @@ int amd_cache_northbridges(void)
 {
 	int i = 0;
 	struct amd_northbridge *nb;
-	struct pci_dev *misc;
+	struct pci_dev *misc, *link;
 
 	if (amd_nb_num())
 		return 0;
@@ -64,10 +69,12 @@ int amd_cache_northbridges(void)
 	amd_northbridges.nb = nb;
 	amd_northbridges.num = i;
 
-	misc = NULL;
+	link = misc = NULL;
 	for (i = 0; i != amd_nb_num(); i++) {
 		node_to_amd_nb(i)->misc = misc =
 			next_northbridge(misc, amd_nb_misc_ids);
+		node_to_amd_nb(i)->link = link =
+			next_northbridge(link, amd_nb_link_ids);
         }
 
 	/* some CPU families (e.g. family 0x11) do not support GART */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 3adb06ebf841..580de67f318b 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -518,6 +518,7 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC	0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK	0x1304
 #define PCI_DEVICE_ID_AMD_15H_NB_MISC	0x1603
+#define PCI_DEVICE_ID_AMD_15H_NB_LINK	0x1604
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
-- 
cgit v1.2.3


From 4dd53d891ca46dcc1fde0376a33540d3fd83cb9a Mon Sep 17 00:00:00 2001
From: Venkatesh Pallipadi <venki@google.com>
Date: Tue, 21 Dec 2010 17:09:00 -0800
Subject: softirqs: Free up pf flag PF_KSOFTIRQD

Cleanup patch, freeing up PF_KSOFTIRQD and use per_cpu ksoftirqd pointer
instead, as suggested by Eric Dumazet.

Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-2-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/interrupt.h | 7 +++++++
 include/linux/sched.h     | 1 -
 kernel/sched.c            | 2 +-
 kernel/softirq.c          | 3 +--
 4 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 55e0d4253e49..a1382b9b5813 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -426,6 +426,13 @@ extern void raise_softirq(unsigned int nr);
  */
 DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
 
+DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
+
+static inline struct task_struct *this_cpu_ksoftirqd(void)
+{
+	return this_cpu_read(ksoftirqd);
+}
+
 /* Try to send a softirq to a remote cpu.  If this cannot be done, the
  * work will be queued to the local cpu.
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d747f948b34e..af6e15fbfb78 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1715,7 +1715,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_KSOFTIRQD	0x00000001	/* I am ksoftirqd */
 #define PF_STARTING	0x00000002	/* being created */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
diff --git a/kernel/sched.c b/kernel/sched.c
index 6820b5b3a969..8b89b3bba565 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1880,7 +1880,7 @@ void account_system_vtime(struct task_struct *curr)
 	 */
 	if (hardirq_count())
 		__this_cpu_add(cpu_hardirq_time, delta);
-	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
 		__this_cpu_add(cpu_softirq_time, delta);
 
 	irq_time_write_end();
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 68eb5efec388..0cee50487629 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_stat);
 
 static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
-static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
@@ -721,7 +721,6 @@ static int run_ksoftirqd(void * __bind_cpu)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	current->flags |= PF_KSOFTIRQD;
 	while (!kthread_should_stop()) {
 		preempt_disable();
 		if (!local_softirq_pending()) {
-- 
cgit v1.2.3


From a1dabb6bfffccb897eff3e1d102dacf2a4bedf3b Mon Sep 17 00:00:00 2001
From: Venkatesh Pallipadi <venki@google.com>
Date: Tue, 21 Dec 2010 17:09:01 -0800
Subject: time: Add nsecs_to_cputime64 interface for asm-generic

Add nsecs_to_cputime64 interface. This is used in following patches that
updates cpu irq stat based on ns granularity info in IRQ_TIME_ACCOUNTING.

Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-3-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-generic/cputime.h |  3 +++
 include/linux/jiffies.h       |  1 +
 kernel/time.c                 | 23 +++++++++++++++++++++--
 3 files changed, 25 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 2bcc5c7c22a6..61e03dd7939e 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -30,6 +30,9 @@ typedef u64 cputime64_t;
 #define cputime64_to_jiffies64(__ct)	(__ct)
 #define jiffies64_to_cputime64(__jif)	(__jif)
 #define cputime_to_cputime64(__ct)	((u64) __ct)
+#define cputime64_gt(__a, __b)		((__a) >  (__b))
+
+#define nsecs_to_cputime64(__ct)	nsecs_to_jiffies64(__ct)
 
 
 /*
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 6811f4bfc6e7..922aa313c9f9 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x);
 extern unsigned long clock_t_to_jiffies(unsigned long x);
 extern u64 jiffies_64_to_clock_t(u64 x);
 extern u64 nsec_to_clock_t(u64 x);
+extern u64 nsecs_to_jiffies64(u64 n);
 extern unsigned long nsecs_to_jiffies(u64 n);
 
 #define TIMESTAMP_SIZE	30
diff --git a/kernel/time.c b/kernel/time.c
index 32174359576f..55337a816b20 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -645,7 +645,7 @@ u64 nsec_to_clock_t(u64 x)
 }
 
 /**
- * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
  *
  * @n:	nsecs in u64
  *
@@ -657,7 +657,7 @@ u64 nsec_to_clock_t(u64 x)
  *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
  *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
  */
-unsigned long nsecs_to_jiffies(u64 n)
+u64 nsecs_to_jiffies64(u64 n)
 {
 #if (NSEC_PER_SEC % HZ) == 0
 	/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
@@ -674,6 +674,25 @@ unsigned long nsecs_to_jiffies(u64 n)
 #endif
 }
 
+
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n:	nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ *   NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ *   ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
+{
+	return (unsigned long)nsecs_to_jiffies64(n);
+}
+
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
-- 
cgit v1.2.3


From da7a735e51f9622eb3e1672594d4a41da01d7e4f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Mon, 17 Jan 2011 17:03:27 +0100
Subject: sched: Fix switch_from_fair()

When a task is taken out of the fair class we must ensure the vruntime
is properly normalized because when we put it back in it will assume
to be normalized.

The case that goes wrong is when changing away from the fair class
while sleeping. Sleeping tasks have non-normalized vruntime in order
to make sleeper-fairness work. So treat the switch away from fair as a
wakeup and preserve the relative vruntime.

Also update sysrq-n to call the ->switch_{to,from} methods.

Reported-by: Onkalo Samu <samu.p.onkalo@nokia.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h   |  8 +++-----
 kernel/sched.c          | 25 ++++++++++++++-----------
 kernel/sched_fair.c     | 42 ++++++++++++++++++++++++++++++++++++------
 kernel/sched_idletask.c |  7 +++----
 kernel/sched_rt.c       | 19 ++++++++++---------
 kernel/sched_stoptask.c |  7 +++----
 6 files changed, 69 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index af6e15fbfb78..0542774914d4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1084,12 +1084,10 @@ struct sched_class {
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork) (struct task_struct *p);
 
-	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
-			       int running);
-	void (*switched_to) (struct rq *this_rq, struct task_struct *task,
-			     int running);
+	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
+	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-			     int oldprio, int running);
+			     int oldprio);
 
 	unsigned int (*get_rr_interval) (struct rq *rq,
 					 struct task_struct *task);
diff --git a/kernel/sched.c b/kernel/sched.c
index 8b718b59b09f..78fa75394011 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2057,14 +2057,14 @@ inline int task_curr(const struct task_struct *p)
 
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 				       const struct sched_class *prev_class,
-				       int oldprio, int running)
+				       int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
-			prev_class->switched_from(rq, p, running);
-		p->sched_class->switched_to(rq, p, running);
-	} else
-		p->sched_class->prio_changed(rq, p, oldprio, running);
+			prev_class->switched_from(rq, p);
+		p->sched_class->switched_to(rq, p);
+	} else if (oldprio != p->prio)
+		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
 static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
@@ -2598,6 +2598,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
+	p->se.vruntime			= 0;
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -4696,11 +4697,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, &flags);
 }
 
@@ -5028,11 +5028,10 @@ recheck:
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		activate_task(rq, p, 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	__task_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -8237,6 +8236,8 @@ EXPORT_SYMBOL(__might_sleep);
 #ifdef CONFIG_MAGIC_SYSRQ
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
+	const struct sched_class *prev_class = p->sched_class;
+	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->se.on_rq;
@@ -8247,6 +8248,8 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 		activate_task(rq, p, 0);
 		resched_task(rq->curr);
 	}
+
+	check_class_changed(rq, p, prev_class, old_prio);
 }
 
 void normalize_rt_tasks(void)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4cbc9121094c..55040f3938d8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -4078,33 +4078,62 @@ static void task_fork_fair(struct task_struct *p)
  * Priority of the task has changed. Check to see if we preempt
  * the current task.
  */
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 {
+	if (!p->se.on_rq)
+		return;
+
 	/*
 	 * Reschedule if we are currently running on this runqueue and
 	 * our priority decreased, or if we are not currently running on
 	 * this runqueue and our priority is higher than the current's
 	 */
-	if (running) {
+	if (rq->curr == p) {
 		if (p->prio > oldprio)
 			resched_task(rq->curr);
 	} else
 		check_preempt_curr(rq, p, 0);
 }
 
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	/*
+	 * Ensure the task's vruntime is normalized, so that when its
+	 * switched back to the fair class the enqueue_entity(.flags=0) will
+	 * do the right thing.
+	 *
+	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * the task is sleeping will it still have non-normalized vruntime.
+	 */
+	if (!se->on_rq && p->state != TASK_RUNNING) {
+		/*
+		 * Fix up our vruntime so that the current sleep doesn't
+		 * cause 'unlimited' sleep bonus.
+		 */
+		place_entity(cfs_rq, se, 0);
+		se->vruntime -= cfs_rq->min_vruntime;
+	}
+}
+
 /*
  * We switched to the sched_fair class.
  */
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
+	if (!p->se.on_rq)
+		return;
+
 	/*
 	 * We were most likely switched from sched_rt, so
 	 * kick off the schedule if running, otherwise just see
 	 * if we can still preempt the current task.
 	 */
-	if (running)
+	if (rq->curr == p)
 		resched_task(rq->curr);
 	else
 		check_preempt_curr(rq, p, 0);
@@ -4190,6 +4219,7 @@ static const struct sched_class fair_sched_class = {
 	.task_fork		= task_fork_fair,
 
 	.prio_changed		= prio_changed_fair,
+	.switched_from		= switched_from_fair,
 	.switched_to		= switched_to_fair,
 
 	.get_rr_interval	= get_rr_interval_fair,
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 41eb62a0808b..c82f26c1b7c3 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -52,14 +52,13 @@ static void set_curr_task_idle(struct rq *rq)
 {
 }
 
-static void
-switched_to_idle(struct rq *rq, struct task_struct *p, int running)
+static void switched_to_idle(struct rq *rq, struct task_struct *p)
 {
 	BUG();
 }
 
-static void prio_changed_idle(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
 {
 	BUG();
 }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index c914ec747ca6..c381fdc18c64 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1595,8 +1595,7 @@ static void rq_offline_rt(struct rq *rq)
  * When switch from the rt queue, we bring ourselves to a position
  * that we might want to pull RT tasks from other runqueues.
  */
-static void switched_from_rt(struct rq *rq, struct task_struct *p,
-			   int running)
+static void switched_from_rt(struct rq *rq, struct task_struct *p)
 {
 	/*
 	 * If there are other RT tasks then we will reschedule
@@ -1605,7 +1604,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p,
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (!rq->rt.rt_nr_running)
+	if (p->se.on_rq && !rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
 
@@ -1624,8 +1623,7 @@ static inline void init_sched_rt_class(void)
  * with RT tasks. In this case we try to push them off to
  * other runqueues.
  */
-static void switched_to_rt(struct rq *rq, struct task_struct *p,
-			   int running)
+static void switched_to_rt(struct rq *rq, struct task_struct *p)
 {
 	int check_resched = 1;
 
@@ -1636,7 +1634,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (!running) {
+	if (p->se.on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->rt.overloaded && push_rt_task(rq) &&
 		    /* Don't resched if we changed runqueues */
@@ -1652,10 +1650,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
  * Priority of the task has changed. This may cause
  * us to initiate a push or pull.
  */
-static void prio_changed_rt(struct rq *rq, struct task_struct *p,
-			    int oldprio, int running)
+static void
+prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (running) {
+	if (!p->se.on_rq)
+		return;
+
+	if (rq->curr == p) {
 #ifdef CONFIG_SMP
 		/*
 		 * If our priority decreases while running, we
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 2bf6b47058c1..84ec9bcf82d9 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -59,14 +59,13 @@ static void set_curr_task_stop(struct rq *rq)
 {
 }
 
-static void switched_to_stop(struct rq *rq, struct task_struct *p,
-			     int running)
+static void switched_to_stop(struct rq *rq, struct task_struct *p)
 {
 	BUG(); /* its impossible to change to this class */
 }
 
-static void prio_changed_stop(struct rq *rq, struct task_struct *p,
-			      int oldprio, int running)
+static void
+prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
 {
 	BUG(); /* how!?, what priority? */
 }
-- 
cgit v1.2.3


From 1ea1bdf7faa4d0b5293e605f2e1ef1c2c59f6b53 Mon Sep 17 00:00:00 2001
From: Ari Kauppi <kauppi@papupata.org>
Date: Thu, 20 Jan 2011 13:57:18 -0500
Subject: oprofile: Fix usage of CONFIG_HW_PERF_EVENTS for oprofile_perf_init
 and friends

The implementations are flagged in Makefile with CONFIG_HW_PERF_EVENTS
instead of CONFIG_PERF_EVENTS.

Cc: stable@kernel.org # 37.x
Signed-off-by: Ari Kauppi <kauppi@papupata.org>
Signed-off-by: Robert Richter <robert.richter@amd.com>
---
 include/linux/oprofile.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 32fb81212fd1..54c83827f913 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -186,10 +186,10 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val);
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_HW_PERF_EVENTS
 int __init oprofile_perf_init(struct oprofile_operations *ops);
 void oprofile_perf_exit(void);
 char *op_name_from_perf_id(void);
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* OPROFILE_H */
-- 
cgit v1.2.3


From d14dd7e20d5e526557f5d3cfef4046a642f80924 Mon Sep 17 00:00:00 2001
From: Ari Kauppi <kauppi@papupata.org>
Date: Thu, 20 Jan 2011 13:57:19 -0500
Subject: ARM: oprofile: Fix backtraces in timer mode

Always allow backtraces when using oprofile on ARM, even if a PMU
isn't present. Restores functionality originally introduced in commit
1b7b56982fdcd9d85effd76f3928cf5d6eb26155 ("oprofile: Always allow
backtraces on ARM") by Richard Purdie.

It is not that obvious, but there is now only one oprofile_arch_init()
function. So the .backtrace callback is available also in timer mode.

Implemented by removing code and using stubs for oprofile_perf_{init,
exit} provided by <linux/oprofile.h>. This allows cleaning of other
architecture specific implementations too.

Cc: stable@kernel.org # 37.x
Signed-off-by: Ari Kauppi <kauppi@papupata.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>
---
 arch/arm/oprofile/common.c | 12 ++----------
 include/linux/oprofile.h   |  9 +++++++++
 2 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 8aa974491dfc..2b663918c464 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -10,8 +10,6 @@
  */
 
 #include <linux/cpumask.h>
-#include <linux/err.h>
-#include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/oprofile.h>
@@ -46,6 +44,7 @@ char *op_name_from_perf_id(void)
 		return NULL;
 	}
 }
+#endif
 
 static int report_trace(struct stackframe *frame, void *d)
 {
@@ -111,6 +110,7 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth)
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
+	/* provide backtrace support also in timer mode: */
 	ops->backtrace		= arm_backtrace;
 
 	return oprofile_perf_init(ops);
@@ -120,11 +120,3 @@ void __exit oprofile_arch_exit(void)
 {
 	oprofile_perf_exit();
 }
-#else
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
-	pr_info("oprofile: hardware counters not available\n");
-	return -ENODEV;
-}
-void __exit oprofile_arch_exit(void) {}
-#endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 54c83827f913..1ca64113efe8 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/printk.h>
 #include <asm/atomic.h>
  
 /* Each escaped entry is prefixed by ESCAPE_CODE
@@ -190,6 +192,13 @@ int oprofile_write_commit(struct op_entry *entry);
 int __init oprofile_perf_init(struct oprofile_operations *ops);
 void oprofile_perf_exit(void);
 char *op_name_from_perf_id(void);
+#else
+static inline int __init oprofile_perf_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
+}
+static inline void oprofile_perf_exit(void) { }
 #endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* OPROFILE_H */
-- 
cgit v1.2.3


From 62fa8a846d7de4b299232e330c74b7783539df76 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 26 Jan 2011 20:51:05 -0800
Subject: net: Implement read-only protection and COW'ing of metrics.

Routing metrics are now copy-on-write.

Initially a route entry points it's metrics at a read-only location.
If a routing table entry exists, it will point there.  Else it will
point at the all zero metric place-holder called 'dst_default_metrics'.

The writeability state of the metrics is stored in the low bits of the
metrics pointer, we have two bits left to spare if we want to store
more states.

For the initial implementation, COW is implemented simply via kmalloc.
However future enhancements will change this to place the writable
metrics somewhere else, in order to increase sharing.  Very likely
this "somewhere else" will be the inetpeer cache.

Note also that this means that metrics updates may transiently fail
if we cannot COW the metrics successfully.

But even by itself, this patch should decrease memory usage and
increase cache locality especially for routing workloads.  In those
cases the read-only metric copies stay in place and never get written
to.

TCP workloads where metrics get updated, and those rare cases where
PMTU triggers occur, will take a very slight performance hit.  But
that hit will be alleviated when the long-term writable metrics
move to a more sharable location.

Since the metrics storage went from a u32 array of RTAX_MAX entries to
what is essentially a pointer, some retooling of the dst_entry layout
was necessary.

Most importantly, we need to preserve the alignment of the reference
count so that it doesn't share cache lines with the read-mostly state,
as per Eric Dumazet's alignment assertion checks.

The only non-trivial bit here is the move of the 'flags' member into
the writeable cacheline.  This is OK since we are always accessing the
flags around the same moment when we made a modification to the
reference count.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h       | 114 ++++++++++++++++++++++++++++++++----------------
 include/net/dst_ops.h   |   1 +
 include/net/route.h     |   2 +
 net/core/dst.c          |  39 +++++++++++++++++
 net/decnet/dn_route.c   |  18 +++++---
 net/ipv4/route.c        |  45 ++++++++++++++++++-
 net/ipv4/xfrm4_policy.c |   4 ++
 net/ipv6/route.c        |  15 +++++--
 net/ipv6/xfrm6_policy.c |   2 +
 9 files changed, 194 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index be5a0d4c491d..94a8c234ea2a 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -40,24 +40,10 @@ struct dst_entry {
 	struct rcu_head		rcu_head;
 	struct dst_entry	*child;
 	struct net_device       *dev;
-	short			error;
-	short			obsolete;
-	int			flags;
-#define DST_HOST		0x0001
-#define DST_NOXFRM		0x0002
-#define DST_NOPOLICY		0x0004
-#define DST_NOHASH		0x0008
-#define DST_NOCACHE		0x0010
+	struct  dst_ops	        *ops;
+	unsigned long		_metrics;
 	unsigned long		expires;
-
-	unsigned short		header_len;	/* more space at head required */
-	unsigned short		trailer_len;	/* space to reserve at tail */
-
-	unsigned int		rate_tokens;
-	unsigned long		rate_last;	/* rate limiting for ICMP */
-
 	struct dst_entry	*path;
-
 	struct neighbour	*neighbour;
 	struct hh_cache		*hh;
 #ifdef CONFIG_XFRM
@@ -68,17 +54,16 @@ struct dst_entry {
 	int			(*input)(struct sk_buff*);
 	int			(*output)(struct sk_buff*);
 
-	struct  dst_ops	        *ops;
-
-	u32			_metrics[RTAX_MAX];
-
+	short			error;
+	short			obsolete;
+	unsigned short		header_len;	/* more space at head required */
+	unsigned short		trailer_len;	/* space to reserve at tail */
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			tclassid;
 #else
 	__u32			__pad2;
 #endif
 
-
 	/*
 	 * Align __refcnt to a 64 bytes alignment
 	 * (L1_CACHE_SIZE would be too much)
@@ -93,6 +78,14 @@ struct dst_entry {
 	atomic_t		__refcnt;	/* client references	*/
 	int			__use;
 	unsigned long		lastuse;
+	unsigned long		rate_last;	/* rate limiting for ICMP */
+	unsigned int		rate_tokens;
+	int			flags;
+#define DST_HOST		0x0001
+#define DST_NOXFRM		0x0002
+#define DST_NOPOLICY		0x0004
+#define DST_NOHASH		0x0008
+#define DST_NOCACHE		0x0010
 	union {
 		struct dst_entry	*next;
 		struct rtable __rcu	*rt_next;
@@ -103,10 +96,69 @@ struct dst_entry {
 
 #ifdef __KERNEL__
 
+extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
+
+#define DST_METRICS_READ_ONLY	0x1UL
+#define __DST_METRICS_PTR(Y)	\
+	((u32 *)((Y) & ~DST_METRICS_READ_ONLY))
+#define DST_METRICS_PTR(X)	__DST_METRICS_PTR((X)->_metrics)
+
+static inline bool dst_metrics_read_only(const struct dst_entry *dst)
+{
+	return dst->_metrics & DST_METRICS_READ_ONLY;
+}
+
+extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
+
+static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
+{
+	unsigned long val = dst->_metrics;
+	if (!(val & DST_METRICS_READ_ONLY))
+		__dst_destroy_metrics_generic(dst, val);
+}
+
+static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst)
+{
+	unsigned long p = dst->_metrics;
+
+	if (p & DST_METRICS_READ_ONLY)
+		return dst->ops->cow_metrics(dst, p);
+	return __DST_METRICS_PTR(p);
+}
+
+/* This may only be invoked before the entry has reached global
+ * visibility.
+ */
+static inline void dst_init_metrics(struct dst_entry *dst,
+				    const u32 *src_metrics,
+				    bool read_only)
+{
+	dst->_metrics = ((unsigned long) src_metrics) |
+		(read_only ? DST_METRICS_READ_ONLY : 0);
+}
+
+static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src)
+{
+	u32 *dst_metrics = dst_metrics_write_ptr(dest);
+
+	if (dst_metrics) {
+		u32 *src_metrics = DST_METRICS_PTR(src);
+
+		memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32));
+	}
+}
+
+static inline u32 *dst_metrics_ptr(struct dst_entry *dst)
+{
+	return DST_METRICS_PTR(dst);
+}
+
 static inline u32
 dst_metric_raw(const struct dst_entry *dst, const int metric)
 {
-	return dst->_metrics[metric-1];
+	u32 *p = DST_METRICS_PTR(dst);
+
+	return p[metric-1];
 }
 
 static inline u32
@@ -131,22 +183,10 @@ dst_metric_advmss(const struct dst_entry *dst)
 
 static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
 {
-	dst->_metrics[metric-1] = val;
-}
-
-static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics)
-{
-	memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32));
-}
+	u32 *p = dst_metrics_write_ptr(dst);
 
-static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src)
-{
-	dst_import_metrics(dest, src->_metrics);
-}
-
-static inline u32 *dst_metrics_ptr(struct dst_entry *dst)
-{
-	return dst->_metrics;
+	if (p)
+		p[metric-1] = val;
 }
 
 static inline u32
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 21a320b8708e..dc0746328947 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -18,6 +18,7 @@ struct dst_ops {
 	struct dst_entry *	(*check)(struct dst_entry *, __u32 cookie);
 	unsigned int		(*default_advmss)(const struct dst_entry *);
 	unsigned int		(*default_mtu)(const struct dst_entry *);
+	u32 *			(*cow_metrics)(struct dst_entry *, unsigned long);
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
 					  struct net_device *dev, int how);
diff --git a/include/net/route.h b/include/net/route.h
index 93e10c453f6b..5677cbf0c6e6 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -49,6 +49,7 @@
 
 struct fib_nh;
 struct inet_peer;
+struct fib_info;
 struct rtable {
 	struct dst_entry	dst;
 
@@ -69,6 +70,7 @@ struct rtable {
 	/* Miscellaneous cached information */
 	__be32			rt_spec_dst; /* RFC1122 specific destination */
 	struct inet_peer	*peer; /* long-living peer info */
+	struct fib_info		*fi; /* for client ref to shared metrics */
 };
 
 static inline bool rt_is_input_route(struct rtable *rt)
diff --git a/net/core/dst.c b/net/core/dst.c
index b99c7c7ffce2..578893505702 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -164,6 +164,8 @@ int dst_discard(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard);
 
+static const u32 dst_default_metrics[RTAX_MAX];
+
 void *dst_alloc(struct dst_ops *ops)
 {
 	struct dst_entry *dst;
@@ -180,6 +182,7 @@ void *dst_alloc(struct dst_ops *ops)
 	dst->lastuse = jiffies;
 	dst->path = dst;
 	dst->input = dst->output = dst_discard;
+	dst_init_metrics(dst, dst_default_metrics, true);
 #if RT_CACHE_DEBUG >= 2
 	atomic_inc(&dst_total);
 #endif
@@ -282,6 +285,42 @@ void dst_release(struct dst_entry *dst)
 }
 EXPORT_SYMBOL(dst_release);
 
+u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
+{
+	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+
+	if (p) {
+		u32 *old_p = __DST_METRICS_PTR(old);
+		unsigned long prev, new;
+
+		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+
+		new = (unsigned long) p;
+		prev = cmpxchg(&dst->_metrics, old, new);
+
+		if (prev != old) {
+			kfree(p);
+			p = __DST_METRICS_PTR(prev);
+			if (prev & DST_METRICS_READ_ONLY)
+				p = NULL;
+		}
+	}
+	return p;
+}
+EXPORT_SYMBOL(dst_cow_metrics_generic);
+
+/* Caller asserts that dst_metrics_read_only(dst) is false.  */
+void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
+{
+	unsigned long prev, new;
+
+	new = (unsigned long) dst_default_metrics;
+	prev = cmpxchg(&dst->_metrics, old, new);
+	if (prev == old)
+		kfree(__DST_METRICS_PTR(old));
+}
+EXPORT_SYMBOL(__dst_destroy_metrics_generic);
+
 /**
  * skb_dst_set_noref - sets skb dst, without a reference
  * @skb: buffer
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 5e636365d33c..42c9c62d3417 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -112,6 +112,7 @@ static int dn_dst_gc(struct dst_ops *ops);
 static struct dst_entry *dn_dst_check(struct dst_entry *, __u32);
 static unsigned int dn_dst_default_advmss(const struct dst_entry *dst);
 static unsigned int dn_dst_default_mtu(const struct dst_entry *dst);
+static void dn_dst_destroy(struct dst_entry *);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
 static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu);
@@ -133,11 +134,18 @@ static struct dst_ops dn_dst_ops = {
 	.check =		dn_dst_check,
 	.default_advmss =	dn_dst_default_advmss,
 	.default_mtu =		dn_dst_default_mtu,
+	.cow_metrics =		dst_cow_metrics_generic,
+	.destroy =		dn_dst_destroy,
 	.negative_advice =	dn_dst_negative_advice,
 	.link_failure =		dn_dst_link_failure,
 	.update_pmtu =		dn_dst_update_pmtu,
 };
 
+static void dn_dst_destroy(struct dst_entry *dst)
+{
+	dst_destroy_metrics_generic(dst);
+}
+
 static __inline__ unsigned dn_hash(__le16 src, __le16 dst)
 {
 	__u16 tmp = (__u16 __force)(src ^ dst);
@@ -814,14 +822,14 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res)
 {
 	struct dn_fib_info *fi = res->fi;
 	struct net_device *dev = rt->dst.dev;
+	unsigned int mss_metric;
 	struct neighbour *n;
-	unsigned int metric;
 
 	if (fi) {
 		if (DN_FIB_RES_GW(*res) &&
 		    DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
 			rt->rt_gateway = DN_FIB_RES_GW(*res);
-		dst_import_metrics(&rt->dst, fi->fib_metrics);
+		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
 	}
 	rt->rt_type = res->type;
 
@@ -834,10 +842,10 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res)
 
 	if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu)
 		dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu);
-	metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS);
-	if (metric) {
+	mss_metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS);
+	if (mss_metric) {
 		unsigned int mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst));
-		if (metric > mss)
+		if (mss_metric > mss)
 			dst_metric_set(&rt->dst, RTAX_ADVMSS, mss);
 	}
 	return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3e5b7cc2db4f..980030d4e4ae 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -152,6 +152,36 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 {
 }
 
+static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+
+	if (p) {
+		u32 *old_p = __DST_METRICS_PTR(old);
+		unsigned long prev, new;
+
+		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+
+		new = (unsigned long) p;
+		prev = cmpxchg(&dst->_metrics, old, new);
+
+		if (prev != old) {
+			kfree(p);
+			p = __DST_METRICS_PTR(prev);
+			if (prev & DST_METRICS_READ_ONLY)
+				p = NULL;
+		} else {
+			struct rtable *rt = (struct rtable *) dst;
+
+			if (rt->fi) {
+				fib_info_put(rt->fi);
+				rt->fi = NULL;
+			}
+		}
+	}
+	return p;
+}
+
 static struct dst_ops ipv4_dst_ops = {
 	.family =		AF_INET,
 	.protocol =		cpu_to_be16(ETH_P_IP),
@@ -159,6 +189,7 @@ static struct dst_ops ipv4_dst_ops = {
 	.check =		ipv4_dst_check,
 	.default_advmss =	ipv4_default_advmss,
 	.default_mtu =		ipv4_default_mtu,
+	.cow_metrics =		ipv4_cow_metrics,
 	.destroy =		ipv4_dst_destroy,
 	.ifdown =		ipv4_dst_ifdown,
 	.negative_advice =	ipv4_negative_advice,
@@ -1441,6 +1472,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 
 				if (rt->peer)
 					atomic_inc(&rt->peer->refcnt);
+				if (rt->fi)
+					atomic_inc(&rt->fi->fib_clntref);
 
 				if (arp_bind_neighbour(&rt->dst) ||
 				    !(rt->dst.neighbour->nud_state &
@@ -1720,6 +1753,11 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	struct rtable *rt = (struct rtable *) dst;
 	struct inet_peer *peer = rt->peer;
 
+	dst_destroy_metrics_generic(dst);
+	if (rt->fi) {
+		fib_info_put(rt->fi);
+		rt->fi = NULL;
+	}
 	if (peer) {
 		rt->peer = NULL;
 		inet_putpeer(peer);
@@ -1824,7 +1862,9 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 		if (FIB_RES_GW(*res) &&
 		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
 			rt->rt_gateway = FIB_RES_GW(*res);
-		dst_import_metrics(dst, fi->fib_metrics);
+		rt->fi = fi;
+		atomic_inc(&fi->fib_clntref);
+		dst_init_metrics(dst, fi->fib_metrics, true);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
 #endif
@@ -2752,6 +2792,9 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi
 		rt->peer = ort->peer;
 		if (rt->peer)
 			atomic_inc(&rt->peer->refcnt);
+		rt->fi = ort->fi;
+		if (rt->fi)
+			atomic_inc(&rt->fi->fib_clntref);
 
 		dst_free(new);
 	}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index b057d40addec..19fbdec6baaa 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -196,8 +196,11 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
+	dst_destroy_metrics_generic(dst);
+
 	if (likely(xdst->u.rt.peer))
 		inet_putpeer(xdst->u.rt.peer);
+
 	xfrm_dst_destroy(xdst);
 }
 
@@ -215,6 +218,7 @@ static struct dst_ops xfrm4_dst_ops = {
 	.protocol =		cpu_to_be16(ETH_P_IP),
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
+	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
 	.local_out =		__ip_local_out,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1534508f6c68..45fafa018f12 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -105,6 +105,7 @@ static struct dst_ops ip6_dst_ops_template = {
 	.check			=	ip6_dst_check,
 	.default_advmss		=	ip6_default_advmss,
 	.default_mtu		=	ip6_default_mtu,
+	.cow_metrics		=	dst_cow_metrics_generic,
 	.destroy		=	ip6_dst_destroy,
 	.ifdown			=	ip6_dst_ifdown,
 	.negative_advice	=	ip6_negative_advice,
@@ -125,6 +126,10 @@ static struct dst_ops ip6_dst_blackhole_ops = {
 	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
 };
 
+static const u32 ip6_template_metrics[RTAX_MAX] = {
+	[RTAX_HOPLIMIT - 1] = 255,
+};
+
 static struct rt6_info ip6_null_entry_template = {
 	.dst = {
 		.__refcnt	= ATOMIC_INIT(1),
@@ -193,6 +198,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		rt->rt6i_idev = NULL;
 		in6_dev_put(idev);
 	}
+	dst_destroy_metrics_generic(dst);
 	if (peer) {
 		BUG_ON(!(rt->rt6i_flags & RTF_CACHE));
 		rt->rt6i_peer = NULL;
@@ -2681,7 +2687,8 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_null_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_null_entry;
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-	dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255);
+	dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
+			 ip6_template_metrics, true);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
@@ -2692,7 +2699,8 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_prohibit_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
 	net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-	dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255);
+	dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
+			 ip6_template_metrics, true);
 
 	net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
 					       sizeof(*net->ipv6.ip6_blk_hole_entry),
@@ -2702,7 +2710,8 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_blk_hole_entry->dst.path =
 		(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
 	net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-	dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255);
+	dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
+			 ip6_template_metrics, true);
 #endif
 
 	net->ipv6.sysctl.flush_delay = 0;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index da87428681cc..834dc02f1d4f 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -220,6 +220,7 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
+	dst_destroy_metrics_generic(dst);
 	if (likely(xdst->u.rt6.rt6i_peer))
 		inet_putpeer(xdst->u.rt6.rt6i_peer);
 	xfrm_dst_destroy(xdst);
@@ -257,6 +258,7 @@ static struct dst_ops xfrm6_dst_ops = {
 	.protocol =		cpu_to_be16(ETH_P_IPV6),
 	.gc =			xfrm6_garbage_collect,
 	.update_pmtu =		xfrm6_update_pmtu,
+	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm6_dst_destroy,
 	.ifdown =		xfrm6_dst_ifdown,
 	.local_out =		__ip6_local_out,
-- 
cgit v1.2.3


From 92578c0b8078f6919f9b47e7e16a1cf770bd127b Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 23 Jan 2011 15:24:55 +0100
Subject: kthread: Replace deprecated spinlock initialization

SPIN_LOCK_UNLOCK is deprecated. Use the lockdep capable variant
instead.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/kthread.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index ce0775aa64c3..7ff16f7d3ed4 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -64,7 +64,7 @@ struct kthread_work {
 };
 
 #define KTHREAD_WORKER_INIT(worker)	{				\
-	.lock = SPIN_LOCK_UNLOCKED,					\
+	.lock = __SPIN_LOCK_UNLOCKED((worker).lock),			\
 	.work_list = LIST_HEAD_INIT((worker).work_list),		\
 	}
 
-- 
cgit v1.2.3


From d04fa5a3ba06c3b7a1c4a6860d0fa4825507a755 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 23 Jan 2011 15:30:09 +0100
Subject: locking: Remove deprecated lock initializers

Last users are gone. Remove the left overs.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/spinlocks.txt    | 24 +-----------------------
 include/linux/rwlock_types.h   |  8 --------
 include/linux/spinlock_types.h |  8 --------
 scripts/checkpatch.pl          |  5 -----
 4 files changed, 1 insertion(+), 44 deletions(-)

(limited to 'include')

diff --git a/Documentation/spinlocks.txt b/Documentation/spinlocks.txt
index 178c831b907d..2e3c64b1a6a5 100644
--- a/Documentation/spinlocks.txt
+++ b/Documentation/spinlocks.txt
@@ -86,7 +86,7 @@ to change the variables it has to get an exclusive write lock.
 
 The routines look the same as above:
 
-   rwlock_t xxx_lock = RW_LOCK_UNLOCKED;
+   rwlock_t xxx_lock = __RW_LOCK_UNLOCKED(xxx_lock);
 
 	unsigned long flags;
 
@@ -196,25 +196,3 @@ appropriate:
 
 For static initialization, use DEFINE_SPINLOCK() / DEFINE_RWLOCK() or
 __SPIN_LOCK_UNLOCKED() / __RW_LOCK_UNLOCKED() as appropriate.
-
-SPIN_LOCK_UNLOCKED and RW_LOCK_UNLOCKED are deprecated.  These interfere
-with lockdep state tracking.
-
-Most of the time, you can simply turn:
-	static spinlock_t xxx_lock = SPIN_LOCK_UNLOCKED;
-into:
-	static DEFINE_SPINLOCK(xxx_lock);
-
-Static structure member variables go from:
-
-	struct foo bar {
-		.lock	=	SPIN_LOCK_UNLOCKED;
-	};
-
-to:
-
-	struct foo bar {
-		.lock	=	__SPIN_LOCK_UNLOCKED(bar.lock);
-	};
-
-Declaration of static rw_locks undergo a similar transformation.
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index bd31808c7d8e..cc0072e93e36 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -43,14 +43,6 @@ typedef struct {
 				RW_DEP_MAP_INIT(lockname) }
 #endif
 
-/*
- * RW_LOCK_UNLOCKED defeat lockdep state tracking and is hence
- * deprecated.
- *
- * Please use DEFINE_RWLOCK() or __RW_LOCK_UNLOCKED() as appropriate.
- */
-#define RW_LOCK_UNLOCKED	__RW_LOCK_UNLOCKED(old_style_rw_init)
-
 #define DEFINE_RWLOCK(x)	rwlock_t x = __RW_LOCK_UNLOCKED(x)
 
 #endif /* __LINUX_RWLOCK_TYPES_H */
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 851b7783720d..73548eb13a5d 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -81,14 +81,6 @@ typedef struct spinlock {
 #define __SPIN_LOCK_UNLOCKED(lockname) \
 	(spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
 
-/*
- * SPIN_LOCK_UNLOCKED defeats lockdep state tracking and is hence
- * deprecated.
- * Please use DEFINE_SPINLOCK() or __SPIN_LOCK_UNLOCKED() as
- * appropriate.
- */
-#define SPIN_LOCK_UNLOCKED	__SPIN_LOCK_UNLOCKED(old_style_spin_init)
-
 #define DEFINE_SPINLOCK(x)	spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
 
 #include <linux/rwlock_types.h>
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4c0383da1c9a..58848e3e392c 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2654,11 +2654,6 @@ sub process {
 			WARN("Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr);
 		}
 
-# SPIN_LOCK_UNLOCKED & RW_LOCK_UNLOCKED are deprecated
-		if ($line =~ /\b(SPIN_LOCK_UNLOCKED|RW_LOCK_UNLOCKED)/) {
-			ERROR("Use of $1 is deprecated: see Documentation/spinlocks.txt\n" . $herecurr);
-		}
-
 # warn about #if 0
 		if ($line =~ /^.\s*\#\s*if\s+0\b/) {
 			CHK("if this code is redundant consider removing it\n" .
-- 
cgit v1.2.3


From c16a87ce063f79e0ec7d25ce2950e1bc6db03c72 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Jan 2011 20:05:50 +0000
Subject: rwsem: Cleanup includes

All rwsem implementations include the same headers. Include them from
include/linux/rwsem.h

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matt Turner <mattst88@gmail.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Acked-by: David Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
LKML-Reference: <20110126195833.483520950@linutronix.de>
---
 arch/alpha/include/asm/rwsem.h   | 4 ----
 arch/ia64/include/asm/rwsem.h    | 3 ---
 arch/powerpc/include/asm/rwsem.h | 5 -----
 arch/s390/include/asm/rwsem.h    | 5 -----
 arch/sh/include/asm/rwsem.h      | 5 -----
 arch/sparc/include/asm/rwsem.h   | 6 ------
 arch/x86/include/asm/rwsem.h     | 6 ------
 arch/xtensa/include/asm/rwsem.h  | 6 ------
 include/linux/rwsem-spinlock.h   | 8 --------
 include/linux/rwsem.h            | 3 +++
 10 files changed, 3 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 19c9cc7ed94b..839a3fa20944 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -13,10 +13,6 @@
 #ifdef __KERNEL__
 
 #include <linux/compiler.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
 
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 215d5454c7d3..9bcf0792b01c 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -25,9 +25,6 @@
 #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
 #endif
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
 #include <asm/intrinsics.h>
 
 /*
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 8447d89fbe72..c12abbe1d06f 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -13,11 +13,6 @@
  * by Paul Mackerras <paulus@samba.org>.
  */
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
 /*
  * the semaphore definition
  */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 423fdda2322d..9cc8592b33bb 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -43,11 +43,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index 06e2251a5e48..df6f34623c54 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -11,11 +11,6 @@
 #endif
 
 #ifdef __KERNEL__
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
 /*
  * the semaphore definition
  */
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index a2b4302869bc..902d36bf150d 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -12,12 +12,6 @@
 #endif
 
 #ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
 struct rw_semaphore {
 	signed long			count;
 #define RWSEM_UNLOCKED_VALUE		0x00000000L
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index d1e41b0f9b60..a626cff86041 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -37,14 +37,8 @@
 #endif
 
 #ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/lockdep.h>
 #include <asm/asm.h>
 
-struct rwsem_waiter;
-
 extern asmregparm struct rw_semaphore *
  rwsem_down_read_failed(struct rw_semaphore *sem);
 extern asmregparm struct rw_semaphore *
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index 9d32f6874393..1be2102c648e 100644
--- a/arch/xtensa/include/asm/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
@@ -16,12 +16,6 @@
 #ifndef _LINUX_RWSEM_H
 #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
 #endif
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
 /*
  * the semaphore definition
  */
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index bdfcc2527970..8c0dc7fc07a4 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -12,15 +12,7 @@
 #error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
 #endif
 
-#include <linux/spinlock.h>
-#include <linux/list.h>
-
 #ifdef __KERNEL__
-
-#include <linux/types.h>
-
-struct rwsem_waiter;
-
 /*
  * the rw-semaphore definition
  * - if activity is 0 then there are no active readers or writers
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index efd348fe8ca7..496296d12d62 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -11,6 +11,9 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
 #include <asm/system.h>
 #include <asm/atomic.h>
 
-- 
cgit v1.2.3


From 1c8ed640d918290ddc1de5ada02ef6686a733c9f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Jan 2011 20:05:56 +0000
Subject: rwsem: Move duplicate struct rwsem declaration to linux/rwsem.h

The difference between these declarations is the data type of the
count member and the lack of lockdep in some architectures/

long is equivivalent to signed long and the #ifdef guarded dep_map
member does not hurt anyone.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matt Turner <mattst88@gmail.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Acked-by: David Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
LKML-Reference: <20110126195833.679641914@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/alpha/include/asm/rwsem.h   |  8 --------
 arch/ia64/include/asm/rwsem.h    |  9 ---------
 arch/powerpc/include/asm/rwsem.h |  9 ---------
 arch/s390/include/asm/rwsem.h    | 12 ------------
 arch/sh/include/asm/rwsem.h      | 12 +-----------
 arch/sparc/include/asm/rwsem.h   |  9 +--------
 arch/x86/include/asm/rwsem.h     | 12 ------------
 arch/xtensa/include/asm/rwsem.h  |  9 +--------
 include/linux/rwsem.h            | 13 ++++++++++++-
 9 files changed, 15 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 839a3fa20944..3e5619ead29d 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -19,20 +19,12 @@ extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	long			count;
 #define RWSEM_UNLOCKED_VALUE		0x0000000000000000L
 #define RWSEM_ACTIVE_BIAS		0x0000000000000001L
 #define RWSEM_ACTIVE_MASK		0x00000000ffffffffL
 #define RWSEM_WAITING_BIAS		(-0x0000000100000000L)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-};
 
 #define __RWSEM_INITIALIZER(name) \
 	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock),	\
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 9bcf0792b01c..1fe465804dc7 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -27,15 +27,6 @@
 
 #include <asm/intrinsics.h>
 
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-};
-
 #define RWSEM_UNLOCKED_VALUE		__IA64_UL_CONST(0x0000000000000000)
 #define RWSEM_ACTIVE_BIAS		(1L)
 #define RWSEM_ACTIVE_MASK		(0xffffffffL)
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index c12abbe1d06f..bc1acc229223 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -28,15 +28,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-struct rw_semaphore {
-	long			count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
 #else
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 9cc8592b33bb..6e075f1d97b4 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -49,18 +49,6 @@ extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *);
 extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *);
 
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifndef __s390x__
 #define RWSEM_UNLOCKED_VALUE	0x00000000
 #define RWSEM_ACTIVE_BIAS	0x00000001
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index df6f34623c54..dffc62589f79 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -11,23 +11,13 @@
 #endif
 
 #ifdef __KERNEL__
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	long		count;
+
 #define RWSEM_UNLOCKED_VALUE		0x00000000
 #define RWSEM_ACTIVE_BIAS		0x00000001
 #define RWSEM_ACTIVE_MASK		0x0000ffff
 #define RWSEM_WAITING_BIAS		(-0x00010000)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index 902d36bf150d..4c16d1de2ab5 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -12,20 +12,13 @@
 #endif
 
 #ifdef __KERNEL__
-struct rw_semaphore {
-	signed long			count;
+
 #define RWSEM_UNLOCKED_VALUE		0x00000000L
 #define RWSEM_ACTIVE_BIAS		0x00000001L
 #define RWSEM_ACTIVE_MASK		0xffffffffL
 #define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t			wait_lock;
-	struct list_head		wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map		dep_map;
-#endif
-};
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index c30206c2bbf9..995cfe4c985d 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -49,8 +49,6 @@ extern asmregparm struct rw_semaphore *
  rwsem_downgrade_wake(struct rw_semaphore *sem);
 
 /*
- * the semaphore definition
- *
  * The bias values and the counter type limits the number of
  * potential readers/writers to 32767 for 32 bits and 2147483647
  * for 64 bits.
@@ -68,22 +66,12 @@ extern asmregparm struct rw_semaphore *
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-struct rw_semaphore {
-	long			count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-};
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
 #else
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-
 #define __RWSEM_INITIALIZER(name)				\
 {								\
 	RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index 1be2102c648e..585cab9b0bdf 100644
--- a/arch/xtensa/include/asm/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
@@ -16,20 +16,13 @@
 #ifndef _LINUX_RWSEM_H
 #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
 #endif
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
+
 #define RWSEM_UNLOCKED_VALUE		0x00000000
 #define RWSEM_ACTIVE_BIAS		0x00000001
 #define RWSEM_ACTIVE_MASK		0x0000ffff
 #define RWSEM_WAITING_BIAS		(-0x00010000)
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-};
 
 #define __RWSEM_INITIALIZER(name) \
 	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock),	\
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 496296d12d62..e8be18edb664 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -22,7 +22,18 @@ struct rw_semaphore;
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
 #include <linux/rwsem-spinlock.h> /* use a generic implementation */
 #else
-#include <asm/rwsem.h> /* use an arch-specific implementation */
+/* All arch specific implementations share the same struct */
+struct rw_semaphore {
+	long			count;
+	spinlock_t		wait_lock;
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+/* Include the arch specific part */
+#include <asm/rwsem.h>
 #endif
 
 /*
-- 
cgit v1.2.3


From 12249b34414dba7f386aadcf6be7ca36c6878300 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Jan 2011 20:06:00 +0000
Subject: rwsem: Move duplicate init macros and functions to linux/rwsem.h

The rwsem initializers and related macros and functions are mostly the
same. Some of them lack the lockdep initializer, but having it in
place does not matter for architectures which do not support lockdep.

powerpc, sparc, x86: No functional change

sh, s390: Removes the duplicate init_rwsem (inline and #define)

alpha, ia64, xtensa: Use the lockdep capable init function in
       	     	     lib/rwsem.c which is just uninlining the init
       	     	     function for the LOCKDEP=n case

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matt Turner <mattst88@gmail.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Acked-by: David Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
LKML-Reference: <20110126195833.771812729@linutronix.de>
---
 arch/alpha/include/asm/rwsem.h   | 14 --------------
 arch/ia64/include/asm/rwsem.h    | 15 ---------------
 arch/powerpc/include/asm/rwsem.h | 27 ---------------------------
 arch/s390/include/asm/rwsem.h    | 35 -----------------------------------
 arch/sh/include/asm/rwsem.h      | 31 -------------------------------
 arch/sparc/include/asm/rwsem.h   | 23 -----------------------
 arch/x86/include/asm/rwsem.h     | 25 -------------------------
 arch/xtensa/include/asm/rwsem.h  | 14 --------------
 include/linux/rwsem-spinlock.h   | 23 +----------------------
 include/linux/rwsem.h            | 25 +++++++++++++++++++++++++
 10 files changed, 26 insertions(+), 206 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 3e5619ead29d..c9f5b90e926e 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -26,20 +26,6 @@ extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock),	\
-	LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
 static inline void __down_read(struct rw_semaphore *sem)
 {
 	long oldcount;
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 1fe465804dc7..379854630e9d 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -34,26 +34,11 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-static inline void
-init_rwsem (struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
 /*
  * lock for reading
  */
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index bc1acc229223..f86fdf743afb 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -28,38 +28,11 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE,					\
-	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
-	LIST_HEAD_INIT((name).wait_list)			\
-	__RWSEM_DEP_MAP_INIT(name)				\
-}
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)					\
-	do {						\
-		static struct lock_class_key __key;	\
-							\
-		__init_rwsem((sem), #sem, &__key);	\
-	} while (0)
-
 /*
  * lock for reading
  */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 6e075f1d97b4..f0f527756ee1 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -63,41 +63,6 @@ extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *);
 #define RWSEM_ACTIVE_READ_BIAS	RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS	(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-/*
- * initialisation
- */
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait.lock), \
-   LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)				\
-do {						\
-	static struct lock_class_key __key;	\
-						\
-	__init_rwsem((sem), #sem, &__key);	\
-} while (0)
-
-
 /*
  * lock for reading
  */
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index dffc62589f79..798699d0687b 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -19,42 +19,11 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	  LIST_HEAD_INIT((name).wait_list) \
-	  __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)				\
-do {						\
-	static struct lock_class_key __key;	\
-						\
-	__init_rwsem((sem), #sem, &__key);	\
-} while (0)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
 /*
  * lock for reading
  */
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index 4c16d1de2ab5..79f7c1ca6f91 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -20,34 +20,11 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
-
 /*
  * lock for reading
  */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 995cfe4c985d..c0c91b4ecc81 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -66,31 +66,6 @@ extern asmregparm struct rw_semaphore *
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
-}
-
-#define DECLARE_RWSEM(name)					\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
-
 /*
  * lock for reading
  */
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index 585cab9b0bdf..2fa420212353 100644
--- a/arch/xtensa/include/asm/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
@@ -24,25 +24,11 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-#define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock),	\
-	  LIST_HEAD_INIT((name).wait_list) }
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
 /*
  * lock for reading
  */
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index 8c0dc7fc07a4..34701241b673 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -29,28 +29,7 @@ struct rw_semaphore {
 #endif
 };
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
-{ 0, __SPIN_LOCK_UNLOCKED(name.wait_lock), LIST_HEAD_INIT((name).wait_list) \
-  __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
+#define RWSEM_UNLOCKED_VALUE		0x00000000
 
 extern void __down_read(struct rw_semaphore *sem);
 extern int __down_read_trylock(struct rw_semaphore *sem);
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index e8be18edb664..8970c3e802e2 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -36,6 +36,31 @@ struct rw_semaphore {
 #include <asm/rwsem.h>
 #endif
 
+/* Common initializer macros and functions */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+#define __RWSEM_INITIALIZER(name) \
+	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED(name.wait_lock),	\
+	  LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+
+#define DECLARE_RWSEM(name) \
+	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+			 struct lock_class_key *key);
+
+#define init_rwsem(sem)						\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	__init_rwsem((sem), #sem, &__key);			\
+} while (0)
+
 /*
  * lock for reading
  */
-- 
cgit v1.2.3


From 41e5887fa39ab272d9266a09cbefdef270e28b93 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Jan 2011 20:06:03 +0000
Subject: rwsem: Unify the duplicate rwsem_is_locked() inlines

Instead of having the same implementation in each architecture, move
it to linux/rwsem.h and remove the duplicates. It's unlikely that an
arch will ever implement something different, but we can deal with
that when it happens.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matt Turner <mattst88@gmail.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Acked-by: David Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
LKML-Reference: <20110126195833.876773757@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/alpha/include/asm/rwsem.h   | 5 -----
 arch/ia64/include/asm/rwsem.h    | 5 -----
 arch/powerpc/include/asm/rwsem.h | 5 -----
 arch/s390/include/asm/rwsem.h    | 5 -----
 arch/sh/include/asm/rwsem.h      | 5 -----
 arch/sparc/include/asm/rwsem.h   | 5 -----
 arch/x86/include/asm/rwsem.h     | 5 -----
 arch/xtensa/include/asm/rwsem.h  | 5 -----
 include/linux/rwsem.h            | 7 +++++++
 9 files changed, 7 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index c9f5b90e926e..fc7f54337c3a 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -224,10 +224,5 @@ static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem)
 #endif
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ALPHA_RWSEM_H */
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 379854630e9d..148b61a96b8c 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -147,9 +147,4 @@ __downgrade_write (struct rw_semaphore *sem)
 #define rwsem_atomic_add(delta, sem)	atomic64_add(delta, (atomic64_t *)(&(sem)->count))
 #define rwsem_atomic_update(delta, sem)	atomic64_add_return(delta, (atomic64_t *)(&(sem)->count))
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* _ASM_IA64_RWSEM_H */
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index f86fdf743afb..38e8e5c508d5 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -133,10 +133,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return sem->count != 0;
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_RWSEM_H */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index f0f527756ee1..80522dcb6cc2 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -325,10 +325,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return new;
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _S390_RWSEM_H */
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index 798699d0687b..2f8cf9761eb5 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -133,10 +133,5 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
 	return atomic_add_return(delta, (atomic_t *)(&sem->count));
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_SH_RWSEM_H */
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index 79f7c1ca6f91..4f4391fd5658 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -124,11 +124,6 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return atomic64_add_return(delta, (atomic64_t *)(&sem->count));
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _SPARC64_RWSEM_H */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index c0c91b4ecc81..776d76fe2f90 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -222,10 +222,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return tmp + delta;
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index 2fa420212353..da61633ccba8 100644
--- a/arch/xtensa/include/asm/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
@@ -133,9 +133,4 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
 	return atomic_add_return(delta, (atomic_t *)(&sem->count));
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif	/* _XTENSA_RWSEM_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 8970c3e802e2..8b9c7e9f6910 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -34,6 +34,13 @@ struct rw_semaphore {
 
 /* Include the arch specific part */
 #include <asm/rwsem.h>
+
+/* In all implementations count != 0 means locked */
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return sem->count != 0;
+}
+
 #endif
 
 /* Common initializer macros and functions */
-- 
cgit v1.2.3


From aac72277fda6ef788bb8d5deaa502ce9b9b6e472 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Jan 2011 20:06:06 +0000
Subject: rwsem: Move duplicate function prototypes to linux/rwsem.h

All architecture specific rwsem headers carry the same function
prototypes. Just x86 adds asmregparm, which is an empty define on all
other architectures. S390 has a stale rwsem_downgrade_write()
prototype.

Remove the duplicates and add the prototypes to linux/rwsem.h

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Richard Henderson <rth@twiddle.net>
Acked-by: Tony Luck <tony.luck@intel.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Acked-by: David Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
LKML-Reference: <20110126195833.970840140@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/alpha/include/asm/rwsem.h   | 5 -----
 arch/ia64/include/asm/rwsem.h    | 5 -----
 arch/powerpc/include/asm/rwsem.h | 5 -----
 arch/s390/include/asm/rwsem.h    | 6 ------
 arch/sh/include/asm/rwsem.h      | 5 -----
 arch/sparc/include/asm/rwsem.h   | 5 -----
 arch/x86/include/asm/rwsem.h     | 9 ---------
 arch/xtensa/include/asm/rwsem.h  | 5 -----
 include/linux/rwsem.h            | 5 +++++
 9 files changed, 5 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index fc7f54337c3a..a83bbea62c67 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -14,11 +14,6 @@
 
 #include <linux/compiler.h>
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 #define RWSEM_UNLOCKED_VALUE		0x0000000000000000L
 #define RWSEM_ACTIVE_BIAS		0x0000000000000001L
 #define RWSEM_ACTIVE_MASK		0x00000000ffffffffL
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 148b61a96b8c..3027e7516d85 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -34,11 +34,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
  * lock for reading
  */
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 38e8e5c508d5..bb1e2cdeb9bf 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -28,11 +28,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
  * lock for reading
  */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 80522dcb6cc2..d0eb4653cebd 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -43,12 +43,6 @@
 
 #ifdef __KERNEL__
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *);
-
 #ifndef __s390x__
 #define RWSEM_UNLOCKED_VALUE	0x00000000
 #define RWSEM_ACTIVE_BIAS	0x00000001
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index 2f8cf9761eb5..edab57265293 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -19,11 +19,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
  * lock for reading
  */
diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h
index 4f4391fd5658..069bf4d663a1 100644
--- a/arch/sparc/include/asm/rwsem.h
+++ b/arch/sparc/include/asm/rwsem.h
@@ -20,11 +20,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
  * lock for reading
  */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 776d76fe2f90..df4cd32b4cc6 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -39,15 +39,6 @@
 #ifdef __KERNEL__
 #include <asm/asm.h>
 
-extern asmregparm struct rw_semaphore *
- rwsem_down_read_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_down_write_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_wake(struct rw_semaphore *);
-extern asmregparm struct rw_semaphore *
- rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
  * The bias values and the counter type limits the number of
  * potential readers/writers to 32767 for 32 bits and 2147483647
diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index da61633ccba8..249619e7e7f2 100644
--- a/arch/xtensa/include/asm/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
@@ -24,11 +24,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
 /*
  * lock for reading
  */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 8b9c7e9f6910..f7c957f3165f 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -32,6 +32,11 @@ struct rw_semaphore {
 #endif
 };
 
+extern asmregparm struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern asmregparm struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
+extern asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
 /* Include the arch specific part */
 #include <asm/rwsem.h>
 
-- 
cgit v1.2.3


From d123375425d7df4b6081a631fc1203fceafa59b2 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Jan 2011 21:32:01 +0100
Subject: rwsem: Remove redundant asmregparm annotation

Peter Zijlstra pointed out, that the only user of asmregparm (x86) is
compiling the kernel already with -mregparm=3. So the annotation of
the rwsem functions is redundant. Remove it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: David Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
LKML-Reference: <alpine.LFD.2.00.1101262130450.31804@localhost6.localdomain6>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/rwsem.h |  8 ++++----
 lib/rwsem.c           | 10 ++++------
 2 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index f7c957f3165f..a8afe9cd000c 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -32,10 +32,10 @@ struct rw_semaphore {
 #endif
 };
 
-extern asmregparm struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 
 /* Include the arch specific part */
 #include <asm/rwsem.h>
diff --git a/lib/rwsem.c b/lib/rwsem.c
index f236d7cd5cf3..aa7c3052261f 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -222,8 +222,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 /*
  * wait for the read lock to be granted
  */
-asmregparm struct rw_semaphore __sched *
-rwsem_down_read_failed(struct rw_semaphore *sem)
+struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 {
 	return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_READ,
 					-RWSEM_ACTIVE_READ_BIAS);
@@ -232,8 +231,7 @@ rwsem_down_read_failed(struct rw_semaphore *sem)
 /*
  * wait for the write lock to be granted
  */
-asmregparm struct rw_semaphore __sched *
-rwsem_down_write_failed(struct rw_semaphore *sem)
+struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 {
 	return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_WRITE,
 					-RWSEM_ACTIVE_WRITE_BIAS);
@@ -243,7 +241,7 @@ rwsem_down_write_failed(struct rw_semaphore *sem)
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
  */
-asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
+struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
@@ -263,7 +261,7 @@ asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
  * - caller incremented waiting part of count and discovered it still negative
  * - just wake up any readers at the front of the queue
  */
-asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
-- 
cgit v1.2.3


From 606598237c856b0c6584c2263288657658140da9 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 26 Jan 2011 20:55:53 -0800
Subject: inetpeer: Add metrics storage to inetpeer entries.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 599d96e74114..2af0c63d3975 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/jiffies.h>
 #include <linux/spinlock.h>
+#include <linux/rtnetlink.h>
 #include <net/ipv6.h>
 #include <asm/atomic.h>
 
@@ -33,8 +34,8 @@ struct inet_peer {
 	atomic_t		refcnt;
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp
-	 * We can share memory with rcu_head to keep inet_peer small
+	 * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp, metrics
+	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
@@ -42,6 +43,7 @@ struct inet_peer {
 			atomic_t	ip_id_count;	/* IP ID for the next packet */
 			__u32		tcp_ts;
 			__u32		tcp_ts_stamp;
+			u32		metrics[RTAX_MAX];
 		};
 		struct rcu_head         rcu;
 	};
-- 
cgit v1.2.3


From 144001bddcb4db62c2261f1d703d835851031577 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 27 Jan 2011 13:52:16 -0800
Subject: inetpeer: Mark metrics as "new" in fresh inetpeer entries.

Set the RTAX_LOCKED metric to INETPEER_METRICS_NEW (basically,
all ones) on fresh inetpeer entries.

This way code can determine if default metrics have been loaded
in from a routing table entry already.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 7 +++++++
 net/ipv4/inetpeer.c    | 1 +
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 2af0c63d3975..61f2c66edb2a 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -51,6 +51,13 @@ struct inet_peer {
 
 void			inet_initpeers(void) __init;
 
+#define INETPEER_METRICS_NEW	(~(u32) 0)
+
+static inline bool inet_metrics_new(const struct inet_peer *p)
+{
+	return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW;
+}
+
 /* can be called with or without local BH being disabled */
 struct inet_peer	*inet_getpeer(struct inetpeer_addr *daddr, int create);
 
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index a96e65674ac3..b6513b13d729 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -512,6 +512,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 		atomic_set(&p->rid, 0);
 		atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4));
 		p->tcp_ts_stamp = 0;
+		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		INIT_LIST_HEAD(&p->unused);
 
 
-- 
cgit v1.2.3


From ccf434380d1a67df2dcb9113206b77d0cb0a1cef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 26 Jan 2011 18:08:02 +0000
Subject: net: fix dev_seq_next()

Commit c6d14c84566d (net: Introduce for_each_netdev_rcu() iterator)
added a race in dev_seq_next().

The rcu_dereference() call should be done _before_ testing the end of
list, or we might return a wrong net_device if a concurrent thread
changes net_device list under us.

Note : discovered thanks to a sparse warning :

net/core/dev.c:3919:9: error: incompatible types in comparison expression
(different address spaces)

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  9 ++++++++-
 net/core/dev.c            | 11 +++++++----
 2 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8858422c5c5d..c7d707452228 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1447,7 +1447,7 @@ static inline struct net_device *next_net_device_rcu(struct net_device *dev)
 	struct net *net;
 
 	net = dev_net(dev);
-	lh = rcu_dereference(dev->dev_list.next);
+	lh = rcu_dereference(list_next_rcu(&dev->dev_list));
 	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
 }
 
@@ -1457,6 +1457,13 @@ static inline struct net_device *first_net_device(struct net *net)
 		net_device_entry(net->dev_base_head.next);
 }
 
+static inline struct net_device *first_net_device_rcu(struct net *net)
+{
+	struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head));
+
+	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
+}
+
 extern int 			netdev_boot_setup_check(struct net_device *dev);
 extern unsigned long		netdev_boot_base(const char *prefix, int unit);
 extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
diff --git a/net/core/dev.c b/net/core/dev.c
index 1b4c07fe295f..ddd5df2b61d4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4051,12 +4051,15 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos)
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct net_device *dev = (v == SEQ_START_TOKEN) ?
-				  first_net_device(seq_file_net(seq)) :
-				  next_net_device((struct net_device *)v);
+	struct net_device *dev = v;
+
+	if (v == SEQ_START_TOKEN)
+		dev = first_net_device_rcu(seq_file_net(seq));
+	else
+		dev = next_net_device_rcu(dev);
 
 	++*pos;
-	return rcu_dereference(dev);
+	return dev;
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
-- 
cgit v1.2.3


From a4daad6b0923030fbd3b00a01f570e4c3eef446b Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 27 Jan 2011 22:01:53 -0800
Subject: net: Pre-COW metrics for TCP.

TCP is going to record metrics for the connection,
so pre-COW the route metrics at route cache entry
creation time.

This avoids several atomic operations that have to
occur if we COW the metrics after the entry reaches
global visibility.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h      |  3 ++-
 include/net/inet_sock.h |  8 +++++++-
 include/net/route.h     |  4 ++++
 net/ipv4/route.c        | 26 +++++++++++++++++++++++---
 4 files changed, 36 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 240b7f356c71..1ae901f24436 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -48,7 +48,8 @@ struct flowi {
 
 	__u8	proto;
 	__u8	flags;
-#define FLOWI_FLAG_ANYSRC 0x01
+#define FLOWI_FLAG_ANYSRC		0x01
+#define FLOWI_FLAG_PRECOW_METRICS	0x02
 	union {
 		struct {
 			__be16	sport;
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 8181498fa96c..6e6dfd757682 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -219,7 +219,13 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops
 
 static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
 {
-	return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0;
+	__u8 flags = 0;
+
+	if (inet_sk(sk)->transparent)
+		flags |= FLOWI_FLAG_ANYSRC;
+	if (sk->sk_protocol == IPPROTO_TCP)
+		flags |= FLOWI_FLAG_PRECOW_METRICS;
+	return flags;
 }
 
 #endif	/* _INET_SOCK_H */
diff --git a/include/net/route.h b/include/net/route.h
index 5677cbf0c6e6..e5864658dc76 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -182,6 +182,8 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 
 	if (inet_sk(sk)->transparent)
 		fl.flags |= FLOWI_FLAG_ANYSRC;
+	if (protocol == IPPROTO_TCP)
+		fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
 
 	if (!dst || !src) {
 		err = __ip_route_output_key(net, rp, &fl);
@@ -209,6 +211,8 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol,
 		fl.proto = protocol;
 		if (inet_sk(sk)->transparent)
 			fl.flags |= FLOWI_FLAG_ANYSRC;
+		if (protocol == IPPROTO_TCP)
+			fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
 		ip_rt_put(*rp);
 		*rp = NULL;
 		security_sk_classify_flow(sk, &fl);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 68cee358d9a3..dd57f4896736 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1857,6 +1857,28 @@ static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
 	return mtu;
 }
 
+static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
+{
+	if (!(rt->fl.flags & FLOWI_FLAG_PRECOW_METRICS)) {
+	no_cow:
+		rt->fi = fi;
+		atomic_inc(&fi->fib_clntref);
+		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+	} else {
+		struct inet_peer *peer;
+
+		if (!rt->peer)
+			rt_bind_peer(rt, 1);
+		peer = rt->peer;
+		if (!peer)
+			goto no_cow;
+		if (inet_metrics_new(peer))
+			memcpy(peer->metrics, fi->fib_metrics,
+			       sizeof(u32) * RTAX_MAX);
+		dst_init_metrics(&rt->dst, peer->metrics, false);
+	}
+}
+
 static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 {
 	struct dst_entry *dst = &rt->dst;
@@ -1866,9 +1888,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 		if (FIB_RES_GW(*res) &&
 		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
 			rt->rt_gateway = FIB_RES_GW(*res);
-		rt->fi = fi;
-		atomic_inc(&fi->fib_clntref);
-		dst_init_metrics(dst, fi->fib_metrics, true);
+		rt_init_metrics(rt, fi);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
 #endif
-- 
cgit v1.2.3


From 6d744bacee8195c915c514409a81d470ce7b1177 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 27 Jan 2011 14:13:17 +0100
Subject: mac80211: add MCS information to radiotap

This adds the MCS information we currently get
from the drivers into radiotap.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/ieee80211_radiotap.h | 25 +++++++++++++++++++++++++
 net/mac80211/rx.c                | 17 +++++++++++++++++
 2 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index af49f8ab7f81..b0be5fb9de19 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -178,6 +178,11 @@ struct ieee80211_radiotap_header {
  *
  *     Number of unicast retries a transmitted frame used.
  *
+ * IEEE80211_RADIOTAP_MCS	u8, u8, u8		unitless
+ *
+ *     Contains a bitmap of known fields/flags, the flags, and
+ *     the MCS index.
+ *
  */
 enum ieee80211_radiotap_type {
 	IEEE80211_RADIOTAP_TSFT = 0,
@@ -199,6 +204,8 @@ enum ieee80211_radiotap_type {
 	IEEE80211_RADIOTAP_RTS_RETRIES = 16,
 	IEEE80211_RADIOTAP_DATA_RETRIES = 17,
 
+	IEEE80211_RADIOTAP_MCS = 19,
+
 	/* valid in every it_present bitmap, even vendor namespaces */
 	IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29,
 	IEEE80211_RADIOTAP_VENDOR_NAMESPACE = 30,
@@ -245,6 +252,24 @@ enum ieee80211_radiotap_type {
 #define IEEE80211_RADIOTAP_F_TX_CTS	0x0002	/* used cts 'protection' */
 #define IEEE80211_RADIOTAP_F_TX_RTS	0x0004	/* used rts/cts handshake */
 
+
+/* For IEEE80211_RADIOTAP_MCS */
+#define IEEE80211_RADIOTAP_MCS_HAVE_BW		0x01
+#define IEEE80211_RADIOTAP_MCS_HAVE_MCS		0x02
+#define IEEE80211_RADIOTAP_MCS_HAVE_GI		0x04
+#define IEEE80211_RADIOTAP_MCS_HAVE_FMT		0x08
+#define IEEE80211_RADIOTAP_MCS_HAVE_FEC		0x10
+
+#define IEEE80211_RADIOTAP_MCS_BW_MASK		0x03
+#define		IEEE80211_RADIOTAP_MCS_BW_20	0
+#define		IEEE80211_RADIOTAP_MCS_BW_40	1
+#define		IEEE80211_RADIOTAP_MCS_BW_20L	2
+#define		IEEE80211_RADIOTAP_MCS_BW_20U	3
+#define IEEE80211_RADIOTAP_MCS_SGI		0x04
+#define IEEE80211_RADIOTAP_MCS_FMT_GF		0x08
+#define IEEE80211_RADIOTAP_MCS_FEC_LDPC		0x10
+
+
 /* Ugly macro to convert literal channel numbers into their mhz equivalents
  * There are certianly some conditions that will break this (like feeding it '30')
  * but they shouldn't arise since nothing talks on channel 30. */
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index f36d70f5b062..7185c9316be2 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -85,6 +85,9 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local,
 	if (len & 1) /* padding for RX_FLAGS if necessary */
 		len++;
 
+	if (status->flag & RX_FLAG_HT) /* HT info */
+		len += 3;
+
 	return len;
 }
 
@@ -193,6 +196,20 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		rx_flags |= IEEE80211_RADIOTAP_F_RX_BADPLCP;
 	put_unaligned_le16(rx_flags, pos);
 	pos += 2;
+
+	if (status->flag & RX_FLAG_HT) {
+		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS);
+		*pos++ = IEEE80211_RADIOTAP_MCS_HAVE_MCS |
+			 IEEE80211_RADIOTAP_MCS_HAVE_GI |
+			 IEEE80211_RADIOTAP_MCS_HAVE_BW;
+		*pos = 0;
+		if (status->flag & RX_FLAG_SHORT_GI)
+			*pos |= IEEE80211_RADIOTAP_MCS_SGI;
+		if (status->flag & RX_FLAG_40MHZ)
+			*pos |= IEEE80211_RADIOTAP_MCS_BW_40;
+		pos++;
+		*pos++ = status->rate_idx;
+	}
 }
 
 /*
-- 
cgit v1.2.3


From 9c150e82ac50a611237bbebd508d17f6347d577c Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 28 Jan 2011 14:01:25 -0800
Subject: ipv4: Allocate fib metrics dynamically.

This is the initial gateway towards super-sharing metrics
if they are all set to zero for a route.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 2 +-
 net/ipv4/fib_semantics.c | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 65d1fcdbc63b..2c0508a6e07c 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -77,7 +77,7 @@ struct fib_info {
 	int			fib_protocol;
 	__be32			fib_prefsrc;
 	u32			fib_priority;
-	u32			fib_metrics[RTAX_MAX];
+	u32			*fib_metrics;
 #define fib_mtu fib_metrics[RTAX_MTU-1]
 #define fib_window fib_metrics[RTAX_WINDOW-1]
 #define fib_rtt fib_metrics[RTAX_RTT-1]
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 9aff11d7278f..363ec39228d3 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -152,6 +152,7 @@ static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
 
+	kfree(fi->fib_metrics);
 	kfree(fi);
 }
 
@@ -742,6 +743,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+	if (!fi->fib_metrics)
+		goto failure;
 	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
-- 
cgit v1.2.3


From 725d1e1b457dc2bbebb337677e73efe7c6d14da5 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 28 Jan 2011 14:05:05 -0800
Subject: ipv4: Attach FIB info to dst_default_metrics when possible

If there are no explicit metrics attached to a route, hook
fi->fib_info up to dst_default_metrics.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h        |  1 +
 net/core/dst.c           |  2 +-
 net/ipv4/fib_semantics.c | 12 ++++++++----
 3 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 94a8c234ea2a..484f80b69ada 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -97,6 +97,7 @@ struct dst_entry {
 #ifdef __KERNEL__
 
 extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
+extern const u32 dst_default_metrics[RTAX_MAX];
 
 #define DST_METRICS_READ_ONLY	0x1UL
 #define __DST_METRICS_PTR(Y)	\
diff --git a/net/core/dst.c b/net/core/dst.c
index 578893505702..c1674fde827d 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -164,7 +164,7 @@ int dst_discard(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard);
 
-static const u32 dst_default_metrics[RTAX_MAX];
+const u32 dst_default_metrics[RTAX_MAX];
 
 void *dst_alloc(struct dst_ops *ops)
 {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 363ec39228d3..48e93a560077 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -152,7 +152,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
 
-	kfree(fi->fib_metrics);
+	if (fi->fib_metrics != (u32 *) dst_default_metrics)
+		kfree(fi->fib_metrics);
 	kfree(fi);
 }
 
@@ -743,9 +744,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
-	fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
-	if (!fi->fib_metrics)
-		goto failure;
+	if (cfg->fc_mx) {
+		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+		if (!fi->fib_metrics)
+			goto failure;
+	} else
+		fi->fib_metrics = (u32 *) dst_default_metrics;
 	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
-- 
cgit v1.2.3


From 871cf1e5f2a17702f58539a3af8b18fc8666ad4c Mon Sep 17 00:00:00 2001
From: Torben Hohn <torbenh@gmx.de>
Date: Thu, 27 Jan 2011 15:58:55 +0100
Subject: time: Move do_timer() to kernel/time/timekeeping.c

do_timer() is primary timekeeping related. calc_global_load() is
called from do_timer() as well, but that's more for historical
reasons.

[ tglx: Fixed up the calc_global_load() reject andmassaged changelog ]

Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145855.23248.56933.stgit@localhost>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/time.h      |  1 -
 kernel/time/timekeeping.c | 14 +++++++++++++-
 kernel/timer.c            | 13 -------------
 3 files changed, 13 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index 1e6d3b59238d..86a9c487fdd8 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -166,7 +166,6 @@ extern void monotonic_to_bootbased(struct timespec *ts);
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
-extern void update_wall_time(void);
 extern void timekeeping_leap_insert(int leapsecond);
 
 struct tms;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d27c7562902c..c1a178ca0f50 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -779,7 +779,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
  *
  * Called from the timer interrupt, must hold a write on xtime_lock.
  */
-void update_wall_time(void)
+static void update_wall_time(void)
 {
 	struct clocksource *clock;
 	cycle_t offset;
@@ -946,3 +946,15 @@ struct timespec get_monotonic_coarse(void)
 				now.tv_nsec + mono.tv_nsec);
 	return now;
 }
+
+/*
+ * The 64-bit jiffies value is not atomic - you MUST NOT read it
+ * without sampling the sequence number in xtime_lock.
+ * jiffies is defined in the linker script...
+ */
+void do_timer(unsigned long ticks)
+{
+	jiffies_64 += ticks;
+	update_wall_time();
+	calc_global_load(ticks);
+}
diff --git a/kernel/timer.c b/kernel/timer.c
index 43ca9936f2d0..87f656cc2a55 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1293,19 +1293,6 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
-/*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
- */
-
-void do_timer(unsigned long ticks)
-{
-	jiffies_64 += ticks;
-	update_wall_time();
-	calc_global_load(ticks);
-}
-
 #ifdef __ARCH_WANT_SYS_ALARM
 
 /*
-- 
cgit v1.2.3


From 48cf76f7104f655bbd48a75c7759dce82c3e1ab6 Mon Sep 17 00:00:00 2001
From: Torben Hohn <torbenh@gmx.de>
Date: Thu, 27 Jan 2011 15:59:05 +0100
Subject: time: Provide get_xtime_and_monotonic_offset()

The hrtimer code accesses timekeeping variables under
xtime_lock. Provide a sensible accessor function and use it.

[ tglx: Removed the conditionals, unused variable, fixed codingstyle
  	and massaged changelog ]

Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145905.23248.30458.stgit@localhost>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/time.h      |  1 +
 kernel/hrtimer.c          | 13 ++-----------
 kernel/time/timekeeping.c | 16 ++++++++++++++++
 3 files changed, 19 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index 86a9c487fdd8..4007a12a1b50 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -127,6 +127,7 @@ struct timespec current_kernel_time(void);
 struct timespec __current_kernel_time(void); /* does not take xtime_lock */
 struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */
 struct timespec get_monotonic_coarse(void);
+void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom);
 
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c048615..57c4d33c9a9d 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -85,13 +85,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
 	ktime_t xtim, tomono;
 	struct timespec xts, tom;
-	unsigned long seq;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		xts = __current_kernel_time();
-		tom = __get_wall_to_monotonic();
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_offset(&xts, &tom);
 
 	xtim = timespec_to_ktime(xts);
 	tomono = timespec_to_ktime(tom);
@@ -612,15 +607,11 @@ static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base;
 	struct timespec realtime_offset, wtm;
-	unsigned long seq;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		wtm = __get_wall_to_monotonic();
-	} while (read_seqretry(&xtime_lock, seq));
+	get_xtime_and_monotonic_offset(&realtime_offset, &wtm);
 	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
 
 	base = &__get_cpu_var(hrtimer_bases);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c1a178ca0f50..c50aaf6cd01d 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -958,3 +958,19 @@ void do_timer(unsigned long ticks)
 	update_wall_time();
 	calc_global_load(ticks);
 }
+
+/**
+ * get_xtime_and_monotonic_offset() - get xtime and wall_to_monotonic
+ * @xtim:	pointer to timespec to be set with xtime
+ * @wtom:	pointer to timespec to be set with wall_to_monotonic
+ */
+void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom)
+{
+	unsigned long seq;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*xtim = xtime;
+		*wtom = wall_to_monotonic;
+	} while (read_seqretry(&xtime_lock, seq));
+}
-- 
cgit v1.2.3


From 79ecaf0d15344d78904becf0f25de3fc9b49d430 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 31 Jan 2011 11:07:54 +0100
Subject: time: Remove unused __get_wall_to_monotonic()

No users left. Remove it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/time.h      | 1 -
 kernel/time/timekeeping.c | 5 -----
 2 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index 4007a12a1b50..ce29c86882b1 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -125,7 +125,6 @@ extern int timekeeping_suspended;
 unsigned long get_seconds(void);
 struct timespec current_kernel_time(void);
 struct timespec __current_kernel_time(void); /* does not take xtime_lock */
-struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */
 struct timespec get_monotonic_coarse(void);
 void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom);
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c50aaf6cd01d..8da35d1b9e16 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -910,11 +910,6 @@ struct timespec __current_kernel_time(void)
 	return xtime;
 }
 
-struct timespec __get_wall_to_monotonic(void)
-{
-	return wall_to_monotonic;
-}
-
 struct timespec current_kernel_time(void)
 {
 	struct timespec now;
-- 
cgit v1.2.3


From f0af911a9dec9de702645182c8d269449e24d24b Mon Sep 17 00:00:00 2001
From: Torben Hohn <torbenh@gmx.de>
Date: Thu, 27 Jan 2011 15:59:10 +0100
Subject: time: Provide xtime_update()

xtime_update() takes xtime_lock write locked and calls
do_timer(). Provided to replace the do_timer() calls in the
architecture code.

Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145910.23248.21379.stgit@localhost>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/sched.h     |  1 +
 kernel/time/timekeeping.c | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d747f948b34e..9d9a0787eed3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2050,6 +2050,7 @@ extern void release_uids(struct user_namespace *ns);
 #include <asm/current.h>
 
 extern void do_timer(unsigned long ticks);
+extern void xtime_update(unsigned long ticks);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 8da35d1b9e16..02c13a313d15 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -969,3 +969,16 @@ void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom
 		*wtom = wall_to_monotonic;
 	} while (read_seqretry(&xtime_lock, seq));
 }
+
+/**
+ * xtime_update() - advances the timekeeping infrastructure
+ * @ticks:	number of ticks, that have elapsed since the last call.
+ *
+ * Must be called with interrupts disabled.
+ */
+void xtime_update(unsigned long ticks)
+{
+	write_seqlock(&xtime_lock);
+	do_timer(ticks);
+	write_sequnlock(&xtime_lock);
+}
-- 
cgit v1.2.3


From e2830b5c1b2b2217894370a3b95af87d4a958401 Mon Sep 17 00:00:00 2001
From: Torben Hohn <torbenh@gmx.de>
Date: Thu, 27 Jan 2011 16:00:32 +0100
Subject: time: Make do_timer() and xtime_lock local to kernel/time/

All callers of do_timer() are converted to xtime_update(). The only
users of xtime_lock are in kernel/time/. Make both local to
kernel/time/ and remove them from the global header files.

[ tglx: Reuse tick-internal.h instead of creating another local header
  	file. Massaged changelog ]

Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/sched.h        | 1 -
 include/linux/time.h         | 2 --
 kernel/time/clockevents.c    | 1 -
 kernel/time/jiffies.c        | 2 ++
 kernel/time/ntp.c            | 2 ++
 kernel/time/tick-broadcast.c | 1 -
 kernel/time/tick-common.c    | 1 -
 kernel/time/tick-internal.h  | 5 +++++
 kernel/time/tick-oneshot.c   | 1 -
 kernel/time/tick-sched.c     | 1 -
 10 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9d9a0787eed3..cdef640aa446 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2049,7 +2049,6 @@ extern void release_uids(struct user_namespace *ns);
 
 #include <asm/current.h>
 
-extern void do_timer(unsigned long ticks);
 extern void xtime_update(unsigned long ticks);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
diff --git a/include/linux/time.h b/include/linux/time.h
index ce29c86882b1..38c5206c2673 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -113,8 +113,6 @@ static inline struct timespec timespec_sub(struct timespec lhs,
 #define timespec_valid(ts) \
 	(((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC))
 
-extern seqlock_t xtime_lock;
-
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_boot_clock(struct timespec *ts);
 extern int update_persistent_clock(struct timespec now);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index d7395fdfb9f3..0d74b9ba90c8 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -18,7 +18,6 @@
 #include <linux/notifier.h>
 #include <linux/smp.h>
 #include <linux/sysdev.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 2fbc20744797..b2fa506667c0 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -25,6 +25,8 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
+#include "tick-internal.h"
+
 /* The Jiffies based clocksource is the lowest common
  * denominator clock source which should function on
  * all systems. It has the same coarse resolution as
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5c00242fa921..ed8cfdf16983 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -16,6 +16,8 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 
+#include "tick-internal.h"
+
 /*
  * NTP timekeeping variables:
  */
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 48b2761b5668..92ef9a54f0a4 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 051bc80a0c43..0e98fac3d479 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include <asm/irq_regs.h>
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 290eefbc1f60..28c578568c9d 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,8 @@
 /*
  * tick internal variable and functions used by low/high res code
  */
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
 
 #define TICK_DO_TIMER_NONE	-1
 #define TICK_DO_TIMER_BOOT	-2
@@ -132,3 +134,6 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 {
 	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
+
+extern void do_timer(unsigned long ticks);
+extern seqlock_t xtime_lock;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 5cbc101f908b..2d04411a5f05 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -18,7 +18,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c55ea2433471..d5097c44b407 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -19,7 +19,6 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <linux/tick.h>
 #include <linux/module.h>
 
 #include <asm/irq_regs.h>
-- 
cgit v1.2.3


From a6238f21736af3f47bdebf3895f477f5f23f1af9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Jan 2011 23:17:27 +0100
Subject: appletalk: move to staging

For all I know, Appletalk is dead, the only reasonable
use right now would be nostalgia, and that can be served
well enough by old kernels. The code is largely not
in a bad shape, but it still uses the big kernel lock,
and nobody seems motivated to change that.

FWIW, the last release of MacOS that supported Appletalk
was MacOS X 10.5, made in 2007, and it has been abandoned
by Apple with 10.6. Using TCP/IP instead of Appletalk has
been supported since MacOS 7.6, which was released in
1997 and is able to run on most of the legacy hardware.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 MAINTAINERS                                  |    3 +-
 drivers/net/Makefile                         |    1 -
 drivers/net/appletalk/Kconfig                |  126 --
 drivers/net/appletalk/Makefile               |    7 -
 drivers/net/appletalk/cops.c                 | 1013 -------------
 drivers/net/appletalk/cops.h                 |   60 -
 drivers/net/appletalk/cops_ffdrv.h           |  532 -------
 drivers/net/appletalk/cops_ltdrv.h           |  241 ----
 drivers/net/appletalk/ipddp.c                |  335 -----
 drivers/net/appletalk/ipddp.h                |   27 -
 drivers/net/appletalk/ltpc.c                 | 1288 -----------------
 drivers/net/appletalk/ltpc.h                 |   73 -
 drivers/staging/Kconfig                      |    2 +
 drivers/staging/Makefile                     |    1 +
 drivers/staging/appletalk/Kconfig            |  126 ++
 drivers/staging/appletalk/Makefile           |   12 +
 drivers/staging/appletalk/aarp.c             | 1063 ++++++++++++++
 drivers/staging/appletalk/atalk.h            |  208 +++
 drivers/staging/appletalk/atalk_proc.c       |  301 ++++
 drivers/staging/appletalk/cops.c             | 1013 +++++++++++++
 drivers/staging/appletalk/cops.h             |   60 +
 drivers/staging/appletalk/cops_ffdrv.h       |  532 +++++++
 drivers/staging/appletalk/cops_ltdrv.h       |  241 ++++
 drivers/staging/appletalk/ddp.c              | 1981 ++++++++++++++++++++++++++
 drivers/staging/appletalk/dev.c              |   44 +
 drivers/staging/appletalk/ipddp.c            |  335 +++++
 drivers/staging/appletalk/ipddp.h            |   27 +
 drivers/staging/appletalk/ltpc.c             | 1288 +++++++++++++++++
 drivers/staging/appletalk/ltpc.h             |   73 +
 drivers/staging/appletalk/sysctl_net_atalk.c |   61 +
 fs/compat_ioctl.c                            |    1 -
 include/linux/Kbuild                         |    1 -
 include/linux/atalk.h                        |  208 ---
 net/Kconfig                                  |    1 -
 net/Makefile                                 |    1 -
 net/appletalk/Makefile                       |    9 -
 net/appletalk/aarp.c                         | 1063 --------------
 net/appletalk/atalk_proc.c                   |  301 ----
 net/appletalk/ddp.c                          | 1981 --------------------------
 net/appletalk/dev.c                          |   44 -
 net/appletalk/sysctl_net_atalk.c             |   61 -
 net/socket.c                                 |    1 -
 42 files changed, 7369 insertions(+), 7377 deletions(-)
 delete mode 100644 drivers/net/appletalk/Kconfig
 delete mode 100644 drivers/net/appletalk/Makefile
 delete mode 100644 drivers/net/appletalk/cops.c
 delete mode 100644 drivers/net/appletalk/cops.h
 delete mode 100644 drivers/net/appletalk/cops_ffdrv.h
 delete mode 100644 drivers/net/appletalk/cops_ltdrv.h
 delete mode 100644 drivers/net/appletalk/ipddp.c
 delete mode 100644 drivers/net/appletalk/ipddp.h
 delete mode 100644 drivers/net/appletalk/ltpc.c
 delete mode 100644 drivers/net/appletalk/ltpc.h
 create mode 100644 drivers/staging/appletalk/Kconfig
 create mode 100644 drivers/staging/appletalk/Makefile
 create mode 100644 drivers/staging/appletalk/aarp.c
 create mode 100644 drivers/staging/appletalk/atalk.h
 create mode 100644 drivers/staging/appletalk/atalk_proc.c
 create mode 100644 drivers/staging/appletalk/cops.c
 create mode 100644 drivers/staging/appletalk/cops.h
 create mode 100644 drivers/staging/appletalk/cops_ffdrv.h
 create mode 100644 drivers/staging/appletalk/cops_ltdrv.h
 create mode 100644 drivers/staging/appletalk/ddp.c
 create mode 100644 drivers/staging/appletalk/dev.c
 create mode 100644 drivers/staging/appletalk/ipddp.c
 create mode 100644 drivers/staging/appletalk/ipddp.h
 create mode 100644 drivers/staging/appletalk/ltpc.c
 create mode 100644 drivers/staging/appletalk/ltpc.h
 create mode 100644 drivers/staging/appletalk/sysctl_net_atalk.c
 delete mode 100644 include/linux/atalk.h
 delete mode 100644 net/appletalk/Makefile
 delete mode 100644 net/appletalk/aarp.c
 delete mode 100644 net/appletalk/atalk_proc.c
 delete mode 100644 net/appletalk/ddp.c
 delete mode 100644 net/appletalk/dev.c
 delete mode 100644 net/appletalk/sysctl_net_atalk.c

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index dd6ca456cde3..3118d67d68fb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -554,8 +554,7 @@ F:	drivers/hwmon/applesmc.c
 APPLETALK NETWORK LAYER
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 S:	Maintained
-F:	drivers/net/appletalk/
-F:	net/appletalk/
+F:	drivers/staging/appletalk/
 
 ARC FRAMEBUFFER DRIVER
 M:	Jaya Kumar <jayalk@intworks.biz>
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index b90738d13994..11a9c053f0c8 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -265,7 +265,6 @@ obj-$(CONFIG_MACB) += macb.o
 obj-$(CONFIG_S6GMAC) += s6gmac.o
 
 obj-$(CONFIG_ARM) += arm/
-obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_TR) += tokenring/
 obj-$(CONFIG_WAN) += wan/
 obj-$(CONFIG_ARCNET) += arcnet/
diff --git a/drivers/net/appletalk/Kconfig b/drivers/net/appletalk/Kconfig
deleted file mode 100644
index 0b376a990972..000000000000
--- a/drivers/net/appletalk/Kconfig
+++ /dev/null
@@ -1,126 +0,0 @@
-#
-# Appletalk driver configuration
-#
-config ATALK
-	tristate "Appletalk protocol support"
-	depends on BKL # waiting to be removed from net/appletalk/ddp.c
-	select LLC
-	---help---
-	  AppleTalk is the protocol that Apple computers can use to communicate
-	  on a network.  If your Linux box is connected to such a network and you
-	  wish to connect to it, say Y.  You will need to use the netatalk package
-	  so that your Linux box can act as a print and file server for Macs as
-	  well as access AppleTalk printers.  Check out
-	  <http://www.zettabyte.net/netatalk/> on the WWW for details.
-	  EtherTalk is the name used for AppleTalk over Ethernet and the
-	  cheaper and slower LocalTalk is AppleTalk over a proprietary Apple
-	  network using serial links.  EtherTalk and LocalTalk are fully
-	  supported by Linux.
-
-	  General information about how to connect Linux, Windows machines and
-	  Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>.  The
-	  NET3-4-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>, contains valuable
-	  information as well.
-
-	  To compile this driver as a module, choose M here: the module will be
-	  called appletalk. You almost certainly want to compile it as a
-	  module so you can restart your AppleTalk stack without rebooting
-	  your machine. I hear that the GNU boycott of Apple is over, so
-	  even politically correct people are allowed to say Y here.
-
-config DEV_APPLETALK
-	tristate "Appletalk interfaces support"
-	depends on ATALK
-	help
-	  AppleTalk is the protocol that Apple computers can use to communicate
-	  on a network.  If your Linux box is connected to such a network, and wish
-	  to do IP over it, or you have a LocalTalk card and wish to use it to
-	  connect to the AppleTalk network, say Y.
-	  
-
-config LTPC
-	tristate "Apple/Farallon LocalTalk PC support"
-	depends on DEV_APPLETALK && (ISA || EISA) && ISA_DMA_API
-	help
-	  This allows you to use the AppleTalk PC card to connect to LocalTalk
-	  networks. The card is also known as the Farallon PhoneNet PC card.
-	  If you are in doubt, this card is the one with the 65C02 chip on it.
-	  You also need version 1.3.3 or later of the netatalk package.
-	  This driver is experimental, which means that it may not work.
-	  See the file <file:Documentation/networking/ltpc.txt>.
-
-config COPS
-	tristate "COPS LocalTalk PC support"
-	depends on DEV_APPLETALK && (ISA || EISA)
-	help
-	  This allows you to use COPS AppleTalk cards to connect to LocalTalk
-	  networks. You also need version 1.3.3 or later of the netatalk
-	  package. This driver is experimental, which means that it may not
-	  work. This driver will only work if you choose "AppleTalk DDP"
-	  networking support, above.
-	  Please read the file <file:Documentation/networking/cops.txt>.
-
-config COPS_DAYNA
-	bool "Dayna firmware support"
-	depends on COPS
-	help
-	  Support COPS compatible cards with Dayna style firmware (Dayna
-	  DL2000/ Daynatalk/PC (half length), COPS LT-95, Farallon PhoneNET PC
-	  III, Farallon PhoneNET PC II).
-
-config COPS_TANGENT
-	bool "Tangent firmware support"
-	depends on COPS
-	help
-	  Support COPS compatible cards with Tangent style firmware (Tangent
-	  ATB_II, Novell NL-1000, Daystar Digital LT-200.
-
-config IPDDP
-	tristate "Appletalk-IP driver support"
-	depends on DEV_APPLETALK && ATALK
-	---help---
-	  This allows IP networking for users who only have AppleTalk
-	  networking available. This feature is experimental. With this
-	  driver, you can encapsulate IP inside AppleTalk (e.g. if your Linux
-	  box is stuck on an AppleTalk only network) or decapsulate (e.g. if
-	  you want your Linux box to act as an Internet gateway for a zoo of
-	  AppleTalk connected Macs). Please see the file
-	  <file:Documentation/networking/ipddp.txt> for more information.
-
-	  If you say Y here, the AppleTalk-IP support will be compiled into
-	  the kernel. In this case, you can either use encapsulation or
-	  decapsulation, but not both. With the following two questions, you
-	  decide which one you want.
-
-	  To compile the AppleTalk-IP support as a module, choose M here: the
-	  module will be called ipddp.
-	  In this case, you will be able to use both encapsulation and
-	  decapsulation simultaneously, by loading two copies of the module
-	  and specifying different values for the module option ipddp_mode.
-
-config IPDDP_ENCAP
-	bool "IP to Appletalk-IP Encapsulation support"
-	depends on IPDDP
-	help
-	  If you say Y here, the AppleTalk-IP code will be able to encapsulate
-	  IP packets inside AppleTalk frames; this is useful if your Linux box
-	  is stuck on an AppleTalk network (which hopefully contains a
-	  decapsulator somewhere). Please see
-	  <file:Documentation/networking/ipddp.txt> for more information. If
-	  you said Y to "AppleTalk-IP driver support" above and you say Y
-	  here, then you cannot say Y to "AppleTalk-IP to IP Decapsulation
-	  support", below.
-
-config IPDDP_DECAP
-	bool "Appletalk-IP to IP Decapsulation support"
-	depends on IPDDP
-	help
-	  If you say Y here, the AppleTalk-IP code will be able to decapsulate
-	  AppleTalk-IP frames to IP packets; this is useful if you want your
-	  Linux box to act as an Internet gateway for an AppleTalk network.
-	  Please see <file:Documentation/networking/ipddp.txt> for more
-	  information.  If you said Y to "AppleTalk-IP driver support" above
-	  and you say Y here, then you cannot say Y to "IP to AppleTalk-IP
-	  Encapsulation support", above.
-
diff --git a/drivers/net/appletalk/Makefile b/drivers/net/appletalk/Makefile
deleted file mode 100644
index 6cfc705f7c5c..000000000000
--- a/drivers/net/appletalk/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for drivers/net/appletalk
-#
-
-obj-$(CONFIG_IPDDP) += ipddp.o
-obj-$(CONFIG_COPS) += cops.o
-obj-$(CONFIG_LTPC) += ltpc.o
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
deleted file mode 100644
index 748c9f526e71..000000000000
--- a/drivers/net/appletalk/cops.c
+++ /dev/null
@@ -1,1013 +0,0 @@
-/*      cops.c: LocalTalk driver for Linux.
- *
- *	Authors:
- *      - Jay Schulist <jschlst@samba.org>
- *
- *	With more than a little help from;
- *	- Alan Cox <alan@lxorguk.ukuu.org.uk>
- *
- *      Derived from:
- *      - skeleton.c: A network driver outline for linux.
- *        Written 1993-94 by Donald Becker.
- *	- ltpc.c: A driver for the LocalTalk PC card.
- *	  Written by Bradford W. Johnson.
- *
- *      Copyright 1993 United States Government as represented by the
- *      Director, National Security Agency.
- *
- *      This software may be used and distributed according to the terms
- *      of the GNU General Public License, incorporated herein by reference.
- *
- *	Changes:
- *	19970608	Alan Cox	Allowed dual card type support
- *					Can set board type in insmod
- *					Hooks for cops_setup routine
- *					(not yet implemented).
- *	19971101	Jay Schulist	Fixes for multiple lt* devices.
- *	19980607	Steven Hirsch	Fixed the badly broken support
- *					for Tangent type cards. Only
- *                                      tested on Daystar LT200. Some
- *                                      cleanup of formatting and program
- *                                      logic.  Added emacs 'local-vars'
- *                                      setup for Jay's brace style.
- *	20000211	Alan Cox	Cleaned up for softnet
- */
-
-static const char *version =
-"cops.c:v0.04 6/7/98 Jay Schulist <jschlst@samba.org>\n";
-/*
- *  Sources:
- *      COPS Localtalk SDK. This provides almost all of the information
- *      needed.
- */
-
-/*
- * insmod/modprobe configurable stuff.
- *	- IO Port, choose one your card supports or 0 if you dare.
- *	- IRQ, also choose one your card supports or nothing and let
- *	  the driver figure it out.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/in.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_ltalk.h>
-#include <linux/delay.h>	/* For udelay() */
-#include <linux/atalk.h>
-#include <linux/spinlock.h>
-#include <linux/bitops.h>
-#include <linux/jiffies.h>
-
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/dma.h>
-
-#include "cops.h"		/* Our Stuff */
-#include "cops_ltdrv.h"		/* Firmware code for Tangent type cards. */
-#include "cops_ffdrv.h"		/* Firmware code for Dayna type cards. */
-
-/*
- *      The name of the card. Is used for messages and in the requests for
- *      io regions, irqs and dma channels
- */
-
-static const char *cardname = "cops";
-
-#ifdef CONFIG_COPS_DAYNA
-static int board_type = DAYNA;	/* Module exported */
-#else
-static int board_type = TANGENT;
-#endif
-
-static int io = 0x240;		/* Default IO for Dayna */
-static int irq = 5;		/* Default IRQ */
-
-/*
- *	COPS Autoprobe information.
- *	Right now if port address is right but IRQ is not 5 this will
- *      return a 5 no matter what since we will still get a status response.
- *      Need one more additional check to narrow down after we have gotten
- *      the ioaddr. But since only other possible IRQs is 3 and 4 so no real
- *	hurry on this. I *STRONGLY* recommend using IRQ 5 for your card with
- *	this driver.
- * 
- *	This driver has 2 modes and they are: Dayna mode and Tangent mode.
- *	Each mode corresponds with the type of card. It has been found
- *	that there are 2 main types of cards and all other cards are
- *	the same and just have different names or only have minor differences
- *	such as more IO ports. As this driver is tested it will
- *	become more clear on exactly what cards are supported. The driver
- *	defaults to using Dayna mode. To change the drivers mode, simply
- *	select Dayna or Tangent mode when configuring the kernel.
- *
- *      This driver should support:
- *      TANGENT driver mode:
- *              Tangent ATB-II, Novell NL-1000, Daystar Digital LT-200,
- *		COPS LT-1
- *      DAYNA driver mode:
- *              Dayna DL2000/DaynaTalk PC (Half Length), COPS LT-95, 
- *		Farallon PhoneNET PC III, Farallon PhoneNET PC II
- *	Other cards possibly supported mode unknown though:
- *		Dayna DL2000 (Full length), COPS LT/M (Micro-Channel)
- *
- *	Cards NOT supported by this driver but supported by the ltpc.c
- *	driver written by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *		Farallon PhoneNET PC
- *		Original Apple LocalTalk PC card
- * 
- *      N.B.
- *
- *      The Daystar Digital LT200 boards do not support interrupt-driven
- *      IO.  You must specify 'irq=0xff' as a module parameter to invoke
- *      polled mode.  I also believe that the port probing logic is quite
- *      dangerous at best and certainly hopeless for a polled card.  Best to 
- *      specify both. - Steve H.
- *
- */
-
-/*
- * Zero terminated list of IO ports to probe.
- */
-
-static unsigned int ports[] = { 
-	0x240, 0x340, 0x200, 0x210, 0x220, 0x230, 0x260, 
-	0x2A0, 0x300, 0x310, 0x320, 0x330, 0x350, 0x360,
-	0
-};
-
-/*
- * Zero terminated list of IRQ ports to probe.
- */
-
-static int cops_irqlist[] = {
-	5, 4, 3, 0 
-};
-
-static struct timer_list cops_timer;
-
-/* use 0 for production, 1 for verification, 2 for debug, 3 for verbose debug */
-#ifndef COPS_DEBUG
-#define COPS_DEBUG 1 
-#endif
-static unsigned int cops_debug = COPS_DEBUG;
-
-/* The number of low I/O ports used by the card. */
-#define COPS_IO_EXTENT       8
-
-/* Information that needs to be kept for each board. */
-
-struct cops_local
-{
-        int board;			/* Holds what board type is. */
-	int nodeid;			/* Set to 1 once have nodeid. */
-        unsigned char node_acquire;	/* Node ID when acquired. */
-        struct atalk_addr node_addr;	/* Full node address */
-	spinlock_t lock;		/* RX/TX lock */
-};
-
-/* Index to functions, as function prototypes. */
-static int  cops_probe1 (struct net_device *dev, int ioaddr);
-static int  cops_irq (int ioaddr, int board);
-
-static int  cops_open (struct net_device *dev);
-static int  cops_jumpstart (struct net_device *dev);
-static void cops_reset (struct net_device *dev, int sleep);
-static void cops_load (struct net_device *dev);
-static int  cops_nodeid (struct net_device *dev, int nodeid);
-
-static irqreturn_t cops_interrupt (int irq, void *dev_id);
-static void cops_poll (unsigned long ltdev);
-static void cops_timeout(struct net_device *dev);
-static void cops_rx (struct net_device *dev);
-static netdev_tx_t  cops_send_packet (struct sk_buff *skb,
-					    struct net_device *dev);
-static void set_multicast_list (struct net_device *dev);
-static int  cops_ioctl (struct net_device *dev, struct ifreq *rq, int cmd);
-static int  cops_close (struct net_device *dev);
-
-static void cleanup_card(struct net_device *dev)
-{
-	if (dev->irq)
-		free_irq(dev->irq, dev);
-	release_region(dev->base_addr, COPS_IO_EXTENT);
-}
-
-/*
- *      Check for a network adaptor of this type, and return '0' iff one exists.
- *      If dev->base_addr == 0, probe all likely locations.
- *      If dev->base_addr in [1..0x1ff], always return failure.
- *        otherwise go with what we pass in.
- */
-struct net_device * __init cops_probe(int unit)
-{
-	struct net_device *dev;
-	unsigned *port;
-	int base_addr;
-	int err = 0;
-
-	dev = alloc_ltalkdev(sizeof(struct cops_local));
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	if (unit >= 0) {
-		sprintf(dev->name, "lt%d", unit);
-		netdev_boot_setup_check(dev);
-		irq = dev->irq;
-		base_addr = dev->base_addr;
-	} else {
-		base_addr = dev->base_addr = io;
-	}
-
-	if (base_addr > 0x1ff) {    /* Check a single specified location. */
-		err = cops_probe1(dev, base_addr);
-	} else if (base_addr != 0) { /* Don't probe at all. */
-		err = -ENXIO;
-	} else {
-		/* FIXME  Does this really work for cards which generate irq?
-		 * It's definitely N.G. for polled Tangent. sh
-		 * Dayna cards don't autoprobe well at all, but if your card is
-		 * at IRQ 5 & IO 0x240 we find it every time. ;) JS
-		 */
-		for (port = ports; *port && cops_probe1(dev, *port) < 0; port++)
-			;
-		if (!*port)
-			err = -ENODEV;
-	}
-	if (err)
-		goto out;
-	err = register_netdev(dev);
-	if (err)
-		goto out1;
-	return dev;
-out1:
-	cleanup_card(dev);
-out:
-	free_netdev(dev);
-	return ERR_PTR(err);
-}
-
-static const struct net_device_ops cops_netdev_ops = {
-	.ndo_open               = cops_open,
-        .ndo_stop               = cops_close,
-	.ndo_start_xmit   	= cops_send_packet,
-	.ndo_tx_timeout		= cops_timeout,
-        .ndo_do_ioctl           = cops_ioctl,
-	.ndo_set_multicast_list = set_multicast_list,
-};
-
-/*
- *      This is the real probe routine. Linux has a history of friendly device
- *      probes on the ISA bus. A good device probes avoids doing writes, and
- *      verifies that the correct device exists and functions.
- */
-static int __init cops_probe1(struct net_device *dev, int ioaddr)
-{
-        struct cops_local *lp;
-	static unsigned version_printed;
-	int board = board_type;
-	int retval;
-	
-        if(cops_debug && version_printed++ == 0)
-		printk("%s", version);
-
-	/* Grab the region so no one else tries to probe our ioports. */
-	if (!request_region(ioaddr, COPS_IO_EXTENT, dev->name))
-		return -EBUSY;
-
-        /*
-         * Since this board has jumpered interrupts, allocate the interrupt
-         * vector now. There is no point in waiting since no other device
-         * can use the interrupt, and this marks the irq as busy. Jumpered
-         * interrupts are typically not reported by the boards, and we must
-         * used AutoIRQ to find them.
-	 */
-	dev->irq = irq;
-	switch (dev->irq)
-	{
-		case 0:
-			/* COPS AutoIRQ routine */
-			dev->irq = cops_irq(ioaddr, board);
-			if (dev->irq)
-				break;
-			/* No IRQ found on this port, fallthrough */
-		case 1:
-			retval = -EINVAL;
-			goto err_out;
-
-		/* Fixup for users that don't know that IRQ 2 is really
-		 * IRQ 9, or don't know which one to set.
-		 */
-		case 2:
-			dev->irq = 9;
-			break;
-
-		/* Polled operation requested. Although irq of zero passed as
-		 * a parameter tells the init routines to probe, we'll
-		 * overload it to denote polled operation at runtime.
-		 */
-		case 0xff:
-			dev->irq = 0;
-			break;
-
-		default:
-			break;
-	}
-
-	/* Reserve any actual interrupt. */
-	if (dev->irq) {
-		retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev);
-		if (retval)
-			goto err_out;
-	}
-
-	dev->base_addr = ioaddr;
-
-        lp = netdev_priv(dev);
-        spin_lock_init(&lp->lock);
-
-	/* Copy local board variable to lp struct. */
-	lp->board               = board;
-
-	dev->netdev_ops 	= &cops_netdev_ops;
-	dev->watchdog_timeo	= HZ * 2;
-
-
-	/* Tell the user where the card is and what mode we're in. */
-	if(board==DAYNA)
-		printk("%s: %s at %#3x, using IRQ %d, in Dayna mode.\n", 
-			dev->name, cardname, ioaddr, dev->irq);
-	if(board==TANGENT) {
-		if(dev->irq)
-			printk("%s: %s at %#3x, IRQ %d, in Tangent mode\n", 
-				dev->name, cardname, ioaddr, dev->irq);
-		else
-			printk("%s: %s at %#3x, using polled IO, in Tangent mode.\n", 
-				dev->name, cardname, ioaddr);
-
-	}
-        return 0;
-
-err_out:
-	release_region(ioaddr, COPS_IO_EXTENT);
-	return retval;
-}
-
-static int __init cops_irq (int ioaddr, int board)
-{       /*
-         * This does not use the IRQ to determine where the IRQ is. We just
-         * assume that when we get a correct status response that it's the IRQ.
-         * This really just verifies the IO port but since we only have access
-         * to such a small number of IRQs (5, 4, 3) this is not bad.
-         * This will probably not work for more than one card.
-         */
-        int irqaddr=0;
-        int i, x, status;
-
-        if(board==DAYNA)
-        {
-                outb(0, ioaddr+DAYNA_RESET);
-                inb(ioaddr+DAYNA_RESET);
-                mdelay(333);
-        }
-        if(board==TANGENT)
-        {
-                inb(ioaddr);
-                outb(0, ioaddr);
-                outb(0, ioaddr+TANG_RESET);
-        }
-
-        for(i=0; cops_irqlist[i] !=0; i++)
-        {
-                irqaddr = cops_irqlist[i];
-                for(x = 0xFFFF; x>0; x --)    /* wait for response */
-                {
-                        if(board==DAYNA)
-                        {
-                                status = (inb(ioaddr+DAYNA_CARD_STATUS)&3);
-                                if(status == 1)
-                                        return irqaddr;
-                        }
-                        if(board==TANGENT)
-                        {
-                                if((inb(ioaddr+TANG_CARD_STATUS)& TANG_TX_READY) !=0)
-                                        return irqaddr;
-                        }
-                }
-        }
-        return 0;       /* no IRQ found */
-}
-
-/*
- * Open/initialize the board. This is called (in the current kernel)
- * sometime after booting when the 'ifconfig' program is run.
- */
-static int cops_open(struct net_device *dev)
-{
-    struct cops_local *lp = netdev_priv(dev);
-
-	if(dev->irq==0)
-	{
-		/*
-		 * I don't know if the Dayna-style boards support polled 
-		 * operation.  For now, only allow it for Tangent.
-		 */
-		if(lp->board==TANGENT)	/* Poll 20 times per second */
-		{
-		    init_timer(&cops_timer);
-		    cops_timer.function = cops_poll;
-		    cops_timer.data 	= (unsigned long)dev;
-		    cops_timer.expires 	= jiffies + HZ/20;
-		    add_timer(&cops_timer);
-		} 
-		else 
-		{
-			printk(KERN_WARNING "%s: No irq line set\n", dev->name);
-			return -EAGAIN;
-		}
-	}
-
-	cops_jumpstart(dev);	/* Start the card up. */
-
-	netif_start_queue(dev);
-        return 0;
-}
-
-/*
- *	This allows for a dynamic start/restart of the entire card.
- */
-static int cops_jumpstart(struct net_device *dev)
-{
-	struct cops_local *lp = netdev_priv(dev);
-
-	/*
-         *      Once the card has the firmware loaded and has acquired
-         *      the nodeid, if it is reset it will lose it all.
-         */
-        cops_reset(dev,1);	/* Need to reset card before load firmware. */
-        cops_load(dev);		/* Load the firmware. */
-
-	/*
-	 *	If atalkd already gave us a nodeid we will use that
-	 *	one again, else we wait for atalkd to give us a nodeid
-	 *	in cops_ioctl. This may cause a problem if someone steals
-	 *	our nodeid while we are resetting.
-	 */	
-	if(lp->nodeid == 1)
-		cops_nodeid(dev,lp->node_acquire);
-
-	return 0;
-}
-
-static void tangent_wait_reset(int ioaddr)
-{
-	int timeout=0;
-
-	while(timeout++ < 5 && (inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-		mdelay(1);   /* Wait 1 second */
-}
-
-/*
- *      Reset the LocalTalk board.
- */
-static void cops_reset(struct net_device *dev, int sleep)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr=dev->base_addr;
-
-        if(lp->board==TANGENT)
-        {
-                inb(ioaddr);		/* Clear request latch. */
-                outb(0,ioaddr);		/* Clear the TANG_TX_READY flop. */
-                outb(0, ioaddr+TANG_RESET);	/* Reset the adapter. */
-
-		tangent_wait_reset(ioaddr);
-                outb(0, ioaddr+TANG_CLEAR_INT);
-        }
-        if(lp->board==DAYNA)
-        {
-                outb(0, ioaddr+DAYNA_RESET);	/* Assert the reset port */
-                inb(ioaddr+DAYNA_RESET);	/* Clear the reset */
-		if (sleep)
-			msleep(333);
-		else
-			mdelay(333);
-        }
-
-	netif_wake_queue(dev);
-}
-
-static void cops_load (struct net_device *dev)
-{
-        struct ifreq ifr;
-        struct ltfirmware *ltf= (struct ltfirmware *)&ifr.ifr_ifru;
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr=dev->base_addr;
-	int length, i = 0;
-
-        strcpy(ifr.ifr_name,"lt0");
-
-        /* Get card's firmware code and do some checks on it. */
-#ifdef CONFIG_COPS_DAYNA        
-        if(lp->board==DAYNA)
-        {
-                ltf->length=sizeof(ffdrv_code);
-                ltf->data=ffdrv_code;
-        }
-        else
-#endif        
-#ifdef CONFIG_COPS_TANGENT
-        if(lp->board==TANGENT)
-        {
-                ltf->length=sizeof(ltdrv_code);
-                ltf->data=ltdrv_code;
-        }
-        else
-#endif
-	{
-		printk(KERN_INFO "%s; unsupported board type.\n", dev->name);
-		return;
-	}
-	
-        /* Check to make sure firmware is correct length. */
-        if(lp->board==DAYNA && ltf->length!=5983)
-        {
-                printk(KERN_WARNING "%s: Firmware is not length of FFDRV.BIN.\n", dev->name);
-                return;
-        }
-        if(lp->board==TANGENT && ltf->length!=2501)
-        {
-                printk(KERN_WARNING "%s: Firmware is not length of DRVCODE.BIN.\n", dev->name);
-                return;
-        }
-
-        if(lp->board==DAYNA)
-        {
-                /*
-                 *      We must wait for a status response
-                 *      with the DAYNA board.
-                 */
-                while(++i<65536)
-                {
-                       if((inb(ioaddr+DAYNA_CARD_STATUS)&3)==1)
-                                break;
-                }
-
-                if(i==65536)
-                        return;
-        }
-
-        /*
-         *      Upload the firmware and kick. Byte-by-byte works nicely here.
-         */
-	i=0;
-        length = ltf->length;
-        while(length--)
-        {
-                outb(ltf->data[i], ioaddr);
-                i++;
-        }
-
-	if(cops_debug > 1)
-		printk("%s: Uploaded firmware - %d bytes of %d bytes.\n", 
-			dev->name, i, ltf->length);
-
-        if(lp->board==DAYNA) 	/* Tell Dayna to run the firmware code. */
-                outb(1, ioaddr+DAYNA_INT_CARD);
-	else			/* Tell Tang to run the firmware code. */
-		inb(ioaddr);
-
-        if(lp->board==TANGENT)
-        {
-                tangent_wait_reset(ioaddr);
-                inb(ioaddr);	/* Clear initial ready signal. */
-        }
-}
-
-/*
- * 	Get the LocalTalk Nodeid from the card. We can suggest
- *	any nodeid 1-254. The card will try and get that exact
- *	address else we can specify 0 as the nodeid and the card
- *	will autoprobe for a nodeid.
- */
-static int cops_nodeid (struct net_device *dev, int nodeid)
-{
-	struct cops_local *lp = netdev_priv(dev);
-	int ioaddr = dev->base_addr;
-
-	if(lp->board == DAYNA)
-        {
-        	/* Empty any pending adapter responses. */
-                while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
-                {
-			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupts. */
-        		if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
-                		cops_rx(dev);	/* Kick any packets waiting. */
-			schedule();
-                }
-
-                outb(2, ioaddr);       	/* Output command packet length as 2. */
-                outb(0, ioaddr);
-                outb(LAP_INIT, ioaddr);	/* Send LAP_INIT command byte. */
-                outb(nodeid, ioaddr);  	/* Suggest node address. */
-        }
-
-	if(lp->board == TANGENT)
-        {
-                /* Empty any pending adapter responses. */
-                while(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
-                {
-			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupt. */
-                	cops_rx(dev);          	/* Kick out packets waiting. */
-			schedule();
-                }
-
-		/* Not sure what Tangent does if nodeid picked is used. */
-                if(nodeid == 0)	         		/* Seed. */
-                	nodeid = jiffies&0xFF;		/* Get a random try */
-                outb(2, ioaddr);        		/* Command length LSB */
-                outb(0, ioaddr);       			/* Command length MSB */
-                outb(LAP_INIT, ioaddr); 		/* Send LAP_INIT byte */
-                outb(nodeid, ioaddr); 		  	/* LAP address hint. */
-                outb(0xFF, ioaddr);     		/* Int. level to use */
-        }
-
-	lp->node_acquire=0;		/* Set nodeid holder to 0. */
-        while(lp->node_acquire==0)	/* Get *True* nodeid finally. */
-	{
-		outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear any interrupt. */
-
-		if(lp->board == DAYNA)
-		{
-                	if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
-                		cops_rx(dev);	/* Grab the nodeid put in lp->node_acquire. */
-		}
-		if(lp->board == TANGENT)
-		{	
-			if(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
-                                cops_rx(dev);   /* Grab the nodeid put in lp->node_acquire. */
-		}
-		schedule();
-	}
-
-	if(cops_debug > 1)
-		printk(KERN_DEBUG "%s: Node ID %d has been acquired.\n", 
-			dev->name, lp->node_acquire);
-
-	lp->nodeid=1;	/* Set got nodeid to 1. */
-
-        return 0;
-}
-
-/*
- *	Poll the Tangent type cards to see if we have work.
- */
- 
-static void cops_poll(unsigned long ltdev)
-{
-	int ioaddr, status;
-	int boguscount = 0;
-
-	struct net_device *dev = (struct net_device *)ltdev;
-
-	del_timer(&cops_timer);
-
-	if(dev == NULL)
-		return;	/* We've been downed */
-
-	ioaddr = dev->base_addr;
-	do {
-		status=inb(ioaddr+TANG_CARD_STATUS);
-		if(status & TANG_RX_READY)
-			cops_rx(dev);
-		if(status & TANG_TX_READY)
-			netif_wake_queue(dev);
-		status = inb(ioaddr+TANG_CARD_STATUS);
-	} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
-
-	/* poll 20 times per second */
-	cops_timer.expires = jiffies + HZ/20;
-	add_timer(&cops_timer);
-}
-
-/*
- *      The typical workload of the driver:
- *      Handle the network interface interrupts.
- */
-static irqreturn_t cops_interrupt(int irq, void *dev_id)
-{
-        struct net_device *dev = dev_id;
-        struct cops_local *lp;
-        int ioaddr, status;
-        int boguscount = 0;
-
-        ioaddr = dev->base_addr;
-        lp = netdev_priv(dev);
-
-	if(lp->board==DAYNA)
-	{
-		do {
-			outb(0, ioaddr + COPS_CLEAR_INT);
-                       	status=inb(ioaddr+DAYNA_CARD_STATUS);
-                       	if((status&0x03)==DAYNA_RX_REQUEST)
-                       	        cops_rx(dev);
-                	netif_wake_queue(dev);
-		} while(++boguscount < 20);
-	}
-	else
-	{
-		do {
-                       	status=inb(ioaddr+TANG_CARD_STATUS);
-			if(status & TANG_RX_READY)
-				cops_rx(dev);
-			if(status & TANG_TX_READY)
-				netif_wake_queue(dev);
-			status=inb(ioaddr+TANG_CARD_STATUS);
-		} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
-	}
-
-        return IRQ_HANDLED;
-}
-
-/*
- *      We have a good packet(s), get it/them out of the buffers.
- */
-static void cops_rx(struct net_device *dev)
-{
-        int pkt_len = 0;
-        int rsp_type = 0;
-        struct sk_buff *skb = NULL;
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr = dev->base_addr;
-        int boguscount = 0;
-        unsigned long flags;
-
-
-	spin_lock_irqsave(&lp->lock, flags);
-	
-        if(lp->board==DAYNA)
-        {
-                outb(0, ioaddr);                /* Send out Zero length. */
-                outb(0, ioaddr);
-                outb(DATA_READ, ioaddr);        /* Send read command out. */
-
-                /* Wait for DMA to turn around. */
-                while(++boguscount<1000000)
-                {
-			barrier();
-                        if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_READY)
-                                break;
-                }
-
-                if(boguscount==1000000)
-                {
-                        printk(KERN_WARNING "%s: DMA timed out.\n",dev->name);
-			spin_unlock_irqrestore(&lp->lock, flags);
-                        return;
-                }
-        }
-
-        /* Get response length. */
-	if(lp->board==DAYNA)
-        	pkt_len = inb(ioaddr) & 0xFF;
-	else
-		pkt_len = inb(ioaddr) & 0x00FF;
-        pkt_len |= (inb(ioaddr) << 8);
-        /* Input IO code. */
-        rsp_type=inb(ioaddr);
-
-        /* Malloc up new buffer. */
-        skb = dev_alloc_skb(pkt_len);
-        if(skb == NULL)
-        {
-                printk(KERN_WARNING "%s: Memory squeeze, dropping packet.\n",
-			dev->name);
-                dev->stats.rx_dropped++;
-                while(pkt_len--)        /* Discard packet */
-                        inb(ioaddr);
-                spin_unlock_irqrestore(&lp->lock, flags);
-                return;
-        }
-        skb->dev = dev;
-        skb_put(skb, pkt_len);
-        skb->protocol = htons(ETH_P_LOCALTALK);
-
-        insb(ioaddr, skb->data, pkt_len);               /* Eat the Data */
-
-        if(lp->board==DAYNA)
-                outb(1, ioaddr+DAYNA_INT_CARD);         /* Interrupt the card */
-
-        spin_unlock_irqrestore(&lp->lock, flags);  /* Restore interrupts. */
-
-        /* Check for bad response length */
-        if(pkt_len < 0 || pkt_len > MAX_LLAP_SIZE)
-        {
-		printk(KERN_WARNING "%s: Bad packet length of %d bytes.\n", 
-			dev->name, pkt_len);
-                dev->stats.tx_errors++;
-                dev_kfree_skb_any(skb);
-                return;
-        }
-
-        /* Set nodeid and then get out. */
-        if(rsp_type == LAP_INIT_RSP)
-        {	/* Nodeid taken from received packet. */
-                lp->node_acquire = skb->data[0];
-                dev_kfree_skb_any(skb);
-                return;
-        }
-
-        /* One last check to make sure we have a good packet. */
-        if(rsp_type != LAP_RESPONSE)
-        {
-                printk(KERN_WARNING "%s: Bad packet type %d.\n", dev->name, rsp_type);
-                dev->stats.tx_errors++;
-                dev_kfree_skb_any(skb);
-                return;
-        }
-
-        skb_reset_mac_header(skb);    /* Point to entire packet. */
-        skb_pull(skb,3);
-        skb_reset_transport_header(skb);    /* Point to data (Skip header). */
-
-        /* Update the counters. */
-        dev->stats.rx_packets++;
-        dev->stats.rx_bytes += skb->len;
-
-        /* Send packet to a higher place. */
-        netif_rx(skb);
-}
-
-static void cops_timeout(struct net_device *dev)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr = dev->base_addr;
-
-	dev->stats.tx_errors++;
-        if(lp->board==TANGENT)
-        {
-		if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-               		printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name);
-	}
-	printk(KERN_WARNING "%s: Transmit timed out.\n", dev->name);
-	cops_jumpstart(dev);	/* Restart the card. */
-	dev->trans_start = jiffies; /* prevent tx timeout */
-	netif_wake_queue(dev);
-}
-
-
-/*
- *	Make the card transmit a LocalTalk packet.
- */
-
-static netdev_tx_t cops_send_packet(struct sk_buff *skb,
-					  struct net_device *dev)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr = dev->base_addr;
-        unsigned long flags;
-
-        /*
-         * Block a timer-based transmit from overlapping. 
-	 */
-	 
-	netif_stop_queue(dev);
-
-	spin_lock_irqsave(&lp->lock, flags);
-	if(lp->board == DAYNA)	 /* Wait for adapter transmit buffer. */
-		while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
-			cpu_relax();
-	if(lp->board == TANGENT) /* Wait for adapter transmit buffer. */
-		while((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-			cpu_relax();
-
-	/* Output IO length. */
-	outb(skb->len, ioaddr);
-	if(lp->board == DAYNA)
-               	outb(skb->len >> 8, ioaddr);
-	else
-		outb((skb->len >> 8)&0x0FF, ioaddr);
-
-	/* Output IO code. */
-	outb(LAP_WRITE, ioaddr);
-
-	if(lp->board == DAYNA)	/* Check the transmit buffer again. */
-        	while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0);
-
-	outsb(ioaddr, skb->data, skb->len);	/* Send out the data. */
-
-	if(lp->board==DAYNA)	/* Dayna requires you kick the card */
-		outb(1, ioaddr+DAYNA_INT_CARD);
-
-	spin_unlock_irqrestore(&lp->lock, flags);	/* Restore interrupts. */
-
-	/* Done sending packet, update counters and cleanup. */
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-	dev_kfree_skb (skb);
-	return NETDEV_TX_OK;
-}
-
-/*
- *	Dummy function to keep the Appletalk layer happy.
- */
- 
-static void set_multicast_list(struct net_device *dev)
-{
-        if(cops_debug >= 3)
-		printk("%s: set_multicast_list executed\n", dev->name);
-}
-
-/*
- *      System ioctls for the COPS LocalTalk card.
- */
- 
-static int cops_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        struct sockaddr_at *sa = (struct sockaddr_at *)&ifr->ifr_addr;
-        struct atalk_addr *aa = (struct atalk_addr *)&lp->node_addr;
-
-        switch(cmd)
-        {
-                case SIOCSIFADDR:
-			/* Get and set the nodeid and network # atalkd wants. */
-			cops_nodeid(dev, sa->sat_addr.s_node);
-			aa->s_net               = sa->sat_addr.s_net;
-                        aa->s_node              = lp->node_acquire;
-
-			/* Set broardcast address. */
-                        dev->broadcast[0]       = 0xFF;
-			
-			/* Set hardware address. */
-                        dev->dev_addr[0]        = aa->s_node;
-                        dev->addr_len           = 1;
-                        return 0;
-
-                case SIOCGIFADDR:
-                        sa->sat_addr.s_net      = aa->s_net;
-                        sa->sat_addr.s_node     = aa->s_node;
-                        return 0;
-
-                default:
-                        return -EOPNOTSUPP;
-        }
-}
-
-/*
- *	The inverse routine to cops_open().
- */
- 
-static int cops_close(struct net_device *dev)
-{
-	struct cops_local *lp = netdev_priv(dev);
-
-	/* If we were running polled, yank the timer.
-	 */
-	if(lp->board==TANGENT && dev->irq==0)
-		del_timer(&cops_timer);
-
-	netif_stop_queue(dev);
-        return 0;
-}
-
-
-#ifdef MODULE
-static struct net_device *cops_dev;
-
-MODULE_LICENSE("GPL");
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(board_type, int, 0);
-
-static int __init cops_module_init(void)
-{
-	if (io == 0)
-		printk(KERN_WARNING "%s: You shouldn't autoprobe with insmod\n",
-			cardname);
-	cops_dev = cops_probe(-1);
-	if (IS_ERR(cops_dev))
-		return PTR_ERR(cops_dev);
-        return 0;
-}
-
-static void __exit cops_module_exit(void)
-{
-	unregister_netdev(cops_dev);
-	cleanup_card(cops_dev);
-	free_netdev(cops_dev);
-}
-module_init(cops_module_init);
-module_exit(cops_module_exit);
-#endif /* MODULE */
diff --git a/drivers/net/appletalk/cops.h b/drivers/net/appletalk/cops.h
deleted file mode 100644
index fd2750b269c8..000000000000
--- a/drivers/net/appletalk/cops.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*      cops.h: LocalTalk driver for Linux.
- *
- *      Authors:
- *      - Jay Schulist <jschlst@samba.org>
- */
-
-#ifndef __LINUX_COPSLTALK_H
-#define __LINUX_COPSLTALK_H
-
-#ifdef __KERNEL__
-
-/* Max LLAP size we will accept. */
-#define MAX_LLAP_SIZE		603
-
-/* Tangent */
-#define TANG_CARD_STATUS        1
-#define TANG_CLEAR_INT          1
-#define TANG_RESET              3
-
-#define TANG_TX_READY           1
-#define TANG_RX_READY           2
-
-/* Dayna */
-#define DAYNA_CMD_DATA          0
-#define DAYNA_CLEAR_INT         1
-#define DAYNA_CARD_STATUS       2
-#define DAYNA_INT_CARD          3
-#define DAYNA_RESET             4
-
-#define DAYNA_RX_READY          0
-#define DAYNA_TX_READY          1
-#define DAYNA_RX_REQUEST        3
-
-/* Same on both card types */
-#define COPS_CLEAR_INT  1
-
-/* LAP response codes received from the cards. */
-#define LAP_INIT        1       /* Init cmd */
-#define LAP_INIT_RSP    2       /* Init response */
-#define LAP_WRITE       3       /* Write cmd */
-#define DATA_READ       4       /* Data read */
-#define LAP_RESPONSE    4       /* Received ALAP frame response */
-#define LAP_GETSTAT     5       /* Get LAP and HW status */
-#define LAP_RSPSTAT     6       /* Status response */
-
-#endif
-
-/*
- *	Structure to hold the firmware information.
- */
-struct ltfirmware
-{
-        unsigned int length;
-        const unsigned char *data;
-};
-
-#define DAYNA 1
-#define TANGENT 2
-
-#endif
diff --git a/drivers/net/appletalk/cops_ffdrv.h b/drivers/net/appletalk/cops_ffdrv.h
deleted file mode 100644
index b02005087c1b..000000000000
--- a/drivers/net/appletalk/cops_ffdrv.h
+++ /dev/null
@@ -1,532 +0,0 @@
-
-/*
- *	The firmware this driver downloads into the Localtalk card is a
- *	separate program and is not GPL'd source code, even though the Linux
- *	side driver and the routine that loads this data into the card are.
- *	
- *	It is taken from the COPS SDK and is under the following license
- *
- *	This material is licensed to you strictly for use in conjunction with
- *	the use of COPS LocalTalk adapters.
- *	There is no charge for this SDK. And no waranty express or implied
- *	about its fitness for any purpose. However, we will cheerefully
- *	refund every penny you paid for this SDK...
- *	Regards,
- *
- *	Thomas F. Divine
- *	Chief Scientist
- */
-
-
-/*      cops_ffdrv.h: LocalTalk driver firmware dump for Linux.
- *
- *      Authors:
- *      - Jay Schulist <jschlst@samba.org>
- */
-
-
-#ifdef CONFIG_COPS_DAYNA
-
-static const unsigned char ffdrv_code[] = {
-	58,3,0,50,228,149,33,255,255,34,226,149,
-	249,17,40,152,33,202,154,183,237,82,77,68,
-	11,107,98,19,54,0,237,176,175,50,80,0,
-	62,128,237,71,62,32,237,57,51,62,12,237,
-	57,50,237,57,54,62,6,237,57,52,62,12,
-	237,57,49,33,107,137,34,32,128,33,83,130,
-	34,40,128,33,86,130,34,42,128,33,112,130,
-	34,36,128,33,211,130,34,38,128,62,0,237,
-	57,16,33,63,148,34,34,128,237,94,205,15,
-	130,251,205,168,145,24,141,67,111,112,121,114,
-	105,103,104,116,32,40,67,41,32,49,57,56,
-	56,32,45,32,68,97,121,110,97,32,67,111,
-	109,109,117,110,105,99,97,116,105,111,110,115,
-	32,32,32,65,108,108,32,114,105,103,104,116,
-	115,32,114,101,115,101,114,118,101,100,46,32,
-	32,40,68,40,68,7,16,8,34,7,22,6,
-	16,5,12,4,8,3,6,140,0,16,39,128,
-	0,4,96,10,224,6,0,7,126,2,64,11,
-	118,12,6,13,0,14,193,15,0,5,96,3,
-	192,1,64,9,8,62,9,211,66,62,192,211,
-	66,62,100,61,32,253,6,28,33,205,129,14,
-	66,237,163,194,253,129,6,28,33,205,129,14,
-	64,237,163,194,9,130,201,62,47,50,71,152,
-	62,47,211,68,58,203,129,237,57,20,58,204,
-	129,237,57,21,33,77,152,54,132,205,233,129,
-	58,228,149,254,209,40,6,56,4,62,0,24,
-	2,219,96,33,233,149,119,230,62,33,232,149,
-	119,213,33,8,152,17,7,0,25,119,19,25,
-	119,209,201,251,237,77,245,197,213,229,221,229,
-	205,233,129,62,1,50,106,137,205,158,139,221,
-	225,225,209,193,241,251,237,77,245,197,213,219,
-	72,237,56,16,230,46,237,57,16,237,56,12,
-	58,72,152,183,32,26,6,20,17,128,2,237,
-	56,46,187,32,35,237,56,47,186,32,29,219,
-	72,230,1,32,3,5,32,232,175,50,72,152,
-	229,221,229,62,1,50,106,137,205,158,139,221,
-	225,225,24,25,62,1,50,72,152,58,201,129,
-	237,57,12,58,202,129,237,57,13,237,56,16,
-	246,17,237,57,16,209,193,241,251,237,77,245,
-	197,229,213,221,229,237,56,16,230,17,237,57,
-	16,237,56,20,58,34,152,246,16,246,8,211,
-	68,62,6,61,32,253,58,34,152,246,8,211,
-	68,58,203,129,237,57,20,58,204,129,237,57,
-	21,237,56,16,246,34,237,57,16,221,225,209,
-	225,193,241,251,237,77,33,2,0,57,126,230,
-	3,237,100,1,40,2,246,128,230,130,245,62,
-	5,211,64,241,211,64,201,229,213,243,237,56,
-	16,230,46,237,57,16,237,56,12,251,70,35,
-	35,126,254,175,202,77,133,254,129,202,15,133,
-	230,128,194,191,132,43,58,44,152,119,33,76,
-	152,119,35,62,132,119,120,254,255,40,4,58,
-	49,152,119,219,72,43,43,112,17,3,0,237,
-	56,52,230,248,237,57,52,219,72,230,1,194,
-	141,131,209,225,237,56,52,246,6,237,57,52,
-	62,1,55,251,201,62,3,211,66,62,192,211,
-	66,62,48,211,66,0,0,219,66,230,1,40,
-	4,219,67,24,240,205,203,135,58,75,152,254,
-	255,202,128,132,58,49,152,254,161,250,207,131,
-	58,34,152,211,68,62,10,211,66,62,128,211,
-	66,62,11,211,66,62,6,211,66,24,0,62,
-	14,211,66,62,33,211,66,62,1,211,66,62,
-	64,211,66,62,3,211,66,62,209,211,66,62,
-	100,71,219,66,230,1,32,6,5,32,247,195,
-	248,132,219,67,71,58,44,152,184,194,248,132,
-	62,100,71,219,66,230,1,32,6,5,32,247,
-	195,248,132,219,67,62,100,71,219,66,230,1,
-	32,6,5,32,247,195,248,132,219,67,254,133,
-	32,7,62,0,50,74,152,24,17,254,173,32,
-	7,62,1,50,74,152,24,6,254,141,194,248,
-	132,71,209,225,58,49,152,254,132,32,10,62,
-	50,205,2,134,205,144,135,24,27,254,140,32,
-	15,62,110,205,2,134,62,141,184,32,5,205,
-	144,135,24,8,62,10,205,2,134,205,8,134,
-	62,1,50,106,137,205,158,139,237,56,52,246,
-	6,237,57,52,175,183,251,201,62,20,135,237,
-	57,20,175,237,57,21,237,56,16,246,2,237,
-	57,16,237,56,20,95,237,56,21,123,254,10,
-	48,244,237,56,16,230,17,237,57,16,209,225,
-	205,144,135,62,1,50,106,137,205,158,139,237,
-	56,52,246,6,237,57,52,175,183,251,201,209,
-	225,243,219,72,230,1,40,13,62,10,211,66,
-	0,0,219,66,230,192,202,226,132,237,56,52,
-	246,6,237,57,52,62,1,55,251,201,205,203,
-	135,62,1,50,106,137,205,158,139,237,56,52,
-	246,6,237,57,52,183,251,201,209,225,62,1,
-	50,106,137,205,158,139,237,56,52,246,6,237,
-	57,52,62,2,55,251,201,209,225,243,219,72,
-	230,1,202,213,132,62,10,211,66,0,0,219,
-	66,230,192,194,213,132,229,62,1,50,106,137,
-	42,40,152,205,65,143,225,17,3,0,205,111,
-	136,62,6,211,66,58,44,152,211,66,237,56,
-	52,246,6,237,57,52,183,251,201,209,197,237,
-	56,52,230,248,237,57,52,219,72,230,1,32,
-	15,193,225,237,56,52,246,6,237,57,52,62,
-	1,55,251,201,14,23,58,37,152,254,0,40,
-	14,14,2,254,1,32,5,62,140,119,24,3,
-	62,132,119,43,43,197,205,203,135,193,62,1,
-	211,66,62,64,211,66,62,3,211,66,62,193,
-	211,66,62,100,203,39,71,219,66,230,1,32,
-	6,5,32,247,195,229,133,33,238,151,219,67,
-	71,58,44,152,184,194,229,133,119,62,100,71,
-	219,66,230,1,32,6,5,32,247,195,229,133,
-	219,67,35,119,13,32,234,193,225,62,1,50,
-	106,137,205,158,139,237,56,52,246,6,237,57,
-	52,175,183,251,201,33,234,151,35,35,62,255,
-	119,193,225,62,1,50,106,137,205,158,139,237,
-	56,52,246,6,237,57,52,175,251,201,243,61,
-	32,253,251,201,62,3,211,66,62,192,211,66,
-	58,49,152,254,140,32,19,197,229,213,17,181,
-	129,33,185,129,1,2,0,237,176,209,225,193,
-	24,27,229,213,33,187,129,58,49,152,230,15,
-	87,30,2,237,92,25,17,181,129,126,18,19,
-	35,126,18,209,225,58,34,152,246,8,211,68,
-	58,49,152,254,165,40,14,254,164,40,10,62,
-	10,211,66,62,224,211,66,24,25,58,74,152,
-	254,0,40,10,62,10,211,66,62,160,211,66,
-	24,8,62,10,211,66,62,128,211,66,62,11,
-	211,66,62,6,211,66,205,147,143,62,5,211,
-	66,62,224,211,66,62,5,211,66,62,96,211,
-	66,62,5,61,32,253,62,5,211,66,62,224,
-	211,66,62,14,61,32,253,62,5,211,66,62,
-	233,211,66,62,128,211,66,58,181,129,61,32,
-	253,62,1,211,66,62,192,211,66,1,254,19,
-	237,56,46,187,32,6,13,32,247,195,226,134,
-	62,192,211,66,0,0,219,66,203,119,40,250,
-	219,66,203,87,40,250,243,237,56,16,230,17,
-	237,57,16,237,56,20,251,62,5,211,66,62,
-	224,211,66,58,182,129,61,32,253,229,33,181,
-	129,58,183,129,203,63,119,35,58,184,129,119,
-	225,62,10,211,66,62,224,211,66,62,11,211,
-	66,62,118,211,66,62,47,211,68,62,5,211,
-	66,62,233,211,66,58,181,129,61,32,253,62,
-	5,211,66,62,224,211,66,58,182,129,61,32,
-	253,62,5,211,66,62,96,211,66,201,229,213,
-	58,50,152,230,15,87,30,2,237,92,33,187,
-	129,25,17,181,129,126,18,35,19,126,18,209,
-	225,58,71,152,246,8,211,68,58,50,152,254,
-	165,40,14,254,164,40,10,62,10,211,66,62,
-	224,211,66,24,8,62,10,211,66,62,128,211,
-	66,62,11,211,66,62,6,211,66,195,248,135,
-	62,3,211,66,62,192,211,66,197,229,213,17,
-	181,129,33,183,129,1,2,0,237,176,209,225,
-	193,62,47,211,68,62,10,211,66,62,224,211,
-	66,62,11,211,66,62,118,211,66,62,1,211,
-	66,62,0,211,66,205,147,143,195,16,136,62,
-	3,211,66,62,192,211,66,197,229,213,17,181,
-	129,33,183,129,1,2,0,237,176,209,225,193,
-	62,47,211,68,62,10,211,66,62,224,211,66,
-	62,11,211,66,62,118,211,66,205,147,143,62,
-	5,211,66,62,224,211,66,62,5,211,66,62,
-	96,211,66,62,5,61,32,253,62,5,211,66,
-	62,224,211,66,62,14,61,32,253,62,5,211,
-	66,62,233,211,66,62,128,211,66,58,181,129,
-	61,32,253,62,1,211,66,62,192,211,66,1,
-	254,19,237,56,46,187,32,6,13,32,247,195,
-	88,136,62,192,211,66,0,0,219,66,203,119,
-	40,250,219,66,203,87,40,250,62,5,211,66,
-	62,224,211,66,58,182,129,61,32,253,62,5,
-	211,66,62,96,211,66,201,197,14,67,6,0,
-	62,3,211,66,62,192,211,66,62,48,211,66,
-	0,0,219,66,230,1,40,4,219,67,24,240,
-	62,5,211,66,62,233,211,66,62,128,211,66,
-	58,181,129,61,32,253,237,163,29,62,192,211,
-	66,219,66,230,4,40,250,237,163,29,32,245,
-	219,66,230,4,40,250,62,255,71,219,66,230,
-	4,40,3,5,32,247,219,66,230,4,40,250,
-	62,5,211,66,62,224,211,66,58,182,129,61,
-	32,253,62,5,211,66,62,96,211,66,58,71,
-	152,254,1,202,18,137,62,16,211,66,62,56,
-	211,66,62,14,211,66,62,33,211,66,62,1,
-	211,66,62,248,211,66,237,56,48,246,153,230,
-	207,237,57,48,62,3,211,66,62,221,211,66,
-	193,201,58,71,152,211,68,62,10,211,66,62,
-	128,211,66,62,11,211,66,62,6,211,66,62,
-	6,211,66,58,44,152,211,66,62,16,211,66,
-	62,56,211,66,62,48,211,66,0,0,62,14,
-	211,66,62,33,211,66,62,1,211,66,62,248,
-	211,66,237,56,48,246,145,246,8,230,207,237,
-	57,48,62,3,211,66,62,221,211,66,193,201,
-	44,3,1,0,70,69,1,245,197,213,229,175,
-	50,72,152,237,56,16,230,46,237,57,16,237,
-	56,12,62,1,211,66,0,0,219,66,95,230,
-	160,32,3,195,20,139,123,230,96,194,72,139,
-	62,48,211,66,62,1,211,66,62,64,211,66,
-	237,91,40,152,205,207,143,25,43,55,237,82,
-	218,70,139,34,42,152,98,107,58,44,152,190,
-	194,210,138,35,35,62,130,190,194,200,137,62,
-	1,50,48,152,62,175,190,202,82,139,62,132,
-	190,32,44,50,50,152,62,47,50,71,152,229,
-	175,50,106,137,42,40,152,205,65,143,225,54,
-	133,43,70,58,44,152,119,43,112,17,3,0,
-	62,10,205,2,134,205,111,136,195,158,138,62,
-	140,190,32,19,50,50,152,58,233,149,230,4,
-	202,222,138,62,1,50,71,152,195,219,137,126,
-	254,160,250,185,138,254,166,242,185,138,50,50,
-	152,43,126,35,229,213,33,234,149,95,22,0,
-	25,126,254,132,40,18,254,140,40,14,58,50,
-	152,230,15,87,126,31,21,242,65,138,56,2,
-	175,119,58,50,152,230,15,87,58,233,149,230,
-	62,31,21,242,85,138,218,98,138,209,225,195,
-	20,139,58,50,152,33,100,137,230,15,95,22,
-	0,25,126,50,71,152,209,225,58,50,152,254,
-	164,250,135,138,58,73,152,254,0,40,4,54,
-	173,24,2,54,133,43,70,58,44,152,119,43,
-	112,17,3,0,205,70,135,175,50,106,137,205,
-	208,139,58,199,129,237,57,12,58,200,129,237,
-	57,13,237,56,16,246,17,237,57,16,225,209,
-	193,241,251,237,77,62,129,190,194,227,138,54,
-	130,43,70,58,44,152,119,43,112,17,3,0,
-	205,144,135,195,20,139,35,35,126,254,132,194,
-	227,138,175,50,106,137,205,158,139,24,42,58,
-	201,154,254,1,40,7,62,1,50,106,137,24,
-	237,58,106,137,254,1,202,222,138,62,128,166,
-	194,222,138,221,229,221,33,67,152,205,127,142,
-	205,109,144,221,225,225,209,193,241,251,237,77,
-	58,106,137,254,1,202,44,139,58,50,152,254,
-	164,250,44,139,58,73,152,238,1,50,73,152,
-	221,229,221,33,51,152,205,127,142,221,225,62,
-	1,50,106,137,205,158,139,195,13,139,24,208,
-	24,206,24,204,230,64,40,3,195,20,139,195,
-	20,139,43,126,33,8,152,119,35,58,44,152,
-	119,43,237,91,35,152,205,203,135,205,158,139,
-	195,13,139,175,50,78,152,62,3,211,66,62,
-	192,211,66,201,197,33,4,0,57,126,35,102,
-	111,62,1,50,106,137,219,72,205,141,139,193,
-	201,62,1,50,78,152,34,40,152,54,0,35,
-	35,54,0,195,163,139,58,78,152,183,200,229,
-	33,181,129,58,183,129,119,35,58,184,129,119,
-	225,62,47,211,68,62,14,211,66,62,193,211,
-	66,62,10,211,66,62,224,211,66,62,11,211,
-	66,62,118,211,66,195,3,140,58,78,152,183,
-	200,58,71,152,211,68,254,69,40,4,254,70,
-	32,17,58,73,152,254,0,40,10,62,10,211,
-	66,62,160,211,66,24,8,62,10,211,66,62,
-	128,211,66,62,11,211,66,62,6,211,66,62,
-	6,211,66,58,44,152,211,66,62,16,211,66,
-	62,56,211,66,62,48,211,66,0,0,219,66,
-	230,1,40,4,219,67,24,240,62,14,211,66,
-	62,33,211,66,42,40,152,205,65,143,62,1,
-	211,66,62,248,211,66,237,56,48,246,145,246,
-	8,230,207,237,57,48,62,3,211,66,62,221,
-	211,66,201,62,16,211,66,62,56,211,66,62,
-	48,211,66,0,0,219,66,230,1,40,4,219,
-	67,24,240,62,14,211,66,62,33,211,66,62,
-	1,211,66,62,248,211,66,237,56,48,246,153,
-	230,207,237,57,48,62,3,211,66,62,221,211,
-	66,201,229,213,33,234,149,95,22,0,25,126,
-	254,132,40,4,254,140,32,2,175,119,123,209,
-	225,201,6,8,14,0,31,48,1,12,16,250,
-	121,201,33,4,0,57,94,35,86,33,2,0,
-	57,126,35,102,111,221,229,34,89,152,237,83,
-	91,152,221,33,63,152,205,127,142,58,81,152,
-	50,82,152,58,80,152,135,50,80,152,205,162,
-	140,254,3,56,16,58,81,152,135,60,230,15,
-	50,81,152,175,50,80,152,24,23,58,79,152,
-	205,162,140,254,3,48,13,58,81,152,203,63,
-	50,81,152,62,255,50,79,152,58,81,152,50,
-	82,152,58,79,152,135,50,79,152,62,32,50,
-	83,152,50,84,152,237,56,16,230,17,237,57,
-	16,219,72,62,192,50,93,152,62,93,50,94,
-	152,58,93,152,61,50,93,152,32,9,58,94,
-	152,61,50,94,152,40,44,62,170,237,57,20,
-	175,237,57,21,237,56,16,246,2,237,57,16,
-	219,72,230,1,202,29,141,237,56,20,71,237,
-	56,21,120,254,10,48,237,237,56,16,230,17,
-	237,57,16,243,62,14,211,66,62,65,211,66,
-	251,58,39,152,23,23,60,50,39,152,71,58,
-	82,152,160,230,15,40,22,71,14,10,219,66,
-	230,16,202,186,141,219,72,230,1,202,186,141,
-	13,32,239,16,235,42,89,152,237,91,91,152,
-	205,47,131,48,7,61,202,186,141,195,227,141,
-	221,225,33,0,0,201,221,33,55,152,205,127,
-	142,58,84,152,61,50,84,152,40,19,58,82,
-	152,246,1,50,82,152,58,79,152,246,1,50,
-	79,152,195,29,141,221,225,33,1,0,201,221,
-	33,59,152,205,127,142,58,80,152,246,1,50,
-	80,152,58,82,152,135,246,1,50,82,152,58,
-	83,152,61,50,83,152,194,29,141,221,225,33,
-	2,0,201,221,229,33,0,0,57,17,4,0,
-	25,126,50,44,152,230,128,50,85,152,58,85,
-	152,183,40,6,221,33,88,2,24,4,221,33,
-	150,0,58,44,152,183,40,53,60,40,50,60,
-	40,47,61,61,33,86,152,119,35,119,35,54,
-	129,175,50,48,152,221,43,221,229,225,124,181,
-	40,42,33,86,152,17,3,0,205,189,140,17,
-	232,3,27,123,178,32,251,58,48,152,183,40,
-	224,58,44,152,71,62,7,128,230,127,71,58,
-	85,152,176,50,44,152,24,162,221,225,201,183,
-	221,52,0,192,221,52,1,192,221,52,2,192,
-	221,52,3,192,55,201,245,62,1,211,100,241,
-	201,245,62,1,211,96,241,201,33,2,0,57,
-	126,35,102,111,237,56,48,230,175,237,57,48,
-	62,48,237,57,49,125,237,57,32,124,237,57,
-	33,62,0,237,57,34,62,88,237,57,35,62,
-	0,237,57,36,237,57,37,33,128,2,125,237,
-	57,38,124,237,57,39,237,56,48,246,97,230,
-	207,237,57,48,62,0,237,57,0,62,0,211,
-	96,211,100,201,33,2,0,57,126,35,102,111,
-	237,56,48,230,175,237,57,48,62,12,237,57,
-	49,62,76,237,57,32,62,0,237,57,33,237,
-	57,34,125,237,57,35,124,237,57,36,62,0,
-	237,57,37,33,128,2,125,237,57,38,124,237,
-	57,39,237,56,48,246,97,230,207,237,57,48,
-	62,1,211,96,201,33,2,0,57,126,35,102,
-	111,229,237,56,48,230,87,237,57,48,125,237,
-	57,40,124,237,57,41,62,0,237,57,42,62,
-	67,237,57,43,62,0,237,57,44,58,106,137,
-	254,1,32,5,33,6,0,24,3,33,128,2,
-	125,237,57,46,124,237,57,47,237,56,50,230,
-	252,246,2,237,57,50,225,201,33,4,0,57,
-	94,35,86,33,2,0,57,126,35,102,111,237,
-	56,48,230,87,237,57,48,125,237,57,40,124,
-	237,57,41,62,0,237,57,42,62,67,237,57,
-	43,62,0,237,57,44,123,237,57,46,122,237,
-	57,47,237,56,50,230,244,246,0,237,57,50,
-	237,56,48,246,145,230,207,237,57,48,201,213,
-	237,56,46,95,237,56,47,87,237,56,46,111,
-	237,56,47,103,183,237,82,32,235,33,128,2,
-	183,237,82,209,201,213,237,56,38,95,237,56,
-	39,87,237,56,38,111,237,56,39,103,183,237,
-	82,32,235,33,128,2,183,237,82,209,201,245,
-	197,1,52,0,237,120,230,253,237,121,193,241,
-	201,245,197,1,52,0,237,120,246,2,237,121,
-	193,241,201,33,2,0,57,126,35,102,111,126,
-	35,110,103,201,33,0,0,34,102,152,34,96,
-	152,34,98,152,33,202,154,34,104,152,237,91,
-	104,152,42,226,149,183,237,82,17,0,255,25,
-	34,100,152,203,124,40,6,33,0,125,34,100,
-	152,42,104,152,35,35,35,229,205,120,139,193,
-	201,205,186,149,229,42,40,152,35,35,35,229,
-	205,39,144,193,124,230,3,103,221,117,254,221,
-	116,255,237,91,42,152,35,35,35,183,237,82,
-	32,12,17,5,0,42,42,152,205,171,149,242,
-	169,144,42,40,152,229,205,120,139,193,195,198,
-	149,237,91,42,152,42,98,152,25,34,98,152,
-	19,19,19,42,102,152,25,34,102,152,237,91,
-	100,152,33,158,253,25,237,91,102,152,205,171,
-	149,242,214,144,33,0,0,34,102,152,62,1,
-	50,95,152,205,225,144,195,198,149,58,95,152,
-	183,200,237,91,96,152,42,102,152,205,171,149,
-	242,5,145,237,91,102,152,33,98,2,25,237,
-	91,96,152,205,171,149,250,37,145,237,91,96,
-	152,42,102,152,183,237,82,32,7,42,98,152,
-	125,180,40,13,237,91,102,152,42,96,152,205,
-	171,149,242,58,145,237,91,104,152,42,102,152,
-	25,35,35,35,229,205,120,139,193,175,50,95,
-	152,201,195,107,139,205,206,149,250,255,243,205,
-	225,144,251,58,230,149,183,194,198,149,17,1,
-	0,42,98,152,205,171,149,250,198,149,62,1,
-	50,230,149,237,91,96,152,42,104,152,25,221,
-	117,252,221,116,253,237,91,104,152,42,96,152,
-	25,35,35,35,221,117,254,221,116,255,35,35,
-	35,229,205,39,144,124,230,3,103,35,35,35,
-	221,117,250,221,116,251,235,221,110,252,221,102,
-	253,115,35,114,35,54,4,62,1,211,100,211,
-	84,195,198,149,33,0,0,34,102,152,34,96,
-	152,34,98,152,33,202,154,34,104,152,237,91,
-	104,152,42,226,149,183,237,82,17,0,255,25,
-	34,100,152,33,109,152,54,0,33,107,152,229,
-	205,240,142,193,62,47,50,34,152,62,132,50,
-	49,152,205,241,145,205,61,145,58,39,152,60,
-	50,39,152,24,241,205,206,149,251,255,33,109,
-	152,126,183,202,198,149,110,221,117,251,33,109,
-	152,54,0,221,126,251,254,1,40,28,254,3,
-	40,101,254,4,202,190,147,254,5,202,147,147,
-	254,8,40,87,33,107,152,229,205,240,142,195,
-	198,149,58,201,154,183,32,21,33,111,152,126,
-	50,229,149,205,52,144,33,110,152,110,38,0,
-	229,205,11,142,193,237,91,96,152,42,104,152,
-	25,221,117,254,221,116,255,35,35,54,2,17,
-	2,0,43,43,115,35,114,58,44,152,35,35,
-	119,58,228,149,35,119,62,1,211,100,211,84,
-	62,1,50,201,154,24,169,205,153,142,58,231,
-	149,183,40,250,175,50,231,149,33,110,152,126,
-	254,255,40,91,58,233,149,230,63,183,40,83,
-	94,22,0,33,234,149,25,126,183,40,13,33,
-	110,152,94,33,234,150,25,126,254,3,32,36,
-	205,81,148,125,180,33,110,152,94,22,0,40,
-	17,33,234,149,25,54,0,33,107,152,229,205,
-	240,142,193,195,198,149,33,234,150,25,54,0,
-	33,110,152,94,22,0,33,234,149,25,126,50,
-	49,152,254,132,32,37,62,47,50,34,152,42,
-	107,152,229,33,110,152,229,205,174,140,193,193,
-	125,180,33,110,152,94,22,0,33,234,150,202,
-	117,147,25,52,195,120,147,58,49,152,254,140,
-	32,7,62,1,50,34,152,24,210,62,32,50,
-	106,152,24,19,58,49,152,95,58,106,152,163,
-	183,58,106,152,32,11,203,63,50,106,152,58,
-	106,152,183,32,231,254,2,40,51,254,4,40,
-	38,254,8,40,26,254,16,40,13,254,32,32,
-	158,62,165,50,49,152,62,69,24,190,62,164,
-	50,49,152,62,70,24,181,62,163,50,49,152,
-	175,24,173,62,162,50,49,152,62,1,24,164,
-	62,161,50,49,152,62,3,24,155,25,54,0,
-	221,126,251,254,8,40,7,58,230,149,183,202,
-	32,146,33,107,152,229,205,240,142,193,211,84,
-	195,198,149,237,91,96,152,42,104,152,25,221,
-	117,254,221,116,255,35,35,54,6,17,2,0,
-	43,43,115,35,114,58,228,149,35,35,119,58,
-	233,149,35,119,205,146,142,195,32,146,237,91,
-	96,152,42,104,152,25,229,205,160,142,193,58,
-	231,149,183,40,250,175,50,231,149,243,237,91,
-	96,152,42,104,152,25,221,117,254,221,116,255,
-	78,35,70,221,113,252,221,112,253,89,80,42,
-	98,152,183,237,82,34,98,152,203,124,40,19,
-	33,0,0,34,98,152,34,102,152,34,96,152,
-	62,1,50,95,152,24,40,221,94,252,221,86,
-	253,19,19,19,42,96,152,25,34,96,152,237,
-	91,100,152,33,158,253,25,237,91,96,152,205,
-	171,149,242,55,148,33,0,0,34,96,152,175,
-	50,230,149,251,195,32,146,245,62,1,50,231,
-	149,62,16,237,57,0,211,80,241,251,237,77,
-	201,205,186,149,229,229,33,0,0,34,37,152,
-	33,110,152,126,50,234,151,58,44,152,33,235,
-	151,119,221,54,253,0,221,54,254,0,195,230,
-	148,33,236,151,54,175,33,3,0,229,33,234,
-	151,229,205,174,140,193,193,33,236,151,126,254,
-	255,40,74,33,245,151,110,221,117,255,33,249,
-	151,126,221,166,255,221,119,255,33,253,151,126,
-	221,166,255,221,119,255,58,232,149,95,221,126,
-	255,163,221,119,255,183,40,15,230,191,33,110,
-	152,94,22,0,33,234,149,25,119,24,12,33,
-	110,152,94,22,0,33,234,149,25,54,132,33,
-	0,0,195,198,149,221,110,253,221,102,254,35,
-	221,117,253,221,116,254,17,32,0,221,110,253,
-	221,102,254,205,171,149,250,117,148,58,233,149,
-	203,87,40,84,33,1,0,34,37,152,221,54,
-	253,0,221,54,254,0,24,53,33,236,151,54,
-	175,33,3,0,229,33,234,151,229,205,174,140,
-	193,193,33,236,151,126,254,255,40,14,33,110,
-	152,94,22,0,33,234,149,25,54,140,24,159,
-	221,110,253,221,102,254,35,221,117,253,221,116,
-	254,17,32,0,221,110,253,221,102,254,205,171,
-	149,250,12,149,33,2,0,34,37,152,221,54,
-	253,0,221,54,254,0,24,54,33,236,151,54,
-	175,33,3,0,229,33,234,151,229,205,174,140,
-	193,193,33,236,151,126,254,255,40,15,33,110,
-	152,94,22,0,33,234,149,25,54,132,195,211,
-	148,221,110,253,221,102,254,35,221,117,253,221,
-	116,254,17,32,0,221,110,253,221,102,254,205,
-	171,149,250,96,149,33,1,0,195,198,149,124,
-	170,250,179,149,237,82,201,124,230,128,237,82,
-	60,201,225,253,229,221,229,221,33,0,0,221,
-	57,233,221,249,221,225,253,225,201,233,225,253,
-	229,221,229,221,33,0,0,221,57,94,35,86,
-	35,235,57,249,235,233,0,0,0,0,0,0,
-	62,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	175,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,133,1,0,0,0,63,
-	255,255,255,255,0,0,0,63,0,0,0,0,
-	0,0,0,0,0,0,0,24,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0
-	} ;
-
-#endif
diff --git a/drivers/net/appletalk/cops_ltdrv.h b/drivers/net/appletalk/cops_ltdrv.h
deleted file mode 100644
index c699b1ad31da..000000000000
--- a/drivers/net/appletalk/cops_ltdrv.h
+++ /dev/null
@@ -1,241 +0,0 @@
-/*
- *	The firmware this driver downloads into the Localtalk card is a
- *	separate program and is not GPL'd source code, even though the Linux
- *	side driver and the routine that loads this data into the card are.
- *	
- *	It is taken from the COPS SDK and is under the following license
- *
- *	This material is licensed to you strictly for use in conjunction with
- *	the use of COPS LocalTalk adapters.
- *	There is no charge for this SDK. And no waranty express or implied
- *	about its fitness for any purpose. However, we will cheerefully
- *	refund every penny you paid for this SDK...
- *	Regards,
- *
- *	Thomas F. Divine
- *	Chief Scientist
- */
-
-
-/*      cops_ltdrv.h: LocalTalk driver firmware dump for Linux.
- *
- *      Authors:
- *      - Jay Schulist <jschlst@samba.org>
- */
- 
-
-#ifdef CONFIG_COPS_TANGENT
-
-static const unsigned char ltdrv_code[] = {
-	58,3,0,50,148,10,33,143,15,62,85,119,
-	190,32,9,62,170,119,190,32,3,35,24,241,
-	34,146,10,249,17,150,10,33,143,15,183,237,
-	82,77,68,11,107,98,19,54,0,237,176,62,
-	16,237,57,51,62,0,237,57,50,237,57,54,
-	62,12,237,57,49,62,195,33,39,2,50,56,
-	0,34,57,0,237,86,205,30,2,251,205,60,
-	10,24,169,67,111,112,121,114,105,103,104,116,
-	32,40,99,41,32,49,57,56,56,45,49,57,
-	57,50,44,32,80,114,105,110,116,105,110,103,
-	32,67,111,109,109,117,110,105,99,97,116,105,
-	111,110,115,32,65,115,115,111,99,105,97,116,
-	101,115,44,32,73,110,99,46,65,108,108,32,
-	114,105,103,104,116,115,32,114,101,115,101,114,
-	118,101,100,46,32,32,4,4,22,40,255,60,
-	4,96,10,224,6,0,7,126,2,64,11,246,
-	12,6,13,0,14,193,15,0,5,96,3,192,
-	1,0,9,8,62,3,211,82,62,192,211,82,
-	201,62,3,211,82,62,213,211,82,201,62,5,
-	211,82,62,224,211,82,201,62,5,211,82,62,
-	224,211,82,201,62,5,211,82,62,96,211,82,
-	201,6,28,33,180,1,14,82,237,163,194,4,
-	2,33,39,2,34,64,0,58,3,0,230,1,
-	192,62,11,237,121,62,118,237,121,201,33,182,
-	10,54,132,205,253,1,201,245,197,213,229,42,
-	150,10,14,83,17,98,2,67,20,237,162,58,
-	179,1,95,219,82,230,1,32,6,29,32,247,
-	195,17,3,62,1,211,82,219,82,95,230,160,
-	32,10,237,162,32,225,21,32,222,195,15,3,
-	237,162,123,230,96,194,21,3,62,48,211,82,
-	62,1,211,82,175,211,82,237,91,150,10,43,
-	55,237,82,218,19,3,34,152,10,98,107,58,
-	154,10,190,32,81,62,1,50,158,10,35,35,
-	62,132,190,32,44,54,133,43,70,58,154,10,
-	119,43,112,17,3,0,205,137,3,62,16,211,
-	82,62,56,211,82,205,217,1,42,150,10,14,
-	83,17,98,2,67,20,58,178,1,95,195,59,
-	2,62,129,190,194,227,2,54,130,43,70,58,
-	154,10,119,43,112,17,3,0,205,137,3,195,
-	254,2,35,35,126,254,132,194,227,2,205,61,
-	3,24,20,62,128,166,194,222,2,221,229,221,
-	33,175,10,205,93,6,205,144,7,221,225,225,
-	209,193,241,251,237,77,221,229,221,33,159,10,
-	205,93,6,221,225,205,61,3,195,247,2,24,
-	237,24,235,24,233,230,64,40,2,24,227,24,
-	225,175,50,179,10,205,208,1,201,197,33,4,
-	0,57,126,35,102,111,205,51,3,193,201,62,
-	1,50,179,10,34,150,10,54,0,58,179,10,
-	183,200,62,14,211,82,62,193,211,82,62,10,
-	211,82,62,224,211,82,62,6,211,82,58,154,
-	10,211,82,62,16,211,82,62,56,211,82,62,
-	48,211,82,219,82,230,1,40,4,219,83,24,
-	242,62,14,211,82,62,33,211,82,62,1,211,
-	82,62,9,211,82,62,32,211,82,205,217,1,
-	201,14,83,205,208,1,24,23,14,83,205,208,
-	1,205,226,1,58,174,1,61,32,253,205,244,
-	1,58,174,1,61,32,253,205,226,1,58,175,
-	1,61,32,253,62,5,211,82,62,233,211,82,
-	62,128,211,82,58,176,1,61,32,253,237,163,
-	27,62,192,211,82,219,82,230,4,40,250,237,
-	163,27,122,179,32,243,219,82,230,4,40,250,
-	58,178,1,71,219,82,230,4,40,3,5,32,
-	247,219,82,230,4,40,250,205,235,1,58,177,
-	1,61,32,253,205,244,1,201,229,213,35,35,
-	126,230,128,194,145,4,43,58,154,10,119,43,
-	70,33,181,10,119,43,112,17,3,0,243,62,
-	10,211,82,219,82,230,128,202,41,4,209,225,
-	62,1,55,251,201,205,144,3,58,180,10,254,
-	255,202,127,4,205,217,1,58,178,1,71,219,
-	82,230,1,32,6,5,32,247,195,173,4,219,
-	83,71,58,154,10,184,194,173,4,58,178,1,
-	71,219,82,230,1,32,6,5,32,247,195,173,
-	4,219,83,58,178,1,71,219,82,230,1,32,
-	6,5,32,247,195,173,4,219,83,254,133,194,
-	173,4,58,179,1,24,4,58,179,1,135,61,
-	32,253,209,225,205,137,3,205,61,3,183,251,
-	201,209,225,243,62,10,211,82,219,82,230,128,
-	202,164,4,62,1,55,251,201,205,144,3,205,
-	61,3,183,251,201,209,225,62,2,55,251,201,
-	243,62,14,211,82,62,33,211,82,251,201,33,
-	4,0,57,94,35,86,33,2,0,57,126,35,
-	102,111,221,229,34,193,10,237,83,195,10,221,
-	33,171,10,205,93,6,58,185,10,50,186,10,
-	58,184,10,135,50,184,10,205,112,6,254,3,
-	56,16,58,185,10,135,60,230,15,50,185,10,
-	175,50,184,10,24,23,58,183,10,205,112,6,
-	254,3,48,13,58,185,10,203,63,50,185,10,
-	62,255,50,183,10,58,185,10,50,186,10,58,
-	183,10,135,50,183,10,62,32,50,187,10,50,
-	188,10,6,255,219,82,230,16,32,3,5,32,
-	247,205,180,4,6,40,219,82,230,16,40,3,
-	5,32,247,62,10,211,82,219,82,230,128,194,
-	46,5,219,82,230,16,40,214,237,95,71,58,
-	186,10,160,230,15,40,32,71,14,10,62,10,
-	211,82,219,82,230,128,202,119,5,205,180,4,
-	195,156,5,219,82,230,16,202,156,5,13,32,
-	229,16,225,42,193,10,237,91,195,10,205,252,
-	3,48,7,61,202,156,5,195,197,5,221,225,
-	33,0,0,201,221,33,163,10,205,93,6,58,
-	188,10,61,50,188,10,40,19,58,186,10,246,
-	1,50,186,10,58,183,10,246,1,50,183,10,
-	195,46,5,221,225,33,1,0,201,221,33,167,
-	10,205,93,6,58,184,10,246,1,50,184,10,
-	58,186,10,135,246,1,50,186,10,58,187,10,
-	61,50,187,10,194,46,5,221,225,33,2,0,
-	201,221,229,33,0,0,57,17,4,0,25,126,
-	50,154,10,230,128,50,189,10,58,189,10,183,
-	40,6,221,33,88,2,24,4,221,33,150,0,
-	58,154,10,183,40,49,60,40,46,61,33,190,
-	10,119,35,119,35,54,129,175,50,158,10,221,
-	43,221,229,225,124,181,40,42,33,190,10,17,
-	3,0,205,206,4,17,232,3,27,123,178,32,
-	251,58,158,10,183,40,224,58,154,10,71,62,
-	7,128,230,127,71,58,189,10,176,50,154,10,
-	24,166,221,225,201,183,221,52,0,192,221,52,
-	1,192,221,52,2,192,221,52,3,192,55,201,
-	6,8,14,0,31,48,1,12,16,250,121,201,
-	33,2,0,57,94,35,86,35,78,35,70,35,
-	126,35,102,105,79,120,68,103,237,176,201,33,
-	2,0,57,126,35,102,111,62,17,237,57,48,
-	125,237,57,40,124,237,57,41,62,0,237,57,
-	42,62,64,237,57,43,62,0,237,57,44,33,
-	128,2,125,237,57,46,124,237,57,47,62,145,
-	237,57,48,211,68,58,149,10,211,66,201,33,
-	2,0,57,126,35,102,111,62,33,237,57,48,
-	62,64,237,57,32,62,0,237,57,33,237,57,
-	34,125,237,57,35,124,237,57,36,62,0,237,
-	57,37,33,128,2,125,237,57,38,124,237,57,
-	39,62,97,237,57,48,211,67,58,149,10,211,
-	66,201,237,56,46,95,237,56,47,87,237,56,
-	46,111,237,56,47,103,183,237,82,32,235,33,
-	128,2,183,237,82,201,237,56,38,95,237,56,
-	39,87,237,56,38,111,237,56,39,103,183,237,
-	82,32,235,33,128,2,183,237,82,201,205,106,
-	10,221,110,6,221,102,7,126,35,110,103,195,
-	118,10,205,106,10,33,0,0,34,205,10,34,
-	198,10,34,200,10,33,143,15,34,207,10,237,
-	91,207,10,42,146,10,183,237,82,17,0,255,
-	25,34,203,10,203,124,40,6,33,0,125,34,
-	203,10,42,207,10,229,205,37,3,195,118,10,
-	205,106,10,229,42,150,10,35,35,35,229,205,
-	70,7,193,124,230,3,103,221,117,254,221,116,
-	255,237,91,152,10,35,35,35,183,237,82,32,
-	12,17,5,0,42,152,10,205,91,10,242,203,
-	7,42,150,10,229,205,37,3,195,118,10,237,
-	91,152,10,42,200,10,25,34,200,10,42,205,
-	10,25,34,205,10,237,91,203,10,33,158,253,
-	25,237,91,205,10,205,91,10,242,245,7,33,
-	0,0,34,205,10,62,1,50,197,10,205,5,
-	8,33,0,0,57,249,195,118,10,205,106,10,
-	58,197,10,183,202,118,10,237,91,198,10,42,
-	205,10,205,91,10,242,46,8,237,91,205,10,
-	33,98,2,25,237,91,198,10,205,91,10,250,
-	78,8,237,91,198,10,42,205,10,183,237,82,
-	32,7,42,200,10,125,180,40,13,237,91,205,
-	10,42,198,10,205,91,10,242,97,8,237,91,
-	207,10,42,205,10,25,229,205,37,3,175,50,
-	197,10,195,118,10,205,29,3,33,0,0,57,
-	249,195,118,10,205,106,10,58,202,10,183,40,
-	22,205,14,7,237,91,209,10,19,19,19,205,
-	91,10,242,139,8,33,1,0,195,118,10,33,
-	0,0,195,118,10,205,126,10,252,255,205,108,
-	8,125,180,194,118,10,237,91,200,10,33,0,
-	0,205,91,10,242,118,10,237,91,207,10,42,
-	198,10,25,221,117,254,221,116,255,35,35,35,
-	229,205,70,7,193,124,230,3,103,35,35,35,
-	221,117,252,221,116,253,229,221,110,254,221,102,
-	255,229,33,212,10,229,205,124,6,193,193,221,
-	110,252,221,102,253,34,209,10,33,211,10,54,
-	4,33,209,10,227,205,147,6,193,62,1,50,
-	202,10,243,221,94,252,221,86,253,42,200,10,
-	183,237,82,34,200,10,203,124,40,17,33,0,
-	0,34,200,10,34,205,10,34,198,10,50,197,
-	10,24,37,221,94,252,221,86,253,42,198,10,
-	25,34,198,10,237,91,203,10,33,158,253,25,
-	237,91,198,10,205,91,10,242,68,9,33,0,
-	0,34,198,10,205,5,8,33,0,0,57,249,
-	251,195,118,10,205,106,10,33,49,13,126,183,
-	40,16,205,42,7,237,91,47,13,19,19,19,
-	205,91,10,242,117,9,58,142,15,198,1,50,
-	142,15,195,118,10,33,49,13,126,254,1,40,
-	25,254,3,202,7,10,254,5,202,21,10,33,
-	49,13,54,0,33,47,13,229,205,207,6,195,
-	118,10,58,141,15,183,32,72,33,51,13,126,
-	50,149,10,205,86,7,33,50,13,126,230,127,
-	183,32,40,58,142,15,230,127,50,142,15,183,
-	32,5,198,1,50,142,15,33,50,13,126,111,
-	23,159,103,203,125,58,142,15,40,5,198,128,
-	50,142,15,33,50,13,119,33,50,13,126,111,
-	23,159,103,229,205,237,5,193,33,211,10,54,
-	2,33,2,0,34,209,10,58,154,10,33,212,
-	10,119,58,148,10,33,213,10,119,33,209,10,
-	229,205,147,6,193,24,128,42,47,13,229,33,
-	50,13,229,205,191,4,193,24,239,33,211,10,
-	54,6,33,3,0,34,209,10,58,154,10,33,
-	212,10,119,58,148,10,33,213,10,119,33,214,
-	10,54,5,33,209,10,229,205,147,6,24,200,
-	205,106,10,33,49,13,54,0,33,47,13,229,
-	205,207,6,33,209,10,227,205,147,6,193,205,
-	80,9,205,145,8,24,248,124,170,250,99,10,
-	237,82,201,124,230,128,237,82,60,201,225,253,
-	229,221,229,221,33,0,0,221,57,233,221,249,
-	221,225,253,225,201,233,225,253,229,221,229,221,
-	33,0,0,221,57,94,35,86,35,235,57,249,
-	235,233,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0
-	} ;
-
-#endif
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
deleted file mode 100644
index 10d0dba572c2..000000000000
--- a/drivers/net/appletalk/ipddp.c
+++ /dev/null
@@ -1,335 +0,0 @@
-/*
- *	ipddp.c: IP to Appletalk-IP Encapsulation driver for Linux
- *		 Appletalk-IP to IP Decapsulation driver for Linux
- *
- *	Authors:
- *      - DDP-IP Encap by: Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *	- DDP-IP Decap by: Jay Schulist <jschlst@samba.org>
- *
- *	Derived from:
- *	- Almost all code already existed in net/appletalk/ddp.c I just
- *	  moved/reorginized it into a driver file. Original IP-over-DDP code
- *	  was done by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *      - skeleton.c: A network driver outline for linux.
- *        Written 1993-94 by Donald Becker.
- *	- dummy.c: A dummy net driver. By Nick Holloway.
- *	- MacGate: A user space Daemon for Appletalk-IP Decap for
- *	  Linux by Jay Schulist <jschlst@samba.org>
- *
- *      Copyright 1993 United States Government as represented by the
- *      Director, National Security Agency.
- *
- *      This software may be used and distributed according to the terms
- *      of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/ip.h>
-#include <linux/atalk.h>
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <net/route.h>
-#include <asm/uaccess.h>
-
-#include "ipddp.h"		/* Our stuff */
-
-static const char version[] = KERN_INFO "ipddp.c:v0.01 8/28/97 Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n";
-
-static struct ipddp_route *ipddp_route_list;
-static DEFINE_SPINLOCK(ipddp_route_lock);
-
-#ifdef CONFIG_IPDDP_ENCAP
-static int ipddp_mode = IPDDP_ENCAP;
-#else
-static int ipddp_mode = IPDDP_DECAP;
-#endif
-
-/* Index to functions, as function prototypes. */
-static netdev_tx_t ipddp_xmit(struct sk_buff *skb,
-				    struct net_device *dev);
-static int ipddp_create(struct ipddp_route *new_rt);
-static int ipddp_delete(struct ipddp_route *rt);
-static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt);
-static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
-
-static const struct net_device_ops ipddp_netdev_ops = {
-	.ndo_start_xmit		= ipddp_xmit,
-	.ndo_do_ioctl   	= ipddp_ioctl,
-	.ndo_change_mtu		= eth_change_mtu,
-	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static struct net_device * __init ipddp_init(void)
-{
-	static unsigned version_printed;
-	struct net_device *dev;
-	int err;
-
-	dev = alloc_etherdev(0);
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
-	strcpy(dev->name, "ipddp%d");
-
-	if (version_printed++ == 0)
-                printk(version);
-
-	/* Initialize the device structure. */
-	dev->netdev_ops = &ipddp_netdev_ops;
-
-        dev->type = ARPHRD_IPDDP;       	/* IP over DDP tunnel */
-        dev->mtu = 585;
-        dev->flags |= IFF_NOARP;
-
-        /*
-         *      The worst case header we will need is currently a
-         *      ethernet header (14 bytes) and a ddp header (sizeof ddpehdr+1)
-         *      We send over SNAP so that takes another 8 bytes.
-         */
-        dev->hard_header_len = 14+8+sizeof(struct ddpehdr)+1;
-
-	err = register_netdev(dev);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
-
-	/* Let the user now what mode we are in */
-	if(ipddp_mode == IPDDP_ENCAP)
-		printk("%s: Appletalk-IP Encap. mode by Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n", 
-			dev->name);
-	if(ipddp_mode == IPDDP_DECAP)
-		printk("%s: Appletalk-IP Decap. mode by Jay Schulist <jschlst@samba.org>\n", 
-			dev->name);
-
-        return dev;
-}
-
-
-/*
- * Transmit LLAP/ELAP frame using aarp_send_ddp.
- */
-static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	__be32 paddr = skb_rtable(skb)->rt_gateway;
-        struct ddpehdr *ddp;
-        struct ipddp_route *rt;
-        struct atalk_addr *our_addr;
-
-	spin_lock(&ipddp_route_lock);
-
-	/*
-         * Find appropriate route to use, based only on IP number.
-         */
-        for(rt = ipddp_route_list; rt != NULL; rt = rt->next)
-        {
-                if(rt->ip == paddr)
-                        break;
-        }
-        if(rt == NULL) {
-		spin_unlock(&ipddp_route_lock);
-                return NETDEV_TX_OK;
-	}
-
-        our_addr = atalk_find_dev_addr(rt->dev);
-
-	if(ipddp_mode == IPDDP_DECAP)
-		/* 
-		 * Pull off the excess room that should not be there.
-		 * This is due to a hard-header problem. This is the
-		 * quick fix for now though, till it breaks.
-		 */
-		skb_pull(skb, 35-(sizeof(struct ddpehdr)+1));
-
-	/* Create the Extended DDP header */
-	ddp = (struct ddpehdr *)skb->data;
-        ddp->deh_len_hops = htons(skb->len + (1<<10));
-        ddp->deh_sum = 0;
-
-	/*
-         * For Localtalk we need aarp_send_ddp to strip the
-         * long DDP header and place a shot DDP header on it.
-         */
-        if(rt->dev->type == ARPHRD_LOCALTLK)
-        {
-                ddp->deh_dnet  = 0;   /* FIXME more hops?? */
-                ddp->deh_snet  = 0;
-        }
-        else
-        {
-                ddp->deh_dnet  = rt->at.s_net;   /* FIXME more hops?? */
-                ddp->deh_snet  = our_addr->s_net;
-        }
-        ddp->deh_dnode = rt->at.s_node;
-        ddp->deh_snode = our_addr->s_node;
-        ddp->deh_dport = 72;
-        ddp->deh_sport = 72;
-
-        *((__u8 *)(ddp+1)) = 22;        	/* ddp type = IP */
-
-        skb->protocol = htons(ETH_P_ATALK);     /* Protocol has changed */
-
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	aarp_send_ddp(rt->dev, skb, &rt->at, NULL);
-
-	spin_unlock(&ipddp_route_lock);
-
-        return NETDEV_TX_OK;
-}
-
-/*
- * Create a routing entry. We first verify that the
- * record does not already exist. If it does we return -EEXIST
- */
-static int ipddp_create(struct ipddp_route *new_rt)
-{
-        struct ipddp_route *rt = kmalloc(sizeof(*rt), GFP_KERNEL);
-
-        if (rt == NULL)
-                return -ENOMEM;
-
-        rt->ip = new_rt->ip;
-        rt->at = new_rt->at;
-        rt->next = NULL;
-        if ((rt->dev = atrtr_get_dev(&rt->at)) == NULL) {
-		kfree(rt);
-                return -ENETUNREACH;
-        }
-
-	spin_lock_bh(&ipddp_route_lock);
-	if (__ipddp_find_route(rt)) {
-		spin_unlock_bh(&ipddp_route_lock);
-		kfree(rt);
-		return -EEXIST;
-	}
-
-        rt->next = ipddp_route_list;
-        ipddp_route_list = rt;
-
-	spin_unlock_bh(&ipddp_route_lock);
-
-        return 0;
-}
-
-/*
- * Delete a route, we only delete a FULL match.
- * If route does not exist we return -ENOENT.
- */
-static int ipddp_delete(struct ipddp_route *rt)
-{
-        struct ipddp_route **r = &ipddp_route_list;
-        struct ipddp_route *tmp;
-
-	spin_lock_bh(&ipddp_route_lock);
-        while((tmp = *r) != NULL)
-        {
-                if(tmp->ip == rt->ip &&
-		   tmp->at.s_net == rt->at.s_net &&
-		   tmp->at.s_node == rt->at.s_node)
-                {
-                        *r = tmp->next;
-			spin_unlock_bh(&ipddp_route_lock);
-                        kfree(tmp);
-                        return 0;
-                }
-                r = &tmp->next;
-        }
-
-	spin_unlock_bh(&ipddp_route_lock);
-        return -ENOENT;
-}
-
-/*
- * Find a routing entry, we only return a FULL match
- */
-static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt)
-{
-        struct ipddp_route *f;
-
-        for(f = ipddp_route_list; f != NULL; f = f->next)
-        {
-                if(f->ip == rt->ip &&
-		   f->at.s_net == rt->at.s_net &&
-		   f->at.s_node == rt->at.s_node)
-                        return f;
-        }
-
-        return NULL;
-}
-
-static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-        struct ipddp_route __user *rt = ifr->ifr_data;
-        struct ipddp_route rcp, rcp2, *rp;
-
-        if(!capable(CAP_NET_ADMIN))
-                return -EPERM;
-
-	if(copy_from_user(&rcp, rt, sizeof(rcp)))
-		return -EFAULT;
-
-        switch(cmd)
-        {
-		case SIOCADDIPDDPRT:
-                        return ipddp_create(&rcp);
-
-                case SIOCFINDIPDDPRT:
-			spin_lock_bh(&ipddp_route_lock);
-			rp = __ipddp_find_route(&rcp);
-			if (rp)
-				memcpy(&rcp2, rp, sizeof(rcp2));
-			spin_unlock_bh(&ipddp_route_lock);
-
-			if (rp) {
-				if (copy_to_user(rt, &rcp2,
-						 sizeof(struct ipddp_route)))
-					return -EFAULT;
-				return 0;
-			} else
-				return -ENOENT;
-
-                case SIOCDELIPDDPRT:
-                        return ipddp_delete(&rcp);
-
-                default:
-                        return -EINVAL;
-        }
-}
-
-static struct net_device *dev_ipddp;
-
-MODULE_LICENSE("GPL");
-module_param(ipddp_mode, int, 0);
-
-static int __init ipddp_init_module(void)
-{
-	dev_ipddp = ipddp_init();
-        if (IS_ERR(dev_ipddp))
-                return PTR_ERR(dev_ipddp);
-	return 0;
-}
-
-static void __exit ipddp_cleanup_module(void)
-{
-        struct ipddp_route *p;
-
-	unregister_netdev(dev_ipddp);
-        free_netdev(dev_ipddp);
-
-        while (ipddp_route_list) {
-                p = ipddp_route_list->next;
-                kfree(ipddp_route_list);
-                ipddp_route_list = p;
-        }
-}
-
-module_init(ipddp_init_module);
-module_exit(ipddp_cleanup_module);
diff --git a/drivers/net/appletalk/ipddp.h b/drivers/net/appletalk/ipddp.h
deleted file mode 100644
index 531519da99a3..000000000000
--- a/drivers/net/appletalk/ipddp.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- *	ipddp.h: Header for IP-over-DDP driver for Linux.
- */
-
-#ifndef __LINUX_IPDDP_H
-#define __LINUX_IPDDP_H
-
-#ifdef __KERNEL__
-
-#define SIOCADDIPDDPRT   (SIOCDEVPRIVATE)
-#define SIOCDELIPDDPRT   (SIOCDEVPRIVATE+1)
-#define SIOCFINDIPDDPRT  (SIOCDEVPRIVATE+2)
-
-struct ipddp_route
-{
-        struct net_device *dev;             /* Carrier device */
-        __be32 ip;                       /* IP address */
-        struct atalk_addr at;              /* Gateway appletalk address */
-        int flags;
-        struct ipddp_route *next;
-};
-
-#define IPDDP_ENCAP	1
-#define IPDDP_DECAP	2
-
-#endif	/* __KERNEL__ */
-#endif	/* __LINUX_IPDDP_H */
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
deleted file mode 100644
index e69eead12ec7..000000000000
--- a/drivers/net/appletalk/ltpc.c
+++ /dev/null
@@ -1,1288 +0,0 @@
-/***    ltpc.c -- a driver for the LocalTalk PC card.
- *
- *      Copyright (c) 1995,1996 Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *
- *      This software may be used and distributed according to the terms
- *      of the GNU General Public License, incorporated herein by reference.
- *
- *      This is ALPHA code at best.  It may not work for you.  It may
- *      damage your equipment.  It may damage your relations with other
- *      users of your network.  Use it at your own risk!
- *
- *      Based in part on:
- *      skeleton.c      by Donald Becker
- *      dummy.c         by Nick Holloway and Alan Cox
- *      loopback.c      by Ross Biro, Fred van Kampen, Donald Becker
- *      the netatalk source code (UMICH)
- *      lots of work on the card...
- *
- *      I do not have access to the (proprietary) SDK that goes with the card.
- *      If you do, I don't want to know about it, and you can probably write
- *      a better driver yourself anyway.  This does mean that the pieces that
- *      talk to the card are guesswork on my part, so use at your own risk!
- *
- *      This is my first try at writing Linux networking code, and is also
- *      guesswork.  Again, use at your own risk!  (Although on this part, I'd
- *      welcome suggestions)
- *
- *      This is a loadable kernel module which seems to work at my site
- *      consisting of a 1.2.13 linux box running netatalk 1.3.3, and with
- *      the kernel support from 1.3.3b2 including patches routing.patch
- *      and ddp.disappears.from.chooser.  In order to run it, you will need
- *      to patch ddp.c and aarp.c in the kernel, but only a little...
- *
- *      I'm fairly confident that while this is arguably badly written, the
- *      problems that people experience will be "higher level", that is, with
- *      complications in the netatalk code.  The driver itself doesn't do
- *      anything terribly complicated -- it pretends to be an ether device
- *      as far as netatalk is concerned, strips the DDP data out of the ether
- *      frame and builds a LLAP packet to send out the card.  In the other
- *      direction, it receives LLAP frames from the card and builds a fake
- *      ether packet that it then tosses up to the networking code.  You can
- *      argue (correctly) that this is an ugly way to do things, but it
- *      requires a minimal amount of fooling with the code in ddp.c and aarp.c.
- *
- *      The card will do a lot more than is used here -- I *think* it has the
- *      layers up through ATP.  Even if you knew how that part works (which I
- *      don't) it would be a big job to carve up the kernel ddp code to insert
- *      things at a higher level, and probably a bad idea...
- *
- *      There are a number of other cards that do LocalTalk on the PC.  If
- *      nobody finds any insurmountable (at the netatalk level) problems
- *      here, this driver should encourage people to put some work into the
- *      other cards (some of which I gather are still commercially available)
- *      and also to put hooks for LocalTalk into the official ddp code.
- *
- *      I welcome comments and suggestions.  This is my first try at Linux
- *      networking stuff, and there are probably lots of things that I did
- *      suboptimally.  
- *
- ***/
-
-/***
- *
- * $Log: ltpc.c,v $
- * Revision 1.1.2.1  2000/03/01 05:35:07  jgarzik
- * at and tr cleanup
- *
- * Revision 1.8  1997/01/28 05:44:54  bradford
- * Clean up for non-module a little.
- * Hacked about a bit to clean things up - Alan Cox 
- * Probably broken it from the origina 1.8
- *
-
- * 1998/11/09: David Huggins-Daines <dhd@debian.org>
- * Cleaned up the initialization code to use the standard autoirq methods,
-   and to probe for things in the standard order of i/o, irq, dma.  This
-   removes the "reset the reset" hack, because I couldn't figure out an
-   easy way to get the card to trigger an interrupt after it.
- * Added support for passing configuration parameters on the kernel command
-   line and through insmod
- * Changed the device name from "ltalk0" to "lt0", both to conform with the
-   other localtalk driver, and to clear up the inconsistency between the
-   module and the non-module versions of the driver :-)
- * Added a bunch of comments (I was going to make some enums for the state
-   codes and the register offsets, but I'm still not sure exactly what their
-   semantics are)
- * Don't poll anymore in interrupt-driven mode
- * It seems to work as a module now (as of 2.1.127), but I don't think
-   I'm responsible for that...
-
- *
- * Revision 1.7  1996/12/12 03:42:33  bradford
- * DMA alloc cribbed from 3c505.c.
- *
- * Revision 1.6  1996/12/12 03:18:58  bradford
- * Added virt_to_bus; works in 2.1.13.
- *
- * Revision 1.5  1996/12/12 03:13:22  root
- * xmitQel initialization -- think through better though.
- *
- * Revision 1.4  1996/06/18 14:55:55  root
- * Change names to ltpc. Tabs. Took a shot at dma alloc,
- * although more needs to be done eventually.
- *
- * Revision 1.3  1996/05/22 14:59:39  root
- * Change dev->open, dev->close to track dummy.c in 1.99.(around 7)
- *
- * Revision 1.2  1996/05/22 14:58:24  root
- * Change tabs mostly.
- *
- * Revision 1.1  1996/04/23 04:45:09  root
- * Initial revision
- *
- * Revision 0.16  1996/03/05 15:59:56  root
- * Change ARPHRD_LOCALTLK definition to the "real" one.
- *
- * Revision 0.15  1996/03/05 06:28:30  root
- * Changes for kernel 1.3.70.  Still need a few patches to kernel, but
- * it's getting closer.
- *
- * Revision 0.14  1996/02/25 17:38:32  root
- * More cleanups.  Removed query to card on get_stats.
- *
- * Revision 0.13  1996/02/21  16:27:40  root
- * Refix debug_print_skb.  Fix mac.raw gotcha that appeared in 1.3.65.
- * Clean up receive code a little.
- *
- * Revision 0.12  1996/02/19  16:34:53  root
- * Fix debug_print_skb.  Kludge outgoing snet to 0 when using startup
- * range.  Change debug to mask: 1 for verbose, 2 for higher level stuff
- * including packet printing, 4 for lower level (card i/o) stuff.
- *
- * Revision 0.11  1996/02/12  15:53:38  root
- * Added router sends (requires new aarp.c patch)
- *
- * Revision 0.10  1996/02/11  00:19:35  root
- * Change source LTALK_LOGGING debug switch to insmod ... debug=2.
- *
- * Revision 0.9  1996/02/10  23:59:35  root
- * Fixed those fixes for 1.2 -- DANGER!  The at.h that comes with netatalk
- * has a *different* definition of struct sockaddr_at than the Linux kernel
- * does.  This is an "insidious and invidious" bug...
- * (Actually the preceding comment is false -- it's the atalk.h in the
- * ancient atalk-0.06 that's the problem)
- *
- * Revision 0.8  1996/02/10 19:09:00  root
- * Merge 1.3 changes.  Tested OK under 1.3.60.
- *
- * Revision 0.7  1996/02/10 17:56:56  root
- * Added debug=1 parameter on insmod for debugging prints.  Tried
- * to fix timer unload on rmmod, but I don't think that's the problem.
- *
- * Revision 0.6  1995/12/31  19:01:09  root
- * Clean up rmmod, irq comments per feedback from Corin Anderson (Thanks Corey!)
- * Clean up initial probing -- sometimes the card wakes up latched in reset.
- *
- * Revision 0.5  1995/12/22  06:03:44  root
- * Added comments in front and cleaned up a bit.
- * This version sent out to people.
- *
- * Revision 0.4  1995/12/18  03:46:44  root
- * Return shortDDP to longDDP fake to 0/0.  Added command structs.
- *
- ***/
-
-/* ltpc jumpers are:
-*
-*	Interrupts -- set at most one.  If none are set, the driver uses
-*	polled mode.  Because the card was developed in the XT era, the
-*	original documentation refers to IRQ2.  Since you'll be running
-*	this on an AT (or later) class machine, that really means IRQ9.
-*
-*	SW1	IRQ 4
-*	SW2	IRQ 3
-*	SW3	IRQ 9 (2 in original card documentation only applies to XT)
-*
-*
-*	DMA -- choose DMA 1 or 3, and set both corresponding switches.
-*
-*	SW4	DMA 3
-*	SW5	DMA 1
-*	SW6	DMA 3
-*	SW7	DMA 1
-*
-*
-*	I/O address -- choose one.  
-*
-*	SW8	220 / 240
-*/
-
-/*	To have some stuff logged, do 
-*	insmod ltpc.o debug=1
-*
-*	For a whole bunch of stuff, use higher numbers.
-*
-*	The default is 0, i.e. no messages except for the probe results.
-*/
-
-/* insmod-tweakable variables */
-static int debug;
-#define DEBUG_VERBOSE 1
-#define DEBUG_UPPER 2
-#define DEBUG_LOWER 4
-
-static int io;
-static int irq;
-static int dma;
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/spinlock.h>
-#include <linux/in.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_ltalk.h>
-#include <linux/delay.h>
-#include <linux/timer.h>
-#include <linux/atalk.h>
-#include <linux/bitops.h>
-#include <linux/gfp.h>
-
-#include <asm/system.h>
-#include <asm/dma.h>
-#include <asm/io.h>
-
-/* our stuff */
-#include "ltpc.h"
-
-static DEFINE_SPINLOCK(txqueue_lock);
-static DEFINE_SPINLOCK(mbox_lock);
-
-/* function prototypes */
-static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
-	void *dbuf, int dbuflen);
-static int sendup_buffer (struct net_device *dev);
-
-/* Dma Memory related stuff, cribbed directly from 3c505.c */
-
-static unsigned long dma_mem_alloc(int size)
-{
-        int order = get_order(size);
-
-        return __get_dma_pages(GFP_KERNEL, order);
-}
-
-/* DMA data buffer, DMA command buffer */
-static unsigned char *ltdmabuf;
-static unsigned char *ltdmacbuf;
-
-/* private struct, holds our appletalk address */
-
-struct ltpc_private
-{
-	struct atalk_addr my_addr;
-};
-
-/* transmit queue element struct */
-
-struct xmitQel {
-	struct xmitQel *next;
-	/* command buffer */
-	unsigned char *cbuf;
-	short cbuflen;
-	/* data buffer */
-	unsigned char *dbuf;
-	short dbuflen;
-	unsigned char QWrite;	/* read or write data */
-	unsigned char mailbox;
-};
-
-/* the transmit queue itself */
-
-static struct xmitQel *xmQhd, *xmQtl;
-
-static void enQ(struct xmitQel *qel)
-{
-	unsigned long flags;
-	qel->next = NULL;
-	
-	spin_lock_irqsave(&txqueue_lock, flags);
-	if (xmQtl) {
-		xmQtl->next = qel;
-	} else {
-		xmQhd = qel;
-	}
-	xmQtl = qel;
-	spin_unlock_irqrestore(&txqueue_lock, flags);
-
-	if (debug & DEBUG_LOWER)
-		printk("enqueued a 0x%02x command\n",qel->cbuf[0]);
-}
-
-static struct xmitQel *deQ(void)
-{
-	unsigned long flags;
-	int i;
-	struct xmitQel *qel=NULL;
-	
-	spin_lock_irqsave(&txqueue_lock, flags);
-	if (xmQhd) {
-		qel = xmQhd;
-		xmQhd = qel->next;
-		if(!xmQhd) xmQtl = NULL;
-	}
-	spin_unlock_irqrestore(&txqueue_lock, flags);
-
-	if ((debug & DEBUG_LOWER) && qel) {
-		int n;
-		printk(KERN_DEBUG "ltpc: dequeued command ");
-		n = qel->cbuflen;
-		if (n>100) n=100;
-		for(i=0;i<n;i++) printk("%02x ",qel->cbuf[i]);
-		printk("\n");
-	}
-
-	return qel;
-}
-
-/* and... the queue elements we'll be using */
-static struct xmitQel qels[16];
-
-/* and their corresponding mailboxes */
-static unsigned char mailbox[16];
-static unsigned char mboxinuse[16] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};
-
-static int wait_timeout(struct net_device *dev, int c)
-{
-	/* returns true if it stayed c */
-	/* this uses base+6, but it's ok */
-	int i;
-
-	/* twenty second or so total */
-
-	for(i=0;i<200000;i++) {
-		if ( c != inb_p(dev->base_addr+6) ) return 0;
-		udelay(100);
-	}
-	return 1; /* timed out */
-}
-
-/* get the first free mailbox */
-
-static int getmbox(void)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&mbox_lock, flags);
-	for(i=1;i<16;i++) if(!mboxinuse[i]) {
-		mboxinuse[i]=1;
-		spin_unlock_irqrestore(&mbox_lock, flags);
-		return i;
-	}
-	spin_unlock_irqrestore(&mbox_lock, flags);
-	return 0;
-}
-
-/* read a command from the card */
-static void handlefc(struct net_device *dev)
-{
-	/* called *only* from idle, non-reentrant */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
-	set_dma_count(dma,50);
-	enable_dma(dma);
-	release_dma_lock(flags);
-
-	inb_p(base+3);
-	inb_p(base+2);
-
-	if ( wait_timeout(dev,0xfc) ) printk("timed out in handlefc\n");
-}
-
-/* read data from the card */
-static void handlefd(struct net_device *dev)
-{
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,800);
-	enable_dma(dma);
-	release_dma_lock(flags);
-
-	inb_p(base+3);
-	inb_p(base+2);
-
-	if ( wait_timeout(dev,0xfd) ) printk("timed out in handlefd\n");
-	sendup_buffer(dev);
-} 
-
-static void handlewrite(struct net_device *dev)
-{
-	/* called *only* from idle, non-reentrant */
-	/* on entry, 0xfb and ltdmabuf holds data */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-	
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_WRITE);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,800);
-	enable_dma(dma);
-	release_dma_lock(flags);
-	
-	inb_p(base+3);
-	inb_p(base+2);
-
-	if ( wait_timeout(dev,0xfb) ) {
-		flags=claim_dma_lock();
-		printk("timed out in handlewrite, dma res %d\n",
-			get_dma_residue(dev->dma) );
-		release_dma_lock(flags);
-	}
-}
-
-static void handleread(struct net_device *dev)
-{
-	/* on entry, 0xfb */
-	/* on exit, ltdmabuf holds data */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-	
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,800);
-	enable_dma(dma);
-	release_dma_lock(flags);
-
-	inb_p(base+3);
-	inb_p(base+2);
-	if ( wait_timeout(dev,0xfb) ) printk("timed out in handleread\n");
-}
-
-static void handlecommand(struct net_device *dev)
-{
-	/* on entry, 0xfa and ltdmacbuf holds command */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_WRITE);
-	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
-	set_dma_count(dma,50);
-	enable_dma(dma);
-	release_dma_lock(flags);
-	inb_p(base+3);
-	inb_p(base+2);
-	if ( wait_timeout(dev,0xfa) ) printk("timed out in handlecommand\n");
-} 
-
-/* ready made command for getting the result from the card */
-static unsigned char rescbuf[2] = {LT_GETRESULT,0};
-static unsigned char resdbuf[2];
-
-static int QInIdle;
-
-/* idle expects to be called with the IRQ line high -- either because of
- * an interrupt, or because the line is tri-stated
- */
-
-static void idle(struct net_device *dev)
-{
-	unsigned long flags;
-	int state;
-	/* FIXME This is initialized to shut the warning up, but I need to
-	 * think this through again.
-	 */
-	struct xmitQel *q = NULL;
-	int oops;
-	int i;
-	int base = dev->base_addr;
-
-	spin_lock_irqsave(&txqueue_lock, flags);
-	if(QInIdle) {
-		spin_unlock_irqrestore(&txqueue_lock, flags);
-		return;
-	}
-	QInIdle = 1;
-	spin_unlock_irqrestore(&txqueue_lock, flags);
-
-	/* this tri-states the IRQ line */
-	(void) inb_p(base+6);
-
-	oops = 100;
-
-loop:
-	if (0>oops--) { 
-		printk("idle: looped too many times\n");
-		goto done;
-	}
-
-	state = inb_p(base+6);
-	if (state != inb_p(base+6)) goto loop;
-
-	switch(state) {
-		case 0xfc:
-			/* incoming command */
-			if (debug & DEBUG_LOWER) printk("idle: fc\n");
-			handlefc(dev); 
-			break;
-		case 0xfd:
-			/* incoming data */
-			if(debug & DEBUG_LOWER) printk("idle: fd\n");
-			handlefd(dev); 
-			break;
-		case 0xf9:
-			/* result ready */
-			if (debug & DEBUG_LOWER) printk("idle: f9\n");
-			if(!mboxinuse[0]) {
-				mboxinuse[0] = 1;
-				qels[0].cbuf = rescbuf;
-				qels[0].cbuflen = 2;
-				qels[0].dbuf = resdbuf;
-				qels[0].dbuflen = 2;
-				qels[0].QWrite = 0;
-				qels[0].mailbox = 0;
-				enQ(&qels[0]);
-			}
-			inb_p(dev->base_addr+1);
-			inb_p(dev->base_addr+0);
-			if( wait_timeout(dev,0xf9) )
-				printk("timed out idle f9\n");
-			break;
-		case 0xf8:
-			/* ?? */
-			if (xmQhd) {
-				inb_p(dev->base_addr+1);
-				inb_p(dev->base_addr+0);
-				if(wait_timeout(dev,0xf8) )
-					printk("timed out idle f8\n");
-			} else {
-				goto done;
-			}
-			break;
-		case 0xfa:
-			/* waiting for command */
-			if(debug & DEBUG_LOWER) printk("idle: fa\n");
-			if (xmQhd) {
-				q=deQ();
-				memcpy(ltdmacbuf,q->cbuf,q->cbuflen);
-				ltdmacbuf[1] = q->mailbox;
-				if (debug>1) { 
-					int n;
-					printk("ltpc: sent command     ");
-					n = q->cbuflen;
-					if (n>100) n=100;
-					for(i=0;i<n;i++)
-						printk("%02x ",ltdmacbuf[i]);
-					printk("\n");
-				}
-				handlecommand(dev);
-					if(0xfa==inb_p(base+6)) {
-						/* we timed out, so return */
-						goto done;
-					} 
-			} else {
-				/* we don't seem to have a command */
-				if (!mboxinuse[0]) {
-					mboxinuse[0] = 1;
-					qels[0].cbuf = rescbuf;
-					qels[0].cbuflen = 2;
-					qels[0].dbuf = resdbuf;
-					qels[0].dbuflen = 2;
-					qels[0].QWrite = 0;
-					qels[0].mailbox = 0;
-					enQ(&qels[0]);
-				} else {
-					printk("trouble: response command already queued\n");
-					goto done;
-				}
-			} 
-			break;
-		case 0Xfb:
-			/* data transfer ready */
-			if(debug & DEBUG_LOWER) printk("idle: fb\n");
-			if(q->QWrite) {
-				memcpy(ltdmabuf,q->dbuf,q->dbuflen);
-				handlewrite(dev);
-			} else {
-				handleread(dev);
-				/* non-zero mailbox numbers are for
-				   commmands, 0 is for GETRESULT
-				   requests */
-				if(q->mailbox) {
-					memcpy(q->dbuf,ltdmabuf,q->dbuflen);
-				} else { 
-					/* this was a result */
-					mailbox[ 0x0f & ltdmabuf[0] ] = ltdmabuf[1];
-					mboxinuse[0]=0;
-				}
-			}
-			break;
-	}
-	goto loop;
-
-done:
-	QInIdle=0;
-
-	/* now set the interrupts back as appropriate */
-	/* the first read takes it out of tri-state (but still high) */
-	/* the second resets it */
-	/* note that after this point, any read of base+6 will
-	   trigger an interrupt */
-
-	if (dev->irq) {
-		inb_p(base+7);
-		inb_p(base+7);
-	}
-}
-
-
-static int do_write(struct net_device *dev, void *cbuf, int cbuflen,
-	void *dbuf, int dbuflen)
-{
-
-	int i = getmbox();
-	int ret;
-
-	if(i) {
-		qels[i].cbuf = (unsigned char *) cbuf;
-		qels[i].cbuflen = cbuflen;
-		qels[i].dbuf = (unsigned char *) dbuf;
-		qels[i].dbuflen = dbuflen;
-		qels[i].QWrite = 1;
-		qels[i].mailbox = i;  /* this should be initted rather */
-		enQ(&qels[i]);
-		idle(dev);
-		ret = mailbox[i];
-		mboxinuse[i]=0;
-		return ret;
-	}
-	printk("ltpc: could not allocate mbox\n");
-	return -1;
-}
-
-static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
-	void *dbuf, int dbuflen)
-{
-
-	int i = getmbox();
-	int ret;
-
-	if(i) {
-		qels[i].cbuf = (unsigned char *) cbuf;
-		qels[i].cbuflen = cbuflen;
-		qels[i].dbuf = (unsigned char *) dbuf;
-		qels[i].dbuflen = dbuflen;
-		qels[i].QWrite = 0;
-		qels[i].mailbox = i;  /* this should be initted rather */
-		enQ(&qels[i]);
-		idle(dev);
-		ret = mailbox[i];
-		mboxinuse[i]=0;
-		return ret;
-	}
-	printk("ltpc: could not allocate mbox\n");
-	return -1;
-}
-
-/* end of idle handlers -- what should be seen is do_read, do_write */
-
-static struct timer_list ltpc_timer;
-
-static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev);
-
-static int read_30 ( struct net_device *dev)
-{
-	lt_command c;
-	c.getflags.command = LT_GETFLAGS;
-	return do_read(dev, &c, sizeof(c.getflags),&c,0);
-}
-
-static int set_30 (struct net_device *dev,int x)
-{
-	lt_command c;
-	c.setflags.command = LT_SETFLAGS;
-	c.setflags.flags = x;
-	return do_write(dev, &c, sizeof(c.setflags),&c,0);
-}
-
-/* LLAP to DDP translation */
-
-static int sendup_buffer (struct net_device *dev)
-{
-	/* on entry, command is in ltdmacbuf, data in ltdmabuf */
-	/* called from idle, non-reentrant */
-
-	int dnode, snode, llaptype, len; 
-	int sklen;
-	struct sk_buff *skb;
-	struct lt_rcvlap *ltc = (struct lt_rcvlap *) ltdmacbuf;
-
-	if (ltc->command != LT_RCVLAP) {
-		printk("unknown command 0x%02x from ltpc card\n",ltc->command);
-		return -1;
-	}
-	dnode = ltc->dnode;
-	snode = ltc->snode;
-	llaptype = ltc->laptype;
-	len = ltc->length; 
-
-	sklen = len;
-	if (llaptype == 1) 
-		sklen += 8;  /* correct for short ddp */
-	if(sklen > 800) {
-		printk(KERN_INFO "%s: nonsense length in ltpc command 0x14: 0x%08x\n",
-			dev->name,sklen);
-		return -1;
-	}
-
-	if ( (llaptype==0) || (llaptype>2) ) {
-		printk(KERN_INFO "%s: unknown LLAP type: %d\n",dev->name,llaptype);
-		return -1;
-	}
-
-
-	skb = dev_alloc_skb(3+sklen);
-	if (skb == NULL) 
-	{
-		printk("%s: dropping packet due to memory squeeze.\n",
-			dev->name);
-		return -1;
-	}
-	skb->dev = dev;
-
-	if (sklen > len)
-		skb_reserve(skb,8);
-	skb_put(skb,len+3);
-	skb->protocol = htons(ETH_P_LOCALTALK);
-	/* add LLAP header */
-	skb->data[0] = dnode;
-	skb->data[1] = snode;
-	skb->data[2] = llaptype;
-	skb_reset_mac_header(skb);	/* save pointer to llap header */
-	skb_pull(skb,3);
-
-	/* copy ddp(s,e)hdr + contents */
-	skb_copy_to_linear_data(skb, ltdmabuf, len);
-
-	skb_reset_transport_header(skb);
-
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += skb->len;
-
-	/* toss it onwards */
-	netif_rx(skb);
-	return 0;
-}
-
-/* the handler for the board interrupt */
- 
-static irqreturn_t
-ltpc_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-
-	if (dev==NULL) {
-		printk("ltpc_interrupt: unknown device.\n");
-		return IRQ_NONE;
-	}
-
-	inb_p(dev->base_addr+6);  /* disable further interrupts from board */
-
-	idle(dev); /* handle whatever is coming in */
- 
-	/* idle re-enables interrupts from board */ 
-
-	return IRQ_HANDLED;
-}
-
-/***
- *
- *    The ioctls that the driver responds to are:
- *
- *    SIOCSIFADDR -- do probe using the passed node hint.
- *    SIOCGIFADDR -- return net, node.
- *
- *    some of this stuff should be done elsewhere.
- *
- ***/
-
-static int ltpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct sockaddr_at *sa = (struct sockaddr_at *) &ifr->ifr_addr;
-	/* we'll keep the localtalk node address in dev->pa_addr */
-	struct ltpc_private *ltpc_priv = netdev_priv(dev);
-	struct atalk_addr *aa = &ltpc_priv->my_addr;
-	struct lt_init c;
-	int ltflags;
-
-	if(debug & DEBUG_VERBOSE) printk("ltpc_ioctl called\n");
-
-	switch(cmd) {
-		case SIOCSIFADDR:
-
-			aa->s_net  = sa->sat_addr.s_net;
-      
-			/* this does the probe and returns the node addr */
-			c.command = LT_INIT;
-			c.hint = sa->sat_addr.s_node;
-
-			aa->s_node = do_read(dev,&c,sizeof(c),&c,0);
-
-			/* get all llap frames raw */
-			ltflags = read_30(dev);
-			ltflags |= LT_FLAG_ALLLAP;
-			set_30 (dev,ltflags);  
-
-			dev->broadcast[0] = 0xFF;
-			dev->dev_addr[0] = aa->s_node;
-
-			dev->addr_len=1;
-   
-			return 0;
-
-		case SIOCGIFADDR:
-
-			sa->sat_addr.s_net = aa->s_net;
-			sa->sat_addr.s_node = aa->s_node;
-
-			return 0;
-
-		default: 
-			return -EINVAL;
-	}
-}
-
-static void set_multicast_list(struct net_device *dev)
-{
-	/* This needs to be present to keep netatalk happy. */
-	/* Actually netatalk needs fixing! */
-}
-
-static int ltpc_poll_counter;
-
-static void ltpc_poll(unsigned long l)
-{
-	struct net_device *dev = (struct net_device *) l;
-
-	del_timer(&ltpc_timer);
-
-	if(debug & DEBUG_VERBOSE) {
-		if (!ltpc_poll_counter) {
-			ltpc_poll_counter = 50;
-			printk("ltpc poll is alive\n");
-		}
-		ltpc_poll_counter--;
-	}
-  
-	if (!dev)
-		return;  /* we've been downed */
-
-	/* poll 20 times per second */
-	idle(dev);
-	ltpc_timer.expires = jiffies + HZ/20;
-	
-	add_timer(&ltpc_timer);
-}
-
-/* DDP to LLAP translation */
-
-static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	/* in kernel 1.3.xx, on entry skb->data points to ddp header,
-	 * and skb->len is the length of the ddp data + ddp header
-	 */
-	int i;
-	struct lt_sendlap cbuf;
-	unsigned char *hdr;
-
-	cbuf.command = LT_SENDLAP;
-	cbuf.dnode = skb->data[0];
-	cbuf.laptype = skb->data[2];
-	skb_pull(skb,3);	/* skip past LLAP header */
-	cbuf.length = skb->len;	/* this is host order */
-	skb_reset_transport_header(skb);
-
-	if(debug & DEBUG_UPPER) {
-		printk("command ");
-		for(i=0;i<6;i++)
-			printk("%02x ",((unsigned char *)&cbuf)[i]);
-		printk("\n");
-	}
-
-	hdr = skb_transport_header(skb);
-	do_write(dev, &cbuf, sizeof(cbuf), hdr, skb->len);
-
-	if(debug & DEBUG_UPPER) {
-		printk("sent %d ddp bytes\n",skb->len);
-		for (i = 0; i < skb->len; i++)
-			printk("%02x ", hdr[i]);
-		printk("\n");
-	}
-
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-}
-
-/* initialization stuff */
-  
-static int __init ltpc_probe_dma(int base, int dma)
-{
-	int want = (dma == 3) ? 2 : (dma == 1) ? 1 : 3;
-  	unsigned long timeout;
-  	unsigned long f;
-  
-  	if (want & 1) {
-		if (request_dma(1,"ltpc")) {
-			want &= ~1;
-		} else {
-			f=claim_dma_lock();
-			disable_dma(1);
-			clear_dma_ff(1);
-			set_dma_mode(1,DMA_MODE_WRITE);
-			set_dma_addr(1,virt_to_bus(ltdmabuf));
-			set_dma_count(1,sizeof(struct lt_mem));
-			enable_dma(1);
-			release_dma_lock(f);
-		}
-	}
-	if (want & 2) {
-		if (request_dma(3,"ltpc")) {
-			want &= ~2;
-		} else {
-			f=claim_dma_lock();
-			disable_dma(3);
-			clear_dma_ff(3);
-			set_dma_mode(3,DMA_MODE_WRITE);
-			set_dma_addr(3,virt_to_bus(ltdmabuf));
-			set_dma_count(3,sizeof(struct lt_mem));
-			enable_dma(3);
-			release_dma_lock(f);
-		}
-	}
-	/* set up request */
-
-	/* FIXME -- do timings better! */
-
-	ltdmabuf[0] = LT_READMEM;
-	ltdmabuf[1] = 1;  /* mailbox */
-	ltdmabuf[2] = 0; ltdmabuf[3] = 0;  /* address */
-	ltdmabuf[4] = 0; ltdmabuf[5] = 1;  /* read 0x0100 bytes */
-	ltdmabuf[6] = 0; /* dunno if this is necessary */
-
-	inb_p(io+1);
-	inb_p(io+0);
-	timeout = jiffies+100*HZ/100;
-	while(time_before(jiffies, timeout)) {
-		if ( 0xfa == inb_p(io+6) ) break;
-	}
-
-	inb_p(io+3);
-	inb_p(io+2);
-	while(time_before(jiffies, timeout)) {
-		if ( 0xfb == inb_p(io+6) ) break;
-	}
-
-	/* release the other dma channel (if we opened both of them) */
-
-	if ((want & 2) && (get_dma_residue(3)==sizeof(struct lt_mem))) {
-		want &= ~2;
-		free_dma(3);
-	}
-
-	if ((want & 1) && (get_dma_residue(1)==sizeof(struct lt_mem))) {
-		want &= ~1;
-		free_dma(1);
-	}
-
-	if (!want)
-		return 0;
-
-	return (want & 2) ? 3 : 1;
-}
-
-static const struct net_device_ops ltpc_netdev = {
-	.ndo_start_xmit		= ltpc_xmit,
-	.ndo_do_ioctl		= ltpc_ioctl,
-	.ndo_set_multicast_list = set_multicast_list,
-};
-
-struct net_device * __init ltpc_probe(void)
-{
-	struct net_device *dev;
-	int err = -ENOMEM;
-	int x=0,y=0;
-	int autoirq;
-	unsigned long f;
-	unsigned long timeout;
-
-	dev = alloc_ltalkdev(sizeof(struct ltpc_private));
-	if (!dev)
-		goto out;
-
-	/* probe for the I/O port address */
-	
-	if (io != 0x240 && request_region(0x220,8,"ltpc")) {
-		x = inb_p(0x220+6);
-		if ( (x!=0xff) && (x>=0xf0) ) {
-			io = 0x220;
-			goto got_port;
-		}
-		release_region(0x220,8);
-	}
-	if (io != 0x220 && request_region(0x240,8,"ltpc")) {
-		y = inb_p(0x240+6);
-		if ( (y!=0xff) && (y>=0xf0) ){ 
-			io = 0x240;
-			goto got_port;
-		}
-		release_region(0x240,8);
-	} 
-
-	/* give up in despair */
-	printk(KERN_ERR "LocalTalk card not found; 220 = %02x, 240 = %02x.\n", x,y);
-	err = -ENODEV;
-	goto out1;
-
- got_port:
-	/* probe for the IRQ line */
-	if (irq < 2) {
-		unsigned long irq_mask;
-
-		irq_mask = probe_irq_on();
-		/* reset the interrupt line */
-		inb_p(io+7);
-		inb_p(io+7);
-		/* trigger an interrupt (I hope) */
-		inb_p(io+6);
-		mdelay(2);
-		autoirq = probe_irq_off(irq_mask);
-
-		if (autoirq == 0) {
-			printk(KERN_ERR "ltpc: probe at %#x failed to detect IRQ line.\n", io);
-		} else {
-			irq = autoirq;
-		}
-	}
-
-	/* allocate a DMA buffer */
-	ltdmabuf = (unsigned char *) dma_mem_alloc(1000);
-	if (!ltdmabuf) {
-		printk(KERN_ERR "ltpc: mem alloc failed\n");
-		err = -ENOMEM;
-		goto out2;
-	}
-
-	ltdmacbuf = &ltdmabuf[800];
-
-	if(debug & DEBUG_VERBOSE) {
-		printk("ltdmabuf pointer %08lx\n",(unsigned long) ltdmabuf);
-	}
-
-	/* reset the card */
-
-	inb_p(io+1);
-	inb_p(io+3);
-
-	msleep(20);
-
-	inb_p(io+0);
-	inb_p(io+2);
-	inb_p(io+7); /* clear reset */
-	inb_p(io+4); 
-	inb_p(io+5);
-	inb_p(io+5); /* enable dma */
-	inb_p(io+6); /* tri-state interrupt line */
-
-	ssleep(1);
-	
-	/* now, figure out which dma channel we're using, unless it's
-	   already been specified */
-	/* well, 0 is a legal DMA channel, but the LTPC card doesn't
-	   use it... */
-	dma = ltpc_probe_dma(io, dma);
-	if (!dma) {  /* no dma channel */
-		printk(KERN_ERR "No DMA channel found on ltpc card.\n");
-		err = -ENODEV;
-		goto out3;
-	}
-
-	/* print out friendly message */
-	if(irq)
-		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, IR%d, DMA%d.\n",io,irq,dma);
-	else
-		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, DMA%d.  Using polled mode.\n",io,dma);
-
-	dev->netdev_ops = &ltpc_netdev;
-	dev->base_addr = io;
-	dev->irq = irq;
-	dev->dma = dma;
-
-	/* the card will want to send a result at this point */
-	/* (I think... leaving out this part makes the kernel crash,
-           so I put it back in...) */
-
-	f=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,0x100);
-	enable_dma(dma);
-	release_dma_lock(f);
-
-	(void) inb_p(io+3);
-	(void) inb_p(io+2);
-	timeout = jiffies+100*HZ/100;
-
-	while(time_before(jiffies, timeout)) {
-		if( 0xf9 == inb_p(io+6))
-			break;
-		schedule();
-	}
-
-	if(debug & DEBUG_VERBOSE) {
-		printk("setting up timer and irq\n");
-	}
-
-	/* grab it and don't let go :-) */
-	if (irq && request_irq( irq, ltpc_interrupt, 0, "ltpc", dev) >= 0)
-	{
-		(void) inb_p(io+7);  /* enable interrupts from board */
-		(void) inb_p(io+7);  /* and reset irq line */
-	} else {
-		if( irq )
-			printk(KERN_ERR "ltpc: IRQ already in use, using polled mode.\n");
-		dev->irq = 0;
-		/* polled mode -- 20 times per second */
-		/* this is really, really slow... should it poll more often? */
-		init_timer(&ltpc_timer);
-		ltpc_timer.function=ltpc_poll;
-		ltpc_timer.data = (unsigned long) dev;
-
-		ltpc_timer.expires = jiffies + HZ/20;
-		add_timer(&ltpc_timer);
-	}
-	err = register_netdev(dev);
-	if (err)
-		goto out4;
-
-	return NULL;
-out4:
-	del_timer_sync(&ltpc_timer);
-	if (dev->irq)
-		free_irq(dev->irq, dev);
-out3:
-	free_pages((unsigned long)ltdmabuf, get_order(1000));
-out2:
-	release_region(io, 8);
-out1:
-	free_netdev(dev);
-out:
-	return ERR_PTR(err);
-}
-
-#ifndef MODULE
-/* handles "ltpc=io,irq,dma" kernel command lines */
-static int __init ltpc_setup(char *str)
-{
-	int ints[5];
-
-	str = get_options(str, ARRAY_SIZE(ints), ints);
-
-	if (ints[0] == 0) {
-		if (str && !strncmp(str, "auto", 4)) {
-			/* do nothing :-) */
-		}
-		else {
-			/* usage message */
-			printk (KERN_ERR
-				"ltpc: usage: ltpc=auto|iobase[,irq[,dma]]\n");
-			return 0;
-		}
-	} else {
-		io = ints[1];
-		if (ints[0] > 1) {
-			irq = ints[2];
-		}
-		if (ints[0] > 2) {
-			dma = ints[3];
-		}
-		/* ignore any other parameters */
-	}
-	return 1;
-}
-
-__setup("ltpc=", ltpc_setup);
-#endif /* MODULE */
-
-static struct net_device *dev_ltpc;
-
-#ifdef MODULE
-
-MODULE_LICENSE("GPL");
-module_param(debug, int, 0);
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(dma, int, 0);
-
-
-static int __init ltpc_module_init(void)
-{
-        if(io == 0)
-		printk(KERN_NOTICE
-		       "ltpc: Autoprobing is not recommended for modules\n");
-
-	dev_ltpc = ltpc_probe();
-	if (IS_ERR(dev_ltpc))
-		return PTR_ERR(dev_ltpc);
-	return 0;
-}
-module_init(ltpc_module_init);
-#endif
-
-static void __exit ltpc_cleanup(void)
-{
-
-	if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n");
-	unregister_netdev(dev_ltpc);
-
-	ltpc_timer.data = 0;  /* signal the poll routine that we're done */
-
-	del_timer_sync(&ltpc_timer);
-
-	if(debug & DEBUG_VERBOSE) printk("freeing irq\n");
-
-	if (dev_ltpc->irq)
-		free_irq(dev_ltpc->irq, dev_ltpc);
-
-	if(debug & DEBUG_VERBOSE) printk("freeing dma\n");
-
-	if (dev_ltpc->dma)
-		free_dma(dev_ltpc->dma);
-
-	if(debug & DEBUG_VERBOSE) printk("freeing ioaddr\n");
-
-	if (dev_ltpc->base_addr)
-		release_region(dev_ltpc->base_addr,8);
-
-	free_netdev(dev_ltpc);
-
-	if(debug & DEBUG_VERBOSE) printk("free_pages\n");
-
-	free_pages( (unsigned long) ltdmabuf, get_order(1000));
-
-	if(debug & DEBUG_VERBOSE) printk("returning from cleanup_module\n");
-}
-
-module_exit(ltpc_cleanup);
diff --git a/drivers/net/appletalk/ltpc.h b/drivers/net/appletalk/ltpc.h
deleted file mode 100644
index cd30544a3729..000000000000
--- a/drivers/net/appletalk/ltpc.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/***   ltpc.h
- *
- *
- ***/
-
-#define LT_GETRESULT  0x00
-#define LT_WRITEMEM   0x01
-#define LT_READMEM    0x02
-#define LT_GETFLAGS   0x04
-#define LT_SETFLAGS   0x05
-#define LT_INIT       0x10
-#define LT_SENDLAP    0x13
-#define LT_RCVLAP     0x14
-
-/* the flag that we care about */
-#define LT_FLAG_ALLLAP 0x04
-
-struct lt_getresult {
-	unsigned char command;
-	unsigned char mailbox;
-};
-
-struct lt_mem {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned short addr;	/* host order */
-	unsigned short length;	/* host order */
-};
-
-struct lt_setflags {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned char flags;
-};
-
-struct lt_getflags {
-	unsigned char command;
-	unsigned char mailbox;
-};
-
-struct lt_init {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned char hint;
-};
-
-struct lt_sendlap {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned char dnode;
-	unsigned char laptype;
-	unsigned short length;	/* host order */
-};
-
-struct lt_rcvlap {
-	unsigned char command;
-	unsigned char dnode;
-	unsigned char snode;
-	unsigned char laptype;
-	unsigned short length;	/* host order */
-};
-
-union lt_command {
-	struct lt_getresult getresult;
-	struct lt_mem mem;
-	struct lt_setflags setflags;
-	struct lt_getflags getflags;
-	struct lt_init init;
-	struct lt_sendlap sendlap;
-	struct lt_rcvlap rcvlap;
-};
-typedef union lt_command lt_command;
-
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index b80755da5394..584d4e264807 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -169,6 +169,8 @@ source "drivers/staging/bcm/Kconfig"
 
 source "drivers/staging/ft1000/Kconfig"
 
+source "drivers/staging/appletalk/Kconfig"
+
 source "drivers/staging/intel_sst/Kconfig"
 
 source "drivers/staging/speakup/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index fd26509e5efa..88f0c64e7e58 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_ATH6K_LEGACY)	+= ath6kl/
 obj-$(CONFIG_USB_ENESTORAGE)	+= keucr/
 obj-$(CONFIG_BCM_WIMAX)	+= bcm/
 obj-$(CONFIG_FT1000)		+= ft1000/
+obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_SND_INTEL_SST)		+= intel_sst/
 obj-$(CONFIG_SPEAKUP)	+= speakup/
 obj-$(CONFIG_TOUCHSCREEN_CLEARPAD_TM1217)	+= cptm1217/
diff --git a/drivers/staging/appletalk/Kconfig b/drivers/staging/appletalk/Kconfig
new file mode 100644
index 000000000000..0b376a990972
--- /dev/null
+++ b/drivers/staging/appletalk/Kconfig
@@ -0,0 +1,126 @@
+#
+# Appletalk driver configuration
+#
+config ATALK
+	tristate "Appletalk protocol support"
+	depends on BKL # waiting to be removed from net/appletalk/ddp.c
+	select LLC
+	---help---
+	  AppleTalk is the protocol that Apple computers can use to communicate
+	  on a network.  If your Linux box is connected to such a network and you
+	  wish to connect to it, say Y.  You will need to use the netatalk package
+	  so that your Linux box can act as a print and file server for Macs as
+	  well as access AppleTalk printers.  Check out
+	  <http://www.zettabyte.net/netatalk/> on the WWW for details.
+	  EtherTalk is the name used for AppleTalk over Ethernet and the
+	  cheaper and slower LocalTalk is AppleTalk over a proprietary Apple
+	  network using serial links.  EtherTalk and LocalTalk are fully
+	  supported by Linux.
+
+	  General information about how to connect Linux, Windows machines and
+	  Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>.  The
+	  NET3-4-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>, contains valuable
+	  information as well.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called appletalk. You almost certainly want to compile it as a
+	  module so you can restart your AppleTalk stack without rebooting
+	  your machine. I hear that the GNU boycott of Apple is over, so
+	  even politically correct people are allowed to say Y here.
+
+config DEV_APPLETALK
+	tristate "Appletalk interfaces support"
+	depends on ATALK
+	help
+	  AppleTalk is the protocol that Apple computers can use to communicate
+	  on a network.  If your Linux box is connected to such a network, and wish
+	  to do IP over it, or you have a LocalTalk card and wish to use it to
+	  connect to the AppleTalk network, say Y.
+	  
+
+config LTPC
+	tristate "Apple/Farallon LocalTalk PC support"
+	depends on DEV_APPLETALK && (ISA || EISA) && ISA_DMA_API
+	help
+	  This allows you to use the AppleTalk PC card to connect to LocalTalk
+	  networks. The card is also known as the Farallon PhoneNet PC card.
+	  If you are in doubt, this card is the one with the 65C02 chip on it.
+	  You also need version 1.3.3 or later of the netatalk package.
+	  This driver is experimental, which means that it may not work.
+	  See the file <file:Documentation/networking/ltpc.txt>.
+
+config COPS
+	tristate "COPS LocalTalk PC support"
+	depends on DEV_APPLETALK && (ISA || EISA)
+	help
+	  This allows you to use COPS AppleTalk cards to connect to LocalTalk
+	  networks. You also need version 1.3.3 or later of the netatalk
+	  package. This driver is experimental, which means that it may not
+	  work. This driver will only work if you choose "AppleTalk DDP"
+	  networking support, above.
+	  Please read the file <file:Documentation/networking/cops.txt>.
+
+config COPS_DAYNA
+	bool "Dayna firmware support"
+	depends on COPS
+	help
+	  Support COPS compatible cards with Dayna style firmware (Dayna
+	  DL2000/ Daynatalk/PC (half length), COPS LT-95, Farallon PhoneNET PC
+	  III, Farallon PhoneNET PC II).
+
+config COPS_TANGENT
+	bool "Tangent firmware support"
+	depends on COPS
+	help
+	  Support COPS compatible cards with Tangent style firmware (Tangent
+	  ATB_II, Novell NL-1000, Daystar Digital LT-200.
+
+config IPDDP
+	tristate "Appletalk-IP driver support"
+	depends on DEV_APPLETALK && ATALK
+	---help---
+	  This allows IP networking for users who only have AppleTalk
+	  networking available. This feature is experimental. With this
+	  driver, you can encapsulate IP inside AppleTalk (e.g. if your Linux
+	  box is stuck on an AppleTalk only network) or decapsulate (e.g. if
+	  you want your Linux box to act as an Internet gateway for a zoo of
+	  AppleTalk connected Macs). Please see the file
+	  <file:Documentation/networking/ipddp.txt> for more information.
+
+	  If you say Y here, the AppleTalk-IP support will be compiled into
+	  the kernel. In this case, you can either use encapsulation or
+	  decapsulation, but not both. With the following two questions, you
+	  decide which one you want.
+
+	  To compile the AppleTalk-IP support as a module, choose M here: the
+	  module will be called ipddp.
+	  In this case, you will be able to use both encapsulation and
+	  decapsulation simultaneously, by loading two copies of the module
+	  and specifying different values for the module option ipddp_mode.
+
+config IPDDP_ENCAP
+	bool "IP to Appletalk-IP Encapsulation support"
+	depends on IPDDP
+	help
+	  If you say Y here, the AppleTalk-IP code will be able to encapsulate
+	  IP packets inside AppleTalk frames; this is useful if your Linux box
+	  is stuck on an AppleTalk network (which hopefully contains a
+	  decapsulator somewhere). Please see
+	  <file:Documentation/networking/ipddp.txt> for more information. If
+	  you said Y to "AppleTalk-IP driver support" above and you say Y
+	  here, then you cannot say Y to "AppleTalk-IP to IP Decapsulation
+	  support", below.
+
+config IPDDP_DECAP
+	bool "Appletalk-IP to IP Decapsulation support"
+	depends on IPDDP
+	help
+	  If you say Y here, the AppleTalk-IP code will be able to decapsulate
+	  AppleTalk-IP frames to IP packets; this is useful if you want your
+	  Linux box to act as an Internet gateway for an AppleTalk network.
+	  Please see <file:Documentation/networking/ipddp.txt> for more
+	  information.  If you said Y to "AppleTalk-IP driver support" above
+	  and you say Y here, then you cannot say Y to "IP to AppleTalk-IP
+	  Encapsulation support", above.
+
diff --git a/drivers/staging/appletalk/Makefile b/drivers/staging/appletalk/Makefile
new file mode 100644
index 000000000000..2a5129a5c6bc
--- /dev/null
+++ b/drivers/staging/appletalk/Makefile
@@ -0,0 +1,12 @@
+#
+# Makefile for drivers/staging/appletalk
+#
+obj-$(CONFIG_ATALK) += appletalk.o
+
+appletalk-y			:= aarp.o ddp.o dev.o
+appletalk-$(CONFIG_PROC_FS)	+= atalk_proc.o
+appletalk-$(CONFIG_SYSCTL)	+= sysctl_net_atalk.o
+
+obj-$(CONFIG_IPDDP) += ipddp.o
+obj-$(CONFIG_COPS) += cops.o
+obj-$(CONFIG_LTPC) += ltpc.o
diff --git a/drivers/staging/appletalk/aarp.c b/drivers/staging/appletalk/aarp.c
new file mode 100644
index 000000000000..7163a1dd501f
--- /dev/null
+++ b/drivers/staging/appletalk/aarp.c
@@ -0,0 +1,1063 @@
+/*
+ *	AARP:		An implementation of the AppleTalk AARP protocol for
+ *			Ethernet 'ELAP'.
+ *
+ *		Alan Cox  <Alan.Cox@linux.org>
+ *
+ *	This doesn't fit cleanly with the IP arp. Potentially we can use
+ *	the generic neighbour discovery code to clean this up.
+ *
+ *	FIXME:
+ *		We ought to handle the retransmits with a single list and a
+ *	separate fast timer for when it is needed.
+ *		Use neighbour discovery code.
+ *		Token Ring Support.
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ *
+ *	References:
+ *		Inside AppleTalk (2nd Ed).
+ *	Fixes:
+ *		Jaume Grau	-	flush caches on AARP_PROBE
+ *		Rob Newberry	-	Added proxy AARP and AARP proc fs,
+ *					moved probing from DDP module.
+ *		Arnaldo C. Melo -	don't mangle rx packets
+ *
+ */
+
+#include <linux/if_arp.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/datalink.h>
+#include <net/psnap.h>
+#include "atalk.h"
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
+int sysctl_aarp_tick_time = AARP_TICK_TIME;
+int sysctl_aarp_retransmit_limit = AARP_RETRANSMIT_LIMIT;
+int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
+
+/* Lists of aarp entries */
+/**
+ *	struct aarp_entry - AARP entry
+ *	@last_sent - Last time we xmitted the aarp request
+ *	@packet_queue - Queue of frames wait for resolution
+ *	@status - Used for proxy AARP
+ *	expires_at - Entry expiry time
+ *	target_addr - DDP Address
+ *	dev - Device to use
+ *	hwaddr - Physical i/f address of target/router
+ *	xmit_count - When this hits 10 we give up
+ *	next - Next entry in chain
+ */
+struct aarp_entry {
+	/* These first two are only used for unresolved entries */
+	unsigned long		last_sent;
+	struct sk_buff_head	packet_queue;
+	int			status;
+	unsigned long		expires_at;
+	struct atalk_addr	target_addr;
+	struct net_device	*dev;
+	char			hwaddr[6];
+	unsigned short		xmit_count;
+	struct aarp_entry	*next;
+};
+
+/* Hashed list of resolved, unresolved and proxy entries */
+static struct aarp_entry *resolved[AARP_HASH_SIZE];
+static struct aarp_entry *unresolved[AARP_HASH_SIZE];
+static struct aarp_entry *proxies[AARP_HASH_SIZE];
+static int unresolved_count;
+
+/* One lock protects it all. */
+static DEFINE_RWLOCK(aarp_lock);
+
+/* Used to walk the list and purge/kick entries.  */
+static struct timer_list aarp_timer;
+
+/*
+ *	Delete an aarp queue
+ *
+ *	Must run under aarp_lock.
+ */
+static void __aarp_expire(struct aarp_entry *a)
+{
+	skb_queue_purge(&a->packet_queue);
+	kfree(a);
+}
+
+/*
+ *	Send an aarp queue entry request
+ *
+ *	Must run under aarp_lock.
+ */
+static void __aarp_send_query(struct aarp_entry *a)
+{
+	static unsigned char aarp_eth_multicast[ETH_ALEN] =
+					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
+	struct net_device *dev = a->dev;
+	struct elapaarp *eah;
+	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
+	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
+	struct atalk_addr *sat = atalk_find_dev_addr(dev);
+
+	if (!skb)
+		return;
+
+	if (!sat) {
+		kfree_skb(skb);
+		return;
+	}
+
+	/* Set up the buffer */
+	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
+	skb->protocol    = htons(ETH_P_ATALK);
+	skb->dev	 = dev;
+	eah		 = aarp_hdr(skb);
+
+	/* Set up the ARP */
+	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
+	eah->pa_type	 = htons(ETH_P_ATALK);
+	eah->hw_len	 = ETH_ALEN;
+	eah->pa_len	 = AARP_PA_ALEN;
+	eah->function	 = htons(AARP_REQUEST);
+
+	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+
+	eah->pa_src_zero = 0;
+	eah->pa_src_net	 = sat->s_net;
+	eah->pa_src_node = sat->s_node;
+
+	memset(eah->hw_dst, '\0', ETH_ALEN);
+
+	eah->pa_dst_zero = 0;
+	eah->pa_dst_net	 = a->target_addr.s_net;
+	eah->pa_dst_node = a->target_addr.s_node;
+
+	/* Send it */
+	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
+	/* Update the sending count */
+	a->xmit_count++;
+	a->last_sent = jiffies;
+}
+
+/* This runs under aarp_lock and in softint context, so only atomic memory
+ * allocations can be used. */
+static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
+			    struct atalk_addr *them, unsigned char *sha)
+{
+	struct elapaarp *eah;
+	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
+	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
+
+	if (!skb)
+		return;
+
+	/* Set up the buffer */
+	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
+	skb->protocol    = htons(ETH_P_ATALK);
+	skb->dev	 = dev;
+	eah		 = aarp_hdr(skb);
+
+	/* Set up the ARP */
+	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
+	eah->pa_type	 = htons(ETH_P_ATALK);
+	eah->hw_len	 = ETH_ALEN;
+	eah->pa_len	 = AARP_PA_ALEN;
+	eah->function	 = htons(AARP_REPLY);
+
+	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+
+	eah->pa_src_zero = 0;
+	eah->pa_src_net	 = us->s_net;
+	eah->pa_src_node = us->s_node;
+
+	if (!sha)
+		memset(eah->hw_dst, '\0', ETH_ALEN);
+	else
+		memcpy(eah->hw_dst, sha, ETH_ALEN);
+
+	eah->pa_dst_zero = 0;
+	eah->pa_dst_net	 = them->s_net;
+	eah->pa_dst_node = them->s_node;
+
+	/* Send it */
+	aarp_dl->request(aarp_dl, skb, sha);
+}
+
+/*
+ *	Send probe frames. Called from aarp_probe_network and
+ *	aarp_proxy_probe_network.
+ */
+
+static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
+{
+	struct elapaarp *eah;
+	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
+	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
+	static unsigned char aarp_eth_multicast[ETH_ALEN] =
+					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
+
+	if (!skb)
+		return;
+
+	/* Set up the buffer */
+	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
+	skb->protocol    = htons(ETH_P_ATALK);
+	skb->dev	 = dev;
+	eah		 = aarp_hdr(skb);
+
+	/* Set up the ARP */
+	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
+	eah->pa_type	 = htons(ETH_P_ATALK);
+	eah->hw_len	 = ETH_ALEN;
+	eah->pa_len	 = AARP_PA_ALEN;
+	eah->function	 = htons(AARP_PROBE);
+
+	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+
+	eah->pa_src_zero = 0;
+	eah->pa_src_net	 = us->s_net;
+	eah->pa_src_node = us->s_node;
+
+	memset(eah->hw_dst, '\0', ETH_ALEN);
+
+	eah->pa_dst_zero = 0;
+	eah->pa_dst_net	 = us->s_net;
+	eah->pa_dst_node = us->s_node;
+
+	/* Send it */
+	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
+}
+
+/*
+ *	Handle an aarp timer expire
+ *
+ *	Must run under the aarp_lock.
+ */
+
+static void __aarp_expire_timer(struct aarp_entry **n)
+{
+	struct aarp_entry *t;
+
+	while (*n)
+		/* Expired ? */
+		if (time_after(jiffies, (*n)->expires_at)) {
+			t = *n;
+			*n = (*n)->next;
+			__aarp_expire(t);
+		} else
+			n = &((*n)->next);
+}
+
+/*
+ *	Kick all pending requests 5 times a second.
+ *
+ *	Must run under the aarp_lock.
+ */
+static void __aarp_kick(struct aarp_entry **n)
+{
+	struct aarp_entry *t;
+
+	while (*n)
+		/* Expired: if this will be the 11th tx, we delete instead. */
+		if ((*n)->xmit_count >= sysctl_aarp_retransmit_limit) {
+			t = *n;
+			*n = (*n)->next;
+			__aarp_expire(t);
+		} else {
+			__aarp_send_query(*n);
+			n = &((*n)->next);
+		}
+}
+
+/*
+ *	A device has gone down. Take all entries referring to the device
+ *	and remove them.
+ *
+ *	Must run under the aarp_lock.
+ */
+static void __aarp_expire_device(struct aarp_entry **n, struct net_device *dev)
+{
+	struct aarp_entry *t;
+
+	while (*n)
+		if ((*n)->dev == dev) {
+			t = *n;
+			*n = (*n)->next;
+			__aarp_expire(t);
+		} else
+			n = &((*n)->next);
+}
+
+/* Handle the timer event */
+static void aarp_expire_timeout(unsigned long unused)
+{
+	int ct;
+
+	write_lock_bh(&aarp_lock);
+
+	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+		__aarp_expire_timer(&resolved[ct]);
+		__aarp_kick(&unresolved[ct]);
+		__aarp_expire_timer(&unresolved[ct]);
+		__aarp_expire_timer(&proxies[ct]);
+	}
+
+	write_unlock_bh(&aarp_lock);
+	mod_timer(&aarp_timer, jiffies +
+			       (unresolved_count ? sysctl_aarp_tick_time :
+				sysctl_aarp_expiry_time));
+}
+
+/* Network device notifier chain handler. */
+static int aarp_device_event(struct notifier_block *this, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *dev = ptr;
+	int ct;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_DOWN) {
+		write_lock_bh(&aarp_lock);
+
+		for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+			__aarp_expire_device(&resolved[ct], dev);
+			__aarp_expire_device(&unresolved[ct], dev);
+			__aarp_expire_device(&proxies[ct], dev);
+		}
+
+		write_unlock_bh(&aarp_lock);
+	}
+	return NOTIFY_DONE;
+}
+
+/* Expire all entries in a hash chain */
+static void __aarp_expire_all(struct aarp_entry **n)
+{
+	struct aarp_entry *t;
+
+	while (*n) {
+		t = *n;
+		*n = (*n)->next;
+		__aarp_expire(t);
+	}
+}
+
+/* Cleanup all hash chains -- module unloading */
+static void aarp_purge(void)
+{
+	int ct;
+
+	write_lock_bh(&aarp_lock);
+	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+		__aarp_expire_all(&resolved[ct]);
+		__aarp_expire_all(&unresolved[ct]);
+		__aarp_expire_all(&proxies[ct]);
+	}
+	write_unlock_bh(&aarp_lock);
+}
+
+/*
+ *	Create a new aarp entry.  This must use GFP_ATOMIC because it
+ *	runs while holding spinlocks.
+ */
+static struct aarp_entry *aarp_alloc(void)
+{
+	struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC);
+
+	if (a)
+		skb_queue_head_init(&a->packet_queue);
+	return a;
+}
+
+/*
+ * Find an entry. We might return an expired but not yet purged entry. We
+ * don't care as it will do no harm.
+ *
+ * This must run under the aarp_lock.
+ */
+static struct aarp_entry *__aarp_find_entry(struct aarp_entry *list,
+					    struct net_device *dev,
+					    struct atalk_addr *sat)
+{
+	while (list) {
+		if (list->target_addr.s_net == sat->s_net &&
+		    list->target_addr.s_node == sat->s_node &&
+		    list->dev == dev)
+			break;
+		list = list->next;
+	}
+
+	return list;
+}
+
+/* Called from the DDP code, and thus must be exported. */
+void aarp_proxy_remove(struct net_device *dev, struct atalk_addr *sa)
+{
+	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
+	struct aarp_entry *a;
+
+	write_lock_bh(&aarp_lock);
+
+	a = __aarp_find_entry(proxies[hash], dev, sa);
+	if (a)
+		a->expires_at = jiffies - 1;
+
+	write_unlock_bh(&aarp_lock);
+}
+
+/* This must run under aarp_lock. */
+static struct atalk_addr *__aarp_proxy_find(struct net_device *dev,
+					    struct atalk_addr *sa)
+{
+	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
+	struct aarp_entry *a = __aarp_find_entry(proxies[hash], dev, sa);
+
+	return a ? sa : NULL;
+}
+
+/*
+ * Probe a Phase 1 device or a device that requires its Net:Node to
+ * be set via an ioctl.
+ */
+static void aarp_send_probe_phase1(struct atalk_iface *iface)
+{
+	struct ifreq atreq;
+	struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr;
+	const struct net_device_ops *ops = iface->dev->netdev_ops;
+
+	sa->sat_addr.s_node = iface->address.s_node;
+	sa->sat_addr.s_net = ntohs(iface->address.s_net);
+
+	/* We pass the Net:Node to the drivers/cards by a Device ioctl. */
+	if (!(ops->ndo_do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) {
+		ops->ndo_do_ioctl(iface->dev, &atreq, SIOCGIFADDR);
+		if (iface->address.s_net != htons(sa->sat_addr.s_net) ||
+		    iface->address.s_node != sa->sat_addr.s_node)
+			iface->status |= ATIF_PROBE_FAIL;
+
+		iface->address.s_net  = htons(sa->sat_addr.s_net);
+		iface->address.s_node = sa->sat_addr.s_node;
+	}
+}
+
+
+void aarp_probe_network(struct atalk_iface *atif)
+{
+	if (atif->dev->type == ARPHRD_LOCALTLK ||
+	    atif->dev->type == ARPHRD_PPP)
+		aarp_send_probe_phase1(atif);
+	else {
+		unsigned int count;
+
+		for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
+			aarp_send_probe(atif->dev, &atif->address);
+
+			/* Defer 1/10th */
+			msleep(100);
+
+			if (atif->status & ATIF_PROBE_FAIL)
+				break;
+		}
+	}
+}
+
+int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa)
+{
+	int hash, retval = -EPROTONOSUPPORT;
+	struct aarp_entry *entry;
+	unsigned int count;
+
+	/*
+	 * we don't currently support LocalTalk or PPP for proxy AARP;
+	 * if someone wants to try and add it, have fun
+	 */
+	if (atif->dev->type == ARPHRD_LOCALTLK ||
+	    atif->dev->type == ARPHRD_PPP)
+		goto out;
+
+	/*
+	 * create a new AARP entry with the flags set to be published --
+	 * we need this one to hang around even if it's in use
+	 */
+	entry = aarp_alloc();
+	retval = -ENOMEM;
+	if (!entry)
+		goto out;
+
+	entry->expires_at = -1;
+	entry->status = ATIF_PROBE;
+	entry->target_addr.s_node = sa->s_node;
+	entry->target_addr.s_net = sa->s_net;
+	entry->dev = atif->dev;
+
+	write_lock_bh(&aarp_lock);
+
+	hash = sa->s_node % (AARP_HASH_SIZE - 1);
+	entry->next = proxies[hash];
+	proxies[hash] = entry;
+
+	for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
+		aarp_send_probe(atif->dev, sa);
+
+		/* Defer 1/10th */
+		write_unlock_bh(&aarp_lock);
+		msleep(100);
+		write_lock_bh(&aarp_lock);
+
+		if (entry->status & ATIF_PROBE_FAIL)
+			break;
+	}
+
+	if (entry->status & ATIF_PROBE_FAIL) {
+		entry->expires_at = jiffies - 1; /* free the entry */
+		retval = -EADDRINUSE; /* return network full */
+	} else { /* clear the probing flag */
+		entry->status &= ~ATIF_PROBE;
+		retval = 1;
+	}
+
+	write_unlock_bh(&aarp_lock);
+out:
+	return retval;
+}
+
+/* Send a DDP frame */
+int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
+		  struct atalk_addr *sa, void *hwaddr)
+{
+	static char ddp_eth_multicast[ETH_ALEN] =
+		{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
+	int hash;
+	struct aarp_entry *a;
+
+	skb_reset_network_header(skb);
+
+	/* Check for LocalTalk first */
+	if (dev->type == ARPHRD_LOCALTLK) {
+		struct atalk_addr *at = atalk_find_dev_addr(dev);
+		struct ddpehdr *ddp = (struct ddpehdr *)skb->data;
+		int ft = 2;
+
+		/*
+		 * Compressible ?
+		 *
+		 * IFF: src_net == dest_net == device_net
+		 * (zero matches anything)
+		 */
+
+		if ((!ddp->deh_snet || at->s_net == ddp->deh_snet) &&
+		    (!ddp->deh_dnet || at->s_net == ddp->deh_dnet)) {
+			skb_pull(skb, sizeof(*ddp) - 4);
+
+			/*
+			 *	The upper two remaining bytes are the port
+			 *	numbers	we just happen to need. Now put the
+			 *	length in the lower two.
+			 */
+			*((__be16 *)skb->data) = htons(skb->len);
+			ft = 1;
+		}
+		/*
+		 * Nice and easy. No AARP type protocols occur here so we can
+		 * just shovel it out with a 3 byte LLAP header
+		 */
+
+		skb_push(skb, 3);
+		skb->data[0] = sa->s_node;
+		skb->data[1] = at->s_node;
+		skb->data[2] = ft;
+		skb->dev     = dev;
+		goto sendit;
+	}
+
+	/* On a PPP link we neither compress nor aarp.  */
+	if (dev->type == ARPHRD_PPP) {
+		skb->protocol = htons(ETH_P_PPPTALK);
+		skb->dev = dev;
+		goto sendit;
+	}
+
+	/* Non ELAP we cannot do. */
+	if (dev->type != ARPHRD_ETHER)
+		goto free_it;
+
+	skb->dev = dev;
+	skb->protocol = htons(ETH_P_ATALK);
+	hash = sa->s_node % (AARP_HASH_SIZE - 1);
+
+	/* Do we have a resolved entry? */
+	if (sa->s_node == ATADDR_BCAST) {
+		/* Send it */
+		ddp_dl->request(ddp_dl, skb, ddp_eth_multicast);
+		goto sent;
+	}
+
+	write_lock_bh(&aarp_lock);
+	a = __aarp_find_entry(resolved[hash], dev, sa);
+
+	if (a) { /* Return 1 and fill in the address */
+		a->expires_at = jiffies + (sysctl_aarp_expiry_time * 10);
+		ddp_dl->request(ddp_dl, skb, a->hwaddr);
+		write_unlock_bh(&aarp_lock);
+		goto sent;
+	}
+
+	/* Do we have an unresolved entry: This is the less common path */
+	a = __aarp_find_entry(unresolved[hash], dev, sa);
+	if (a) { /* Queue onto the unresolved queue */
+		skb_queue_tail(&a->packet_queue, skb);
+		goto out_unlock;
+	}
+
+	/* Allocate a new entry */
+	a = aarp_alloc();
+	if (!a) {
+		/* Whoops slipped... good job it's an unreliable protocol 8) */
+		write_unlock_bh(&aarp_lock);
+		goto free_it;
+	}
+
+	/* Set up the queue */
+	skb_queue_tail(&a->packet_queue, skb);
+	a->expires_at	 = jiffies + sysctl_aarp_resolve_time;
+	a->dev		 = dev;
+	a->next		 = unresolved[hash];
+	a->target_addr	 = *sa;
+	a->xmit_count	 = 0;
+	unresolved[hash] = a;
+	unresolved_count++;
+
+	/* Send an initial request for the address */
+	__aarp_send_query(a);
+
+	/*
+	 * Switch to fast timer if needed (That is if this is the first
+	 * unresolved entry to get added)
+	 */
+
+	if (unresolved_count == 1)
+		mod_timer(&aarp_timer, jiffies + sysctl_aarp_tick_time);
+
+	/* Now finally, it is safe to drop the lock. */
+out_unlock:
+	write_unlock_bh(&aarp_lock);
+
+	/* Tell the ddp layer we have taken over for this frame. */
+	goto sent;
+
+sendit:
+	if (skb->sk)
+		skb->priority = skb->sk->sk_priority;
+	if (dev_queue_xmit(skb))
+		goto drop;
+sent:
+	return NET_XMIT_SUCCESS;
+free_it:
+	kfree_skb(skb);
+drop:
+	return NET_XMIT_DROP;
+}
+EXPORT_SYMBOL(aarp_send_ddp);
+
+/*
+ *	An entry in the aarp unresolved queue has become resolved. Send
+ *	all the frames queued under it.
+ *
+ *	Must run under aarp_lock.
+ */
+static void __aarp_resolved(struct aarp_entry **list, struct aarp_entry *a,
+			    int hash)
+{
+	struct sk_buff *skb;
+
+	while (*list)
+		if (*list == a) {
+			unresolved_count--;
+			*list = a->next;
+
+			/* Move into the resolved list */
+			a->next = resolved[hash];
+			resolved[hash] = a;
+
+			/* Kick frames off */
+			while ((skb = skb_dequeue(&a->packet_queue)) != NULL) {
+				a->expires_at = jiffies +
+						sysctl_aarp_expiry_time * 10;
+				ddp_dl->request(ddp_dl, skb, a->hwaddr);
+			}
+		} else
+			list = &((*list)->next);
+}
+
+/*
+ *	This is called by the SNAP driver whenever we see an AARP SNAP
+ *	frame. We currently only support Ethernet.
+ */
+static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
+		    struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct elapaarp *ea = aarp_hdr(skb);
+	int hash, ret = 0;
+	__u16 function;
+	struct aarp_entry *a;
+	struct atalk_addr sa, *ma, da;
+	struct atalk_iface *ifa;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		goto out0;
+
+	/* We only do Ethernet SNAP AARP. */
+	if (dev->type != ARPHRD_ETHER)
+		goto out0;
+
+	/* Frame size ok? */
+	if (!skb_pull(skb, sizeof(*ea)))
+		goto out0;
+
+	function = ntohs(ea->function);
+
+	/* Sanity check fields. */
+	if (function < AARP_REQUEST || function > AARP_PROBE ||
+	    ea->hw_len != ETH_ALEN || ea->pa_len != AARP_PA_ALEN ||
+	    ea->pa_src_zero || ea->pa_dst_zero)
+		goto out0;
+
+	/* Looks good. */
+	hash = ea->pa_src_node % (AARP_HASH_SIZE - 1);
+
+	/* Build an address. */
+	sa.s_node = ea->pa_src_node;
+	sa.s_net = ea->pa_src_net;
+
+	/* Process the packet. Check for replies of me. */
+	ifa = atalk_find_dev(dev);
+	if (!ifa)
+		goto out1;
+
+	if (ifa->status & ATIF_PROBE &&
+	    ifa->address.s_node == ea->pa_dst_node &&
+	    ifa->address.s_net == ea->pa_dst_net) {
+		ifa->status |= ATIF_PROBE_FAIL; /* Fail the probe (in use) */
+		goto out1;
+	}
+
+	/* Check for replies of proxy AARP entries */
+	da.s_node = ea->pa_dst_node;
+	da.s_net  = ea->pa_dst_net;
+
+	write_lock_bh(&aarp_lock);
+	a = __aarp_find_entry(proxies[hash], dev, &da);
+
+	if (a && a->status & ATIF_PROBE) {
+		a->status |= ATIF_PROBE_FAIL;
+		/*
+		 * we do not respond to probe or request packets for
+		 * this address while we are probing this address
+		 */
+		goto unlock;
+	}
+
+	switch (function) {
+		case AARP_REPLY:
+			if (!unresolved_count)	/* Speed up */
+				break;
+
+			/* Find the entry.  */
+			a = __aarp_find_entry(unresolved[hash], dev, &sa);
+			if (!a || dev != a->dev)
+				break;
+
+			/* We can fill one in - this is good. */
+			memcpy(a->hwaddr, ea->hw_src, ETH_ALEN);
+			__aarp_resolved(&unresolved[hash], a, hash);
+			if (!unresolved_count)
+				mod_timer(&aarp_timer,
+					  jiffies + sysctl_aarp_expiry_time);
+			break;
+
+		case AARP_REQUEST:
+		case AARP_PROBE:
+
+			/*
+			 * If it is my address set ma to my address and reply.
+			 * We can treat probe and request the same.  Probe
+			 * simply means we shouldn't cache the querying host,
+			 * as in a probe they are proposing an address not
+			 * using one.
+			 *
+			 * Support for proxy-AARP added. We check if the
+			 * address is one of our proxies before we toss the
+			 * packet out.
+			 */
+
+			sa.s_node = ea->pa_dst_node;
+			sa.s_net  = ea->pa_dst_net;
+
+			/* See if we have a matching proxy. */
+			ma = __aarp_proxy_find(dev, &sa);
+			if (!ma)
+				ma = &ifa->address;
+			else { /* We need to make a copy of the entry. */
+				da.s_node = sa.s_node;
+				da.s_net = sa.s_net;
+				ma = &da;
+			}
+
+			if (function == AARP_PROBE) {
+				/*
+				 * A probe implies someone trying to get an
+				 * address. So as a precaution flush any
+				 * entries we have for this address.
+				 */
+				a = __aarp_find_entry(resolved[sa.s_node %
+							  (AARP_HASH_SIZE - 1)],
+						      skb->dev, &sa);
+
+				/*
+				 * Make it expire next tick - that avoids us
+				 * getting into a probe/flush/learn/probe/
+				 * flush/learn cycle during probing of a slow
+				 * to respond host addr.
+				 */
+				if (a) {
+					a->expires_at = jiffies - 1;
+					mod_timer(&aarp_timer, jiffies +
+							sysctl_aarp_tick_time);
+				}
+			}
+
+			if (sa.s_node != ma->s_node)
+				break;
+
+			if (sa.s_net && ma->s_net && sa.s_net != ma->s_net)
+				break;
+
+			sa.s_node = ea->pa_src_node;
+			sa.s_net = ea->pa_src_net;
+
+			/* aarp_my_address has found the address to use for us.
+			*/
+			aarp_send_reply(dev, ma, &sa, ea->hw_src);
+			break;
+	}
+
+unlock:
+	write_unlock_bh(&aarp_lock);
+out1:
+	ret = 1;
+out0:
+	kfree_skb(skb);
+	return ret;
+}
+
+static struct notifier_block aarp_notifier = {
+	.notifier_call = aarp_device_event,
+};
+
+static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 };
+
+void __init aarp_proto_init(void)
+{
+	aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv);
+	if (!aarp_dl)
+		printk(KERN_CRIT "Unable to register AARP with SNAP.\n");
+	setup_timer(&aarp_timer, aarp_expire_timeout, 0);
+	aarp_timer.expires  = jiffies + sysctl_aarp_expiry_time;
+	add_timer(&aarp_timer);
+	register_netdevice_notifier(&aarp_notifier);
+}
+
+/* Remove the AARP entries associated with a device. */
+void aarp_device_down(struct net_device *dev)
+{
+	int ct;
+
+	write_lock_bh(&aarp_lock);
+
+	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+		__aarp_expire_device(&resolved[ct], dev);
+		__aarp_expire_device(&unresolved[ct], dev);
+		__aarp_expire_device(&proxies[ct], dev);
+	}
+
+	write_unlock_bh(&aarp_lock);
+}
+
+#ifdef CONFIG_PROC_FS
+struct aarp_iter_state {
+	int bucket;
+	struct aarp_entry **table;
+};
+
+/*
+ * Get the aarp entry that is in the chain described
+ * by the iterator.
+ * If pos is set then skip till that index.
+ * pos = 1 is the first entry
+ */
+static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
+{
+	int ct = iter->bucket;
+	struct aarp_entry **table = iter->table;
+	loff_t off = 0;
+	struct aarp_entry *entry;
+
+ rescan:
+	while(ct < AARP_HASH_SIZE) {
+		for (entry = table[ct]; entry; entry = entry->next) {
+			if (!pos || ++off == *pos) {
+				iter->table = table;
+				iter->bucket = ct;
+				return entry;
+			}
+		}
+		++ct;
+	}
+
+	if (table == resolved) {
+		ct = 0;
+		table = unresolved;
+		goto rescan;
+	}
+	if (table == unresolved) {
+		ct = 0;
+		table = proxies;
+		goto rescan;
+	}
+	return NULL;
+}
+
+static void *aarp_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(aarp_lock)
+{
+	struct aarp_iter_state *iter = seq->private;
+
+	read_lock_bh(&aarp_lock);
+	iter->table     = resolved;
+	iter->bucket    = 0;
+
+	return *pos ? iter_next(iter, pos) : SEQ_START_TOKEN;
+}
+
+static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct aarp_entry *entry = v;
+	struct aarp_iter_state *iter = seq->private;
+
+	++*pos;
+
+	/* first line after header */
+	if (v == SEQ_START_TOKEN)
+		entry = iter_next(iter, NULL);
+
+	/* next entry in current bucket */
+	else if (entry->next)
+		entry = entry->next;
+
+	/* next bucket or table */
+	else {
+		++iter->bucket;
+		entry = iter_next(iter, NULL);
+	}
+	return entry;
+}
+
+static void aarp_seq_stop(struct seq_file *seq, void *v)
+	__releases(aarp_lock)
+{
+	read_unlock_bh(&aarp_lock);
+}
+
+static const char *dt2str(unsigned long ticks)
+{
+	static char buf[32];
+
+	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
+
+	return buf;
+}
+
+static int aarp_seq_show(struct seq_file *seq, void *v)
+{
+	struct aarp_iter_state *iter = seq->private;
+	struct aarp_entry *entry = v;
+	unsigned long now = jiffies;
+
+	if (v == SEQ_START_TOKEN)
+		seq_puts(seq,
+			 "Address  Interface   Hardware Address"
+			 "   Expires LastSend  Retry Status\n");
+	else {
+		seq_printf(seq, "%04X:%02X  %-12s",
+			   ntohs(entry->target_addr.s_net),
+			   (unsigned int) entry->target_addr.s_node,
+			   entry->dev ? entry->dev->name : "????");
+		seq_printf(seq, "%pM", entry->hwaddr);
+		seq_printf(seq, " %8s",
+			   dt2str((long)entry->expires_at - (long)now));
+		if (iter->table == unresolved)
+			seq_printf(seq, " %8s %6hu",
+				   dt2str(now - entry->last_sent),
+				   entry->xmit_count);
+		else
+			seq_puts(seq, "                ");
+		seq_printf(seq, " %s\n",
+			   (iter->table == resolved) ? "resolved"
+			   : (iter->table == unresolved) ? "unresolved"
+			   : (iter->table == proxies) ? "proxies"
+			   : "unknown");
+	}
+	return 0;
+}
+
+static const struct seq_operations aarp_seq_ops = {
+	.start  = aarp_seq_start,
+	.next   = aarp_seq_next,
+	.stop   = aarp_seq_stop,
+	.show   = aarp_seq_show,
+};
+
+static int aarp_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open_private(file, &aarp_seq_ops,
+			sizeof(struct aarp_iter_state));
+}
+
+const struct file_operations atalk_seq_arp_fops = {
+	.owner		= THIS_MODULE,
+	.open           = aarp_seq_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release	= seq_release_private,
+};
+#endif
+
+/* General module cleanup. Called from cleanup_module() in ddp.c. */
+void aarp_cleanup_module(void)
+{
+	del_timer_sync(&aarp_timer);
+	unregister_netdevice_notifier(&aarp_notifier);
+	unregister_snap_client(aarp_dl);
+	aarp_purge();
+}
diff --git a/drivers/staging/appletalk/atalk.h b/drivers/staging/appletalk/atalk.h
new file mode 100644
index 000000000000..d34c187432ed
--- /dev/null
+++ b/drivers/staging/appletalk/atalk.h
@@ -0,0 +1,208 @@
+#ifndef __LINUX_ATALK_H__
+#define __LINUX_ATALK_H__
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/*
+ * AppleTalk networking structures
+ *
+ * The following are directly referenced from the University Of Michigan
+ * netatalk for compatibility reasons.
+ */
+#define ATPORT_FIRST	1
+#define ATPORT_RESERVED	128
+#define ATPORT_LAST	254		/* 254 is only legal on localtalk */ 
+#define ATADDR_ANYNET	(__u16)0
+#define ATADDR_ANYNODE	(__u8)0
+#define ATADDR_ANYPORT  (__u8)0
+#define ATADDR_BCAST	(__u8)255
+#define DDP_MAXSZ	587
+#define DDP_MAXHOPS     15		/* 4 bits of hop counter */
+
+#define SIOCATALKDIFADDR       (SIOCPROTOPRIVATE + 0)
+
+struct atalk_addr {
+	__be16	s_net;
+	__u8	s_node;
+};
+
+struct sockaddr_at {
+	sa_family_t	  sat_family;
+	__u8		  sat_port;
+	struct atalk_addr sat_addr;
+	char		  sat_zero[8];
+};
+
+struct atalk_netrange {
+	__u8	nr_phase;
+	__be16	nr_firstnet;
+	__be16	nr_lastnet;
+};
+
+#ifdef __KERNEL__
+
+#include <net/sock.h>
+
+struct atalk_route {
+	struct net_device  *dev;
+	struct atalk_addr  target;
+	struct atalk_addr  gateway;
+	int		   flags;
+	struct atalk_route *next;
+};
+
+/**
+ *	struct atalk_iface - AppleTalk Interface
+ *	@dev - Network device associated with this interface
+ *	@address - Our address
+ *	@status - What are we doing?
+ *	@nets - Associated direct netrange
+ *	@next - next element in the list of interfaces
+ */
+struct atalk_iface {
+	struct net_device	*dev;
+	struct atalk_addr	address;
+	int			status;
+#define ATIF_PROBE	1		/* Probing for an address */
+#define ATIF_PROBE_FAIL	2		/* Probe collided */
+	struct atalk_netrange	nets;
+	struct atalk_iface	*next;
+};
+	
+struct atalk_sock {
+	/* struct sock has to be the first member of atalk_sock */
+	struct sock	sk;
+	__be16		dest_net;
+	__be16		src_net;
+	unsigned char	dest_node;
+	unsigned char	src_node;
+	unsigned char	dest_port;
+	unsigned char	src_port;
+};
+
+static inline struct atalk_sock *at_sk(struct sock *sk)
+{
+	return (struct atalk_sock *)sk;
+}
+
+struct ddpehdr {
+	__be16	deh_len_hops;	/* lower 10 bits are length, next 4 - hops */
+	__be16	deh_sum;
+	__be16	deh_dnet;
+	__be16	deh_snet;
+	__u8	deh_dnode;
+	__u8	deh_snode;
+	__u8	deh_dport;
+	__u8	deh_sport;
+	/* And netatalk apps expect to stick the type in themselves */
+};
+
+static __inline__ struct ddpehdr *ddp_hdr(struct sk_buff *skb)
+{
+	return (struct ddpehdr *)skb_transport_header(skb);
+}
+
+/* AppleTalk AARP headers */
+struct elapaarp {
+	__be16	hw_type;
+#define AARP_HW_TYPE_ETHERNET		1
+#define AARP_HW_TYPE_TOKENRING		2
+	__be16	pa_type;
+	__u8	hw_len;
+	__u8	pa_len;
+#define AARP_PA_ALEN			4
+	__be16	function;
+#define AARP_REQUEST			1
+#define AARP_REPLY			2
+#define AARP_PROBE			3
+	__u8	hw_src[ETH_ALEN];
+	__u8	pa_src_zero;
+	__be16	pa_src_net;
+	__u8	pa_src_node;
+	__u8	hw_dst[ETH_ALEN];
+	__u8	pa_dst_zero;
+	__be16	pa_dst_net;
+	__u8	pa_dst_node;
+} __attribute__ ((packed));
+
+static __inline__ struct elapaarp *aarp_hdr(struct sk_buff *skb)
+{
+	return (struct elapaarp *)skb_transport_header(skb);
+}
+
+/* Not specified - how long till we drop a resolved entry */
+#define AARP_EXPIRY_TIME	(5 * 60 * HZ)
+/* Size of hash table */
+#define AARP_HASH_SIZE		16
+/* Fast retransmission timer when resolving */
+#define AARP_TICK_TIME		(HZ / 5)
+/* Send 10 requests then give up (2 seconds) */
+#define AARP_RETRANSMIT_LIMIT	10
+/*
+ * Some value bigger than total retransmit time + a bit for last reply to
+ * appear and to stop continual requests
+ */
+#define AARP_RESOLVE_TIME	(10 * HZ)
+
+extern struct datalink_proto *ddp_dl, *aarp_dl;
+extern void aarp_proto_init(void);
+
+/* Inter module exports */
+
+/* Give a device find its atif control structure */
+static inline struct atalk_iface *atalk_find_dev(struct net_device *dev)
+{
+	return dev->atalk_ptr;
+}
+
+extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev);
+extern struct net_device *atrtr_get_dev(struct atalk_addr *sa);
+extern int		 aarp_send_ddp(struct net_device *dev,
+				       struct sk_buff *skb,
+				       struct atalk_addr *sa, void *hwaddr);
+extern void		 aarp_device_down(struct net_device *dev);
+extern void		 aarp_probe_network(struct atalk_iface *atif);
+extern int 		 aarp_proxy_probe_network(struct atalk_iface *atif,
+				     struct atalk_addr *sa);
+extern void		 aarp_proxy_remove(struct net_device *dev,
+					   struct atalk_addr *sa);
+
+extern void		aarp_cleanup_module(void);
+
+extern struct hlist_head atalk_sockets;
+extern rwlock_t atalk_sockets_lock;
+
+extern struct atalk_route *atalk_routes;
+extern rwlock_t atalk_routes_lock;
+
+extern struct atalk_iface *atalk_interfaces;
+extern rwlock_t atalk_interfaces_lock;
+
+extern struct atalk_route atrtr_default;
+
+extern const struct file_operations atalk_seq_arp_fops;
+
+extern int sysctl_aarp_expiry_time;
+extern int sysctl_aarp_tick_time;
+extern int sysctl_aarp_retransmit_limit;
+extern int sysctl_aarp_resolve_time;
+
+#ifdef CONFIG_SYSCTL
+extern void atalk_register_sysctl(void);
+extern void atalk_unregister_sysctl(void);
+#else
+#define atalk_register_sysctl()		do { } while(0)
+#define atalk_unregister_sysctl()	do { } while(0)
+#endif
+
+#ifdef CONFIG_PROC_FS
+extern int atalk_proc_init(void);
+extern void atalk_proc_exit(void);
+#else
+#define atalk_proc_init()	({ 0; })
+#define atalk_proc_exit()	do { } while(0)
+#endif /* CONFIG_PROC_FS */
+
+#endif /* __KERNEL__ */
+#endif /* __LINUX_ATALK_H__ */
diff --git a/drivers/staging/appletalk/atalk_proc.c b/drivers/staging/appletalk/atalk_proc.c
new file mode 100644
index 000000000000..d012ba2e67d1
--- /dev/null
+++ b/drivers/staging/appletalk/atalk_proc.c
@@ -0,0 +1,301 @@
+/*
+ * 	atalk_proc.c - proc support for Appletalk
+ *
+ * 	Copyright(c) Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ *	This program is free software; you can redistribute it and/or modify it
+ *	under the terms of the GNU General Public License as published by the
+ *	Free Software Foundation, version 2.
+ */
+
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include "atalk.h"
+
+
+static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos)
+{
+	struct atalk_iface *i;
+
+	for (i = atalk_interfaces; pos && i; i = i->next)
+		--pos;
+
+	return i;
+}
+
+static void *atalk_seq_interface_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_interfaces_lock)
+{
+	loff_t l = *pos;
+
+	read_lock_bh(&atalk_interfaces_lock);
+	return l ? atalk_get_interface_idx(--l) : SEQ_START_TOKEN;
+}
+
+static void *atalk_seq_interface_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct atalk_iface *i;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN) {
+		i = NULL;
+		if (atalk_interfaces)
+			i = atalk_interfaces;
+		goto out;
+	}
+	i = v;
+	i = i->next;
+out:
+	return i;
+}
+
+static void atalk_seq_interface_stop(struct seq_file *seq, void *v)
+	__releases(atalk_interfaces_lock)
+{
+	read_unlock_bh(&atalk_interfaces_lock);
+}
+
+static int atalk_seq_interface_show(struct seq_file *seq, void *v)
+{
+	struct atalk_iface *iface;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Interface        Address   Networks  "
+			      "Status\n");
+		goto out;
+	}
+
+	iface = v;
+	seq_printf(seq, "%-16s %04X:%02X  %04X-%04X  %d\n",
+		   iface->dev->name, ntohs(iface->address.s_net),
+		   iface->address.s_node, ntohs(iface->nets.nr_firstnet),
+		   ntohs(iface->nets.nr_lastnet), iface->status);
+out:
+	return 0;
+}
+
+static __inline__ struct atalk_route *atalk_get_route_idx(loff_t pos)
+{
+	struct atalk_route *r;
+
+	for (r = atalk_routes; pos && r; r = r->next)
+		--pos;
+
+	return r;
+}
+
+static void *atalk_seq_route_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_routes_lock)
+{
+	loff_t l = *pos;
+
+	read_lock_bh(&atalk_routes_lock);
+	return l ? atalk_get_route_idx(--l) : SEQ_START_TOKEN;
+}
+
+static void *atalk_seq_route_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct atalk_route *r;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN) {
+		r = NULL;
+		if (atalk_routes)
+			r = atalk_routes;
+		goto out;
+	}
+	r = v;
+	r = r->next;
+out:
+	return r;
+}
+
+static void atalk_seq_route_stop(struct seq_file *seq, void *v)
+	__releases(atalk_routes_lock)
+{
+	read_unlock_bh(&atalk_routes_lock);
+}
+
+static int atalk_seq_route_show(struct seq_file *seq, void *v)
+{
+	struct atalk_route *rt;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Target        Router  Flags Dev\n");
+		goto out;
+	}
+
+	if (atrtr_default.dev) {
+		rt = &atrtr_default;
+		seq_printf(seq, "Default     %04X:%02X  %-4d  %s\n",
+			       ntohs(rt->gateway.s_net), rt->gateway.s_node,
+			       rt->flags, rt->dev->name);
+	}
+
+	rt = v;
+	seq_printf(seq, "%04X:%02X     %04X:%02X  %-4d  %s\n",
+		   ntohs(rt->target.s_net), rt->target.s_node,
+		   ntohs(rt->gateway.s_net), rt->gateway.s_node,
+		   rt->flags, rt->dev->name);
+out:
+	return 0;
+}
+
+static void *atalk_seq_socket_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_sockets_lock)
+{
+	read_lock_bh(&atalk_sockets_lock);
+	return seq_hlist_start_head(&atalk_sockets, *pos);
+}
+
+static void *atalk_seq_socket_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	return seq_hlist_next(v, &atalk_sockets, pos);
+}
+
+static void atalk_seq_socket_stop(struct seq_file *seq, void *v)
+	__releases(atalk_sockets_lock)
+{
+	read_unlock_bh(&atalk_sockets_lock);
+}
+
+static int atalk_seq_socket_show(struct seq_file *seq, void *v)
+{
+	struct sock *s;
+	struct atalk_sock *at;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_printf(seq, "Type Local_addr  Remote_addr Tx_queue "
+				"Rx_queue St UID\n");
+		goto out;
+	}
+
+	s = sk_entry(v);
+	at = at_sk(s);
+
+	seq_printf(seq, "%02X   %04X:%02X:%02X  %04X:%02X:%02X  %08X:%08X "
+			"%02X %d\n",
+		   s->sk_type, ntohs(at->src_net), at->src_node, at->src_port,
+		   ntohs(at->dest_net), at->dest_node, at->dest_port,
+		   sk_wmem_alloc_get(s),
+		   sk_rmem_alloc_get(s),
+		   s->sk_state, SOCK_INODE(s->sk_socket)->i_uid);
+out:
+	return 0;
+}
+
+static const struct seq_operations atalk_seq_interface_ops = {
+	.start  = atalk_seq_interface_start,
+	.next   = atalk_seq_interface_next,
+	.stop   = atalk_seq_interface_stop,
+	.show   = atalk_seq_interface_show,
+};
+
+static const struct seq_operations atalk_seq_route_ops = {
+	.start  = atalk_seq_route_start,
+	.next   = atalk_seq_route_next,
+	.stop   = atalk_seq_route_stop,
+	.show   = atalk_seq_route_show,
+};
+
+static const struct seq_operations atalk_seq_socket_ops = {
+	.start  = atalk_seq_socket_start,
+	.next   = atalk_seq_socket_next,
+	.stop   = atalk_seq_socket_stop,
+	.show   = atalk_seq_socket_show,
+};
+
+static int atalk_seq_interface_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &atalk_seq_interface_ops);
+}
+
+static int atalk_seq_route_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &atalk_seq_route_ops);
+}
+
+static int atalk_seq_socket_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &atalk_seq_socket_ops);
+}
+
+static const struct file_operations atalk_seq_interface_fops = {
+	.owner		= THIS_MODULE,
+	.open		= atalk_seq_interface_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static const struct file_operations atalk_seq_route_fops = {
+	.owner		= THIS_MODULE,
+	.open		= atalk_seq_route_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static const struct file_operations atalk_seq_socket_fops = {
+	.owner		= THIS_MODULE,
+	.open		= atalk_seq_socket_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static struct proc_dir_entry *atalk_proc_dir;
+
+int __init atalk_proc_init(void)
+{
+	struct proc_dir_entry *p;
+	int rc = -ENOMEM;
+
+	atalk_proc_dir = proc_mkdir("atalk", init_net.proc_net);
+	if (!atalk_proc_dir)
+		goto out;
+
+	p = proc_create("interface", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_interface_fops);
+	if (!p)
+		goto out_interface;
+
+	p = proc_create("route", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_route_fops);
+	if (!p)
+		goto out_route;
+
+	p = proc_create("socket", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_socket_fops);
+	if (!p)
+		goto out_socket;
+
+	p = proc_create("arp", S_IRUGO, atalk_proc_dir, &atalk_seq_arp_fops);
+	if (!p)
+		goto out_arp;
+
+	rc = 0;
+out:
+	return rc;
+out_arp:
+	remove_proc_entry("socket", atalk_proc_dir);
+out_socket:
+	remove_proc_entry("route", atalk_proc_dir);
+out_route:
+	remove_proc_entry("interface", atalk_proc_dir);
+out_interface:
+	remove_proc_entry("atalk", init_net.proc_net);
+	goto out;
+}
+
+void __exit atalk_proc_exit(void)
+{
+	remove_proc_entry("interface", atalk_proc_dir);
+	remove_proc_entry("route", atalk_proc_dir);
+	remove_proc_entry("socket", atalk_proc_dir);
+	remove_proc_entry("arp", atalk_proc_dir);
+	remove_proc_entry("atalk", init_net.proc_net);
+}
diff --git a/drivers/staging/appletalk/cops.c b/drivers/staging/appletalk/cops.c
new file mode 100644
index 000000000000..661d42eff7d8
--- /dev/null
+++ b/drivers/staging/appletalk/cops.c
@@ -0,0 +1,1013 @@
+/*      cops.c: LocalTalk driver for Linux.
+ *
+ *	Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ *
+ *	With more than a little help from;
+ *	- Alan Cox <alan@lxorguk.ukuu.org.uk>
+ *
+ *      Derived from:
+ *      - skeleton.c: A network driver outline for linux.
+ *        Written 1993-94 by Donald Becker.
+ *	- ltpc.c: A driver for the LocalTalk PC card.
+ *	  Written by Bradford W. Johnson.
+ *
+ *      Copyright 1993 United States Government as represented by the
+ *      Director, National Security Agency.
+ *
+ *      This software may be used and distributed according to the terms
+ *      of the GNU General Public License, incorporated herein by reference.
+ *
+ *	Changes:
+ *	19970608	Alan Cox	Allowed dual card type support
+ *					Can set board type in insmod
+ *					Hooks for cops_setup routine
+ *					(not yet implemented).
+ *	19971101	Jay Schulist	Fixes for multiple lt* devices.
+ *	19980607	Steven Hirsch	Fixed the badly broken support
+ *					for Tangent type cards. Only
+ *                                      tested on Daystar LT200. Some
+ *                                      cleanup of formatting and program
+ *                                      logic.  Added emacs 'local-vars'
+ *                                      setup for Jay's brace style.
+ *	20000211	Alan Cox	Cleaned up for softnet
+ */
+
+static const char *version =
+"cops.c:v0.04 6/7/98 Jay Schulist <jschlst@samba.org>\n";
+/*
+ *  Sources:
+ *      COPS Localtalk SDK. This provides almost all of the information
+ *      needed.
+ */
+
+/*
+ * insmod/modprobe configurable stuff.
+ *	- IO Port, choose one your card supports or 0 if you dare.
+ *	- IRQ, also choose one your card supports or nothing and let
+ *	  the driver figure it out.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/in.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/if_ltalk.h>
+#include <linux/delay.h>	/* For udelay() */
+#include <linux/spinlock.h>
+#include <linux/bitops.h>
+#include <linux/jiffies.h>
+
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/dma.h>
+
+#include "atalk.h"
+#include "cops.h"		/* Our Stuff */
+#include "cops_ltdrv.h"		/* Firmware code for Tangent type cards. */
+#include "cops_ffdrv.h"		/* Firmware code for Dayna type cards. */
+
+/*
+ *      The name of the card. Is used for messages and in the requests for
+ *      io regions, irqs and dma channels
+ */
+
+static const char *cardname = "cops";
+
+#ifdef CONFIG_COPS_DAYNA
+static int board_type = DAYNA;	/* Module exported */
+#else
+static int board_type = TANGENT;
+#endif
+
+static int io = 0x240;		/* Default IO for Dayna */
+static int irq = 5;		/* Default IRQ */
+
+/*
+ *	COPS Autoprobe information.
+ *	Right now if port address is right but IRQ is not 5 this will
+ *      return a 5 no matter what since we will still get a status response.
+ *      Need one more additional check to narrow down after we have gotten
+ *      the ioaddr. But since only other possible IRQs is 3 and 4 so no real
+ *	hurry on this. I *STRONGLY* recommend using IRQ 5 for your card with
+ *	this driver.
+ * 
+ *	This driver has 2 modes and they are: Dayna mode and Tangent mode.
+ *	Each mode corresponds with the type of card. It has been found
+ *	that there are 2 main types of cards and all other cards are
+ *	the same and just have different names or only have minor differences
+ *	such as more IO ports. As this driver is tested it will
+ *	become more clear on exactly what cards are supported. The driver
+ *	defaults to using Dayna mode. To change the drivers mode, simply
+ *	select Dayna or Tangent mode when configuring the kernel.
+ *
+ *      This driver should support:
+ *      TANGENT driver mode:
+ *              Tangent ATB-II, Novell NL-1000, Daystar Digital LT-200,
+ *		COPS LT-1
+ *      DAYNA driver mode:
+ *              Dayna DL2000/DaynaTalk PC (Half Length), COPS LT-95, 
+ *		Farallon PhoneNET PC III, Farallon PhoneNET PC II
+ *	Other cards possibly supported mode unknown though:
+ *		Dayna DL2000 (Full length), COPS LT/M (Micro-Channel)
+ *
+ *	Cards NOT supported by this driver but supported by the ltpc.c
+ *	driver written by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *		Farallon PhoneNET PC
+ *		Original Apple LocalTalk PC card
+ * 
+ *      N.B.
+ *
+ *      The Daystar Digital LT200 boards do not support interrupt-driven
+ *      IO.  You must specify 'irq=0xff' as a module parameter to invoke
+ *      polled mode.  I also believe that the port probing logic is quite
+ *      dangerous at best and certainly hopeless for a polled card.  Best to 
+ *      specify both. - Steve H.
+ *
+ */
+
+/*
+ * Zero terminated list of IO ports to probe.
+ */
+
+static unsigned int ports[] = { 
+	0x240, 0x340, 0x200, 0x210, 0x220, 0x230, 0x260, 
+	0x2A0, 0x300, 0x310, 0x320, 0x330, 0x350, 0x360,
+	0
+};
+
+/*
+ * Zero terminated list of IRQ ports to probe.
+ */
+
+static int cops_irqlist[] = {
+	5, 4, 3, 0 
+};
+
+static struct timer_list cops_timer;
+
+/* use 0 for production, 1 for verification, 2 for debug, 3 for verbose debug */
+#ifndef COPS_DEBUG
+#define COPS_DEBUG 1 
+#endif
+static unsigned int cops_debug = COPS_DEBUG;
+
+/* The number of low I/O ports used by the card. */
+#define COPS_IO_EXTENT       8
+
+/* Information that needs to be kept for each board. */
+
+struct cops_local
+{
+        int board;			/* Holds what board type is. */
+	int nodeid;			/* Set to 1 once have nodeid. */
+        unsigned char node_acquire;	/* Node ID when acquired. */
+        struct atalk_addr node_addr;	/* Full node address */
+	spinlock_t lock;		/* RX/TX lock */
+};
+
+/* Index to functions, as function prototypes. */
+static int  cops_probe1 (struct net_device *dev, int ioaddr);
+static int  cops_irq (int ioaddr, int board);
+
+static int  cops_open (struct net_device *dev);
+static int  cops_jumpstart (struct net_device *dev);
+static void cops_reset (struct net_device *dev, int sleep);
+static void cops_load (struct net_device *dev);
+static int  cops_nodeid (struct net_device *dev, int nodeid);
+
+static irqreturn_t cops_interrupt (int irq, void *dev_id);
+static void cops_poll (unsigned long ltdev);
+static void cops_timeout(struct net_device *dev);
+static void cops_rx (struct net_device *dev);
+static netdev_tx_t  cops_send_packet (struct sk_buff *skb,
+					    struct net_device *dev);
+static void set_multicast_list (struct net_device *dev);
+static int  cops_ioctl (struct net_device *dev, struct ifreq *rq, int cmd);
+static int  cops_close (struct net_device *dev);
+
+static void cleanup_card(struct net_device *dev)
+{
+	if (dev->irq)
+		free_irq(dev->irq, dev);
+	release_region(dev->base_addr, COPS_IO_EXTENT);
+}
+
+/*
+ *      Check for a network adaptor of this type, and return '0' iff one exists.
+ *      If dev->base_addr == 0, probe all likely locations.
+ *      If dev->base_addr in [1..0x1ff], always return failure.
+ *        otherwise go with what we pass in.
+ */
+struct net_device * __init cops_probe(int unit)
+{
+	struct net_device *dev;
+	unsigned *port;
+	int base_addr;
+	int err = 0;
+
+	dev = alloc_ltalkdev(sizeof(struct cops_local));
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	if (unit >= 0) {
+		sprintf(dev->name, "lt%d", unit);
+		netdev_boot_setup_check(dev);
+		irq = dev->irq;
+		base_addr = dev->base_addr;
+	} else {
+		base_addr = dev->base_addr = io;
+	}
+
+	if (base_addr > 0x1ff) {    /* Check a single specified location. */
+		err = cops_probe1(dev, base_addr);
+	} else if (base_addr != 0) { /* Don't probe at all. */
+		err = -ENXIO;
+	} else {
+		/* FIXME  Does this really work for cards which generate irq?
+		 * It's definitely N.G. for polled Tangent. sh
+		 * Dayna cards don't autoprobe well at all, but if your card is
+		 * at IRQ 5 & IO 0x240 we find it every time. ;) JS
+		 */
+		for (port = ports; *port && cops_probe1(dev, *port) < 0; port++)
+			;
+		if (!*port)
+			err = -ENODEV;
+	}
+	if (err)
+		goto out;
+	err = register_netdev(dev);
+	if (err)
+		goto out1;
+	return dev;
+out1:
+	cleanup_card(dev);
+out:
+	free_netdev(dev);
+	return ERR_PTR(err);
+}
+
+static const struct net_device_ops cops_netdev_ops = {
+	.ndo_open               = cops_open,
+        .ndo_stop               = cops_close,
+	.ndo_start_xmit   	= cops_send_packet,
+	.ndo_tx_timeout		= cops_timeout,
+        .ndo_do_ioctl           = cops_ioctl,
+	.ndo_set_multicast_list = set_multicast_list,
+};
+
+/*
+ *      This is the real probe routine. Linux has a history of friendly device
+ *      probes on the ISA bus. A good device probes avoids doing writes, and
+ *      verifies that the correct device exists and functions.
+ */
+static int __init cops_probe1(struct net_device *dev, int ioaddr)
+{
+        struct cops_local *lp;
+	static unsigned version_printed;
+	int board = board_type;
+	int retval;
+	
+        if(cops_debug && version_printed++ == 0)
+		printk("%s", version);
+
+	/* Grab the region so no one else tries to probe our ioports. */
+	if (!request_region(ioaddr, COPS_IO_EXTENT, dev->name))
+		return -EBUSY;
+
+        /*
+         * Since this board has jumpered interrupts, allocate the interrupt
+         * vector now. There is no point in waiting since no other device
+         * can use the interrupt, and this marks the irq as busy. Jumpered
+         * interrupts are typically not reported by the boards, and we must
+         * used AutoIRQ to find them.
+	 */
+	dev->irq = irq;
+	switch (dev->irq)
+	{
+		case 0:
+			/* COPS AutoIRQ routine */
+			dev->irq = cops_irq(ioaddr, board);
+			if (dev->irq)
+				break;
+			/* No IRQ found on this port, fallthrough */
+		case 1:
+			retval = -EINVAL;
+			goto err_out;
+
+		/* Fixup for users that don't know that IRQ 2 is really
+		 * IRQ 9, or don't know which one to set.
+		 */
+		case 2:
+			dev->irq = 9;
+			break;
+
+		/* Polled operation requested. Although irq of zero passed as
+		 * a parameter tells the init routines to probe, we'll
+		 * overload it to denote polled operation at runtime.
+		 */
+		case 0xff:
+			dev->irq = 0;
+			break;
+
+		default:
+			break;
+	}
+
+	/* Reserve any actual interrupt. */
+	if (dev->irq) {
+		retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev);
+		if (retval)
+			goto err_out;
+	}
+
+	dev->base_addr = ioaddr;
+
+        lp = netdev_priv(dev);
+        spin_lock_init(&lp->lock);
+
+	/* Copy local board variable to lp struct. */
+	lp->board               = board;
+
+	dev->netdev_ops 	= &cops_netdev_ops;
+	dev->watchdog_timeo	= HZ * 2;
+
+
+	/* Tell the user where the card is and what mode we're in. */
+	if(board==DAYNA)
+		printk("%s: %s at %#3x, using IRQ %d, in Dayna mode.\n", 
+			dev->name, cardname, ioaddr, dev->irq);
+	if(board==TANGENT) {
+		if(dev->irq)
+			printk("%s: %s at %#3x, IRQ %d, in Tangent mode\n", 
+				dev->name, cardname, ioaddr, dev->irq);
+		else
+			printk("%s: %s at %#3x, using polled IO, in Tangent mode.\n", 
+				dev->name, cardname, ioaddr);
+
+	}
+        return 0;
+
+err_out:
+	release_region(ioaddr, COPS_IO_EXTENT);
+	return retval;
+}
+
+static int __init cops_irq (int ioaddr, int board)
+{       /*
+         * This does not use the IRQ to determine where the IRQ is. We just
+         * assume that when we get a correct status response that it's the IRQ.
+         * This really just verifies the IO port but since we only have access
+         * to such a small number of IRQs (5, 4, 3) this is not bad.
+         * This will probably not work for more than one card.
+         */
+        int irqaddr=0;
+        int i, x, status;
+
+        if(board==DAYNA)
+        {
+                outb(0, ioaddr+DAYNA_RESET);
+                inb(ioaddr+DAYNA_RESET);
+                mdelay(333);
+        }
+        if(board==TANGENT)
+        {
+                inb(ioaddr);
+                outb(0, ioaddr);
+                outb(0, ioaddr+TANG_RESET);
+        }
+
+        for(i=0; cops_irqlist[i] !=0; i++)
+        {
+                irqaddr = cops_irqlist[i];
+                for(x = 0xFFFF; x>0; x --)    /* wait for response */
+                {
+                        if(board==DAYNA)
+                        {
+                                status = (inb(ioaddr+DAYNA_CARD_STATUS)&3);
+                                if(status == 1)
+                                        return irqaddr;
+                        }
+                        if(board==TANGENT)
+                        {
+                                if((inb(ioaddr+TANG_CARD_STATUS)& TANG_TX_READY) !=0)
+                                        return irqaddr;
+                        }
+                }
+        }
+        return 0;       /* no IRQ found */
+}
+
+/*
+ * Open/initialize the board. This is called (in the current kernel)
+ * sometime after booting when the 'ifconfig' program is run.
+ */
+static int cops_open(struct net_device *dev)
+{
+    struct cops_local *lp = netdev_priv(dev);
+
+	if(dev->irq==0)
+	{
+		/*
+		 * I don't know if the Dayna-style boards support polled 
+		 * operation.  For now, only allow it for Tangent.
+		 */
+		if(lp->board==TANGENT)	/* Poll 20 times per second */
+		{
+		    init_timer(&cops_timer);
+		    cops_timer.function = cops_poll;
+		    cops_timer.data 	= (unsigned long)dev;
+		    cops_timer.expires 	= jiffies + HZ/20;
+		    add_timer(&cops_timer);
+		} 
+		else 
+		{
+			printk(KERN_WARNING "%s: No irq line set\n", dev->name);
+			return -EAGAIN;
+		}
+	}
+
+	cops_jumpstart(dev);	/* Start the card up. */
+
+	netif_start_queue(dev);
+        return 0;
+}
+
+/*
+ *	This allows for a dynamic start/restart of the entire card.
+ */
+static int cops_jumpstart(struct net_device *dev)
+{
+	struct cops_local *lp = netdev_priv(dev);
+
+	/*
+         *      Once the card has the firmware loaded and has acquired
+         *      the nodeid, if it is reset it will lose it all.
+         */
+        cops_reset(dev,1);	/* Need to reset card before load firmware. */
+        cops_load(dev);		/* Load the firmware. */
+
+	/*
+	 *	If atalkd already gave us a nodeid we will use that
+	 *	one again, else we wait for atalkd to give us a nodeid
+	 *	in cops_ioctl. This may cause a problem if someone steals
+	 *	our nodeid while we are resetting.
+	 */	
+	if(lp->nodeid == 1)
+		cops_nodeid(dev,lp->node_acquire);
+
+	return 0;
+}
+
+static void tangent_wait_reset(int ioaddr)
+{
+	int timeout=0;
+
+	while(timeout++ < 5 && (inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
+		mdelay(1);   /* Wait 1 second */
+}
+
+/*
+ *      Reset the LocalTalk board.
+ */
+static void cops_reset(struct net_device *dev, int sleep)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr=dev->base_addr;
+
+        if(lp->board==TANGENT)
+        {
+                inb(ioaddr);		/* Clear request latch. */
+                outb(0,ioaddr);		/* Clear the TANG_TX_READY flop. */
+                outb(0, ioaddr+TANG_RESET);	/* Reset the adapter. */
+
+		tangent_wait_reset(ioaddr);
+                outb(0, ioaddr+TANG_CLEAR_INT);
+        }
+        if(lp->board==DAYNA)
+        {
+                outb(0, ioaddr+DAYNA_RESET);	/* Assert the reset port */
+                inb(ioaddr+DAYNA_RESET);	/* Clear the reset */
+		if (sleep)
+			msleep(333);
+		else
+			mdelay(333);
+        }
+
+	netif_wake_queue(dev);
+}
+
+static void cops_load (struct net_device *dev)
+{
+        struct ifreq ifr;
+        struct ltfirmware *ltf= (struct ltfirmware *)&ifr.ifr_ifru;
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr=dev->base_addr;
+	int length, i = 0;
+
+        strcpy(ifr.ifr_name,"lt0");
+
+        /* Get card's firmware code and do some checks on it. */
+#ifdef CONFIG_COPS_DAYNA        
+        if(lp->board==DAYNA)
+        {
+                ltf->length=sizeof(ffdrv_code);
+                ltf->data=ffdrv_code;
+        }
+        else
+#endif        
+#ifdef CONFIG_COPS_TANGENT
+        if(lp->board==TANGENT)
+        {
+                ltf->length=sizeof(ltdrv_code);
+                ltf->data=ltdrv_code;
+        }
+        else
+#endif
+	{
+		printk(KERN_INFO "%s; unsupported board type.\n", dev->name);
+		return;
+	}
+	
+        /* Check to make sure firmware is correct length. */
+        if(lp->board==DAYNA && ltf->length!=5983)
+        {
+                printk(KERN_WARNING "%s: Firmware is not length of FFDRV.BIN.\n", dev->name);
+                return;
+        }
+        if(lp->board==TANGENT && ltf->length!=2501)
+        {
+                printk(KERN_WARNING "%s: Firmware is not length of DRVCODE.BIN.\n", dev->name);
+                return;
+        }
+
+        if(lp->board==DAYNA)
+        {
+                /*
+                 *      We must wait for a status response
+                 *      with the DAYNA board.
+                 */
+                while(++i<65536)
+                {
+                       if((inb(ioaddr+DAYNA_CARD_STATUS)&3)==1)
+                                break;
+                }
+
+                if(i==65536)
+                        return;
+        }
+
+        /*
+         *      Upload the firmware and kick. Byte-by-byte works nicely here.
+         */
+	i=0;
+        length = ltf->length;
+        while(length--)
+        {
+                outb(ltf->data[i], ioaddr);
+                i++;
+        }
+
+	if(cops_debug > 1)
+		printk("%s: Uploaded firmware - %d bytes of %d bytes.\n", 
+			dev->name, i, ltf->length);
+
+        if(lp->board==DAYNA) 	/* Tell Dayna to run the firmware code. */
+                outb(1, ioaddr+DAYNA_INT_CARD);
+	else			/* Tell Tang to run the firmware code. */
+		inb(ioaddr);
+
+        if(lp->board==TANGENT)
+        {
+                tangent_wait_reset(ioaddr);
+                inb(ioaddr);	/* Clear initial ready signal. */
+        }
+}
+
+/*
+ * 	Get the LocalTalk Nodeid from the card. We can suggest
+ *	any nodeid 1-254. The card will try and get that exact
+ *	address else we can specify 0 as the nodeid and the card
+ *	will autoprobe for a nodeid.
+ */
+static int cops_nodeid (struct net_device *dev, int nodeid)
+{
+	struct cops_local *lp = netdev_priv(dev);
+	int ioaddr = dev->base_addr;
+
+	if(lp->board == DAYNA)
+        {
+        	/* Empty any pending adapter responses. */
+                while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
+                {
+			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupts. */
+        		if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
+                		cops_rx(dev);	/* Kick any packets waiting. */
+			schedule();
+                }
+
+                outb(2, ioaddr);       	/* Output command packet length as 2. */
+                outb(0, ioaddr);
+                outb(LAP_INIT, ioaddr);	/* Send LAP_INIT command byte. */
+                outb(nodeid, ioaddr);  	/* Suggest node address. */
+        }
+
+	if(lp->board == TANGENT)
+        {
+                /* Empty any pending adapter responses. */
+                while(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
+                {
+			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupt. */
+                	cops_rx(dev);          	/* Kick out packets waiting. */
+			schedule();
+                }
+
+		/* Not sure what Tangent does if nodeid picked is used. */
+                if(nodeid == 0)	         		/* Seed. */
+                	nodeid = jiffies&0xFF;		/* Get a random try */
+                outb(2, ioaddr);        		/* Command length LSB */
+                outb(0, ioaddr);       			/* Command length MSB */
+                outb(LAP_INIT, ioaddr); 		/* Send LAP_INIT byte */
+                outb(nodeid, ioaddr); 		  	/* LAP address hint. */
+                outb(0xFF, ioaddr);     		/* Int. level to use */
+        }
+
+	lp->node_acquire=0;		/* Set nodeid holder to 0. */
+        while(lp->node_acquire==0)	/* Get *True* nodeid finally. */
+	{
+		outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear any interrupt. */
+
+		if(lp->board == DAYNA)
+		{
+                	if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
+                		cops_rx(dev);	/* Grab the nodeid put in lp->node_acquire. */
+		}
+		if(lp->board == TANGENT)
+		{	
+			if(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
+                                cops_rx(dev);   /* Grab the nodeid put in lp->node_acquire. */
+		}
+		schedule();
+	}
+
+	if(cops_debug > 1)
+		printk(KERN_DEBUG "%s: Node ID %d has been acquired.\n", 
+			dev->name, lp->node_acquire);
+
+	lp->nodeid=1;	/* Set got nodeid to 1. */
+
+        return 0;
+}
+
+/*
+ *	Poll the Tangent type cards to see if we have work.
+ */
+ 
+static void cops_poll(unsigned long ltdev)
+{
+	int ioaddr, status;
+	int boguscount = 0;
+
+	struct net_device *dev = (struct net_device *)ltdev;
+
+	del_timer(&cops_timer);
+
+	if(dev == NULL)
+		return;	/* We've been downed */
+
+	ioaddr = dev->base_addr;
+	do {
+		status=inb(ioaddr+TANG_CARD_STATUS);
+		if(status & TANG_RX_READY)
+			cops_rx(dev);
+		if(status & TANG_TX_READY)
+			netif_wake_queue(dev);
+		status = inb(ioaddr+TANG_CARD_STATUS);
+	} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
+
+	/* poll 20 times per second */
+	cops_timer.expires = jiffies + HZ/20;
+	add_timer(&cops_timer);
+}
+
+/*
+ *      The typical workload of the driver:
+ *      Handle the network interface interrupts.
+ */
+static irqreturn_t cops_interrupt(int irq, void *dev_id)
+{
+        struct net_device *dev = dev_id;
+        struct cops_local *lp;
+        int ioaddr, status;
+        int boguscount = 0;
+
+        ioaddr = dev->base_addr;
+        lp = netdev_priv(dev);
+
+	if(lp->board==DAYNA)
+	{
+		do {
+			outb(0, ioaddr + COPS_CLEAR_INT);
+                       	status=inb(ioaddr+DAYNA_CARD_STATUS);
+                       	if((status&0x03)==DAYNA_RX_REQUEST)
+                       	        cops_rx(dev);
+                	netif_wake_queue(dev);
+		} while(++boguscount < 20);
+	}
+	else
+	{
+		do {
+                       	status=inb(ioaddr+TANG_CARD_STATUS);
+			if(status & TANG_RX_READY)
+				cops_rx(dev);
+			if(status & TANG_TX_READY)
+				netif_wake_queue(dev);
+			status=inb(ioaddr+TANG_CARD_STATUS);
+		} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
+	}
+
+        return IRQ_HANDLED;
+}
+
+/*
+ *      We have a good packet(s), get it/them out of the buffers.
+ */
+static void cops_rx(struct net_device *dev)
+{
+        int pkt_len = 0;
+        int rsp_type = 0;
+        struct sk_buff *skb = NULL;
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr = dev->base_addr;
+        int boguscount = 0;
+        unsigned long flags;
+
+
+	spin_lock_irqsave(&lp->lock, flags);
+	
+        if(lp->board==DAYNA)
+        {
+                outb(0, ioaddr);                /* Send out Zero length. */
+                outb(0, ioaddr);
+                outb(DATA_READ, ioaddr);        /* Send read command out. */
+
+                /* Wait for DMA to turn around. */
+                while(++boguscount<1000000)
+                {
+			barrier();
+                        if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_READY)
+                                break;
+                }
+
+                if(boguscount==1000000)
+                {
+                        printk(KERN_WARNING "%s: DMA timed out.\n",dev->name);
+			spin_unlock_irqrestore(&lp->lock, flags);
+                        return;
+                }
+        }
+
+        /* Get response length. */
+	if(lp->board==DAYNA)
+        	pkt_len = inb(ioaddr) & 0xFF;
+	else
+		pkt_len = inb(ioaddr) & 0x00FF;
+        pkt_len |= (inb(ioaddr) << 8);
+        /* Input IO code. */
+        rsp_type=inb(ioaddr);
+
+        /* Malloc up new buffer. */
+        skb = dev_alloc_skb(pkt_len);
+        if(skb == NULL)
+        {
+                printk(KERN_WARNING "%s: Memory squeeze, dropping packet.\n",
+			dev->name);
+                dev->stats.rx_dropped++;
+                while(pkt_len--)        /* Discard packet */
+                        inb(ioaddr);
+                spin_unlock_irqrestore(&lp->lock, flags);
+                return;
+        }
+        skb->dev = dev;
+        skb_put(skb, pkt_len);
+        skb->protocol = htons(ETH_P_LOCALTALK);
+
+        insb(ioaddr, skb->data, pkt_len);               /* Eat the Data */
+
+        if(lp->board==DAYNA)
+                outb(1, ioaddr+DAYNA_INT_CARD);         /* Interrupt the card */
+
+        spin_unlock_irqrestore(&lp->lock, flags);  /* Restore interrupts. */
+
+        /* Check for bad response length */
+        if(pkt_len < 0 || pkt_len > MAX_LLAP_SIZE)
+        {
+		printk(KERN_WARNING "%s: Bad packet length of %d bytes.\n", 
+			dev->name, pkt_len);
+                dev->stats.tx_errors++;
+                dev_kfree_skb_any(skb);
+                return;
+        }
+
+        /* Set nodeid and then get out. */
+        if(rsp_type == LAP_INIT_RSP)
+        {	/* Nodeid taken from received packet. */
+                lp->node_acquire = skb->data[0];
+                dev_kfree_skb_any(skb);
+                return;
+        }
+
+        /* One last check to make sure we have a good packet. */
+        if(rsp_type != LAP_RESPONSE)
+        {
+                printk(KERN_WARNING "%s: Bad packet type %d.\n", dev->name, rsp_type);
+                dev->stats.tx_errors++;
+                dev_kfree_skb_any(skb);
+                return;
+        }
+
+        skb_reset_mac_header(skb);    /* Point to entire packet. */
+        skb_pull(skb,3);
+        skb_reset_transport_header(skb);    /* Point to data (Skip header). */
+
+        /* Update the counters. */
+        dev->stats.rx_packets++;
+        dev->stats.rx_bytes += skb->len;
+
+        /* Send packet to a higher place. */
+        netif_rx(skb);
+}
+
+static void cops_timeout(struct net_device *dev)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr = dev->base_addr;
+
+	dev->stats.tx_errors++;
+        if(lp->board==TANGENT)
+        {
+		if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
+               		printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name);
+	}
+	printk(KERN_WARNING "%s: Transmit timed out.\n", dev->name);
+	cops_jumpstart(dev);	/* Restart the card. */
+	dev->trans_start = jiffies; /* prevent tx timeout */
+	netif_wake_queue(dev);
+}
+
+
+/*
+ *	Make the card transmit a LocalTalk packet.
+ */
+
+static netdev_tx_t cops_send_packet(struct sk_buff *skb,
+					  struct net_device *dev)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr = dev->base_addr;
+        unsigned long flags;
+
+        /*
+         * Block a timer-based transmit from overlapping. 
+	 */
+	 
+	netif_stop_queue(dev);
+
+	spin_lock_irqsave(&lp->lock, flags);
+	if(lp->board == DAYNA)	 /* Wait for adapter transmit buffer. */
+		while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
+			cpu_relax();
+	if(lp->board == TANGENT) /* Wait for adapter transmit buffer. */
+		while((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
+			cpu_relax();
+
+	/* Output IO length. */
+	outb(skb->len, ioaddr);
+	if(lp->board == DAYNA)
+               	outb(skb->len >> 8, ioaddr);
+	else
+		outb((skb->len >> 8)&0x0FF, ioaddr);
+
+	/* Output IO code. */
+	outb(LAP_WRITE, ioaddr);
+
+	if(lp->board == DAYNA)	/* Check the transmit buffer again. */
+        	while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0);
+
+	outsb(ioaddr, skb->data, skb->len);	/* Send out the data. */
+
+	if(lp->board==DAYNA)	/* Dayna requires you kick the card */
+		outb(1, ioaddr+DAYNA_INT_CARD);
+
+	spin_unlock_irqrestore(&lp->lock, flags);	/* Restore interrupts. */
+
+	/* Done sending packet, update counters and cleanup. */
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+	dev_kfree_skb (skb);
+	return NETDEV_TX_OK;
+}
+
+/*
+ *	Dummy function to keep the Appletalk layer happy.
+ */
+ 
+static void set_multicast_list(struct net_device *dev)
+{
+        if(cops_debug >= 3)
+		printk("%s: set_multicast_list executed\n", dev->name);
+}
+
+/*
+ *      System ioctls for the COPS LocalTalk card.
+ */
+ 
+static int cops_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        struct sockaddr_at *sa = (struct sockaddr_at *)&ifr->ifr_addr;
+        struct atalk_addr *aa = (struct atalk_addr *)&lp->node_addr;
+
+        switch(cmd)
+        {
+                case SIOCSIFADDR:
+			/* Get and set the nodeid and network # atalkd wants. */
+			cops_nodeid(dev, sa->sat_addr.s_node);
+			aa->s_net               = sa->sat_addr.s_net;
+                        aa->s_node              = lp->node_acquire;
+
+			/* Set broardcast address. */
+                        dev->broadcast[0]       = 0xFF;
+			
+			/* Set hardware address. */
+                        dev->dev_addr[0]        = aa->s_node;
+                        dev->addr_len           = 1;
+                        return 0;
+
+                case SIOCGIFADDR:
+                        sa->sat_addr.s_net      = aa->s_net;
+                        sa->sat_addr.s_node     = aa->s_node;
+                        return 0;
+
+                default:
+                        return -EOPNOTSUPP;
+        }
+}
+
+/*
+ *	The inverse routine to cops_open().
+ */
+ 
+static int cops_close(struct net_device *dev)
+{
+	struct cops_local *lp = netdev_priv(dev);
+
+	/* If we were running polled, yank the timer.
+	 */
+	if(lp->board==TANGENT && dev->irq==0)
+		del_timer(&cops_timer);
+
+	netif_stop_queue(dev);
+        return 0;
+}
+
+
+#ifdef MODULE
+static struct net_device *cops_dev;
+
+MODULE_LICENSE("GPL");
+module_param(io, int, 0);
+module_param(irq, int, 0);
+module_param(board_type, int, 0);
+
+static int __init cops_module_init(void)
+{
+	if (io == 0)
+		printk(KERN_WARNING "%s: You shouldn't autoprobe with insmod\n",
+			cardname);
+	cops_dev = cops_probe(-1);
+	if (IS_ERR(cops_dev))
+		return PTR_ERR(cops_dev);
+        return 0;
+}
+
+static void __exit cops_module_exit(void)
+{
+	unregister_netdev(cops_dev);
+	cleanup_card(cops_dev);
+	free_netdev(cops_dev);
+}
+module_init(cops_module_init);
+module_exit(cops_module_exit);
+#endif /* MODULE */
diff --git a/drivers/staging/appletalk/cops.h b/drivers/staging/appletalk/cops.h
new file mode 100644
index 000000000000..fd2750b269c8
--- /dev/null
+++ b/drivers/staging/appletalk/cops.h
@@ -0,0 +1,60 @@
+/*      cops.h: LocalTalk driver for Linux.
+ *
+ *      Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ */
+
+#ifndef __LINUX_COPSLTALK_H
+#define __LINUX_COPSLTALK_H
+
+#ifdef __KERNEL__
+
+/* Max LLAP size we will accept. */
+#define MAX_LLAP_SIZE		603
+
+/* Tangent */
+#define TANG_CARD_STATUS        1
+#define TANG_CLEAR_INT          1
+#define TANG_RESET              3
+
+#define TANG_TX_READY           1
+#define TANG_RX_READY           2
+
+/* Dayna */
+#define DAYNA_CMD_DATA          0
+#define DAYNA_CLEAR_INT         1
+#define DAYNA_CARD_STATUS       2
+#define DAYNA_INT_CARD          3
+#define DAYNA_RESET             4
+
+#define DAYNA_RX_READY          0
+#define DAYNA_TX_READY          1
+#define DAYNA_RX_REQUEST        3
+
+/* Same on both card types */
+#define COPS_CLEAR_INT  1
+
+/* LAP response codes received from the cards. */
+#define LAP_INIT        1       /* Init cmd */
+#define LAP_INIT_RSP    2       /* Init response */
+#define LAP_WRITE       3       /* Write cmd */
+#define DATA_READ       4       /* Data read */
+#define LAP_RESPONSE    4       /* Received ALAP frame response */
+#define LAP_GETSTAT     5       /* Get LAP and HW status */
+#define LAP_RSPSTAT     6       /* Status response */
+
+#endif
+
+/*
+ *	Structure to hold the firmware information.
+ */
+struct ltfirmware
+{
+        unsigned int length;
+        const unsigned char *data;
+};
+
+#define DAYNA 1
+#define TANGENT 2
+
+#endif
diff --git a/drivers/staging/appletalk/cops_ffdrv.h b/drivers/staging/appletalk/cops_ffdrv.h
new file mode 100644
index 000000000000..b02005087c1b
--- /dev/null
+++ b/drivers/staging/appletalk/cops_ffdrv.h
@@ -0,0 +1,532 @@
+
+/*
+ *	The firmware this driver downloads into the Localtalk card is a
+ *	separate program and is not GPL'd source code, even though the Linux
+ *	side driver and the routine that loads this data into the card are.
+ *	
+ *	It is taken from the COPS SDK and is under the following license
+ *
+ *	This material is licensed to you strictly for use in conjunction with
+ *	the use of COPS LocalTalk adapters.
+ *	There is no charge for this SDK. And no waranty express or implied
+ *	about its fitness for any purpose. However, we will cheerefully
+ *	refund every penny you paid for this SDK...
+ *	Regards,
+ *
+ *	Thomas F. Divine
+ *	Chief Scientist
+ */
+
+
+/*      cops_ffdrv.h: LocalTalk driver firmware dump for Linux.
+ *
+ *      Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ */
+
+
+#ifdef CONFIG_COPS_DAYNA
+
+static const unsigned char ffdrv_code[] = {
+	58,3,0,50,228,149,33,255,255,34,226,149,
+	249,17,40,152,33,202,154,183,237,82,77,68,
+	11,107,98,19,54,0,237,176,175,50,80,0,
+	62,128,237,71,62,32,237,57,51,62,12,237,
+	57,50,237,57,54,62,6,237,57,52,62,12,
+	237,57,49,33,107,137,34,32,128,33,83,130,
+	34,40,128,33,86,130,34,42,128,33,112,130,
+	34,36,128,33,211,130,34,38,128,62,0,237,
+	57,16,33,63,148,34,34,128,237,94,205,15,
+	130,251,205,168,145,24,141,67,111,112,121,114,
+	105,103,104,116,32,40,67,41,32,49,57,56,
+	56,32,45,32,68,97,121,110,97,32,67,111,
+	109,109,117,110,105,99,97,116,105,111,110,115,
+	32,32,32,65,108,108,32,114,105,103,104,116,
+	115,32,114,101,115,101,114,118,101,100,46,32,
+	32,40,68,40,68,7,16,8,34,7,22,6,
+	16,5,12,4,8,3,6,140,0,16,39,128,
+	0,4,96,10,224,6,0,7,126,2,64,11,
+	118,12,6,13,0,14,193,15,0,5,96,3,
+	192,1,64,9,8,62,9,211,66,62,192,211,
+	66,62,100,61,32,253,6,28,33,205,129,14,
+	66,237,163,194,253,129,6,28,33,205,129,14,
+	64,237,163,194,9,130,201,62,47,50,71,152,
+	62,47,211,68,58,203,129,237,57,20,58,204,
+	129,237,57,21,33,77,152,54,132,205,233,129,
+	58,228,149,254,209,40,6,56,4,62,0,24,
+	2,219,96,33,233,149,119,230,62,33,232,149,
+	119,213,33,8,152,17,7,0,25,119,19,25,
+	119,209,201,251,237,77,245,197,213,229,221,229,
+	205,233,129,62,1,50,106,137,205,158,139,221,
+	225,225,209,193,241,251,237,77,245,197,213,219,
+	72,237,56,16,230,46,237,57,16,237,56,12,
+	58,72,152,183,32,26,6,20,17,128,2,237,
+	56,46,187,32,35,237,56,47,186,32,29,219,
+	72,230,1,32,3,5,32,232,175,50,72,152,
+	229,221,229,62,1,50,106,137,205,158,139,221,
+	225,225,24,25,62,1,50,72,152,58,201,129,
+	237,57,12,58,202,129,237,57,13,237,56,16,
+	246,17,237,57,16,209,193,241,251,237,77,245,
+	197,229,213,221,229,237,56,16,230,17,237,57,
+	16,237,56,20,58,34,152,246,16,246,8,211,
+	68,62,6,61,32,253,58,34,152,246,8,211,
+	68,58,203,129,237,57,20,58,204,129,237,57,
+	21,237,56,16,246,34,237,57,16,221,225,209,
+	225,193,241,251,237,77,33,2,0,57,126,230,
+	3,237,100,1,40,2,246,128,230,130,245,62,
+	5,211,64,241,211,64,201,229,213,243,237,56,
+	16,230,46,237,57,16,237,56,12,251,70,35,
+	35,126,254,175,202,77,133,254,129,202,15,133,
+	230,128,194,191,132,43,58,44,152,119,33,76,
+	152,119,35,62,132,119,120,254,255,40,4,58,
+	49,152,119,219,72,43,43,112,17,3,0,237,
+	56,52,230,248,237,57,52,219,72,230,1,194,
+	141,131,209,225,237,56,52,246,6,237,57,52,
+	62,1,55,251,201,62,3,211,66,62,192,211,
+	66,62,48,211,66,0,0,219,66,230,1,40,
+	4,219,67,24,240,205,203,135,58,75,152,254,
+	255,202,128,132,58,49,152,254,161,250,207,131,
+	58,34,152,211,68,62,10,211,66,62,128,211,
+	66,62,11,211,66,62,6,211,66,24,0,62,
+	14,211,66,62,33,211,66,62,1,211,66,62,
+	64,211,66,62,3,211,66,62,209,211,66,62,
+	100,71,219,66,230,1,32,6,5,32,247,195,
+	248,132,219,67,71,58,44,152,184,194,248,132,
+	62,100,71,219,66,230,1,32,6,5,32,247,
+	195,248,132,219,67,62,100,71,219,66,230,1,
+	32,6,5,32,247,195,248,132,219,67,254,133,
+	32,7,62,0,50,74,152,24,17,254,173,32,
+	7,62,1,50,74,152,24,6,254,141,194,248,
+	132,71,209,225,58,49,152,254,132,32,10,62,
+	50,205,2,134,205,144,135,24,27,254,140,32,
+	15,62,110,205,2,134,62,141,184,32,5,205,
+	144,135,24,8,62,10,205,2,134,205,8,134,
+	62,1,50,106,137,205,158,139,237,56,52,246,
+	6,237,57,52,175,183,251,201,62,20,135,237,
+	57,20,175,237,57,21,237,56,16,246,2,237,
+	57,16,237,56,20,95,237,56,21,123,254,10,
+	48,244,237,56,16,230,17,237,57,16,209,225,
+	205,144,135,62,1,50,106,137,205,158,139,237,
+	56,52,246,6,237,57,52,175,183,251,201,209,
+	225,243,219,72,230,1,40,13,62,10,211,66,
+	0,0,219,66,230,192,202,226,132,237,56,52,
+	246,6,237,57,52,62,1,55,251,201,205,203,
+	135,62,1,50,106,137,205,158,139,237,56,52,
+	246,6,237,57,52,183,251,201,209,225,62,1,
+	50,106,137,205,158,139,237,56,52,246,6,237,
+	57,52,62,2,55,251,201,209,225,243,219,72,
+	230,1,202,213,132,62,10,211,66,0,0,219,
+	66,230,192,194,213,132,229,62,1,50,106,137,
+	42,40,152,205,65,143,225,17,3,0,205,111,
+	136,62,6,211,66,58,44,152,211,66,237,56,
+	52,246,6,237,57,52,183,251,201,209,197,237,
+	56,52,230,248,237,57,52,219,72,230,1,32,
+	15,193,225,237,56,52,246,6,237,57,52,62,
+	1,55,251,201,14,23,58,37,152,254,0,40,
+	14,14,2,254,1,32,5,62,140,119,24,3,
+	62,132,119,43,43,197,205,203,135,193,62,1,
+	211,66,62,64,211,66,62,3,211,66,62,193,
+	211,66,62,100,203,39,71,219,66,230,1,32,
+	6,5,32,247,195,229,133,33,238,151,219,67,
+	71,58,44,152,184,194,229,133,119,62,100,71,
+	219,66,230,1,32,6,5,32,247,195,229,133,
+	219,67,35,119,13,32,234,193,225,62,1,50,
+	106,137,205,158,139,237,56,52,246,6,237,57,
+	52,175,183,251,201,33,234,151,35,35,62,255,
+	119,193,225,62,1,50,106,137,205,158,139,237,
+	56,52,246,6,237,57,52,175,251,201,243,61,
+	32,253,251,201,62,3,211,66,62,192,211,66,
+	58,49,152,254,140,32,19,197,229,213,17,181,
+	129,33,185,129,1,2,0,237,176,209,225,193,
+	24,27,229,213,33,187,129,58,49,152,230,15,
+	87,30,2,237,92,25,17,181,129,126,18,19,
+	35,126,18,209,225,58,34,152,246,8,211,68,
+	58,49,152,254,165,40,14,254,164,40,10,62,
+	10,211,66,62,224,211,66,24,25,58,74,152,
+	254,0,40,10,62,10,211,66,62,160,211,66,
+	24,8,62,10,211,66,62,128,211,66,62,11,
+	211,66,62,6,211,66,205,147,143,62,5,211,
+	66,62,224,211,66,62,5,211,66,62,96,211,
+	66,62,5,61,32,253,62,5,211,66,62,224,
+	211,66,62,14,61,32,253,62,5,211,66,62,
+	233,211,66,62,128,211,66,58,181,129,61,32,
+	253,62,1,211,66,62,192,211,66,1,254,19,
+	237,56,46,187,32,6,13,32,247,195,226,134,
+	62,192,211,66,0,0,219,66,203,119,40,250,
+	219,66,203,87,40,250,243,237,56,16,230,17,
+	237,57,16,237,56,20,251,62,5,211,66,62,
+	224,211,66,58,182,129,61,32,253,229,33,181,
+	129,58,183,129,203,63,119,35,58,184,129,119,
+	225,62,10,211,66,62,224,211,66,62,11,211,
+	66,62,118,211,66,62,47,211,68,62,5,211,
+	66,62,233,211,66,58,181,129,61,32,253,62,
+	5,211,66,62,224,211,66,58,182,129,61,32,
+	253,62,5,211,66,62,96,211,66,201,229,213,
+	58,50,152,230,15,87,30,2,237,92,33,187,
+	129,25,17,181,129,126,18,35,19,126,18,209,
+	225,58,71,152,246,8,211,68,58,50,152,254,
+	165,40,14,254,164,40,10,62,10,211,66,62,
+	224,211,66,24,8,62,10,211,66,62,128,211,
+	66,62,11,211,66,62,6,211,66,195,248,135,
+	62,3,211,66,62,192,211,66,197,229,213,17,
+	181,129,33,183,129,1,2,0,237,176,209,225,
+	193,62,47,211,68,62,10,211,66,62,224,211,
+	66,62,11,211,66,62,118,211,66,62,1,211,
+	66,62,0,211,66,205,147,143,195,16,136,62,
+	3,211,66,62,192,211,66,197,229,213,17,181,
+	129,33,183,129,1,2,0,237,176,209,225,193,
+	62,47,211,68,62,10,211,66,62,224,211,66,
+	62,11,211,66,62,118,211,66,205,147,143,62,
+	5,211,66,62,224,211,66,62,5,211,66,62,
+	96,211,66,62,5,61,32,253,62,5,211,66,
+	62,224,211,66,62,14,61,32,253,62,5,211,
+	66,62,233,211,66,62,128,211,66,58,181,129,
+	61,32,253,62,1,211,66,62,192,211,66,1,
+	254,19,237,56,46,187,32,6,13,32,247,195,
+	88,136,62,192,211,66,0,0,219,66,203,119,
+	40,250,219,66,203,87,40,250,62,5,211,66,
+	62,224,211,66,58,182,129,61,32,253,62,5,
+	211,66,62,96,211,66,201,197,14,67,6,0,
+	62,3,211,66,62,192,211,66,62,48,211,66,
+	0,0,219,66,230,1,40,4,219,67,24,240,
+	62,5,211,66,62,233,211,66,62,128,211,66,
+	58,181,129,61,32,253,237,163,29,62,192,211,
+	66,219,66,230,4,40,250,237,163,29,32,245,
+	219,66,230,4,40,250,62,255,71,219,66,230,
+	4,40,3,5,32,247,219,66,230,4,40,250,
+	62,5,211,66,62,224,211,66,58,182,129,61,
+	32,253,62,5,211,66,62,96,211,66,58,71,
+	152,254,1,202,18,137,62,16,211,66,62,56,
+	211,66,62,14,211,66,62,33,211,66,62,1,
+	211,66,62,248,211,66,237,56,48,246,153,230,
+	207,237,57,48,62,3,211,66,62,221,211,66,
+	193,201,58,71,152,211,68,62,10,211,66,62,
+	128,211,66,62,11,211,66,62,6,211,66,62,
+	6,211,66,58,44,152,211,66,62,16,211,66,
+	62,56,211,66,62,48,211,66,0,0,62,14,
+	211,66,62,33,211,66,62,1,211,66,62,248,
+	211,66,237,56,48,246,145,246,8,230,207,237,
+	57,48,62,3,211,66,62,221,211,66,193,201,
+	44,3,1,0,70,69,1,245,197,213,229,175,
+	50,72,152,237,56,16,230,46,237,57,16,237,
+	56,12,62,1,211,66,0,0,219,66,95,230,
+	160,32,3,195,20,139,123,230,96,194,72,139,
+	62,48,211,66,62,1,211,66,62,64,211,66,
+	237,91,40,152,205,207,143,25,43,55,237,82,
+	218,70,139,34,42,152,98,107,58,44,152,190,
+	194,210,138,35,35,62,130,190,194,200,137,62,
+	1,50,48,152,62,175,190,202,82,139,62,132,
+	190,32,44,50,50,152,62,47,50,71,152,229,
+	175,50,106,137,42,40,152,205,65,143,225,54,
+	133,43,70,58,44,152,119,43,112,17,3,0,
+	62,10,205,2,134,205,111,136,195,158,138,62,
+	140,190,32,19,50,50,152,58,233,149,230,4,
+	202,222,138,62,1,50,71,152,195,219,137,126,
+	254,160,250,185,138,254,166,242,185,138,50,50,
+	152,43,126,35,229,213,33,234,149,95,22,0,
+	25,126,254,132,40,18,254,140,40,14,58,50,
+	152,230,15,87,126,31,21,242,65,138,56,2,
+	175,119,58,50,152,230,15,87,58,233,149,230,
+	62,31,21,242,85,138,218,98,138,209,225,195,
+	20,139,58,50,152,33,100,137,230,15,95,22,
+	0,25,126,50,71,152,209,225,58,50,152,254,
+	164,250,135,138,58,73,152,254,0,40,4,54,
+	173,24,2,54,133,43,70,58,44,152,119,43,
+	112,17,3,0,205,70,135,175,50,106,137,205,
+	208,139,58,199,129,237,57,12,58,200,129,237,
+	57,13,237,56,16,246,17,237,57,16,225,209,
+	193,241,251,237,77,62,129,190,194,227,138,54,
+	130,43,70,58,44,152,119,43,112,17,3,0,
+	205,144,135,195,20,139,35,35,126,254,132,194,
+	227,138,175,50,106,137,205,158,139,24,42,58,
+	201,154,254,1,40,7,62,1,50,106,137,24,
+	237,58,106,137,254,1,202,222,138,62,128,166,
+	194,222,138,221,229,221,33,67,152,205,127,142,
+	205,109,144,221,225,225,209,193,241,251,237,77,
+	58,106,137,254,1,202,44,139,58,50,152,254,
+	164,250,44,139,58,73,152,238,1,50,73,152,
+	221,229,221,33,51,152,205,127,142,221,225,62,
+	1,50,106,137,205,158,139,195,13,139,24,208,
+	24,206,24,204,230,64,40,3,195,20,139,195,
+	20,139,43,126,33,8,152,119,35,58,44,152,
+	119,43,237,91,35,152,205,203,135,205,158,139,
+	195,13,139,175,50,78,152,62,3,211,66,62,
+	192,211,66,201,197,33,4,0,57,126,35,102,
+	111,62,1,50,106,137,219,72,205,141,139,193,
+	201,62,1,50,78,152,34,40,152,54,0,35,
+	35,54,0,195,163,139,58,78,152,183,200,229,
+	33,181,129,58,183,129,119,35,58,184,129,119,
+	225,62,47,211,68,62,14,211,66,62,193,211,
+	66,62,10,211,66,62,224,211,66,62,11,211,
+	66,62,118,211,66,195,3,140,58,78,152,183,
+	200,58,71,152,211,68,254,69,40,4,254,70,
+	32,17,58,73,152,254,0,40,10,62,10,211,
+	66,62,160,211,66,24,8,62,10,211,66,62,
+	128,211,66,62,11,211,66,62,6,211,66,62,
+	6,211,66,58,44,152,211,66,62,16,211,66,
+	62,56,211,66,62,48,211,66,0,0,219,66,
+	230,1,40,4,219,67,24,240,62,14,211,66,
+	62,33,211,66,42,40,152,205,65,143,62,1,
+	211,66,62,248,211,66,237,56,48,246,145,246,
+	8,230,207,237,57,48,62,3,211,66,62,221,
+	211,66,201,62,16,211,66,62,56,211,66,62,
+	48,211,66,0,0,219,66,230,1,40,4,219,
+	67,24,240,62,14,211,66,62,33,211,66,62,
+	1,211,66,62,248,211,66,237,56,48,246,153,
+	230,207,237,57,48,62,3,211,66,62,221,211,
+	66,201,229,213,33,234,149,95,22,0,25,126,
+	254,132,40,4,254,140,32,2,175,119,123,209,
+	225,201,6,8,14,0,31,48,1,12,16,250,
+	121,201,33,4,0,57,94,35,86,33,2,0,
+	57,126,35,102,111,221,229,34,89,152,237,83,
+	91,152,221,33,63,152,205,127,142,58,81,152,
+	50,82,152,58,80,152,135,50,80,152,205,162,
+	140,254,3,56,16,58,81,152,135,60,230,15,
+	50,81,152,175,50,80,152,24,23,58,79,152,
+	205,162,140,254,3,48,13,58,81,152,203,63,
+	50,81,152,62,255,50,79,152,58,81,152,50,
+	82,152,58,79,152,135,50,79,152,62,32,50,
+	83,152,50,84,152,237,56,16,230,17,237,57,
+	16,219,72,62,192,50,93,152,62,93,50,94,
+	152,58,93,152,61,50,93,152,32,9,58,94,
+	152,61,50,94,152,40,44,62,170,237,57,20,
+	175,237,57,21,237,56,16,246,2,237,57,16,
+	219,72,230,1,202,29,141,237,56,20,71,237,
+	56,21,120,254,10,48,237,237,56,16,230,17,
+	237,57,16,243,62,14,211,66,62,65,211,66,
+	251,58,39,152,23,23,60,50,39,152,71,58,
+	82,152,160,230,15,40,22,71,14,10,219,66,
+	230,16,202,186,141,219,72,230,1,202,186,141,
+	13,32,239,16,235,42,89,152,237,91,91,152,
+	205,47,131,48,7,61,202,186,141,195,227,141,
+	221,225,33,0,0,201,221,33,55,152,205,127,
+	142,58,84,152,61,50,84,152,40,19,58,82,
+	152,246,1,50,82,152,58,79,152,246,1,50,
+	79,152,195,29,141,221,225,33,1,0,201,221,
+	33,59,152,205,127,142,58,80,152,246,1,50,
+	80,152,58,82,152,135,246,1,50,82,152,58,
+	83,152,61,50,83,152,194,29,141,221,225,33,
+	2,0,201,221,229,33,0,0,57,17,4,0,
+	25,126,50,44,152,230,128,50,85,152,58,85,
+	152,183,40,6,221,33,88,2,24,4,221,33,
+	150,0,58,44,152,183,40,53,60,40,50,60,
+	40,47,61,61,33,86,152,119,35,119,35,54,
+	129,175,50,48,152,221,43,221,229,225,124,181,
+	40,42,33,86,152,17,3,0,205,189,140,17,
+	232,3,27,123,178,32,251,58,48,152,183,40,
+	224,58,44,152,71,62,7,128,230,127,71,58,
+	85,152,176,50,44,152,24,162,221,225,201,183,
+	221,52,0,192,221,52,1,192,221,52,2,192,
+	221,52,3,192,55,201,245,62,1,211,100,241,
+	201,245,62,1,211,96,241,201,33,2,0,57,
+	126,35,102,111,237,56,48,230,175,237,57,48,
+	62,48,237,57,49,125,237,57,32,124,237,57,
+	33,62,0,237,57,34,62,88,237,57,35,62,
+	0,237,57,36,237,57,37,33,128,2,125,237,
+	57,38,124,237,57,39,237,56,48,246,97,230,
+	207,237,57,48,62,0,237,57,0,62,0,211,
+	96,211,100,201,33,2,0,57,126,35,102,111,
+	237,56,48,230,175,237,57,48,62,12,237,57,
+	49,62,76,237,57,32,62,0,237,57,33,237,
+	57,34,125,237,57,35,124,237,57,36,62,0,
+	237,57,37,33,128,2,125,237,57,38,124,237,
+	57,39,237,56,48,246,97,230,207,237,57,48,
+	62,1,211,96,201,33,2,0,57,126,35,102,
+	111,229,237,56,48,230,87,237,57,48,125,237,
+	57,40,124,237,57,41,62,0,237,57,42,62,
+	67,237,57,43,62,0,237,57,44,58,106,137,
+	254,1,32,5,33,6,0,24,3,33,128,2,
+	125,237,57,46,124,237,57,47,237,56,50,230,
+	252,246,2,237,57,50,225,201,33,4,0,57,
+	94,35,86,33,2,0,57,126,35,102,111,237,
+	56,48,230,87,237,57,48,125,237,57,40,124,
+	237,57,41,62,0,237,57,42,62,67,237,57,
+	43,62,0,237,57,44,123,237,57,46,122,237,
+	57,47,237,56,50,230,244,246,0,237,57,50,
+	237,56,48,246,145,230,207,237,57,48,201,213,
+	237,56,46,95,237,56,47,87,237,56,46,111,
+	237,56,47,103,183,237,82,32,235,33,128,2,
+	183,237,82,209,201,213,237,56,38,95,237,56,
+	39,87,237,56,38,111,237,56,39,103,183,237,
+	82,32,235,33,128,2,183,237,82,209,201,245,
+	197,1,52,0,237,120,230,253,237,121,193,241,
+	201,245,197,1,52,0,237,120,246,2,237,121,
+	193,241,201,33,2,0,57,126,35,102,111,126,
+	35,110,103,201,33,0,0,34,102,152,34,96,
+	152,34,98,152,33,202,154,34,104,152,237,91,
+	104,152,42,226,149,183,237,82,17,0,255,25,
+	34,100,152,203,124,40,6,33,0,125,34,100,
+	152,42,104,152,35,35,35,229,205,120,139,193,
+	201,205,186,149,229,42,40,152,35,35,35,229,
+	205,39,144,193,124,230,3,103,221,117,254,221,
+	116,255,237,91,42,152,35,35,35,183,237,82,
+	32,12,17,5,0,42,42,152,205,171,149,242,
+	169,144,42,40,152,229,205,120,139,193,195,198,
+	149,237,91,42,152,42,98,152,25,34,98,152,
+	19,19,19,42,102,152,25,34,102,152,237,91,
+	100,152,33,158,253,25,237,91,102,152,205,171,
+	149,242,214,144,33,0,0,34,102,152,62,1,
+	50,95,152,205,225,144,195,198,149,58,95,152,
+	183,200,237,91,96,152,42,102,152,205,171,149,
+	242,5,145,237,91,102,152,33,98,2,25,237,
+	91,96,152,205,171,149,250,37,145,237,91,96,
+	152,42,102,152,183,237,82,32,7,42,98,152,
+	125,180,40,13,237,91,102,152,42,96,152,205,
+	171,149,242,58,145,237,91,104,152,42,102,152,
+	25,35,35,35,229,205,120,139,193,175,50,95,
+	152,201,195,107,139,205,206,149,250,255,243,205,
+	225,144,251,58,230,149,183,194,198,149,17,1,
+	0,42,98,152,205,171,149,250,198,149,62,1,
+	50,230,149,237,91,96,152,42,104,152,25,221,
+	117,252,221,116,253,237,91,104,152,42,96,152,
+	25,35,35,35,221,117,254,221,116,255,35,35,
+	35,229,205,39,144,124,230,3,103,35,35,35,
+	221,117,250,221,116,251,235,221,110,252,221,102,
+	253,115,35,114,35,54,4,62,1,211,100,211,
+	84,195,198,149,33,0,0,34,102,152,34,96,
+	152,34,98,152,33,202,154,34,104,152,237,91,
+	104,152,42,226,149,183,237,82,17,0,255,25,
+	34,100,152,33,109,152,54,0,33,107,152,229,
+	205,240,142,193,62,47,50,34,152,62,132,50,
+	49,152,205,241,145,205,61,145,58,39,152,60,
+	50,39,152,24,241,205,206,149,251,255,33,109,
+	152,126,183,202,198,149,110,221,117,251,33,109,
+	152,54,0,221,126,251,254,1,40,28,254,3,
+	40,101,254,4,202,190,147,254,5,202,147,147,
+	254,8,40,87,33,107,152,229,205,240,142,195,
+	198,149,58,201,154,183,32,21,33,111,152,126,
+	50,229,149,205,52,144,33,110,152,110,38,0,
+	229,205,11,142,193,237,91,96,152,42,104,152,
+	25,221,117,254,221,116,255,35,35,54,2,17,
+	2,0,43,43,115,35,114,58,44,152,35,35,
+	119,58,228,149,35,119,62,1,211,100,211,84,
+	62,1,50,201,154,24,169,205,153,142,58,231,
+	149,183,40,250,175,50,231,149,33,110,152,126,
+	254,255,40,91,58,233,149,230,63,183,40,83,
+	94,22,0,33,234,149,25,126,183,40,13,33,
+	110,152,94,33,234,150,25,126,254,3,32,36,
+	205,81,148,125,180,33,110,152,94,22,0,40,
+	17,33,234,149,25,54,0,33,107,152,229,205,
+	240,142,193,195,198,149,33,234,150,25,54,0,
+	33,110,152,94,22,0,33,234,149,25,126,50,
+	49,152,254,132,32,37,62,47,50,34,152,42,
+	107,152,229,33,110,152,229,205,174,140,193,193,
+	125,180,33,110,152,94,22,0,33,234,150,202,
+	117,147,25,52,195,120,147,58,49,152,254,140,
+	32,7,62,1,50,34,152,24,210,62,32,50,
+	106,152,24,19,58,49,152,95,58,106,152,163,
+	183,58,106,152,32,11,203,63,50,106,152,58,
+	106,152,183,32,231,254,2,40,51,254,4,40,
+	38,254,8,40,26,254,16,40,13,254,32,32,
+	158,62,165,50,49,152,62,69,24,190,62,164,
+	50,49,152,62,70,24,181,62,163,50,49,152,
+	175,24,173,62,162,50,49,152,62,1,24,164,
+	62,161,50,49,152,62,3,24,155,25,54,0,
+	221,126,251,254,8,40,7,58,230,149,183,202,
+	32,146,33,107,152,229,205,240,142,193,211,84,
+	195,198,149,237,91,96,152,42,104,152,25,221,
+	117,254,221,116,255,35,35,54,6,17,2,0,
+	43,43,115,35,114,58,228,149,35,35,119,58,
+	233,149,35,119,205,146,142,195,32,146,237,91,
+	96,152,42,104,152,25,229,205,160,142,193,58,
+	231,149,183,40,250,175,50,231,149,243,237,91,
+	96,152,42,104,152,25,221,117,254,221,116,255,
+	78,35,70,221,113,252,221,112,253,89,80,42,
+	98,152,183,237,82,34,98,152,203,124,40,19,
+	33,0,0,34,98,152,34,102,152,34,96,152,
+	62,1,50,95,152,24,40,221,94,252,221,86,
+	253,19,19,19,42,96,152,25,34,96,152,237,
+	91,100,152,33,158,253,25,237,91,96,152,205,
+	171,149,242,55,148,33,0,0,34,96,152,175,
+	50,230,149,251,195,32,146,245,62,1,50,231,
+	149,62,16,237,57,0,211,80,241,251,237,77,
+	201,205,186,149,229,229,33,0,0,34,37,152,
+	33,110,152,126,50,234,151,58,44,152,33,235,
+	151,119,221,54,253,0,221,54,254,0,195,230,
+	148,33,236,151,54,175,33,3,0,229,33,234,
+	151,229,205,174,140,193,193,33,236,151,126,254,
+	255,40,74,33,245,151,110,221,117,255,33,249,
+	151,126,221,166,255,221,119,255,33,253,151,126,
+	221,166,255,221,119,255,58,232,149,95,221,126,
+	255,163,221,119,255,183,40,15,230,191,33,110,
+	152,94,22,0,33,234,149,25,119,24,12,33,
+	110,152,94,22,0,33,234,149,25,54,132,33,
+	0,0,195,198,149,221,110,253,221,102,254,35,
+	221,117,253,221,116,254,17,32,0,221,110,253,
+	221,102,254,205,171,149,250,117,148,58,233,149,
+	203,87,40,84,33,1,0,34,37,152,221,54,
+	253,0,221,54,254,0,24,53,33,236,151,54,
+	175,33,3,0,229,33,234,151,229,205,174,140,
+	193,193,33,236,151,126,254,255,40,14,33,110,
+	152,94,22,0,33,234,149,25,54,140,24,159,
+	221,110,253,221,102,254,35,221,117,253,221,116,
+	254,17,32,0,221,110,253,221,102,254,205,171,
+	149,250,12,149,33,2,0,34,37,152,221,54,
+	253,0,221,54,254,0,24,54,33,236,151,54,
+	175,33,3,0,229,33,234,151,229,205,174,140,
+	193,193,33,236,151,126,254,255,40,15,33,110,
+	152,94,22,0,33,234,149,25,54,132,195,211,
+	148,221,110,253,221,102,254,35,221,117,253,221,
+	116,254,17,32,0,221,110,253,221,102,254,205,
+	171,149,250,96,149,33,1,0,195,198,149,124,
+	170,250,179,149,237,82,201,124,230,128,237,82,
+	60,201,225,253,229,221,229,221,33,0,0,221,
+	57,233,221,249,221,225,253,225,201,233,225,253,
+	229,221,229,221,33,0,0,221,57,94,35,86,
+	35,235,57,249,235,233,0,0,0,0,0,0,
+	62,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	175,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,133,1,0,0,0,63,
+	255,255,255,255,0,0,0,63,0,0,0,0,
+	0,0,0,0,0,0,0,24,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0
+	} ;
+
+#endif
diff --git a/drivers/staging/appletalk/cops_ltdrv.h b/drivers/staging/appletalk/cops_ltdrv.h
new file mode 100644
index 000000000000..c699b1ad31da
--- /dev/null
+++ b/drivers/staging/appletalk/cops_ltdrv.h
@@ -0,0 +1,241 @@
+/*
+ *	The firmware this driver downloads into the Localtalk card is a
+ *	separate program and is not GPL'd source code, even though the Linux
+ *	side driver and the routine that loads this data into the card are.
+ *	
+ *	It is taken from the COPS SDK and is under the following license
+ *
+ *	This material is licensed to you strictly for use in conjunction with
+ *	the use of COPS LocalTalk adapters.
+ *	There is no charge for this SDK. And no waranty express or implied
+ *	about its fitness for any purpose. However, we will cheerefully
+ *	refund every penny you paid for this SDK...
+ *	Regards,
+ *
+ *	Thomas F. Divine
+ *	Chief Scientist
+ */
+
+
+/*      cops_ltdrv.h: LocalTalk driver firmware dump for Linux.
+ *
+ *      Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ */
+ 
+
+#ifdef CONFIG_COPS_TANGENT
+
+static const unsigned char ltdrv_code[] = {
+	58,3,0,50,148,10,33,143,15,62,85,119,
+	190,32,9,62,170,119,190,32,3,35,24,241,
+	34,146,10,249,17,150,10,33,143,15,183,237,
+	82,77,68,11,107,98,19,54,0,237,176,62,
+	16,237,57,51,62,0,237,57,50,237,57,54,
+	62,12,237,57,49,62,195,33,39,2,50,56,
+	0,34,57,0,237,86,205,30,2,251,205,60,
+	10,24,169,67,111,112,121,114,105,103,104,116,
+	32,40,99,41,32,49,57,56,56,45,49,57,
+	57,50,44,32,80,114,105,110,116,105,110,103,
+	32,67,111,109,109,117,110,105,99,97,116,105,
+	111,110,115,32,65,115,115,111,99,105,97,116,
+	101,115,44,32,73,110,99,46,65,108,108,32,
+	114,105,103,104,116,115,32,114,101,115,101,114,
+	118,101,100,46,32,32,4,4,22,40,255,60,
+	4,96,10,224,6,0,7,126,2,64,11,246,
+	12,6,13,0,14,193,15,0,5,96,3,192,
+	1,0,9,8,62,3,211,82,62,192,211,82,
+	201,62,3,211,82,62,213,211,82,201,62,5,
+	211,82,62,224,211,82,201,62,5,211,82,62,
+	224,211,82,201,62,5,211,82,62,96,211,82,
+	201,6,28,33,180,1,14,82,237,163,194,4,
+	2,33,39,2,34,64,0,58,3,0,230,1,
+	192,62,11,237,121,62,118,237,121,201,33,182,
+	10,54,132,205,253,1,201,245,197,213,229,42,
+	150,10,14,83,17,98,2,67,20,237,162,58,
+	179,1,95,219,82,230,1,32,6,29,32,247,
+	195,17,3,62,1,211,82,219,82,95,230,160,
+	32,10,237,162,32,225,21,32,222,195,15,3,
+	237,162,123,230,96,194,21,3,62,48,211,82,
+	62,1,211,82,175,211,82,237,91,150,10,43,
+	55,237,82,218,19,3,34,152,10,98,107,58,
+	154,10,190,32,81,62,1,50,158,10,35,35,
+	62,132,190,32,44,54,133,43,70,58,154,10,
+	119,43,112,17,3,0,205,137,3,62,16,211,
+	82,62,56,211,82,205,217,1,42,150,10,14,
+	83,17,98,2,67,20,58,178,1,95,195,59,
+	2,62,129,190,194,227,2,54,130,43,70,58,
+	154,10,119,43,112,17,3,0,205,137,3,195,
+	254,2,35,35,126,254,132,194,227,2,205,61,
+	3,24,20,62,128,166,194,222,2,221,229,221,
+	33,175,10,205,93,6,205,144,7,221,225,225,
+	209,193,241,251,237,77,221,229,221,33,159,10,
+	205,93,6,221,225,205,61,3,195,247,2,24,
+	237,24,235,24,233,230,64,40,2,24,227,24,
+	225,175,50,179,10,205,208,1,201,197,33,4,
+	0,57,126,35,102,111,205,51,3,193,201,62,
+	1,50,179,10,34,150,10,54,0,58,179,10,
+	183,200,62,14,211,82,62,193,211,82,62,10,
+	211,82,62,224,211,82,62,6,211,82,58,154,
+	10,211,82,62,16,211,82,62,56,211,82,62,
+	48,211,82,219,82,230,1,40,4,219,83,24,
+	242,62,14,211,82,62,33,211,82,62,1,211,
+	82,62,9,211,82,62,32,211,82,205,217,1,
+	201,14,83,205,208,1,24,23,14,83,205,208,
+	1,205,226,1,58,174,1,61,32,253,205,244,
+	1,58,174,1,61,32,253,205,226,1,58,175,
+	1,61,32,253,62,5,211,82,62,233,211,82,
+	62,128,211,82,58,176,1,61,32,253,237,163,
+	27,62,192,211,82,219,82,230,4,40,250,237,
+	163,27,122,179,32,243,219,82,230,4,40,250,
+	58,178,1,71,219,82,230,4,40,3,5,32,
+	247,219,82,230,4,40,250,205,235,1,58,177,
+	1,61,32,253,205,244,1,201,229,213,35,35,
+	126,230,128,194,145,4,43,58,154,10,119,43,
+	70,33,181,10,119,43,112,17,3,0,243,62,
+	10,211,82,219,82,230,128,202,41,4,209,225,
+	62,1,55,251,201,205,144,3,58,180,10,254,
+	255,202,127,4,205,217,1,58,178,1,71,219,
+	82,230,1,32,6,5,32,247,195,173,4,219,
+	83,71,58,154,10,184,194,173,4,58,178,1,
+	71,219,82,230,1,32,6,5,32,247,195,173,
+	4,219,83,58,178,1,71,219,82,230,1,32,
+	6,5,32,247,195,173,4,219,83,254,133,194,
+	173,4,58,179,1,24,4,58,179,1,135,61,
+	32,253,209,225,205,137,3,205,61,3,183,251,
+	201,209,225,243,62,10,211,82,219,82,230,128,
+	202,164,4,62,1,55,251,201,205,144,3,205,
+	61,3,183,251,201,209,225,62,2,55,251,201,
+	243,62,14,211,82,62,33,211,82,251,201,33,
+	4,0,57,94,35,86,33,2,0,57,126,35,
+	102,111,221,229,34,193,10,237,83,195,10,221,
+	33,171,10,205,93,6,58,185,10,50,186,10,
+	58,184,10,135,50,184,10,205,112,6,254,3,
+	56,16,58,185,10,135,60,230,15,50,185,10,
+	175,50,184,10,24,23,58,183,10,205,112,6,
+	254,3,48,13,58,185,10,203,63,50,185,10,
+	62,255,50,183,10,58,185,10,50,186,10,58,
+	183,10,135,50,183,10,62,32,50,187,10,50,
+	188,10,6,255,219,82,230,16,32,3,5,32,
+	247,205,180,4,6,40,219,82,230,16,40,3,
+	5,32,247,62,10,211,82,219,82,230,128,194,
+	46,5,219,82,230,16,40,214,237,95,71,58,
+	186,10,160,230,15,40,32,71,14,10,62,10,
+	211,82,219,82,230,128,202,119,5,205,180,4,
+	195,156,5,219,82,230,16,202,156,5,13,32,
+	229,16,225,42,193,10,237,91,195,10,205,252,
+	3,48,7,61,202,156,5,195,197,5,221,225,
+	33,0,0,201,221,33,163,10,205,93,6,58,
+	188,10,61,50,188,10,40,19,58,186,10,246,
+	1,50,186,10,58,183,10,246,1,50,183,10,
+	195,46,5,221,225,33,1,0,201,221,33,167,
+	10,205,93,6,58,184,10,246,1,50,184,10,
+	58,186,10,135,246,1,50,186,10,58,187,10,
+	61,50,187,10,194,46,5,221,225,33,2,0,
+	201,221,229,33,0,0,57,17,4,0,25,126,
+	50,154,10,230,128,50,189,10,58,189,10,183,
+	40,6,221,33,88,2,24,4,221,33,150,0,
+	58,154,10,183,40,49,60,40,46,61,33,190,
+	10,119,35,119,35,54,129,175,50,158,10,221,
+	43,221,229,225,124,181,40,42,33,190,10,17,
+	3,0,205,206,4,17,232,3,27,123,178,32,
+	251,58,158,10,183,40,224,58,154,10,71,62,
+	7,128,230,127,71,58,189,10,176,50,154,10,
+	24,166,221,225,201,183,221,52,0,192,221,52,
+	1,192,221,52,2,192,221,52,3,192,55,201,
+	6,8,14,0,31,48,1,12,16,250,121,201,
+	33,2,0,57,94,35,86,35,78,35,70,35,
+	126,35,102,105,79,120,68,103,237,176,201,33,
+	2,0,57,126,35,102,111,62,17,237,57,48,
+	125,237,57,40,124,237,57,41,62,0,237,57,
+	42,62,64,237,57,43,62,0,237,57,44,33,
+	128,2,125,237,57,46,124,237,57,47,62,145,
+	237,57,48,211,68,58,149,10,211,66,201,33,
+	2,0,57,126,35,102,111,62,33,237,57,48,
+	62,64,237,57,32,62,0,237,57,33,237,57,
+	34,125,237,57,35,124,237,57,36,62,0,237,
+	57,37,33,128,2,125,237,57,38,124,237,57,
+	39,62,97,237,57,48,211,67,58,149,10,211,
+	66,201,237,56,46,95,237,56,47,87,237,56,
+	46,111,237,56,47,103,183,237,82,32,235,33,
+	128,2,183,237,82,201,237,56,38,95,237,56,
+	39,87,237,56,38,111,237,56,39,103,183,237,
+	82,32,235,33,128,2,183,237,82,201,205,106,
+	10,221,110,6,221,102,7,126,35,110,103,195,
+	118,10,205,106,10,33,0,0,34,205,10,34,
+	198,10,34,200,10,33,143,15,34,207,10,237,
+	91,207,10,42,146,10,183,237,82,17,0,255,
+	25,34,203,10,203,124,40,6,33,0,125,34,
+	203,10,42,207,10,229,205,37,3,195,118,10,
+	205,106,10,229,42,150,10,35,35,35,229,205,
+	70,7,193,124,230,3,103,221,117,254,221,116,
+	255,237,91,152,10,35,35,35,183,237,82,32,
+	12,17,5,0,42,152,10,205,91,10,242,203,
+	7,42,150,10,229,205,37,3,195,118,10,237,
+	91,152,10,42,200,10,25,34,200,10,42,205,
+	10,25,34,205,10,237,91,203,10,33,158,253,
+	25,237,91,205,10,205,91,10,242,245,7,33,
+	0,0,34,205,10,62,1,50,197,10,205,5,
+	8,33,0,0,57,249,195,118,10,205,106,10,
+	58,197,10,183,202,118,10,237,91,198,10,42,
+	205,10,205,91,10,242,46,8,237,91,205,10,
+	33,98,2,25,237,91,198,10,205,91,10,250,
+	78,8,237,91,198,10,42,205,10,183,237,82,
+	32,7,42,200,10,125,180,40,13,237,91,205,
+	10,42,198,10,205,91,10,242,97,8,237,91,
+	207,10,42,205,10,25,229,205,37,3,175,50,
+	197,10,195,118,10,205,29,3,33,0,0,57,
+	249,195,118,10,205,106,10,58,202,10,183,40,
+	22,205,14,7,237,91,209,10,19,19,19,205,
+	91,10,242,139,8,33,1,0,195,118,10,33,
+	0,0,195,118,10,205,126,10,252,255,205,108,
+	8,125,180,194,118,10,237,91,200,10,33,0,
+	0,205,91,10,242,118,10,237,91,207,10,42,
+	198,10,25,221,117,254,221,116,255,35,35,35,
+	229,205,70,7,193,124,230,3,103,35,35,35,
+	221,117,252,221,116,253,229,221,110,254,221,102,
+	255,229,33,212,10,229,205,124,6,193,193,221,
+	110,252,221,102,253,34,209,10,33,211,10,54,
+	4,33,209,10,227,205,147,6,193,62,1,50,
+	202,10,243,221,94,252,221,86,253,42,200,10,
+	183,237,82,34,200,10,203,124,40,17,33,0,
+	0,34,200,10,34,205,10,34,198,10,50,197,
+	10,24,37,221,94,252,221,86,253,42,198,10,
+	25,34,198,10,237,91,203,10,33,158,253,25,
+	237,91,198,10,205,91,10,242,68,9,33,0,
+	0,34,198,10,205,5,8,33,0,0,57,249,
+	251,195,118,10,205,106,10,33,49,13,126,183,
+	40,16,205,42,7,237,91,47,13,19,19,19,
+	205,91,10,242,117,9,58,142,15,198,1,50,
+	142,15,195,118,10,33,49,13,126,254,1,40,
+	25,254,3,202,7,10,254,5,202,21,10,33,
+	49,13,54,0,33,47,13,229,205,207,6,195,
+	118,10,58,141,15,183,32,72,33,51,13,126,
+	50,149,10,205,86,7,33,50,13,126,230,127,
+	183,32,40,58,142,15,230,127,50,142,15,183,
+	32,5,198,1,50,142,15,33,50,13,126,111,
+	23,159,103,203,125,58,142,15,40,5,198,128,
+	50,142,15,33,50,13,119,33,50,13,126,111,
+	23,159,103,229,205,237,5,193,33,211,10,54,
+	2,33,2,0,34,209,10,58,154,10,33,212,
+	10,119,58,148,10,33,213,10,119,33,209,10,
+	229,205,147,6,193,24,128,42,47,13,229,33,
+	50,13,229,205,191,4,193,24,239,33,211,10,
+	54,6,33,3,0,34,209,10,58,154,10,33,
+	212,10,119,58,148,10,33,213,10,119,33,214,
+	10,54,5,33,209,10,229,205,147,6,24,200,
+	205,106,10,33,49,13,54,0,33,47,13,229,
+	205,207,6,33,209,10,227,205,147,6,193,205,
+	80,9,205,145,8,24,248,124,170,250,99,10,
+	237,82,201,124,230,128,237,82,60,201,225,253,
+	229,221,229,221,33,0,0,221,57,233,221,249,
+	221,225,253,225,201,233,225,253,229,221,229,221,
+	33,0,0,221,57,94,35,86,35,235,57,249,
+	235,233,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0
+	} ;
+
+#endif
diff --git a/drivers/staging/appletalk/ddp.c b/drivers/staging/appletalk/ddp.c
new file mode 100644
index 000000000000..940dd1908339
--- /dev/null
+++ b/drivers/staging/appletalk/ddp.c
@@ -0,0 +1,1981 @@
+/*
+ *	DDP:	An implementation of the AppleTalk DDP protocol for
+ *		Ethernet 'ELAP'.
+ *
+ *		Alan Cox  <alan@lxorguk.ukuu.org.uk>
+ *
+ *		With more than a little assistance from
+ *
+ *		Wesley Craig <netatalk@umich.edu>
+ *
+ *	Fixes:
+ *		Neil Horman		:	Added missing device ioctls
+ *		Michael Callahan	:	Made routing work
+ *		Wesley Craig		:	Fix probing to listen to a
+ *						passed node id.
+ *		Alan Cox		:	Added send/recvmsg support
+ *		Alan Cox		:	Moved at. to protinfo in
+ *						socket.
+ *		Alan Cox		:	Added firewall hooks.
+ *		Alan Cox		:	Supports new ARPHRD_LOOPBACK
+ *		Christer Weinigel	: 	Routing and /proc fixes.
+ *		Bradford Johnson	:	LocalTalk.
+ *		Tom Dyas		:	Module support.
+ *		Alan Cox		:	Hooks for PPP (based on the
+ *						LocalTalk hook).
+ *		Alan Cox		:	Posix bits
+ *		Alan Cox/Mike Freeman	:	Possible fix to NBP problems
+ *		Bradford Johnson	:	IP-over-DDP (experimental)
+ *		Jay Schulist		:	Moved IP-over-DDP to its own
+ *						driver file. (ipddp.c & ipddp.h)
+ *		Jay Schulist		:	Made work as module with
+ *						AppleTalk drivers, cleaned it.
+ *		Rob Newberry		:	Added proxy AARP and AARP
+ *						procfs, moved probing to AARP
+ *						module.
+ *              Adrian Sun/
+ *              Michael Zuelsdorff      :       fix for net.0 packets. don't
+ *                                              allow illegal ether/tokentalk
+ *                                              port assignment. we lose a
+ *                                              valid localtalk port as a
+ *                                              result.
+ *		Arnaldo C. de Melo	:	Cleanup, in preparation for
+ *						shared skb support 8)
+ *		Arnaldo C. de Melo	:	Move proc stuff to atalk_proc.c,
+ *						use seq_file
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/smp_lock.h>
+#include <linux/termios.h>	/* For TIOCOUTQ/INQ */
+#include <linux/compat.h>
+#include <linux/slab.h>
+#include <net/datalink.h>
+#include <net/psnap.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+#include <net/route.h>
+#include "atalk.h"
+#include "../../net/core/kmap_skb.h"
+
+struct datalink_proto *ddp_dl, *aarp_dl;
+static const struct proto_ops atalk_dgram_ops;
+
+/**************************************************************************\
+*                                                                          *
+* Handlers for the socket list.                                            *
+*                                                                          *
+\**************************************************************************/
+
+HLIST_HEAD(atalk_sockets);
+DEFINE_RWLOCK(atalk_sockets_lock);
+
+static inline void __atalk_insert_socket(struct sock *sk)
+{
+	sk_add_node(sk, &atalk_sockets);
+}
+
+static inline void atalk_remove_socket(struct sock *sk)
+{
+	write_lock_bh(&atalk_sockets_lock);
+	sk_del_node_init(sk);
+	write_unlock_bh(&atalk_sockets_lock);
+}
+
+static struct sock *atalk_search_socket(struct sockaddr_at *to,
+					struct atalk_iface *atif)
+{
+	struct sock *s;
+	struct hlist_node *node;
+
+	read_lock_bh(&atalk_sockets_lock);
+	sk_for_each(s, node, &atalk_sockets) {
+		struct atalk_sock *at = at_sk(s);
+
+		if (to->sat_port != at->src_port)
+			continue;
+
+		if (to->sat_addr.s_net == ATADDR_ANYNET &&
+		    to->sat_addr.s_node == ATADDR_BCAST)
+			goto found;
+
+		if (to->sat_addr.s_net == at->src_net &&
+		    (to->sat_addr.s_node == at->src_node ||
+		     to->sat_addr.s_node == ATADDR_BCAST ||
+		     to->sat_addr.s_node == ATADDR_ANYNODE))
+			goto found;
+
+		/* XXXX.0 -- we got a request for this router. make sure
+		 * that the node is appropriately set. */
+		if (to->sat_addr.s_node == ATADDR_ANYNODE &&
+		    to->sat_addr.s_net != ATADDR_ANYNET &&
+		    atif->address.s_node == at->src_node) {
+			to->sat_addr.s_node = atif->address.s_node;
+			goto found;
+		}
+	}
+	s = NULL;
+found:
+	read_unlock_bh(&atalk_sockets_lock);
+	return s;
+}
+
+/**
+ * atalk_find_or_insert_socket - Try to find a socket matching ADDR
+ * @sk - socket to insert in the list if it is not there already
+ * @sat - address to search for
+ *
+ * Try to find a socket matching ADDR in the socket list, if found then return
+ * it. If not, insert SK into the socket list.
+ *
+ * This entire operation must execute atomically.
+ */
+static struct sock *atalk_find_or_insert_socket(struct sock *sk,
+						struct sockaddr_at *sat)
+{
+	struct sock *s;
+	struct hlist_node *node;
+	struct atalk_sock *at;
+
+	write_lock_bh(&atalk_sockets_lock);
+	sk_for_each(s, node, &atalk_sockets) {
+		at = at_sk(s);
+
+		if (at->src_net == sat->sat_addr.s_net &&
+		    at->src_node == sat->sat_addr.s_node &&
+		    at->src_port == sat->sat_port)
+			goto found;
+	}
+	s = NULL;
+	__atalk_insert_socket(sk); /* Wheee, it's free, assign and insert. */
+found:
+	write_unlock_bh(&atalk_sockets_lock);
+	return s;
+}
+
+static void atalk_destroy_timer(unsigned long data)
+{
+	struct sock *sk = (struct sock *)data;
+
+	if (sk_has_allocations(sk)) {
+		sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME;
+		add_timer(&sk->sk_timer);
+	} else
+		sock_put(sk);
+}
+
+static inline void atalk_destroy_socket(struct sock *sk)
+{
+	atalk_remove_socket(sk);
+	skb_queue_purge(&sk->sk_receive_queue);
+
+	if (sk_has_allocations(sk)) {
+		setup_timer(&sk->sk_timer, atalk_destroy_timer,
+				(unsigned long)sk);
+		sk->sk_timer.expires	= jiffies + SOCK_DESTROY_TIME;
+		add_timer(&sk->sk_timer);
+	} else
+		sock_put(sk);
+}
+
+/**************************************************************************\
+*                                                                          *
+* Routing tables for the AppleTalk socket layer.                           *
+*                                                                          *
+\**************************************************************************/
+
+/* Anti-deadlock ordering is atalk_routes_lock --> iface_lock -DaveM */
+struct atalk_route *atalk_routes;
+DEFINE_RWLOCK(atalk_routes_lock);
+
+struct atalk_iface *atalk_interfaces;
+DEFINE_RWLOCK(atalk_interfaces_lock);
+
+/* For probing devices or in a routerless network */
+struct atalk_route atrtr_default;
+
+/* AppleTalk interface control */
+/*
+ * Drop a device. Doesn't drop any of its routes - that is the caller's
+ * problem. Called when we down the interface or delete the address.
+ */
+static void atif_drop_device(struct net_device *dev)
+{
+	struct atalk_iface **iface = &atalk_interfaces;
+	struct atalk_iface *tmp;
+
+	write_lock_bh(&atalk_interfaces_lock);
+	while ((tmp = *iface) != NULL) {
+		if (tmp->dev == dev) {
+			*iface = tmp->next;
+			dev_put(dev);
+			kfree(tmp);
+			dev->atalk_ptr = NULL;
+		} else
+			iface = &tmp->next;
+	}
+	write_unlock_bh(&atalk_interfaces_lock);
+}
+
+static struct atalk_iface *atif_add_device(struct net_device *dev,
+					   struct atalk_addr *sa)
+{
+	struct atalk_iface *iface = kzalloc(sizeof(*iface), GFP_KERNEL);
+
+	if (!iface)
+		goto out;
+
+	dev_hold(dev);
+	iface->dev = dev;
+	dev->atalk_ptr = iface;
+	iface->address = *sa;
+	iface->status = 0;
+
+	write_lock_bh(&atalk_interfaces_lock);
+	iface->next = atalk_interfaces;
+	atalk_interfaces = iface;
+	write_unlock_bh(&atalk_interfaces_lock);
+out:
+	return iface;
+}
+
+/* Perform phase 2 AARP probing on our tentative address */
+static int atif_probe_device(struct atalk_iface *atif)
+{
+	int netrange = ntohs(atif->nets.nr_lastnet) -
+			ntohs(atif->nets.nr_firstnet) + 1;
+	int probe_net = ntohs(atif->address.s_net);
+	int probe_node = atif->address.s_node;
+	int netct, nodect;
+
+	/* Offset the network we start probing with */
+	if (probe_net == ATADDR_ANYNET) {
+		probe_net = ntohs(atif->nets.nr_firstnet);
+		if (netrange)
+			probe_net += jiffies % netrange;
+	}
+	if (probe_node == ATADDR_ANYNODE)
+		probe_node = jiffies & 0xFF;
+
+	/* Scan the networks */
+	atif->status |= ATIF_PROBE;
+	for (netct = 0; netct <= netrange; netct++) {
+		/* Sweep the available nodes from a given start */
+		atif->address.s_net = htons(probe_net);
+		for (nodect = 0; nodect < 256; nodect++) {
+			atif->address.s_node = (nodect + probe_node) & 0xFF;
+			if (atif->address.s_node > 0 &&
+			    atif->address.s_node < 254) {
+				/* Probe a proposed address */
+				aarp_probe_network(atif);
+
+				if (!(atif->status & ATIF_PROBE_FAIL)) {
+					atif->status &= ~ATIF_PROBE;
+					return 0;
+				}
+			}
+			atif->status &= ~ATIF_PROBE_FAIL;
+		}
+		probe_net++;
+		if (probe_net > ntohs(atif->nets.nr_lastnet))
+			probe_net = ntohs(atif->nets.nr_firstnet);
+	}
+	atif->status &= ~ATIF_PROBE;
+
+	return -EADDRINUSE;	/* Network is full... */
+}
+
+
+/* Perform AARP probing for a proxy address */
+static int atif_proxy_probe_device(struct atalk_iface *atif,
+				   struct atalk_addr* proxy_addr)
+{
+	int netrange = ntohs(atif->nets.nr_lastnet) -
+			ntohs(atif->nets.nr_firstnet) + 1;
+	/* we probe the interface's network */
+	int probe_net = ntohs(atif->address.s_net);
+	int probe_node = ATADDR_ANYNODE;	    /* we'll take anything */
+	int netct, nodect;
+
+	/* Offset the network we start probing with */
+	if (probe_net == ATADDR_ANYNET) {
+		probe_net = ntohs(atif->nets.nr_firstnet);
+		if (netrange)
+			probe_net += jiffies % netrange;
+	}
+
+	if (probe_node == ATADDR_ANYNODE)
+		probe_node = jiffies & 0xFF;
+
+	/* Scan the networks */
+	for (netct = 0; netct <= netrange; netct++) {
+		/* Sweep the available nodes from a given start */
+		proxy_addr->s_net = htons(probe_net);
+		for (nodect = 0; nodect < 256; nodect++) {
+			proxy_addr->s_node = (nodect + probe_node) & 0xFF;
+			if (proxy_addr->s_node > 0 &&
+			    proxy_addr->s_node < 254) {
+				/* Tell AARP to probe a proposed address */
+				int ret = aarp_proxy_probe_network(atif,
+								    proxy_addr);
+
+				if (ret != -EADDRINUSE)
+					return ret;
+			}
+		}
+		probe_net++;
+		if (probe_net > ntohs(atif->nets.nr_lastnet))
+			probe_net = ntohs(atif->nets.nr_firstnet);
+	}
+
+	return -EADDRINUSE;	/* Network is full... */
+}
+
+
+struct atalk_addr *atalk_find_dev_addr(struct net_device *dev)
+{
+	struct atalk_iface *iface = dev->atalk_ptr;
+	return iface ? &iface->address : NULL;
+}
+
+static struct atalk_addr *atalk_find_primary(void)
+{
+	struct atalk_iface *fiface = NULL;
+	struct atalk_addr *retval;
+	struct atalk_iface *iface;
+
+	/*
+	 * Return a point-to-point interface only if
+	 * there is no non-ptp interface available.
+	 */
+	read_lock_bh(&atalk_interfaces_lock);
+	for (iface = atalk_interfaces; iface; iface = iface->next) {
+		if (!fiface && !(iface->dev->flags & IFF_LOOPBACK))
+			fiface = iface;
+		if (!(iface->dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))) {
+			retval = &iface->address;
+			goto out;
+		}
+	}
+
+	if (fiface)
+		retval = &fiface->address;
+	else if (atalk_interfaces)
+		retval = &atalk_interfaces->address;
+	else
+		retval = NULL;
+out:
+	read_unlock_bh(&atalk_interfaces_lock);
+	return retval;
+}
+
+/*
+ * Find a match for 'any network' - ie any of our interfaces with that
+ * node number will do just nicely.
+ */
+static struct atalk_iface *atalk_find_anynet(int node, struct net_device *dev)
+{
+	struct atalk_iface *iface = dev->atalk_ptr;
+
+	if (!iface || iface->status & ATIF_PROBE)
+		goto out_err;
+
+	if (node != ATADDR_BCAST &&
+	    iface->address.s_node != node &&
+	    node != ATADDR_ANYNODE)
+		goto out_err;
+out:
+	return iface;
+out_err:
+	iface = NULL;
+	goto out;
+}
+
+/* Find a match for a specific network:node pair */
+static struct atalk_iface *atalk_find_interface(__be16 net, int node)
+{
+	struct atalk_iface *iface;
+
+	read_lock_bh(&atalk_interfaces_lock);
+	for (iface = atalk_interfaces; iface; iface = iface->next) {
+		if ((node == ATADDR_BCAST ||
+		     node == ATADDR_ANYNODE ||
+		     iface->address.s_node == node) &&
+		    iface->address.s_net == net &&
+		    !(iface->status & ATIF_PROBE))
+			break;
+
+		/* XXXX.0 -- net.0 returns the iface associated with net */
+		if (node == ATADDR_ANYNODE && net != ATADDR_ANYNET &&
+		    ntohs(iface->nets.nr_firstnet) <= ntohs(net) &&
+		    ntohs(net) <= ntohs(iface->nets.nr_lastnet))
+			break;
+	}
+	read_unlock_bh(&atalk_interfaces_lock);
+	return iface;
+}
+
+
+/*
+ * Find a route for an AppleTalk packet. This ought to get cached in
+ * the socket (later on...). We know about host routes and the fact
+ * that a route must be direct to broadcast.
+ */
+static struct atalk_route *atrtr_find(struct atalk_addr *target)
+{
+	/*
+	 * we must search through all routes unless we find a
+	 * host route, because some host routes might overlap
+	 * network routes
+	 */
+	struct atalk_route *net_route = NULL;
+	struct atalk_route *r;
+
+	read_lock_bh(&atalk_routes_lock);
+	for (r = atalk_routes; r; r = r->next) {
+		if (!(r->flags & RTF_UP))
+			continue;
+
+		if (r->target.s_net == target->s_net) {
+			if (r->flags & RTF_HOST) {
+				/*
+				 * if this host route is for the target,
+				 * the we're done
+				 */
+				if (r->target.s_node == target->s_node)
+					goto out;
+			} else
+				/*
+				 * this route will work if there isn't a
+				 * direct host route, so cache it
+				 */
+				net_route = r;
+		}
+	}
+
+	/*
+	 * if we found a network route but not a direct host
+	 * route, then return it
+	 */
+	if (net_route)
+		r = net_route;
+	else if (atrtr_default.dev)
+		r = &atrtr_default;
+	else /* No route can be found */
+		r = NULL;
+out:
+	read_unlock_bh(&atalk_routes_lock);
+	return r;
+}
+
+
+/*
+ * Given an AppleTalk network, find the device to use. This can be
+ * a simple lookup.
+ */
+struct net_device *atrtr_get_dev(struct atalk_addr *sa)
+{
+	struct atalk_route *atr = atrtr_find(sa);
+	return atr ? atr->dev : NULL;
+}
+
+/* Set up a default router */
+static void atrtr_set_default(struct net_device *dev)
+{
+	atrtr_default.dev	     = dev;
+	atrtr_default.flags	     = RTF_UP;
+	atrtr_default.gateway.s_net  = htons(0);
+	atrtr_default.gateway.s_node = 0;
+}
+
+/*
+ * Add a router. Basically make sure it looks valid and stuff the
+ * entry in the list. While it uses netranges we always set them to one
+ * entry to work like netatalk.
+ */
+static int atrtr_create(struct rtentry *r, struct net_device *devhint)
+{
+	struct sockaddr_at *ta = (struct sockaddr_at *)&r->rt_dst;
+	struct sockaddr_at *ga = (struct sockaddr_at *)&r->rt_gateway;
+	struct atalk_route *rt;
+	struct atalk_iface *iface, *riface;
+	int retval = -EINVAL;
+
+	/*
+	 * Fixme: Raise/Lower a routing change semaphore for these
+	 * operations.
+	 */
+
+	/* Validate the request */
+	if (ta->sat_family != AF_APPLETALK ||
+	    (!devhint && ga->sat_family != AF_APPLETALK))
+		goto out;
+
+	/* Now walk the routing table and make our decisions */
+	write_lock_bh(&atalk_routes_lock);
+	for (rt = atalk_routes; rt; rt = rt->next) {
+		if (r->rt_flags != rt->flags)
+			continue;
+
+		if (ta->sat_addr.s_net == rt->target.s_net) {
+			if (!(rt->flags & RTF_HOST))
+				break;
+			if (ta->sat_addr.s_node == rt->target.s_node)
+				break;
+		}
+	}
+
+	if (!devhint) {
+		riface = NULL;
+
+		read_lock_bh(&atalk_interfaces_lock);
+		for (iface = atalk_interfaces; iface; iface = iface->next) {
+			if (!riface &&
+			    ntohs(ga->sat_addr.s_net) >=
+					ntohs(iface->nets.nr_firstnet) &&
+			    ntohs(ga->sat_addr.s_net) <=
+					ntohs(iface->nets.nr_lastnet))
+				riface = iface;
+
+			if (ga->sat_addr.s_net == iface->address.s_net &&
+			    ga->sat_addr.s_node == iface->address.s_node)
+				riface = iface;
+		}
+		read_unlock_bh(&atalk_interfaces_lock);
+
+		retval = -ENETUNREACH;
+		if (!riface)
+			goto out_unlock;
+
+		devhint = riface->dev;
+	}
+
+	if (!rt) {
+		rt = kzalloc(sizeof(*rt), GFP_ATOMIC);
+
+		retval = -ENOBUFS;
+		if (!rt)
+			goto out_unlock;
+
+		rt->next = atalk_routes;
+		atalk_routes = rt;
+	}
+
+	/* Fill in the routing entry */
+	rt->target  = ta->sat_addr;
+	dev_hold(devhint);
+	rt->dev     = devhint;
+	rt->flags   = r->rt_flags;
+	rt->gateway = ga->sat_addr;
+
+	retval = 0;
+out_unlock:
+	write_unlock_bh(&atalk_routes_lock);
+out:
+	return retval;
+}
+
+/* Delete a route. Find it and discard it */
+static int atrtr_delete(struct atalk_addr * addr)
+{
+	struct atalk_route **r = &atalk_routes;
+	int retval = 0;
+	struct atalk_route *tmp;
+
+	write_lock_bh(&atalk_routes_lock);
+	while ((tmp = *r) != NULL) {
+		if (tmp->target.s_net == addr->s_net &&
+		    (!(tmp->flags&RTF_GATEWAY) ||
+		     tmp->target.s_node == addr->s_node)) {
+			*r = tmp->next;
+			dev_put(tmp->dev);
+			kfree(tmp);
+			goto out;
+		}
+		r = &tmp->next;
+	}
+	retval = -ENOENT;
+out:
+	write_unlock_bh(&atalk_routes_lock);
+	return retval;
+}
+
+/*
+ * Called when a device is downed. Just throw away any routes
+ * via it.
+ */
+static void atrtr_device_down(struct net_device *dev)
+{
+	struct atalk_route **r = &atalk_routes;
+	struct atalk_route *tmp;
+
+	write_lock_bh(&atalk_routes_lock);
+	while ((tmp = *r) != NULL) {
+		if (tmp->dev == dev) {
+			*r = tmp->next;
+			dev_put(dev);
+			kfree(tmp);
+		} else
+			r = &tmp->next;
+	}
+	write_unlock_bh(&atalk_routes_lock);
+
+	if (atrtr_default.dev == dev)
+		atrtr_set_default(NULL);
+}
+
+/* Actually down the interface */
+static inline void atalk_dev_down(struct net_device *dev)
+{
+	atrtr_device_down(dev);	/* Remove all routes for the device */
+	aarp_device_down(dev);	/* Remove AARP entries for the device */
+	atif_drop_device(dev);	/* Remove the device */
+}
+
+/*
+ * A device event has occurred. Watch for devices going down and
+ * delete our use of them (iface and route).
+ */
+static int ddp_device_event(struct notifier_block *this, unsigned long event,
+			    void *ptr)
+{
+	struct net_device *dev = ptr;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_DOWN)
+		/* Discard any use of this */
+		atalk_dev_down(dev);
+
+	return NOTIFY_DONE;
+}
+
+/* ioctl calls. Shouldn't even need touching */
+/* Device configuration ioctl calls */
+static int atif_ioctl(int cmd, void __user *arg)
+{
+	static char aarp_mcast[6] = { 0x09, 0x00, 0x00, 0xFF, 0xFF, 0xFF };
+	struct ifreq atreq;
+	struct atalk_netrange *nr;
+	struct sockaddr_at *sa;
+	struct net_device *dev;
+	struct atalk_iface *atif;
+	int ct;
+	int limit;
+	struct rtentry rtdef;
+	int add_route;
+
+	if (copy_from_user(&atreq, arg, sizeof(atreq)))
+		return -EFAULT;
+
+	dev = __dev_get_by_name(&init_net, atreq.ifr_name);
+	if (!dev)
+		return -ENODEV;
+
+	sa = (struct sockaddr_at *)&atreq.ifr_addr;
+	atif = atalk_find_dev(dev);
+
+	switch (cmd) {
+		case SIOCSIFADDR:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			if (dev->type != ARPHRD_ETHER &&
+			    dev->type != ARPHRD_LOOPBACK &&
+			    dev->type != ARPHRD_LOCALTLK &&
+			    dev->type != ARPHRD_PPP)
+				return -EPROTONOSUPPORT;
+
+			nr = (struct atalk_netrange *)&sa->sat_zero[0];
+			add_route = 1;
+
+			/*
+			 * if this is a point-to-point iface, and we already
+			 * have an iface for this AppleTalk address, then we
+			 * should not add a route
+			 */
+			if ((dev->flags & IFF_POINTOPOINT) &&
+			    atalk_find_interface(sa->sat_addr.s_net,
+						 sa->sat_addr.s_node)) {
+				printk(KERN_DEBUG "AppleTalk: point-to-point "
+						  "interface added with "
+						  "existing address\n");
+				add_route = 0;
+			}
+
+			/*
+			 * Phase 1 is fine on LocalTalk but we don't do
+			 * EtherTalk phase 1. Anyone wanting to add it go ahead.
+			 */
+			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
+				return -EPROTONOSUPPORT;
+			if (sa->sat_addr.s_node == ATADDR_BCAST ||
+			    sa->sat_addr.s_node == 254)
+				return -EINVAL;
+			if (atif) {
+				/* Already setting address */
+				if (atif->status & ATIF_PROBE)
+					return -EBUSY;
+
+				atif->address.s_net  = sa->sat_addr.s_net;
+				atif->address.s_node = sa->sat_addr.s_node;
+				atrtr_device_down(dev);	/* Flush old routes */
+			} else {
+				atif = atif_add_device(dev, &sa->sat_addr);
+				if (!atif)
+					return -ENOMEM;
+			}
+			atif->nets = *nr;
+
+			/*
+			 * Check if the chosen address is used. If so we
+			 * error and atalkd will try another.
+			 */
+
+			if (!(dev->flags & IFF_LOOPBACK) &&
+			    !(dev->flags & IFF_POINTOPOINT) &&
+			    atif_probe_device(atif) < 0) {
+				atif_drop_device(dev);
+				return -EADDRINUSE;
+			}
+
+			/* Hey it worked - add the direct routes */
+			sa = (struct sockaddr_at *)&rtdef.rt_gateway;
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr.s_net  = atif->address.s_net;
+			sa->sat_addr.s_node = atif->address.s_node;
+			sa = (struct sockaddr_at *)&rtdef.rt_dst;
+			rtdef.rt_flags = RTF_UP;
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr.s_node = ATADDR_ANYNODE;
+			if (dev->flags & IFF_LOOPBACK ||
+			    dev->flags & IFF_POINTOPOINT)
+				rtdef.rt_flags |= RTF_HOST;
+
+			/* Routerless initial state */
+			if (nr->nr_firstnet == htons(0) &&
+			    nr->nr_lastnet == htons(0xFFFE)) {
+				sa->sat_addr.s_net = atif->address.s_net;
+				atrtr_create(&rtdef, dev);
+				atrtr_set_default(dev);
+			} else {
+				limit = ntohs(nr->nr_lastnet);
+				if (limit - ntohs(nr->nr_firstnet) > 4096) {
+					printk(KERN_WARNING "Too many routes/"
+							    "iface.\n");
+					return -EINVAL;
+				}
+				if (add_route)
+					for (ct = ntohs(nr->nr_firstnet);
+					     ct <= limit; ct++) {
+						sa->sat_addr.s_net = htons(ct);
+						atrtr_create(&rtdef, dev);
+					}
+			}
+			dev_mc_add_global(dev, aarp_mcast);
+			return 0;
+
+		case SIOCGIFADDR:
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr = atif->address;
+			break;
+
+		case SIOCGIFBRDADDR:
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr.s_net = atif->address.s_net;
+			sa->sat_addr.s_node = ATADDR_BCAST;
+			break;
+
+		case SIOCATALKDIFADDR:
+		case SIOCDIFADDR:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			atalk_dev_down(dev);
+			break;
+
+		case SIOCSARP:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			/*
+			 * for now, we only support proxy AARP on ELAP;
+			 * we should be able to do it for LocalTalk, too.
+			 */
+			if (dev->type != ARPHRD_ETHER)
+				return -EPROTONOSUPPORT;
+
+			/*
+			 * atif points to the current interface on this network;
+			 * we aren't concerned about its current status (at
+			 * least for now), but it has all the settings about
+			 * the network we're going to probe. Consequently, it
+			 * must exist.
+			 */
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			nr = (struct atalk_netrange *)&(atif->nets);
+			/*
+			 * Phase 1 is fine on Localtalk but we don't do
+			 * Ethertalk phase 1. Anyone wanting to add it go ahead.
+			 */
+			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
+				return -EPROTONOSUPPORT;
+
+			if (sa->sat_addr.s_node == ATADDR_BCAST ||
+			    sa->sat_addr.s_node == 254)
+				return -EINVAL;
+
+			/*
+			 * Check if the chosen address is used. If so we
+			 * error and ATCP will try another.
+			 */
+			if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0)
+				return -EADDRINUSE;
+
+			/*
+			 * We now have an address on the local network, and
+			 * the AARP code will defend it for us until we take it
+			 * down. We don't set up any routes right now, because
+			 * ATCP will install them manually via SIOCADDRT.
+			 */
+			break;
+
+		case SIOCDARP:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			/* give to aarp module to remove proxy entry */
+			aarp_proxy_remove(atif->dev, &(sa->sat_addr));
+			return 0;
+	}
+
+	return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0;
+}
+
+/* Routing ioctl() calls */
+static int atrtr_ioctl(unsigned int cmd, void __user *arg)
+{
+	struct rtentry rt;
+
+	if (copy_from_user(&rt, arg, sizeof(rt)))
+		return -EFAULT;
+
+	switch (cmd) {
+		case SIOCDELRT:
+			if (rt.rt_dst.sa_family != AF_APPLETALK)
+				return -EINVAL;
+			return atrtr_delete(&((struct sockaddr_at *)
+						&rt.rt_dst)->sat_addr);
+
+		case SIOCADDRT: {
+			struct net_device *dev = NULL;
+			if (rt.rt_dev) {
+				char name[IFNAMSIZ];
+				if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1))
+					return -EFAULT;
+				name[IFNAMSIZ-1] = '\0';
+				dev = __dev_get_by_name(&init_net, name);
+				if (!dev)
+					return -ENODEV;
+			}
+			return atrtr_create(&rt, dev);
+		}
+	}
+	return -EINVAL;
+}
+
+/**************************************************************************\
+*                                                                          *
+* Handling for system calls applied via the various interfaces to an       *
+* AppleTalk socket object.                                                 *
+*                                                                          *
+\**************************************************************************/
+
+/*
+ * Checksum: This is 'optional'. It's quite likely also a good
+ * candidate for assembler hackery 8)
+ */
+static unsigned long atalk_sum_partial(const unsigned char *data,
+				       int len, unsigned long sum)
+{
+	/* This ought to be unwrapped neatly. I'll trust gcc for now */
+	while (len--) {
+		sum += *data++;
+		sum = rol16(sum, 1);
+	}
+	return sum;
+}
+
+/*  Checksum skb data --  similar to skb_checksum  */
+static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
+				   int len, unsigned long sum)
+{
+	int start = skb_headlen(skb);
+	struct sk_buff *frag_iter;
+	int i, copy;
+
+	/* checksum stuff in header space */
+	if ( (copy = start - offset) > 0) {
+		if (copy > len)
+			copy = len;
+		sum = atalk_sum_partial(skb->data + offset, copy, sum);
+		if ( (len -= copy) == 0)
+			return sum;
+
+		offset += copy;
+	}
+
+	/* checksum stuff in frags */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			u8 *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap_skb_frag(frag);
+			sum = atalk_sum_partial(vaddr + frag->page_offset +
+						  offset - start, copy, sum);
+			kunmap_skb_frag(vaddr);
+
+			if (!(len -= copy))
+				return sum;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			sum = atalk_sum_skb(frag_iter, offset - start,
+					    copy, sum);
+			if ((len -= copy) == 0)
+				return sum;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	BUG_ON(len > 0);
+
+	return sum;
+}
+
+static __be16 atalk_checksum(const struct sk_buff *skb, int len)
+{
+	unsigned long sum;
+
+	/* skip header 4 bytes */
+	sum = atalk_sum_skb(skb, 4, len-4, 0);
+
+	/* Use 0xFFFF for 0. 0 itself means none */
+	return sum ? htons((unsigned short)sum) : htons(0xFFFF);
+}
+
+static struct proto ddp_proto = {
+	.name	  = "DDP",
+	.owner	  = THIS_MODULE,
+	.obj_size = sizeof(struct atalk_sock),
+};
+
+/*
+ * Create a socket. Initialise the socket, blank the addresses
+ * set the state.
+ */
+static int atalk_create(struct net *net, struct socket *sock, int protocol,
+			int kern)
+{
+	struct sock *sk;
+	int rc = -ESOCKTNOSUPPORT;
+
+	if (!net_eq(net, &init_net))
+		return -EAFNOSUPPORT;
+
+	/*
+	 * We permit SOCK_DGRAM and RAW is an extension. It is trivial to do
+	 * and gives you the full ELAP frame. Should be handy for CAP 8)
+	 */
+	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
+		goto out;
+	rc = -ENOMEM;
+	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto);
+	if (!sk)
+		goto out;
+	rc = 0;
+	sock->ops = &atalk_dgram_ops;
+	sock_init_data(sock, sk);
+
+	/* Checksums on by default */
+	sock_set_flag(sk, SOCK_ZAPPED);
+out:
+	return rc;
+}
+
+/* Free a socket. No work needed */
+static int atalk_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	lock_kernel();
+	if (sk) {
+		sock_orphan(sk);
+		sock->sk = NULL;
+		atalk_destroy_socket(sk);
+	}
+	unlock_kernel();
+	return 0;
+}
+
+/**
+ * atalk_pick_and_bind_port - Pick a source port when one is not given
+ * @sk - socket to insert into the tables
+ * @sat - address to search for
+ *
+ * Pick a source port when one is not given. If we can find a suitable free
+ * one, we insert the socket into the tables using it.
+ *
+ * This whole operation must be atomic.
+ */
+static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat)
+{
+	int retval;
+
+	write_lock_bh(&atalk_sockets_lock);
+
+	for (sat->sat_port = ATPORT_RESERVED;
+	     sat->sat_port < ATPORT_LAST;
+	     sat->sat_port++) {
+		struct sock *s;
+		struct hlist_node *node;
+
+		sk_for_each(s, node, &atalk_sockets) {
+			struct atalk_sock *at = at_sk(s);
+
+			if (at->src_net == sat->sat_addr.s_net &&
+			    at->src_node == sat->sat_addr.s_node &&
+			    at->src_port == sat->sat_port)
+				goto try_next_port;
+		}
+
+		/* Wheee, it's free, assign and insert. */
+		__atalk_insert_socket(sk);
+		at_sk(sk)->src_port = sat->sat_port;
+		retval = 0;
+		goto out;
+
+try_next_port:;
+	}
+
+	retval = -EBUSY;
+out:
+	write_unlock_bh(&atalk_sockets_lock);
+	return retval;
+}
+
+static int atalk_autobind(struct sock *sk)
+{
+	struct atalk_sock *at = at_sk(sk);
+	struct sockaddr_at sat;
+	struct atalk_addr *ap = atalk_find_primary();
+	int n = -EADDRNOTAVAIL;
+
+	if (!ap || ap->s_net == htons(ATADDR_ANYNET))
+		goto out;
+
+	at->src_net  = sat.sat_addr.s_net  = ap->s_net;
+	at->src_node = sat.sat_addr.s_node = ap->s_node;
+
+	n = atalk_pick_and_bind_port(sk, &sat);
+	if (!n)
+		sock_reset_flag(sk, SOCK_ZAPPED);
+out:
+	return n;
+}
+
+/* Set the address 'our end' of the connection */
+static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	struct sockaddr_at *addr = (struct sockaddr_at *)uaddr;
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	int err;
+
+	if (!sock_flag(sk, SOCK_ZAPPED) ||
+	    addr_len != sizeof(struct sockaddr_at))
+		return -EINVAL;
+
+	if (addr->sat_family != AF_APPLETALK)
+		return -EAFNOSUPPORT;
+
+	lock_kernel();
+	if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) {
+		struct atalk_addr *ap = atalk_find_primary();
+
+		err = -EADDRNOTAVAIL;
+		if (!ap)
+			goto out;
+
+		at->src_net  = addr->sat_addr.s_net = ap->s_net;
+		at->src_node = addr->sat_addr.s_node= ap->s_node;
+	} else {
+		err = -EADDRNOTAVAIL;
+		if (!atalk_find_interface(addr->sat_addr.s_net,
+					  addr->sat_addr.s_node))
+			goto out;
+
+		at->src_net  = addr->sat_addr.s_net;
+		at->src_node = addr->sat_addr.s_node;
+	}
+
+	if (addr->sat_port == ATADDR_ANYPORT) {
+		err = atalk_pick_and_bind_port(sk, addr);
+
+		if (err < 0)
+			goto out;
+	} else {
+		at->src_port = addr->sat_port;
+
+		err = -EADDRINUSE;
+		if (atalk_find_or_insert_socket(sk, addr))
+			goto out;
+	}
+
+	sock_reset_flag(sk, SOCK_ZAPPED);
+	err = 0;
+out:
+	unlock_kernel();
+	return err;
+}
+
+/* Set the address we talk to */
+static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
+			 int addr_len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	struct sockaddr_at *addr;
+	int err;
+
+	sk->sk_state   = TCP_CLOSE;
+	sock->state = SS_UNCONNECTED;
+
+	if (addr_len != sizeof(*addr))
+		return -EINVAL;
+
+	addr = (struct sockaddr_at *)uaddr;
+
+	if (addr->sat_family != AF_APPLETALK)
+		return -EAFNOSUPPORT;
+
+	if (addr->sat_addr.s_node == ATADDR_BCAST &&
+	    !sock_flag(sk, SOCK_BROADCAST)) {
+#if 1
+		printk(KERN_WARNING "%s is broken and did not set "
+				    "SO_BROADCAST. It will break when 2.2 is "
+				    "released.\n",
+			current->comm);
+#else
+		return -EACCES;
+#endif
+	}
+
+	lock_kernel();
+	err = -EBUSY;
+	if (sock_flag(sk, SOCK_ZAPPED))
+		if (atalk_autobind(sk) < 0)
+			goto out;
+
+	err = -ENETUNREACH;
+	if (!atrtr_get_dev(&addr->sat_addr))
+		goto out;
+
+	at->dest_port = addr->sat_port;
+	at->dest_net  = addr->sat_addr.s_net;
+	at->dest_node = addr->sat_addr.s_node;
+
+	sock->state  = SS_CONNECTED;
+	sk->sk_state = TCP_ESTABLISHED;
+	err = 0;
+out:
+	unlock_kernel();
+	return err;
+}
+
+/*
+ * Find the name of an AppleTalk socket. Just copy the right
+ * fields into the sockaddr.
+ */
+static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
+			 int *uaddr_len, int peer)
+{
+	struct sockaddr_at sat;
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	int err;
+
+	lock_kernel();
+	err = -ENOBUFS;
+	if (sock_flag(sk, SOCK_ZAPPED))
+		if (atalk_autobind(sk) < 0)
+			goto out;
+
+	*uaddr_len = sizeof(struct sockaddr_at);
+	memset(&sat.sat_zero, 0, sizeof(sat.sat_zero));
+
+	if (peer) {
+		err = -ENOTCONN;
+		if (sk->sk_state != TCP_ESTABLISHED)
+			goto out;
+
+		sat.sat_addr.s_net  = at->dest_net;
+		sat.sat_addr.s_node = at->dest_node;
+		sat.sat_port	    = at->dest_port;
+	} else {
+		sat.sat_addr.s_net  = at->src_net;
+		sat.sat_addr.s_node = at->src_node;
+		sat.sat_port	    = at->src_port;
+	}
+
+	err = 0;
+	sat.sat_family = AF_APPLETALK;
+	memcpy(uaddr, &sat, sizeof(sat));
+
+out:
+	unlock_kernel();
+	return err;
+}
+
+static unsigned int atalk_poll(struct file *file, struct socket *sock,
+			   poll_table *wait)
+{
+	int err;
+	lock_kernel();
+	err = datagram_poll(file, sock, wait);
+	unlock_kernel();
+	return err;
+}
+
+#if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE)
+static __inline__ int is_ip_over_ddp(struct sk_buff *skb)
+{
+	return skb->data[12] == 22;
+}
+
+static int handle_ip_over_ddp(struct sk_buff *skb)
+{
+	struct net_device *dev = __dev_get_by_name(&init_net, "ipddp0");
+	struct net_device_stats *stats;
+
+	/* This needs to be able to handle ipddp"N" devices */
+	if (!dev) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb->protocol = htons(ETH_P_IP);
+	skb_pull(skb, 13);
+	skb->dev   = dev;
+	skb_reset_transport_header(skb);
+
+	stats = netdev_priv(dev);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len + 13;
+	return netif_rx(skb);  /* Send the SKB up to a higher place. */
+}
+#else
+/* make it easy for gcc to optimize this test out, i.e. kill the code */
+#define is_ip_over_ddp(skb) 0
+#define handle_ip_over_ddp(skb) 0
+#endif
+
+static int atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
+			      struct ddpehdr *ddp, __u16 len_hops, int origlen)
+{
+	struct atalk_route *rt;
+	struct atalk_addr ta;
+
+	/*
+	 * Don't route multicast, etc., packets, or packets sent to "this
+	 * network"
+	 */
+	if (skb->pkt_type != PACKET_HOST || !ddp->deh_dnet) {
+		/*
+		 * FIXME:
+		 *
+		 * Can it ever happen that a packet is from a PPP iface and
+		 * needs to be broadcast onto the default network?
+		 */
+		if (dev->type == ARPHRD_PPP)
+			printk(KERN_DEBUG "AppleTalk: didn't forward broadcast "
+					  "packet received from PPP iface\n");
+		goto free_it;
+	}
+
+	ta.s_net  = ddp->deh_dnet;
+	ta.s_node = ddp->deh_dnode;
+
+	/* Route the packet */
+	rt = atrtr_find(&ta);
+	/* increment hops count */
+	len_hops += 1 << 10;
+	if (!rt || !(len_hops & (15 << 10)))
+		goto free_it;
+
+	/* FIXME: use skb->cb to be able to use shared skbs */
+
+	/*
+	 * Route goes through another gateway, so set the target to the
+	 * gateway instead.
+	 */
+
+	if (rt->flags & RTF_GATEWAY) {
+		ta.s_net  = rt->gateway.s_net;
+		ta.s_node = rt->gateway.s_node;
+	}
+
+	/* Fix up skb->len field */
+	skb_trim(skb, min_t(unsigned int, origlen,
+			    (rt->dev->hard_header_len +
+			     ddp_dl->header_length + (len_hops & 1023))));
+
+	/* FIXME: use skb->cb to be able to use shared skbs */
+	ddp->deh_len_hops = htons(len_hops);
+
+	/*
+	 * Send the buffer onwards
+	 *
+	 * Now we must always be careful. If it's come from LocalTalk to
+	 * EtherTalk it might not fit
+	 *
+	 * Order matters here: If a packet has to be copied to make a new
+	 * headroom (rare hopefully) then it won't need unsharing.
+	 *
+	 * Note. ddp-> becomes invalid at the realloc.
+	 */
+	if (skb_headroom(skb) < 22) {
+		/* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */
+		struct sk_buff *nskb = skb_realloc_headroom(skb, 32);
+		kfree_skb(skb);
+		skb = nskb;
+	} else
+		skb = skb_unshare(skb, GFP_ATOMIC);
+
+	/*
+	 * If the buffer didn't vanish into the lack of space bitbucket we can
+	 * send it.
+	 */
+	if (skb == NULL)
+		goto drop;
+
+	if (aarp_send_ddp(rt->dev, skb, &ta, NULL) == NET_XMIT_DROP)
+		return NET_RX_DROP;
+	return NET_RX_SUCCESS;
+free_it:
+	kfree_skb(skb);
+drop:
+	return NET_RX_DROP;
+}
+
+/**
+ *	atalk_rcv - Receive a packet (in skb) from device dev
+ *	@skb - packet received
+ *	@dev - network device where the packet comes from
+ *	@pt - packet type
+ *
+ *	Receive a packet (in skb) from device dev. This has come from the SNAP
+ *	decoder, and on entry skb->transport_header is the DDP header, skb->len
+ *	is the DDP header, skb->len is the DDP length. The physical headers
+ *	have been extracted. PPP should probably pass frames marked as for this
+ *	layer.  [ie ARPHRD_ETHERTALK]
+ */
+static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
+		     struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct ddpehdr *ddp;
+	struct sock *sock;
+	struct atalk_iface *atif;
+	struct sockaddr_at tosat;
+	int origlen;
+	__u16 len_hops;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		goto drop;
+
+	/* Don't mangle buffer if shared */
+	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
+		goto out;
+
+	/* Size check and make sure header is contiguous */
+	if (!pskb_may_pull(skb, sizeof(*ddp)))
+		goto drop;
+
+	ddp = ddp_hdr(skb);
+
+	len_hops = ntohs(ddp->deh_len_hops);
+
+	/* Trim buffer in case of stray trailing data */
+	origlen = skb->len;
+	skb_trim(skb, min_t(unsigned int, skb->len, len_hops & 1023));
+
+	/*
+	 * Size check to see if ddp->deh_len was crap
+	 * (Otherwise we'll detonate most spectacularly
+	 * in the middle of atalk_checksum() or recvmsg()).
+	 */
+	if (skb->len < sizeof(*ddp) || skb->len < (len_hops & 1023)) {
+		pr_debug("AppleTalk: dropping corrupted frame (deh_len=%u, "
+			 "skb->len=%u)\n", len_hops & 1023, skb->len);
+		goto drop;
+	}
+
+	/*
+	 * Any checksums. Note we don't do htons() on this == is assumed to be
+	 * valid for net byte orders all over the networking code...
+	 */
+	if (ddp->deh_sum &&
+	    atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum)
+		/* Not a valid AppleTalk frame - dustbin time */
+		goto drop;
+
+	/* Check the packet is aimed at us */
+	if (!ddp->deh_dnet)	/* Net 0 is 'this network' */
+		atif = atalk_find_anynet(ddp->deh_dnode, dev);
+	else
+		atif = atalk_find_interface(ddp->deh_dnet, ddp->deh_dnode);
+
+	if (!atif) {
+		/* Not ours, so we route the packet via the correct
+		 * AppleTalk iface
+		 */
+		return atalk_route_packet(skb, dev, ddp, len_hops, origlen);
+	}
+
+	/* if IP over DDP is not selected this code will be optimized out */
+	if (is_ip_over_ddp(skb))
+		return handle_ip_over_ddp(skb);
+	/*
+	 * Which socket - atalk_search_socket() looks for a *full match*
+	 * of the <net, node, port> tuple.
+	 */
+	tosat.sat_addr.s_net  = ddp->deh_dnet;
+	tosat.sat_addr.s_node = ddp->deh_dnode;
+	tosat.sat_port	      = ddp->deh_dport;
+
+	sock = atalk_search_socket(&tosat, atif);
+	if (!sock) /* But not one of our sockets */
+		goto drop;
+
+	/* Queue packet (standard) */
+	skb->sk = sock;
+
+	if (sock_queue_rcv_skb(sock, skb) < 0)
+		goto drop;
+
+	return NET_RX_SUCCESS;
+
+drop:
+	kfree_skb(skb);
+out:
+	return NET_RX_DROP;
+
+}
+
+/*
+ * Receive a LocalTalk frame. We make some demands on the caller here.
+ * Caller must provide enough headroom on the packet to pull the short
+ * header and append a long one.
+ */
+static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
+		     struct packet_type *pt, struct net_device *orig_dev)
+{
+	if (!net_eq(dev_net(dev), &init_net))
+		goto freeit;
+
+	/* Expand any short form frames */
+	if (skb_mac_header(skb)[2] == 1) {
+		struct ddpehdr *ddp;
+		/* Find our address */
+		struct atalk_addr *ap = atalk_find_dev_addr(dev);
+
+		if (!ap || skb->len < sizeof(__be16) || skb->len > 1023)
+			goto freeit;
+
+		/* Don't mangle buffer if shared */
+		if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
+			return 0;
+
+		/*
+		 * The push leaves us with a ddephdr not an shdr, and
+		 * handily the port bytes in the right place preset.
+		 */
+		ddp = (struct ddpehdr *) skb_push(skb, sizeof(*ddp) - 4);
+
+		/* Now fill in the long header */
+
+		/*
+		 * These two first. The mac overlays the new source/dest
+		 * network information so we MUST copy these before
+		 * we write the network numbers !
+		 */
+
+		ddp->deh_dnode = skb_mac_header(skb)[0];     /* From physical header */
+		ddp->deh_snode = skb_mac_header(skb)[1];     /* From physical header */
+
+		ddp->deh_dnet  = ap->s_net;	/* Network number */
+		ddp->deh_snet  = ap->s_net;
+		ddp->deh_sum   = 0;		/* No checksum */
+		/*
+		 * Not sure about this bit...
+		 */
+		/* Non routable, so force a drop if we slip up later */
+		ddp->deh_len_hops = htons(skb->len + (DDP_MAXHOPS << 10));
+	}
+	skb_reset_transport_header(skb);
+
+	return atalk_rcv(skb, dev, pt, orig_dev);
+freeit:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+			 size_t len)
+{
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name;
+	int flags = msg->msg_flags;
+	int loopback = 0;
+	struct sockaddr_at local_satalk, gsat;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	struct ddpehdr *ddp;
+	int size;
+	struct atalk_route *rt;
+	int err;
+
+	if (flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
+		return -EINVAL;
+
+	if (len > DDP_MAXSZ)
+		return -EMSGSIZE;
+
+	lock_kernel();
+	if (usat) {
+		err = -EBUSY;
+		if (sock_flag(sk, SOCK_ZAPPED))
+			if (atalk_autobind(sk) < 0)
+				goto out;
+
+		err = -EINVAL;
+		if (msg->msg_namelen < sizeof(*usat) ||
+		    usat->sat_family != AF_APPLETALK)
+			goto out;
+
+		err = -EPERM;
+		/* netatalk didn't implement this check */
+		if (usat->sat_addr.s_node == ATADDR_BCAST &&
+		    !sock_flag(sk, SOCK_BROADCAST)) {
+			goto out;
+		}
+	} else {
+		err = -ENOTCONN;
+		if (sk->sk_state != TCP_ESTABLISHED)
+			goto out;
+		usat = &local_satalk;
+		usat->sat_family      = AF_APPLETALK;
+		usat->sat_port	      = at->dest_port;
+		usat->sat_addr.s_node = at->dest_node;
+		usat->sat_addr.s_net  = at->dest_net;
+	}
+
+	/* Build a packet */
+	SOCK_DEBUG(sk, "SK %p: Got address.\n", sk);
+
+	/* For headers */
+	size = sizeof(struct ddpehdr) + len + ddp_dl->header_length;
+
+	if (usat->sat_addr.s_net || usat->sat_addr.s_node == ATADDR_ANYNODE) {
+		rt = atrtr_find(&usat->sat_addr);
+	} else {
+		struct atalk_addr at_hint;
+
+		at_hint.s_node = 0;
+		at_hint.s_net  = at->src_net;
+
+		rt = atrtr_find(&at_hint);
+	}
+	err = ENETUNREACH;
+	if (!rt)
+		goto out;
+
+	dev = rt->dev;
+
+	SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n",
+			sk, size, dev->name);
+
+	size += dev->hard_header_len;
+	skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err);
+	if (!skb)
+		goto out;
+
+	skb->sk = sk;
+	skb_reserve(skb, ddp_dl->header_length);
+	skb_reserve(skb, dev->hard_header_len);
+	skb->dev = dev;
+
+	SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk);
+
+	ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr));
+	ddp->deh_len_hops  = htons(len + sizeof(*ddp));
+	ddp->deh_dnet  = usat->sat_addr.s_net;
+	ddp->deh_snet  = at->src_net;
+	ddp->deh_dnode = usat->sat_addr.s_node;
+	ddp->deh_snode = at->src_node;
+	ddp->deh_dport = usat->sat_port;
+	ddp->deh_sport = at->src_port;
+
+	SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len);
+
+	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	if (err) {
+		kfree_skb(skb);
+		err = -EFAULT;
+		goto out;
+	}
+
+	if (sk->sk_no_check == 1)
+		ddp->deh_sum = 0;
+	else
+		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
+
+	/*
+	 * Loopback broadcast packets to non gateway targets (ie routes
+	 * to group we are in)
+	 */
+	if (ddp->deh_dnode == ATADDR_BCAST &&
+	    !(rt->flags & RTF_GATEWAY) && !(dev->flags & IFF_LOOPBACK)) {
+		struct sk_buff *skb2 = skb_copy(skb, GFP_KERNEL);
+
+		if (skb2) {
+			loopback = 1;
+			SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk);
+			/*
+			 * If it fails it is queued/sent above in the aarp queue
+			 */
+			aarp_send_ddp(dev, skb2, &usat->sat_addr, NULL);
+		}
+	}
+
+	if (dev->flags & IFF_LOOPBACK || loopback) {
+		SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk);
+		/* loop back */
+		skb_orphan(skb);
+		if (ddp->deh_dnode == ATADDR_BCAST) {
+			struct atalk_addr at_lo;
+
+			at_lo.s_node = 0;
+			at_lo.s_net  = 0;
+
+			rt = atrtr_find(&at_lo);
+			if (!rt) {
+				kfree_skb(skb);
+				err = -ENETUNREACH;
+				goto out;
+			}
+			dev = rt->dev;
+			skb->dev = dev;
+		}
+		ddp_dl->request(ddp_dl, skb, dev->dev_addr);
+	} else {
+		SOCK_DEBUG(sk, "SK %p: send out.\n", sk);
+		if (rt->flags & RTF_GATEWAY) {
+		    gsat.sat_addr = rt->gateway;
+		    usat = &gsat;
+		}
+
+		/*
+		 * If it fails it is queued/sent above in the aarp queue
+		 */
+		aarp_send_ddp(dev, skb, &usat->sat_addr, NULL);
+	}
+	SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len);
+
+out:
+	unlock_kernel();
+	return err ? : len;
+}
+
+static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+			 size_t size, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
+	struct ddpehdr *ddp;
+	int copied = 0;
+	int offset = 0;
+	int err = 0;
+	struct sk_buff *skb;
+
+	lock_kernel();
+	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
+						flags & MSG_DONTWAIT, &err);
+	if (!skb)
+		goto out;
+
+	/* FIXME: use skb->cb to be able to use shared skbs */
+	ddp = ddp_hdr(skb);
+	copied = ntohs(ddp->deh_len_hops) & 1023;
+
+	if (sk->sk_type != SOCK_RAW) {
+		offset = sizeof(*ddp);
+		copied -= offset;
+	}
+
+	if (copied > size) {
+		copied = size;
+		msg->msg_flags |= MSG_TRUNC;
+	}
+	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
+
+	if (!err) {
+		if (sat) {
+			sat->sat_family      = AF_APPLETALK;
+			sat->sat_port        = ddp->deh_sport;
+			sat->sat_addr.s_node = ddp->deh_snode;
+			sat->sat_addr.s_net  = ddp->deh_snet;
+		}
+		msg->msg_namelen = sizeof(*sat);
+	}
+
+	skb_free_datagram(sk, skb);	/* Free the datagram. */
+
+out:
+	unlock_kernel();
+	return err ? : copied;
+}
+
+
+/*
+ * AppleTalk ioctl calls.
+ */
+static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	int rc = -ENOIOCTLCMD;
+	struct sock *sk = sock->sk;
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+		/* Protocol layer */
+		case TIOCOUTQ: {
+			long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
+
+			if (amount < 0)
+				amount = 0;
+			rc = put_user(amount, (int __user *)argp);
+			break;
+		}
+		case TIOCINQ: {
+			/*
+			 * These two are safe on a single CPU system as only
+			 * user tasks fiddle here
+			 */
+			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+			long amount = 0;
+
+			if (skb)
+				amount = skb->len - sizeof(struct ddpehdr);
+			rc = put_user(amount, (int __user *)argp);
+			break;
+		}
+		case SIOCGSTAMP:
+			rc = sock_get_timestamp(sk, argp);
+			break;
+		case SIOCGSTAMPNS:
+			rc = sock_get_timestampns(sk, argp);
+			break;
+		/* Routing */
+		case SIOCADDRT:
+		case SIOCDELRT:
+			rc = -EPERM;
+			if (capable(CAP_NET_ADMIN))
+				rc = atrtr_ioctl(cmd, argp);
+			break;
+		/* Interface */
+		case SIOCGIFADDR:
+		case SIOCSIFADDR:
+		case SIOCGIFBRDADDR:
+		case SIOCATALKDIFADDR:
+		case SIOCDIFADDR:
+		case SIOCSARP:		/* proxy AARP */
+		case SIOCDARP:		/* proxy AARP */
+			rtnl_lock();
+			rc = atif_ioctl(cmd, argp);
+			rtnl_unlock();
+			break;
+	}
+
+	return rc;
+}
+
+
+#ifdef CONFIG_COMPAT
+static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	/*
+	 * SIOCATALKDIFADDR is a SIOCPROTOPRIVATE ioctl number, so we
+	 * cannot handle it in common code. The data we access if ifreq
+	 * here is compatible, so we can simply call the native
+	 * handler.
+	 */
+	if (cmd == SIOCATALKDIFADDR)
+		return atalk_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+
+	return -ENOIOCTLCMD;
+}
+#endif
+
+
+static const struct net_proto_family atalk_family_ops = {
+	.family		= PF_APPLETALK,
+	.create		= atalk_create,
+	.owner		= THIS_MODULE,
+};
+
+static const struct proto_ops atalk_dgram_ops = {
+	.family		= PF_APPLETALK,
+	.owner		= THIS_MODULE,
+	.release	= atalk_release,
+	.bind		= atalk_bind,
+	.connect	= atalk_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= sock_no_accept,
+	.getname	= atalk_getname,
+	.poll		= atalk_poll,
+	.ioctl		= atalk_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= atalk_compat_ioctl,
+#endif
+	.listen		= sock_no_listen,
+	.shutdown	= sock_no_shutdown,
+	.setsockopt	= sock_no_setsockopt,
+	.getsockopt	= sock_no_getsockopt,
+	.sendmsg	= atalk_sendmsg,
+	.recvmsg	= atalk_recvmsg,
+	.mmap		= sock_no_mmap,
+	.sendpage	= sock_no_sendpage,
+};
+
+static struct notifier_block ddp_notifier = {
+	.notifier_call	= ddp_device_event,
+};
+
+static struct packet_type ltalk_packet_type __read_mostly = {
+	.type		= cpu_to_be16(ETH_P_LOCALTALK),
+	.func		= ltalk_rcv,
+};
+
+static struct packet_type ppptalk_packet_type __read_mostly = {
+	.type		= cpu_to_be16(ETH_P_PPPTALK),
+	.func		= atalk_rcv,
+};
+
+static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B };
+
+/* Export symbols for use by drivers when AppleTalk is a module */
+EXPORT_SYMBOL(atrtr_get_dev);
+EXPORT_SYMBOL(atalk_find_dev_addr);
+
+static const char atalk_err_snap[] __initconst =
+	KERN_CRIT "Unable to register DDP with SNAP.\n";
+
+/* Called by proto.c on kernel start up */
+static int __init atalk_init(void)
+{
+	int rc = proto_register(&ddp_proto, 0);
+
+	if (rc != 0)
+		goto out;
+
+	(void)sock_register(&atalk_family_ops);
+	ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
+	if (!ddp_dl)
+		printk(atalk_err_snap);
+
+	dev_add_pack(&ltalk_packet_type);
+	dev_add_pack(&ppptalk_packet_type);
+
+	register_netdevice_notifier(&ddp_notifier);
+	aarp_proto_init();
+	atalk_proc_init();
+	atalk_register_sysctl();
+out:
+	return rc;
+}
+module_init(atalk_init);
+
+/*
+ * No explicit module reference count manipulation is needed in the
+ * protocol. Socket layer sets module reference count for us
+ * and interfaces reference counting is done
+ * by the network device layer.
+ *
+ * Ergo, before the AppleTalk module can be removed, all AppleTalk
+ * sockets be closed from user space.
+ */
+static void __exit atalk_exit(void)
+{
+#ifdef CONFIG_SYSCTL
+	atalk_unregister_sysctl();
+#endif /* CONFIG_SYSCTL */
+	atalk_proc_exit();
+	aarp_cleanup_module();	/* General aarp clean-up. */
+	unregister_netdevice_notifier(&ddp_notifier);
+	dev_remove_pack(&ltalk_packet_type);
+	dev_remove_pack(&ppptalk_packet_type);
+	unregister_snap_client(ddp_dl);
+	sock_unregister(PF_APPLETALK);
+	proto_unregister(&ddp_proto);
+}
+module_exit(atalk_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alan Cox <alan@lxorguk.ukuu.org.uk>");
+MODULE_DESCRIPTION("AppleTalk 0.20\n");
+MODULE_ALIAS_NETPROTO(PF_APPLETALK);
diff --git a/drivers/staging/appletalk/dev.c b/drivers/staging/appletalk/dev.c
new file mode 100644
index 000000000000..6c8016f61866
--- /dev/null
+++ b/drivers/staging/appletalk/dev.c
@@ -0,0 +1,44 @@
+/*
+ * Moved here from drivers/net/net_init.c, which is:
+ *	Written 1993,1994,1995 by Donald Becker.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_ltalk.h>
+
+static void ltalk_setup(struct net_device *dev)
+{
+	/* Fill in the fields of the device structure with localtalk-generic values. */
+
+	dev->type		= ARPHRD_LOCALTLK;
+	dev->hard_header_len 	= LTALK_HLEN;
+	dev->mtu		= LTALK_MTU;
+	dev->addr_len		= LTALK_ALEN;
+	dev->tx_queue_len	= 10;
+
+	dev->broadcast[0]	= 0xFF;
+
+	dev->flags		= IFF_BROADCAST|IFF_MULTICAST|IFF_NOARP;
+}
+
+/**
+ * alloc_ltalkdev - Allocates and sets up an localtalk device
+ * @sizeof_priv: Size of additional driver-private structure to be allocated
+ *	for this localtalk device
+ *
+ * Fill in the fields of the device structure with localtalk-generic
+ * values. Basically does everything except registering the device.
+ *
+ * Constructs a new net device, complete with a private data area of
+ * size @sizeof_priv.  A 32-byte (not bit) alignment is enforced for
+ * this private data area.
+ */
+
+struct net_device *alloc_ltalkdev(int sizeof_priv)
+{
+	return alloc_netdev(sizeof_priv, "lt%d", ltalk_setup);
+}
+EXPORT_SYMBOL(alloc_ltalkdev);
diff --git a/drivers/staging/appletalk/ipddp.c b/drivers/staging/appletalk/ipddp.c
new file mode 100644
index 000000000000..58b4e6098ad4
--- /dev/null
+++ b/drivers/staging/appletalk/ipddp.c
@@ -0,0 +1,335 @@
+/*
+ *	ipddp.c: IP to Appletalk-IP Encapsulation driver for Linux
+ *		 Appletalk-IP to IP Decapsulation driver for Linux
+ *
+ *	Authors:
+ *      - DDP-IP Encap by: Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *	- DDP-IP Decap by: Jay Schulist <jschlst@samba.org>
+ *
+ *	Derived from:
+ *	- Almost all code already existed in net/appletalk/ddp.c I just
+ *	  moved/reorginized it into a driver file. Original IP-over-DDP code
+ *	  was done by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *      - skeleton.c: A network driver outline for linux.
+ *        Written 1993-94 by Donald Becker.
+ *	- dummy.c: A dummy net driver. By Nick Holloway.
+ *	- MacGate: A user space Daemon for Appletalk-IP Decap for
+ *	  Linux by Jay Schulist <jschlst@samba.org>
+ *
+ *      Copyright 1993 United States Government as represented by the
+ *      Director, National Security Agency.
+ *
+ *      This software may be used and distributed according to the terms
+ *      of the GNU General Public License, incorporated herein by reference.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ip.h>
+#include <linux/if_arp.h>
+#include <linux/slab.h>
+#include <net/route.h>
+#include <asm/uaccess.h>
+
+#include "atalk.h"
+#include "ipddp.h"		/* Our stuff */
+
+static const char version[] = KERN_INFO "ipddp.c:v0.01 8/28/97 Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n";
+
+static struct ipddp_route *ipddp_route_list;
+static DEFINE_SPINLOCK(ipddp_route_lock);
+
+#ifdef CONFIG_IPDDP_ENCAP
+static int ipddp_mode = IPDDP_ENCAP;
+#else
+static int ipddp_mode = IPDDP_DECAP;
+#endif
+
+/* Index to functions, as function prototypes. */
+static netdev_tx_t ipddp_xmit(struct sk_buff *skb,
+				    struct net_device *dev);
+static int ipddp_create(struct ipddp_route *new_rt);
+static int ipddp_delete(struct ipddp_route *rt);
+static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt);
+static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+
+static const struct net_device_ops ipddp_netdev_ops = {
+	.ndo_start_xmit		= ipddp_xmit,
+	.ndo_do_ioctl   	= ipddp_ioctl,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
+static struct net_device * __init ipddp_init(void)
+{
+	static unsigned version_printed;
+	struct net_device *dev;
+	int err;
+
+	dev = alloc_etherdev(0);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	strcpy(dev->name, "ipddp%d");
+
+	if (version_printed++ == 0)
+                printk(version);
+
+	/* Initialize the device structure. */
+	dev->netdev_ops = &ipddp_netdev_ops;
+
+        dev->type = ARPHRD_IPDDP;       	/* IP over DDP tunnel */
+        dev->mtu = 585;
+        dev->flags |= IFF_NOARP;
+
+        /*
+         *      The worst case header we will need is currently a
+         *      ethernet header (14 bytes) and a ddp header (sizeof ddpehdr+1)
+         *      We send over SNAP so that takes another 8 bytes.
+         */
+        dev->hard_header_len = 14+8+sizeof(struct ddpehdr)+1;
+
+	err = register_netdev(dev);
+	if (err) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
+	/* Let the user now what mode we are in */
+	if(ipddp_mode == IPDDP_ENCAP)
+		printk("%s: Appletalk-IP Encap. mode by Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n", 
+			dev->name);
+	if(ipddp_mode == IPDDP_DECAP)
+		printk("%s: Appletalk-IP Decap. mode by Jay Schulist <jschlst@samba.org>\n", 
+			dev->name);
+
+        return dev;
+}
+
+
+/*
+ * Transmit LLAP/ELAP frame using aarp_send_ddp.
+ */
+static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	__be32 paddr = skb_rtable(skb)->rt_gateway;
+        struct ddpehdr *ddp;
+        struct ipddp_route *rt;
+        struct atalk_addr *our_addr;
+
+	spin_lock(&ipddp_route_lock);
+
+	/*
+         * Find appropriate route to use, based only on IP number.
+         */
+        for(rt = ipddp_route_list; rt != NULL; rt = rt->next)
+        {
+                if(rt->ip == paddr)
+                        break;
+        }
+        if(rt == NULL) {
+		spin_unlock(&ipddp_route_lock);
+                return NETDEV_TX_OK;
+	}
+
+        our_addr = atalk_find_dev_addr(rt->dev);
+
+	if(ipddp_mode == IPDDP_DECAP)
+		/* 
+		 * Pull off the excess room that should not be there.
+		 * This is due to a hard-header problem. This is the
+		 * quick fix for now though, till it breaks.
+		 */
+		skb_pull(skb, 35-(sizeof(struct ddpehdr)+1));
+
+	/* Create the Extended DDP header */
+	ddp = (struct ddpehdr *)skb->data;
+        ddp->deh_len_hops = htons(skb->len + (1<<10));
+        ddp->deh_sum = 0;
+
+	/*
+         * For Localtalk we need aarp_send_ddp to strip the
+         * long DDP header and place a shot DDP header on it.
+         */
+        if(rt->dev->type == ARPHRD_LOCALTLK)
+        {
+                ddp->deh_dnet  = 0;   /* FIXME more hops?? */
+                ddp->deh_snet  = 0;
+        }
+        else
+        {
+                ddp->deh_dnet  = rt->at.s_net;   /* FIXME more hops?? */
+                ddp->deh_snet  = our_addr->s_net;
+        }
+        ddp->deh_dnode = rt->at.s_node;
+        ddp->deh_snode = our_addr->s_node;
+        ddp->deh_dport = 72;
+        ddp->deh_sport = 72;
+
+        *((__u8 *)(ddp+1)) = 22;        	/* ddp type = IP */
+
+        skb->protocol = htons(ETH_P_ATALK);     /* Protocol has changed */
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	aarp_send_ddp(rt->dev, skb, &rt->at, NULL);
+
+	spin_unlock(&ipddp_route_lock);
+
+        return NETDEV_TX_OK;
+}
+
+/*
+ * Create a routing entry. We first verify that the
+ * record does not already exist. If it does we return -EEXIST
+ */
+static int ipddp_create(struct ipddp_route *new_rt)
+{
+        struct ipddp_route *rt = kmalloc(sizeof(*rt), GFP_KERNEL);
+
+        if (rt == NULL)
+                return -ENOMEM;
+
+        rt->ip = new_rt->ip;
+        rt->at = new_rt->at;
+        rt->next = NULL;
+        if ((rt->dev = atrtr_get_dev(&rt->at)) == NULL) {
+		kfree(rt);
+                return -ENETUNREACH;
+        }
+
+	spin_lock_bh(&ipddp_route_lock);
+	if (__ipddp_find_route(rt)) {
+		spin_unlock_bh(&ipddp_route_lock);
+		kfree(rt);
+		return -EEXIST;
+	}
+
+        rt->next = ipddp_route_list;
+        ipddp_route_list = rt;
+
+	spin_unlock_bh(&ipddp_route_lock);
+
+        return 0;
+}
+
+/*
+ * Delete a route, we only delete a FULL match.
+ * If route does not exist we return -ENOENT.
+ */
+static int ipddp_delete(struct ipddp_route *rt)
+{
+        struct ipddp_route **r = &ipddp_route_list;
+        struct ipddp_route *tmp;
+
+	spin_lock_bh(&ipddp_route_lock);
+        while((tmp = *r) != NULL)
+        {
+                if(tmp->ip == rt->ip &&
+		   tmp->at.s_net == rt->at.s_net &&
+		   tmp->at.s_node == rt->at.s_node)
+                {
+                        *r = tmp->next;
+			spin_unlock_bh(&ipddp_route_lock);
+                        kfree(tmp);
+                        return 0;
+                }
+                r = &tmp->next;
+        }
+
+	spin_unlock_bh(&ipddp_route_lock);
+        return -ENOENT;
+}
+
+/*
+ * Find a routing entry, we only return a FULL match
+ */
+static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt)
+{
+        struct ipddp_route *f;
+
+        for(f = ipddp_route_list; f != NULL; f = f->next)
+        {
+                if(f->ip == rt->ip &&
+		   f->at.s_net == rt->at.s_net &&
+		   f->at.s_node == rt->at.s_node)
+                        return f;
+        }
+
+        return NULL;
+}
+
+static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+        struct ipddp_route __user *rt = ifr->ifr_data;
+        struct ipddp_route rcp, rcp2, *rp;
+
+        if(!capable(CAP_NET_ADMIN))
+                return -EPERM;
+
+	if(copy_from_user(&rcp, rt, sizeof(rcp)))
+		return -EFAULT;
+
+        switch(cmd)
+        {
+		case SIOCADDIPDDPRT:
+                        return ipddp_create(&rcp);
+
+                case SIOCFINDIPDDPRT:
+			spin_lock_bh(&ipddp_route_lock);
+			rp = __ipddp_find_route(&rcp);
+			if (rp)
+				memcpy(&rcp2, rp, sizeof(rcp2));
+			spin_unlock_bh(&ipddp_route_lock);
+
+			if (rp) {
+				if (copy_to_user(rt, &rcp2,
+						 sizeof(struct ipddp_route)))
+					return -EFAULT;
+				return 0;
+			} else
+				return -ENOENT;
+
+                case SIOCDELIPDDPRT:
+                        return ipddp_delete(&rcp);
+
+                default:
+                        return -EINVAL;
+        }
+}
+
+static struct net_device *dev_ipddp;
+
+MODULE_LICENSE("GPL");
+module_param(ipddp_mode, int, 0);
+
+static int __init ipddp_init_module(void)
+{
+	dev_ipddp = ipddp_init();
+        if (IS_ERR(dev_ipddp))
+                return PTR_ERR(dev_ipddp);
+	return 0;
+}
+
+static void __exit ipddp_cleanup_module(void)
+{
+        struct ipddp_route *p;
+
+	unregister_netdev(dev_ipddp);
+        free_netdev(dev_ipddp);
+
+        while (ipddp_route_list) {
+                p = ipddp_route_list->next;
+                kfree(ipddp_route_list);
+                ipddp_route_list = p;
+        }
+}
+
+module_init(ipddp_init_module);
+module_exit(ipddp_cleanup_module);
diff --git a/drivers/staging/appletalk/ipddp.h b/drivers/staging/appletalk/ipddp.h
new file mode 100644
index 000000000000..531519da99a3
--- /dev/null
+++ b/drivers/staging/appletalk/ipddp.h
@@ -0,0 +1,27 @@
+/*
+ *	ipddp.h: Header for IP-over-DDP driver for Linux.
+ */
+
+#ifndef __LINUX_IPDDP_H
+#define __LINUX_IPDDP_H
+
+#ifdef __KERNEL__
+
+#define SIOCADDIPDDPRT   (SIOCDEVPRIVATE)
+#define SIOCDELIPDDPRT   (SIOCDEVPRIVATE+1)
+#define SIOCFINDIPDDPRT  (SIOCDEVPRIVATE+2)
+
+struct ipddp_route
+{
+        struct net_device *dev;             /* Carrier device */
+        __be32 ip;                       /* IP address */
+        struct atalk_addr at;              /* Gateway appletalk address */
+        int flags;
+        struct ipddp_route *next;
+};
+
+#define IPDDP_ENCAP	1
+#define IPDDP_DECAP	2
+
+#endif	/* __KERNEL__ */
+#endif	/* __LINUX_IPDDP_H */
diff --git a/drivers/staging/appletalk/ltpc.c b/drivers/staging/appletalk/ltpc.c
new file mode 100644
index 000000000000..60caf892695e
--- /dev/null
+++ b/drivers/staging/appletalk/ltpc.c
@@ -0,0 +1,1288 @@
+/***    ltpc.c -- a driver for the LocalTalk PC card.
+ *
+ *      Copyright (c) 1995,1996 Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *
+ *      This software may be used and distributed according to the terms
+ *      of the GNU General Public License, incorporated herein by reference.
+ *
+ *      This is ALPHA code at best.  It may not work for you.  It may
+ *      damage your equipment.  It may damage your relations with other
+ *      users of your network.  Use it at your own risk!
+ *
+ *      Based in part on:
+ *      skeleton.c      by Donald Becker
+ *      dummy.c         by Nick Holloway and Alan Cox
+ *      loopback.c      by Ross Biro, Fred van Kampen, Donald Becker
+ *      the netatalk source code (UMICH)
+ *      lots of work on the card...
+ *
+ *      I do not have access to the (proprietary) SDK that goes with the card.
+ *      If you do, I don't want to know about it, and you can probably write
+ *      a better driver yourself anyway.  This does mean that the pieces that
+ *      talk to the card are guesswork on my part, so use at your own risk!
+ *
+ *      This is my first try at writing Linux networking code, and is also
+ *      guesswork.  Again, use at your own risk!  (Although on this part, I'd
+ *      welcome suggestions)
+ *
+ *      This is a loadable kernel module which seems to work at my site
+ *      consisting of a 1.2.13 linux box running netatalk 1.3.3, and with
+ *      the kernel support from 1.3.3b2 including patches routing.patch
+ *      and ddp.disappears.from.chooser.  In order to run it, you will need
+ *      to patch ddp.c and aarp.c in the kernel, but only a little...
+ *
+ *      I'm fairly confident that while this is arguably badly written, the
+ *      problems that people experience will be "higher level", that is, with
+ *      complications in the netatalk code.  The driver itself doesn't do
+ *      anything terribly complicated -- it pretends to be an ether device
+ *      as far as netatalk is concerned, strips the DDP data out of the ether
+ *      frame and builds a LLAP packet to send out the card.  In the other
+ *      direction, it receives LLAP frames from the card and builds a fake
+ *      ether packet that it then tosses up to the networking code.  You can
+ *      argue (correctly) that this is an ugly way to do things, but it
+ *      requires a minimal amount of fooling with the code in ddp.c and aarp.c.
+ *
+ *      The card will do a lot more than is used here -- I *think* it has the
+ *      layers up through ATP.  Even if you knew how that part works (which I
+ *      don't) it would be a big job to carve up the kernel ddp code to insert
+ *      things at a higher level, and probably a bad idea...
+ *
+ *      There are a number of other cards that do LocalTalk on the PC.  If
+ *      nobody finds any insurmountable (at the netatalk level) problems
+ *      here, this driver should encourage people to put some work into the
+ *      other cards (some of which I gather are still commercially available)
+ *      and also to put hooks for LocalTalk into the official ddp code.
+ *
+ *      I welcome comments and suggestions.  This is my first try at Linux
+ *      networking stuff, and there are probably lots of things that I did
+ *      suboptimally.  
+ *
+ ***/
+
+/***
+ *
+ * $Log: ltpc.c,v $
+ * Revision 1.1.2.1  2000/03/01 05:35:07  jgarzik
+ * at and tr cleanup
+ *
+ * Revision 1.8  1997/01/28 05:44:54  bradford
+ * Clean up for non-module a little.
+ * Hacked about a bit to clean things up - Alan Cox 
+ * Probably broken it from the origina 1.8
+ *
+
+ * 1998/11/09: David Huggins-Daines <dhd@debian.org>
+ * Cleaned up the initialization code to use the standard autoirq methods,
+   and to probe for things in the standard order of i/o, irq, dma.  This
+   removes the "reset the reset" hack, because I couldn't figure out an
+   easy way to get the card to trigger an interrupt after it.
+ * Added support for passing configuration parameters on the kernel command
+   line and through insmod
+ * Changed the device name from "ltalk0" to "lt0", both to conform with the
+   other localtalk driver, and to clear up the inconsistency between the
+   module and the non-module versions of the driver :-)
+ * Added a bunch of comments (I was going to make some enums for the state
+   codes and the register offsets, but I'm still not sure exactly what their
+   semantics are)
+ * Don't poll anymore in interrupt-driven mode
+ * It seems to work as a module now (as of 2.1.127), but I don't think
+   I'm responsible for that...
+
+ *
+ * Revision 1.7  1996/12/12 03:42:33  bradford
+ * DMA alloc cribbed from 3c505.c.
+ *
+ * Revision 1.6  1996/12/12 03:18:58  bradford
+ * Added virt_to_bus; works in 2.1.13.
+ *
+ * Revision 1.5  1996/12/12 03:13:22  root
+ * xmitQel initialization -- think through better though.
+ *
+ * Revision 1.4  1996/06/18 14:55:55  root
+ * Change names to ltpc. Tabs. Took a shot at dma alloc,
+ * although more needs to be done eventually.
+ *
+ * Revision 1.3  1996/05/22 14:59:39  root
+ * Change dev->open, dev->close to track dummy.c in 1.99.(around 7)
+ *
+ * Revision 1.2  1996/05/22 14:58:24  root
+ * Change tabs mostly.
+ *
+ * Revision 1.1  1996/04/23 04:45:09  root
+ * Initial revision
+ *
+ * Revision 0.16  1996/03/05 15:59:56  root
+ * Change ARPHRD_LOCALTLK definition to the "real" one.
+ *
+ * Revision 0.15  1996/03/05 06:28:30  root
+ * Changes for kernel 1.3.70.  Still need a few patches to kernel, but
+ * it's getting closer.
+ *
+ * Revision 0.14  1996/02/25 17:38:32  root
+ * More cleanups.  Removed query to card on get_stats.
+ *
+ * Revision 0.13  1996/02/21  16:27:40  root
+ * Refix debug_print_skb.  Fix mac.raw gotcha that appeared in 1.3.65.
+ * Clean up receive code a little.
+ *
+ * Revision 0.12  1996/02/19  16:34:53  root
+ * Fix debug_print_skb.  Kludge outgoing snet to 0 when using startup
+ * range.  Change debug to mask: 1 for verbose, 2 for higher level stuff
+ * including packet printing, 4 for lower level (card i/o) stuff.
+ *
+ * Revision 0.11  1996/02/12  15:53:38  root
+ * Added router sends (requires new aarp.c patch)
+ *
+ * Revision 0.10  1996/02/11  00:19:35  root
+ * Change source LTALK_LOGGING debug switch to insmod ... debug=2.
+ *
+ * Revision 0.9  1996/02/10  23:59:35  root
+ * Fixed those fixes for 1.2 -- DANGER!  The at.h that comes with netatalk
+ * has a *different* definition of struct sockaddr_at than the Linux kernel
+ * does.  This is an "insidious and invidious" bug...
+ * (Actually the preceding comment is false -- it's the atalk.h in the
+ * ancient atalk-0.06 that's the problem)
+ *
+ * Revision 0.8  1996/02/10 19:09:00  root
+ * Merge 1.3 changes.  Tested OK under 1.3.60.
+ *
+ * Revision 0.7  1996/02/10 17:56:56  root
+ * Added debug=1 parameter on insmod for debugging prints.  Tried
+ * to fix timer unload on rmmod, but I don't think that's the problem.
+ *
+ * Revision 0.6  1995/12/31  19:01:09  root
+ * Clean up rmmod, irq comments per feedback from Corin Anderson (Thanks Corey!)
+ * Clean up initial probing -- sometimes the card wakes up latched in reset.
+ *
+ * Revision 0.5  1995/12/22  06:03:44  root
+ * Added comments in front and cleaned up a bit.
+ * This version sent out to people.
+ *
+ * Revision 0.4  1995/12/18  03:46:44  root
+ * Return shortDDP to longDDP fake to 0/0.  Added command structs.
+ *
+ ***/
+
+/* ltpc jumpers are:
+*
+*	Interrupts -- set at most one.  If none are set, the driver uses
+*	polled mode.  Because the card was developed in the XT era, the
+*	original documentation refers to IRQ2.  Since you'll be running
+*	this on an AT (or later) class machine, that really means IRQ9.
+*
+*	SW1	IRQ 4
+*	SW2	IRQ 3
+*	SW3	IRQ 9 (2 in original card documentation only applies to XT)
+*
+*
+*	DMA -- choose DMA 1 or 3, and set both corresponding switches.
+*
+*	SW4	DMA 3
+*	SW5	DMA 1
+*	SW6	DMA 3
+*	SW7	DMA 1
+*
+*
+*	I/O address -- choose one.  
+*
+*	SW8	220 / 240
+*/
+
+/*	To have some stuff logged, do 
+*	insmod ltpc.o debug=1
+*
+*	For a whole bunch of stuff, use higher numbers.
+*
+*	The default is 0, i.e. no messages except for the probe results.
+*/
+
+/* insmod-tweakable variables */
+static int debug;
+#define DEBUG_VERBOSE 1
+#define DEBUG_UPPER 2
+#define DEBUG_LOWER 4
+
+static int io;
+static int irq;
+static int dma;
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/spinlock.h>
+#include <linux/in.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/if_ltalk.h>
+#include <linux/delay.h>
+#include <linux/timer.h>
+#include <linux/bitops.h>
+#include <linux/gfp.h>
+
+#include <asm/system.h>
+#include <asm/dma.h>
+#include <asm/io.h>
+
+/* our stuff */
+#include "atalk.h"
+#include "ltpc.h"
+
+static DEFINE_SPINLOCK(txqueue_lock);
+static DEFINE_SPINLOCK(mbox_lock);
+
+/* function prototypes */
+static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
+	void *dbuf, int dbuflen);
+static int sendup_buffer (struct net_device *dev);
+
+/* Dma Memory related stuff, cribbed directly from 3c505.c */
+
+static unsigned long dma_mem_alloc(int size)
+{
+        int order = get_order(size);
+
+        return __get_dma_pages(GFP_KERNEL, order);
+}
+
+/* DMA data buffer, DMA command buffer */
+static unsigned char *ltdmabuf;
+static unsigned char *ltdmacbuf;
+
+/* private struct, holds our appletalk address */
+
+struct ltpc_private
+{
+	struct atalk_addr my_addr;
+};
+
+/* transmit queue element struct */
+
+struct xmitQel {
+	struct xmitQel *next;
+	/* command buffer */
+	unsigned char *cbuf;
+	short cbuflen;
+	/* data buffer */
+	unsigned char *dbuf;
+	short dbuflen;
+	unsigned char QWrite;	/* read or write data */
+	unsigned char mailbox;
+};
+
+/* the transmit queue itself */
+
+static struct xmitQel *xmQhd, *xmQtl;
+
+static void enQ(struct xmitQel *qel)
+{
+	unsigned long flags;
+	qel->next = NULL;
+	
+	spin_lock_irqsave(&txqueue_lock, flags);
+	if (xmQtl) {
+		xmQtl->next = qel;
+	} else {
+		xmQhd = qel;
+	}
+	xmQtl = qel;
+	spin_unlock_irqrestore(&txqueue_lock, flags);
+
+	if (debug & DEBUG_LOWER)
+		printk("enqueued a 0x%02x command\n",qel->cbuf[0]);
+}
+
+static struct xmitQel *deQ(void)
+{
+	unsigned long flags;
+	int i;
+	struct xmitQel *qel=NULL;
+	
+	spin_lock_irqsave(&txqueue_lock, flags);
+	if (xmQhd) {
+		qel = xmQhd;
+		xmQhd = qel->next;
+		if(!xmQhd) xmQtl = NULL;
+	}
+	spin_unlock_irqrestore(&txqueue_lock, flags);
+
+	if ((debug & DEBUG_LOWER) && qel) {
+		int n;
+		printk(KERN_DEBUG "ltpc: dequeued command ");
+		n = qel->cbuflen;
+		if (n>100) n=100;
+		for(i=0;i<n;i++) printk("%02x ",qel->cbuf[i]);
+		printk("\n");
+	}
+
+	return qel;
+}
+
+/* and... the queue elements we'll be using */
+static struct xmitQel qels[16];
+
+/* and their corresponding mailboxes */
+static unsigned char mailbox[16];
+static unsigned char mboxinuse[16] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};
+
+static int wait_timeout(struct net_device *dev, int c)
+{
+	/* returns true if it stayed c */
+	/* this uses base+6, but it's ok */
+	int i;
+
+	/* twenty second or so total */
+
+	for(i=0;i<200000;i++) {
+		if ( c != inb_p(dev->base_addr+6) ) return 0;
+		udelay(100);
+	}
+	return 1; /* timed out */
+}
+
+/* get the first free mailbox */
+
+static int getmbox(void)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&mbox_lock, flags);
+	for(i=1;i<16;i++) if(!mboxinuse[i]) {
+		mboxinuse[i]=1;
+		spin_unlock_irqrestore(&mbox_lock, flags);
+		return i;
+	}
+	spin_unlock_irqrestore(&mbox_lock, flags);
+	return 0;
+}
+
+/* read a command from the card */
+static void handlefc(struct net_device *dev)
+{
+	/* called *only* from idle, non-reentrant */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
+	set_dma_count(dma,50);
+	enable_dma(dma);
+	release_dma_lock(flags);
+
+	inb_p(base+3);
+	inb_p(base+2);
+
+	if ( wait_timeout(dev,0xfc) ) printk("timed out in handlefc\n");
+}
+
+/* read data from the card */
+static void handlefd(struct net_device *dev)
+{
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,800);
+	enable_dma(dma);
+	release_dma_lock(flags);
+
+	inb_p(base+3);
+	inb_p(base+2);
+
+	if ( wait_timeout(dev,0xfd) ) printk("timed out in handlefd\n");
+	sendup_buffer(dev);
+} 
+
+static void handlewrite(struct net_device *dev)
+{
+	/* called *only* from idle, non-reentrant */
+	/* on entry, 0xfb and ltdmabuf holds data */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+	
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_WRITE);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,800);
+	enable_dma(dma);
+	release_dma_lock(flags);
+	
+	inb_p(base+3);
+	inb_p(base+2);
+
+	if ( wait_timeout(dev,0xfb) ) {
+		flags=claim_dma_lock();
+		printk("timed out in handlewrite, dma res %d\n",
+			get_dma_residue(dev->dma) );
+		release_dma_lock(flags);
+	}
+}
+
+static void handleread(struct net_device *dev)
+{
+	/* on entry, 0xfb */
+	/* on exit, ltdmabuf holds data */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+	
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,800);
+	enable_dma(dma);
+	release_dma_lock(flags);
+
+	inb_p(base+3);
+	inb_p(base+2);
+	if ( wait_timeout(dev,0xfb) ) printk("timed out in handleread\n");
+}
+
+static void handlecommand(struct net_device *dev)
+{
+	/* on entry, 0xfa and ltdmacbuf holds command */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_WRITE);
+	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
+	set_dma_count(dma,50);
+	enable_dma(dma);
+	release_dma_lock(flags);
+	inb_p(base+3);
+	inb_p(base+2);
+	if ( wait_timeout(dev,0xfa) ) printk("timed out in handlecommand\n");
+} 
+
+/* ready made command for getting the result from the card */
+static unsigned char rescbuf[2] = {LT_GETRESULT,0};
+static unsigned char resdbuf[2];
+
+static int QInIdle;
+
+/* idle expects to be called with the IRQ line high -- either because of
+ * an interrupt, or because the line is tri-stated
+ */
+
+static void idle(struct net_device *dev)
+{
+	unsigned long flags;
+	int state;
+	/* FIXME This is initialized to shut the warning up, but I need to
+	 * think this through again.
+	 */
+	struct xmitQel *q = NULL;
+	int oops;
+	int i;
+	int base = dev->base_addr;
+
+	spin_lock_irqsave(&txqueue_lock, flags);
+	if(QInIdle) {
+		spin_unlock_irqrestore(&txqueue_lock, flags);
+		return;
+	}
+	QInIdle = 1;
+	spin_unlock_irqrestore(&txqueue_lock, flags);
+
+	/* this tri-states the IRQ line */
+	(void) inb_p(base+6);
+
+	oops = 100;
+
+loop:
+	if (0>oops--) { 
+		printk("idle: looped too many times\n");
+		goto done;
+	}
+
+	state = inb_p(base+6);
+	if (state != inb_p(base+6)) goto loop;
+
+	switch(state) {
+		case 0xfc:
+			/* incoming command */
+			if (debug & DEBUG_LOWER) printk("idle: fc\n");
+			handlefc(dev); 
+			break;
+		case 0xfd:
+			/* incoming data */
+			if(debug & DEBUG_LOWER) printk("idle: fd\n");
+			handlefd(dev); 
+			break;
+		case 0xf9:
+			/* result ready */
+			if (debug & DEBUG_LOWER) printk("idle: f9\n");
+			if(!mboxinuse[0]) {
+				mboxinuse[0] = 1;
+				qels[0].cbuf = rescbuf;
+				qels[0].cbuflen = 2;
+				qels[0].dbuf = resdbuf;
+				qels[0].dbuflen = 2;
+				qels[0].QWrite = 0;
+				qels[0].mailbox = 0;
+				enQ(&qels[0]);
+			}
+			inb_p(dev->base_addr+1);
+			inb_p(dev->base_addr+0);
+			if( wait_timeout(dev,0xf9) )
+				printk("timed out idle f9\n");
+			break;
+		case 0xf8:
+			/* ?? */
+			if (xmQhd) {
+				inb_p(dev->base_addr+1);
+				inb_p(dev->base_addr+0);
+				if(wait_timeout(dev,0xf8) )
+					printk("timed out idle f8\n");
+			} else {
+				goto done;
+			}
+			break;
+		case 0xfa:
+			/* waiting for command */
+			if(debug & DEBUG_LOWER) printk("idle: fa\n");
+			if (xmQhd) {
+				q=deQ();
+				memcpy(ltdmacbuf,q->cbuf,q->cbuflen);
+				ltdmacbuf[1] = q->mailbox;
+				if (debug>1) { 
+					int n;
+					printk("ltpc: sent command     ");
+					n = q->cbuflen;
+					if (n>100) n=100;
+					for(i=0;i<n;i++)
+						printk("%02x ",ltdmacbuf[i]);
+					printk("\n");
+				}
+				handlecommand(dev);
+					if(0xfa==inb_p(base+6)) {
+						/* we timed out, so return */
+						goto done;
+					} 
+			} else {
+				/* we don't seem to have a command */
+				if (!mboxinuse[0]) {
+					mboxinuse[0] = 1;
+					qels[0].cbuf = rescbuf;
+					qels[0].cbuflen = 2;
+					qels[0].dbuf = resdbuf;
+					qels[0].dbuflen = 2;
+					qels[0].QWrite = 0;
+					qels[0].mailbox = 0;
+					enQ(&qels[0]);
+				} else {
+					printk("trouble: response command already queued\n");
+					goto done;
+				}
+			} 
+			break;
+		case 0Xfb:
+			/* data transfer ready */
+			if(debug & DEBUG_LOWER) printk("idle: fb\n");
+			if(q->QWrite) {
+				memcpy(ltdmabuf,q->dbuf,q->dbuflen);
+				handlewrite(dev);
+			} else {
+				handleread(dev);
+				/* non-zero mailbox numbers are for
+				   commmands, 0 is for GETRESULT
+				   requests */
+				if(q->mailbox) {
+					memcpy(q->dbuf,ltdmabuf,q->dbuflen);
+				} else { 
+					/* this was a result */
+					mailbox[ 0x0f & ltdmabuf[0] ] = ltdmabuf[1];
+					mboxinuse[0]=0;
+				}
+			}
+			break;
+	}
+	goto loop;
+
+done:
+	QInIdle=0;
+
+	/* now set the interrupts back as appropriate */
+	/* the first read takes it out of tri-state (but still high) */
+	/* the second resets it */
+	/* note that after this point, any read of base+6 will
+	   trigger an interrupt */
+
+	if (dev->irq) {
+		inb_p(base+7);
+		inb_p(base+7);
+	}
+}
+
+
+static int do_write(struct net_device *dev, void *cbuf, int cbuflen,
+	void *dbuf, int dbuflen)
+{
+
+	int i = getmbox();
+	int ret;
+
+	if(i) {
+		qels[i].cbuf = (unsigned char *) cbuf;
+		qels[i].cbuflen = cbuflen;
+		qels[i].dbuf = (unsigned char *) dbuf;
+		qels[i].dbuflen = dbuflen;
+		qels[i].QWrite = 1;
+		qels[i].mailbox = i;  /* this should be initted rather */
+		enQ(&qels[i]);
+		idle(dev);
+		ret = mailbox[i];
+		mboxinuse[i]=0;
+		return ret;
+	}
+	printk("ltpc: could not allocate mbox\n");
+	return -1;
+}
+
+static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
+	void *dbuf, int dbuflen)
+{
+
+	int i = getmbox();
+	int ret;
+
+	if(i) {
+		qels[i].cbuf = (unsigned char *) cbuf;
+		qels[i].cbuflen = cbuflen;
+		qels[i].dbuf = (unsigned char *) dbuf;
+		qels[i].dbuflen = dbuflen;
+		qels[i].QWrite = 0;
+		qels[i].mailbox = i;  /* this should be initted rather */
+		enQ(&qels[i]);
+		idle(dev);
+		ret = mailbox[i];
+		mboxinuse[i]=0;
+		return ret;
+	}
+	printk("ltpc: could not allocate mbox\n");
+	return -1;
+}
+
+/* end of idle handlers -- what should be seen is do_read, do_write */
+
+static struct timer_list ltpc_timer;
+
+static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev);
+
+static int read_30 ( struct net_device *dev)
+{
+	lt_command c;
+	c.getflags.command = LT_GETFLAGS;
+	return do_read(dev, &c, sizeof(c.getflags),&c,0);
+}
+
+static int set_30 (struct net_device *dev,int x)
+{
+	lt_command c;
+	c.setflags.command = LT_SETFLAGS;
+	c.setflags.flags = x;
+	return do_write(dev, &c, sizeof(c.setflags),&c,0);
+}
+
+/* LLAP to DDP translation */
+
+static int sendup_buffer (struct net_device *dev)
+{
+	/* on entry, command is in ltdmacbuf, data in ltdmabuf */
+	/* called from idle, non-reentrant */
+
+	int dnode, snode, llaptype, len; 
+	int sklen;
+	struct sk_buff *skb;
+	struct lt_rcvlap *ltc = (struct lt_rcvlap *) ltdmacbuf;
+
+	if (ltc->command != LT_RCVLAP) {
+		printk("unknown command 0x%02x from ltpc card\n",ltc->command);
+		return -1;
+	}
+	dnode = ltc->dnode;
+	snode = ltc->snode;
+	llaptype = ltc->laptype;
+	len = ltc->length; 
+
+	sklen = len;
+	if (llaptype == 1) 
+		sklen += 8;  /* correct for short ddp */
+	if(sklen > 800) {
+		printk(KERN_INFO "%s: nonsense length in ltpc command 0x14: 0x%08x\n",
+			dev->name,sklen);
+		return -1;
+	}
+
+	if ( (llaptype==0) || (llaptype>2) ) {
+		printk(KERN_INFO "%s: unknown LLAP type: %d\n",dev->name,llaptype);
+		return -1;
+	}
+
+
+	skb = dev_alloc_skb(3+sklen);
+	if (skb == NULL) 
+	{
+		printk("%s: dropping packet due to memory squeeze.\n",
+			dev->name);
+		return -1;
+	}
+	skb->dev = dev;
+
+	if (sklen > len)
+		skb_reserve(skb,8);
+	skb_put(skb,len+3);
+	skb->protocol = htons(ETH_P_LOCALTALK);
+	/* add LLAP header */
+	skb->data[0] = dnode;
+	skb->data[1] = snode;
+	skb->data[2] = llaptype;
+	skb_reset_mac_header(skb);	/* save pointer to llap header */
+	skb_pull(skb,3);
+
+	/* copy ddp(s,e)hdr + contents */
+	skb_copy_to_linear_data(skb, ltdmabuf, len);
+
+	skb_reset_transport_header(skb);
+
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += skb->len;
+
+	/* toss it onwards */
+	netif_rx(skb);
+	return 0;
+}
+
+/* the handler for the board interrupt */
+ 
+static irqreturn_t
+ltpc_interrupt(int irq, void *dev_id)
+{
+	struct net_device *dev = dev_id;
+
+	if (dev==NULL) {
+		printk("ltpc_interrupt: unknown device.\n");
+		return IRQ_NONE;
+	}
+
+	inb_p(dev->base_addr+6);  /* disable further interrupts from board */
+
+	idle(dev); /* handle whatever is coming in */
+ 
+	/* idle re-enables interrupts from board */ 
+
+	return IRQ_HANDLED;
+}
+
+/***
+ *
+ *    The ioctls that the driver responds to are:
+ *
+ *    SIOCSIFADDR -- do probe using the passed node hint.
+ *    SIOCGIFADDR -- return net, node.
+ *
+ *    some of this stuff should be done elsewhere.
+ *
+ ***/
+
+static int ltpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	struct sockaddr_at *sa = (struct sockaddr_at *) &ifr->ifr_addr;
+	/* we'll keep the localtalk node address in dev->pa_addr */
+	struct ltpc_private *ltpc_priv = netdev_priv(dev);
+	struct atalk_addr *aa = &ltpc_priv->my_addr;
+	struct lt_init c;
+	int ltflags;
+
+	if(debug & DEBUG_VERBOSE) printk("ltpc_ioctl called\n");
+
+	switch(cmd) {
+		case SIOCSIFADDR:
+
+			aa->s_net  = sa->sat_addr.s_net;
+      
+			/* this does the probe and returns the node addr */
+			c.command = LT_INIT;
+			c.hint = sa->sat_addr.s_node;
+
+			aa->s_node = do_read(dev,&c,sizeof(c),&c,0);
+
+			/* get all llap frames raw */
+			ltflags = read_30(dev);
+			ltflags |= LT_FLAG_ALLLAP;
+			set_30 (dev,ltflags);  
+
+			dev->broadcast[0] = 0xFF;
+			dev->dev_addr[0] = aa->s_node;
+
+			dev->addr_len=1;
+   
+			return 0;
+
+		case SIOCGIFADDR:
+
+			sa->sat_addr.s_net = aa->s_net;
+			sa->sat_addr.s_node = aa->s_node;
+
+			return 0;
+
+		default: 
+			return -EINVAL;
+	}
+}
+
+static void set_multicast_list(struct net_device *dev)
+{
+	/* This needs to be present to keep netatalk happy. */
+	/* Actually netatalk needs fixing! */
+}
+
+static int ltpc_poll_counter;
+
+static void ltpc_poll(unsigned long l)
+{
+	struct net_device *dev = (struct net_device *) l;
+
+	del_timer(&ltpc_timer);
+
+	if(debug & DEBUG_VERBOSE) {
+		if (!ltpc_poll_counter) {
+			ltpc_poll_counter = 50;
+			printk("ltpc poll is alive\n");
+		}
+		ltpc_poll_counter--;
+	}
+  
+	if (!dev)
+		return;  /* we've been downed */
+
+	/* poll 20 times per second */
+	idle(dev);
+	ltpc_timer.expires = jiffies + HZ/20;
+	
+	add_timer(&ltpc_timer);
+}
+
+/* DDP to LLAP translation */
+
+static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	/* in kernel 1.3.xx, on entry skb->data points to ddp header,
+	 * and skb->len is the length of the ddp data + ddp header
+	 */
+	int i;
+	struct lt_sendlap cbuf;
+	unsigned char *hdr;
+
+	cbuf.command = LT_SENDLAP;
+	cbuf.dnode = skb->data[0];
+	cbuf.laptype = skb->data[2];
+	skb_pull(skb,3);	/* skip past LLAP header */
+	cbuf.length = skb->len;	/* this is host order */
+	skb_reset_transport_header(skb);
+
+	if(debug & DEBUG_UPPER) {
+		printk("command ");
+		for(i=0;i<6;i++)
+			printk("%02x ",((unsigned char *)&cbuf)[i]);
+		printk("\n");
+	}
+
+	hdr = skb_transport_header(skb);
+	do_write(dev, &cbuf, sizeof(cbuf), hdr, skb->len);
+
+	if(debug & DEBUG_UPPER) {
+		printk("sent %d ddp bytes\n",skb->len);
+		for (i = 0; i < skb->len; i++)
+			printk("%02x ", hdr[i]);
+		printk("\n");
+	}
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+/* initialization stuff */
+  
+static int __init ltpc_probe_dma(int base, int dma)
+{
+	int want = (dma == 3) ? 2 : (dma == 1) ? 1 : 3;
+  	unsigned long timeout;
+  	unsigned long f;
+  
+  	if (want & 1) {
+		if (request_dma(1,"ltpc")) {
+			want &= ~1;
+		} else {
+			f=claim_dma_lock();
+			disable_dma(1);
+			clear_dma_ff(1);
+			set_dma_mode(1,DMA_MODE_WRITE);
+			set_dma_addr(1,virt_to_bus(ltdmabuf));
+			set_dma_count(1,sizeof(struct lt_mem));
+			enable_dma(1);
+			release_dma_lock(f);
+		}
+	}
+	if (want & 2) {
+		if (request_dma(3,"ltpc")) {
+			want &= ~2;
+		} else {
+			f=claim_dma_lock();
+			disable_dma(3);
+			clear_dma_ff(3);
+			set_dma_mode(3,DMA_MODE_WRITE);
+			set_dma_addr(3,virt_to_bus(ltdmabuf));
+			set_dma_count(3,sizeof(struct lt_mem));
+			enable_dma(3);
+			release_dma_lock(f);
+		}
+	}
+	/* set up request */
+
+	/* FIXME -- do timings better! */
+
+	ltdmabuf[0] = LT_READMEM;
+	ltdmabuf[1] = 1;  /* mailbox */
+	ltdmabuf[2] = 0; ltdmabuf[3] = 0;  /* address */
+	ltdmabuf[4] = 0; ltdmabuf[5] = 1;  /* read 0x0100 bytes */
+	ltdmabuf[6] = 0; /* dunno if this is necessary */
+
+	inb_p(io+1);
+	inb_p(io+0);
+	timeout = jiffies+100*HZ/100;
+	while(time_before(jiffies, timeout)) {
+		if ( 0xfa == inb_p(io+6) ) break;
+	}
+
+	inb_p(io+3);
+	inb_p(io+2);
+	while(time_before(jiffies, timeout)) {
+		if ( 0xfb == inb_p(io+6) ) break;
+	}
+
+	/* release the other dma channel (if we opened both of them) */
+
+	if ((want & 2) && (get_dma_residue(3)==sizeof(struct lt_mem))) {
+		want &= ~2;
+		free_dma(3);
+	}
+
+	if ((want & 1) && (get_dma_residue(1)==sizeof(struct lt_mem))) {
+		want &= ~1;
+		free_dma(1);
+	}
+
+	if (!want)
+		return 0;
+
+	return (want & 2) ? 3 : 1;
+}
+
+static const struct net_device_ops ltpc_netdev = {
+	.ndo_start_xmit		= ltpc_xmit,
+	.ndo_do_ioctl		= ltpc_ioctl,
+	.ndo_set_multicast_list = set_multicast_list,
+};
+
+struct net_device * __init ltpc_probe(void)
+{
+	struct net_device *dev;
+	int err = -ENOMEM;
+	int x=0,y=0;
+	int autoirq;
+	unsigned long f;
+	unsigned long timeout;
+
+	dev = alloc_ltalkdev(sizeof(struct ltpc_private));
+	if (!dev)
+		goto out;
+
+	/* probe for the I/O port address */
+	
+	if (io != 0x240 && request_region(0x220,8,"ltpc")) {
+		x = inb_p(0x220+6);
+		if ( (x!=0xff) && (x>=0xf0) ) {
+			io = 0x220;
+			goto got_port;
+		}
+		release_region(0x220,8);
+	}
+	if (io != 0x220 && request_region(0x240,8,"ltpc")) {
+		y = inb_p(0x240+6);
+		if ( (y!=0xff) && (y>=0xf0) ){ 
+			io = 0x240;
+			goto got_port;
+		}
+		release_region(0x240,8);
+	} 
+
+	/* give up in despair */
+	printk(KERN_ERR "LocalTalk card not found; 220 = %02x, 240 = %02x.\n", x,y);
+	err = -ENODEV;
+	goto out1;
+
+ got_port:
+	/* probe for the IRQ line */
+	if (irq < 2) {
+		unsigned long irq_mask;
+
+		irq_mask = probe_irq_on();
+		/* reset the interrupt line */
+		inb_p(io+7);
+		inb_p(io+7);
+		/* trigger an interrupt (I hope) */
+		inb_p(io+6);
+		mdelay(2);
+		autoirq = probe_irq_off(irq_mask);
+
+		if (autoirq == 0) {
+			printk(KERN_ERR "ltpc: probe at %#x failed to detect IRQ line.\n", io);
+		} else {
+			irq = autoirq;
+		}
+	}
+
+	/* allocate a DMA buffer */
+	ltdmabuf = (unsigned char *) dma_mem_alloc(1000);
+	if (!ltdmabuf) {
+		printk(KERN_ERR "ltpc: mem alloc failed\n");
+		err = -ENOMEM;
+		goto out2;
+	}
+
+	ltdmacbuf = &ltdmabuf[800];
+
+	if(debug & DEBUG_VERBOSE) {
+		printk("ltdmabuf pointer %08lx\n",(unsigned long) ltdmabuf);
+	}
+
+	/* reset the card */
+
+	inb_p(io+1);
+	inb_p(io+3);
+
+	msleep(20);
+
+	inb_p(io+0);
+	inb_p(io+2);
+	inb_p(io+7); /* clear reset */
+	inb_p(io+4); 
+	inb_p(io+5);
+	inb_p(io+5); /* enable dma */
+	inb_p(io+6); /* tri-state interrupt line */
+
+	ssleep(1);
+	
+	/* now, figure out which dma channel we're using, unless it's
+	   already been specified */
+	/* well, 0 is a legal DMA channel, but the LTPC card doesn't
+	   use it... */
+	dma = ltpc_probe_dma(io, dma);
+	if (!dma) {  /* no dma channel */
+		printk(KERN_ERR "No DMA channel found on ltpc card.\n");
+		err = -ENODEV;
+		goto out3;
+	}
+
+	/* print out friendly message */
+	if(irq)
+		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, IR%d, DMA%d.\n",io,irq,dma);
+	else
+		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, DMA%d.  Using polled mode.\n",io,dma);
+
+	dev->netdev_ops = &ltpc_netdev;
+	dev->base_addr = io;
+	dev->irq = irq;
+	dev->dma = dma;
+
+	/* the card will want to send a result at this point */
+	/* (I think... leaving out this part makes the kernel crash,
+           so I put it back in...) */
+
+	f=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,0x100);
+	enable_dma(dma);
+	release_dma_lock(f);
+
+	(void) inb_p(io+3);
+	(void) inb_p(io+2);
+	timeout = jiffies+100*HZ/100;
+
+	while(time_before(jiffies, timeout)) {
+		if( 0xf9 == inb_p(io+6))
+			break;
+		schedule();
+	}
+
+	if(debug & DEBUG_VERBOSE) {
+		printk("setting up timer and irq\n");
+	}
+
+	/* grab it and don't let go :-) */
+	if (irq && request_irq( irq, ltpc_interrupt, 0, "ltpc", dev) >= 0)
+	{
+		(void) inb_p(io+7);  /* enable interrupts from board */
+		(void) inb_p(io+7);  /* and reset irq line */
+	} else {
+		if( irq )
+			printk(KERN_ERR "ltpc: IRQ already in use, using polled mode.\n");
+		dev->irq = 0;
+		/* polled mode -- 20 times per second */
+		/* this is really, really slow... should it poll more often? */
+		init_timer(&ltpc_timer);
+		ltpc_timer.function=ltpc_poll;
+		ltpc_timer.data = (unsigned long) dev;
+
+		ltpc_timer.expires = jiffies + HZ/20;
+		add_timer(&ltpc_timer);
+	}
+	err = register_netdev(dev);
+	if (err)
+		goto out4;
+
+	return NULL;
+out4:
+	del_timer_sync(&ltpc_timer);
+	if (dev->irq)
+		free_irq(dev->irq, dev);
+out3:
+	free_pages((unsigned long)ltdmabuf, get_order(1000));
+out2:
+	release_region(io, 8);
+out1:
+	free_netdev(dev);
+out:
+	return ERR_PTR(err);
+}
+
+#ifndef MODULE
+/* handles "ltpc=io,irq,dma" kernel command lines */
+static int __init ltpc_setup(char *str)
+{
+	int ints[5];
+
+	str = get_options(str, ARRAY_SIZE(ints), ints);
+
+	if (ints[0] == 0) {
+		if (str && !strncmp(str, "auto", 4)) {
+			/* do nothing :-) */
+		}
+		else {
+			/* usage message */
+			printk (KERN_ERR
+				"ltpc: usage: ltpc=auto|iobase[,irq[,dma]]\n");
+			return 0;
+		}
+	} else {
+		io = ints[1];
+		if (ints[0] > 1) {
+			irq = ints[2];
+		}
+		if (ints[0] > 2) {
+			dma = ints[3];
+		}
+		/* ignore any other parameters */
+	}
+	return 1;
+}
+
+__setup("ltpc=", ltpc_setup);
+#endif /* MODULE */
+
+static struct net_device *dev_ltpc;
+
+#ifdef MODULE
+
+MODULE_LICENSE("GPL");
+module_param(debug, int, 0);
+module_param(io, int, 0);
+module_param(irq, int, 0);
+module_param(dma, int, 0);
+
+
+static int __init ltpc_module_init(void)
+{
+        if(io == 0)
+		printk(KERN_NOTICE
+		       "ltpc: Autoprobing is not recommended for modules\n");
+
+	dev_ltpc = ltpc_probe();
+	if (IS_ERR(dev_ltpc))
+		return PTR_ERR(dev_ltpc);
+	return 0;
+}
+module_init(ltpc_module_init);
+#endif
+
+static void __exit ltpc_cleanup(void)
+{
+
+	if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n");
+	unregister_netdev(dev_ltpc);
+
+	ltpc_timer.data = 0;  /* signal the poll routine that we're done */
+
+	del_timer_sync(&ltpc_timer);
+
+	if(debug & DEBUG_VERBOSE) printk("freeing irq\n");
+
+	if (dev_ltpc->irq)
+		free_irq(dev_ltpc->irq, dev_ltpc);
+
+	if(debug & DEBUG_VERBOSE) printk("freeing dma\n");
+
+	if (dev_ltpc->dma)
+		free_dma(dev_ltpc->dma);
+
+	if(debug & DEBUG_VERBOSE) printk("freeing ioaddr\n");
+
+	if (dev_ltpc->base_addr)
+		release_region(dev_ltpc->base_addr,8);
+
+	free_netdev(dev_ltpc);
+
+	if(debug & DEBUG_VERBOSE) printk("free_pages\n");
+
+	free_pages( (unsigned long) ltdmabuf, get_order(1000));
+
+	if(debug & DEBUG_VERBOSE) printk("returning from cleanup_module\n");
+}
+
+module_exit(ltpc_cleanup);
diff --git a/drivers/staging/appletalk/ltpc.h b/drivers/staging/appletalk/ltpc.h
new file mode 100644
index 000000000000..cd30544a3729
--- /dev/null
+++ b/drivers/staging/appletalk/ltpc.h
@@ -0,0 +1,73 @@
+/***   ltpc.h
+ *
+ *
+ ***/
+
+#define LT_GETRESULT  0x00
+#define LT_WRITEMEM   0x01
+#define LT_READMEM    0x02
+#define LT_GETFLAGS   0x04
+#define LT_SETFLAGS   0x05
+#define LT_INIT       0x10
+#define LT_SENDLAP    0x13
+#define LT_RCVLAP     0x14
+
+/* the flag that we care about */
+#define LT_FLAG_ALLLAP 0x04
+
+struct lt_getresult {
+	unsigned char command;
+	unsigned char mailbox;
+};
+
+struct lt_mem {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned short addr;	/* host order */
+	unsigned short length;	/* host order */
+};
+
+struct lt_setflags {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned char flags;
+};
+
+struct lt_getflags {
+	unsigned char command;
+	unsigned char mailbox;
+};
+
+struct lt_init {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned char hint;
+};
+
+struct lt_sendlap {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned char dnode;
+	unsigned char laptype;
+	unsigned short length;	/* host order */
+};
+
+struct lt_rcvlap {
+	unsigned char command;
+	unsigned char dnode;
+	unsigned char snode;
+	unsigned char laptype;
+	unsigned short length;	/* host order */
+};
+
+union lt_command {
+	struct lt_getresult getresult;
+	struct lt_mem mem;
+	struct lt_setflags setflags;
+	struct lt_getflags getflags;
+	struct lt_init init;
+	struct lt_sendlap sendlap;
+	struct lt_rcvlap rcvlap;
+};
+typedef union lt_command lt_command;
+
diff --git a/drivers/staging/appletalk/sysctl_net_atalk.c b/drivers/staging/appletalk/sysctl_net_atalk.c
new file mode 100644
index 000000000000..4c896b625b2b
--- /dev/null
+++ b/drivers/staging/appletalk/sysctl_net_atalk.c
@@ -0,0 +1,61 @@
+/*
+ * sysctl_net_atalk.c: sysctl interface to net AppleTalk subsystem.
+ *
+ * Begun April 1, 1996, Mike Shaver.
+ * Added /proc/sys/net/atalk directory entry (empty =) ). [MS]
+ * Dynamic registration, added aarp entries. (5/30/97 Chris Horn)
+ */
+
+#include <linux/sysctl.h>
+#include <net/sock.h>
+#include "atalk.h"
+
+static struct ctl_table atalk_table[] = {
+	{
+		.procname	= "aarp-expiry-time",
+		.data		= &sysctl_aarp_expiry_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "aarp-tick-time",
+		.data		= &sysctl_aarp_tick_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "aarp-retransmit-limit",
+		.data		= &sysctl_aarp_retransmit_limit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "aarp-resolve-time",
+		.data		= &sysctl_aarp_resolve_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ },
+};
+
+static struct ctl_path atalk_path[] = {
+	{ .procname = "net", },
+	{ .procname = "appletalk", },
+	{ }
+};
+
+static struct ctl_table_header *atalk_table_header;
+
+void atalk_register_sysctl(void)
+{
+	atalk_table_header = register_sysctl_paths(atalk_path, atalk_table);
+}
+
+void atalk_unregister_sysctl(void)
+{
+	unregister_sysctl_table(atalk_table_header);
+}
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 61abb638b4bf..86a2d7d905c0 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -56,7 +56,6 @@
 #include <linux/syscalls.h>
 #include <linux/i2c.h>
 #include <linux/i2c-dev.h>
-#include <linux/atalk.h>
 #include <linux/gfp.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 2296d8b1931f..362041b73a2f 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -43,7 +43,6 @@ header-y += agpgart.h
 header-y += aio_abi.h
 header-y += apm_bios.h
 header-y += arcfb.h
-header-y += atalk.h
 header-y += atm.h
 header-y += atm_eni.h
 header-y += atm_he.h
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
deleted file mode 100644
index d34c187432ed..000000000000
--- a/include/linux/atalk.h
+++ /dev/null
@@ -1,208 +0,0 @@
-#ifndef __LINUX_ATALK_H__
-#define __LINUX_ATALK_H__
-
-#include <linux/types.h>
-#include <asm/byteorder.h>
-
-/*
- * AppleTalk networking structures
- *
- * The following are directly referenced from the University Of Michigan
- * netatalk for compatibility reasons.
- */
-#define ATPORT_FIRST	1
-#define ATPORT_RESERVED	128
-#define ATPORT_LAST	254		/* 254 is only legal on localtalk */ 
-#define ATADDR_ANYNET	(__u16)0
-#define ATADDR_ANYNODE	(__u8)0
-#define ATADDR_ANYPORT  (__u8)0
-#define ATADDR_BCAST	(__u8)255
-#define DDP_MAXSZ	587
-#define DDP_MAXHOPS     15		/* 4 bits of hop counter */
-
-#define SIOCATALKDIFADDR       (SIOCPROTOPRIVATE + 0)
-
-struct atalk_addr {
-	__be16	s_net;
-	__u8	s_node;
-};
-
-struct sockaddr_at {
-	sa_family_t	  sat_family;
-	__u8		  sat_port;
-	struct atalk_addr sat_addr;
-	char		  sat_zero[8];
-};
-
-struct atalk_netrange {
-	__u8	nr_phase;
-	__be16	nr_firstnet;
-	__be16	nr_lastnet;
-};
-
-#ifdef __KERNEL__
-
-#include <net/sock.h>
-
-struct atalk_route {
-	struct net_device  *dev;
-	struct atalk_addr  target;
-	struct atalk_addr  gateway;
-	int		   flags;
-	struct atalk_route *next;
-};
-
-/**
- *	struct atalk_iface - AppleTalk Interface
- *	@dev - Network device associated with this interface
- *	@address - Our address
- *	@status - What are we doing?
- *	@nets - Associated direct netrange
- *	@next - next element in the list of interfaces
- */
-struct atalk_iface {
-	struct net_device	*dev;
-	struct atalk_addr	address;
-	int			status;
-#define ATIF_PROBE	1		/* Probing for an address */
-#define ATIF_PROBE_FAIL	2		/* Probe collided */
-	struct atalk_netrange	nets;
-	struct atalk_iface	*next;
-};
-	
-struct atalk_sock {
-	/* struct sock has to be the first member of atalk_sock */
-	struct sock	sk;
-	__be16		dest_net;
-	__be16		src_net;
-	unsigned char	dest_node;
-	unsigned char	src_node;
-	unsigned char	dest_port;
-	unsigned char	src_port;
-};
-
-static inline struct atalk_sock *at_sk(struct sock *sk)
-{
-	return (struct atalk_sock *)sk;
-}
-
-struct ddpehdr {
-	__be16	deh_len_hops;	/* lower 10 bits are length, next 4 - hops */
-	__be16	deh_sum;
-	__be16	deh_dnet;
-	__be16	deh_snet;
-	__u8	deh_dnode;
-	__u8	deh_snode;
-	__u8	deh_dport;
-	__u8	deh_sport;
-	/* And netatalk apps expect to stick the type in themselves */
-};
-
-static __inline__ struct ddpehdr *ddp_hdr(struct sk_buff *skb)
-{
-	return (struct ddpehdr *)skb_transport_header(skb);
-}
-
-/* AppleTalk AARP headers */
-struct elapaarp {
-	__be16	hw_type;
-#define AARP_HW_TYPE_ETHERNET		1
-#define AARP_HW_TYPE_TOKENRING		2
-	__be16	pa_type;
-	__u8	hw_len;
-	__u8	pa_len;
-#define AARP_PA_ALEN			4
-	__be16	function;
-#define AARP_REQUEST			1
-#define AARP_REPLY			2
-#define AARP_PROBE			3
-	__u8	hw_src[ETH_ALEN];
-	__u8	pa_src_zero;
-	__be16	pa_src_net;
-	__u8	pa_src_node;
-	__u8	hw_dst[ETH_ALEN];
-	__u8	pa_dst_zero;
-	__be16	pa_dst_net;
-	__u8	pa_dst_node;
-} __attribute__ ((packed));
-
-static __inline__ struct elapaarp *aarp_hdr(struct sk_buff *skb)
-{
-	return (struct elapaarp *)skb_transport_header(skb);
-}
-
-/* Not specified - how long till we drop a resolved entry */
-#define AARP_EXPIRY_TIME	(5 * 60 * HZ)
-/* Size of hash table */
-#define AARP_HASH_SIZE		16
-/* Fast retransmission timer when resolving */
-#define AARP_TICK_TIME		(HZ / 5)
-/* Send 10 requests then give up (2 seconds) */
-#define AARP_RETRANSMIT_LIMIT	10
-/*
- * Some value bigger than total retransmit time + a bit for last reply to
- * appear and to stop continual requests
- */
-#define AARP_RESOLVE_TIME	(10 * HZ)
-
-extern struct datalink_proto *ddp_dl, *aarp_dl;
-extern void aarp_proto_init(void);
-
-/* Inter module exports */
-
-/* Give a device find its atif control structure */
-static inline struct atalk_iface *atalk_find_dev(struct net_device *dev)
-{
-	return dev->atalk_ptr;
-}
-
-extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev);
-extern struct net_device *atrtr_get_dev(struct atalk_addr *sa);
-extern int		 aarp_send_ddp(struct net_device *dev,
-				       struct sk_buff *skb,
-				       struct atalk_addr *sa, void *hwaddr);
-extern void		 aarp_device_down(struct net_device *dev);
-extern void		 aarp_probe_network(struct atalk_iface *atif);
-extern int 		 aarp_proxy_probe_network(struct atalk_iface *atif,
-				     struct atalk_addr *sa);
-extern void		 aarp_proxy_remove(struct net_device *dev,
-					   struct atalk_addr *sa);
-
-extern void		aarp_cleanup_module(void);
-
-extern struct hlist_head atalk_sockets;
-extern rwlock_t atalk_sockets_lock;
-
-extern struct atalk_route *atalk_routes;
-extern rwlock_t atalk_routes_lock;
-
-extern struct atalk_iface *atalk_interfaces;
-extern rwlock_t atalk_interfaces_lock;
-
-extern struct atalk_route atrtr_default;
-
-extern const struct file_operations atalk_seq_arp_fops;
-
-extern int sysctl_aarp_expiry_time;
-extern int sysctl_aarp_tick_time;
-extern int sysctl_aarp_retransmit_limit;
-extern int sysctl_aarp_resolve_time;
-
-#ifdef CONFIG_SYSCTL
-extern void atalk_register_sysctl(void);
-extern void atalk_unregister_sysctl(void);
-#else
-#define atalk_register_sysctl()		do { } while(0)
-#define atalk_unregister_sysctl()	do { } while(0)
-#endif
-
-#ifdef CONFIG_PROC_FS
-extern int atalk_proc_init(void);
-extern void atalk_proc_exit(void);
-#else
-#define atalk_proc_init()	({ 0; })
-#define atalk_proc_exit()	do { } while(0)
-#endif /* CONFIG_PROC_FS */
-
-#endif /* __KERNEL__ */
-#endif /* __LINUX_ATALK_H__ */
diff --git a/net/Kconfig b/net/Kconfig
index 72840626284b..082c8bc977e1 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -204,7 +204,6 @@ source "net/8021q/Kconfig"
 source "net/decnet/Kconfig"
 source "net/llc/Kconfig"
 source "net/ipx/Kconfig"
-source "drivers/net/appletalk/Kconfig"
 source "net/x25/Kconfig"
 source "net/lapb/Kconfig"
 source "net/econet/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index a3330ebe2c53..16d9947b4b95 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -27,7 +27,6 @@ obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
 obj-$(CONFIG_NET_DSA)		+= dsa/
 obj-$(CONFIG_IPX)		+= ipx/
-obj-$(CONFIG_ATALK)		+= appletalk/
 obj-$(CONFIG_WAN_ROUTER)	+= wanrouter/
 obj-$(CONFIG_X25)		+= x25/
 obj-$(CONFIG_LAPB)		+= lapb/
diff --git a/net/appletalk/Makefile b/net/appletalk/Makefile
deleted file mode 100644
index 5cda56edef57..000000000000
--- a/net/appletalk/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-#
-# Makefile for the Linux AppleTalk layer.
-#
-
-obj-$(CONFIG_ATALK) += appletalk.o
-
-appletalk-y			:= aarp.o ddp.o dev.o
-appletalk-$(CONFIG_PROC_FS)	+= atalk_proc.o
-appletalk-$(CONFIG_SYSCTL)	+= sysctl_net_atalk.o
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
deleted file mode 100644
index 50dce7981321..000000000000
--- a/net/appletalk/aarp.c
+++ /dev/null
@@ -1,1063 +0,0 @@
-/*
- *	AARP:		An implementation of the AppleTalk AARP protocol for
- *			Ethernet 'ELAP'.
- *
- *		Alan Cox  <Alan.Cox@linux.org>
- *
- *	This doesn't fit cleanly with the IP arp. Potentially we can use
- *	the generic neighbour discovery code to clean this up.
- *
- *	FIXME:
- *		We ought to handle the retransmits with a single list and a
- *	separate fast timer for when it is needed.
- *		Use neighbour discovery code.
- *		Token Ring Support.
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
- *
- *	References:
- *		Inside AppleTalk (2nd Ed).
- *	Fixes:
- *		Jaume Grau	-	flush caches on AARP_PROBE
- *		Rob Newberry	-	Added proxy AARP and AARP proc fs,
- *					moved probing from DDP module.
- *		Arnaldo C. Melo -	don't mangle rx packets
- *
- */
-
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/datalink.h>
-#include <net/psnap.h>
-#include <linux/atalk.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-
-int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
-int sysctl_aarp_tick_time = AARP_TICK_TIME;
-int sysctl_aarp_retransmit_limit = AARP_RETRANSMIT_LIMIT;
-int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
-
-/* Lists of aarp entries */
-/**
- *	struct aarp_entry - AARP entry
- *	@last_sent - Last time we xmitted the aarp request
- *	@packet_queue - Queue of frames wait for resolution
- *	@status - Used for proxy AARP
- *	expires_at - Entry expiry time
- *	target_addr - DDP Address
- *	dev - Device to use
- *	hwaddr - Physical i/f address of target/router
- *	xmit_count - When this hits 10 we give up
- *	next - Next entry in chain
- */
-struct aarp_entry {
-	/* These first two are only used for unresolved entries */
-	unsigned long		last_sent;
-	struct sk_buff_head	packet_queue;
-	int			status;
-	unsigned long		expires_at;
-	struct atalk_addr	target_addr;
-	struct net_device	*dev;
-	char			hwaddr[6];
-	unsigned short		xmit_count;
-	struct aarp_entry	*next;
-};
-
-/* Hashed list of resolved, unresolved and proxy entries */
-static struct aarp_entry *resolved[AARP_HASH_SIZE];
-static struct aarp_entry *unresolved[AARP_HASH_SIZE];
-static struct aarp_entry *proxies[AARP_HASH_SIZE];
-static int unresolved_count;
-
-/* One lock protects it all. */
-static DEFINE_RWLOCK(aarp_lock);
-
-/* Used to walk the list and purge/kick entries.  */
-static struct timer_list aarp_timer;
-
-/*
- *	Delete an aarp queue
- *
- *	Must run under aarp_lock.
- */
-static void __aarp_expire(struct aarp_entry *a)
-{
-	skb_queue_purge(&a->packet_queue);
-	kfree(a);
-}
-
-/*
- *	Send an aarp queue entry request
- *
- *	Must run under aarp_lock.
- */
-static void __aarp_send_query(struct aarp_entry *a)
-{
-	static unsigned char aarp_eth_multicast[ETH_ALEN] =
-					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
-	struct net_device *dev = a->dev;
-	struct elapaarp *eah;
-	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
-	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
-	struct atalk_addr *sat = atalk_find_dev_addr(dev);
-
-	if (!skb)
-		return;
-
-	if (!sat) {
-		kfree_skb(skb);
-		return;
-	}
-
-	/* Set up the buffer */
-	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_put(skb, sizeof(*eah));
-	skb->protocol    = htons(ETH_P_ATALK);
-	skb->dev	 = dev;
-	eah		 = aarp_hdr(skb);
-
-	/* Set up the ARP */
-	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
-	eah->pa_type	 = htons(ETH_P_ATALK);
-	eah->hw_len	 = ETH_ALEN;
-	eah->pa_len	 = AARP_PA_ALEN;
-	eah->function	 = htons(AARP_REQUEST);
-
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
-
-	eah->pa_src_zero = 0;
-	eah->pa_src_net	 = sat->s_net;
-	eah->pa_src_node = sat->s_node;
-
-	memset(eah->hw_dst, '\0', ETH_ALEN);
-
-	eah->pa_dst_zero = 0;
-	eah->pa_dst_net	 = a->target_addr.s_net;
-	eah->pa_dst_node = a->target_addr.s_node;
-
-	/* Send it */
-	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
-	/* Update the sending count */
-	a->xmit_count++;
-	a->last_sent = jiffies;
-}
-
-/* This runs under aarp_lock and in softint context, so only atomic memory
- * allocations can be used. */
-static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
-			    struct atalk_addr *them, unsigned char *sha)
-{
-	struct elapaarp *eah;
-	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
-	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
-
-	if (!skb)
-		return;
-
-	/* Set up the buffer */
-	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_put(skb, sizeof(*eah));
-	skb->protocol    = htons(ETH_P_ATALK);
-	skb->dev	 = dev;
-	eah		 = aarp_hdr(skb);
-
-	/* Set up the ARP */
-	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
-	eah->pa_type	 = htons(ETH_P_ATALK);
-	eah->hw_len	 = ETH_ALEN;
-	eah->pa_len	 = AARP_PA_ALEN;
-	eah->function	 = htons(AARP_REPLY);
-
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
-
-	eah->pa_src_zero = 0;
-	eah->pa_src_net	 = us->s_net;
-	eah->pa_src_node = us->s_node;
-
-	if (!sha)
-		memset(eah->hw_dst, '\0', ETH_ALEN);
-	else
-		memcpy(eah->hw_dst, sha, ETH_ALEN);
-
-	eah->pa_dst_zero = 0;
-	eah->pa_dst_net	 = them->s_net;
-	eah->pa_dst_node = them->s_node;
-
-	/* Send it */
-	aarp_dl->request(aarp_dl, skb, sha);
-}
-
-/*
- *	Send probe frames. Called from aarp_probe_network and
- *	aarp_proxy_probe_network.
- */
-
-static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
-{
-	struct elapaarp *eah;
-	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
-	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
-	static unsigned char aarp_eth_multicast[ETH_ALEN] =
-					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
-
-	if (!skb)
-		return;
-
-	/* Set up the buffer */
-	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_put(skb, sizeof(*eah));
-	skb->protocol    = htons(ETH_P_ATALK);
-	skb->dev	 = dev;
-	eah		 = aarp_hdr(skb);
-
-	/* Set up the ARP */
-	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
-	eah->pa_type	 = htons(ETH_P_ATALK);
-	eah->hw_len	 = ETH_ALEN;
-	eah->pa_len	 = AARP_PA_ALEN;
-	eah->function	 = htons(AARP_PROBE);
-
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
-
-	eah->pa_src_zero = 0;
-	eah->pa_src_net	 = us->s_net;
-	eah->pa_src_node = us->s_node;
-
-	memset(eah->hw_dst, '\0', ETH_ALEN);
-
-	eah->pa_dst_zero = 0;
-	eah->pa_dst_net	 = us->s_net;
-	eah->pa_dst_node = us->s_node;
-
-	/* Send it */
-	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
-}
-
-/*
- *	Handle an aarp timer expire
- *
- *	Must run under the aarp_lock.
- */
-
-static void __aarp_expire_timer(struct aarp_entry **n)
-{
-	struct aarp_entry *t;
-
-	while (*n)
-		/* Expired ? */
-		if (time_after(jiffies, (*n)->expires_at)) {
-			t = *n;
-			*n = (*n)->next;
-			__aarp_expire(t);
-		} else
-			n = &((*n)->next);
-}
-
-/*
- *	Kick all pending requests 5 times a second.
- *
- *	Must run under the aarp_lock.
- */
-static void __aarp_kick(struct aarp_entry **n)
-{
-	struct aarp_entry *t;
-
-	while (*n)
-		/* Expired: if this will be the 11th tx, we delete instead. */
-		if ((*n)->xmit_count >= sysctl_aarp_retransmit_limit) {
-			t = *n;
-			*n = (*n)->next;
-			__aarp_expire(t);
-		} else {
-			__aarp_send_query(*n);
-			n = &((*n)->next);
-		}
-}
-
-/*
- *	A device has gone down. Take all entries referring to the device
- *	and remove them.
- *
- *	Must run under the aarp_lock.
- */
-static void __aarp_expire_device(struct aarp_entry **n, struct net_device *dev)
-{
-	struct aarp_entry *t;
-
-	while (*n)
-		if ((*n)->dev == dev) {
-			t = *n;
-			*n = (*n)->next;
-			__aarp_expire(t);
-		} else
-			n = &((*n)->next);
-}
-
-/* Handle the timer event */
-static void aarp_expire_timeout(unsigned long unused)
-{
-	int ct;
-
-	write_lock_bh(&aarp_lock);
-
-	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-		__aarp_expire_timer(&resolved[ct]);
-		__aarp_kick(&unresolved[ct]);
-		__aarp_expire_timer(&unresolved[ct]);
-		__aarp_expire_timer(&proxies[ct]);
-	}
-
-	write_unlock_bh(&aarp_lock);
-	mod_timer(&aarp_timer, jiffies +
-			       (unresolved_count ? sysctl_aarp_tick_time :
-				sysctl_aarp_expiry_time));
-}
-
-/* Network device notifier chain handler. */
-static int aarp_device_event(struct notifier_block *this, unsigned long event,
-			     void *ptr)
-{
-	struct net_device *dev = ptr;
-	int ct;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
-	if (event == NETDEV_DOWN) {
-		write_lock_bh(&aarp_lock);
-
-		for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-			__aarp_expire_device(&resolved[ct], dev);
-			__aarp_expire_device(&unresolved[ct], dev);
-			__aarp_expire_device(&proxies[ct], dev);
-		}
-
-		write_unlock_bh(&aarp_lock);
-	}
-	return NOTIFY_DONE;
-}
-
-/* Expire all entries in a hash chain */
-static void __aarp_expire_all(struct aarp_entry **n)
-{
-	struct aarp_entry *t;
-
-	while (*n) {
-		t = *n;
-		*n = (*n)->next;
-		__aarp_expire(t);
-	}
-}
-
-/* Cleanup all hash chains -- module unloading */
-static void aarp_purge(void)
-{
-	int ct;
-
-	write_lock_bh(&aarp_lock);
-	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-		__aarp_expire_all(&resolved[ct]);
-		__aarp_expire_all(&unresolved[ct]);
-		__aarp_expire_all(&proxies[ct]);
-	}
-	write_unlock_bh(&aarp_lock);
-}
-
-/*
- *	Create a new aarp entry.  This must use GFP_ATOMIC because it
- *	runs while holding spinlocks.
- */
-static struct aarp_entry *aarp_alloc(void)
-{
-	struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC);
-
-	if (a)
-		skb_queue_head_init(&a->packet_queue);
-	return a;
-}
-
-/*
- * Find an entry. We might return an expired but not yet purged entry. We
- * don't care as it will do no harm.
- *
- * This must run under the aarp_lock.
- */
-static struct aarp_entry *__aarp_find_entry(struct aarp_entry *list,
-					    struct net_device *dev,
-					    struct atalk_addr *sat)
-{
-	while (list) {
-		if (list->target_addr.s_net == sat->s_net &&
-		    list->target_addr.s_node == sat->s_node &&
-		    list->dev == dev)
-			break;
-		list = list->next;
-	}
-
-	return list;
-}
-
-/* Called from the DDP code, and thus must be exported. */
-void aarp_proxy_remove(struct net_device *dev, struct atalk_addr *sa)
-{
-	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
-	struct aarp_entry *a;
-
-	write_lock_bh(&aarp_lock);
-
-	a = __aarp_find_entry(proxies[hash], dev, sa);
-	if (a)
-		a->expires_at = jiffies - 1;
-
-	write_unlock_bh(&aarp_lock);
-}
-
-/* This must run under aarp_lock. */
-static struct atalk_addr *__aarp_proxy_find(struct net_device *dev,
-					    struct atalk_addr *sa)
-{
-	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
-	struct aarp_entry *a = __aarp_find_entry(proxies[hash], dev, sa);
-
-	return a ? sa : NULL;
-}
-
-/*
- * Probe a Phase 1 device or a device that requires its Net:Node to
- * be set via an ioctl.
- */
-static void aarp_send_probe_phase1(struct atalk_iface *iface)
-{
-	struct ifreq atreq;
-	struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr;
-	const struct net_device_ops *ops = iface->dev->netdev_ops;
-
-	sa->sat_addr.s_node = iface->address.s_node;
-	sa->sat_addr.s_net = ntohs(iface->address.s_net);
-
-	/* We pass the Net:Node to the drivers/cards by a Device ioctl. */
-	if (!(ops->ndo_do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) {
-		ops->ndo_do_ioctl(iface->dev, &atreq, SIOCGIFADDR);
-		if (iface->address.s_net != htons(sa->sat_addr.s_net) ||
-		    iface->address.s_node != sa->sat_addr.s_node)
-			iface->status |= ATIF_PROBE_FAIL;
-
-		iface->address.s_net  = htons(sa->sat_addr.s_net);
-		iface->address.s_node = sa->sat_addr.s_node;
-	}
-}
-
-
-void aarp_probe_network(struct atalk_iface *atif)
-{
-	if (atif->dev->type == ARPHRD_LOCALTLK ||
-	    atif->dev->type == ARPHRD_PPP)
-		aarp_send_probe_phase1(atif);
-	else {
-		unsigned int count;
-
-		for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
-			aarp_send_probe(atif->dev, &atif->address);
-
-			/* Defer 1/10th */
-			msleep(100);
-
-			if (atif->status & ATIF_PROBE_FAIL)
-				break;
-		}
-	}
-}
-
-int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa)
-{
-	int hash, retval = -EPROTONOSUPPORT;
-	struct aarp_entry *entry;
-	unsigned int count;
-
-	/*
-	 * we don't currently support LocalTalk or PPP for proxy AARP;
-	 * if someone wants to try and add it, have fun
-	 */
-	if (atif->dev->type == ARPHRD_LOCALTLK ||
-	    atif->dev->type == ARPHRD_PPP)
-		goto out;
-
-	/*
-	 * create a new AARP entry with the flags set to be published --
-	 * we need this one to hang around even if it's in use
-	 */
-	entry = aarp_alloc();
-	retval = -ENOMEM;
-	if (!entry)
-		goto out;
-
-	entry->expires_at = -1;
-	entry->status = ATIF_PROBE;
-	entry->target_addr.s_node = sa->s_node;
-	entry->target_addr.s_net = sa->s_net;
-	entry->dev = atif->dev;
-
-	write_lock_bh(&aarp_lock);
-
-	hash = sa->s_node % (AARP_HASH_SIZE - 1);
-	entry->next = proxies[hash];
-	proxies[hash] = entry;
-
-	for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
-		aarp_send_probe(atif->dev, sa);
-
-		/* Defer 1/10th */
-		write_unlock_bh(&aarp_lock);
-		msleep(100);
-		write_lock_bh(&aarp_lock);
-
-		if (entry->status & ATIF_PROBE_FAIL)
-			break;
-	}
-
-	if (entry->status & ATIF_PROBE_FAIL) {
-		entry->expires_at = jiffies - 1; /* free the entry */
-		retval = -EADDRINUSE; /* return network full */
-	} else { /* clear the probing flag */
-		entry->status &= ~ATIF_PROBE;
-		retval = 1;
-	}
-
-	write_unlock_bh(&aarp_lock);
-out:
-	return retval;
-}
-
-/* Send a DDP frame */
-int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
-		  struct atalk_addr *sa, void *hwaddr)
-{
-	static char ddp_eth_multicast[ETH_ALEN] =
-		{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
-	int hash;
-	struct aarp_entry *a;
-
-	skb_reset_network_header(skb);
-
-	/* Check for LocalTalk first */
-	if (dev->type == ARPHRD_LOCALTLK) {
-		struct atalk_addr *at = atalk_find_dev_addr(dev);
-		struct ddpehdr *ddp = (struct ddpehdr *)skb->data;
-		int ft = 2;
-
-		/*
-		 * Compressible ?
-		 *
-		 * IFF: src_net == dest_net == device_net
-		 * (zero matches anything)
-		 */
-
-		if ((!ddp->deh_snet || at->s_net == ddp->deh_snet) &&
-		    (!ddp->deh_dnet || at->s_net == ddp->deh_dnet)) {
-			skb_pull(skb, sizeof(*ddp) - 4);
-
-			/*
-			 *	The upper two remaining bytes are the port
-			 *	numbers	we just happen to need. Now put the
-			 *	length in the lower two.
-			 */
-			*((__be16 *)skb->data) = htons(skb->len);
-			ft = 1;
-		}
-		/*
-		 * Nice and easy. No AARP type protocols occur here so we can
-		 * just shovel it out with a 3 byte LLAP header
-		 */
-
-		skb_push(skb, 3);
-		skb->data[0] = sa->s_node;
-		skb->data[1] = at->s_node;
-		skb->data[2] = ft;
-		skb->dev     = dev;
-		goto sendit;
-	}
-
-	/* On a PPP link we neither compress nor aarp.  */
-	if (dev->type == ARPHRD_PPP) {
-		skb->protocol = htons(ETH_P_PPPTALK);
-		skb->dev = dev;
-		goto sendit;
-	}
-
-	/* Non ELAP we cannot do. */
-	if (dev->type != ARPHRD_ETHER)
-		goto free_it;
-
-	skb->dev = dev;
-	skb->protocol = htons(ETH_P_ATALK);
-	hash = sa->s_node % (AARP_HASH_SIZE - 1);
-
-	/* Do we have a resolved entry? */
-	if (sa->s_node == ATADDR_BCAST) {
-		/* Send it */
-		ddp_dl->request(ddp_dl, skb, ddp_eth_multicast);
-		goto sent;
-	}
-
-	write_lock_bh(&aarp_lock);
-	a = __aarp_find_entry(resolved[hash], dev, sa);
-
-	if (a) { /* Return 1 and fill in the address */
-		a->expires_at = jiffies + (sysctl_aarp_expiry_time * 10);
-		ddp_dl->request(ddp_dl, skb, a->hwaddr);
-		write_unlock_bh(&aarp_lock);
-		goto sent;
-	}
-
-	/* Do we have an unresolved entry: This is the less common path */
-	a = __aarp_find_entry(unresolved[hash], dev, sa);
-	if (a) { /* Queue onto the unresolved queue */
-		skb_queue_tail(&a->packet_queue, skb);
-		goto out_unlock;
-	}
-
-	/* Allocate a new entry */
-	a = aarp_alloc();
-	if (!a) {
-		/* Whoops slipped... good job it's an unreliable protocol 8) */
-		write_unlock_bh(&aarp_lock);
-		goto free_it;
-	}
-
-	/* Set up the queue */
-	skb_queue_tail(&a->packet_queue, skb);
-	a->expires_at	 = jiffies + sysctl_aarp_resolve_time;
-	a->dev		 = dev;
-	a->next		 = unresolved[hash];
-	a->target_addr	 = *sa;
-	a->xmit_count	 = 0;
-	unresolved[hash] = a;
-	unresolved_count++;
-
-	/* Send an initial request for the address */
-	__aarp_send_query(a);
-
-	/*
-	 * Switch to fast timer if needed (That is if this is the first
-	 * unresolved entry to get added)
-	 */
-
-	if (unresolved_count == 1)
-		mod_timer(&aarp_timer, jiffies + sysctl_aarp_tick_time);
-
-	/* Now finally, it is safe to drop the lock. */
-out_unlock:
-	write_unlock_bh(&aarp_lock);
-
-	/* Tell the ddp layer we have taken over for this frame. */
-	goto sent;
-
-sendit:
-	if (skb->sk)
-		skb->priority = skb->sk->sk_priority;
-	if (dev_queue_xmit(skb))
-		goto drop;
-sent:
-	return NET_XMIT_SUCCESS;
-free_it:
-	kfree_skb(skb);
-drop:
-	return NET_XMIT_DROP;
-}
-EXPORT_SYMBOL(aarp_send_ddp);
-
-/*
- *	An entry in the aarp unresolved queue has become resolved. Send
- *	all the frames queued under it.
- *
- *	Must run under aarp_lock.
- */
-static void __aarp_resolved(struct aarp_entry **list, struct aarp_entry *a,
-			    int hash)
-{
-	struct sk_buff *skb;
-
-	while (*list)
-		if (*list == a) {
-			unresolved_count--;
-			*list = a->next;
-
-			/* Move into the resolved list */
-			a->next = resolved[hash];
-			resolved[hash] = a;
-
-			/* Kick frames off */
-			while ((skb = skb_dequeue(&a->packet_queue)) != NULL) {
-				a->expires_at = jiffies +
-						sysctl_aarp_expiry_time * 10;
-				ddp_dl->request(ddp_dl, skb, a->hwaddr);
-			}
-		} else
-			list = &((*list)->next);
-}
-
-/*
- *	This is called by the SNAP driver whenever we see an AARP SNAP
- *	frame. We currently only support Ethernet.
- */
-static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
-		    struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct elapaarp *ea = aarp_hdr(skb);
-	int hash, ret = 0;
-	__u16 function;
-	struct aarp_entry *a;
-	struct atalk_addr sa, *ma, da;
-	struct atalk_iface *ifa;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		goto out0;
-
-	/* We only do Ethernet SNAP AARP. */
-	if (dev->type != ARPHRD_ETHER)
-		goto out0;
-
-	/* Frame size ok? */
-	if (!skb_pull(skb, sizeof(*ea)))
-		goto out0;
-
-	function = ntohs(ea->function);
-
-	/* Sanity check fields. */
-	if (function < AARP_REQUEST || function > AARP_PROBE ||
-	    ea->hw_len != ETH_ALEN || ea->pa_len != AARP_PA_ALEN ||
-	    ea->pa_src_zero || ea->pa_dst_zero)
-		goto out0;
-
-	/* Looks good. */
-	hash = ea->pa_src_node % (AARP_HASH_SIZE - 1);
-
-	/* Build an address. */
-	sa.s_node = ea->pa_src_node;
-	sa.s_net = ea->pa_src_net;
-
-	/* Process the packet. Check for replies of me. */
-	ifa = atalk_find_dev(dev);
-	if (!ifa)
-		goto out1;
-
-	if (ifa->status & ATIF_PROBE &&
-	    ifa->address.s_node == ea->pa_dst_node &&
-	    ifa->address.s_net == ea->pa_dst_net) {
-		ifa->status |= ATIF_PROBE_FAIL; /* Fail the probe (in use) */
-		goto out1;
-	}
-
-	/* Check for replies of proxy AARP entries */
-	da.s_node = ea->pa_dst_node;
-	da.s_net  = ea->pa_dst_net;
-
-	write_lock_bh(&aarp_lock);
-	a = __aarp_find_entry(proxies[hash], dev, &da);
-
-	if (a && a->status & ATIF_PROBE) {
-		a->status |= ATIF_PROBE_FAIL;
-		/*
-		 * we do not respond to probe or request packets for
-		 * this address while we are probing this address
-		 */
-		goto unlock;
-	}
-
-	switch (function) {
-		case AARP_REPLY:
-			if (!unresolved_count)	/* Speed up */
-				break;
-
-			/* Find the entry.  */
-			a = __aarp_find_entry(unresolved[hash], dev, &sa);
-			if (!a || dev != a->dev)
-				break;
-
-			/* We can fill one in - this is good. */
-			memcpy(a->hwaddr, ea->hw_src, ETH_ALEN);
-			__aarp_resolved(&unresolved[hash], a, hash);
-			if (!unresolved_count)
-				mod_timer(&aarp_timer,
-					  jiffies + sysctl_aarp_expiry_time);
-			break;
-
-		case AARP_REQUEST:
-		case AARP_PROBE:
-
-			/*
-			 * If it is my address set ma to my address and reply.
-			 * We can treat probe and request the same.  Probe
-			 * simply means we shouldn't cache the querying host,
-			 * as in a probe they are proposing an address not
-			 * using one.
-			 *
-			 * Support for proxy-AARP added. We check if the
-			 * address is one of our proxies before we toss the
-			 * packet out.
-			 */
-
-			sa.s_node = ea->pa_dst_node;
-			sa.s_net  = ea->pa_dst_net;
-
-			/* See if we have a matching proxy. */
-			ma = __aarp_proxy_find(dev, &sa);
-			if (!ma)
-				ma = &ifa->address;
-			else { /* We need to make a copy of the entry. */
-				da.s_node = sa.s_node;
-				da.s_net = sa.s_net;
-				ma = &da;
-			}
-
-			if (function == AARP_PROBE) {
-				/*
-				 * A probe implies someone trying to get an
-				 * address. So as a precaution flush any
-				 * entries we have for this address.
-				 */
-				a = __aarp_find_entry(resolved[sa.s_node %
-							  (AARP_HASH_SIZE - 1)],
-						      skb->dev, &sa);
-
-				/*
-				 * Make it expire next tick - that avoids us
-				 * getting into a probe/flush/learn/probe/
-				 * flush/learn cycle during probing of a slow
-				 * to respond host addr.
-				 */
-				if (a) {
-					a->expires_at = jiffies - 1;
-					mod_timer(&aarp_timer, jiffies +
-							sysctl_aarp_tick_time);
-				}
-			}
-
-			if (sa.s_node != ma->s_node)
-				break;
-
-			if (sa.s_net && ma->s_net && sa.s_net != ma->s_net)
-				break;
-
-			sa.s_node = ea->pa_src_node;
-			sa.s_net = ea->pa_src_net;
-
-			/* aarp_my_address has found the address to use for us.
-			*/
-			aarp_send_reply(dev, ma, &sa, ea->hw_src);
-			break;
-	}
-
-unlock:
-	write_unlock_bh(&aarp_lock);
-out1:
-	ret = 1;
-out0:
-	kfree_skb(skb);
-	return ret;
-}
-
-static struct notifier_block aarp_notifier = {
-	.notifier_call = aarp_device_event,
-};
-
-static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 };
-
-void __init aarp_proto_init(void)
-{
-	aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv);
-	if (!aarp_dl)
-		printk(KERN_CRIT "Unable to register AARP with SNAP.\n");
-	setup_timer(&aarp_timer, aarp_expire_timeout, 0);
-	aarp_timer.expires  = jiffies + sysctl_aarp_expiry_time;
-	add_timer(&aarp_timer);
-	register_netdevice_notifier(&aarp_notifier);
-}
-
-/* Remove the AARP entries associated with a device. */
-void aarp_device_down(struct net_device *dev)
-{
-	int ct;
-
-	write_lock_bh(&aarp_lock);
-
-	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-		__aarp_expire_device(&resolved[ct], dev);
-		__aarp_expire_device(&unresolved[ct], dev);
-		__aarp_expire_device(&proxies[ct], dev);
-	}
-
-	write_unlock_bh(&aarp_lock);
-}
-
-#ifdef CONFIG_PROC_FS
-struct aarp_iter_state {
-	int bucket;
-	struct aarp_entry **table;
-};
-
-/*
- * Get the aarp entry that is in the chain described
- * by the iterator.
- * If pos is set then skip till that index.
- * pos = 1 is the first entry
- */
-static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
-{
-	int ct = iter->bucket;
-	struct aarp_entry **table = iter->table;
-	loff_t off = 0;
-	struct aarp_entry *entry;
-
- rescan:
-	while(ct < AARP_HASH_SIZE) {
-		for (entry = table[ct]; entry; entry = entry->next) {
-			if (!pos || ++off == *pos) {
-				iter->table = table;
-				iter->bucket = ct;
-				return entry;
-			}
-		}
-		++ct;
-	}
-
-	if (table == resolved) {
-		ct = 0;
-		table = unresolved;
-		goto rescan;
-	}
-	if (table == unresolved) {
-		ct = 0;
-		table = proxies;
-		goto rescan;
-	}
-	return NULL;
-}
-
-static void *aarp_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(aarp_lock)
-{
-	struct aarp_iter_state *iter = seq->private;
-
-	read_lock_bh(&aarp_lock);
-	iter->table     = resolved;
-	iter->bucket    = 0;
-
-	return *pos ? iter_next(iter, pos) : SEQ_START_TOKEN;
-}
-
-static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct aarp_entry *entry = v;
-	struct aarp_iter_state *iter = seq->private;
-
-	++*pos;
-
-	/* first line after header */
-	if (v == SEQ_START_TOKEN)
-		entry = iter_next(iter, NULL);
-
-	/* next entry in current bucket */
-	else if (entry->next)
-		entry = entry->next;
-
-	/* next bucket or table */
-	else {
-		++iter->bucket;
-		entry = iter_next(iter, NULL);
-	}
-	return entry;
-}
-
-static void aarp_seq_stop(struct seq_file *seq, void *v)
-	__releases(aarp_lock)
-{
-	read_unlock_bh(&aarp_lock);
-}
-
-static const char *dt2str(unsigned long ticks)
-{
-	static char buf[32];
-
-	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
-
-	return buf;
-}
-
-static int aarp_seq_show(struct seq_file *seq, void *v)
-{
-	struct aarp_iter_state *iter = seq->private;
-	struct aarp_entry *entry = v;
-	unsigned long now = jiffies;
-
-	if (v == SEQ_START_TOKEN)
-		seq_puts(seq,
-			 "Address  Interface   Hardware Address"
-			 "   Expires LastSend  Retry Status\n");
-	else {
-		seq_printf(seq, "%04X:%02X  %-12s",
-			   ntohs(entry->target_addr.s_net),
-			   (unsigned int) entry->target_addr.s_node,
-			   entry->dev ? entry->dev->name : "????");
-		seq_printf(seq, "%pM", entry->hwaddr);
-		seq_printf(seq, " %8s",
-			   dt2str((long)entry->expires_at - (long)now));
-		if (iter->table == unresolved)
-			seq_printf(seq, " %8s %6hu",
-				   dt2str(now - entry->last_sent),
-				   entry->xmit_count);
-		else
-			seq_puts(seq, "                ");
-		seq_printf(seq, " %s\n",
-			   (iter->table == resolved) ? "resolved"
-			   : (iter->table == unresolved) ? "unresolved"
-			   : (iter->table == proxies) ? "proxies"
-			   : "unknown");
-	}
-	return 0;
-}
-
-static const struct seq_operations aarp_seq_ops = {
-	.start  = aarp_seq_start,
-	.next   = aarp_seq_next,
-	.stop   = aarp_seq_stop,
-	.show   = aarp_seq_show,
-};
-
-static int aarp_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_private(file, &aarp_seq_ops,
-			sizeof(struct aarp_iter_state));
-}
-
-const struct file_operations atalk_seq_arp_fops = {
-	.owner		= THIS_MODULE,
-	.open           = aarp_seq_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release	= seq_release_private,
-};
-#endif
-
-/* General module cleanup. Called from cleanup_module() in ddp.c. */
-void aarp_cleanup_module(void)
-{
-	del_timer_sync(&aarp_timer);
-	unregister_netdevice_notifier(&aarp_notifier);
-	unregister_snap_client(aarp_dl);
-	aarp_purge();
-}
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
deleted file mode 100644
index 6ef0e761e5de..000000000000
--- a/net/appletalk/atalk_proc.c
+++ /dev/null
@@ -1,301 +0,0 @@
-/*
- * 	atalk_proc.c - proc support for Appletalk
- *
- * 	Copyright(c) Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *
- *	This program is free software; you can redistribute it and/or modify it
- *	under the terms of the GNU General Public License as published by the
- *	Free Software Foundation, version 2.
- */
-
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <net/net_namespace.h>
-#include <net/sock.h>
-#include <linux/atalk.h>
-
-
-static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos)
-{
-	struct atalk_iface *i;
-
-	for (i = atalk_interfaces; pos && i; i = i->next)
-		--pos;
-
-	return i;
-}
-
-static void *atalk_seq_interface_start(struct seq_file *seq, loff_t *pos)
-	__acquires(atalk_interfaces_lock)
-{
-	loff_t l = *pos;
-
-	read_lock_bh(&atalk_interfaces_lock);
-	return l ? atalk_get_interface_idx(--l) : SEQ_START_TOKEN;
-}
-
-static void *atalk_seq_interface_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct atalk_iface *i;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN) {
-		i = NULL;
-		if (atalk_interfaces)
-			i = atalk_interfaces;
-		goto out;
-	}
-	i = v;
-	i = i->next;
-out:
-	return i;
-}
-
-static void atalk_seq_interface_stop(struct seq_file *seq, void *v)
-	__releases(atalk_interfaces_lock)
-{
-	read_unlock_bh(&atalk_interfaces_lock);
-}
-
-static int atalk_seq_interface_show(struct seq_file *seq, void *v)
-{
-	struct atalk_iface *iface;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_puts(seq, "Interface        Address   Networks  "
-			      "Status\n");
-		goto out;
-	}
-
-	iface = v;
-	seq_printf(seq, "%-16s %04X:%02X  %04X-%04X  %d\n",
-		   iface->dev->name, ntohs(iface->address.s_net),
-		   iface->address.s_node, ntohs(iface->nets.nr_firstnet),
-		   ntohs(iface->nets.nr_lastnet), iface->status);
-out:
-	return 0;
-}
-
-static __inline__ struct atalk_route *atalk_get_route_idx(loff_t pos)
-{
-	struct atalk_route *r;
-
-	for (r = atalk_routes; pos && r; r = r->next)
-		--pos;
-
-	return r;
-}
-
-static void *atalk_seq_route_start(struct seq_file *seq, loff_t *pos)
-	__acquires(atalk_routes_lock)
-{
-	loff_t l = *pos;
-
-	read_lock_bh(&atalk_routes_lock);
-	return l ? atalk_get_route_idx(--l) : SEQ_START_TOKEN;
-}
-
-static void *atalk_seq_route_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct atalk_route *r;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN) {
-		r = NULL;
-		if (atalk_routes)
-			r = atalk_routes;
-		goto out;
-	}
-	r = v;
-	r = r->next;
-out:
-	return r;
-}
-
-static void atalk_seq_route_stop(struct seq_file *seq, void *v)
-	__releases(atalk_routes_lock)
-{
-	read_unlock_bh(&atalk_routes_lock);
-}
-
-static int atalk_seq_route_show(struct seq_file *seq, void *v)
-{
-	struct atalk_route *rt;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_puts(seq, "Target        Router  Flags Dev\n");
-		goto out;
-	}
-
-	if (atrtr_default.dev) {
-		rt = &atrtr_default;
-		seq_printf(seq, "Default     %04X:%02X  %-4d  %s\n",
-			       ntohs(rt->gateway.s_net), rt->gateway.s_node,
-			       rt->flags, rt->dev->name);
-	}
-
-	rt = v;
-	seq_printf(seq, "%04X:%02X     %04X:%02X  %-4d  %s\n",
-		   ntohs(rt->target.s_net), rt->target.s_node,
-		   ntohs(rt->gateway.s_net), rt->gateway.s_node,
-		   rt->flags, rt->dev->name);
-out:
-	return 0;
-}
-
-static void *atalk_seq_socket_start(struct seq_file *seq, loff_t *pos)
-	__acquires(atalk_sockets_lock)
-{
-	read_lock_bh(&atalk_sockets_lock);
-	return seq_hlist_start_head(&atalk_sockets, *pos);
-}
-
-static void *atalk_seq_socket_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return seq_hlist_next(v, &atalk_sockets, pos);
-}
-
-static void atalk_seq_socket_stop(struct seq_file *seq, void *v)
-	__releases(atalk_sockets_lock)
-{
-	read_unlock_bh(&atalk_sockets_lock);
-}
-
-static int atalk_seq_socket_show(struct seq_file *seq, void *v)
-{
-	struct sock *s;
-	struct atalk_sock *at;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq, "Type Local_addr  Remote_addr Tx_queue "
-				"Rx_queue St UID\n");
-		goto out;
-	}
-
-	s = sk_entry(v);
-	at = at_sk(s);
-
-	seq_printf(seq, "%02X   %04X:%02X:%02X  %04X:%02X:%02X  %08X:%08X "
-			"%02X %d\n",
-		   s->sk_type, ntohs(at->src_net), at->src_node, at->src_port,
-		   ntohs(at->dest_net), at->dest_node, at->dest_port,
-		   sk_wmem_alloc_get(s),
-		   sk_rmem_alloc_get(s),
-		   s->sk_state, SOCK_INODE(s->sk_socket)->i_uid);
-out:
-	return 0;
-}
-
-static const struct seq_operations atalk_seq_interface_ops = {
-	.start  = atalk_seq_interface_start,
-	.next   = atalk_seq_interface_next,
-	.stop   = atalk_seq_interface_stop,
-	.show   = atalk_seq_interface_show,
-};
-
-static const struct seq_operations atalk_seq_route_ops = {
-	.start  = atalk_seq_route_start,
-	.next   = atalk_seq_route_next,
-	.stop   = atalk_seq_route_stop,
-	.show   = atalk_seq_route_show,
-};
-
-static const struct seq_operations atalk_seq_socket_ops = {
-	.start  = atalk_seq_socket_start,
-	.next   = atalk_seq_socket_next,
-	.stop   = atalk_seq_socket_stop,
-	.show   = atalk_seq_socket_show,
-};
-
-static int atalk_seq_interface_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_interface_ops);
-}
-
-static int atalk_seq_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_route_ops);
-}
-
-static int atalk_seq_socket_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_socket_ops);
-}
-
-static const struct file_operations atalk_seq_interface_fops = {
-	.owner		= THIS_MODULE,
-	.open		= atalk_seq_interface_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations atalk_seq_route_fops = {
-	.owner		= THIS_MODULE,
-	.open		= atalk_seq_route_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations atalk_seq_socket_fops = {
-	.owner		= THIS_MODULE,
-	.open		= atalk_seq_socket_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static struct proc_dir_entry *atalk_proc_dir;
-
-int __init atalk_proc_init(void)
-{
-	struct proc_dir_entry *p;
-	int rc = -ENOMEM;
-
-	atalk_proc_dir = proc_mkdir("atalk", init_net.proc_net);
-	if (!atalk_proc_dir)
-		goto out;
-
-	p = proc_create("interface", S_IRUGO, atalk_proc_dir,
-			&atalk_seq_interface_fops);
-	if (!p)
-		goto out_interface;
-
-	p = proc_create("route", S_IRUGO, atalk_proc_dir,
-			&atalk_seq_route_fops);
-	if (!p)
-		goto out_route;
-
-	p = proc_create("socket", S_IRUGO, atalk_proc_dir,
-			&atalk_seq_socket_fops);
-	if (!p)
-		goto out_socket;
-
-	p = proc_create("arp", S_IRUGO, atalk_proc_dir, &atalk_seq_arp_fops);
-	if (!p)
-		goto out_arp;
-
-	rc = 0;
-out:
-	return rc;
-out_arp:
-	remove_proc_entry("socket", atalk_proc_dir);
-out_socket:
-	remove_proc_entry("route", atalk_proc_dir);
-out_route:
-	remove_proc_entry("interface", atalk_proc_dir);
-out_interface:
-	remove_proc_entry("atalk", init_net.proc_net);
-	goto out;
-}
-
-void __exit atalk_proc_exit(void)
-{
-	remove_proc_entry("interface", atalk_proc_dir);
-	remove_proc_entry("route", atalk_proc_dir);
-	remove_proc_entry("socket", atalk_proc_dir);
-	remove_proc_entry("arp", atalk_proc_dir);
-	remove_proc_entry("atalk", init_net.proc_net);
-}
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
deleted file mode 100644
index c410b93fda2e..000000000000
--- a/net/appletalk/ddp.c
+++ /dev/null
@@ -1,1981 +0,0 @@
-/*
- *	DDP:	An implementation of the AppleTalk DDP protocol for
- *		Ethernet 'ELAP'.
- *
- *		Alan Cox  <alan@lxorguk.ukuu.org.uk>
- *
- *		With more than a little assistance from
- *
- *		Wesley Craig <netatalk@umich.edu>
- *
- *	Fixes:
- *		Neil Horman		:	Added missing device ioctls
- *		Michael Callahan	:	Made routing work
- *		Wesley Craig		:	Fix probing to listen to a
- *						passed node id.
- *		Alan Cox		:	Added send/recvmsg support
- *		Alan Cox		:	Moved at. to protinfo in
- *						socket.
- *		Alan Cox		:	Added firewall hooks.
- *		Alan Cox		:	Supports new ARPHRD_LOOPBACK
- *		Christer Weinigel	: 	Routing and /proc fixes.
- *		Bradford Johnson	:	LocalTalk.
- *		Tom Dyas		:	Module support.
- *		Alan Cox		:	Hooks for PPP (based on the
- *						LocalTalk hook).
- *		Alan Cox		:	Posix bits
- *		Alan Cox/Mike Freeman	:	Possible fix to NBP problems
- *		Bradford Johnson	:	IP-over-DDP (experimental)
- *		Jay Schulist		:	Moved IP-over-DDP to its own
- *						driver file. (ipddp.c & ipddp.h)
- *		Jay Schulist		:	Made work as module with
- *						AppleTalk drivers, cleaned it.
- *		Rob Newberry		:	Added proxy AARP and AARP
- *						procfs, moved probing to AARP
- *						module.
- *              Adrian Sun/
- *              Michael Zuelsdorff      :       fix for net.0 packets. don't
- *                                              allow illegal ether/tokentalk
- *                                              port assignment. we lose a
- *                                              valid localtalk port as a
- *                                              result.
- *		Arnaldo C. de Melo	:	Cleanup, in preparation for
- *						shared skb support 8)
- *		Arnaldo C. de Melo	:	Move proc stuff to atalk_proc.c,
- *						use seq_file
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/capability.h>
-#include <linux/module.h>
-#include <linux/if_arp.h>
-#include <linux/smp_lock.h>
-#include <linux/termios.h>	/* For TIOCOUTQ/INQ */
-#include <linux/compat.h>
-#include <linux/slab.h>
-#include <net/datalink.h>
-#include <net/psnap.h>
-#include <net/sock.h>
-#include <net/tcp_states.h>
-#include <net/route.h>
-#include <linux/atalk.h>
-#include "../core/kmap_skb.h"
-
-struct datalink_proto *ddp_dl, *aarp_dl;
-static const struct proto_ops atalk_dgram_ops;
-
-/**************************************************************************\
-*                                                                          *
-* Handlers for the socket list.                                            *
-*                                                                          *
-\**************************************************************************/
-
-HLIST_HEAD(atalk_sockets);
-DEFINE_RWLOCK(atalk_sockets_lock);
-
-static inline void __atalk_insert_socket(struct sock *sk)
-{
-	sk_add_node(sk, &atalk_sockets);
-}
-
-static inline void atalk_remove_socket(struct sock *sk)
-{
-	write_lock_bh(&atalk_sockets_lock);
-	sk_del_node_init(sk);
-	write_unlock_bh(&atalk_sockets_lock);
-}
-
-static struct sock *atalk_search_socket(struct sockaddr_at *to,
-					struct atalk_iface *atif)
-{
-	struct sock *s;
-	struct hlist_node *node;
-
-	read_lock_bh(&atalk_sockets_lock);
-	sk_for_each(s, node, &atalk_sockets) {
-		struct atalk_sock *at = at_sk(s);
-
-		if (to->sat_port != at->src_port)
-			continue;
-
-		if (to->sat_addr.s_net == ATADDR_ANYNET &&
-		    to->sat_addr.s_node == ATADDR_BCAST)
-			goto found;
-
-		if (to->sat_addr.s_net == at->src_net &&
-		    (to->sat_addr.s_node == at->src_node ||
-		     to->sat_addr.s_node == ATADDR_BCAST ||
-		     to->sat_addr.s_node == ATADDR_ANYNODE))
-			goto found;
-
-		/* XXXX.0 -- we got a request for this router. make sure
-		 * that the node is appropriately set. */
-		if (to->sat_addr.s_node == ATADDR_ANYNODE &&
-		    to->sat_addr.s_net != ATADDR_ANYNET &&
-		    atif->address.s_node == at->src_node) {
-			to->sat_addr.s_node = atif->address.s_node;
-			goto found;
-		}
-	}
-	s = NULL;
-found:
-	read_unlock_bh(&atalk_sockets_lock);
-	return s;
-}
-
-/**
- * atalk_find_or_insert_socket - Try to find a socket matching ADDR
- * @sk - socket to insert in the list if it is not there already
- * @sat - address to search for
- *
- * Try to find a socket matching ADDR in the socket list, if found then return
- * it. If not, insert SK into the socket list.
- *
- * This entire operation must execute atomically.
- */
-static struct sock *atalk_find_or_insert_socket(struct sock *sk,
-						struct sockaddr_at *sat)
-{
-	struct sock *s;
-	struct hlist_node *node;
-	struct atalk_sock *at;
-
-	write_lock_bh(&atalk_sockets_lock);
-	sk_for_each(s, node, &atalk_sockets) {
-		at = at_sk(s);
-
-		if (at->src_net == sat->sat_addr.s_net &&
-		    at->src_node == sat->sat_addr.s_node &&
-		    at->src_port == sat->sat_port)
-			goto found;
-	}
-	s = NULL;
-	__atalk_insert_socket(sk); /* Wheee, it's free, assign and insert. */
-found:
-	write_unlock_bh(&atalk_sockets_lock);
-	return s;
-}
-
-static void atalk_destroy_timer(unsigned long data)
-{
-	struct sock *sk = (struct sock *)data;
-
-	if (sk_has_allocations(sk)) {
-		sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME;
-		add_timer(&sk->sk_timer);
-	} else
-		sock_put(sk);
-}
-
-static inline void atalk_destroy_socket(struct sock *sk)
-{
-	atalk_remove_socket(sk);
-	skb_queue_purge(&sk->sk_receive_queue);
-
-	if (sk_has_allocations(sk)) {
-		setup_timer(&sk->sk_timer, atalk_destroy_timer,
-				(unsigned long)sk);
-		sk->sk_timer.expires	= jiffies + SOCK_DESTROY_TIME;
-		add_timer(&sk->sk_timer);
-	} else
-		sock_put(sk);
-}
-
-/**************************************************************************\
-*                                                                          *
-* Routing tables for the AppleTalk socket layer.                           *
-*                                                                          *
-\**************************************************************************/
-
-/* Anti-deadlock ordering is atalk_routes_lock --> iface_lock -DaveM */
-struct atalk_route *atalk_routes;
-DEFINE_RWLOCK(atalk_routes_lock);
-
-struct atalk_iface *atalk_interfaces;
-DEFINE_RWLOCK(atalk_interfaces_lock);
-
-/* For probing devices or in a routerless network */
-struct atalk_route atrtr_default;
-
-/* AppleTalk interface control */
-/*
- * Drop a device. Doesn't drop any of its routes - that is the caller's
- * problem. Called when we down the interface or delete the address.
- */
-static void atif_drop_device(struct net_device *dev)
-{
-	struct atalk_iface **iface = &atalk_interfaces;
-	struct atalk_iface *tmp;
-
-	write_lock_bh(&atalk_interfaces_lock);
-	while ((tmp = *iface) != NULL) {
-		if (tmp->dev == dev) {
-			*iface = tmp->next;
-			dev_put(dev);
-			kfree(tmp);
-			dev->atalk_ptr = NULL;
-		} else
-			iface = &tmp->next;
-	}
-	write_unlock_bh(&atalk_interfaces_lock);
-}
-
-static struct atalk_iface *atif_add_device(struct net_device *dev,
-					   struct atalk_addr *sa)
-{
-	struct atalk_iface *iface = kzalloc(sizeof(*iface), GFP_KERNEL);
-
-	if (!iface)
-		goto out;
-
-	dev_hold(dev);
-	iface->dev = dev;
-	dev->atalk_ptr = iface;
-	iface->address = *sa;
-	iface->status = 0;
-
-	write_lock_bh(&atalk_interfaces_lock);
-	iface->next = atalk_interfaces;
-	atalk_interfaces = iface;
-	write_unlock_bh(&atalk_interfaces_lock);
-out:
-	return iface;
-}
-
-/* Perform phase 2 AARP probing on our tentative address */
-static int atif_probe_device(struct atalk_iface *atif)
-{
-	int netrange = ntohs(atif->nets.nr_lastnet) -
-			ntohs(atif->nets.nr_firstnet) + 1;
-	int probe_net = ntohs(atif->address.s_net);
-	int probe_node = atif->address.s_node;
-	int netct, nodect;
-
-	/* Offset the network we start probing with */
-	if (probe_net == ATADDR_ANYNET) {
-		probe_net = ntohs(atif->nets.nr_firstnet);
-		if (netrange)
-			probe_net += jiffies % netrange;
-	}
-	if (probe_node == ATADDR_ANYNODE)
-		probe_node = jiffies & 0xFF;
-
-	/* Scan the networks */
-	atif->status |= ATIF_PROBE;
-	for (netct = 0; netct <= netrange; netct++) {
-		/* Sweep the available nodes from a given start */
-		atif->address.s_net = htons(probe_net);
-		for (nodect = 0; nodect < 256; nodect++) {
-			atif->address.s_node = (nodect + probe_node) & 0xFF;
-			if (atif->address.s_node > 0 &&
-			    atif->address.s_node < 254) {
-				/* Probe a proposed address */
-				aarp_probe_network(atif);
-
-				if (!(atif->status & ATIF_PROBE_FAIL)) {
-					atif->status &= ~ATIF_PROBE;
-					return 0;
-				}
-			}
-			atif->status &= ~ATIF_PROBE_FAIL;
-		}
-		probe_net++;
-		if (probe_net > ntohs(atif->nets.nr_lastnet))
-			probe_net = ntohs(atif->nets.nr_firstnet);
-	}
-	atif->status &= ~ATIF_PROBE;
-
-	return -EADDRINUSE;	/* Network is full... */
-}
-
-
-/* Perform AARP probing for a proxy address */
-static int atif_proxy_probe_device(struct atalk_iface *atif,
-				   struct atalk_addr* proxy_addr)
-{
-	int netrange = ntohs(atif->nets.nr_lastnet) -
-			ntohs(atif->nets.nr_firstnet) + 1;
-	/* we probe the interface's network */
-	int probe_net = ntohs(atif->address.s_net);
-	int probe_node = ATADDR_ANYNODE;	    /* we'll take anything */
-	int netct, nodect;
-
-	/* Offset the network we start probing with */
-	if (probe_net == ATADDR_ANYNET) {
-		probe_net = ntohs(atif->nets.nr_firstnet);
-		if (netrange)
-			probe_net += jiffies % netrange;
-	}
-
-	if (probe_node == ATADDR_ANYNODE)
-		probe_node = jiffies & 0xFF;
-
-	/* Scan the networks */
-	for (netct = 0; netct <= netrange; netct++) {
-		/* Sweep the available nodes from a given start */
-		proxy_addr->s_net = htons(probe_net);
-		for (nodect = 0; nodect < 256; nodect++) {
-			proxy_addr->s_node = (nodect + probe_node) & 0xFF;
-			if (proxy_addr->s_node > 0 &&
-			    proxy_addr->s_node < 254) {
-				/* Tell AARP to probe a proposed address */
-				int ret = aarp_proxy_probe_network(atif,
-								    proxy_addr);
-
-				if (ret != -EADDRINUSE)
-					return ret;
-			}
-		}
-		probe_net++;
-		if (probe_net > ntohs(atif->nets.nr_lastnet))
-			probe_net = ntohs(atif->nets.nr_firstnet);
-	}
-
-	return -EADDRINUSE;	/* Network is full... */
-}
-
-
-struct atalk_addr *atalk_find_dev_addr(struct net_device *dev)
-{
-	struct atalk_iface *iface = dev->atalk_ptr;
-	return iface ? &iface->address : NULL;
-}
-
-static struct atalk_addr *atalk_find_primary(void)
-{
-	struct atalk_iface *fiface = NULL;
-	struct atalk_addr *retval;
-	struct atalk_iface *iface;
-
-	/*
-	 * Return a point-to-point interface only if
-	 * there is no non-ptp interface available.
-	 */
-	read_lock_bh(&atalk_interfaces_lock);
-	for (iface = atalk_interfaces; iface; iface = iface->next) {
-		if (!fiface && !(iface->dev->flags & IFF_LOOPBACK))
-			fiface = iface;
-		if (!(iface->dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))) {
-			retval = &iface->address;
-			goto out;
-		}
-	}
-
-	if (fiface)
-		retval = &fiface->address;
-	else if (atalk_interfaces)
-		retval = &atalk_interfaces->address;
-	else
-		retval = NULL;
-out:
-	read_unlock_bh(&atalk_interfaces_lock);
-	return retval;
-}
-
-/*
- * Find a match for 'any network' - ie any of our interfaces with that
- * node number will do just nicely.
- */
-static struct atalk_iface *atalk_find_anynet(int node, struct net_device *dev)
-{
-	struct atalk_iface *iface = dev->atalk_ptr;
-
-	if (!iface || iface->status & ATIF_PROBE)
-		goto out_err;
-
-	if (node != ATADDR_BCAST &&
-	    iface->address.s_node != node &&
-	    node != ATADDR_ANYNODE)
-		goto out_err;
-out:
-	return iface;
-out_err:
-	iface = NULL;
-	goto out;
-}
-
-/* Find a match for a specific network:node pair */
-static struct atalk_iface *atalk_find_interface(__be16 net, int node)
-{
-	struct atalk_iface *iface;
-
-	read_lock_bh(&atalk_interfaces_lock);
-	for (iface = atalk_interfaces; iface; iface = iface->next) {
-		if ((node == ATADDR_BCAST ||
-		     node == ATADDR_ANYNODE ||
-		     iface->address.s_node == node) &&
-		    iface->address.s_net == net &&
-		    !(iface->status & ATIF_PROBE))
-			break;
-
-		/* XXXX.0 -- net.0 returns the iface associated with net */
-		if (node == ATADDR_ANYNODE && net != ATADDR_ANYNET &&
-		    ntohs(iface->nets.nr_firstnet) <= ntohs(net) &&
-		    ntohs(net) <= ntohs(iface->nets.nr_lastnet))
-			break;
-	}
-	read_unlock_bh(&atalk_interfaces_lock);
-	return iface;
-}
-
-
-/*
- * Find a route for an AppleTalk packet. This ought to get cached in
- * the socket (later on...). We know about host routes and the fact
- * that a route must be direct to broadcast.
- */
-static struct atalk_route *atrtr_find(struct atalk_addr *target)
-{
-	/*
-	 * we must search through all routes unless we find a
-	 * host route, because some host routes might overlap
-	 * network routes
-	 */
-	struct atalk_route *net_route = NULL;
-	struct atalk_route *r;
-
-	read_lock_bh(&atalk_routes_lock);
-	for (r = atalk_routes; r; r = r->next) {
-		if (!(r->flags & RTF_UP))
-			continue;
-
-		if (r->target.s_net == target->s_net) {
-			if (r->flags & RTF_HOST) {
-				/*
-				 * if this host route is for the target,
-				 * the we're done
-				 */
-				if (r->target.s_node == target->s_node)
-					goto out;
-			} else
-				/*
-				 * this route will work if there isn't a
-				 * direct host route, so cache it
-				 */
-				net_route = r;
-		}
-	}
-
-	/*
-	 * if we found a network route but not a direct host
-	 * route, then return it
-	 */
-	if (net_route)
-		r = net_route;
-	else if (atrtr_default.dev)
-		r = &atrtr_default;
-	else /* No route can be found */
-		r = NULL;
-out:
-	read_unlock_bh(&atalk_routes_lock);
-	return r;
-}
-
-
-/*
- * Given an AppleTalk network, find the device to use. This can be
- * a simple lookup.
- */
-struct net_device *atrtr_get_dev(struct atalk_addr *sa)
-{
-	struct atalk_route *atr = atrtr_find(sa);
-	return atr ? atr->dev : NULL;
-}
-
-/* Set up a default router */
-static void atrtr_set_default(struct net_device *dev)
-{
-	atrtr_default.dev	     = dev;
-	atrtr_default.flags	     = RTF_UP;
-	atrtr_default.gateway.s_net  = htons(0);
-	atrtr_default.gateway.s_node = 0;
-}
-
-/*
- * Add a router. Basically make sure it looks valid and stuff the
- * entry in the list. While it uses netranges we always set them to one
- * entry to work like netatalk.
- */
-static int atrtr_create(struct rtentry *r, struct net_device *devhint)
-{
-	struct sockaddr_at *ta = (struct sockaddr_at *)&r->rt_dst;
-	struct sockaddr_at *ga = (struct sockaddr_at *)&r->rt_gateway;
-	struct atalk_route *rt;
-	struct atalk_iface *iface, *riface;
-	int retval = -EINVAL;
-
-	/*
-	 * Fixme: Raise/Lower a routing change semaphore for these
-	 * operations.
-	 */
-
-	/* Validate the request */
-	if (ta->sat_family != AF_APPLETALK ||
-	    (!devhint && ga->sat_family != AF_APPLETALK))
-		goto out;
-
-	/* Now walk the routing table and make our decisions */
-	write_lock_bh(&atalk_routes_lock);
-	for (rt = atalk_routes; rt; rt = rt->next) {
-		if (r->rt_flags != rt->flags)
-			continue;
-
-		if (ta->sat_addr.s_net == rt->target.s_net) {
-			if (!(rt->flags & RTF_HOST))
-				break;
-			if (ta->sat_addr.s_node == rt->target.s_node)
-				break;
-		}
-	}
-
-	if (!devhint) {
-		riface = NULL;
-
-		read_lock_bh(&atalk_interfaces_lock);
-		for (iface = atalk_interfaces; iface; iface = iface->next) {
-			if (!riface &&
-			    ntohs(ga->sat_addr.s_net) >=
-					ntohs(iface->nets.nr_firstnet) &&
-			    ntohs(ga->sat_addr.s_net) <=
-					ntohs(iface->nets.nr_lastnet))
-				riface = iface;
-
-			if (ga->sat_addr.s_net == iface->address.s_net &&
-			    ga->sat_addr.s_node == iface->address.s_node)
-				riface = iface;
-		}
-		read_unlock_bh(&atalk_interfaces_lock);
-
-		retval = -ENETUNREACH;
-		if (!riface)
-			goto out_unlock;
-
-		devhint = riface->dev;
-	}
-
-	if (!rt) {
-		rt = kzalloc(sizeof(*rt), GFP_ATOMIC);
-
-		retval = -ENOBUFS;
-		if (!rt)
-			goto out_unlock;
-
-		rt->next = atalk_routes;
-		atalk_routes = rt;
-	}
-
-	/* Fill in the routing entry */
-	rt->target  = ta->sat_addr;
-	dev_hold(devhint);
-	rt->dev     = devhint;
-	rt->flags   = r->rt_flags;
-	rt->gateway = ga->sat_addr;
-
-	retval = 0;
-out_unlock:
-	write_unlock_bh(&atalk_routes_lock);
-out:
-	return retval;
-}
-
-/* Delete a route. Find it and discard it */
-static int atrtr_delete(struct atalk_addr * addr)
-{
-	struct atalk_route **r = &atalk_routes;
-	int retval = 0;
-	struct atalk_route *tmp;
-
-	write_lock_bh(&atalk_routes_lock);
-	while ((tmp = *r) != NULL) {
-		if (tmp->target.s_net == addr->s_net &&
-		    (!(tmp->flags&RTF_GATEWAY) ||
-		     tmp->target.s_node == addr->s_node)) {
-			*r = tmp->next;
-			dev_put(tmp->dev);
-			kfree(tmp);
-			goto out;
-		}
-		r = &tmp->next;
-	}
-	retval = -ENOENT;
-out:
-	write_unlock_bh(&atalk_routes_lock);
-	return retval;
-}
-
-/*
- * Called when a device is downed. Just throw away any routes
- * via it.
- */
-static void atrtr_device_down(struct net_device *dev)
-{
-	struct atalk_route **r = &atalk_routes;
-	struct atalk_route *tmp;
-
-	write_lock_bh(&atalk_routes_lock);
-	while ((tmp = *r) != NULL) {
-		if (tmp->dev == dev) {
-			*r = tmp->next;
-			dev_put(dev);
-			kfree(tmp);
-		} else
-			r = &tmp->next;
-	}
-	write_unlock_bh(&atalk_routes_lock);
-
-	if (atrtr_default.dev == dev)
-		atrtr_set_default(NULL);
-}
-
-/* Actually down the interface */
-static inline void atalk_dev_down(struct net_device *dev)
-{
-	atrtr_device_down(dev);	/* Remove all routes for the device */
-	aarp_device_down(dev);	/* Remove AARP entries for the device */
-	atif_drop_device(dev);	/* Remove the device */
-}
-
-/*
- * A device event has occurred. Watch for devices going down and
- * delete our use of them (iface and route).
- */
-static int ddp_device_event(struct notifier_block *this, unsigned long event,
-			    void *ptr)
-{
-	struct net_device *dev = ptr;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
-	if (event == NETDEV_DOWN)
-		/* Discard any use of this */
-		atalk_dev_down(dev);
-
-	return NOTIFY_DONE;
-}
-
-/* ioctl calls. Shouldn't even need touching */
-/* Device configuration ioctl calls */
-static int atif_ioctl(int cmd, void __user *arg)
-{
-	static char aarp_mcast[6] = { 0x09, 0x00, 0x00, 0xFF, 0xFF, 0xFF };
-	struct ifreq atreq;
-	struct atalk_netrange *nr;
-	struct sockaddr_at *sa;
-	struct net_device *dev;
-	struct atalk_iface *atif;
-	int ct;
-	int limit;
-	struct rtentry rtdef;
-	int add_route;
-
-	if (copy_from_user(&atreq, arg, sizeof(atreq)))
-		return -EFAULT;
-
-	dev = __dev_get_by_name(&init_net, atreq.ifr_name);
-	if (!dev)
-		return -ENODEV;
-
-	sa = (struct sockaddr_at *)&atreq.ifr_addr;
-	atif = atalk_find_dev(dev);
-
-	switch (cmd) {
-		case SIOCSIFADDR:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			if (dev->type != ARPHRD_ETHER &&
-			    dev->type != ARPHRD_LOOPBACK &&
-			    dev->type != ARPHRD_LOCALTLK &&
-			    dev->type != ARPHRD_PPP)
-				return -EPROTONOSUPPORT;
-
-			nr = (struct atalk_netrange *)&sa->sat_zero[0];
-			add_route = 1;
-
-			/*
-			 * if this is a point-to-point iface, and we already
-			 * have an iface for this AppleTalk address, then we
-			 * should not add a route
-			 */
-			if ((dev->flags & IFF_POINTOPOINT) &&
-			    atalk_find_interface(sa->sat_addr.s_net,
-						 sa->sat_addr.s_node)) {
-				printk(KERN_DEBUG "AppleTalk: point-to-point "
-						  "interface added with "
-						  "existing address\n");
-				add_route = 0;
-			}
-
-			/*
-			 * Phase 1 is fine on LocalTalk but we don't do
-			 * EtherTalk phase 1. Anyone wanting to add it go ahead.
-			 */
-			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
-				return -EPROTONOSUPPORT;
-			if (sa->sat_addr.s_node == ATADDR_BCAST ||
-			    sa->sat_addr.s_node == 254)
-				return -EINVAL;
-			if (atif) {
-				/* Already setting address */
-				if (atif->status & ATIF_PROBE)
-					return -EBUSY;
-
-				atif->address.s_net  = sa->sat_addr.s_net;
-				atif->address.s_node = sa->sat_addr.s_node;
-				atrtr_device_down(dev);	/* Flush old routes */
-			} else {
-				atif = atif_add_device(dev, &sa->sat_addr);
-				if (!atif)
-					return -ENOMEM;
-			}
-			atif->nets = *nr;
-
-			/*
-			 * Check if the chosen address is used. If so we
-			 * error and atalkd will try another.
-			 */
-
-			if (!(dev->flags & IFF_LOOPBACK) &&
-			    !(dev->flags & IFF_POINTOPOINT) &&
-			    atif_probe_device(atif) < 0) {
-				atif_drop_device(dev);
-				return -EADDRINUSE;
-			}
-
-			/* Hey it worked - add the direct routes */
-			sa = (struct sockaddr_at *)&rtdef.rt_gateway;
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_net  = atif->address.s_net;
-			sa->sat_addr.s_node = atif->address.s_node;
-			sa = (struct sockaddr_at *)&rtdef.rt_dst;
-			rtdef.rt_flags = RTF_UP;
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_node = ATADDR_ANYNODE;
-			if (dev->flags & IFF_LOOPBACK ||
-			    dev->flags & IFF_POINTOPOINT)
-				rtdef.rt_flags |= RTF_HOST;
-
-			/* Routerless initial state */
-			if (nr->nr_firstnet == htons(0) &&
-			    nr->nr_lastnet == htons(0xFFFE)) {
-				sa->sat_addr.s_net = atif->address.s_net;
-				atrtr_create(&rtdef, dev);
-				atrtr_set_default(dev);
-			} else {
-				limit = ntohs(nr->nr_lastnet);
-				if (limit - ntohs(nr->nr_firstnet) > 4096) {
-					printk(KERN_WARNING "Too many routes/"
-							    "iface.\n");
-					return -EINVAL;
-				}
-				if (add_route)
-					for (ct = ntohs(nr->nr_firstnet);
-					     ct <= limit; ct++) {
-						sa->sat_addr.s_net = htons(ct);
-						atrtr_create(&rtdef, dev);
-					}
-			}
-			dev_mc_add_global(dev, aarp_mcast);
-			return 0;
-
-		case SIOCGIFADDR:
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr = atif->address;
-			break;
-
-		case SIOCGIFBRDADDR:
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_net = atif->address.s_net;
-			sa->sat_addr.s_node = ATADDR_BCAST;
-			break;
-
-		case SIOCATALKDIFADDR:
-		case SIOCDIFADDR:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			atalk_dev_down(dev);
-			break;
-
-		case SIOCSARP:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			/*
-			 * for now, we only support proxy AARP on ELAP;
-			 * we should be able to do it for LocalTalk, too.
-			 */
-			if (dev->type != ARPHRD_ETHER)
-				return -EPROTONOSUPPORT;
-
-			/*
-			 * atif points to the current interface on this network;
-			 * we aren't concerned about its current status (at
-			 * least for now), but it has all the settings about
-			 * the network we're going to probe. Consequently, it
-			 * must exist.
-			 */
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			nr = (struct atalk_netrange *)&(atif->nets);
-			/*
-			 * Phase 1 is fine on Localtalk but we don't do
-			 * Ethertalk phase 1. Anyone wanting to add it go ahead.
-			 */
-			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
-				return -EPROTONOSUPPORT;
-
-			if (sa->sat_addr.s_node == ATADDR_BCAST ||
-			    sa->sat_addr.s_node == 254)
-				return -EINVAL;
-
-			/*
-			 * Check if the chosen address is used. If so we
-			 * error and ATCP will try another.
-			 */
-			if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0)
-				return -EADDRINUSE;
-
-			/*
-			 * We now have an address on the local network, and
-			 * the AARP code will defend it for us until we take it
-			 * down. We don't set up any routes right now, because
-			 * ATCP will install them manually via SIOCADDRT.
-			 */
-			break;
-
-		case SIOCDARP:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			/* give to aarp module to remove proxy entry */
-			aarp_proxy_remove(atif->dev, &(sa->sat_addr));
-			return 0;
-	}
-
-	return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0;
-}
-
-/* Routing ioctl() calls */
-static int atrtr_ioctl(unsigned int cmd, void __user *arg)
-{
-	struct rtentry rt;
-
-	if (copy_from_user(&rt, arg, sizeof(rt)))
-		return -EFAULT;
-
-	switch (cmd) {
-		case SIOCDELRT:
-			if (rt.rt_dst.sa_family != AF_APPLETALK)
-				return -EINVAL;
-			return atrtr_delete(&((struct sockaddr_at *)
-						&rt.rt_dst)->sat_addr);
-
-		case SIOCADDRT: {
-			struct net_device *dev = NULL;
-			if (rt.rt_dev) {
-				char name[IFNAMSIZ];
-				if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1))
-					return -EFAULT;
-				name[IFNAMSIZ-1] = '\0';
-				dev = __dev_get_by_name(&init_net, name);
-				if (!dev)
-					return -ENODEV;
-			}
-			return atrtr_create(&rt, dev);
-		}
-	}
-	return -EINVAL;
-}
-
-/**************************************************************************\
-*                                                                          *
-* Handling for system calls applied via the various interfaces to an       *
-* AppleTalk socket object.                                                 *
-*                                                                          *
-\**************************************************************************/
-
-/*
- * Checksum: This is 'optional'. It's quite likely also a good
- * candidate for assembler hackery 8)
- */
-static unsigned long atalk_sum_partial(const unsigned char *data,
-				       int len, unsigned long sum)
-{
-	/* This ought to be unwrapped neatly. I'll trust gcc for now */
-	while (len--) {
-		sum += *data++;
-		sum = rol16(sum, 1);
-	}
-	return sum;
-}
-
-/*  Checksum skb data --  similar to skb_checksum  */
-static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
-				   int len, unsigned long sum)
-{
-	int start = skb_headlen(skb);
-	struct sk_buff *frag_iter;
-	int i, copy;
-
-	/* checksum stuff in header space */
-	if ( (copy = start - offset) > 0) {
-		if (copy > len)
-			copy = len;
-		sum = atalk_sum_partial(skb->data + offset, copy, sum);
-		if ( (len -= copy) == 0)
-			return sum;
-
-		offset += copy;
-	}
-
-	/* checksum stuff in frags */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_shinfo(skb)->frags[i].size;
-		if ((copy = end - offset) > 0) {
-			u8 *vaddr;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-			if (copy > len)
-				copy = len;
-			vaddr = kmap_skb_frag(frag);
-			sum = atalk_sum_partial(vaddr + frag->page_offset +
-						  offset - start, copy, sum);
-			kunmap_skb_frag(vaddr);
-
-			if (!(len -= copy))
-				return sum;
-			offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			if (copy > len)
-				copy = len;
-			sum = atalk_sum_skb(frag_iter, offset - start,
-					    copy, sum);
-			if ((len -= copy) == 0)
-				return sum;
-			offset += copy;
-		}
-		start = end;
-	}
-
-	BUG_ON(len > 0);
-
-	return sum;
-}
-
-static __be16 atalk_checksum(const struct sk_buff *skb, int len)
-{
-	unsigned long sum;
-
-	/* skip header 4 bytes */
-	sum = atalk_sum_skb(skb, 4, len-4, 0);
-
-	/* Use 0xFFFF for 0. 0 itself means none */
-	return sum ? htons((unsigned short)sum) : htons(0xFFFF);
-}
-
-static struct proto ddp_proto = {
-	.name	  = "DDP",
-	.owner	  = THIS_MODULE,
-	.obj_size = sizeof(struct atalk_sock),
-};
-
-/*
- * Create a socket. Initialise the socket, blank the addresses
- * set the state.
- */
-static int atalk_create(struct net *net, struct socket *sock, int protocol,
-			int kern)
-{
-	struct sock *sk;
-	int rc = -ESOCKTNOSUPPORT;
-
-	if (!net_eq(net, &init_net))
-		return -EAFNOSUPPORT;
-
-	/*
-	 * We permit SOCK_DGRAM and RAW is an extension. It is trivial to do
-	 * and gives you the full ELAP frame. Should be handy for CAP 8)
-	 */
-	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
-		goto out;
-	rc = -ENOMEM;
-	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto);
-	if (!sk)
-		goto out;
-	rc = 0;
-	sock->ops = &atalk_dgram_ops;
-	sock_init_data(sock, sk);
-
-	/* Checksums on by default */
-	sock_set_flag(sk, SOCK_ZAPPED);
-out:
-	return rc;
-}
-
-/* Free a socket. No work needed */
-static int atalk_release(struct socket *sock)
-{
-	struct sock *sk = sock->sk;
-
-	lock_kernel();
-	if (sk) {
-		sock_orphan(sk);
-		sock->sk = NULL;
-		atalk_destroy_socket(sk);
-	}
-	unlock_kernel();
-	return 0;
-}
-
-/**
- * atalk_pick_and_bind_port - Pick a source port when one is not given
- * @sk - socket to insert into the tables
- * @sat - address to search for
- *
- * Pick a source port when one is not given. If we can find a suitable free
- * one, we insert the socket into the tables using it.
- *
- * This whole operation must be atomic.
- */
-static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat)
-{
-	int retval;
-
-	write_lock_bh(&atalk_sockets_lock);
-
-	for (sat->sat_port = ATPORT_RESERVED;
-	     sat->sat_port < ATPORT_LAST;
-	     sat->sat_port++) {
-		struct sock *s;
-		struct hlist_node *node;
-
-		sk_for_each(s, node, &atalk_sockets) {
-			struct atalk_sock *at = at_sk(s);
-
-			if (at->src_net == sat->sat_addr.s_net &&
-			    at->src_node == sat->sat_addr.s_node &&
-			    at->src_port == sat->sat_port)
-				goto try_next_port;
-		}
-
-		/* Wheee, it's free, assign and insert. */
-		__atalk_insert_socket(sk);
-		at_sk(sk)->src_port = sat->sat_port;
-		retval = 0;
-		goto out;
-
-try_next_port:;
-	}
-
-	retval = -EBUSY;
-out:
-	write_unlock_bh(&atalk_sockets_lock);
-	return retval;
-}
-
-static int atalk_autobind(struct sock *sk)
-{
-	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at sat;
-	struct atalk_addr *ap = atalk_find_primary();
-	int n = -EADDRNOTAVAIL;
-
-	if (!ap || ap->s_net == htons(ATADDR_ANYNET))
-		goto out;
-
-	at->src_net  = sat.sat_addr.s_net  = ap->s_net;
-	at->src_node = sat.sat_addr.s_node = ap->s_node;
-
-	n = atalk_pick_and_bind_port(sk, &sat);
-	if (!n)
-		sock_reset_flag(sk, SOCK_ZAPPED);
-out:
-	return n;
-}
-
-/* Set the address 'our end' of the connection */
-static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
-{
-	struct sockaddr_at *addr = (struct sockaddr_at *)uaddr;
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	int err;
-
-	if (!sock_flag(sk, SOCK_ZAPPED) ||
-	    addr_len != sizeof(struct sockaddr_at))
-		return -EINVAL;
-
-	if (addr->sat_family != AF_APPLETALK)
-		return -EAFNOSUPPORT;
-
-	lock_kernel();
-	if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) {
-		struct atalk_addr *ap = atalk_find_primary();
-
-		err = -EADDRNOTAVAIL;
-		if (!ap)
-			goto out;
-
-		at->src_net  = addr->sat_addr.s_net = ap->s_net;
-		at->src_node = addr->sat_addr.s_node= ap->s_node;
-	} else {
-		err = -EADDRNOTAVAIL;
-		if (!atalk_find_interface(addr->sat_addr.s_net,
-					  addr->sat_addr.s_node))
-			goto out;
-
-		at->src_net  = addr->sat_addr.s_net;
-		at->src_node = addr->sat_addr.s_node;
-	}
-
-	if (addr->sat_port == ATADDR_ANYPORT) {
-		err = atalk_pick_and_bind_port(sk, addr);
-
-		if (err < 0)
-			goto out;
-	} else {
-		at->src_port = addr->sat_port;
-
-		err = -EADDRINUSE;
-		if (atalk_find_or_insert_socket(sk, addr))
-			goto out;
-	}
-
-	sock_reset_flag(sk, SOCK_ZAPPED);
-	err = 0;
-out:
-	unlock_kernel();
-	return err;
-}
-
-/* Set the address we talk to */
-static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
-			 int addr_len, int flags)
-{
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at *addr;
-	int err;
-
-	sk->sk_state   = TCP_CLOSE;
-	sock->state = SS_UNCONNECTED;
-
-	if (addr_len != sizeof(*addr))
-		return -EINVAL;
-
-	addr = (struct sockaddr_at *)uaddr;
-
-	if (addr->sat_family != AF_APPLETALK)
-		return -EAFNOSUPPORT;
-
-	if (addr->sat_addr.s_node == ATADDR_BCAST &&
-	    !sock_flag(sk, SOCK_BROADCAST)) {
-#if 1
-		printk(KERN_WARNING "%s is broken and did not set "
-				    "SO_BROADCAST. It will break when 2.2 is "
-				    "released.\n",
-			current->comm);
-#else
-		return -EACCES;
-#endif
-	}
-
-	lock_kernel();
-	err = -EBUSY;
-	if (sock_flag(sk, SOCK_ZAPPED))
-		if (atalk_autobind(sk) < 0)
-			goto out;
-
-	err = -ENETUNREACH;
-	if (!atrtr_get_dev(&addr->sat_addr))
-		goto out;
-
-	at->dest_port = addr->sat_port;
-	at->dest_net  = addr->sat_addr.s_net;
-	at->dest_node = addr->sat_addr.s_node;
-
-	sock->state  = SS_CONNECTED;
-	sk->sk_state = TCP_ESTABLISHED;
-	err = 0;
-out:
-	unlock_kernel();
-	return err;
-}
-
-/*
- * Find the name of an AppleTalk socket. Just copy the right
- * fields into the sockaddr.
- */
-static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
-			 int *uaddr_len, int peer)
-{
-	struct sockaddr_at sat;
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	int err;
-
-	lock_kernel();
-	err = -ENOBUFS;
-	if (sock_flag(sk, SOCK_ZAPPED))
-		if (atalk_autobind(sk) < 0)
-			goto out;
-
-	*uaddr_len = sizeof(struct sockaddr_at);
-	memset(&sat.sat_zero, 0, sizeof(sat.sat_zero));
-
-	if (peer) {
-		err = -ENOTCONN;
-		if (sk->sk_state != TCP_ESTABLISHED)
-			goto out;
-
-		sat.sat_addr.s_net  = at->dest_net;
-		sat.sat_addr.s_node = at->dest_node;
-		sat.sat_port	    = at->dest_port;
-	} else {
-		sat.sat_addr.s_net  = at->src_net;
-		sat.sat_addr.s_node = at->src_node;
-		sat.sat_port	    = at->src_port;
-	}
-
-	err = 0;
-	sat.sat_family = AF_APPLETALK;
-	memcpy(uaddr, &sat, sizeof(sat));
-
-out:
-	unlock_kernel();
-	return err;
-}
-
-static unsigned int atalk_poll(struct file *file, struct socket *sock,
-			   poll_table *wait)
-{
-	int err;
-	lock_kernel();
-	err = datagram_poll(file, sock, wait);
-	unlock_kernel();
-	return err;
-}
-
-#if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE)
-static __inline__ int is_ip_over_ddp(struct sk_buff *skb)
-{
-	return skb->data[12] == 22;
-}
-
-static int handle_ip_over_ddp(struct sk_buff *skb)
-{
-	struct net_device *dev = __dev_get_by_name(&init_net, "ipddp0");
-	struct net_device_stats *stats;
-
-	/* This needs to be able to handle ipddp"N" devices */
-	if (!dev) {
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
-
-	skb->protocol = htons(ETH_P_IP);
-	skb_pull(skb, 13);
-	skb->dev   = dev;
-	skb_reset_transport_header(skb);
-
-	stats = netdev_priv(dev);
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len + 13;
-	return netif_rx(skb);  /* Send the SKB up to a higher place. */
-}
-#else
-/* make it easy for gcc to optimize this test out, i.e. kill the code */
-#define is_ip_over_ddp(skb) 0
-#define handle_ip_over_ddp(skb) 0
-#endif
-
-static int atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
-			      struct ddpehdr *ddp, __u16 len_hops, int origlen)
-{
-	struct atalk_route *rt;
-	struct atalk_addr ta;
-
-	/*
-	 * Don't route multicast, etc., packets, or packets sent to "this
-	 * network"
-	 */
-	if (skb->pkt_type != PACKET_HOST || !ddp->deh_dnet) {
-		/*
-		 * FIXME:
-		 *
-		 * Can it ever happen that a packet is from a PPP iface and
-		 * needs to be broadcast onto the default network?
-		 */
-		if (dev->type == ARPHRD_PPP)
-			printk(KERN_DEBUG "AppleTalk: didn't forward broadcast "
-					  "packet received from PPP iface\n");
-		goto free_it;
-	}
-
-	ta.s_net  = ddp->deh_dnet;
-	ta.s_node = ddp->deh_dnode;
-
-	/* Route the packet */
-	rt = atrtr_find(&ta);
-	/* increment hops count */
-	len_hops += 1 << 10;
-	if (!rt || !(len_hops & (15 << 10)))
-		goto free_it;
-
-	/* FIXME: use skb->cb to be able to use shared skbs */
-
-	/*
-	 * Route goes through another gateway, so set the target to the
-	 * gateway instead.
-	 */
-
-	if (rt->flags & RTF_GATEWAY) {
-		ta.s_net  = rt->gateway.s_net;
-		ta.s_node = rt->gateway.s_node;
-	}
-
-	/* Fix up skb->len field */
-	skb_trim(skb, min_t(unsigned int, origlen,
-			    (rt->dev->hard_header_len +
-			     ddp_dl->header_length + (len_hops & 1023))));
-
-	/* FIXME: use skb->cb to be able to use shared skbs */
-	ddp->deh_len_hops = htons(len_hops);
-
-	/*
-	 * Send the buffer onwards
-	 *
-	 * Now we must always be careful. If it's come from LocalTalk to
-	 * EtherTalk it might not fit
-	 *
-	 * Order matters here: If a packet has to be copied to make a new
-	 * headroom (rare hopefully) then it won't need unsharing.
-	 *
-	 * Note. ddp-> becomes invalid at the realloc.
-	 */
-	if (skb_headroom(skb) < 22) {
-		/* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */
-		struct sk_buff *nskb = skb_realloc_headroom(skb, 32);
-		kfree_skb(skb);
-		skb = nskb;
-	} else
-		skb = skb_unshare(skb, GFP_ATOMIC);
-
-	/*
-	 * If the buffer didn't vanish into the lack of space bitbucket we can
-	 * send it.
-	 */
-	if (skb == NULL)
-		goto drop;
-
-	if (aarp_send_ddp(rt->dev, skb, &ta, NULL) == NET_XMIT_DROP)
-		return NET_RX_DROP;
-	return NET_RX_SUCCESS;
-free_it:
-	kfree_skb(skb);
-drop:
-	return NET_RX_DROP;
-}
-
-/**
- *	atalk_rcv - Receive a packet (in skb) from device dev
- *	@skb - packet received
- *	@dev - network device where the packet comes from
- *	@pt - packet type
- *
- *	Receive a packet (in skb) from device dev. This has come from the SNAP
- *	decoder, and on entry skb->transport_header is the DDP header, skb->len
- *	is the DDP header, skb->len is the DDP length. The physical headers
- *	have been extracted. PPP should probably pass frames marked as for this
- *	layer.  [ie ARPHRD_ETHERTALK]
- */
-static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
-		     struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct ddpehdr *ddp;
-	struct sock *sock;
-	struct atalk_iface *atif;
-	struct sockaddr_at tosat;
-	int origlen;
-	__u16 len_hops;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		goto drop;
-
-	/* Don't mangle buffer if shared */
-	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
-		goto out;
-
-	/* Size check and make sure header is contiguous */
-	if (!pskb_may_pull(skb, sizeof(*ddp)))
-		goto drop;
-
-	ddp = ddp_hdr(skb);
-
-	len_hops = ntohs(ddp->deh_len_hops);
-
-	/* Trim buffer in case of stray trailing data */
-	origlen = skb->len;
-	skb_trim(skb, min_t(unsigned int, skb->len, len_hops & 1023));
-
-	/*
-	 * Size check to see if ddp->deh_len was crap
-	 * (Otherwise we'll detonate most spectacularly
-	 * in the middle of atalk_checksum() or recvmsg()).
-	 */
-	if (skb->len < sizeof(*ddp) || skb->len < (len_hops & 1023)) {
-		pr_debug("AppleTalk: dropping corrupted frame (deh_len=%u, "
-			 "skb->len=%u)\n", len_hops & 1023, skb->len);
-		goto drop;
-	}
-
-	/*
-	 * Any checksums. Note we don't do htons() on this == is assumed to be
-	 * valid for net byte orders all over the networking code...
-	 */
-	if (ddp->deh_sum &&
-	    atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum)
-		/* Not a valid AppleTalk frame - dustbin time */
-		goto drop;
-
-	/* Check the packet is aimed at us */
-	if (!ddp->deh_dnet)	/* Net 0 is 'this network' */
-		atif = atalk_find_anynet(ddp->deh_dnode, dev);
-	else
-		atif = atalk_find_interface(ddp->deh_dnet, ddp->deh_dnode);
-
-	if (!atif) {
-		/* Not ours, so we route the packet via the correct
-		 * AppleTalk iface
-		 */
-		return atalk_route_packet(skb, dev, ddp, len_hops, origlen);
-	}
-
-	/* if IP over DDP is not selected this code will be optimized out */
-	if (is_ip_over_ddp(skb))
-		return handle_ip_over_ddp(skb);
-	/*
-	 * Which socket - atalk_search_socket() looks for a *full match*
-	 * of the <net, node, port> tuple.
-	 */
-	tosat.sat_addr.s_net  = ddp->deh_dnet;
-	tosat.sat_addr.s_node = ddp->deh_dnode;
-	tosat.sat_port	      = ddp->deh_dport;
-
-	sock = atalk_search_socket(&tosat, atif);
-	if (!sock) /* But not one of our sockets */
-		goto drop;
-
-	/* Queue packet (standard) */
-	skb->sk = sock;
-
-	if (sock_queue_rcv_skb(sock, skb) < 0)
-		goto drop;
-
-	return NET_RX_SUCCESS;
-
-drop:
-	kfree_skb(skb);
-out:
-	return NET_RX_DROP;
-
-}
-
-/*
- * Receive a LocalTalk frame. We make some demands on the caller here.
- * Caller must provide enough headroom on the packet to pull the short
- * header and append a long one.
- */
-static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
-		     struct packet_type *pt, struct net_device *orig_dev)
-{
-	if (!net_eq(dev_net(dev), &init_net))
-		goto freeit;
-
-	/* Expand any short form frames */
-	if (skb_mac_header(skb)[2] == 1) {
-		struct ddpehdr *ddp;
-		/* Find our address */
-		struct atalk_addr *ap = atalk_find_dev_addr(dev);
-
-		if (!ap || skb->len < sizeof(__be16) || skb->len > 1023)
-			goto freeit;
-
-		/* Don't mangle buffer if shared */
-		if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
-			return 0;
-
-		/*
-		 * The push leaves us with a ddephdr not an shdr, and
-		 * handily the port bytes in the right place preset.
-		 */
-		ddp = (struct ddpehdr *) skb_push(skb, sizeof(*ddp) - 4);
-
-		/* Now fill in the long header */
-
-		/*
-		 * These two first. The mac overlays the new source/dest
-		 * network information so we MUST copy these before
-		 * we write the network numbers !
-		 */
-
-		ddp->deh_dnode = skb_mac_header(skb)[0];     /* From physical header */
-		ddp->deh_snode = skb_mac_header(skb)[1];     /* From physical header */
-
-		ddp->deh_dnet  = ap->s_net;	/* Network number */
-		ddp->deh_snet  = ap->s_net;
-		ddp->deh_sum   = 0;		/* No checksum */
-		/*
-		 * Not sure about this bit...
-		 */
-		/* Non routable, so force a drop if we slip up later */
-		ddp->deh_len_hops = htons(skb->len + (DDP_MAXHOPS << 10));
-	}
-	skb_reset_transport_header(skb);
-
-	return atalk_rcv(skb, dev, pt, orig_dev);
-freeit:
-	kfree_skb(skb);
-	return 0;
-}
-
-static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-			 size_t len)
-{
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name;
-	int flags = msg->msg_flags;
-	int loopback = 0;
-	struct sockaddr_at local_satalk, gsat;
-	struct sk_buff *skb;
-	struct net_device *dev;
-	struct ddpehdr *ddp;
-	int size;
-	struct atalk_route *rt;
-	int err;
-
-	if (flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
-		return -EINVAL;
-
-	if (len > DDP_MAXSZ)
-		return -EMSGSIZE;
-
-	lock_kernel();
-	if (usat) {
-		err = -EBUSY;
-		if (sock_flag(sk, SOCK_ZAPPED))
-			if (atalk_autobind(sk) < 0)
-				goto out;
-
-		err = -EINVAL;
-		if (msg->msg_namelen < sizeof(*usat) ||
-		    usat->sat_family != AF_APPLETALK)
-			goto out;
-
-		err = -EPERM;
-		/* netatalk didn't implement this check */
-		if (usat->sat_addr.s_node == ATADDR_BCAST &&
-		    !sock_flag(sk, SOCK_BROADCAST)) {
-			goto out;
-		}
-	} else {
-		err = -ENOTCONN;
-		if (sk->sk_state != TCP_ESTABLISHED)
-			goto out;
-		usat = &local_satalk;
-		usat->sat_family      = AF_APPLETALK;
-		usat->sat_port	      = at->dest_port;
-		usat->sat_addr.s_node = at->dest_node;
-		usat->sat_addr.s_net  = at->dest_net;
-	}
-
-	/* Build a packet */
-	SOCK_DEBUG(sk, "SK %p: Got address.\n", sk);
-
-	/* For headers */
-	size = sizeof(struct ddpehdr) + len + ddp_dl->header_length;
-
-	if (usat->sat_addr.s_net || usat->sat_addr.s_node == ATADDR_ANYNODE) {
-		rt = atrtr_find(&usat->sat_addr);
-	} else {
-		struct atalk_addr at_hint;
-
-		at_hint.s_node = 0;
-		at_hint.s_net  = at->src_net;
-
-		rt = atrtr_find(&at_hint);
-	}
-	err = ENETUNREACH;
-	if (!rt)
-		goto out;
-
-	dev = rt->dev;
-
-	SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n",
-			sk, size, dev->name);
-
-	size += dev->hard_header_len;
-	skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err);
-	if (!skb)
-		goto out;
-
-	skb->sk = sk;
-	skb_reserve(skb, ddp_dl->header_length);
-	skb_reserve(skb, dev->hard_header_len);
-	skb->dev = dev;
-
-	SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk);
-
-	ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr));
-	ddp->deh_len_hops  = htons(len + sizeof(*ddp));
-	ddp->deh_dnet  = usat->sat_addr.s_net;
-	ddp->deh_snet  = at->src_net;
-	ddp->deh_dnode = usat->sat_addr.s_node;
-	ddp->deh_snode = at->src_node;
-	ddp->deh_dport = usat->sat_port;
-	ddp->deh_sport = at->src_port;
-
-	SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len);
-
-	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
-	if (err) {
-		kfree_skb(skb);
-		err = -EFAULT;
-		goto out;
-	}
-
-	if (sk->sk_no_check == 1)
-		ddp->deh_sum = 0;
-	else
-		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
-
-	/*
-	 * Loopback broadcast packets to non gateway targets (ie routes
-	 * to group we are in)
-	 */
-	if (ddp->deh_dnode == ATADDR_BCAST &&
-	    !(rt->flags & RTF_GATEWAY) && !(dev->flags & IFF_LOOPBACK)) {
-		struct sk_buff *skb2 = skb_copy(skb, GFP_KERNEL);
-
-		if (skb2) {
-			loopback = 1;
-			SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk);
-			/*
-			 * If it fails it is queued/sent above in the aarp queue
-			 */
-			aarp_send_ddp(dev, skb2, &usat->sat_addr, NULL);
-		}
-	}
-
-	if (dev->flags & IFF_LOOPBACK || loopback) {
-		SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk);
-		/* loop back */
-		skb_orphan(skb);
-		if (ddp->deh_dnode == ATADDR_BCAST) {
-			struct atalk_addr at_lo;
-
-			at_lo.s_node = 0;
-			at_lo.s_net  = 0;
-
-			rt = atrtr_find(&at_lo);
-			if (!rt) {
-				kfree_skb(skb);
-				err = -ENETUNREACH;
-				goto out;
-			}
-			dev = rt->dev;
-			skb->dev = dev;
-		}
-		ddp_dl->request(ddp_dl, skb, dev->dev_addr);
-	} else {
-		SOCK_DEBUG(sk, "SK %p: send out.\n", sk);
-		if (rt->flags & RTF_GATEWAY) {
-		    gsat.sat_addr = rt->gateway;
-		    usat = &gsat;
-		}
-
-		/*
-		 * If it fails it is queued/sent above in the aarp queue
-		 */
-		aarp_send_ddp(dev, skb, &usat->sat_addr, NULL);
-	}
-	SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len);
-
-out:
-	unlock_kernel();
-	return err ? : len;
-}
-
-static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-			 size_t size, int flags)
-{
-	struct sock *sk = sock->sk;
-	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
-	struct ddpehdr *ddp;
-	int copied = 0;
-	int offset = 0;
-	int err = 0;
-	struct sk_buff *skb;
-
-	lock_kernel();
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-						flags & MSG_DONTWAIT, &err);
-	if (!skb)
-		goto out;
-
-	/* FIXME: use skb->cb to be able to use shared skbs */
-	ddp = ddp_hdr(skb);
-	copied = ntohs(ddp->deh_len_hops) & 1023;
-
-	if (sk->sk_type != SOCK_RAW) {
-		offset = sizeof(*ddp);
-		copied -= offset;
-	}
-
-	if (copied > size) {
-		copied = size;
-		msg->msg_flags |= MSG_TRUNC;
-	}
-	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
-
-	if (!err) {
-		if (sat) {
-			sat->sat_family      = AF_APPLETALK;
-			sat->sat_port        = ddp->deh_sport;
-			sat->sat_addr.s_node = ddp->deh_snode;
-			sat->sat_addr.s_net  = ddp->deh_snet;
-		}
-		msg->msg_namelen = sizeof(*sat);
-	}
-
-	skb_free_datagram(sk, skb);	/* Free the datagram. */
-
-out:
-	unlock_kernel();
-	return err ? : copied;
-}
-
-
-/*
- * AppleTalk ioctl calls.
- */
-static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
-{
-	int rc = -ENOIOCTLCMD;
-	struct sock *sk = sock->sk;
-	void __user *argp = (void __user *)arg;
-
-	switch (cmd) {
-		/* Protocol layer */
-		case TIOCOUTQ: {
-			long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
-
-			if (amount < 0)
-				amount = 0;
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case TIOCINQ: {
-			/*
-			 * These two are safe on a single CPU system as only
-			 * user tasks fiddle here
-			 */
-			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-			long amount = 0;
-
-			if (skb)
-				amount = skb->len - sizeof(struct ddpehdr);
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case SIOCGSTAMP:
-			rc = sock_get_timestamp(sk, argp);
-			break;
-		case SIOCGSTAMPNS:
-			rc = sock_get_timestampns(sk, argp);
-			break;
-		/* Routing */
-		case SIOCADDRT:
-		case SIOCDELRT:
-			rc = -EPERM;
-			if (capable(CAP_NET_ADMIN))
-				rc = atrtr_ioctl(cmd, argp);
-			break;
-		/* Interface */
-		case SIOCGIFADDR:
-		case SIOCSIFADDR:
-		case SIOCGIFBRDADDR:
-		case SIOCATALKDIFADDR:
-		case SIOCDIFADDR:
-		case SIOCSARP:		/* proxy AARP */
-		case SIOCDARP:		/* proxy AARP */
-			rtnl_lock();
-			rc = atif_ioctl(cmd, argp);
-			rtnl_unlock();
-			break;
-	}
-
-	return rc;
-}
-
-
-#ifdef CONFIG_COMPAT
-static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
-{
-	/*
-	 * SIOCATALKDIFADDR is a SIOCPROTOPRIVATE ioctl number, so we
-	 * cannot handle it in common code. The data we access if ifreq
-	 * here is compatible, so we can simply call the native
-	 * handler.
-	 */
-	if (cmd == SIOCATALKDIFADDR)
-		return atalk_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
-
-	return -ENOIOCTLCMD;
-}
-#endif
-
-
-static const struct net_proto_family atalk_family_ops = {
-	.family		= PF_APPLETALK,
-	.create		= atalk_create,
-	.owner		= THIS_MODULE,
-};
-
-static const struct proto_ops atalk_dgram_ops = {
-	.family		= PF_APPLETALK,
-	.owner		= THIS_MODULE,
-	.release	= atalk_release,
-	.bind		= atalk_bind,
-	.connect	= atalk_connect,
-	.socketpair	= sock_no_socketpair,
-	.accept		= sock_no_accept,
-	.getname	= atalk_getname,
-	.poll		= atalk_poll,
-	.ioctl		= atalk_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= atalk_compat_ioctl,
-#endif
-	.listen		= sock_no_listen,
-	.shutdown	= sock_no_shutdown,
-	.setsockopt	= sock_no_setsockopt,
-	.getsockopt	= sock_no_getsockopt,
-	.sendmsg	= atalk_sendmsg,
-	.recvmsg	= atalk_recvmsg,
-	.mmap		= sock_no_mmap,
-	.sendpage	= sock_no_sendpage,
-};
-
-static struct notifier_block ddp_notifier = {
-	.notifier_call	= ddp_device_event,
-};
-
-static struct packet_type ltalk_packet_type __read_mostly = {
-	.type		= cpu_to_be16(ETH_P_LOCALTALK),
-	.func		= ltalk_rcv,
-};
-
-static struct packet_type ppptalk_packet_type __read_mostly = {
-	.type		= cpu_to_be16(ETH_P_PPPTALK),
-	.func		= atalk_rcv,
-};
-
-static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B };
-
-/* Export symbols for use by drivers when AppleTalk is a module */
-EXPORT_SYMBOL(atrtr_get_dev);
-EXPORT_SYMBOL(atalk_find_dev_addr);
-
-static const char atalk_err_snap[] __initconst =
-	KERN_CRIT "Unable to register DDP with SNAP.\n";
-
-/* Called by proto.c on kernel start up */
-static int __init atalk_init(void)
-{
-	int rc = proto_register(&ddp_proto, 0);
-
-	if (rc != 0)
-		goto out;
-
-	(void)sock_register(&atalk_family_ops);
-	ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
-	if (!ddp_dl)
-		printk(atalk_err_snap);
-
-	dev_add_pack(&ltalk_packet_type);
-	dev_add_pack(&ppptalk_packet_type);
-
-	register_netdevice_notifier(&ddp_notifier);
-	aarp_proto_init();
-	atalk_proc_init();
-	atalk_register_sysctl();
-out:
-	return rc;
-}
-module_init(atalk_init);
-
-/*
- * No explicit module reference count manipulation is needed in the
- * protocol. Socket layer sets module reference count for us
- * and interfaces reference counting is done
- * by the network device layer.
- *
- * Ergo, before the AppleTalk module can be removed, all AppleTalk
- * sockets be closed from user space.
- */
-static void __exit atalk_exit(void)
-{
-#ifdef CONFIG_SYSCTL
-	atalk_unregister_sysctl();
-#endif /* CONFIG_SYSCTL */
-	atalk_proc_exit();
-	aarp_cleanup_module();	/* General aarp clean-up. */
-	unregister_netdevice_notifier(&ddp_notifier);
-	dev_remove_pack(&ltalk_packet_type);
-	dev_remove_pack(&ppptalk_packet_type);
-	unregister_snap_client(ddp_dl);
-	sock_unregister(PF_APPLETALK);
-	proto_unregister(&ddp_proto);
-}
-module_exit(atalk_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alan Cox <alan@lxorguk.ukuu.org.uk>");
-MODULE_DESCRIPTION("AppleTalk 0.20\n");
-MODULE_ALIAS_NETPROTO(PF_APPLETALK);
diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c
deleted file mode 100644
index 6c8016f61866..000000000000
--- a/net/appletalk/dev.c
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Moved here from drivers/net/net_init.c, which is:
- *	Written 1993,1994,1995 by Donald Becker.
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/if_arp.h>
-#include <linux/if_ltalk.h>
-
-static void ltalk_setup(struct net_device *dev)
-{
-	/* Fill in the fields of the device structure with localtalk-generic values. */
-
-	dev->type		= ARPHRD_LOCALTLK;
-	dev->hard_header_len 	= LTALK_HLEN;
-	dev->mtu		= LTALK_MTU;
-	dev->addr_len		= LTALK_ALEN;
-	dev->tx_queue_len	= 10;
-
-	dev->broadcast[0]	= 0xFF;
-
-	dev->flags		= IFF_BROADCAST|IFF_MULTICAST|IFF_NOARP;
-}
-
-/**
- * alloc_ltalkdev - Allocates and sets up an localtalk device
- * @sizeof_priv: Size of additional driver-private structure to be allocated
- *	for this localtalk device
- *
- * Fill in the fields of the device structure with localtalk-generic
- * values. Basically does everything except registering the device.
- *
- * Constructs a new net device, complete with a private data area of
- * size @sizeof_priv.  A 32-byte (not bit) alignment is enforced for
- * this private data area.
- */
-
-struct net_device *alloc_ltalkdev(int sizeof_priv)
-{
-	return alloc_netdev(sizeof_priv, "lt%d", ltalk_setup);
-}
-EXPORT_SYMBOL(alloc_ltalkdev);
diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
deleted file mode 100644
index 04e9c0da7aa9..000000000000
--- a/net/appletalk/sysctl_net_atalk.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * sysctl_net_atalk.c: sysctl interface to net AppleTalk subsystem.
- *
- * Begun April 1, 1996, Mike Shaver.
- * Added /proc/sys/net/atalk directory entry (empty =) ). [MS]
- * Dynamic registration, added aarp entries. (5/30/97 Chris Horn)
- */
-
-#include <linux/sysctl.h>
-#include <net/sock.h>
-#include <linux/atalk.h>
-
-static struct ctl_table atalk_table[] = {
-	{
-		.procname	= "aarp-expiry-time",
-		.data		= &sysctl_aarp_expiry_time,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "aarp-tick-time",
-		.data		= &sysctl_aarp_tick_time,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "aarp-retransmit-limit",
-		.data		= &sysctl_aarp_retransmit_limit,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "aarp-resolve-time",
-		.data		= &sysctl_aarp_resolve_time,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{ },
-};
-
-static struct ctl_path atalk_path[] = {
-	{ .procname = "net", },
-	{ .procname = "appletalk", },
-	{ }
-};
-
-static struct ctl_table_header *atalk_table_header;
-
-void atalk_register_sysctl(void)
-{
-	atalk_table_header = register_sysctl_paths(atalk_path, atalk_table);
-}
-
-void atalk_unregister_sysctl(void)
-{
-	unregister_sysctl_table(atalk_table_header);
-}
diff --git a/net/socket.c b/net/socket.c
index ac2219f90d5d..26f7bcf36810 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -103,7 +103,6 @@
 #include <linux/ipv6_route.h>
 #include <linux/route.h>
 #include <linux/sockios.h>
-#include <linux/atalk.h>
 
 static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
 static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-- 
cgit v1.2.3


From 0ffbf8bf21db0186e9fbb024a1796c3148790578 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@suse.de>
Date: Mon, 31 Jan 2011 14:03:00 -0800
Subject: Revert "appletalk: move to staging"

This reverts commit a6238f21736af3f47bdebf3895f477f5f23f1af9

Appletalk got some patches to fix up the BLK usage in it in the
network tree, so this removal isn't needed.

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: <acme@ghostprotocols.net>
Cc: netdev@vger.kernel.org,
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 MAINTAINERS                                  |    3 +-
 drivers/net/Makefile                         |    1 +
 drivers/net/appletalk/Kconfig                |  126 ++
 drivers/net/appletalk/Makefile               |    7 +
 drivers/net/appletalk/cops.c                 | 1013 +++++++++++++
 drivers/net/appletalk/cops.h                 |   60 +
 drivers/net/appletalk/cops_ffdrv.h           |  532 +++++++
 drivers/net/appletalk/cops_ltdrv.h           |  241 ++++
 drivers/net/appletalk/ipddp.c                |  335 +++++
 drivers/net/appletalk/ipddp.h                |   27 +
 drivers/net/appletalk/ltpc.c                 | 1288 +++++++++++++++++
 drivers/net/appletalk/ltpc.h                 |   73 +
 drivers/staging/Kconfig                      |    2 -
 drivers/staging/Makefile                     |    1 -
 drivers/staging/appletalk/Kconfig            |  126 --
 drivers/staging/appletalk/Makefile           |   12 -
 drivers/staging/appletalk/aarp.c             | 1063 --------------
 drivers/staging/appletalk/atalk.h            |  208 ---
 drivers/staging/appletalk/atalk_proc.c       |  301 ----
 drivers/staging/appletalk/cops.c             | 1013 -------------
 drivers/staging/appletalk/cops.h             |   60 -
 drivers/staging/appletalk/cops_ffdrv.h       |  532 -------
 drivers/staging/appletalk/cops_ltdrv.h       |  241 ----
 drivers/staging/appletalk/ddp.c              | 1981 --------------------------
 drivers/staging/appletalk/dev.c              |   44 -
 drivers/staging/appletalk/ipddp.c            |  335 -----
 drivers/staging/appletalk/ipddp.h            |   27 -
 drivers/staging/appletalk/ltpc.c             | 1288 -----------------
 drivers/staging/appletalk/ltpc.h             |   73 -
 drivers/staging/appletalk/sysctl_net_atalk.c |   61 -
 fs/compat_ioctl.c                            |    1 +
 include/linux/Kbuild                         |    1 +
 include/linux/atalk.h                        |  208 +++
 net/Kconfig                                  |    1 +
 net/Makefile                                 |    1 +
 net/appletalk/Makefile                       |    9 +
 net/appletalk/aarp.c                         | 1063 ++++++++++++++
 net/appletalk/atalk_proc.c                   |  301 ++++
 net/appletalk/ddp.c                          | 1981 ++++++++++++++++++++++++++
 net/appletalk/dev.c                          |   44 +
 net/appletalk/sysctl_net_atalk.c             |   61 +
 net/socket.c                                 |    1 +
 42 files changed, 7377 insertions(+), 7369 deletions(-)
 create mode 100644 drivers/net/appletalk/Kconfig
 create mode 100644 drivers/net/appletalk/Makefile
 create mode 100644 drivers/net/appletalk/cops.c
 create mode 100644 drivers/net/appletalk/cops.h
 create mode 100644 drivers/net/appletalk/cops_ffdrv.h
 create mode 100644 drivers/net/appletalk/cops_ltdrv.h
 create mode 100644 drivers/net/appletalk/ipddp.c
 create mode 100644 drivers/net/appletalk/ipddp.h
 create mode 100644 drivers/net/appletalk/ltpc.c
 create mode 100644 drivers/net/appletalk/ltpc.h
 delete mode 100644 drivers/staging/appletalk/Kconfig
 delete mode 100644 drivers/staging/appletalk/Makefile
 delete mode 100644 drivers/staging/appletalk/aarp.c
 delete mode 100644 drivers/staging/appletalk/atalk.h
 delete mode 100644 drivers/staging/appletalk/atalk_proc.c
 delete mode 100644 drivers/staging/appletalk/cops.c
 delete mode 100644 drivers/staging/appletalk/cops.h
 delete mode 100644 drivers/staging/appletalk/cops_ffdrv.h
 delete mode 100644 drivers/staging/appletalk/cops_ltdrv.h
 delete mode 100644 drivers/staging/appletalk/ddp.c
 delete mode 100644 drivers/staging/appletalk/dev.c
 delete mode 100644 drivers/staging/appletalk/ipddp.c
 delete mode 100644 drivers/staging/appletalk/ipddp.h
 delete mode 100644 drivers/staging/appletalk/ltpc.c
 delete mode 100644 drivers/staging/appletalk/ltpc.h
 delete mode 100644 drivers/staging/appletalk/sysctl_net_atalk.c
 create mode 100644 include/linux/atalk.h
 create mode 100644 net/appletalk/Makefile
 create mode 100644 net/appletalk/aarp.c
 create mode 100644 net/appletalk/atalk_proc.c
 create mode 100644 net/appletalk/ddp.c
 create mode 100644 net/appletalk/dev.c
 create mode 100644 net/appletalk/sysctl_net_atalk.c

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 3118d67d68fb..dd6ca456cde3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -554,7 +554,8 @@ F:	drivers/hwmon/applesmc.c
 APPLETALK NETWORK LAYER
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 S:	Maintained
-F:	drivers/staging/appletalk/
+F:	drivers/net/appletalk/
+F:	net/appletalk/
 
 ARC FRAMEBUFFER DRIVER
 M:	Jaya Kumar <jayalk@intworks.biz>
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 11a9c053f0c8..b90738d13994 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -265,6 +265,7 @@ obj-$(CONFIG_MACB) += macb.o
 obj-$(CONFIG_S6GMAC) += s6gmac.o
 
 obj-$(CONFIG_ARM) += arm/
+obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_TR) += tokenring/
 obj-$(CONFIG_WAN) += wan/
 obj-$(CONFIG_ARCNET) += arcnet/
diff --git a/drivers/net/appletalk/Kconfig b/drivers/net/appletalk/Kconfig
new file mode 100644
index 000000000000..0b376a990972
--- /dev/null
+++ b/drivers/net/appletalk/Kconfig
@@ -0,0 +1,126 @@
+#
+# Appletalk driver configuration
+#
+config ATALK
+	tristate "Appletalk protocol support"
+	depends on BKL # waiting to be removed from net/appletalk/ddp.c
+	select LLC
+	---help---
+	  AppleTalk is the protocol that Apple computers can use to communicate
+	  on a network.  If your Linux box is connected to such a network and you
+	  wish to connect to it, say Y.  You will need to use the netatalk package
+	  so that your Linux box can act as a print and file server for Macs as
+	  well as access AppleTalk printers.  Check out
+	  <http://www.zettabyte.net/netatalk/> on the WWW for details.
+	  EtherTalk is the name used for AppleTalk over Ethernet and the
+	  cheaper and slower LocalTalk is AppleTalk over a proprietary Apple
+	  network using serial links.  EtherTalk and LocalTalk are fully
+	  supported by Linux.
+
+	  General information about how to connect Linux, Windows machines and
+	  Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>.  The
+	  NET3-4-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>, contains valuable
+	  information as well.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called appletalk. You almost certainly want to compile it as a
+	  module so you can restart your AppleTalk stack without rebooting
+	  your machine. I hear that the GNU boycott of Apple is over, so
+	  even politically correct people are allowed to say Y here.
+
+config DEV_APPLETALK
+	tristate "Appletalk interfaces support"
+	depends on ATALK
+	help
+	  AppleTalk is the protocol that Apple computers can use to communicate
+	  on a network.  If your Linux box is connected to such a network, and wish
+	  to do IP over it, or you have a LocalTalk card and wish to use it to
+	  connect to the AppleTalk network, say Y.
+	  
+
+config LTPC
+	tristate "Apple/Farallon LocalTalk PC support"
+	depends on DEV_APPLETALK && (ISA || EISA) && ISA_DMA_API
+	help
+	  This allows you to use the AppleTalk PC card to connect to LocalTalk
+	  networks. The card is also known as the Farallon PhoneNet PC card.
+	  If you are in doubt, this card is the one with the 65C02 chip on it.
+	  You also need version 1.3.3 or later of the netatalk package.
+	  This driver is experimental, which means that it may not work.
+	  See the file <file:Documentation/networking/ltpc.txt>.
+
+config COPS
+	tristate "COPS LocalTalk PC support"
+	depends on DEV_APPLETALK && (ISA || EISA)
+	help
+	  This allows you to use COPS AppleTalk cards to connect to LocalTalk
+	  networks. You also need version 1.3.3 or later of the netatalk
+	  package. This driver is experimental, which means that it may not
+	  work. This driver will only work if you choose "AppleTalk DDP"
+	  networking support, above.
+	  Please read the file <file:Documentation/networking/cops.txt>.
+
+config COPS_DAYNA
+	bool "Dayna firmware support"
+	depends on COPS
+	help
+	  Support COPS compatible cards with Dayna style firmware (Dayna
+	  DL2000/ Daynatalk/PC (half length), COPS LT-95, Farallon PhoneNET PC
+	  III, Farallon PhoneNET PC II).
+
+config COPS_TANGENT
+	bool "Tangent firmware support"
+	depends on COPS
+	help
+	  Support COPS compatible cards with Tangent style firmware (Tangent
+	  ATB_II, Novell NL-1000, Daystar Digital LT-200.
+
+config IPDDP
+	tristate "Appletalk-IP driver support"
+	depends on DEV_APPLETALK && ATALK
+	---help---
+	  This allows IP networking for users who only have AppleTalk
+	  networking available. This feature is experimental. With this
+	  driver, you can encapsulate IP inside AppleTalk (e.g. if your Linux
+	  box is stuck on an AppleTalk only network) or decapsulate (e.g. if
+	  you want your Linux box to act as an Internet gateway for a zoo of
+	  AppleTalk connected Macs). Please see the file
+	  <file:Documentation/networking/ipddp.txt> for more information.
+
+	  If you say Y here, the AppleTalk-IP support will be compiled into
+	  the kernel. In this case, you can either use encapsulation or
+	  decapsulation, but not both. With the following two questions, you
+	  decide which one you want.
+
+	  To compile the AppleTalk-IP support as a module, choose M here: the
+	  module will be called ipddp.
+	  In this case, you will be able to use both encapsulation and
+	  decapsulation simultaneously, by loading two copies of the module
+	  and specifying different values for the module option ipddp_mode.
+
+config IPDDP_ENCAP
+	bool "IP to Appletalk-IP Encapsulation support"
+	depends on IPDDP
+	help
+	  If you say Y here, the AppleTalk-IP code will be able to encapsulate
+	  IP packets inside AppleTalk frames; this is useful if your Linux box
+	  is stuck on an AppleTalk network (which hopefully contains a
+	  decapsulator somewhere). Please see
+	  <file:Documentation/networking/ipddp.txt> for more information. If
+	  you said Y to "AppleTalk-IP driver support" above and you say Y
+	  here, then you cannot say Y to "AppleTalk-IP to IP Decapsulation
+	  support", below.
+
+config IPDDP_DECAP
+	bool "Appletalk-IP to IP Decapsulation support"
+	depends on IPDDP
+	help
+	  If you say Y here, the AppleTalk-IP code will be able to decapsulate
+	  AppleTalk-IP frames to IP packets; this is useful if you want your
+	  Linux box to act as an Internet gateway for an AppleTalk network.
+	  Please see <file:Documentation/networking/ipddp.txt> for more
+	  information.  If you said Y to "AppleTalk-IP driver support" above
+	  and you say Y here, then you cannot say Y to "IP to AppleTalk-IP
+	  Encapsulation support", above.
+
diff --git a/drivers/net/appletalk/Makefile b/drivers/net/appletalk/Makefile
new file mode 100644
index 000000000000..6cfc705f7c5c
--- /dev/null
+++ b/drivers/net/appletalk/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for drivers/net/appletalk
+#
+
+obj-$(CONFIG_IPDDP) += ipddp.o
+obj-$(CONFIG_COPS) += cops.o
+obj-$(CONFIG_LTPC) += ltpc.o
diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c
new file mode 100644
index 000000000000..748c9f526e71
--- /dev/null
+++ b/drivers/net/appletalk/cops.c
@@ -0,0 +1,1013 @@
+/*      cops.c: LocalTalk driver for Linux.
+ *
+ *	Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ *
+ *	With more than a little help from;
+ *	- Alan Cox <alan@lxorguk.ukuu.org.uk>
+ *
+ *      Derived from:
+ *      - skeleton.c: A network driver outline for linux.
+ *        Written 1993-94 by Donald Becker.
+ *	- ltpc.c: A driver for the LocalTalk PC card.
+ *	  Written by Bradford W. Johnson.
+ *
+ *      Copyright 1993 United States Government as represented by the
+ *      Director, National Security Agency.
+ *
+ *      This software may be used and distributed according to the terms
+ *      of the GNU General Public License, incorporated herein by reference.
+ *
+ *	Changes:
+ *	19970608	Alan Cox	Allowed dual card type support
+ *					Can set board type in insmod
+ *					Hooks for cops_setup routine
+ *					(not yet implemented).
+ *	19971101	Jay Schulist	Fixes for multiple lt* devices.
+ *	19980607	Steven Hirsch	Fixed the badly broken support
+ *					for Tangent type cards. Only
+ *                                      tested on Daystar LT200. Some
+ *                                      cleanup of formatting and program
+ *                                      logic.  Added emacs 'local-vars'
+ *                                      setup for Jay's brace style.
+ *	20000211	Alan Cox	Cleaned up for softnet
+ */
+
+static const char *version =
+"cops.c:v0.04 6/7/98 Jay Schulist <jschlst@samba.org>\n";
+/*
+ *  Sources:
+ *      COPS Localtalk SDK. This provides almost all of the information
+ *      needed.
+ */
+
+/*
+ * insmod/modprobe configurable stuff.
+ *	- IO Port, choose one your card supports or 0 if you dare.
+ *	- IRQ, also choose one your card supports or nothing and let
+ *	  the driver figure it out.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/in.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/if_ltalk.h>
+#include <linux/delay.h>	/* For udelay() */
+#include <linux/atalk.h>
+#include <linux/spinlock.h>
+#include <linux/bitops.h>
+#include <linux/jiffies.h>
+
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/dma.h>
+
+#include "cops.h"		/* Our Stuff */
+#include "cops_ltdrv.h"		/* Firmware code for Tangent type cards. */
+#include "cops_ffdrv.h"		/* Firmware code for Dayna type cards. */
+
+/*
+ *      The name of the card. Is used for messages and in the requests for
+ *      io regions, irqs and dma channels
+ */
+
+static const char *cardname = "cops";
+
+#ifdef CONFIG_COPS_DAYNA
+static int board_type = DAYNA;	/* Module exported */
+#else
+static int board_type = TANGENT;
+#endif
+
+static int io = 0x240;		/* Default IO for Dayna */
+static int irq = 5;		/* Default IRQ */
+
+/*
+ *	COPS Autoprobe information.
+ *	Right now if port address is right but IRQ is not 5 this will
+ *      return a 5 no matter what since we will still get a status response.
+ *      Need one more additional check to narrow down after we have gotten
+ *      the ioaddr. But since only other possible IRQs is 3 and 4 so no real
+ *	hurry on this. I *STRONGLY* recommend using IRQ 5 for your card with
+ *	this driver.
+ * 
+ *	This driver has 2 modes and they are: Dayna mode and Tangent mode.
+ *	Each mode corresponds with the type of card. It has been found
+ *	that there are 2 main types of cards and all other cards are
+ *	the same and just have different names or only have minor differences
+ *	such as more IO ports. As this driver is tested it will
+ *	become more clear on exactly what cards are supported. The driver
+ *	defaults to using Dayna mode. To change the drivers mode, simply
+ *	select Dayna or Tangent mode when configuring the kernel.
+ *
+ *      This driver should support:
+ *      TANGENT driver mode:
+ *              Tangent ATB-II, Novell NL-1000, Daystar Digital LT-200,
+ *		COPS LT-1
+ *      DAYNA driver mode:
+ *              Dayna DL2000/DaynaTalk PC (Half Length), COPS LT-95, 
+ *		Farallon PhoneNET PC III, Farallon PhoneNET PC II
+ *	Other cards possibly supported mode unknown though:
+ *		Dayna DL2000 (Full length), COPS LT/M (Micro-Channel)
+ *
+ *	Cards NOT supported by this driver but supported by the ltpc.c
+ *	driver written by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *		Farallon PhoneNET PC
+ *		Original Apple LocalTalk PC card
+ * 
+ *      N.B.
+ *
+ *      The Daystar Digital LT200 boards do not support interrupt-driven
+ *      IO.  You must specify 'irq=0xff' as a module parameter to invoke
+ *      polled mode.  I also believe that the port probing logic is quite
+ *      dangerous at best and certainly hopeless for a polled card.  Best to 
+ *      specify both. - Steve H.
+ *
+ */
+
+/*
+ * Zero terminated list of IO ports to probe.
+ */
+
+static unsigned int ports[] = { 
+	0x240, 0x340, 0x200, 0x210, 0x220, 0x230, 0x260, 
+	0x2A0, 0x300, 0x310, 0x320, 0x330, 0x350, 0x360,
+	0
+};
+
+/*
+ * Zero terminated list of IRQ ports to probe.
+ */
+
+static int cops_irqlist[] = {
+	5, 4, 3, 0 
+};
+
+static struct timer_list cops_timer;
+
+/* use 0 for production, 1 for verification, 2 for debug, 3 for verbose debug */
+#ifndef COPS_DEBUG
+#define COPS_DEBUG 1 
+#endif
+static unsigned int cops_debug = COPS_DEBUG;
+
+/* The number of low I/O ports used by the card. */
+#define COPS_IO_EXTENT       8
+
+/* Information that needs to be kept for each board. */
+
+struct cops_local
+{
+        int board;			/* Holds what board type is. */
+	int nodeid;			/* Set to 1 once have nodeid. */
+        unsigned char node_acquire;	/* Node ID when acquired. */
+        struct atalk_addr node_addr;	/* Full node address */
+	spinlock_t lock;		/* RX/TX lock */
+};
+
+/* Index to functions, as function prototypes. */
+static int  cops_probe1 (struct net_device *dev, int ioaddr);
+static int  cops_irq (int ioaddr, int board);
+
+static int  cops_open (struct net_device *dev);
+static int  cops_jumpstart (struct net_device *dev);
+static void cops_reset (struct net_device *dev, int sleep);
+static void cops_load (struct net_device *dev);
+static int  cops_nodeid (struct net_device *dev, int nodeid);
+
+static irqreturn_t cops_interrupt (int irq, void *dev_id);
+static void cops_poll (unsigned long ltdev);
+static void cops_timeout(struct net_device *dev);
+static void cops_rx (struct net_device *dev);
+static netdev_tx_t  cops_send_packet (struct sk_buff *skb,
+					    struct net_device *dev);
+static void set_multicast_list (struct net_device *dev);
+static int  cops_ioctl (struct net_device *dev, struct ifreq *rq, int cmd);
+static int  cops_close (struct net_device *dev);
+
+static void cleanup_card(struct net_device *dev)
+{
+	if (dev->irq)
+		free_irq(dev->irq, dev);
+	release_region(dev->base_addr, COPS_IO_EXTENT);
+}
+
+/*
+ *      Check for a network adaptor of this type, and return '0' iff one exists.
+ *      If dev->base_addr == 0, probe all likely locations.
+ *      If dev->base_addr in [1..0x1ff], always return failure.
+ *        otherwise go with what we pass in.
+ */
+struct net_device * __init cops_probe(int unit)
+{
+	struct net_device *dev;
+	unsigned *port;
+	int base_addr;
+	int err = 0;
+
+	dev = alloc_ltalkdev(sizeof(struct cops_local));
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	if (unit >= 0) {
+		sprintf(dev->name, "lt%d", unit);
+		netdev_boot_setup_check(dev);
+		irq = dev->irq;
+		base_addr = dev->base_addr;
+	} else {
+		base_addr = dev->base_addr = io;
+	}
+
+	if (base_addr > 0x1ff) {    /* Check a single specified location. */
+		err = cops_probe1(dev, base_addr);
+	} else if (base_addr != 0) { /* Don't probe at all. */
+		err = -ENXIO;
+	} else {
+		/* FIXME  Does this really work for cards which generate irq?
+		 * It's definitely N.G. for polled Tangent. sh
+		 * Dayna cards don't autoprobe well at all, but if your card is
+		 * at IRQ 5 & IO 0x240 we find it every time. ;) JS
+		 */
+		for (port = ports; *port && cops_probe1(dev, *port) < 0; port++)
+			;
+		if (!*port)
+			err = -ENODEV;
+	}
+	if (err)
+		goto out;
+	err = register_netdev(dev);
+	if (err)
+		goto out1;
+	return dev;
+out1:
+	cleanup_card(dev);
+out:
+	free_netdev(dev);
+	return ERR_PTR(err);
+}
+
+static const struct net_device_ops cops_netdev_ops = {
+	.ndo_open               = cops_open,
+        .ndo_stop               = cops_close,
+	.ndo_start_xmit   	= cops_send_packet,
+	.ndo_tx_timeout		= cops_timeout,
+        .ndo_do_ioctl           = cops_ioctl,
+	.ndo_set_multicast_list = set_multicast_list,
+};
+
+/*
+ *      This is the real probe routine. Linux has a history of friendly device
+ *      probes on the ISA bus. A good device probes avoids doing writes, and
+ *      verifies that the correct device exists and functions.
+ */
+static int __init cops_probe1(struct net_device *dev, int ioaddr)
+{
+        struct cops_local *lp;
+	static unsigned version_printed;
+	int board = board_type;
+	int retval;
+	
+        if(cops_debug && version_printed++ == 0)
+		printk("%s", version);
+
+	/* Grab the region so no one else tries to probe our ioports. */
+	if (!request_region(ioaddr, COPS_IO_EXTENT, dev->name))
+		return -EBUSY;
+
+        /*
+         * Since this board has jumpered interrupts, allocate the interrupt
+         * vector now. There is no point in waiting since no other device
+         * can use the interrupt, and this marks the irq as busy. Jumpered
+         * interrupts are typically not reported by the boards, and we must
+         * used AutoIRQ to find them.
+	 */
+	dev->irq = irq;
+	switch (dev->irq)
+	{
+		case 0:
+			/* COPS AutoIRQ routine */
+			dev->irq = cops_irq(ioaddr, board);
+			if (dev->irq)
+				break;
+			/* No IRQ found on this port, fallthrough */
+		case 1:
+			retval = -EINVAL;
+			goto err_out;
+
+		/* Fixup for users that don't know that IRQ 2 is really
+		 * IRQ 9, or don't know which one to set.
+		 */
+		case 2:
+			dev->irq = 9;
+			break;
+
+		/* Polled operation requested. Although irq of zero passed as
+		 * a parameter tells the init routines to probe, we'll
+		 * overload it to denote polled operation at runtime.
+		 */
+		case 0xff:
+			dev->irq = 0;
+			break;
+
+		default:
+			break;
+	}
+
+	/* Reserve any actual interrupt. */
+	if (dev->irq) {
+		retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev);
+		if (retval)
+			goto err_out;
+	}
+
+	dev->base_addr = ioaddr;
+
+        lp = netdev_priv(dev);
+        spin_lock_init(&lp->lock);
+
+	/* Copy local board variable to lp struct. */
+	lp->board               = board;
+
+	dev->netdev_ops 	= &cops_netdev_ops;
+	dev->watchdog_timeo	= HZ * 2;
+
+
+	/* Tell the user where the card is and what mode we're in. */
+	if(board==DAYNA)
+		printk("%s: %s at %#3x, using IRQ %d, in Dayna mode.\n", 
+			dev->name, cardname, ioaddr, dev->irq);
+	if(board==TANGENT) {
+		if(dev->irq)
+			printk("%s: %s at %#3x, IRQ %d, in Tangent mode\n", 
+				dev->name, cardname, ioaddr, dev->irq);
+		else
+			printk("%s: %s at %#3x, using polled IO, in Tangent mode.\n", 
+				dev->name, cardname, ioaddr);
+
+	}
+        return 0;
+
+err_out:
+	release_region(ioaddr, COPS_IO_EXTENT);
+	return retval;
+}
+
+static int __init cops_irq (int ioaddr, int board)
+{       /*
+         * This does not use the IRQ to determine where the IRQ is. We just
+         * assume that when we get a correct status response that it's the IRQ.
+         * This really just verifies the IO port but since we only have access
+         * to such a small number of IRQs (5, 4, 3) this is not bad.
+         * This will probably not work for more than one card.
+         */
+        int irqaddr=0;
+        int i, x, status;
+
+        if(board==DAYNA)
+        {
+                outb(0, ioaddr+DAYNA_RESET);
+                inb(ioaddr+DAYNA_RESET);
+                mdelay(333);
+        }
+        if(board==TANGENT)
+        {
+                inb(ioaddr);
+                outb(0, ioaddr);
+                outb(0, ioaddr+TANG_RESET);
+        }
+
+        for(i=0; cops_irqlist[i] !=0; i++)
+        {
+                irqaddr = cops_irqlist[i];
+                for(x = 0xFFFF; x>0; x --)    /* wait for response */
+                {
+                        if(board==DAYNA)
+                        {
+                                status = (inb(ioaddr+DAYNA_CARD_STATUS)&3);
+                                if(status == 1)
+                                        return irqaddr;
+                        }
+                        if(board==TANGENT)
+                        {
+                                if((inb(ioaddr+TANG_CARD_STATUS)& TANG_TX_READY) !=0)
+                                        return irqaddr;
+                        }
+                }
+        }
+        return 0;       /* no IRQ found */
+}
+
+/*
+ * Open/initialize the board. This is called (in the current kernel)
+ * sometime after booting when the 'ifconfig' program is run.
+ */
+static int cops_open(struct net_device *dev)
+{
+    struct cops_local *lp = netdev_priv(dev);
+
+	if(dev->irq==0)
+	{
+		/*
+		 * I don't know if the Dayna-style boards support polled 
+		 * operation.  For now, only allow it for Tangent.
+		 */
+		if(lp->board==TANGENT)	/* Poll 20 times per second */
+		{
+		    init_timer(&cops_timer);
+		    cops_timer.function = cops_poll;
+		    cops_timer.data 	= (unsigned long)dev;
+		    cops_timer.expires 	= jiffies + HZ/20;
+		    add_timer(&cops_timer);
+		} 
+		else 
+		{
+			printk(KERN_WARNING "%s: No irq line set\n", dev->name);
+			return -EAGAIN;
+		}
+	}
+
+	cops_jumpstart(dev);	/* Start the card up. */
+
+	netif_start_queue(dev);
+        return 0;
+}
+
+/*
+ *	This allows for a dynamic start/restart of the entire card.
+ */
+static int cops_jumpstart(struct net_device *dev)
+{
+	struct cops_local *lp = netdev_priv(dev);
+
+	/*
+         *      Once the card has the firmware loaded and has acquired
+         *      the nodeid, if it is reset it will lose it all.
+         */
+        cops_reset(dev,1);	/* Need to reset card before load firmware. */
+        cops_load(dev);		/* Load the firmware. */
+
+	/*
+	 *	If atalkd already gave us a nodeid we will use that
+	 *	one again, else we wait for atalkd to give us a nodeid
+	 *	in cops_ioctl. This may cause a problem if someone steals
+	 *	our nodeid while we are resetting.
+	 */	
+	if(lp->nodeid == 1)
+		cops_nodeid(dev,lp->node_acquire);
+
+	return 0;
+}
+
+static void tangent_wait_reset(int ioaddr)
+{
+	int timeout=0;
+
+	while(timeout++ < 5 && (inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
+		mdelay(1);   /* Wait 1 second */
+}
+
+/*
+ *      Reset the LocalTalk board.
+ */
+static void cops_reset(struct net_device *dev, int sleep)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr=dev->base_addr;
+
+        if(lp->board==TANGENT)
+        {
+                inb(ioaddr);		/* Clear request latch. */
+                outb(0,ioaddr);		/* Clear the TANG_TX_READY flop. */
+                outb(0, ioaddr+TANG_RESET);	/* Reset the adapter. */
+
+		tangent_wait_reset(ioaddr);
+                outb(0, ioaddr+TANG_CLEAR_INT);
+        }
+        if(lp->board==DAYNA)
+        {
+                outb(0, ioaddr+DAYNA_RESET);	/* Assert the reset port */
+                inb(ioaddr+DAYNA_RESET);	/* Clear the reset */
+		if (sleep)
+			msleep(333);
+		else
+			mdelay(333);
+        }
+
+	netif_wake_queue(dev);
+}
+
+static void cops_load (struct net_device *dev)
+{
+        struct ifreq ifr;
+        struct ltfirmware *ltf= (struct ltfirmware *)&ifr.ifr_ifru;
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr=dev->base_addr;
+	int length, i = 0;
+
+        strcpy(ifr.ifr_name,"lt0");
+
+        /* Get card's firmware code and do some checks on it. */
+#ifdef CONFIG_COPS_DAYNA        
+        if(lp->board==DAYNA)
+        {
+                ltf->length=sizeof(ffdrv_code);
+                ltf->data=ffdrv_code;
+        }
+        else
+#endif        
+#ifdef CONFIG_COPS_TANGENT
+        if(lp->board==TANGENT)
+        {
+                ltf->length=sizeof(ltdrv_code);
+                ltf->data=ltdrv_code;
+        }
+        else
+#endif
+	{
+		printk(KERN_INFO "%s; unsupported board type.\n", dev->name);
+		return;
+	}
+	
+        /* Check to make sure firmware is correct length. */
+        if(lp->board==DAYNA && ltf->length!=5983)
+        {
+                printk(KERN_WARNING "%s: Firmware is not length of FFDRV.BIN.\n", dev->name);
+                return;
+        }
+        if(lp->board==TANGENT && ltf->length!=2501)
+        {
+                printk(KERN_WARNING "%s: Firmware is not length of DRVCODE.BIN.\n", dev->name);
+                return;
+        }
+
+        if(lp->board==DAYNA)
+        {
+                /*
+                 *      We must wait for a status response
+                 *      with the DAYNA board.
+                 */
+                while(++i<65536)
+                {
+                       if((inb(ioaddr+DAYNA_CARD_STATUS)&3)==1)
+                                break;
+                }
+
+                if(i==65536)
+                        return;
+        }
+
+        /*
+         *      Upload the firmware and kick. Byte-by-byte works nicely here.
+         */
+	i=0;
+        length = ltf->length;
+        while(length--)
+        {
+                outb(ltf->data[i], ioaddr);
+                i++;
+        }
+
+	if(cops_debug > 1)
+		printk("%s: Uploaded firmware - %d bytes of %d bytes.\n", 
+			dev->name, i, ltf->length);
+
+        if(lp->board==DAYNA) 	/* Tell Dayna to run the firmware code. */
+                outb(1, ioaddr+DAYNA_INT_CARD);
+	else			/* Tell Tang to run the firmware code. */
+		inb(ioaddr);
+
+        if(lp->board==TANGENT)
+        {
+                tangent_wait_reset(ioaddr);
+                inb(ioaddr);	/* Clear initial ready signal. */
+        }
+}
+
+/*
+ * 	Get the LocalTalk Nodeid from the card. We can suggest
+ *	any nodeid 1-254. The card will try and get that exact
+ *	address else we can specify 0 as the nodeid and the card
+ *	will autoprobe for a nodeid.
+ */
+static int cops_nodeid (struct net_device *dev, int nodeid)
+{
+	struct cops_local *lp = netdev_priv(dev);
+	int ioaddr = dev->base_addr;
+
+	if(lp->board == DAYNA)
+        {
+        	/* Empty any pending adapter responses. */
+                while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
+                {
+			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupts. */
+        		if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
+                		cops_rx(dev);	/* Kick any packets waiting. */
+			schedule();
+                }
+
+                outb(2, ioaddr);       	/* Output command packet length as 2. */
+                outb(0, ioaddr);
+                outb(LAP_INIT, ioaddr);	/* Send LAP_INIT command byte. */
+                outb(nodeid, ioaddr);  	/* Suggest node address. */
+        }
+
+	if(lp->board == TANGENT)
+        {
+                /* Empty any pending adapter responses. */
+                while(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
+                {
+			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupt. */
+                	cops_rx(dev);          	/* Kick out packets waiting. */
+			schedule();
+                }
+
+		/* Not sure what Tangent does if nodeid picked is used. */
+                if(nodeid == 0)	         		/* Seed. */
+                	nodeid = jiffies&0xFF;		/* Get a random try */
+                outb(2, ioaddr);        		/* Command length LSB */
+                outb(0, ioaddr);       			/* Command length MSB */
+                outb(LAP_INIT, ioaddr); 		/* Send LAP_INIT byte */
+                outb(nodeid, ioaddr); 		  	/* LAP address hint. */
+                outb(0xFF, ioaddr);     		/* Int. level to use */
+        }
+
+	lp->node_acquire=0;		/* Set nodeid holder to 0. */
+        while(lp->node_acquire==0)	/* Get *True* nodeid finally. */
+	{
+		outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear any interrupt. */
+
+		if(lp->board == DAYNA)
+		{
+                	if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
+                		cops_rx(dev);	/* Grab the nodeid put in lp->node_acquire. */
+		}
+		if(lp->board == TANGENT)
+		{	
+			if(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
+                                cops_rx(dev);   /* Grab the nodeid put in lp->node_acquire. */
+		}
+		schedule();
+	}
+
+	if(cops_debug > 1)
+		printk(KERN_DEBUG "%s: Node ID %d has been acquired.\n", 
+			dev->name, lp->node_acquire);
+
+	lp->nodeid=1;	/* Set got nodeid to 1. */
+
+        return 0;
+}
+
+/*
+ *	Poll the Tangent type cards to see if we have work.
+ */
+ 
+static void cops_poll(unsigned long ltdev)
+{
+	int ioaddr, status;
+	int boguscount = 0;
+
+	struct net_device *dev = (struct net_device *)ltdev;
+
+	del_timer(&cops_timer);
+
+	if(dev == NULL)
+		return;	/* We've been downed */
+
+	ioaddr = dev->base_addr;
+	do {
+		status=inb(ioaddr+TANG_CARD_STATUS);
+		if(status & TANG_RX_READY)
+			cops_rx(dev);
+		if(status & TANG_TX_READY)
+			netif_wake_queue(dev);
+		status = inb(ioaddr+TANG_CARD_STATUS);
+	} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
+
+	/* poll 20 times per second */
+	cops_timer.expires = jiffies + HZ/20;
+	add_timer(&cops_timer);
+}
+
+/*
+ *      The typical workload of the driver:
+ *      Handle the network interface interrupts.
+ */
+static irqreturn_t cops_interrupt(int irq, void *dev_id)
+{
+        struct net_device *dev = dev_id;
+        struct cops_local *lp;
+        int ioaddr, status;
+        int boguscount = 0;
+
+        ioaddr = dev->base_addr;
+        lp = netdev_priv(dev);
+
+	if(lp->board==DAYNA)
+	{
+		do {
+			outb(0, ioaddr + COPS_CLEAR_INT);
+                       	status=inb(ioaddr+DAYNA_CARD_STATUS);
+                       	if((status&0x03)==DAYNA_RX_REQUEST)
+                       	        cops_rx(dev);
+                	netif_wake_queue(dev);
+		} while(++boguscount < 20);
+	}
+	else
+	{
+		do {
+                       	status=inb(ioaddr+TANG_CARD_STATUS);
+			if(status & TANG_RX_READY)
+				cops_rx(dev);
+			if(status & TANG_TX_READY)
+				netif_wake_queue(dev);
+			status=inb(ioaddr+TANG_CARD_STATUS);
+		} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
+	}
+
+        return IRQ_HANDLED;
+}
+
+/*
+ *      We have a good packet(s), get it/them out of the buffers.
+ */
+static void cops_rx(struct net_device *dev)
+{
+        int pkt_len = 0;
+        int rsp_type = 0;
+        struct sk_buff *skb = NULL;
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr = dev->base_addr;
+        int boguscount = 0;
+        unsigned long flags;
+
+
+	spin_lock_irqsave(&lp->lock, flags);
+	
+        if(lp->board==DAYNA)
+        {
+                outb(0, ioaddr);                /* Send out Zero length. */
+                outb(0, ioaddr);
+                outb(DATA_READ, ioaddr);        /* Send read command out. */
+
+                /* Wait for DMA to turn around. */
+                while(++boguscount<1000000)
+                {
+			barrier();
+                        if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_READY)
+                                break;
+                }
+
+                if(boguscount==1000000)
+                {
+                        printk(KERN_WARNING "%s: DMA timed out.\n",dev->name);
+			spin_unlock_irqrestore(&lp->lock, flags);
+                        return;
+                }
+        }
+
+        /* Get response length. */
+	if(lp->board==DAYNA)
+        	pkt_len = inb(ioaddr) & 0xFF;
+	else
+		pkt_len = inb(ioaddr) & 0x00FF;
+        pkt_len |= (inb(ioaddr) << 8);
+        /* Input IO code. */
+        rsp_type=inb(ioaddr);
+
+        /* Malloc up new buffer. */
+        skb = dev_alloc_skb(pkt_len);
+        if(skb == NULL)
+        {
+                printk(KERN_WARNING "%s: Memory squeeze, dropping packet.\n",
+			dev->name);
+                dev->stats.rx_dropped++;
+                while(pkt_len--)        /* Discard packet */
+                        inb(ioaddr);
+                spin_unlock_irqrestore(&lp->lock, flags);
+                return;
+        }
+        skb->dev = dev;
+        skb_put(skb, pkt_len);
+        skb->protocol = htons(ETH_P_LOCALTALK);
+
+        insb(ioaddr, skb->data, pkt_len);               /* Eat the Data */
+
+        if(lp->board==DAYNA)
+                outb(1, ioaddr+DAYNA_INT_CARD);         /* Interrupt the card */
+
+        spin_unlock_irqrestore(&lp->lock, flags);  /* Restore interrupts. */
+
+        /* Check for bad response length */
+        if(pkt_len < 0 || pkt_len > MAX_LLAP_SIZE)
+        {
+		printk(KERN_WARNING "%s: Bad packet length of %d bytes.\n", 
+			dev->name, pkt_len);
+                dev->stats.tx_errors++;
+                dev_kfree_skb_any(skb);
+                return;
+        }
+
+        /* Set nodeid and then get out. */
+        if(rsp_type == LAP_INIT_RSP)
+        {	/* Nodeid taken from received packet. */
+                lp->node_acquire = skb->data[0];
+                dev_kfree_skb_any(skb);
+                return;
+        }
+
+        /* One last check to make sure we have a good packet. */
+        if(rsp_type != LAP_RESPONSE)
+        {
+                printk(KERN_WARNING "%s: Bad packet type %d.\n", dev->name, rsp_type);
+                dev->stats.tx_errors++;
+                dev_kfree_skb_any(skb);
+                return;
+        }
+
+        skb_reset_mac_header(skb);    /* Point to entire packet. */
+        skb_pull(skb,3);
+        skb_reset_transport_header(skb);    /* Point to data (Skip header). */
+
+        /* Update the counters. */
+        dev->stats.rx_packets++;
+        dev->stats.rx_bytes += skb->len;
+
+        /* Send packet to a higher place. */
+        netif_rx(skb);
+}
+
+static void cops_timeout(struct net_device *dev)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr = dev->base_addr;
+
+	dev->stats.tx_errors++;
+        if(lp->board==TANGENT)
+        {
+		if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
+               		printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name);
+	}
+	printk(KERN_WARNING "%s: Transmit timed out.\n", dev->name);
+	cops_jumpstart(dev);	/* Restart the card. */
+	dev->trans_start = jiffies; /* prevent tx timeout */
+	netif_wake_queue(dev);
+}
+
+
+/*
+ *	Make the card transmit a LocalTalk packet.
+ */
+
+static netdev_tx_t cops_send_packet(struct sk_buff *skb,
+					  struct net_device *dev)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        int ioaddr = dev->base_addr;
+        unsigned long flags;
+
+        /*
+         * Block a timer-based transmit from overlapping. 
+	 */
+	 
+	netif_stop_queue(dev);
+
+	spin_lock_irqsave(&lp->lock, flags);
+	if(lp->board == DAYNA)	 /* Wait for adapter transmit buffer. */
+		while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
+			cpu_relax();
+	if(lp->board == TANGENT) /* Wait for adapter transmit buffer. */
+		while((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
+			cpu_relax();
+
+	/* Output IO length. */
+	outb(skb->len, ioaddr);
+	if(lp->board == DAYNA)
+               	outb(skb->len >> 8, ioaddr);
+	else
+		outb((skb->len >> 8)&0x0FF, ioaddr);
+
+	/* Output IO code. */
+	outb(LAP_WRITE, ioaddr);
+
+	if(lp->board == DAYNA)	/* Check the transmit buffer again. */
+        	while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0);
+
+	outsb(ioaddr, skb->data, skb->len);	/* Send out the data. */
+
+	if(lp->board==DAYNA)	/* Dayna requires you kick the card */
+		outb(1, ioaddr+DAYNA_INT_CARD);
+
+	spin_unlock_irqrestore(&lp->lock, flags);	/* Restore interrupts. */
+
+	/* Done sending packet, update counters and cleanup. */
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+	dev_kfree_skb (skb);
+	return NETDEV_TX_OK;
+}
+
+/*
+ *	Dummy function to keep the Appletalk layer happy.
+ */
+ 
+static void set_multicast_list(struct net_device *dev)
+{
+        if(cops_debug >= 3)
+		printk("%s: set_multicast_list executed\n", dev->name);
+}
+
+/*
+ *      System ioctls for the COPS LocalTalk card.
+ */
+ 
+static int cops_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+        struct cops_local *lp = netdev_priv(dev);
+        struct sockaddr_at *sa = (struct sockaddr_at *)&ifr->ifr_addr;
+        struct atalk_addr *aa = (struct atalk_addr *)&lp->node_addr;
+
+        switch(cmd)
+        {
+                case SIOCSIFADDR:
+			/* Get and set the nodeid and network # atalkd wants. */
+			cops_nodeid(dev, sa->sat_addr.s_node);
+			aa->s_net               = sa->sat_addr.s_net;
+                        aa->s_node              = lp->node_acquire;
+
+			/* Set broardcast address. */
+                        dev->broadcast[0]       = 0xFF;
+			
+			/* Set hardware address. */
+                        dev->dev_addr[0]        = aa->s_node;
+                        dev->addr_len           = 1;
+                        return 0;
+
+                case SIOCGIFADDR:
+                        sa->sat_addr.s_net      = aa->s_net;
+                        sa->sat_addr.s_node     = aa->s_node;
+                        return 0;
+
+                default:
+                        return -EOPNOTSUPP;
+        }
+}
+
+/*
+ *	The inverse routine to cops_open().
+ */
+ 
+static int cops_close(struct net_device *dev)
+{
+	struct cops_local *lp = netdev_priv(dev);
+
+	/* If we were running polled, yank the timer.
+	 */
+	if(lp->board==TANGENT && dev->irq==0)
+		del_timer(&cops_timer);
+
+	netif_stop_queue(dev);
+        return 0;
+}
+
+
+#ifdef MODULE
+static struct net_device *cops_dev;
+
+MODULE_LICENSE("GPL");
+module_param(io, int, 0);
+module_param(irq, int, 0);
+module_param(board_type, int, 0);
+
+static int __init cops_module_init(void)
+{
+	if (io == 0)
+		printk(KERN_WARNING "%s: You shouldn't autoprobe with insmod\n",
+			cardname);
+	cops_dev = cops_probe(-1);
+	if (IS_ERR(cops_dev))
+		return PTR_ERR(cops_dev);
+        return 0;
+}
+
+static void __exit cops_module_exit(void)
+{
+	unregister_netdev(cops_dev);
+	cleanup_card(cops_dev);
+	free_netdev(cops_dev);
+}
+module_init(cops_module_init);
+module_exit(cops_module_exit);
+#endif /* MODULE */
diff --git a/drivers/net/appletalk/cops.h b/drivers/net/appletalk/cops.h
new file mode 100644
index 000000000000..fd2750b269c8
--- /dev/null
+++ b/drivers/net/appletalk/cops.h
@@ -0,0 +1,60 @@
+/*      cops.h: LocalTalk driver for Linux.
+ *
+ *      Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ */
+
+#ifndef __LINUX_COPSLTALK_H
+#define __LINUX_COPSLTALK_H
+
+#ifdef __KERNEL__
+
+/* Max LLAP size we will accept. */
+#define MAX_LLAP_SIZE		603
+
+/* Tangent */
+#define TANG_CARD_STATUS        1
+#define TANG_CLEAR_INT          1
+#define TANG_RESET              3
+
+#define TANG_TX_READY           1
+#define TANG_RX_READY           2
+
+/* Dayna */
+#define DAYNA_CMD_DATA          0
+#define DAYNA_CLEAR_INT         1
+#define DAYNA_CARD_STATUS       2
+#define DAYNA_INT_CARD          3
+#define DAYNA_RESET             4
+
+#define DAYNA_RX_READY          0
+#define DAYNA_TX_READY          1
+#define DAYNA_RX_REQUEST        3
+
+/* Same on both card types */
+#define COPS_CLEAR_INT  1
+
+/* LAP response codes received from the cards. */
+#define LAP_INIT        1       /* Init cmd */
+#define LAP_INIT_RSP    2       /* Init response */
+#define LAP_WRITE       3       /* Write cmd */
+#define DATA_READ       4       /* Data read */
+#define LAP_RESPONSE    4       /* Received ALAP frame response */
+#define LAP_GETSTAT     5       /* Get LAP and HW status */
+#define LAP_RSPSTAT     6       /* Status response */
+
+#endif
+
+/*
+ *	Structure to hold the firmware information.
+ */
+struct ltfirmware
+{
+        unsigned int length;
+        const unsigned char *data;
+};
+
+#define DAYNA 1
+#define TANGENT 2
+
+#endif
diff --git a/drivers/net/appletalk/cops_ffdrv.h b/drivers/net/appletalk/cops_ffdrv.h
new file mode 100644
index 000000000000..b02005087c1b
--- /dev/null
+++ b/drivers/net/appletalk/cops_ffdrv.h
@@ -0,0 +1,532 @@
+
+/*
+ *	The firmware this driver downloads into the Localtalk card is a
+ *	separate program and is not GPL'd source code, even though the Linux
+ *	side driver and the routine that loads this data into the card are.
+ *	
+ *	It is taken from the COPS SDK and is under the following license
+ *
+ *	This material is licensed to you strictly for use in conjunction with
+ *	the use of COPS LocalTalk adapters.
+ *	There is no charge for this SDK. And no waranty express or implied
+ *	about its fitness for any purpose. However, we will cheerefully
+ *	refund every penny you paid for this SDK...
+ *	Regards,
+ *
+ *	Thomas F. Divine
+ *	Chief Scientist
+ */
+
+
+/*      cops_ffdrv.h: LocalTalk driver firmware dump for Linux.
+ *
+ *      Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ */
+
+
+#ifdef CONFIG_COPS_DAYNA
+
+static const unsigned char ffdrv_code[] = {
+	58,3,0,50,228,149,33,255,255,34,226,149,
+	249,17,40,152,33,202,154,183,237,82,77,68,
+	11,107,98,19,54,0,237,176,175,50,80,0,
+	62,128,237,71,62,32,237,57,51,62,12,237,
+	57,50,237,57,54,62,6,237,57,52,62,12,
+	237,57,49,33,107,137,34,32,128,33,83,130,
+	34,40,128,33,86,130,34,42,128,33,112,130,
+	34,36,128,33,211,130,34,38,128,62,0,237,
+	57,16,33,63,148,34,34,128,237,94,205,15,
+	130,251,205,168,145,24,141,67,111,112,121,114,
+	105,103,104,116,32,40,67,41,32,49,57,56,
+	56,32,45,32,68,97,121,110,97,32,67,111,
+	109,109,117,110,105,99,97,116,105,111,110,115,
+	32,32,32,65,108,108,32,114,105,103,104,116,
+	115,32,114,101,115,101,114,118,101,100,46,32,
+	32,40,68,40,68,7,16,8,34,7,22,6,
+	16,5,12,4,8,3,6,140,0,16,39,128,
+	0,4,96,10,224,6,0,7,126,2,64,11,
+	118,12,6,13,0,14,193,15,0,5,96,3,
+	192,1,64,9,8,62,9,211,66,62,192,211,
+	66,62,100,61,32,253,6,28,33,205,129,14,
+	66,237,163,194,253,129,6,28,33,205,129,14,
+	64,237,163,194,9,130,201,62,47,50,71,152,
+	62,47,211,68,58,203,129,237,57,20,58,204,
+	129,237,57,21,33,77,152,54,132,205,233,129,
+	58,228,149,254,209,40,6,56,4,62,0,24,
+	2,219,96,33,233,149,119,230,62,33,232,149,
+	119,213,33,8,152,17,7,0,25,119,19,25,
+	119,209,201,251,237,77,245,197,213,229,221,229,
+	205,233,129,62,1,50,106,137,205,158,139,221,
+	225,225,209,193,241,251,237,77,245,197,213,219,
+	72,237,56,16,230,46,237,57,16,237,56,12,
+	58,72,152,183,32,26,6,20,17,128,2,237,
+	56,46,187,32,35,237,56,47,186,32,29,219,
+	72,230,1,32,3,5,32,232,175,50,72,152,
+	229,221,229,62,1,50,106,137,205,158,139,221,
+	225,225,24,25,62,1,50,72,152,58,201,129,
+	237,57,12,58,202,129,237,57,13,237,56,16,
+	246,17,237,57,16,209,193,241,251,237,77,245,
+	197,229,213,221,229,237,56,16,230,17,237,57,
+	16,237,56,20,58,34,152,246,16,246,8,211,
+	68,62,6,61,32,253,58,34,152,246,8,211,
+	68,58,203,129,237,57,20,58,204,129,237,57,
+	21,237,56,16,246,34,237,57,16,221,225,209,
+	225,193,241,251,237,77,33,2,0,57,126,230,
+	3,237,100,1,40,2,246,128,230,130,245,62,
+	5,211,64,241,211,64,201,229,213,243,237,56,
+	16,230,46,237,57,16,237,56,12,251,70,35,
+	35,126,254,175,202,77,133,254,129,202,15,133,
+	230,128,194,191,132,43,58,44,152,119,33,76,
+	152,119,35,62,132,119,120,254,255,40,4,58,
+	49,152,119,219,72,43,43,112,17,3,0,237,
+	56,52,230,248,237,57,52,219,72,230,1,194,
+	141,131,209,225,237,56,52,246,6,237,57,52,
+	62,1,55,251,201,62,3,211,66,62,192,211,
+	66,62,48,211,66,0,0,219,66,230,1,40,
+	4,219,67,24,240,205,203,135,58,75,152,254,
+	255,202,128,132,58,49,152,254,161,250,207,131,
+	58,34,152,211,68,62,10,211,66,62,128,211,
+	66,62,11,211,66,62,6,211,66,24,0,62,
+	14,211,66,62,33,211,66,62,1,211,66,62,
+	64,211,66,62,3,211,66,62,209,211,66,62,
+	100,71,219,66,230,1,32,6,5,32,247,195,
+	248,132,219,67,71,58,44,152,184,194,248,132,
+	62,100,71,219,66,230,1,32,6,5,32,247,
+	195,248,132,219,67,62,100,71,219,66,230,1,
+	32,6,5,32,247,195,248,132,219,67,254,133,
+	32,7,62,0,50,74,152,24,17,254,173,32,
+	7,62,1,50,74,152,24,6,254,141,194,248,
+	132,71,209,225,58,49,152,254,132,32,10,62,
+	50,205,2,134,205,144,135,24,27,254,140,32,
+	15,62,110,205,2,134,62,141,184,32,5,205,
+	144,135,24,8,62,10,205,2,134,205,8,134,
+	62,1,50,106,137,205,158,139,237,56,52,246,
+	6,237,57,52,175,183,251,201,62,20,135,237,
+	57,20,175,237,57,21,237,56,16,246,2,237,
+	57,16,237,56,20,95,237,56,21,123,254,10,
+	48,244,237,56,16,230,17,237,57,16,209,225,
+	205,144,135,62,1,50,106,137,205,158,139,237,
+	56,52,246,6,237,57,52,175,183,251,201,209,
+	225,243,219,72,230,1,40,13,62,10,211,66,
+	0,0,219,66,230,192,202,226,132,237,56,52,
+	246,6,237,57,52,62,1,55,251,201,205,203,
+	135,62,1,50,106,137,205,158,139,237,56,52,
+	246,6,237,57,52,183,251,201,209,225,62,1,
+	50,106,137,205,158,139,237,56,52,246,6,237,
+	57,52,62,2,55,251,201,209,225,243,219,72,
+	230,1,202,213,132,62,10,211,66,0,0,219,
+	66,230,192,194,213,132,229,62,1,50,106,137,
+	42,40,152,205,65,143,225,17,3,0,205,111,
+	136,62,6,211,66,58,44,152,211,66,237,56,
+	52,246,6,237,57,52,183,251,201,209,197,237,
+	56,52,230,248,237,57,52,219,72,230,1,32,
+	15,193,225,237,56,52,246,6,237,57,52,62,
+	1,55,251,201,14,23,58,37,152,254,0,40,
+	14,14,2,254,1,32,5,62,140,119,24,3,
+	62,132,119,43,43,197,205,203,135,193,62,1,
+	211,66,62,64,211,66,62,3,211,66,62,193,
+	211,66,62,100,203,39,71,219,66,230,1,32,
+	6,5,32,247,195,229,133,33,238,151,219,67,
+	71,58,44,152,184,194,229,133,119,62,100,71,
+	219,66,230,1,32,6,5,32,247,195,229,133,
+	219,67,35,119,13,32,234,193,225,62,1,50,
+	106,137,205,158,139,237,56,52,246,6,237,57,
+	52,175,183,251,201,33,234,151,35,35,62,255,
+	119,193,225,62,1,50,106,137,205,158,139,237,
+	56,52,246,6,237,57,52,175,251,201,243,61,
+	32,253,251,201,62,3,211,66,62,192,211,66,
+	58,49,152,254,140,32,19,197,229,213,17,181,
+	129,33,185,129,1,2,0,237,176,209,225,193,
+	24,27,229,213,33,187,129,58,49,152,230,15,
+	87,30,2,237,92,25,17,181,129,126,18,19,
+	35,126,18,209,225,58,34,152,246,8,211,68,
+	58,49,152,254,165,40,14,254,164,40,10,62,
+	10,211,66,62,224,211,66,24,25,58,74,152,
+	254,0,40,10,62,10,211,66,62,160,211,66,
+	24,8,62,10,211,66,62,128,211,66,62,11,
+	211,66,62,6,211,66,205,147,143,62,5,211,
+	66,62,224,211,66,62,5,211,66,62,96,211,
+	66,62,5,61,32,253,62,5,211,66,62,224,
+	211,66,62,14,61,32,253,62,5,211,66,62,
+	233,211,66,62,128,211,66,58,181,129,61,32,
+	253,62,1,211,66,62,192,211,66,1,254,19,
+	237,56,46,187,32,6,13,32,247,195,226,134,
+	62,192,211,66,0,0,219,66,203,119,40,250,
+	219,66,203,87,40,250,243,237,56,16,230,17,
+	237,57,16,237,56,20,251,62,5,211,66,62,
+	224,211,66,58,182,129,61,32,253,229,33,181,
+	129,58,183,129,203,63,119,35,58,184,129,119,
+	225,62,10,211,66,62,224,211,66,62,11,211,
+	66,62,118,211,66,62,47,211,68,62,5,211,
+	66,62,233,211,66,58,181,129,61,32,253,62,
+	5,211,66,62,224,211,66,58,182,129,61,32,
+	253,62,5,211,66,62,96,211,66,201,229,213,
+	58,50,152,230,15,87,30,2,237,92,33,187,
+	129,25,17,181,129,126,18,35,19,126,18,209,
+	225,58,71,152,246,8,211,68,58,50,152,254,
+	165,40,14,254,164,40,10,62,10,211,66,62,
+	224,211,66,24,8,62,10,211,66,62,128,211,
+	66,62,11,211,66,62,6,211,66,195,248,135,
+	62,3,211,66,62,192,211,66,197,229,213,17,
+	181,129,33,183,129,1,2,0,237,176,209,225,
+	193,62,47,211,68,62,10,211,66,62,224,211,
+	66,62,11,211,66,62,118,211,66,62,1,211,
+	66,62,0,211,66,205,147,143,195,16,136,62,
+	3,211,66,62,192,211,66,197,229,213,17,181,
+	129,33,183,129,1,2,0,237,176,209,225,193,
+	62,47,211,68,62,10,211,66,62,224,211,66,
+	62,11,211,66,62,118,211,66,205,147,143,62,
+	5,211,66,62,224,211,66,62,5,211,66,62,
+	96,211,66,62,5,61,32,253,62,5,211,66,
+	62,224,211,66,62,14,61,32,253,62,5,211,
+	66,62,233,211,66,62,128,211,66,58,181,129,
+	61,32,253,62,1,211,66,62,192,211,66,1,
+	254,19,237,56,46,187,32,6,13,32,247,195,
+	88,136,62,192,211,66,0,0,219,66,203,119,
+	40,250,219,66,203,87,40,250,62,5,211,66,
+	62,224,211,66,58,182,129,61,32,253,62,5,
+	211,66,62,96,211,66,201,197,14,67,6,0,
+	62,3,211,66,62,192,211,66,62,48,211,66,
+	0,0,219,66,230,1,40,4,219,67,24,240,
+	62,5,211,66,62,233,211,66,62,128,211,66,
+	58,181,129,61,32,253,237,163,29,62,192,211,
+	66,219,66,230,4,40,250,237,163,29,32,245,
+	219,66,230,4,40,250,62,255,71,219,66,230,
+	4,40,3,5,32,247,219,66,230,4,40,250,
+	62,5,211,66,62,224,211,66,58,182,129,61,
+	32,253,62,5,211,66,62,96,211,66,58,71,
+	152,254,1,202,18,137,62,16,211,66,62,56,
+	211,66,62,14,211,66,62,33,211,66,62,1,
+	211,66,62,248,211,66,237,56,48,246,153,230,
+	207,237,57,48,62,3,211,66,62,221,211,66,
+	193,201,58,71,152,211,68,62,10,211,66,62,
+	128,211,66,62,11,211,66,62,6,211,66,62,
+	6,211,66,58,44,152,211,66,62,16,211,66,
+	62,56,211,66,62,48,211,66,0,0,62,14,
+	211,66,62,33,211,66,62,1,211,66,62,248,
+	211,66,237,56,48,246,145,246,8,230,207,237,
+	57,48,62,3,211,66,62,221,211,66,193,201,
+	44,3,1,0,70,69,1,245,197,213,229,175,
+	50,72,152,237,56,16,230,46,237,57,16,237,
+	56,12,62,1,211,66,0,0,219,66,95,230,
+	160,32,3,195,20,139,123,230,96,194,72,139,
+	62,48,211,66,62,1,211,66,62,64,211,66,
+	237,91,40,152,205,207,143,25,43,55,237,82,
+	218,70,139,34,42,152,98,107,58,44,152,190,
+	194,210,138,35,35,62,130,190,194,200,137,62,
+	1,50,48,152,62,175,190,202,82,139,62,132,
+	190,32,44,50,50,152,62,47,50,71,152,229,
+	175,50,106,137,42,40,152,205,65,143,225,54,
+	133,43,70,58,44,152,119,43,112,17,3,0,
+	62,10,205,2,134,205,111,136,195,158,138,62,
+	140,190,32,19,50,50,152,58,233,149,230,4,
+	202,222,138,62,1,50,71,152,195,219,137,126,
+	254,160,250,185,138,254,166,242,185,138,50,50,
+	152,43,126,35,229,213,33,234,149,95,22,0,
+	25,126,254,132,40,18,254,140,40,14,58,50,
+	152,230,15,87,126,31,21,242,65,138,56,2,
+	175,119,58,50,152,230,15,87,58,233,149,230,
+	62,31,21,242,85,138,218,98,138,209,225,195,
+	20,139,58,50,152,33,100,137,230,15,95,22,
+	0,25,126,50,71,152,209,225,58,50,152,254,
+	164,250,135,138,58,73,152,254,0,40,4,54,
+	173,24,2,54,133,43,70,58,44,152,119,43,
+	112,17,3,0,205,70,135,175,50,106,137,205,
+	208,139,58,199,129,237,57,12,58,200,129,237,
+	57,13,237,56,16,246,17,237,57,16,225,209,
+	193,241,251,237,77,62,129,190,194,227,138,54,
+	130,43,70,58,44,152,119,43,112,17,3,0,
+	205,144,135,195,20,139,35,35,126,254,132,194,
+	227,138,175,50,106,137,205,158,139,24,42,58,
+	201,154,254,1,40,7,62,1,50,106,137,24,
+	237,58,106,137,254,1,202,222,138,62,128,166,
+	194,222,138,221,229,221,33,67,152,205,127,142,
+	205,109,144,221,225,225,209,193,241,251,237,77,
+	58,106,137,254,1,202,44,139,58,50,152,254,
+	164,250,44,139,58,73,152,238,1,50,73,152,
+	221,229,221,33,51,152,205,127,142,221,225,62,
+	1,50,106,137,205,158,139,195,13,139,24,208,
+	24,206,24,204,230,64,40,3,195,20,139,195,
+	20,139,43,126,33,8,152,119,35,58,44,152,
+	119,43,237,91,35,152,205,203,135,205,158,139,
+	195,13,139,175,50,78,152,62,3,211,66,62,
+	192,211,66,201,197,33,4,0,57,126,35,102,
+	111,62,1,50,106,137,219,72,205,141,139,193,
+	201,62,1,50,78,152,34,40,152,54,0,35,
+	35,54,0,195,163,139,58,78,152,183,200,229,
+	33,181,129,58,183,129,119,35,58,184,129,119,
+	225,62,47,211,68,62,14,211,66,62,193,211,
+	66,62,10,211,66,62,224,211,66,62,11,211,
+	66,62,118,211,66,195,3,140,58,78,152,183,
+	200,58,71,152,211,68,254,69,40,4,254,70,
+	32,17,58,73,152,254,0,40,10,62,10,211,
+	66,62,160,211,66,24,8,62,10,211,66,62,
+	128,211,66,62,11,211,66,62,6,211,66,62,
+	6,211,66,58,44,152,211,66,62,16,211,66,
+	62,56,211,66,62,48,211,66,0,0,219,66,
+	230,1,40,4,219,67,24,240,62,14,211,66,
+	62,33,211,66,42,40,152,205,65,143,62,1,
+	211,66,62,248,211,66,237,56,48,246,145,246,
+	8,230,207,237,57,48,62,3,211,66,62,221,
+	211,66,201,62,16,211,66,62,56,211,66,62,
+	48,211,66,0,0,219,66,230,1,40,4,219,
+	67,24,240,62,14,211,66,62,33,211,66,62,
+	1,211,66,62,248,211,66,237,56,48,246,153,
+	230,207,237,57,48,62,3,211,66,62,221,211,
+	66,201,229,213,33,234,149,95,22,0,25,126,
+	254,132,40,4,254,140,32,2,175,119,123,209,
+	225,201,6,8,14,0,31,48,1,12,16,250,
+	121,201,33,4,0,57,94,35,86,33,2,0,
+	57,126,35,102,111,221,229,34,89,152,237,83,
+	91,152,221,33,63,152,205,127,142,58,81,152,
+	50,82,152,58,80,152,135,50,80,152,205,162,
+	140,254,3,56,16,58,81,152,135,60,230,15,
+	50,81,152,175,50,80,152,24,23,58,79,152,
+	205,162,140,254,3,48,13,58,81,152,203,63,
+	50,81,152,62,255,50,79,152,58,81,152,50,
+	82,152,58,79,152,135,50,79,152,62,32,50,
+	83,152,50,84,152,237,56,16,230,17,237,57,
+	16,219,72,62,192,50,93,152,62,93,50,94,
+	152,58,93,152,61,50,93,152,32,9,58,94,
+	152,61,50,94,152,40,44,62,170,237,57,20,
+	175,237,57,21,237,56,16,246,2,237,57,16,
+	219,72,230,1,202,29,141,237,56,20,71,237,
+	56,21,120,254,10,48,237,237,56,16,230,17,
+	237,57,16,243,62,14,211,66,62,65,211,66,
+	251,58,39,152,23,23,60,50,39,152,71,58,
+	82,152,160,230,15,40,22,71,14,10,219,66,
+	230,16,202,186,141,219,72,230,1,202,186,141,
+	13,32,239,16,235,42,89,152,237,91,91,152,
+	205,47,131,48,7,61,202,186,141,195,227,141,
+	221,225,33,0,0,201,221,33,55,152,205,127,
+	142,58,84,152,61,50,84,152,40,19,58,82,
+	152,246,1,50,82,152,58,79,152,246,1,50,
+	79,152,195,29,141,221,225,33,1,0,201,221,
+	33,59,152,205,127,142,58,80,152,246,1,50,
+	80,152,58,82,152,135,246,1,50,82,152,58,
+	83,152,61,50,83,152,194,29,141,221,225,33,
+	2,0,201,221,229,33,0,0,57,17,4,0,
+	25,126,50,44,152,230,128,50,85,152,58,85,
+	152,183,40,6,221,33,88,2,24,4,221,33,
+	150,0,58,44,152,183,40,53,60,40,50,60,
+	40,47,61,61,33,86,152,119,35,119,35,54,
+	129,175,50,48,152,221,43,221,229,225,124,181,
+	40,42,33,86,152,17,3,0,205,189,140,17,
+	232,3,27,123,178,32,251,58,48,152,183,40,
+	224,58,44,152,71,62,7,128,230,127,71,58,
+	85,152,176,50,44,152,24,162,221,225,201,183,
+	221,52,0,192,221,52,1,192,221,52,2,192,
+	221,52,3,192,55,201,245,62,1,211,100,241,
+	201,245,62,1,211,96,241,201,33,2,0,57,
+	126,35,102,111,237,56,48,230,175,237,57,48,
+	62,48,237,57,49,125,237,57,32,124,237,57,
+	33,62,0,237,57,34,62,88,237,57,35,62,
+	0,237,57,36,237,57,37,33,128,2,125,237,
+	57,38,124,237,57,39,237,56,48,246,97,230,
+	207,237,57,48,62,0,237,57,0,62,0,211,
+	96,211,100,201,33,2,0,57,126,35,102,111,
+	237,56,48,230,175,237,57,48,62,12,237,57,
+	49,62,76,237,57,32,62,0,237,57,33,237,
+	57,34,125,237,57,35,124,237,57,36,62,0,
+	237,57,37,33,128,2,125,237,57,38,124,237,
+	57,39,237,56,48,246,97,230,207,237,57,48,
+	62,1,211,96,201,33,2,0,57,126,35,102,
+	111,229,237,56,48,230,87,237,57,48,125,237,
+	57,40,124,237,57,41,62,0,237,57,42,62,
+	67,237,57,43,62,0,237,57,44,58,106,137,
+	254,1,32,5,33,6,0,24,3,33,128,2,
+	125,237,57,46,124,237,57,47,237,56,50,230,
+	252,246,2,237,57,50,225,201,33,4,0,57,
+	94,35,86,33,2,0,57,126,35,102,111,237,
+	56,48,230,87,237,57,48,125,237,57,40,124,
+	237,57,41,62,0,237,57,42,62,67,237,57,
+	43,62,0,237,57,44,123,237,57,46,122,237,
+	57,47,237,56,50,230,244,246,0,237,57,50,
+	237,56,48,246,145,230,207,237,57,48,201,213,
+	237,56,46,95,237,56,47,87,237,56,46,111,
+	237,56,47,103,183,237,82,32,235,33,128,2,
+	183,237,82,209,201,213,237,56,38,95,237,56,
+	39,87,237,56,38,111,237,56,39,103,183,237,
+	82,32,235,33,128,2,183,237,82,209,201,245,
+	197,1,52,0,237,120,230,253,237,121,193,241,
+	201,245,197,1,52,0,237,120,246,2,237,121,
+	193,241,201,33,2,0,57,126,35,102,111,126,
+	35,110,103,201,33,0,0,34,102,152,34,96,
+	152,34,98,152,33,202,154,34,104,152,237,91,
+	104,152,42,226,149,183,237,82,17,0,255,25,
+	34,100,152,203,124,40,6,33,0,125,34,100,
+	152,42,104,152,35,35,35,229,205,120,139,193,
+	201,205,186,149,229,42,40,152,35,35,35,229,
+	205,39,144,193,124,230,3,103,221,117,254,221,
+	116,255,237,91,42,152,35,35,35,183,237,82,
+	32,12,17,5,0,42,42,152,205,171,149,242,
+	169,144,42,40,152,229,205,120,139,193,195,198,
+	149,237,91,42,152,42,98,152,25,34,98,152,
+	19,19,19,42,102,152,25,34,102,152,237,91,
+	100,152,33,158,253,25,237,91,102,152,205,171,
+	149,242,214,144,33,0,0,34,102,152,62,1,
+	50,95,152,205,225,144,195,198,149,58,95,152,
+	183,200,237,91,96,152,42,102,152,205,171,149,
+	242,5,145,237,91,102,152,33,98,2,25,237,
+	91,96,152,205,171,149,250,37,145,237,91,96,
+	152,42,102,152,183,237,82,32,7,42,98,152,
+	125,180,40,13,237,91,102,152,42,96,152,205,
+	171,149,242,58,145,237,91,104,152,42,102,152,
+	25,35,35,35,229,205,120,139,193,175,50,95,
+	152,201,195,107,139,205,206,149,250,255,243,205,
+	225,144,251,58,230,149,183,194,198,149,17,1,
+	0,42,98,152,205,171,149,250,198,149,62,1,
+	50,230,149,237,91,96,152,42,104,152,25,221,
+	117,252,221,116,253,237,91,104,152,42,96,152,
+	25,35,35,35,221,117,254,221,116,255,35,35,
+	35,229,205,39,144,124,230,3,103,35,35,35,
+	221,117,250,221,116,251,235,221,110,252,221,102,
+	253,115,35,114,35,54,4,62,1,211,100,211,
+	84,195,198,149,33,0,0,34,102,152,34,96,
+	152,34,98,152,33,202,154,34,104,152,237,91,
+	104,152,42,226,149,183,237,82,17,0,255,25,
+	34,100,152,33,109,152,54,0,33,107,152,229,
+	205,240,142,193,62,47,50,34,152,62,132,50,
+	49,152,205,241,145,205,61,145,58,39,152,60,
+	50,39,152,24,241,205,206,149,251,255,33,109,
+	152,126,183,202,198,149,110,221,117,251,33,109,
+	152,54,0,221,126,251,254,1,40,28,254,3,
+	40,101,254,4,202,190,147,254,5,202,147,147,
+	254,8,40,87,33,107,152,229,205,240,142,195,
+	198,149,58,201,154,183,32,21,33,111,152,126,
+	50,229,149,205,52,144,33,110,152,110,38,0,
+	229,205,11,142,193,237,91,96,152,42,104,152,
+	25,221,117,254,221,116,255,35,35,54,2,17,
+	2,0,43,43,115,35,114,58,44,152,35,35,
+	119,58,228,149,35,119,62,1,211,100,211,84,
+	62,1,50,201,154,24,169,205,153,142,58,231,
+	149,183,40,250,175,50,231,149,33,110,152,126,
+	254,255,40,91,58,233,149,230,63,183,40,83,
+	94,22,0,33,234,149,25,126,183,40,13,33,
+	110,152,94,33,234,150,25,126,254,3,32,36,
+	205,81,148,125,180,33,110,152,94,22,0,40,
+	17,33,234,149,25,54,0,33,107,152,229,205,
+	240,142,193,195,198,149,33,234,150,25,54,0,
+	33,110,152,94,22,0,33,234,149,25,126,50,
+	49,152,254,132,32,37,62,47,50,34,152,42,
+	107,152,229,33,110,152,229,205,174,140,193,193,
+	125,180,33,110,152,94,22,0,33,234,150,202,
+	117,147,25,52,195,120,147,58,49,152,254,140,
+	32,7,62,1,50,34,152,24,210,62,32,50,
+	106,152,24,19,58,49,152,95,58,106,152,163,
+	183,58,106,152,32,11,203,63,50,106,152,58,
+	106,152,183,32,231,254,2,40,51,254,4,40,
+	38,254,8,40,26,254,16,40,13,254,32,32,
+	158,62,165,50,49,152,62,69,24,190,62,164,
+	50,49,152,62,70,24,181,62,163,50,49,152,
+	175,24,173,62,162,50,49,152,62,1,24,164,
+	62,161,50,49,152,62,3,24,155,25,54,0,
+	221,126,251,254,8,40,7,58,230,149,183,202,
+	32,146,33,107,152,229,205,240,142,193,211,84,
+	195,198,149,237,91,96,152,42,104,152,25,221,
+	117,254,221,116,255,35,35,54,6,17,2,0,
+	43,43,115,35,114,58,228,149,35,35,119,58,
+	233,149,35,119,205,146,142,195,32,146,237,91,
+	96,152,42,104,152,25,229,205,160,142,193,58,
+	231,149,183,40,250,175,50,231,149,243,237,91,
+	96,152,42,104,152,25,221,117,254,221,116,255,
+	78,35,70,221,113,252,221,112,253,89,80,42,
+	98,152,183,237,82,34,98,152,203,124,40,19,
+	33,0,0,34,98,152,34,102,152,34,96,152,
+	62,1,50,95,152,24,40,221,94,252,221,86,
+	253,19,19,19,42,96,152,25,34,96,152,237,
+	91,100,152,33,158,253,25,237,91,96,152,205,
+	171,149,242,55,148,33,0,0,34,96,152,175,
+	50,230,149,251,195,32,146,245,62,1,50,231,
+	149,62,16,237,57,0,211,80,241,251,237,77,
+	201,205,186,149,229,229,33,0,0,34,37,152,
+	33,110,152,126,50,234,151,58,44,152,33,235,
+	151,119,221,54,253,0,221,54,254,0,195,230,
+	148,33,236,151,54,175,33,3,0,229,33,234,
+	151,229,205,174,140,193,193,33,236,151,126,254,
+	255,40,74,33,245,151,110,221,117,255,33,249,
+	151,126,221,166,255,221,119,255,33,253,151,126,
+	221,166,255,221,119,255,58,232,149,95,221,126,
+	255,163,221,119,255,183,40,15,230,191,33,110,
+	152,94,22,0,33,234,149,25,119,24,12,33,
+	110,152,94,22,0,33,234,149,25,54,132,33,
+	0,0,195,198,149,221,110,253,221,102,254,35,
+	221,117,253,221,116,254,17,32,0,221,110,253,
+	221,102,254,205,171,149,250,117,148,58,233,149,
+	203,87,40,84,33,1,0,34,37,152,221,54,
+	253,0,221,54,254,0,24,53,33,236,151,54,
+	175,33,3,0,229,33,234,151,229,205,174,140,
+	193,193,33,236,151,126,254,255,40,14,33,110,
+	152,94,22,0,33,234,149,25,54,140,24,159,
+	221,110,253,221,102,254,35,221,117,253,221,116,
+	254,17,32,0,221,110,253,221,102,254,205,171,
+	149,250,12,149,33,2,0,34,37,152,221,54,
+	253,0,221,54,254,0,24,54,33,236,151,54,
+	175,33,3,0,229,33,234,151,229,205,174,140,
+	193,193,33,236,151,126,254,255,40,15,33,110,
+	152,94,22,0,33,234,149,25,54,132,195,211,
+	148,221,110,253,221,102,254,35,221,117,253,221,
+	116,254,17,32,0,221,110,253,221,102,254,205,
+	171,149,250,96,149,33,1,0,195,198,149,124,
+	170,250,179,149,237,82,201,124,230,128,237,82,
+	60,201,225,253,229,221,229,221,33,0,0,221,
+	57,233,221,249,221,225,253,225,201,233,225,253,
+	229,221,229,221,33,0,0,221,57,94,35,86,
+	35,235,57,249,235,233,0,0,0,0,0,0,
+	62,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	175,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,133,1,0,0,0,63,
+	255,255,255,255,0,0,0,63,0,0,0,0,
+	0,0,0,0,0,0,0,24,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0
+	} ;
+
+#endif
diff --git a/drivers/net/appletalk/cops_ltdrv.h b/drivers/net/appletalk/cops_ltdrv.h
new file mode 100644
index 000000000000..c699b1ad31da
--- /dev/null
+++ b/drivers/net/appletalk/cops_ltdrv.h
@@ -0,0 +1,241 @@
+/*
+ *	The firmware this driver downloads into the Localtalk card is a
+ *	separate program and is not GPL'd source code, even though the Linux
+ *	side driver and the routine that loads this data into the card are.
+ *	
+ *	It is taken from the COPS SDK and is under the following license
+ *
+ *	This material is licensed to you strictly for use in conjunction with
+ *	the use of COPS LocalTalk adapters.
+ *	There is no charge for this SDK. And no waranty express or implied
+ *	about its fitness for any purpose. However, we will cheerefully
+ *	refund every penny you paid for this SDK...
+ *	Regards,
+ *
+ *	Thomas F. Divine
+ *	Chief Scientist
+ */
+
+
+/*      cops_ltdrv.h: LocalTalk driver firmware dump for Linux.
+ *
+ *      Authors:
+ *      - Jay Schulist <jschlst@samba.org>
+ */
+ 
+
+#ifdef CONFIG_COPS_TANGENT
+
+static const unsigned char ltdrv_code[] = {
+	58,3,0,50,148,10,33,143,15,62,85,119,
+	190,32,9,62,170,119,190,32,3,35,24,241,
+	34,146,10,249,17,150,10,33,143,15,183,237,
+	82,77,68,11,107,98,19,54,0,237,176,62,
+	16,237,57,51,62,0,237,57,50,237,57,54,
+	62,12,237,57,49,62,195,33,39,2,50,56,
+	0,34,57,0,237,86,205,30,2,251,205,60,
+	10,24,169,67,111,112,121,114,105,103,104,116,
+	32,40,99,41,32,49,57,56,56,45,49,57,
+	57,50,44,32,80,114,105,110,116,105,110,103,
+	32,67,111,109,109,117,110,105,99,97,116,105,
+	111,110,115,32,65,115,115,111,99,105,97,116,
+	101,115,44,32,73,110,99,46,65,108,108,32,
+	114,105,103,104,116,115,32,114,101,115,101,114,
+	118,101,100,46,32,32,4,4,22,40,255,60,
+	4,96,10,224,6,0,7,126,2,64,11,246,
+	12,6,13,0,14,193,15,0,5,96,3,192,
+	1,0,9,8,62,3,211,82,62,192,211,82,
+	201,62,3,211,82,62,213,211,82,201,62,5,
+	211,82,62,224,211,82,201,62,5,211,82,62,
+	224,211,82,201,62,5,211,82,62,96,211,82,
+	201,6,28,33,180,1,14,82,237,163,194,4,
+	2,33,39,2,34,64,0,58,3,0,230,1,
+	192,62,11,237,121,62,118,237,121,201,33,182,
+	10,54,132,205,253,1,201,245,197,213,229,42,
+	150,10,14,83,17,98,2,67,20,237,162,58,
+	179,1,95,219,82,230,1,32,6,29,32,247,
+	195,17,3,62,1,211,82,219,82,95,230,160,
+	32,10,237,162,32,225,21,32,222,195,15,3,
+	237,162,123,230,96,194,21,3,62,48,211,82,
+	62,1,211,82,175,211,82,237,91,150,10,43,
+	55,237,82,218,19,3,34,152,10,98,107,58,
+	154,10,190,32,81,62,1,50,158,10,35,35,
+	62,132,190,32,44,54,133,43,70,58,154,10,
+	119,43,112,17,3,0,205,137,3,62,16,211,
+	82,62,56,211,82,205,217,1,42,150,10,14,
+	83,17,98,2,67,20,58,178,1,95,195,59,
+	2,62,129,190,194,227,2,54,130,43,70,58,
+	154,10,119,43,112,17,3,0,205,137,3,195,
+	254,2,35,35,126,254,132,194,227,2,205,61,
+	3,24,20,62,128,166,194,222,2,221,229,221,
+	33,175,10,205,93,6,205,144,7,221,225,225,
+	209,193,241,251,237,77,221,229,221,33,159,10,
+	205,93,6,221,225,205,61,3,195,247,2,24,
+	237,24,235,24,233,230,64,40,2,24,227,24,
+	225,175,50,179,10,205,208,1,201,197,33,4,
+	0,57,126,35,102,111,205,51,3,193,201,62,
+	1,50,179,10,34,150,10,54,0,58,179,10,
+	183,200,62,14,211,82,62,193,211,82,62,10,
+	211,82,62,224,211,82,62,6,211,82,58,154,
+	10,211,82,62,16,211,82,62,56,211,82,62,
+	48,211,82,219,82,230,1,40,4,219,83,24,
+	242,62,14,211,82,62,33,211,82,62,1,211,
+	82,62,9,211,82,62,32,211,82,205,217,1,
+	201,14,83,205,208,1,24,23,14,83,205,208,
+	1,205,226,1,58,174,1,61,32,253,205,244,
+	1,58,174,1,61,32,253,205,226,1,58,175,
+	1,61,32,253,62,5,211,82,62,233,211,82,
+	62,128,211,82,58,176,1,61,32,253,237,163,
+	27,62,192,211,82,219,82,230,4,40,250,237,
+	163,27,122,179,32,243,219,82,230,4,40,250,
+	58,178,1,71,219,82,230,4,40,3,5,32,
+	247,219,82,230,4,40,250,205,235,1,58,177,
+	1,61,32,253,205,244,1,201,229,213,35,35,
+	126,230,128,194,145,4,43,58,154,10,119,43,
+	70,33,181,10,119,43,112,17,3,0,243,62,
+	10,211,82,219,82,230,128,202,41,4,209,225,
+	62,1,55,251,201,205,144,3,58,180,10,254,
+	255,202,127,4,205,217,1,58,178,1,71,219,
+	82,230,1,32,6,5,32,247,195,173,4,219,
+	83,71,58,154,10,184,194,173,4,58,178,1,
+	71,219,82,230,1,32,6,5,32,247,195,173,
+	4,219,83,58,178,1,71,219,82,230,1,32,
+	6,5,32,247,195,173,4,219,83,254,133,194,
+	173,4,58,179,1,24,4,58,179,1,135,61,
+	32,253,209,225,205,137,3,205,61,3,183,251,
+	201,209,225,243,62,10,211,82,219,82,230,128,
+	202,164,4,62,1,55,251,201,205,144,3,205,
+	61,3,183,251,201,209,225,62,2,55,251,201,
+	243,62,14,211,82,62,33,211,82,251,201,33,
+	4,0,57,94,35,86,33,2,0,57,126,35,
+	102,111,221,229,34,193,10,237,83,195,10,221,
+	33,171,10,205,93,6,58,185,10,50,186,10,
+	58,184,10,135,50,184,10,205,112,6,254,3,
+	56,16,58,185,10,135,60,230,15,50,185,10,
+	175,50,184,10,24,23,58,183,10,205,112,6,
+	254,3,48,13,58,185,10,203,63,50,185,10,
+	62,255,50,183,10,58,185,10,50,186,10,58,
+	183,10,135,50,183,10,62,32,50,187,10,50,
+	188,10,6,255,219,82,230,16,32,3,5,32,
+	247,205,180,4,6,40,219,82,230,16,40,3,
+	5,32,247,62,10,211,82,219,82,230,128,194,
+	46,5,219,82,230,16,40,214,237,95,71,58,
+	186,10,160,230,15,40,32,71,14,10,62,10,
+	211,82,219,82,230,128,202,119,5,205,180,4,
+	195,156,5,219,82,230,16,202,156,5,13,32,
+	229,16,225,42,193,10,237,91,195,10,205,252,
+	3,48,7,61,202,156,5,195,197,5,221,225,
+	33,0,0,201,221,33,163,10,205,93,6,58,
+	188,10,61,50,188,10,40,19,58,186,10,246,
+	1,50,186,10,58,183,10,246,1,50,183,10,
+	195,46,5,221,225,33,1,0,201,221,33,167,
+	10,205,93,6,58,184,10,246,1,50,184,10,
+	58,186,10,135,246,1,50,186,10,58,187,10,
+	61,50,187,10,194,46,5,221,225,33,2,0,
+	201,221,229,33,0,0,57,17,4,0,25,126,
+	50,154,10,230,128,50,189,10,58,189,10,183,
+	40,6,221,33,88,2,24,4,221,33,150,0,
+	58,154,10,183,40,49,60,40,46,61,33,190,
+	10,119,35,119,35,54,129,175,50,158,10,221,
+	43,221,229,225,124,181,40,42,33,190,10,17,
+	3,0,205,206,4,17,232,3,27,123,178,32,
+	251,58,158,10,183,40,224,58,154,10,71,62,
+	7,128,230,127,71,58,189,10,176,50,154,10,
+	24,166,221,225,201,183,221,52,0,192,221,52,
+	1,192,221,52,2,192,221,52,3,192,55,201,
+	6,8,14,0,31,48,1,12,16,250,121,201,
+	33,2,0,57,94,35,86,35,78,35,70,35,
+	126,35,102,105,79,120,68,103,237,176,201,33,
+	2,0,57,126,35,102,111,62,17,237,57,48,
+	125,237,57,40,124,237,57,41,62,0,237,57,
+	42,62,64,237,57,43,62,0,237,57,44,33,
+	128,2,125,237,57,46,124,237,57,47,62,145,
+	237,57,48,211,68,58,149,10,211,66,201,33,
+	2,0,57,126,35,102,111,62,33,237,57,48,
+	62,64,237,57,32,62,0,237,57,33,237,57,
+	34,125,237,57,35,124,237,57,36,62,0,237,
+	57,37,33,128,2,125,237,57,38,124,237,57,
+	39,62,97,237,57,48,211,67,58,149,10,211,
+	66,201,237,56,46,95,237,56,47,87,237,56,
+	46,111,237,56,47,103,183,237,82,32,235,33,
+	128,2,183,237,82,201,237,56,38,95,237,56,
+	39,87,237,56,38,111,237,56,39,103,183,237,
+	82,32,235,33,128,2,183,237,82,201,205,106,
+	10,221,110,6,221,102,7,126,35,110,103,195,
+	118,10,205,106,10,33,0,0,34,205,10,34,
+	198,10,34,200,10,33,143,15,34,207,10,237,
+	91,207,10,42,146,10,183,237,82,17,0,255,
+	25,34,203,10,203,124,40,6,33,0,125,34,
+	203,10,42,207,10,229,205,37,3,195,118,10,
+	205,106,10,229,42,150,10,35,35,35,229,205,
+	70,7,193,124,230,3,103,221,117,254,221,116,
+	255,237,91,152,10,35,35,35,183,237,82,32,
+	12,17,5,0,42,152,10,205,91,10,242,203,
+	7,42,150,10,229,205,37,3,195,118,10,237,
+	91,152,10,42,200,10,25,34,200,10,42,205,
+	10,25,34,205,10,237,91,203,10,33,158,253,
+	25,237,91,205,10,205,91,10,242,245,7,33,
+	0,0,34,205,10,62,1,50,197,10,205,5,
+	8,33,0,0,57,249,195,118,10,205,106,10,
+	58,197,10,183,202,118,10,237,91,198,10,42,
+	205,10,205,91,10,242,46,8,237,91,205,10,
+	33,98,2,25,237,91,198,10,205,91,10,250,
+	78,8,237,91,198,10,42,205,10,183,237,82,
+	32,7,42,200,10,125,180,40,13,237,91,205,
+	10,42,198,10,205,91,10,242,97,8,237,91,
+	207,10,42,205,10,25,229,205,37,3,175,50,
+	197,10,195,118,10,205,29,3,33,0,0,57,
+	249,195,118,10,205,106,10,58,202,10,183,40,
+	22,205,14,7,237,91,209,10,19,19,19,205,
+	91,10,242,139,8,33,1,0,195,118,10,33,
+	0,0,195,118,10,205,126,10,252,255,205,108,
+	8,125,180,194,118,10,237,91,200,10,33,0,
+	0,205,91,10,242,118,10,237,91,207,10,42,
+	198,10,25,221,117,254,221,116,255,35,35,35,
+	229,205,70,7,193,124,230,3,103,35,35,35,
+	221,117,252,221,116,253,229,221,110,254,221,102,
+	255,229,33,212,10,229,205,124,6,193,193,221,
+	110,252,221,102,253,34,209,10,33,211,10,54,
+	4,33,209,10,227,205,147,6,193,62,1,50,
+	202,10,243,221,94,252,221,86,253,42,200,10,
+	183,237,82,34,200,10,203,124,40,17,33,0,
+	0,34,200,10,34,205,10,34,198,10,50,197,
+	10,24,37,221,94,252,221,86,253,42,198,10,
+	25,34,198,10,237,91,203,10,33,158,253,25,
+	237,91,198,10,205,91,10,242,68,9,33,0,
+	0,34,198,10,205,5,8,33,0,0,57,249,
+	251,195,118,10,205,106,10,33,49,13,126,183,
+	40,16,205,42,7,237,91,47,13,19,19,19,
+	205,91,10,242,117,9,58,142,15,198,1,50,
+	142,15,195,118,10,33,49,13,126,254,1,40,
+	25,254,3,202,7,10,254,5,202,21,10,33,
+	49,13,54,0,33,47,13,229,205,207,6,195,
+	118,10,58,141,15,183,32,72,33,51,13,126,
+	50,149,10,205,86,7,33,50,13,126,230,127,
+	183,32,40,58,142,15,230,127,50,142,15,183,
+	32,5,198,1,50,142,15,33,50,13,126,111,
+	23,159,103,203,125,58,142,15,40,5,198,128,
+	50,142,15,33,50,13,119,33,50,13,126,111,
+	23,159,103,229,205,237,5,193,33,211,10,54,
+	2,33,2,0,34,209,10,58,154,10,33,212,
+	10,119,58,148,10,33,213,10,119,33,209,10,
+	229,205,147,6,193,24,128,42,47,13,229,33,
+	50,13,229,205,191,4,193,24,239,33,211,10,
+	54,6,33,3,0,34,209,10,58,154,10,33,
+	212,10,119,58,148,10,33,213,10,119,33,214,
+	10,54,5,33,209,10,229,205,147,6,24,200,
+	205,106,10,33,49,13,54,0,33,47,13,229,
+	205,207,6,33,209,10,227,205,147,6,193,205,
+	80,9,205,145,8,24,248,124,170,250,99,10,
+	237,82,201,124,230,128,237,82,60,201,225,253,
+	229,221,229,221,33,0,0,221,57,233,221,249,
+	221,225,253,225,201,233,225,253,229,221,229,221,
+	33,0,0,221,57,94,35,86,35,235,57,249,
+	235,233,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0,0,0,0,0,0,0,0,
+	0,0,0,0,0
+	} ;
+
+#endif
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
new file mode 100644
index 000000000000..10d0dba572c2
--- /dev/null
+++ b/drivers/net/appletalk/ipddp.c
@@ -0,0 +1,335 @@
+/*
+ *	ipddp.c: IP to Appletalk-IP Encapsulation driver for Linux
+ *		 Appletalk-IP to IP Decapsulation driver for Linux
+ *
+ *	Authors:
+ *      - DDP-IP Encap by: Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *	- DDP-IP Decap by: Jay Schulist <jschlst@samba.org>
+ *
+ *	Derived from:
+ *	- Almost all code already existed in net/appletalk/ddp.c I just
+ *	  moved/reorginized it into a driver file. Original IP-over-DDP code
+ *	  was done by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *      - skeleton.c: A network driver outline for linux.
+ *        Written 1993-94 by Donald Becker.
+ *	- dummy.c: A dummy net driver. By Nick Holloway.
+ *	- MacGate: A user space Daemon for Appletalk-IP Decap for
+ *	  Linux by Jay Schulist <jschlst@samba.org>
+ *
+ *      Copyright 1993 United States Government as represented by the
+ *      Director, National Security Agency.
+ *
+ *      This software may be used and distributed according to the terms
+ *      of the GNU General Public License, incorporated herein by reference.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ip.h>
+#include <linux/atalk.h>
+#include <linux/if_arp.h>
+#include <linux/slab.h>
+#include <net/route.h>
+#include <asm/uaccess.h>
+
+#include "ipddp.h"		/* Our stuff */
+
+static const char version[] = KERN_INFO "ipddp.c:v0.01 8/28/97 Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n";
+
+static struct ipddp_route *ipddp_route_list;
+static DEFINE_SPINLOCK(ipddp_route_lock);
+
+#ifdef CONFIG_IPDDP_ENCAP
+static int ipddp_mode = IPDDP_ENCAP;
+#else
+static int ipddp_mode = IPDDP_DECAP;
+#endif
+
+/* Index to functions, as function prototypes. */
+static netdev_tx_t ipddp_xmit(struct sk_buff *skb,
+				    struct net_device *dev);
+static int ipddp_create(struct ipddp_route *new_rt);
+static int ipddp_delete(struct ipddp_route *rt);
+static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt);
+static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
+
+static const struct net_device_ops ipddp_netdev_ops = {
+	.ndo_start_xmit		= ipddp_xmit,
+	.ndo_do_ioctl   	= ipddp_ioctl,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
+static struct net_device * __init ipddp_init(void)
+{
+	static unsigned version_printed;
+	struct net_device *dev;
+	int err;
+
+	dev = alloc_etherdev(0);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	strcpy(dev->name, "ipddp%d");
+
+	if (version_printed++ == 0)
+                printk(version);
+
+	/* Initialize the device structure. */
+	dev->netdev_ops = &ipddp_netdev_ops;
+
+        dev->type = ARPHRD_IPDDP;       	/* IP over DDP tunnel */
+        dev->mtu = 585;
+        dev->flags |= IFF_NOARP;
+
+        /*
+         *      The worst case header we will need is currently a
+         *      ethernet header (14 bytes) and a ddp header (sizeof ddpehdr+1)
+         *      We send over SNAP so that takes another 8 bytes.
+         */
+        dev->hard_header_len = 14+8+sizeof(struct ddpehdr)+1;
+
+	err = register_netdev(dev);
+	if (err) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
+	/* Let the user now what mode we are in */
+	if(ipddp_mode == IPDDP_ENCAP)
+		printk("%s: Appletalk-IP Encap. mode by Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n", 
+			dev->name);
+	if(ipddp_mode == IPDDP_DECAP)
+		printk("%s: Appletalk-IP Decap. mode by Jay Schulist <jschlst@samba.org>\n", 
+			dev->name);
+
+        return dev;
+}
+
+
+/*
+ * Transmit LLAP/ELAP frame using aarp_send_ddp.
+ */
+static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	__be32 paddr = skb_rtable(skb)->rt_gateway;
+        struct ddpehdr *ddp;
+        struct ipddp_route *rt;
+        struct atalk_addr *our_addr;
+
+	spin_lock(&ipddp_route_lock);
+
+	/*
+         * Find appropriate route to use, based only on IP number.
+         */
+        for(rt = ipddp_route_list; rt != NULL; rt = rt->next)
+        {
+                if(rt->ip == paddr)
+                        break;
+        }
+        if(rt == NULL) {
+		spin_unlock(&ipddp_route_lock);
+                return NETDEV_TX_OK;
+	}
+
+        our_addr = atalk_find_dev_addr(rt->dev);
+
+	if(ipddp_mode == IPDDP_DECAP)
+		/* 
+		 * Pull off the excess room that should not be there.
+		 * This is due to a hard-header problem. This is the
+		 * quick fix for now though, till it breaks.
+		 */
+		skb_pull(skb, 35-(sizeof(struct ddpehdr)+1));
+
+	/* Create the Extended DDP header */
+	ddp = (struct ddpehdr *)skb->data;
+        ddp->deh_len_hops = htons(skb->len + (1<<10));
+        ddp->deh_sum = 0;
+
+	/*
+         * For Localtalk we need aarp_send_ddp to strip the
+         * long DDP header and place a shot DDP header on it.
+         */
+        if(rt->dev->type == ARPHRD_LOCALTLK)
+        {
+                ddp->deh_dnet  = 0;   /* FIXME more hops?? */
+                ddp->deh_snet  = 0;
+        }
+        else
+        {
+                ddp->deh_dnet  = rt->at.s_net;   /* FIXME more hops?? */
+                ddp->deh_snet  = our_addr->s_net;
+        }
+        ddp->deh_dnode = rt->at.s_node;
+        ddp->deh_snode = our_addr->s_node;
+        ddp->deh_dport = 72;
+        ddp->deh_sport = 72;
+
+        *((__u8 *)(ddp+1)) = 22;        	/* ddp type = IP */
+
+        skb->protocol = htons(ETH_P_ATALK);     /* Protocol has changed */
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	aarp_send_ddp(rt->dev, skb, &rt->at, NULL);
+
+	spin_unlock(&ipddp_route_lock);
+
+        return NETDEV_TX_OK;
+}
+
+/*
+ * Create a routing entry. We first verify that the
+ * record does not already exist. If it does we return -EEXIST
+ */
+static int ipddp_create(struct ipddp_route *new_rt)
+{
+        struct ipddp_route *rt = kmalloc(sizeof(*rt), GFP_KERNEL);
+
+        if (rt == NULL)
+                return -ENOMEM;
+
+        rt->ip = new_rt->ip;
+        rt->at = new_rt->at;
+        rt->next = NULL;
+        if ((rt->dev = atrtr_get_dev(&rt->at)) == NULL) {
+		kfree(rt);
+                return -ENETUNREACH;
+        }
+
+	spin_lock_bh(&ipddp_route_lock);
+	if (__ipddp_find_route(rt)) {
+		spin_unlock_bh(&ipddp_route_lock);
+		kfree(rt);
+		return -EEXIST;
+	}
+
+        rt->next = ipddp_route_list;
+        ipddp_route_list = rt;
+
+	spin_unlock_bh(&ipddp_route_lock);
+
+        return 0;
+}
+
+/*
+ * Delete a route, we only delete a FULL match.
+ * If route does not exist we return -ENOENT.
+ */
+static int ipddp_delete(struct ipddp_route *rt)
+{
+        struct ipddp_route **r = &ipddp_route_list;
+        struct ipddp_route *tmp;
+
+	spin_lock_bh(&ipddp_route_lock);
+        while((tmp = *r) != NULL)
+        {
+                if(tmp->ip == rt->ip &&
+		   tmp->at.s_net == rt->at.s_net &&
+		   tmp->at.s_node == rt->at.s_node)
+                {
+                        *r = tmp->next;
+			spin_unlock_bh(&ipddp_route_lock);
+                        kfree(tmp);
+                        return 0;
+                }
+                r = &tmp->next;
+        }
+
+	spin_unlock_bh(&ipddp_route_lock);
+        return -ENOENT;
+}
+
+/*
+ * Find a routing entry, we only return a FULL match
+ */
+static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt)
+{
+        struct ipddp_route *f;
+
+        for(f = ipddp_route_list; f != NULL; f = f->next)
+        {
+                if(f->ip == rt->ip &&
+		   f->at.s_net == rt->at.s_net &&
+		   f->at.s_node == rt->at.s_node)
+                        return f;
+        }
+
+        return NULL;
+}
+
+static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+        struct ipddp_route __user *rt = ifr->ifr_data;
+        struct ipddp_route rcp, rcp2, *rp;
+
+        if(!capable(CAP_NET_ADMIN))
+                return -EPERM;
+
+	if(copy_from_user(&rcp, rt, sizeof(rcp)))
+		return -EFAULT;
+
+        switch(cmd)
+        {
+		case SIOCADDIPDDPRT:
+                        return ipddp_create(&rcp);
+
+                case SIOCFINDIPDDPRT:
+			spin_lock_bh(&ipddp_route_lock);
+			rp = __ipddp_find_route(&rcp);
+			if (rp)
+				memcpy(&rcp2, rp, sizeof(rcp2));
+			spin_unlock_bh(&ipddp_route_lock);
+
+			if (rp) {
+				if (copy_to_user(rt, &rcp2,
+						 sizeof(struct ipddp_route)))
+					return -EFAULT;
+				return 0;
+			} else
+				return -ENOENT;
+
+                case SIOCDELIPDDPRT:
+                        return ipddp_delete(&rcp);
+
+                default:
+                        return -EINVAL;
+        }
+}
+
+static struct net_device *dev_ipddp;
+
+MODULE_LICENSE("GPL");
+module_param(ipddp_mode, int, 0);
+
+static int __init ipddp_init_module(void)
+{
+	dev_ipddp = ipddp_init();
+        if (IS_ERR(dev_ipddp))
+                return PTR_ERR(dev_ipddp);
+	return 0;
+}
+
+static void __exit ipddp_cleanup_module(void)
+{
+        struct ipddp_route *p;
+
+	unregister_netdev(dev_ipddp);
+        free_netdev(dev_ipddp);
+
+        while (ipddp_route_list) {
+                p = ipddp_route_list->next;
+                kfree(ipddp_route_list);
+                ipddp_route_list = p;
+        }
+}
+
+module_init(ipddp_init_module);
+module_exit(ipddp_cleanup_module);
diff --git a/drivers/net/appletalk/ipddp.h b/drivers/net/appletalk/ipddp.h
new file mode 100644
index 000000000000..531519da99a3
--- /dev/null
+++ b/drivers/net/appletalk/ipddp.h
@@ -0,0 +1,27 @@
+/*
+ *	ipddp.h: Header for IP-over-DDP driver for Linux.
+ */
+
+#ifndef __LINUX_IPDDP_H
+#define __LINUX_IPDDP_H
+
+#ifdef __KERNEL__
+
+#define SIOCADDIPDDPRT   (SIOCDEVPRIVATE)
+#define SIOCDELIPDDPRT   (SIOCDEVPRIVATE+1)
+#define SIOCFINDIPDDPRT  (SIOCDEVPRIVATE+2)
+
+struct ipddp_route
+{
+        struct net_device *dev;             /* Carrier device */
+        __be32 ip;                       /* IP address */
+        struct atalk_addr at;              /* Gateway appletalk address */
+        int flags;
+        struct ipddp_route *next;
+};
+
+#define IPDDP_ENCAP	1
+#define IPDDP_DECAP	2
+
+#endif	/* __KERNEL__ */
+#endif	/* __LINUX_IPDDP_H */
diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c
new file mode 100644
index 000000000000..e69eead12ec7
--- /dev/null
+++ b/drivers/net/appletalk/ltpc.c
@@ -0,0 +1,1288 @@
+/***    ltpc.c -- a driver for the LocalTalk PC card.
+ *
+ *      Copyright (c) 1995,1996 Bradford W. Johnson <johns393@maroon.tc.umn.edu>
+ *
+ *      This software may be used and distributed according to the terms
+ *      of the GNU General Public License, incorporated herein by reference.
+ *
+ *      This is ALPHA code at best.  It may not work for you.  It may
+ *      damage your equipment.  It may damage your relations with other
+ *      users of your network.  Use it at your own risk!
+ *
+ *      Based in part on:
+ *      skeleton.c      by Donald Becker
+ *      dummy.c         by Nick Holloway and Alan Cox
+ *      loopback.c      by Ross Biro, Fred van Kampen, Donald Becker
+ *      the netatalk source code (UMICH)
+ *      lots of work on the card...
+ *
+ *      I do not have access to the (proprietary) SDK that goes with the card.
+ *      If you do, I don't want to know about it, and you can probably write
+ *      a better driver yourself anyway.  This does mean that the pieces that
+ *      talk to the card are guesswork on my part, so use at your own risk!
+ *
+ *      This is my first try at writing Linux networking code, and is also
+ *      guesswork.  Again, use at your own risk!  (Although on this part, I'd
+ *      welcome suggestions)
+ *
+ *      This is a loadable kernel module which seems to work at my site
+ *      consisting of a 1.2.13 linux box running netatalk 1.3.3, and with
+ *      the kernel support from 1.3.3b2 including patches routing.patch
+ *      and ddp.disappears.from.chooser.  In order to run it, you will need
+ *      to patch ddp.c and aarp.c in the kernel, but only a little...
+ *
+ *      I'm fairly confident that while this is arguably badly written, the
+ *      problems that people experience will be "higher level", that is, with
+ *      complications in the netatalk code.  The driver itself doesn't do
+ *      anything terribly complicated -- it pretends to be an ether device
+ *      as far as netatalk is concerned, strips the DDP data out of the ether
+ *      frame and builds a LLAP packet to send out the card.  In the other
+ *      direction, it receives LLAP frames from the card and builds a fake
+ *      ether packet that it then tosses up to the networking code.  You can
+ *      argue (correctly) that this is an ugly way to do things, but it
+ *      requires a minimal amount of fooling with the code in ddp.c and aarp.c.
+ *
+ *      The card will do a lot more than is used here -- I *think* it has the
+ *      layers up through ATP.  Even if you knew how that part works (which I
+ *      don't) it would be a big job to carve up the kernel ddp code to insert
+ *      things at a higher level, and probably a bad idea...
+ *
+ *      There are a number of other cards that do LocalTalk on the PC.  If
+ *      nobody finds any insurmountable (at the netatalk level) problems
+ *      here, this driver should encourage people to put some work into the
+ *      other cards (some of which I gather are still commercially available)
+ *      and also to put hooks for LocalTalk into the official ddp code.
+ *
+ *      I welcome comments and suggestions.  This is my first try at Linux
+ *      networking stuff, and there are probably lots of things that I did
+ *      suboptimally.  
+ *
+ ***/
+
+/***
+ *
+ * $Log: ltpc.c,v $
+ * Revision 1.1.2.1  2000/03/01 05:35:07  jgarzik
+ * at and tr cleanup
+ *
+ * Revision 1.8  1997/01/28 05:44:54  bradford
+ * Clean up for non-module a little.
+ * Hacked about a bit to clean things up - Alan Cox 
+ * Probably broken it from the origina 1.8
+ *
+
+ * 1998/11/09: David Huggins-Daines <dhd@debian.org>
+ * Cleaned up the initialization code to use the standard autoirq methods,
+   and to probe for things in the standard order of i/o, irq, dma.  This
+   removes the "reset the reset" hack, because I couldn't figure out an
+   easy way to get the card to trigger an interrupt after it.
+ * Added support for passing configuration parameters on the kernel command
+   line and through insmod
+ * Changed the device name from "ltalk0" to "lt0", both to conform with the
+   other localtalk driver, and to clear up the inconsistency between the
+   module and the non-module versions of the driver :-)
+ * Added a bunch of comments (I was going to make some enums for the state
+   codes and the register offsets, but I'm still not sure exactly what their
+   semantics are)
+ * Don't poll anymore in interrupt-driven mode
+ * It seems to work as a module now (as of 2.1.127), but I don't think
+   I'm responsible for that...
+
+ *
+ * Revision 1.7  1996/12/12 03:42:33  bradford
+ * DMA alloc cribbed from 3c505.c.
+ *
+ * Revision 1.6  1996/12/12 03:18:58  bradford
+ * Added virt_to_bus; works in 2.1.13.
+ *
+ * Revision 1.5  1996/12/12 03:13:22  root
+ * xmitQel initialization -- think through better though.
+ *
+ * Revision 1.4  1996/06/18 14:55:55  root
+ * Change names to ltpc. Tabs. Took a shot at dma alloc,
+ * although more needs to be done eventually.
+ *
+ * Revision 1.3  1996/05/22 14:59:39  root
+ * Change dev->open, dev->close to track dummy.c in 1.99.(around 7)
+ *
+ * Revision 1.2  1996/05/22 14:58:24  root
+ * Change tabs mostly.
+ *
+ * Revision 1.1  1996/04/23 04:45:09  root
+ * Initial revision
+ *
+ * Revision 0.16  1996/03/05 15:59:56  root
+ * Change ARPHRD_LOCALTLK definition to the "real" one.
+ *
+ * Revision 0.15  1996/03/05 06:28:30  root
+ * Changes for kernel 1.3.70.  Still need a few patches to kernel, but
+ * it's getting closer.
+ *
+ * Revision 0.14  1996/02/25 17:38:32  root
+ * More cleanups.  Removed query to card on get_stats.
+ *
+ * Revision 0.13  1996/02/21  16:27:40  root
+ * Refix debug_print_skb.  Fix mac.raw gotcha that appeared in 1.3.65.
+ * Clean up receive code a little.
+ *
+ * Revision 0.12  1996/02/19  16:34:53  root
+ * Fix debug_print_skb.  Kludge outgoing snet to 0 when using startup
+ * range.  Change debug to mask: 1 for verbose, 2 for higher level stuff
+ * including packet printing, 4 for lower level (card i/o) stuff.
+ *
+ * Revision 0.11  1996/02/12  15:53:38  root
+ * Added router sends (requires new aarp.c patch)
+ *
+ * Revision 0.10  1996/02/11  00:19:35  root
+ * Change source LTALK_LOGGING debug switch to insmod ... debug=2.
+ *
+ * Revision 0.9  1996/02/10  23:59:35  root
+ * Fixed those fixes for 1.2 -- DANGER!  The at.h that comes with netatalk
+ * has a *different* definition of struct sockaddr_at than the Linux kernel
+ * does.  This is an "insidious and invidious" bug...
+ * (Actually the preceding comment is false -- it's the atalk.h in the
+ * ancient atalk-0.06 that's the problem)
+ *
+ * Revision 0.8  1996/02/10 19:09:00  root
+ * Merge 1.3 changes.  Tested OK under 1.3.60.
+ *
+ * Revision 0.7  1996/02/10 17:56:56  root
+ * Added debug=1 parameter on insmod for debugging prints.  Tried
+ * to fix timer unload on rmmod, but I don't think that's the problem.
+ *
+ * Revision 0.6  1995/12/31  19:01:09  root
+ * Clean up rmmod, irq comments per feedback from Corin Anderson (Thanks Corey!)
+ * Clean up initial probing -- sometimes the card wakes up latched in reset.
+ *
+ * Revision 0.5  1995/12/22  06:03:44  root
+ * Added comments in front and cleaned up a bit.
+ * This version sent out to people.
+ *
+ * Revision 0.4  1995/12/18  03:46:44  root
+ * Return shortDDP to longDDP fake to 0/0.  Added command structs.
+ *
+ ***/
+
+/* ltpc jumpers are:
+*
+*	Interrupts -- set at most one.  If none are set, the driver uses
+*	polled mode.  Because the card was developed in the XT era, the
+*	original documentation refers to IRQ2.  Since you'll be running
+*	this on an AT (or later) class machine, that really means IRQ9.
+*
+*	SW1	IRQ 4
+*	SW2	IRQ 3
+*	SW3	IRQ 9 (2 in original card documentation only applies to XT)
+*
+*
+*	DMA -- choose DMA 1 or 3, and set both corresponding switches.
+*
+*	SW4	DMA 3
+*	SW5	DMA 1
+*	SW6	DMA 3
+*	SW7	DMA 1
+*
+*
+*	I/O address -- choose one.  
+*
+*	SW8	220 / 240
+*/
+
+/*	To have some stuff logged, do 
+*	insmod ltpc.o debug=1
+*
+*	For a whole bunch of stuff, use higher numbers.
+*
+*	The default is 0, i.e. no messages except for the probe results.
+*/
+
+/* insmod-tweakable variables */
+static int debug;
+#define DEBUG_VERBOSE 1
+#define DEBUG_UPPER 2
+#define DEBUG_LOWER 4
+
+static int io;
+static int irq;
+static int dma;
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/spinlock.h>
+#include <linux/in.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_arp.h>
+#include <linux/if_ltalk.h>
+#include <linux/delay.h>
+#include <linux/timer.h>
+#include <linux/atalk.h>
+#include <linux/bitops.h>
+#include <linux/gfp.h>
+
+#include <asm/system.h>
+#include <asm/dma.h>
+#include <asm/io.h>
+
+/* our stuff */
+#include "ltpc.h"
+
+static DEFINE_SPINLOCK(txqueue_lock);
+static DEFINE_SPINLOCK(mbox_lock);
+
+/* function prototypes */
+static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
+	void *dbuf, int dbuflen);
+static int sendup_buffer (struct net_device *dev);
+
+/* Dma Memory related stuff, cribbed directly from 3c505.c */
+
+static unsigned long dma_mem_alloc(int size)
+{
+        int order = get_order(size);
+
+        return __get_dma_pages(GFP_KERNEL, order);
+}
+
+/* DMA data buffer, DMA command buffer */
+static unsigned char *ltdmabuf;
+static unsigned char *ltdmacbuf;
+
+/* private struct, holds our appletalk address */
+
+struct ltpc_private
+{
+	struct atalk_addr my_addr;
+};
+
+/* transmit queue element struct */
+
+struct xmitQel {
+	struct xmitQel *next;
+	/* command buffer */
+	unsigned char *cbuf;
+	short cbuflen;
+	/* data buffer */
+	unsigned char *dbuf;
+	short dbuflen;
+	unsigned char QWrite;	/* read or write data */
+	unsigned char mailbox;
+};
+
+/* the transmit queue itself */
+
+static struct xmitQel *xmQhd, *xmQtl;
+
+static void enQ(struct xmitQel *qel)
+{
+	unsigned long flags;
+	qel->next = NULL;
+	
+	spin_lock_irqsave(&txqueue_lock, flags);
+	if (xmQtl) {
+		xmQtl->next = qel;
+	} else {
+		xmQhd = qel;
+	}
+	xmQtl = qel;
+	spin_unlock_irqrestore(&txqueue_lock, flags);
+
+	if (debug & DEBUG_LOWER)
+		printk("enqueued a 0x%02x command\n",qel->cbuf[0]);
+}
+
+static struct xmitQel *deQ(void)
+{
+	unsigned long flags;
+	int i;
+	struct xmitQel *qel=NULL;
+	
+	spin_lock_irqsave(&txqueue_lock, flags);
+	if (xmQhd) {
+		qel = xmQhd;
+		xmQhd = qel->next;
+		if(!xmQhd) xmQtl = NULL;
+	}
+	spin_unlock_irqrestore(&txqueue_lock, flags);
+
+	if ((debug & DEBUG_LOWER) && qel) {
+		int n;
+		printk(KERN_DEBUG "ltpc: dequeued command ");
+		n = qel->cbuflen;
+		if (n>100) n=100;
+		for(i=0;i<n;i++) printk("%02x ",qel->cbuf[i]);
+		printk("\n");
+	}
+
+	return qel;
+}
+
+/* and... the queue elements we'll be using */
+static struct xmitQel qels[16];
+
+/* and their corresponding mailboxes */
+static unsigned char mailbox[16];
+static unsigned char mboxinuse[16] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};
+
+static int wait_timeout(struct net_device *dev, int c)
+{
+	/* returns true if it stayed c */
+	/* this uses base+6, but it's ok */
+	int i;
+
+	/* twenty second or so total */
+
+	for(i=0;i<200000;i++) {
+		if ( c != inb_p(dev->base_addr+6) ) return 0;
+		udelay(100);
+	}
+	return 1; /* timed out */
+}
+
+/* get the first free mailbox */
+
+static int getmbox(void)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&mbox_lock, flags);
+	for(i=1;i<16;i++) if(!mboxinuse[i]) {
+		mboxinuse[i]=1;
+		spin_unlock_irqrestore(&mbox_lock, flags);
+		return i;
+	}
+	spin_unlock_irqrestore(&mbox_lock, flags);
+	return 0;
+}
+
+/* read a command from the card */
+static void handlefc(struct net_device *dev)
+{
+	/* called *only* from idle, non-reentrant */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
+	set_dma_count(dma,50);
+	enable_dma(dma);
+	release_dma_lock(flags);
+
+	inb_p(base+3);
+	inb_p(base+2);
+
+	if ( wait_timeout(dev,0xfc) ) printk("timed out in handlefc\n");
+}
+
+/* read data from the card */
+static void handlefd(struct net_device *dev)
+{
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,800);
+	enable_dma(dma);
+	release_dma_lock(flags);
+
+	inb_p(base+3);
+	inb_p(base+2);
+
+	if ( wait_timeout(dev,0xfd) ) printk("timed out in handlefd\n");
+	sendup_buffer(dev);
+} 
+
+static void handlewrite(struct net_device *dev)
+{
+	/* called *only* from idle, non-reentrant */
+	/* on entry, 0xfb and ltdmabuf holds data */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+	
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_WRITE);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,800);
+	enable_dma(dma);
+	release_dma_lock(flags);
+	
+	inb_p(base+3);
+	inb_p(base+2);
+
+	if ( wait_timeout(dev,0xfb) ) {
+		flags=claim_dma_lock();
+		printk("timed out in handlewrite, dma res %d\n",
+			get_dma_residue(dev->dma) );
+		release_dma_lock(flags);
+	}
+}
+
+static void handleread(struct net_device *dev)
+{
+	/* on entry, 0xfb */
+	/* on exit, ltdmabuf holds data */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+	
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,800);
+	enable_dma(dma);
+	release_dma_lock(flags);
+
+	inb_p(base+3);
+	inb_p(base+2);
+	if ( wait_timeout(dev,0xfb) ) printk("timed out in handleread\n");
+}
+
+static void handlecommand(struct net_device *dev)
+{
+	/* on entry, 0xfa and ltdmacbuf holds command */
+	int dma = dev->dma;
+	int base = dev->base_addr;
+	unsigned long flags;
+
+	flags=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_WRITE);
+	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
+	set_dma_count(dma,50);
+	enable_dma(dma);
+	release_dma_lock(flags);
+	inb_p(base+3);
+	inb_p(base+2);
+	if ( wait_timeout(dev,0xfa) ) printk("timed out in handlecommand\n");
+} 
+
+/* ready made command for getting the result from the card */
+static unsigned char rescbuf[2] = {LT_GETRESULT,0};
+static unsigned char resdbuf[2];
+
+static int QInIdle;
+
+/* idle expects to be called with the IRQ line high -- either because of
+ * an interrupt, or because the line is tri-stated
+ */
+
+static void idle(struct net_device *dev)
+{
+	unsigned long flags;
+	int state;
+	/* FIXME This is initialized to shut the warning up, but I need to
+	 * think this through again.
+	 */
+	struct xmitQel *q = NULL;
+	int oops;
+	int i;
+	int base = dev->base_addr;
+
+	spin_lock_irqsave(&txqueue_lock, flags);
+	if(QInIdle) {
+		spin_unlock_irqrestore(&txqueue_lock, flags);
+		return;
+	}
+	QInIdle = 1;
+	spin_unlock_irqrestore(&txqueue_lock, flags);
+
+	/* this tri-states the IRQ line */
+	(void) inb_p(base+6);
+
+	oops = 100;
+
+loop:
+	if (0>oops--) { 
+		printk("idle: looped too many times\n");
+		goto done;
+	}
+
+	state = inb_p(base+6);
+	if (state != inb_p(base+6)) goto loop;
+
+	switch(state) {
+		case 0xfc:
+			/* incoming command */
+			if (debug & DEBUG_LOWER) printk("idle: fc\n");
+			handlefc(dev); 
+			break;
+		case 0xfd:
+			/* incoming data */
+			if(debug & DEBUG_LOWER) printk("idle: fd\n");
+			handlefd(dev); 
+			break;
+		case 0xf9:
+			/* result ready */
+			if (debug & DEBUG_LOWER) printk("idle: f9\n");
+			if(!mboxinuse[0]) {
+				mboxinuse[0] = 1;
+				qels[0].cbuf = rescbuf;
+				qels[0].cbuflen = 2;
+				qels[0].dbuf = resdbuf;
+				qels[0].dbuflen = 2;
+				qels[0].QWrite = 0;
+				qels[0].mailbox = 0;
+				enQ(&qels[0]);
+			}
+			inb_p(dev->base_addr+1);
+			inb_p(dev->base_addr+0);
+			if( wait_timeout(dev,0xf9) )
+				printk("timed out idle f9\n");
+			break;
+		case 0xf8:
+			/* ?? */
+			if (xmQhd) {
+				inb_p(dev->base_addr+1);
+				inb_p(dev->base_addr+0);
+				if(wait_timeout(dev,0xf8) )
+					printk("timed out idle f8\n");
+			} else {
+				goto done;
+			}
+			break;
+		case 0xfa:
+			/* waiting for command */
+			if(debug & DEBUG_LOWER) printk("idle: fa\n");
+			if (xmQhd) {
+				q=deQ();
+				memcpy(ltdmacbuf,q->cbuf,q->cbuflen);
+				ltdmacbuf[1] = q->mailbox;
+				if (debug>1) { 
+					int n;
+					printk("ltpc: sent command     ");
+					n = q->cbuflen;
+					if (n>100) n=100;
+					for(i=0;i<n;i++)
+						printk("%02x ",ltdmacbuf[i]);
+					printk("\n");
+				}
+				handlecommand(dev);
+					if(0xfa==inb_p(base+6)) {
+						/* we timed out, so return */
+						goto done;
+					} 
+			} else {
+				/* we don't seem to have a command */
+				if (!mboxinuse[0]) {
+					mboxinuse[0] = 1;
+					qels[0].cbuf = rescbuf;
+					qels[0].cbuflen = 2;
+					qels[0].dbuf = resdbuf;
+					qels[0].dbuflen = 2;
+					qels[0].QWrite = 0;
+					qels[0].mailbox = 0;
+					enQ(&qels[0]);
+				} else {
+					printk("trouble: response command already queued\n");
+					goto done;
+				}
+			} 
+			break;
+		case 0Xfb:
+			/* data transfer ready */
+			if(debug & DEBUG_LOWER) printk("idle: fb\n");
+			if(q->QWrite) {
+				memcpy(ltdmabuf,q->dbuf,q->dbuflen);
+				handlewrite(dev);
+			} else {
+				handleread(dev);
+				/* non-zero mailbox numbers are for
+				   commmands, 0 is for GETRESULT
+				   requests */
+				if(q->mailbox) {
+					memcpy(q->dbuf,ltdmabuf,q->dbuflen);
+				} else { 
+					/* this was a result */
+					mailbox[ 0x0f & ltdmabuf[0] ] = ltdmabuf[1];
+					mboxinuse[0]=0;
+				}
+			}
+			break;
+	}
+	goto loop;
+
+done:
+	QInIdle=0;
+
+	/* now set the interrupts back as appropriate */
+	/* the first read takes it out of tri-state (but still high) */
+	/* the second resets it */
+	/* note that after this point, any read of base+6 will
+	   trigger an interrupt */
+
+	if (dev->irq) {
+		inb_p(base+7);
+		inb_p(base+7);
+	}
+}
+
+
+static int do_write(struct net_device *dev, void *cbuf, int cbuflen,
+	void *dbuf, int dbuflen)
+{
+
+	int i = getmbox();
+	int ret;
+
+	if(i) {
+		qels[i].cbuf = (unsigned char *) cbuf;
+		qels[i].cbuflen = cbuflen;
+		qels[i].dbuf = (unsigned char *) dbuf;
+		qels[i].dbuflen = dbuflen;
+		qels[i].QWrite = 1;
+		qels[i].mailbox = i;  /* this should be initted rather */
+		enQ(&qels[i]);
+		idle(dev);
+		ret = mailbox[i];
+		mboxinuse[i]=0;
+		return ret;
+	}
+	printk("ltpc: could not allocate mbox\n");
+	return -1;
+}
+
+static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
+	void *dbuf, int dbuflen)
+{
+
+	int i = getmbox();
+	int ret;
+
+	if(i) {
+		qels[i].cbuf = (unsigned char *) cbuf;
+		qels[i].cbuflen = cbuflen;
+		qels[i].dbuf = (unsigned char *) dbuf;
+		qels[i].dbuflen = dbuflen;
+		qels[i].QWrite = 0;
+		qels[i].mailbox = i;  /* this should be initted rather */
+		enQ(&qels[i]);
+		idle(dev);
+		ret = mailbox[i];
+		mboxinuse[i]=0;
+		return ret;
+	}
+	printk("ltpc: could not allocate mbox\n");
+	return -1;
+}
+
+/* end of idle handlers -- what should be seen is do_read, do_write */
+
+static struct timer_list ltpc_timer;
+
+static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev);
+
+static int read_30 ( struct net_device *dev)
+{
+	lt_command c;
+	c.getflags.command = LT_GETFLAGS;
+	return do_read(dev, &c, sizeof(c.getflags),&c,0);
+}
+
+static int set_30 (struct net_device *dev,int x)
+{
+	lt_command c;
+	c.setflags.command = LT_SETFLAGS;
+	c.setflags.flags = x;
+	return do_write(dev, &c, sizeof(c.setflags),&c,0);
+}
+
+/* LLAP to DDP translation */
+
+static int sendup_buffer (struct net_device *dev)
+{
+	/* on entry, command is in ltdmacbuf, data in ltdmabuf */
+	/* called from idle, non-reentrant */
+
+	int dnode, snode, llaptype, len; 
+	int sklen;
+	struct sk_buff *skb;
+	struct lt_rcvlap *ltc = (struct lt_rcvlap *) ltdmacbuf;
+
+	if (ltc->command != LT_RCVLAP) {
+		printk("unknown command 0x%02x from ltpc card\n",ltc->command);
+		return -1;
+	}
+	dnode = ltc->dnode;
+	snode = ltc->snode;
+	llaptype = ltc->laptype;
+	len = ltc->length; 
+
+	sklen = len;
+	if (llaptype == 1) 
+		sklen += 8;  /* correct for short ddp */
+	if(sklen > 800) {
+		printk(KERN_INFO "%s: nonsense length in ltpc command 0x14: 0x%08x\n",
+			dev->name,sklen);
+		return -1;
+	}
+
+	if ( (llaptype==0) || (llaptype>2) ) {
+		printk(KERN_INFO "%s: unknown LLAP type: %d\n",dev->name,llaptype);
+		return -1;
+	}
+
+
+	skb = dev_alloc_skb(3+sklen);
+	if (skb == NULL) 
+	{
+		printk("%s: dropping packet due to memory squeeze.\n",
+			dev->name);
+		return -1;
+	}
+	skb->dev = dev;
+
+	if (sklen > len)
+		skb_reserve(skb,8);
+	skb_put(skb,len+3);
+	skb->protocol = htons(ETH_P_LOCALTALK);
+	/* add LLAP header */
+	skb->data[0] = dnode;
+	skb->data[1] = snode;
+	skb->data[2] = llaptype;
+	skb_reset_mac_header(skb);	/* save pointer to llap header */
+	skb_pull(skb,3);
+
+	/* copy ddp(s,e)hdr + contents */
+	skb_copy_to_linear_data(skb, ltdmabuf, len);
+
+	skb_reset_transport_header(skb);
+
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += skb->len;
+
+	/* toss it onwards */
+	netif_rx(skb);
+	return 0;
+}
+
+/* the handler for the board interrupt */
+ 
+static irqreturn_t
+ltpc_interrupt(int irq, void *dev_id)
+{
+	struct net_device *dev = dev_id;
+
+	if (dev==NULL) {
+		printk("ltpc_interrupt: unknown device.\n");
+		return IRQ_NONE;
+	}
+
+	inb_p(dev->base_addr+6);  /* disable further interrupts from board */
+
+	idle(dev); /* handle whatever is coming in */
+ 
+	/* idle re-enables interrupts from board */ 
+
+	return IRQ_HANDLED;
+}
+
+/***
+ *
+ *    The ioctls that the driver responds to are:
+ *
+ *    SIOCSIFADDR -- do probe using the passed node hint.
+ *    SIOCGIFADDR -- return net, node.
+ *
+ *    some of this stuff should be done elsewhere.
+ *
+ ***/
+
+static int ltpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	struct sockaddr_at *sa = (struct sockaddr_at *) &ifr->ifr_addr;
+	/* we'll keep the localtalk node address in dev->pa_addr */
+	struct ltpc_private *ltpc_priv = netdev_priv(dev);
+	struct atalk_addr *aa = &ltpc_priv->my_addr;
+	struct lt_init c;
+	int ltflags;
+
+	if(debug & DEBUG_VERBOSE) printk("ltpc_ioctl called\n");
+
+	switch(cmd) {
+		case SIOCSIFADDR:
+
+			aa->s_net  = sa->sat_addr.s_net;
+      
+			/* this does the probe and returns the node addr */
+			c.command = LT_INIT;
+			c.hint = sa->sat_addr.s_node;
+
+			aa->s_node = do_read(dev,&c,sizeof(c),&c,0);
+
+			/* get all llap frames raw */
+			ltflags = read_30(dev);
+			ltflags |= LT_FLAG_ALLLAP;
+			set_30 (dev,ltflags);  
+
+			dev->broadcast[0] = 0xFF;
+			dev->dev_addr[0] = aa->s_node;
+
+			dev->addr_len=1;
+   
+			return 0;
+
+		case SIOCGIFADDR:
+
+			sa->sat_addr.s_net = aa->s_net;
+			sa->sat_addr.s_node = aa->s_node;
+
+			return 0;
+
+		default: 
+			return -EINVAL;
+	}
+}
+
+static void set_multicast_list(struct net_device *dev)
+{
+	/* This needs to be present to keep netatalk happy. */
+	/* Actually netatalk needs fixing! */
+}
+
+static int ltpc_poll_counter;
+
+static void ltpc_poll(unsigned long l)
+{
+	struct net_device *dev = (struct net_device *) l;
+
+	del_timer(&ltpc_timer);
+
+	if(debug & DEBUG_VERBOSE) {
+		if (!ltpc_poll_counter) {
+			ltpc_poll_counter = 50;
+			printk("ltpc poll is alive\n");
+		}
+		ltpc_poll_counter--;
+	}
+  
+	if (!dev)
+		return;  /* we've been downed */
+
+	/* poll 20 times per second */
+	idle(dev);
+	ltpc_timer.expires = jiffies + HZ/20;
+	
+	add_timer(&ltpc_timer);
+}
+
+/* DDP to LLAP translation */
+
+static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	/* in kernel 1.3.xx, on entry skb->data points to ddp header,
+	 * and skb->len is the length of the ddp data + ddp header
+	 */
+	int i;
+	struct lt_sendlap cbuf;
+	unsigned char *hdr;
+
+	cbuf.command = LT_SENDLAP;
+	cbuf.dnode = skb->data[0];
+	cbuf.laptype = skb->data[2];
+	skb_pull(skb,3);	/* skip past LLAP header */
+	cbuf.length = skb->len;	/* this is host order */
+	skb_reset_transport_header(skb);
+
+	if(debug & DEBUG_UPPER) {
+		printk("command ");
+		for(i=0;i<6;i++)
+			printk("%02x ",((unsigned char *)&cbuf)[i]);
+		printk("\n");
+	}
+
+	hdr = skb_transport_header(skb);
+	do_write(dev, &cbuf, sizeof(cbuf), hdr, skb->len);
+
+	if(debug & DEBUG_UPPER) {
+		printk("sent %d ddp bytes\n",skb->len);
+		for (i = 0; i < skb->len; i++)
+			printk("%02x ", hdr[i]);
+		printk("\n");
+	}
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+/* initialization stuff */
+  
+static int __init ltpc_probe_dma(int base, int dma)
+{
+	int want = (dma == 3) ? 2 : (dma == 1) ? 1 : 3;
+  	unsigned long timeout;
+  	unsigned long f;
+  
+  	if (want & 1) {
+		if (request_dma(1,"ltpc")) {
+			want &= ~1;
+		} else {
+			f=claim_dma_lock();
+			disable_dma(1);
+			clear_dma_ff(1);
+			set_dma_mode(1,DMA_MODE_WRITE);
+			set_dma_addr(1,virt_to_bus(ltdmabuf));
+			set_dma_count(1,sizeof(struct lt_mem));
+			enable_dma(1);
+			release_dma_lock(f);
+		}
+	}
+	if (want & 2) {
+		if (request_dma(3,"ltpc")) {
+			want &= ~2;
+		} else {
+			f=claim_dma_lock();
+			disable_dma(3);
+			clear_dma_ff(3);
+			set_dma_mode(3,DMA_MODE_WRITE);
+			set_dma_addr(3,virt_to_bus(ltdmabuf));
+			set_dma_count(3,sizeof(struct lt_mem));
+			enable_dma(3);
+			release_dma_lock(f);
+		}
+	}
+	/* set up request */
+
+	/* FIXME -- do timings better! */
+
+	ltdmabuf[0] = LT_READMEM;
+	ltdmabuf[1] = 1;  /* mailbox */
+	ltdmabuf[2] = 0; ltdmabuf[3] = 0;  /* address */
+	ltdmabuf[4] = 0; ltdmabuf[5] = 1;  /* read 0x0100 bytes */
+	ltdmabuf[6] = 0; /* dunno if this is necessary */
+
+	inb_p(io+1);
+	inb_p(io+0);
+	timeout = jiffies+100*HZ/100;
+	while(time_before(jiffies, timeout)) {
+		if ( 0xfa == inb_p(io+6) ) break;
+	}
+
+	inb_p(io+3);
+	inb_p(io+2);
+	while(time_before(jiffies, timeout)) {
+		if ( 0xfb == inb_p(io+6) ) break;
+	}
+
+	/* release the other dma channel (if we opened both of them) */
+
+	if ((want & 2) && (get_dma_residue(3)==sizeof(struct lt_mem))) {
+		want &= ~2;
+		free_dma(3);
+	}
+
+	if ((want & 1) && (get_dma_residue(1)==sizeof(struct lt_mem))) {
+		want &= ~1;
+		free_dma(1);
+	}
+
+	if (!want)
+		return 0;
+
+	return (want & 2) ? 3 : 1;
+}
+
+static const struct net_device_ops ltpc_netdev = {
+	.ndo_start_xmit		= ltpc_xmit,
+	.ndo_do_ioctl		= ltpc_ioctl,
+	.ndo_set_multicast_list = set_multicast_list,
+};
+
+struct net_device * __init ltpc_probe(void)
+{
+	struct net_device *dev;
+	int err = -ENOMEM;
+	int x=0,y=0;
+	int autoirq;
+	unsigned long f;
+	unsigned long timeout;
+
+	dev = alloc_ltalkdev(sizeof(struct ltpc_private));
+	if (!dev)
+		goto out;
+
+	/* probe for the I/O port address */
+	
+	if (io != 0x240 && request_region(0x220,8,"ltpc")) {
+		x = inb_p(0x220+6);
+		if ( (x!=0xff) && (x>=0xf0) ) {
+			io = 0x220;
+			goto got_port;
+		}
+		release_region(0x220,8);
+	}
+	if (io != 0x220 && request_region(0x240,8,"ltpc")) {
+		y = inb_p(0x240+6);
+		if ( (y!=0xff) && (y>=0xf0) ){ 
+			io = 0x240;
+			goto got_port;
+		}
+		release_region(0x240,8);
+	} 
+
+	/* give up in despair */
+	printk(KERN_ERR "LocalTalk card not found; 220 = %02x, 240 = %02x.\n", x,y);
+	err = -ENODEV;
+	goto out1;
+
+ got_port:
+	/* probe for the IRQ line */
+	if (irq < 2) {
+		unsigned long irq_mask;
+
+		irq_mask = probe_irq_on();
+		/* reset the interrupt line */
+		inb_p(io+7);
+		inb_p(io+7);
+		/* trigger an interrupt (I hope) */
+		inb_p(io+6);
+		mdelay(2);
+		autoirq = probe_irq_off(irq_mask);
+
+		if (autoirq == 0) {
+			printk(KERN_ERR "ltpc: probe at %#x failed to detect IRQ line.\n", io);
+		} else {
+			irq = autoirq;
+		}
+	}
+
+	/* allocate a DMA buffer */
+	ltdmabuf = (unsigned char *) dma_mem_alloc(1000);
+	if (!ltdmabuf) {
+		printk(KERN_ERR "ltpc: mem alloc failed\n");
+		err = -ENOMEM;
+		goto out2;
+	}
+
+	ltdmacbuf = &ltdmabuf[800];
+
+	if(debug & DEBUG_VERBOSE) {
+		printk("ltdmabuf pointer %08lx\n",(unsigned long) ltdmabuf);
+	}
+
+	/* reset the card */
+
+	inb_p(io+1);
+	inb_p(io+3);
+
+	msleep(20);
+
+	inb_p(io+0);
+	inb_p(io+2);
+	inb_p(io+7); /* clear reset */
+	inb_p(io+4); 
+	inb_p(io+5);
+	inb_p(io+5); /* enable dma */
+	inb_p(io+6); /* tri-state interrupt line */
+
+	ssleep(1);
+	
+	/* now, figure out which dma channel we're using, unless it's
+	   already been specified */
+	/* well, 0 is a legal DMA channel, but the LTPC card doesn't
+	   use it... */
+	dma = ltpc_probe_dma(io, dma);
+	if (!dma) {  /* no dma channel */
+		printk(KERN_ERR "No DMA channel found on ltpc card.\n");
+		err = -ENODEV;
+		goto out3;
+	}
+
+	/* print out friendly message */
+	if(irq)
+		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, IR%d, DMA%d.\n",io,irq,dma);
+	else
+		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, DMA%d.  Using polled mode.\n",io,dma);
+
+	dev->netdev_ops = &ltpc_netdev;
+	dev->base_addr = io;
+	dev->irq = irq;
+	dev->dma = dma;
+
+	/* the card will want to send a result at this point */
+	/* (I think... leaving out this part makes the kernel crash,
+           so I put it back in...) */
+
+	f=claim_dma_lock();
+	disable_dma(dma);
+	clear_dma_ff(dma);
+	set_dma_mode(dma,DMA_MODE_READ);
+	set_dma_addr(dma,virt_to_bus(ltdmabuf));
+	set_dma_count(dma,0x100);
+	enable_dma(dma);
+	release_dma_lock(f);
+
+	(void) inb_p(io+3);
+	(void) inb_p(io+2);
+	timeout = jiffies+100*HZ/100;
+
+	while(time_before(jiffies, timeout)) {
+		if( 0xf9 == inb_p(io+6))
+			break;
+		schedule();
+	}
+
+	if(debug & DEBUG_VERBOSE) {
+		printk("setting up timer and irq\n");
+	}
+
+	/* grab it and don't let go :-) */
+	if (irq && request_irq( irq, ltpc_interrupt, 0, "ltpc", dev) >= 0)
+	{
+		(void) inb_p(io+7);  /* enable interrupts from board */
+		(void) inb_p(io+7);  /* and reset irq line */
+	} else {
+		if( irq )
+			printk(KERN_ERR "ltpc: IRQ already in use, using polled mode.\n");
+		dev->irq = 0;
+		/* polled mode -- 20 times per second */
+		/* this is really, really slow... should it poll more often? */
+		init_timer(&ltpc_timer);
+		ltpc_timer.function=ltpc_poll;
+		ltpc_timer.data = (unsigned long) dev;
+
+		ltpc_timer.expires = jiffies + HZ/20;
+		add_timer(&ltpc_timer);
+	}
+	err = register_netdev(dev);
+	if (err)
+		goto out4;
+
+	return NULL;
+out4:
+	del_timer_sync(&ltpc_timer);
+	if (dev->irq)
+		free_irq(dev->irq, dev);
+out3:
+	free_pages((unsigned long)ltdmabuf, get_order(1000));
+out2:
+	release_region(io, 8);
+out1:
+	free_netdev(dev);
+out:
+	return ERR_PTR(err);
+}
+
+#ifndef MODULE
+/* handles "ltpc=io,irq,dma" kernel command lines */
+static int __init ltpc_setup(char *str)
+{
+	int ints[5];
+
+	str = get_options(str, ARRAY_SIZE(ints), ints);
+
+	if (ints[0] == 0) {
+		if (str && !strncmp(str, "auto", 4)) {
+			/* do nothing :-) */
+		}
+		else {
+			/* usage message */
+			printk (KERN_ERR
+				"ltpc: usage: ltpc=auto|iobase[,irq[,dma]]\n");
+			return 0;
+		}
+	} else {
+		io = ints[1];
+		if (ints[0] > 1) {
+			irq = ints[2];
+		}
+		if (ints[0] > 2) {
+			dma = ints[3];
+		}
+		/* ignore any other parameters */
+	}
+	return 1;
+}
+
+__setup("ltpc=", ltpc_setup);
+#endif /* MODULE */
+
+static struct net_device *dev_ltpc;
+
+#ifdef MODULE
+
+MODULE_LICENSE("GPL");
+module_param(debug, int, 0);
+module_param(io, int, 0);
+module_param(irq, int, 0);
+module_param(dma, int, 0);
+
+
+static int __init ltpc_module_init(void)
+{
+        if(io == 0)
+		printk(KERN_NOTICE
+		       "ltpc: Autoprobing is not recommended for modules\n");
+
+	dev_ltpc = ltpc_probe();
+	if (IS_ERR(dev_ltpc))
+		return PTR_ERR(dev_ltpc);
+	return 0;
+}
+module_init(ltpc_module_init);
+#endif
+
+static void __exit ltpc_cleanup(void)
+{
+
+	if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n");
+	unregister_netdev(dev_ltpc);
+
+	ltpc_timer.data = 0;  /* signal the poll routine that we're done */
+
+	del_timer_sync(&ltpc_timer);
+
+	if(debug & DEBUG_VERBOSE) printk("freeing irq\n");
+
+	if (dev_ltpc->irq)
+		free_irq(dev_ltpc->irq, dev_ltpc);
+
+	if(debug & DEBUG_VERBOSE) printk("freeing dma\n");
+
+	if (dev_ltpc->dma)
+		free_dma(dev_ltpc->dma);
+
+	if(debug & DEBUG_VERBOSE) printk("freeing ioaddr\n");
+
+	if (dev_ltpc->base_addr)
+		release_region(dev_ltpc->base_addr,8);
+
+	free_netdev(dev_ltpc);
+
+	if(debug & DEBUG_VERBOSE) printk("free_pages\n");
+
+	free_pages( (unsigned long) ltdmabuf, get_order(1000));
+
+	if(debug & DEBUG_VERBOSE) printk("returning from cleanup_module\n");
+}
+
+module_exit(ltpc_cleanup);
diff --git a/drivers/net/appletalk/ltpc.h b/drivers/net/appletalk/ltpc.h
new file mode 100644
index 000000000000..cd30544a3729
--- /dev/null
+++ b/drivers/net/appletalk/ltpc.h
@@ -0,0 +1,73 @@
+/***   ltpc.h
+ *
+ *
+ ***/
+
+#define LT_GETRESULT  0x00
+#define LT_WRITEMEM   0x01
+#define LT_READMEM    0x02
+#define LT_GETFLAGS   0x04
+#define LT_SETFLAGS   0x05
+#define LT_INIT       0x10
+#define LT_SENDLAP    0x13
+#define LT_RCVLAP     0x14
+
+/* the flag that we care about */
+#define LT_FLAG_ALLLAP 0x04
+
+struct lt_getresult {
+	unsigned char command;
+	unsigned char mailbox;
+};
+
+struct lt_mem {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned short addr;	/* host order */
+	unsigned short length;	/* host order */
+};
+
+struct lt_setflags {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned char flags;
+};
+
+struct lt_getflags {
+	unsigned char command;
+	unsigned char mailbox;
+};
+
+struct lt_init {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned char hint;
+};
+
+struct lt_sendlap {
+	unsigned char command;
+	unsigned char mailbox;
+	unsigned char dnode;
+	unsigned char laptype;
+	unsigned short length;	/* host order */
+};
+
+struct lt_rcvlap {
+	unsigned char command;
+	unsigned char dnode;
+	unsigned char snode;
+	unsigned char laptype;
+	unsigned short length;	/* host order */
+};
+
+union lt_command {
+	struct lt_getresult getresult;
+	struct lt_mem mem;
+	struct lt_setflags setflags;
+	struct lt_getflags getflags;
+	struct lt_init init;
+	struct lt_sendlap sendlap;
+	struct lt_rcvlap rcvlap;
+};
+typedef union lt_command lt_command;
+
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 584d4e264807..b80755da5394 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -169,8 +169,6 @@ source "drivers/staging/bcm/Kconfig"
 
 source "drivers/staging/ft1000/Kconfig"
 
-source "drivers/staging/appletalk/Kconfig"
-
 source "drivers/staging/intel_sst/Kconfig"
 
 source "drivers/staging/speakup/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 88f0c64e7e58..fd26509e5efa 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -65,7 +65,6 @@ obj-$(CONFIG_ATH6K_LEGACY)	+= ath6kl/
 obj-$(CONFIG_USB_ENESTORAGE)	+= keucr/
 obj-$(CONFIG_BCM_WIMAX)	+= bcm/
 obj-$(CONFIG_FT1000)		+= ft1000/
-obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_SND_INTEL_SST)		+= intel_sst/
 obj-$(CONFIG_SPEAKUP)	+= speakup/
 obj-$(CONFIG_TOUCHSCREEN_CLEARPAD_TM1217)	+= cptm1217/
diff --git a/drivers/staging/appletalk/Kconfig b/drivers/staging/appletalk/Kconfig
deleted file mode 100644
index 0b376a990972..000000000000
--- a/drivers/staging/appletalk/Kconfig
+++ /dev/null
@@ -1,126 +0,0 @@
-#
-# Appletalk driver configuration
-#
-config ATALK
-	tristate "Appletalk protocol support"
-	depends on BKL # waiting to be removed from net/appletalk/ddp.c
-	select LLC
-	---help---
-	  AppleTalk is the protocol that Apple computers can use to communicate
-	  on a network.  If your Linux box is connected to such a network and you
-	  wish to connect to it, say Y.  You will need to use the netatalk package
-	  so that your Linux box can act as a print and file server for Macs as
-	  well as access AppleTalk printers.  Check out
-	  <http://www.zettabyte.net/netatalk/> on the WWW for details.
-	  EtherTalk is the name used for AppleTalk over Ethernet and the
-	  cheaper and slower LocalTalk is AppleTalk over a proprietary Apple
-	  network using serial links.  EtherTalk and LocalTalk are fully
-	  supported by Linux.
-
-	  General information about how to connect Linux, Windows machines and
-	  Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>.  The
-	  NET3-4-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>, contains valuable
-	  information as well.
-
-	  To compile this driver as a module, choose M here: the module will be
-	  called appletalk. You almost certainly want to compile it as a
-	  module so you can restart your AppleTalk stack without rebooting
-	  your machine. I hear that the GNU boycott of Apple is over, so
-	  even politically correct people are allowed to say Y here.
-
-config DEV_APPLETALK
-	tristate "Appletalk interfaces support"
-	depends on ATALK
-	help
-	  AppleTalk is the protocol that Apple computers can use to communicate
-	  on a network.  If your Linux box is connected to such a network, and wish
-	  to do IP over it, or you have a LocalTalk card and wish to use it to
-	  connect to the AppleTalk network, say Y.
-	  
-
-config LTPC
-	tristate "Apple/Farallon LocalTalk PC support"
-	depends on DEV_APPLETALK && (ISA || EISA) && ISA_DMA_API
-	help
-	  This allows you to use the AppleTalk PC card to connect to LocalTalk
-	  networks. The card is also known as the Farallon PhoneNet PC card.
-	  If you are in doubt, this card is the one with the 65C02 chip on it.
-	  You also need version 1.3.3 or later of the netatalk package.
-	  This driver is experimental, which means that it may not work.
-	  See the file <file:Documentation/networking/ltpc.txt>.
-
-config COPS
-	tristate "COPS LocalTalk PC support"
-	depends on DEV_APPLETALK && (ISA || EISA)
-	help
-	  This allows you to use COPS AppleTalk cards to connect to LocalTalk
-	  networks. You also need version 1.3.3 or later of the netatalk
-	  package. This driver is experimental, which means that it may not
-	  work. This driver will only work if you choose "AppleTalk DDP"
-	  networking support, above.
-	  Please read the file <file:Documentation/networking/cops.txt>.
-
-config COPS_DAYNA
-	bool "Dayna firmware support"
-	depends on COPS
-	help
-	  Support COPS compatible cards with Dayna style firmware (Dayna
-	  DL2000/ Daynatalk/PC (half length), COPS LT-95, Farallon PhoneNET PC
-	  III, Farallon PhoneNET PC II).
-
-config COPS_TANGENT
-	bool "Tangent firmware support"
-	depends on COPS
-	help
-	  Support COPS compatible cards with Tangent style firmware (Tangent
-	  ATB_II, Novell NL-1000, Daystar Digital LT-200.
-
-config IPDDP
-	tristate "Appletalk-IP driver support"
-	depends on DEV_APPLETALK && ATALK
-	---help---
-	  This allows IP networking for users who only have AppleTalk
-	  networking available. This feature is experimental. With this
-	  driver, you can encapsulate IP inside AppleTalk (e.g. if your Linux
-	  box is stuck on an AppleTalk only network) or decapsulate (e.g. if
-	  you want your Linux box to act as an Internet gateway for a zoo of
-	  AppleTalk connected Macs). Please see the file
-	  <file:Documentation/networking/ipddp.txt> for more information.
-
-	  If you say Y here, the AppleTalk-IP support will be compiled into
-	  the kernel. In this case, you can either use encapsulation or
-	  decapsulation, but not both. With the following two questions, you
-	  decide which one you want.
-
-	  To compile the AppleTalk-IP support as a module, choose M here: the
-	  module will be called ipddp.
-	  In this case, you will be able to use both encapsulation and
-	  decapsulation simultaneously, by loading two copies of the module
-	  and specifying different values for the module option ipddp_mode.
-
-config IPDDP_ENCAP
-	bool "IP to Appletalk-IP Encapsulation support"
-	depends on IPDDP
-	help
-	  If you say Y here, the AppleTalk-IP code will be able to encapsulate
-	  IP packets inside AppleTalk frames; this is useful if your Linux box
-	  is stuck on an AppleTalk network (which hopefully contains a
-	  decapsulator somewhere). Please see
-	  <file:Documentation/networking/ipddp.txt> for more information. If
-	  you said Y to "AppleTalk-IP driver support" above and you say Y
-	  here, then you cannot say Y to "AppleTalk-IP to IP Decapsulation
-	  support", below.
-
-config IPDDP_DECAP
-	bool "Appletalk-IP to IP Decapsulation support"
-	depends on IPDDP
-	help
-	  If you say Y here, the AppleTalk-IP code will be able to decapsulate
-	  AppleTalk-IP frames to IP packets; this is useful if you want your
-	  Linux box to act as an Internet gateway for an AppleTalk network.
-	  Please see <file:Documentation/networking/ipddp.txt> for more
-	  information.  If you said Y to "AppleTalk-IP driver support" above
-	  and you say Y here, then you cannot say Y to "IP to AppleTalk-IP
-	  Encapsulation support", above.
-
diff --git a/drivers/staging/appletalk/Makefile b/drivers/staging/appletalk/Makefile
deleted file mode 100644
index 2a5129a5c6bc..000000000000
--- a/drivers/staging/appletalk/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-#
-# Makefile for drivers/staging/appletalk
-#
-obj-$(CONFIG_ATALK) += appletalk.o
-
-appletalk-y			:= aarp.o ddp.o dev.o
-appletalk-$(CONFIG_PROC_FS)	+= atalk_proc.o
-appletalk-$(CONFIG_SYSCTL)	+= sysctl_net_atalk.o
-
-obj-$(CONFIG_IPDDP) += ipddp.o
-obj-$(CONFIG_COPS) += cops.o
-obj-$(CONFIG_LTPC) += ltpc.o
diff --git a/drivers/staging/appletalk/aarp.c b/drivers/staging/appletalk/aarp.c
deleted file mode 100644
index 7163a1dd501f..000000000000
--- a/drivers/staging/appletalk/aarp.c
+++ /dev/null
@@ -1,1063 +0,0 @@
-/*
- *	AARP:		An implementation of the AppleTalk AARP protocol for
- *			Ethernet 'ELAP'.
- *
- *		Alan Cox  <Alan.Cox@linux.org>
- *
- *	This doesn't fit cleanly with the IP arp. Potentially we can use
- *	the generic neighbour discovery code to clean this up.
- *
- *	FIXME:
- *		We ought to handle the retransmits with a single list and a
- *	separate fast timer for when it is needed.
- *		Use neighbour discovery code.
- *		Token Ring Support.
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
- *
- *	References:
- *		Inside AppleTalk (2nd Ed).
- *	Fixes:
- *		Jaume Grau	-	flush caches on AARP_PROBE
- *		Rob Newberry	-	Added proxy AARP and AARP proc fs,
- *					moved probing from DDP module.
- *		Arnaldo C. Melo -	don't mangle rx packets
- *
- */
-
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/datalink.h>
-#include <net/psnap.h>
-#include "atalk.h"
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-
-int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
-int sysctl_aarp_tick_time = AARP_TICK_TIME;
-int sysctl_aarp_retransmit_limit = AARP_RETRANSMIT_LIMIT;
-int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
-
-/* Lists of aarp entries */
-/**
- *	struct aarp_entry - AARP entry
- *	@last_sent - Last time we xmitted the aarp request
- *	@packet_queue - Queue of frames wait for resolution
- *	@status - Used for proxy AARP
- *	expires_at - Entry expiry time
- *	target_addr - DDP Address
- *	dev - Device to use
- *	hwaddr - Physical i/f address of target/router
- *	xmit_count - When this hits 10 we give up
- *	next - Next entry in chain
- */
-struct aarp_entry {
-	/* These first two are only used for unresolved entries */
-	unsigned long		last_sent;
-	struct sk_buff_head	packet_queue;
-	int			status;
-	unsigned long		expires_at;
-	struct atalk_addr	target_addr;
-	struct net_device	*dev;
-	char			hwaddr[6];
-	unsigned short		xmit_count;
-	struct aarp_entry	*next;
-};
-
-/* Hashed list of resolved, unresolved and proxy entries */
-static struct aarp_entry *resolved[AARP_HASH_SIZE];
-static struct aarp_entry *unresolved[AARP_HASH_SIZE];
-static struct aarp_entry *proxies[AARP_HASH_SIZE];
-static int unresolved_count;
-
-/* One lock protects it all. */
-static DEFINE_RWLOCK(aarp_lock);
-
-/* Used to walk the list and purge/kick entries.  */
-static struct timer_list aarp_timer;
-
-/*
- *	Delete an aarp queue
- *
- *	Must run under aarp_lock.
- */
-static void __aarp_expire(struct aarp_entry *a)
-{
-	skb_queue_purge(&a->packet_queue);
-	kfree(a);
-}
-
-/*
- *	Send an aarp queue entry request
- *
- *	Must run under aarp_lock.
- */
-static void __aarp_send_query(struct aarp_entry *a)
-{
-	static unsigned char aarp_eth_multicast[ETH_ALEN] =
-					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
-	struct net_device *dev = a->dev;
-	struct elapaarp *eah;
-	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
-	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
-	struct atalk_addr *sat = atalk_find_dev_addr(dev);
-
-	if (!skb)
-		return;
-
-	if (!sat) {
-		kfree_skb(skb);
-		return;
-	}
-
-	/* Set up the buffer */
-	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_put(skb, sizeof(*eah));
-	skb->protocol    = htons(ETH_P_ATALK);
-	skb->dev	 = dev;
-	eah		 = aarp_hdr(skb);
-
-	/* Set up the ARP */
-	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
-	eah->pa_type	 = htons(ETH_P_ATALK);
-	eah->hw_len	 = ETH_ALEN;
-	eah->pa_len	 = AARP_PA_ALEN;
-	eah->function	 = htons(AARP_REQUEST);
-
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
-
-	eah->pa_src_zero = 0;
-	eah->pa_src_net	 = sat->s_net;
-	eah->pa_src_node = sat->s_node;
-
-	memset(eah->hw_dst, '\0', ETH_ALEN);
-
-	eah->pa_dst_zero = 0;
-	eah->pa_dst_net	 = a->target_addr.s_net;
-	eah->pa_dst_node = a->target_addr.s_node;
-
-	/* Send it */
-	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
-	/* Update the sending count */
-	a->xmit_count++;
-	a->last_sent = jiffies;
-}
-
-/* This runs under aarp_lock and in softint context, so only atomic memory
- * allocations can be used. */
-static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
-			    struct atalk_addr *them, unsigned char *sha)
-{
-	struct elapaarp *eah;
-	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
-	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
-
-	if (!skb)
-		return;
-
-	/* Set up the buffer */
-	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_put(skb, sizeof(*eah));
-	skb->protocol    = htons(ETH_P_ATALK);
-	skb->dev	 = dev;
-	eah		 = aarp_hdr(skb);
-
-	/* Set up the ARP */
-	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
-	eah->pa_type	 = htons(ETH_P_ATALK);
-	eah->hw_len	 = ETH_ALEN;
-	eah->pa_len	 = AARP_PA_ALEN;
-	eah->function	 = htons(AARP_REPLY);
-
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
-
-	eah->pa_src_zero = 0;
-	eah->pa_src_net	 = us->s_net;
-	eah->pa_src_node = us->s_node;
-
-	if (!sha)
-		memset(eah->hw_dst, '\0', ETH_ALEN);
-	else
-		memcpy(eah->hw_dst, sha, ETH_ALEN);
-
-	eah->pa_dst_zero = 0;
-	eah->pa_dst_net	 = them->s_net;
-	eah->pa_dst_node = them->s_node;
-
-	/* Send it */
-	aarp_dl->request(aarp_dl, skb, sha);
-}
-
-/*
- *	Send probe frames. Called from aarp_probe_network and
- *	aarp_proxy_probe_network.
- */
-
-static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
-{
-	struct elapaarp *eah;
-	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
-	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
-	static unsigned char aarp_eth_multicast[ETH_ALEN] =
-					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
-
-	if (!skb)
-		return;
-
-	/* Set up the buffer */
-	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_put(skb, sizeof(*eah));
-	skb->protocol    = htons(ETH_P_ATALK);
-	skb->dev	 = dev;
-	eah		 = aarp_hdr(skb);
-
-	/* Set up the ARP */
-	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
-	eah->pa_type	 = htons(ETH_P_ATALK);
-	eah->hw_len	 = ETH_ALEN;
-	eah->pa_len	 = AARP_PA_ALEN;
-	eah->function	 = htons(AARP_PROBE);
-
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
-
-	eah->pa_src_zero = 0;
-	eah->pa_src_net	 = us->s_net;
-	eah->pa_src_node = us->s_node;
-
-	memset(eah->hw_dst, '\0', ETH_ALEN);
-
-	eah->pa_dst_zero = 0;
-	eah->pa_dst_net	 = us->s_net;
-	eah->pa_dst_node = us->s_node;
-
-	/* Send it */
-	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
-}
-
-/*
- *	Handle an aarp timer expire
- *
- *	Must run under the aarp_lock.
- */
-
-static void __aarp_expire_timer(struct aarp_entry **n)
-{
-	struct aarp_entry *t;
-
-	while (*n)
-		/* Expired ? */
-		if (time_after(jiffies, (*n)->expires_at)) {
-			t = *n;
-			*n = (*n)->next;
-			__aarp_expire(t);
-		} else
-			n = &((*n)->next);
-}
-
-/*
- *	Kick all pending requests 5 times a second.
- *
- *	Must run under the aarp_lock.
- */
-static void __aarp_kick(struct aarp_entry **n)
-{
-	struct aarp_entry *t;
-
-	while (*n)
-		/* Expired: if this will be the 11th tx, we delete instead. */
-		if ((*n)->xmit_count >= sysctl_aarp_retransmit_limit) {
-			t = *n;
-			*n = (*n)->next;
-			__aarp_expire(t);
-		} else {
-			__aarp_send_query(*n);
-			n = &((*n)->next);
-		}
-}
-
-/*
- *	A device has gone down. Take all entries referring to the device
- *	and remove them.
- *
- *	Must run under the aarp_lock.
- */
-static void __aarp_expire_device(struct aarp_entry **n, struct net_device *dev)
-{
-	struct aarp_entry *t;
-
-	while (*n)
-		if ((*n)->dev == dev) {
-			t = *n;
-			*n = (*n)->next;
-			__aarp_expire(t);
-		} else
-			n = &((*n)->next);
-}
-
-/* Handle the timer event */
-static void aarp_expire_timeout(unsigned long unused)
-{
-	int ct;
-
-	write_lock_bh(&aarp_lock);
-
-	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-		__aarp_expire_timer(&resolved[ct]);
-		__aarp_kick(&unresolved[ct]);
-		__aarp_expire_timer(&unresolved[ct]);
-		__aarp_expire_timer(&proxies[ct]);
-	}
-
-	write_unlock_bh(&aarp_lock);
-	mod_timer(&aarp_timer, jiffies +
-			       (unresolved_count ? sysctl_aarp_tick_time :
-				sysctl_aarp_expiry_time));
-}
-
-/* Network device notifier chain handler. */
-static int aarp_device_event(struct notifier_block *this, unsigned long event,
-			     void *ptr)
-{
-	struct net_device *dev = ptr;
-	int ct;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
-	if (event == NETDEV_DOWN) {
-		write_lock_bh(&aarp_lock);
-
-		for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-			__aarp_expire_device(&resolved[ct], dev);
-			__aarp_expire_device(&unresolved[ct], dev);
-			__aarp_expire_device(&proxies[ct], dev);
-		}
-
-		write_unlock_bh(&aarp_lock);
-	}
-	return NOTIFY_DONE;
-}
-
-/* Expire all entries in a hash chain */
-static void __aarp_expire_all(struct aarp_entry **n)
-{
-	struct aarp_entry *t;
-
-	while (*n) {
-		t = *n;
-		*n = (*n)->next;
-		__aarp_expire(t);
-	}
-}
-
-/* Cleanup all hash chains -- module unloading */
-static void aarp_purge(void)
-{
-	int ct;
-
-	write_lock_bh(&aarp_lock);
-	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-		__aarp_expire_all(&resolved[ct]);
-		__aarp_expire_all(&unresolved[ct]);
-		__aarp_expire_all(&proxies[ct]);
-	}
-	write_unlock_bh(&aarp_lock);
-}
-
-/*
- *	Create a new aarp entry.  This must use GFP_ATOMIC because it
- *	runs while holding spinlocks.
- */
-static struct aarp_entry *aarp_alloc(void)
-{
-	struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC);
-
-	if (a)
-		skb_queue_head_init(&a->packet_queue);
-	return a;
-}
-
-/*
- * Find an entry. We might return an expired but not yet purged entry. We
- * don't care as it will do no harm.
- *
- * This must run under the aarp_lock.
- */
-static struct aarp_entry *__aarp_find_entry(struct aarp_entry *list,
-					    struct net_device *dev,
-					    struct atalk_addr *sat)
-{
-	while (list) {
-		if (list->target_addr.s_net == sat->s_net &&
-		    list->target_addr.s_node == sat->s_node &&
-		    list->dev == dev)
-			break;
-		list = list->next;
-	}
-
-	return list;
-}
-
-/* Called from the DDP code, and thus must be exported. */
-void aarp_proxy_remove(struct net_device *dev, struct atalk_addr *sa)
-{
-	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
-	struct aarp_entry *a;
-
-	write_lock_bh(&aarp_lock);
-
-	a = __aarp_find_entry(proxies[hash], dev, sa);
-	if (a)
-		a->expires_at = jiffies - 1;
-
-	write_unlock_bh(&aarp_lock);
-}
-
-/* This must run under aarp_lock. */
-static struct atalk_addr *__aarp_proxy_find(struct net_device *dev,
-					    struct atalk_addr *sa)
-{
-	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
-	struct aarp_entry *a = __aarp_find_entry(proxies[hash], dev, sa);
-
-	return a ? sa : NULL;
-}
-
-/*
- * Probe a Phase 1 device or a device that requires its Net:Node to
- * be set via an ioctl.
- */
-static void aarp_send_probe_phase1(struct atalk_iface *iface)
-{
-	struct ifreq atreq;
-	struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr;
-	const struct net_device_ops *ops = iface->dev->netdev_ops;
-
-	sa->sat_addr.s_node = iface->address.s_node;
-	sa->sat_addr.s_net = ntohs(iface->address.s_net);
-
-	/* We pass the Net:Node to the drivers/cards by a Device ioctl. */
-	if (!(ops->ndo_do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) {
-		ops->ndo_do_ioctl(iface->dev, &atreq, SIOCGIFADDR);
-		if (iface->address.s_net != htons(sa->sat_addr.s_net) ||
-		    iface->address.s_node != sa->sat_addr.s_node)
-			iface->status |= ATIF_PROBE_FAIL;
-
-		iface->address.s_net  = htons(sa->sat_addr.s_net);
-		iface->address.s_node = sa->sat_addr.s_node;
-	}
-}
-
-
-void aarp_probe_network(struct atalk_iface *atif)
-{
-	if (atif->dev->type == ARPHRD_LOCALTLK ||
-	    atif->dev->type == ARPHRD_PPP)
-		aarp_send_probe_phase1(atif);
-	else {
-		unsigned int count;
-
-		for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
-			aarp_send_probe(atif->dev, &atif->address);
-
-			/* Defer 1/10th */
-			msleep(100);
-
-			if (atif->status & ATIF_PROBE_FAIL)
-				break;
-		}
-	}
-}
-
-int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa)
-{
-	int hash, retval = -EPROTONOSUPPORT;
-	struct aarp_entry *entry;
-	unsigned int count;
-
-	/*
-	 * we don't currently support LocalTalk or PPP for proxy AARP;
-	 * if someone wants to try and add it, have fun
-	 */
-	if (atif->dev->type == ARPHRD_LOCALTLK ||
-	    atif->dev->type == ARPHRD_PPP)
-		goto out;
-
-	/*
-	 * create a new AARP entry with the flags set to be published --
-	 * we need this one to hang around even if it's in use
-	 */
-	entry = aarp_alloc();
-	retval = -ENOMEM;
-	if (!entry)
-		goto out;
-
-	entry->expires_at = -1;
-	entry->status = ATIF_PROBE;
-	entry->target_addr.s_node = sa->s_node;
-	entry->target_addr.s_net = sa->s_net;
-	entry->dev = atif->dev;
-
-	write_lock_bh(&aarp_lock);
-
-	hash = sa->s_node % (AARP_HASH_SIZE - 1);
-	entry->next = proxies[hash];
-	proxies[hash] = entry;
-
-	for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
-		aarp_send_probe(atif->dev, sa);
-
-		/* Defer 1/10th */
-		write_unlock_bh(&aarp_lock);
-		msleep(100);
-		write_lock_bh(&aarp_lock);
-
-		if (entry->status & ATIF_PROBE_FAIL)
-			break;
-	}
-
-	if (entry->status & ATIF_PROBE_FAIL) {
-		entry->expires_at = jiffies - 1; /* free the entry */
-		retval = -EADDRINUSE; /* return network full */
-	} else { /* clear the probing flag */
-		entry->status &= ~ATIF_PROBE;
-		retval = 1;
-	}
-
-	write_unlock_bh(&aarp_lock);
-out:
-	return retval;
-}
-
-/* Send a DDP frame */
-int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
-		  struct atalk_addr *sa, void *hwaddr)
-{
-	static char ddp_eth_multicast[ETH_ALEN] =
-		{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
-	int hash;
-	struct aarp_entry *a;
-
-	skb_reset_network_header(skb);
-
-	/* Check for LocalTalk first */
-	if (dev->type == ARPHRD_LOCALTLK) {
-		struct atalk_addr *at = atalk_find_dev_addr(dev);
-		struct ddpehdr *ddp = (struct ddpehdr *)skb->data;
-		int ft = 2;
-
-		/*
-		 * Compressible ?
-		 *
-		 * IFF: src_net == dest_net == device_net
-		 * (zero matches anything)
-		 */
-
-		if ((!ddp->deh_snet || at->s_net == ddp->deh_snet) &&
-		    (!ddp->deh_dnet || at->s_net == ddp->deh_dnet)) {
-			skb_pull(skb, sizeof(*ddp) - 4);
-
-			/*
-			 *	The upper two remaining bytes are the port
-			 *	numbers	we just happen to need. Now put the
-			 *	length in the lower two.
-			 */
-			*((__be16 *)skb->data) = htons(skb->len);
-			ft = 1;
-		}
-		/*
-		 * Nice and easy. No AARP type protocols occur here so we can
-		 * just shovel it out with a 3 byte LLAP header
-		 */
-
-		skb_push(skb, 3);
-		skb->data[0] = sa->s_node;
-		skb->data[1] = at->s_node;
-		skb->data[2] = ft;
-		skb->dev     = dev;
-		goto sendit;
-	}
-
-	/* On a PPP link we neither compress nor aarp.  */
-	if (dev->type == ARPHRD_PPP) {
-		skb->protocol = htons(ETH_P_PPPTALK);
-		skb->dev = dev;
-		goto sendit;
-	}
-
-	/* Non ELAP we cannot do. */
-	if (dev->type != ARPHRD_ETHER)
-		goto free_it;
-
-	skb->dev = dev;
-	skb->protocol = htons(ETH_P_ATALK);
-	hash = sa->s_node % (AARP_HASH_SIZE - 1);
-
-	/* Do we have a resolved entry? */
-	if (sa->s_node == ATADDR_BCAST) {
-		/* Send it */
-		ddp_dl->request(ddp_dl, skb, ddp_eth_multicast);
-		goto sent;
-	}
-
-	write_lock_bh(&aarp_lock);
-	a = __aarp_find_entry(resolved[hash], dev, sa);
-
-	if (a) { /* Return 1 and fill in the address */
-		a->expires_at = jiffies + (sysctl_aarp_expiry_time * 10);
-		ddp_dl->request(ddp_dl, skb, a->hwaddr);
-		write_unlock_bh(&aarp_lock);
-		goto sent;
-	}
-
-	/* Do we have an unresolved entry: This is the less common path */
-	a = __aarp_find_entry(unresolved[hash], dev, sa);
-	if (a) { /* Queue onto the unresolved queue */
-		skb_queue_tail(&a->packet_queue, skb);
-		goto out_unlock;
-	}
-
-	/* Allocate a new entry */
-	a = aarp_alloc();
-	if (!a) {
-		/* Whoops slipped... good job it's an unreliable protocol 8) */
-		write_unlock_bh(&aarp_lock);
-		goto free_it;
-	}
-
-	/* Set up the queue */
-	skb_queue_tail(&a->packet_queue, skb);
-	a->expires_at	 = jiffies + sysctl_aarp_resolve_time;
-	a->dev		 = dev;
-	a->next		 = unresolved[hash];
-	a->target_addr	 = *sa;
-	a->xmit_count	 = 0;
-	unresolved[hash] = a;
-	unresolved_count++;
-
-	/* Send an initial request for the address */
-	__aarp_send_query(a);
-
-	/*
-	 * Switch to fast timer if needed (That is if this is the first
-	 * unresolved entry to get added)
-	 */
-
-	if (unresolved_count == 1)
-		mod_timer(&aarp_timer, jiffies + sysctl_aarp_tick_time);
-
-	/* Now finally, it is safe to drop the lock. */
-out_unlock:
-	write_unlock_bh(&aarp_lock);
-
-	/* Tell the ddp layer we have taken over for this frame. */
-	goto sent;
-
-sendit:
-	if (skb->sk)
-		skb->priority = skb->sk->sk_priority;
-	if (dev_queue_xmit(skb))
-		goto drop;
-sent:
-	return NET_XMIT_SUCCESS;
-free_it:
-	kfree_skb(skb);
-drop:
-	return NET_XMIT_DROP;
-}
-EXPORT_SYMBOL(aarp_send_ddp);
-
-/*
- *	An entry in the aarp unresolved queue has become resolved. Send
- *	all the frames queued under it.
- *
- *	Must run under aarp_lock.
- */
-static void __aarp_resolved(struct aarp_entry **list, struct aarp_entry *a,
-			    int hash)
-{
-	struct sk_buff *skb;
-
-	while (*list)
-		if (*list == a) {
-			unresolved_count--;
-			*list = a->next;
-
-			/* Move into the resolved list */
-			a->next = resolved[hash];
-			resolved[hash] = a;
-
-			/* Kick frames off */
-			while ((skb = skb_dequeue(&a->packet_queue)) != NULL) {
-				a->expires_at = jiffies +
-						sysctl_aarp_expiry_time * 10;
-				ddp_dl->request(ddp_dl, skb, a->hwaddr);
-			}
-		} else
-			list = &((*list)->next);
-}
-
-/*
- *	This is called by the SNAP driver whenever we see an AARP SNAP
- *	frame. We currently only support Ethernet.
- */
-static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
-		    struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct elapaarp *ea = aarp_hdr(skb);
-	int hash, ret = 0;
-	__u16 function;
-	struct aarp_entry *a;
-	struct atalk_addr sa, *ma, da;
-	struct atalk_iface *ifa;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		goto out0;
-
-	/* We only do Ethernet SNAP AARP. */
-	if (dev->type != ARPHRD_ETHER)
-		goto out0;
-
-	/* Frame size ok? */
-	if (!skb_pull(skb, sizeof(*ea)))
-		goto out0;
-
-	function = ntohs(ea->function);
-
-	/* Sanity check fields. */
-	if (function < AARP_REQUEST || function > AARP_PROBE ||
-	    ea->hw_len != ETH_ALEN || ea->pa_len != AARP_PA_ALEN ||
-	    ea->pa_src_zero || ea->pa_dst_zero)
-		goto out0;
-
-	/* Looks good. */
-	hash = ea->pa_src_node % (AARP_HASH_SIZE - 1);
-
-	/* Build an address. */
-	sa.s_node = ea->pa_src_node;
-	sa.s_net = ea->pa_src_net;
-
-	/* Process the packet. Check for replies of me. */
-	ifa = atalk_find_dev(dev);
-	if (!ifa)
-		goto out1;
-
-	if (ifa->status & ATIF_PROBE &&
-	    ifa->address.s_node == ea->pa_dst_node &&
-	    ifa->address.s_net == ea->pa_dst_net) {
-		ifa->status |= ATIF_PROBE_FAIL; /* Fail the probe (in use) */
-		goto out1;
-	}
-
-	/* Check for replies of proxy AARP entries */
-	da.s_node = ea->pa_dst_node;
-	da.s_net  = ea->pa_dst_net;
-
-	write_lock_bh(&aarp_lock);
-	a = __aarp_find_entry(proxies[hash], dev, &da);
-
-	if (a && a->status & ATIF_PROBE) {
-		a->status |= ATIF_PROBE_FAIL;
-		/*
-		 * we do not respond to probe or request packets for
-		 * this address while we are probing this address
-		 */
-		goto unlock;
-	}
-
-	switch (function) {
-		case AARP_REPLY:
-			if (!unresolved_count)	/* Speed up */
-				break;
-
-			/* Find the entry.  */
-			a = __aarp_find_entry(unresolved[hash], dev, &sa);
-			if (!a || dev != a->dev)
-				break;
-
-			/* We can fill one in - this is good. */
-			memcpy(a->hwaddr, ea->hw_src, ETH_ALEN);
-			__aarp_resolved(&unresolved[hash], a, hash);
-			if (!unresolved_count)
-				mod_timer(&aarp_timer,
-					  jiffies + sysctl_aarp_expiry_time);
-			break;
-
-		case AARP_REQUEST:
-		case AARP_PROBE:
-
-			/*
-			 * If it is my address set ma to my address and reply.
-			 * We can treat probe and request the same.  Probe
-			 * simply means we shouldn't cache the querying host,
-			 * as in a probe they are proposing an address not
-			 * using one.
-			 *
-			 * Support for proxy-AARP added. We check if the
-			 * address is one of our proxies before we toss the
-			 * packet out.
-			 */
-
-			sa.s_node = ea->pa_dst_node;
-			sa.s_net  = ea->pa_dst_net;
-
-			/* See if we have a matching proxy. */
-			ma = __aarp_proxy_find(dev, &sa);
-			if (!ma)
-				ma = &ifa->address;
-			else { /* We need to make a copy of the entry. */
-				da.s_node = sa.s_node;
-				da.s_net = sa.s_net;
-				ma = &da;
-			}
-
-			if (function == AARP_PROBE) {
-				/*
-				 * A probe implies someone trying to get an
-				 * address. So as a precaution flush any
-				 * entries we have for this address.
-				 */
-				a = __aarp_find_entry(resolved[sa.s_node %
-							  (AARP_HASH_SIZE - 1)],
-						      skb->dev, &sa);
-
-				/*
-				 * Make it expire next tick - that avoids us
-				 * getting into a probe/flush/learn/probe/
-				 * flush/learn cycle during probing of a slow
-				 * to respond host addr.
-				 */
-				if (a) {
-					a->expires_at = jiffies - 1;
-					mod_timer(&aarp_timer, jiffies +
-							sysctl_aarp_tick_time);
-				}
-			}
-
-			if (sa.s_node != ma->s_node)
-				break;
-
-			if (sa.s_net && ma->s_net && sa.s_net != ma->s_net)
-				break;
-
-			sa.s_node = ea->pa_src_node;
-			sa.s_net = ea->pa_src_net;
-
-			/* aarp_my_address has found the address to use for us.
-			*/
-			aarp_send_reply(dev, ma, &sa, ea->hw_src);
-			break;
-	}
-
-unlock:
-	write_unlock_bh(&aarp_lock);
-out1:
-	ret = 1;
-out0:
-	kfree_skb(skb);
-	return ret;
-}
-
-static struct notifier_block aarp_notifier = {
-	.notifier_call = aarp_device_event,
-};
-
-static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 };
-
-void __init aarp_proto_init(void)
-{
-	aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv);
-	if (!aarp_dl)
-		printk(KERN_CRIT "Unable to register AARP with SNAP.\n");
-	setup_timer(&aarp_timer, aarp_expire_timeout, 0);
-	aarp_timer.expires  = jiffies + sysctl_aarp_expiry_time;
-	add_timer(&aarp_timer);
-	register_netdevice_notifier(&aarp_notifier);
-}
-
-/* Remove the AARP entries associated with a device. */
-void aarp_device_down(struct net_device *dev)
-{
-	int ct;
-
-	write_lock_bh(&aarp_lock);
-
-	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
-		__aarp_expire_device(&resolved[ct], dev);
-		__aarp_expire_device(&unresolved[ct], dev);
-		__aarp_expire_device(&proxies[ct], dev);
-	}
-
-	write_unlock_bh(&aarp_lock);
-}
-
-#ifdef CONFIG_PROC_FS
-struct aarp_iter_state {
-	int bucket;
-	struct aarp_entry **table;
-};
-
-/*
- * Get the aarp entry that is in the chain described
- * by the iterator.
- * If pos is set then skip till that index.
- * pos = 1 is the first entry
- */
-static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
-{
-	int ct = iter->bucket;
-	struct aarp_entry **table = iter->table;
-	loff_t off = 0;
-	struct aarp_entry *entry;
-
- rescan:
-	while(ct < AARP_HASH_SIZE) {
-		for (entry = table[ct]; entry; entry = entry->next) {
-			if (!pos || ++off == *pos) {
-				iter->table = table;
-				iter->bucket = ct;
-				return entry;
-			}
-		}
-		++ct;
-	}
-
-	if (table == resolved) {
-		ct = 0;
-		table = unresolved;
-		goto rescan;
-	}
-	if (table == unresolved) {
-		ct = 0;
-		table = proxies;
-		goto rescan;
-	}
-	return NULL;
-}
-
-static void *aarp_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(aarp_lock)
-{
-	struct aarp_iter_state *iter = seq->private;
-
-	read_lock_bh(&aarp_lock);
-	iter->table     = resolved;
-	iter->bucket    = 0;
-
-	return *pos ? iter_next(iter, pos) : SEQ_START_TOKEN;
-}
-
-static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct aarp_entry *entry = v;
-	struct aarp_iter_state *iter = seq->private;
-
-	++*pos;
-
-	/* first line after header */
-	if (v == SEQ_START_TOKEN)
-		entry = iter_next(iter, NULL);
-
-	/* next entry in current bucket */
-	else if (entry->next)
-		entry = entry->next;
-
-	/* next bucket or table */
-	else {
-		++iter->bucket;
-		entry = iter_next(iter, NULL);
-	}
-	return entry;
-}
-
-static void aarp_seq_stop(struct seq_file *seq, void *v)
-	__releases(aarp_lock)
-{
-	read_unlock_bh(&aarp_lock);
-}
-
-static const char *dt2str(unsigned long ticks)
-{
-	static char buf[32];
-
-	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
-
-	return buf;
-}
-
-static int aarp_seq_show(struct seq_file *seq, void *v)
-{
-	struct aarp_iter_state *iter = seq->private;
-	struct aarp_entry *entry = v;
-	unsigned long now = jiffies;
-
-	if (v == SEQ_START_TOKEN)
-		seq_puts(seq,
-			 "Address  Interface   Hardware Address"
-			 "   Expires LastSend  Retry Status\n");
-	else {
-		seq_printf(seq, "%04X:%02X  %-12s",
-			   ntohs(entry->target_addr.s_net),
-			   (unsigned int) entry->target_addr.s_node,
-			   entry->dev ? entry->dev->name : "????");
-		seq_printf(seq, "%pM", entry->hwaddr);
-		seq_printf(seq, " %8s",
-			   dt2str((long)entry->expires_at - (long)now));
-		if (iter->table == unresolved)
-			seq_printf(seq, " %8s %6hu",
-				   dt2str(now - entry->last_sent),
-				   entry->xmit_count);
-		else
-			seq_puts(seq, "                ");
-		seq_printf(seq, " %s\n",
-			   (iter->table == resolved) ? "resolved"
-			   : (iter->table == unresolved) ? "unresolved"
-			   : (iter->table == proxies) ? "proxies"
-			   : "unknown");
-	}
-	return 0;
-}
-
-static const struct seq_operations aarp_seq_ops = {
-	.start  = aarp_seq_start,
-	.next   = aarp_seq_next,
-	.stop   = aarp_seq_stop,
-	.show   = aarp_seq_show,
-};
-
-static int aarp_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open_private(file, &aarp_seq_ops,
-			sizeof(struct aarp_iter_state));
-}
-
-const struct file_operations atalk_seq_arp_fops = {
-	.owner		= THIS_MODULE,
-	.open           = aarp_seq_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release	= seq_release_private,
-};
-#endif
-
-/* General module cleanup. Called from cleanup_module() in ddp.c. */
-void aarp_cleanup_module(void)
-{
-	del_timer_sync(&aarp_timer);
-	unregister_netdevice_notifier(&aarp_notifier);
-	unregister_snap_client(aarp_dl);
-	aarp_purge();
-}
diff --git a/drivers/staging/appletalk/atalk.h b/drivers/staging/appletalk/atalk.h
deleted file mode 100644
index d34c187432ed..000000000000
--- a/drivers/staging/appletalk/atalk.h
+++ /dev/null
@@ -1,208 +0,0 @@
-#ifndef __LINUX_ATALK_H__
-#define __LINUX_ATALK_H__
-
-#include <linux/types.h>
-#include <asm/byteorder.h>
-
-/*
- * AppleTalk networking structures
- *
- * The following are directly referenced from the University Of Michigan
- * netatalk for compatibility reasons.
- */
-#define ATPORT_FIRST	1
-#define ATPORT_RESERVED	128
-#define ATPORT_LAST	254		/* 254 is only legal on localtalk */ 
-#define ATADDR_ANYNET	(__u16)0
-#define ATADDR_ANYNODE	(__u8)0
-#define ATADDR_ANYPORT  (__u8)0
-#define ATADDR_BCAST	(__u8)255
-#define DDP_MAXSZ	587
-#define DDP_MAXHOPS     15		/* 4 bits of hop counter */
-
-#define SIOCATALKDIFADDR       (SIOCPROTOPRIVATE + 0)
-
-struct atalk_addr {
-	__be16	s_net;
-	__u8	s_node;
-};
-
-struct sockaddr_at {
-	sa_family_t	  sat_family;
-	__u8		  sat_port;
-	struct atalk_addr sat_addr;
-	char		  sat_zero[8];
-};
-
-struct atalk_netrange {
-	__u8	nr_phase;
-	__be16	nr_firstnet;
-	__be16	nr_lastnet;
-};
-
-#ifdef __KERNEL__
-
-#include <net/sock.h>
-
-struct atalk_route {
-	struct net_device  *dev;
-	struct atalk_addr  target;
-	struct atalk_addr  gateway;
-	int		   flags;
-	struct atalk_route *next;
-};
-
-/**
- *	struct atalk_iface - AppleTalk Interface
- *	@dev - Network device associated with this interface
- *	@address - Our address
- *	@status - What are we doing?
- *	@nets - Associated direct netrange
- *	@next - next element in the list of interfaces
- */
-struct atalk_iface {
-	struct net_device	*dev;
-	struct atalk_addr	address;
-	int			status;
-#define ATIF_PROBE	1		/* Probing for an address */
-#define ATIF_PROBE_FAIL	2		/* Probe collided */
-	struct atalk_netrange	nets;
-	struct atalk_iface	*next;
-};
-	
-struct atalk_sock {
-	/* struct sock has to be the first member of atalk_sock */
-	struct sock	sk;
-	__be16		dest_net;
-	__be16		src_net;
-	unsigned char	dest_node;
-	unsigned char	src_node;
-	unsigned char	dest_port;
-	unsigned char	src_port;
-};
-
-static inline struct atalk_sock *at_sk(struct sock *sk)
-{
-	return (struct atalk_sock *)sk;
-}
-
-struct ddpehdr {
-	__be16	deh_len_hops;	/* lower 10 bits are length, next 4 - hops */
-	__be16	deh_sum;
-	__be16	deh_dnet;
-	__be16	deh_snet;
-	__u8	deh_dnode;
-	__u8	deh_snode;
-	__u8	deh_dport;
-	__u8	deh_sport;
-	/* And netatalk apps expect to stick the type in themselves */
-};
-
-static __inline__ struct ddpehdr *ddp_hdr(struct sk_buff *skb)
-{
-	return (struct ddpehdr *)skb_transport_header(skb);
-}
-
-/* AppleTalk AARP headers */
-struct elapaarp {
-	__be16	hw_type;
-#define AARP_HW_TYPE_ETHERNET		1
-#define AARP_HW_TYPE_TOKENRING		2
-	__be16	pa_type;
-	__u8	hw_len;
-	__u8	pa_len;
-#define AARP_PA_ALEN			4
-	__be16	function;
-#define AARP_REQUEST			1
-#define AARP_REPLY			2
-#define AARP_PROBE			3
-	__u8	hw_src[ETH_ALEN];
-	__u8	pa_src_zero;
-	__be16	pa_src_net;
-	__u8	pa_src_node;
-	__u8	hw_dst[ETH_ALEN];
-	__u8	pa_dst_zero;
-	__be16	pa_dst_net;
-	__u8	pa_dst_node;
-} __attribute__ ((packed));
-
-static __inline__ struct elapaarp *aarp_hdr(struct sk_buff *skb)
-{
-	return (struct elapaarp *)skb_transport_header(skb);
-}
-
-/* Not specified - how long till we drop a resolved entry */
-#define AARP_EXPIRY_TIME	(5 * 60 * HZ)
-/* Size of hash table */
-#define AARP_HASH_SIZE		16
-/* Fast retransmission timer when resolving */
-#define AARP_TICK_TIME		(HZ / 5)
-/* Send 10 requests then give up (2 seconds) */
-#define AARP_RETRANSMIT_LIMIT	10
-/*
- * Some value bigger than total retransmit time + a bit for last reply to
- * appear and to stop continual requests
- */
-#define AARP_RESOLVE_TIME	(10 * HZ)
-
-extern struct datalink_proto *ddp_dl, *aarp_dl;
-extern void aarp_proto_init(void);
-
-/* Inter module exports */
-
-/* Give a device find its atif control structure */
-static inline struct atalk_iface *atalk_find_dev(struct net_device *dev)
-{
-	return dev->atalk_ptr;
-}
-
-extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev);
-extern struct net_device *atrtr_get_dev(struct atalk_addr *sa);
-extern int		 aarp_send_ddp(struct net_device *dev,
-				       struct sk_buff *skb,
-				       struct atalk_addr *sa, void *hwaddr);
-extern void		 aarp_device_down(struct net_device *dev);
-extern void		 aarp_probe_network(struct atalk_iface *atif);
-extern int 		 aarp_proxy_probe_network(struct atalk_iface *atif,
-				     struct atalk_addr *sa);
-extern void		 aarp_proxy_remove(struct net_device *dev,
-					   struct atalk_addr *sa);
-
-extern void		aarp_cleanup_module(void);
-
-extern struct hlist_head atalk_sockets;
-extern rwlock_t atalk_sockets_lock;
-
-extern struct atalk_route *atalk_routes;
-extern rwlock_t atalk_routes_lock;
-
-extern struct atalk_iface *atalk_interfaces;
-extern rwlock_t atalk_interfaces_lock;
-
-extern struct atalk_route atrtr_default;
-
-extern const struct file_operations atalk_seq_arp_fops;
-
-extern int sysctl_aarp_expiry_time;
-extern int sysctl_aarp_tick_time;
-extern int sysctl_aarp_retransmit_limit;
-extern int sysctl_aarp_resolve_time;
-
-#ifdef CONFIG_SYSCTL
-extern void atalk_register_sysctl(void);
-extern void atalk_unregister_sysctl(void);
-#else
-#define atalk_register_sysctl()		do { } while(0)
-#define atalk_unregister_sysctl()	do { } while(0)
-#endif
-
-#ifdef CONFIG_PROC_FS
-extern int atalk_proc_init(void);
-extern void atalk_proc_exit(void);
-#else
-#define atalk_proc_init()	({ 0; })
-#define atalk_proc_exit()	do { } while(0)
-#endif /* CONFIG_PROC_FS */
-
-#endif /* __KERNEL__ */
-#endif /* __LINUX_ATALK_H__ */
diff --git a/drivers/staging/appletalk/atalk_proc.c b/drivers/staging/appletalk/atalk_proc.c
deleted file mode 100644
index d012ba2e67d1..000000000000
--- a/drivers/staging/appletalk/atalk_proc.c
+++ /dev/null
@@ -1,301 +0,0 @@
-/*
- * 	atalk_proc.c - proc support for Appletalk
- *
- * 	Copyright(c) Arnaldo Carvalho de Melo <acme@conectiva.com.br>
- *
- *	This program is free software; you can redistribute it and/or modify it
- *	under the terms of the GNU General Public License as published by the
- *	Free Software Foundation, version 2.
- */
-
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <net/net_namespace.h>
-#include <net/sock.h>
-#include "atalk.h"
-
-
-static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos)
-{
-	struct atalk_iface *i;
-
-	for (i = atalk_interfaces; pos && i; i = i->next)
-		--pos;
-
-	return i;
-}
-
-static void *atalk_seq_interface_start(struct seq_file *seq, loff_t *pos)
-	__acquires(atalk_interfaces_lock)
-{
-	loff_t l = *pos;
-
-	read_lock_bh(&atalk_interfaces_lock);
-	return l ? atalk_get_interface_idx(--l) : SEQ_START_TOKEN;
-}
-
-static void *atalk_seq_interface_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct atalk_iface *i;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN) {
-		i = NULL;
-		if (atalk_interfaces)
-			i = atalk_interfaces;
-		goto out;
-	}
-	i = v;
-	i = i->next;
-out:
-	return i;
-}
-
-static void atalk_seq_interface_stop(struct seq_file *seq, void *v)
-	__releases(atalk_interfaces_lock)
-{
-	read_unlock_bh(&atalk_interfaces_lock);
-}
-
-static int atalk_seq_interface_show(struct seq_file *seq, void *v)
-{
-	struct atalk_iface *iface;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_puts(seq, "Interface        Address   Networks  "
-			      "Status\n");
-		goto out;
-	}
-
-	iface = v;
-	seq_printf(seq, "%-16s %04X:%02X  %04X-%04X  %d\n",
-		   iface->dev->name, ntohs(iface->address.s_net),
-		   iface->address.s_node, ntohs(iface->nets.nr_firstnet),
-		   ntohs(iface->nets.nr_lastnet), iface->status);
-out:
-	return 0;
-}
-
-static __inline__ struct atalk_route *atalk_get_route_idx(loff_t pos)
-{
-	struct atalk_route *r;
-
-	for (r = atalk_routes; pos && r; r = r->next)
-		--pos;
-
-	return r;
-}
-
-static void *atalk_seq_route_start(struct seq_file *seq, loff_t *pos)
-	__acquires(atalk_routes_lock)
-{
-	loff_t l = *pos;
-
-	read_lock_bh(&atalk_routes_lock);
-	return l ? atalk_get_route_idx(--l) : SEQ_START_TOKEN;
-}
-
-static void *atalk_seq_route_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct atalk_route *r;
-
-	++*pos;
-	if (v == SEQ_START_TOKEN) {
-		r = NULL;
-		if (atalk_routes)
-			r = atalk_routes;
-		goto out;
-	}
-	r = v;
-	r = r->next;
-out:
-	return r;
-}
-
-static void atalk_seq_route_stop(struct seq_file *seq, void *v)
-	__releases(atalk_routes_lock)
-{
-	read_unlock_bh(&atalk_routes_lock);
-}
-
-static int atalk_seq_route_show(struct seq_file *seq, void *v)
-{
-	struct atalk_route *rt;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_puts(seq, "Target        Router  Flags Dev\n");
-		goto out;
-	}
-
-	if (atrtr_default.dev) {
-		rt = &atrtr_default;
-		seq_printf(seq, "Default     %04X:%02X  %-4d  %s\n",
-			       ntohs(rt->gateway.s_net), rt->gateway.s_node,
-			       rt->flags, rt->dev->name);
-	}
-
-	rt = v;
-	seq_printf(seq, "%04X:%02X     %04X:%02X  %-4d  %s\n",
-		   ntohs(rt->target.s_net), rt->target.s_node,
-		   ntohs(rt->gateway.s_net), rt->gateway.s_node,
-		   rt->flags, rt->dev->name);
-out:
-	return 0;
-}
-
-static void *atalk_seq_socket_start(struct seq_file *seq, loff_t *pos)
-	__acquires(atalk_sockets_lock)
-{
-	read_lock_bh(&atalk_sockets_lock);
-	return seq_hlist_start_head(&atalk_sockets, *pos);
-}
-
-static void *atalk_seq_socket_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return seq_hlist_next(v, &atalk_sockets, pos);
-}
-
-static void atalk_seq_socket_stop(struct seq_file *seq, void *v)
-	__releases(atalk_sockets_lock)
-{
-	read_unlock_bh(&atalk_sockets_lock);
-}
-
-static int atalk_seq_socket_show(struct seq_file *seq, void *v)
-{
-	struct sock *s;
-	struct atalk_sock *at;
-
-	if (v == SEQ_START_TOKEN) {
-		seq_printf(seq, "Type Local_addr  Remote_addr Tx_queue "
-				"Rx_queue St UID\n");
-		goto out;
-	}
-
-	s = sk_entry(v);
-	at = at_sk(s);
-
-	seq_printf(seq, "%02X   %04X:%02X:%02X  %04X:%02X:%02X  %08X:%08X "
-			"%02X %d\n",
-		   s->sk_type, ntohs(at->src_net), at->src_node, at->src_port,
-		   ntohs(at->dest_net), at->dest_node, at->dest_port,
-		   sk_wmem_alloc_get(s),
-		   sk_rmem_alloc_get(s),
-		   s->sk_state, SOCK_INODE(s->sk_socket)->i_uid);
-out:
-	return 0;
-}
-
-static const struct seq_operations atalk_seq_interface_ops = {
-	.start  = atalk_seq_interface_start,
-	.next   = atalk_seq_interface_next,
-	.stop   = atalk_seq_interface_stop,
-	.show   = atalk_seq_interface_show,
-};
-
-static const struct seq_operations atalk_seq_route_ops = {
-	.start  = atalk_seq_route_start,
-	.next   = atalk_seq_route_next,
-	.stop   = atalk_seq_route_stop,
-	.show   = atalk_seq_route_show,
-};
-
-static const struct seq_operations atalk_seq_socket_ops = {
-	.start  = atalk_seq_socket_start,
-	.next   = atalk_seq_socket_next,
-	.stop   = atalk_seq_socket_stop,
-	.show   = atalk_seq_socket_show,
-};
-
-static int atalk_seq_interface_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_interface_ops);
-}
-
-static int atalk_seq_route_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_route_ops);
-}
-
-static int atalk_seq_socket_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &atalk_seq_socket_ops);
-}
-
-static const struct file_operations atalk_seq_interface_fops = {
-	.owner		= THIS_MODULE,
-	.open		= atalk_seq_interface_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations atalk_seq_route_fops = {
-	.owner		= THIS_MODULE,
-	.open		= atalk_seq_route_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static const struct file_operations atalk_seq_socket_fops = {
-	.owner		= THIS_MODULE,
-	.open		= atalk_seq_socket_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static struct proc_dir_entry *atalk_proc_dir;
-
-int __init atalk_proc_init(void)
-{
-	struct proc_dir_entry *p;
-	int rc = -ENOMEM;
-
-	atalk_proc_dir = proc_mkdir("atalk", init_net.proc_net);
-	if (!atalk_proc_dir)
-		goto out;
-
-	p = proc_create("interface", S_IRUGO, atalk_proc_dir,
-			&atalk_seq_interface_fops);
-	if (!p)
-		goto out_interface;
-
-	p = proc_create("route", S_IRUGO, atalk_proc_dir,
-			&atalk_seq_route_fops);
-	if (!p)
-		goto out_route;
-
-	p = proc_create("socket", S_IRUGO, atalk_proc_dir,
-			&atalk_seq_socket_fops);
-	if (!p)
-		goto out_socket;
-
-	p = proc_create("arp", S_IRUGO, atalk_proc_dir, &atalk_seq_arp_fops);
-	if (!p)
-		goto out_arp;
-
-	rc = 0;
-out:
-	return rc;
-out_arp:
-	remove_proc_entry("socket", atalk_proc_dir);
-out_socket:
-	remove_proc_entry("route", atalk_proc_dir);
-out_route:
-	remove_proc_entry("interface", atalk_proc_dir);
-out_interface:
-	remove_proc_entry("atalk", init_net.proc_net);
-	goto out;
-}
-
-void __exit atalk_proc_exit(void)
-{
-	remove_proc_entry("interface", atalk_proc_dir);
-	remove_proc_entry("route", atalk_proc_dir);
-	remove_proc_entry("socket", atalk_proc_dir);
-	remove_proc_entry("arp", atalk_proc_dir);
-	remove_proc_entry("atalk", init_net.proc_net);
-}
diff --git a/drivers/staging/appletalk/cops.c b/drivers/staging/appletalk/cops.c
deleted file mode 100644
index 661d42eff7d8..000000000000
--- a/drivers/staging/appletalk/cops.c
+++ /dev/null
@@ -1,1013 +0,0 @@
-/*      cops.c: LocalTalk driver for Linux.
- *
- *	Authors:
- *      - Jay Schulist <jschlst@samba.org>
- *
- *	With more than a little help from;
- *	- Alan Cox <alan@lxorguk.ukuu.org.uk>
- *
- *      Derived from:
- *      - skeleton.c: A network driver outline for linux.
- *        Written 1993-94 by Donald Becker.
- *	- ltpc.c: A driver for the LocalTalk PC card.
- *	  Written by Bradford W. Johnson.
- *
- *      Copyright 1993 United States Government as represented by the
- *      Director, National Security Agency.
- *
- *      This software may be used and distributed according to the terms
- *      of the GNU General Public License, incorporated herein by reference.
- *
- *	Changes:
- *	19970608	Alan Cox	Allowed dual card type support
- *					Can set board type in insmod
- *					Hooks for cops_setup routine
- *					(not yet implemented).
- *	19971101	Jay Schulist	Fixes for multiple lt* devices.
- *	19980607	Steven Hirsch	Fixed the badly broken support
- *					for Tangent type cards. Only
- *                                      tested on Daystar LT200. Some
- *                                      cleanup of formatting and program
- *                                      logic.  Added emacs 'local-vars'
- *                                      setup for Jay's brace style.
- *	20000211	Alan Cox	Cleaned up for softnet
- */
-
-static const char *version =
-"cops.c:v0.04 6/7/98 Jay Schulist <jschlst@samba.org>\n";
-/*
- *  Sources:
- *      COPS Localtalk SDK. This provides almost all of the information
- *      needed.
- */
-
-/*
- * insmod/modprobe configurable stuff.
- *	- IO Port, choose one your card supports or 0 if you dare.
- *	- IRQ, also choose one your card supports or nothing and let
- *	  the driver figure it out.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/in.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_ltalk.h>
-#include <linux/delay.h>	/* For udelay() */
-#include <linux/spinlock.h>
-#include <linux/bitops.h>
-#include <linux/jiffies.h>
-
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/dma.h>
-
-#include "atalk.h"
-#include "cops.h"		/* Our Stuff */
-#include "cops_ltdrv.h"		/* Firmware code for Tangent type cards. */
-#include "cops_ffdrv.h"		/* Firmware code for Dayna type cards. */
-
-/*
- *      The name of the card. Is used for messages and in the requests for
- *      io regions, irqs and dma channels
- */
-
-static const char *cardname = "cops";
-
-#ifdef CONFIG_COPS_DAYNA
-static int board_type = DAYNA;	/* Module exported */
-#else
-static int board_type = TANGENT;
-#endif
-
-static int io = 0x240;		/* Default IO for Dayna */
-static int irq = 5;		/* Default IRQ */
-
-/*
- *	COPS Autoprobe information.
- *	Right now if port address is right but IRQ is not 5 this will
- *      return a 5 no matter what since we will still get a status response.
- *      Need one more additional check to narrow down after we have gotten
- *      the ioaddr. But since only other possible IRQs is 3 and 4 so no real
- *	hurry on this. I *STRONGLY* recommend using IRQ 5 for your card with
- *	this driver.
- * 
- *	This driver has 2 modes and they are: Dayna mode and Tangent mode.
- *	Each mode corresponds with the type of card. It has been found
- *	that there are 2 main types of cards and all other cards are
- *	the same and just have different names or only have minor differences
- *	such as more IO ports. As this driver is tested it will
- *	become more clear on exactly what cards are supported. The driver
- *	defaults to using Dayna mode. To change the drivers mode, simply
- *	select Dayna or Tangent mode when configuring the kernel.
- *
- *      This driver should support:
- *      TANGENT driver mode:
- *              Tangent ATB-II, Novell NL-1000, Daystar Digital LT-200,
- *		COPS LT-1
- *      DAYNA driver mode:
- *              Dayna DL2000/DaynaTalk PC (Half Length), COPS LT-95, 
- *		Farallon PhoneNET PC III, Farallon PhoneNET PC II
- *	Other cards possibly supported mode unknown though:
- *		Dayna DL2000 (Full length), COPS LT/M (Micro-Channel)
- *
- *	Cards NOT supported by this driver but supported by the ltpc.c
- *	driver written by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *		Farallon PhoneNET PC
- *		Original Apple LocalTalk PC card
- * 
- *      N.B.
- *
- *      The Daystar Digital LT200 boards do not support interrupt-driven
- *      IO.  You must specify 'irq=0xff' as a module parameter to invoke
- *      polled mode.  I also believe that the port probing logic is quite
- *      dangerous at best and certainly hopeless for a polled card.  Best to 
- *      specify both. - Steve H.
- *
- */
-
-/*
- * Zero terminated list of IO ports to probe.
- */
-
-static unsigned int ports[] = { 
-	0x240, 0x340, 0x200, 0x210, 0x220, 0x230, 0x260, 
-	0x2A0, 0x300, 0x310, 0x320, 0x330, 0x350, 0x360,
-	0
-};
-
-/*
- * Zero terminated list of IRQ ports to probe.
- */
-
-static int cops_irqlist[] = {
-	5, 4, 3, 0 
-};
-
-static struct timer_list cops_timer;
-
-/* use 0 for production, 1 for verification, 2 for debug, 3 for verbose debug */
-#ifndef COPS_DEBUG
-#define COPS_DEBUG 1 
-#endif
-static unsigned int cops_debug = COPS_DEBUG;
-
-/* The number of low I/O ports used by the card. */
-#define COPS_IO_EXTENT       8
-
-/* Information that needs to be kept for each board. */
-
-struct cops_local
-{
-        int board;			/* Holds what board type is. */
-	int nodeid;			/* Set to 1 once have nodeid. */
-        unsigned char node_acquire;	/* Node ID when acquired. */
-        struct atalk_addr node_addr;	/* Full node address */
-	spinlock_t lock;		/* RX/TX lock */
-};
-
-/* Index to functions, as function prototypes. */
-static int  cops_probe1 (struct net_device *dev, int ioaddr);
-static int  cops_irq (int ioaddr, int board);
-
-static int  cops_open (struct net_device *dev);
-static int  cops_jumpstart (struct net_device *dev);
-static void cops_reset (struct net_device *dev, int sleep);
-static void cops_load (struct net_device *dev);
-static int  cops_nodeid (struct net_device *dev, int nodeid);
-
-static irqreturn_t cops_interrupt (int irq, void *dev_id);
-static void cops_poll (unsigned long ltdev);
-static void cops_timeout(struct net_device *dev);
-static void cops_rx (struct net_device *dev);
-static netdev_tx_t  cops_send_packet (struct sk_buff *skb,
-					    struct net_device *dev);
-static void set_multicast_list (struct net_device *dev);
-static int  cops_ioctl (struct net_device *dev, struct ifreq *rq, int cmd);
-static int  cops_close (struct net_device *dev);
-
-static void cleanup_card(struct net_device *dev)
-{
-	if (dev->irq)
-		free_irq(dev->irq, dev);
-	release_region(dev->base_addr, COPS_IO_EXTENT);
-}
-
-/*
- *      Check for a network adaptor of this type, and return '0' iff one exists.
- *      If dev->base_addr == 0, probe all likely locations.
- *      If dev->base_addr in [1..0x1ff], always return failure.
- *        otherwise go with what we pass in.
- */
-struct net_device * __init cops_probe(int unit)
-{
-	struct net_device *dev;
-	unsigned *port;
-	int base_addr;
-	int err = 0;
-
-	dev = alloc_ltalkdev(sizeof(struct cops_local));
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	if (unit >= 0) {
-		sprintf(dev->name, "lt%d", unit);
-		netdev_boot_setup_check(dev);
-		irq = dev->irq;
-		base_addr = dev->base_addr;
-	} else {
-		base_addr = dev->base_addr = io;
-	}
-
-	if (base_addr > 0x1ff) {    /* Check a single specified location. */
-		err = cops_probe1(dev, base_addr);
-	} else if (base_addr != 0) { /* Don't probe at all. */
-		err = -ENXIO;
-	} else {
-		/* FIXME  Does this really work for cards which generate irq?
-		 * It's definitely N.G. for polled Tangent. sh
-		 * Dayna cards don't autoprobe well at all, but if your card is
-		 * at IRQ 5 & IO 0x240 we find it every time. ;) JS
-		 */
-		for (port = ports; *port && cops_probe1(dev, *port) < 0; port++)
-			;
-		if (!*port)
-			err = -ENODEV;
-	}
-	if (err)
-		goto out;
-	err = register_netdev(dev);
-	if (err)
-		goto out1;
-	return dev;
-out1:
-	cleanup_card(dev);
-out:
-	free_netdev(dev);
-	return ERR_PTR(err);
-}
-
-static const struct net_device_ops cops_netdev_ops = {
-	.ndo_open               = cops_open,
-        .ndo_stop               = cops_close,
-	.ndo_start_xmit   	= cops_send_packet,
-	.ndo_tx_timeout		= cops_timeout,
-        .ndo_do_ioctl           = cops_ioctl,
-	.ndo_set_multicast_list = set_multicast_list,
-};
-
-/*
- *      This is the real probe routine. Linux has a history of friendly device
- *      probes on the ISA bus. A good device probes avoids doing writes, and
- *      verifies that the correct device exists and functions.
- */
-static int __init cops_probe1(struct net_device *dev, int ioaddr)
-{
-        struct cops_local *lp;
-	static unsigned version_printed;
-	int board = board_type;
-	int retval;
-	
-        if(cops_debug && version_printed++ == 0)
-		printk("%s", version);
-
-	/* Grab the region so no one else tries to probe our ioports. */
-	if (!request_region(ioaddr, COPS_IO_EXTENT, dev->name))
-		return -EBUSY;
-
-        /*
-         * Since this board has jumpered interrupts, allocate the interrupt
-         * vector now. There is no point in waiting since no other device
-         * can use the interrupt, and this marks the irq as busy. Jumpered
-         * interrupts are typically not reported by the boards, and we must
-         * used AutoIRQ to find them.
-	 */
-	dev->irq = irq;
-	switch (dev->irq)
-	{
-		case 0:
-			/* COPS AutoIRQ routine */
-			dev->irq = cops_irq(ioaddr, board);
-			if (dev->irq)
-				break;
-			/* No IRQ found on this port, fallthrough */
-		case 1:
-			retval = -EINVAL;
-			goto err_out;
-
-		/* Fixup for users that don't know that IRQ 2 is really
-		 * IRQ 9, or don't know which one to set.
-		 */
-		case 2:
-			dev->irq = 9;
-			break;
-
-		/* Polled operation requested. Although irq of zero passed as
-		 * a parameter tells the init routines to probe, we'll
-		 * overload it to denote polled operation at runtime.
-		 */
-		case 0xff:
-			dev->irq = 0;
-			break;
-
-		default:
-			break;
-	}
-
-	/* Reserve any actual interrupt. */
-	if (dev->irq) {
-		retval = request_irq(dev->irq, cops_interrupt, 0, dev->name, dev);
-		if (retval)
-			goto err_out;
-	}
-
-	dev->base_addr = ioaddr;
-
-        lp = netdev_priv(dev);
-        spin_lock_init(&lp->lock);
-
-	/* Copy local board variable to lp struct. */
-	lp->board               = board;
-
-	dev->netdev_ops 	= &cops_netdev_ops;
-	dev->watchdog_timeo	= HZ * 2;
-
-
-	/* Tell the user where the card is and what mode we're in. */
-	if(board==DAYNA)
-		printk("%s: %s at %#3x, using IRQ %d, in Dayna mode.\n", 
-			dev->name, cardname, ioaddr, dev->irq);
-	if(board==TANGENT) {
-		if(dev->irq)
-			printk("%s: %s at %#3x, IRQ %d, in Tangent mode\n", 
-				dev->name, cardname, ioaddr, dev->irq);
-		else
-			printk("%s: %s at %#3x, using polled IO, in Tangent mode.\n", 
-				dev->name, cardname, ioaddr);
-
-	}
-        return 0;
-
-err_out:
-	release_region(ioaddr, COPS_IO_EXTENT);
-	return retval;
-}
-
-static int __init cops_irq (int ioaddr, int board)
-{       /*
-         * This does not use the IRQ to determine where the IRQ is. We just
-         * assume that when we get a correct status response that it's the IRQ.
-         * This really just verifies the IO port but since we only have access
-         * to such a small number of IRQs (5, 4, 3) this is not bad.
-         * This will probably not work for more than one card.
-         */
-        int irqaddr=0;
-        int i, x, status;
-
-        if(board==DAYNA)
-        {
-                outb(0, ioaddr+DAYNA_RESET);
-                inb(ioaddr+DAYNA_RESET);
-                mdelay(333);
-        }
-        if(board==TANGENT)
-        {
-                inb(ioaddr);
-                outb(0, ioaddr);
-                outb(0, ioaddr+TANG_RESET);
-        }
-
-        for(i=0; cops_irqlist[i] !=0; i++)
-        {
-                irqaddr = cops_irqlist[i];
-                for(x = 0xFFFF; x>0; x --)    /* wait for response */
-                {
-                        if(board==DAYNA)
-                        {
-                                status = (inb(ioaddr+DAYNA_CARD_STATUS)&3);
-                                if(status == 1)
-                                        return irqaddr;
-                        }
-                        if(board==TANGENT)
-                        {
-                                if((inb(ioaddr+TANG_CARD_STATUS)& TANG_TX_READY) !=0)
-                                        return irqaddr;
-                        }
-                }
-        }
-        return 0;       /* no IRQ found */
-}
-
-/*
- * Open/initialize the board. This is called (in the current kernel)
- * sometime after booting when the 'ifconfig' program is run.
- */
-static int cops_open(struct net_device *dev)
-{
-    struct cops_local *lp = netdev_priv(dev);
-
-	if(dev->irq==0)
-	{
-		/*
-		 * I don't know if the Dayna-style boards support polled 
-		 * operation.  For now, only allow it for Tangent.
-		 */
-		if(lp->board==TANGENT)	/* Poll 20 times per second */
-		{
-		    init_timer(&cops_timer);
-		    cops_timer.function = cops_poll;
-		    cops_timer.data 	= (unsigned long)dev;
-		    cops_timer.expires 	= jiffies + HZ/20;
-		    add_timer(&cops_timer);
-		} 
-		else 
-		{
-			printk(KERN_WARNING "%s: No irq line set\n", dev->name);
-			return -EAGAIN;
-		}
-	}
-
-	cops_jumpstart(dev);	/* Start the card up. */
-
-	netif_start_queue(dev);
-        return 0;
-}
-
-/*
- *	This allows for a dynamic start/restart of the entire card.
- */
-static int cops_jumpstart(struct net_device *dev)
-{
-	struct cops_local *lp = netdev_priv(dev);
-
-	/*
-         *      Once the card has the firmware loaded and has acquired
-         *      the nodeid, if it is reset it will lose it all.
-         */
-        cops_reset(dev,1);	/* Need to reset card before load firmware. */
-        cops_load(dev);		/* Load the firmware. */
-
-	/*
-	 *	If atalkd already gave us a nodeid we will use that
-	 *	one again, else we wait for atalkd to give us a nodeid
-	 *	in cops_ioctl. This may cause a problem if someone steals
-	 *	our nodeid while we are resetting.
-	 */	
-	if(lp->nodeid == 1)
-		cops_nodeid(dev,lp->node_acquire);
-
-	return 0;
-}
-
-static void tangent_wait_reset(int ioaddr)
-{
-	int timeout=0;
-
-	while(timeout++ < 5 && (inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-		mdelay(1);   /* Wait 1 second */
-}
-
-/*
- *      Reset the LocalTalk board.
- */
-static void cops_reset(struct net_device *dev, int sleep)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr=dev->base_addr;
-
-        if(lp->board==TANGENT)
-        {
-                inb(ioaddr);		/* Clear request latch. */
-                outb(0,ioaddr);		/* Clear the TANG_TX_READY flop. */
-                outb(0, ioaddr+TANG_RESET);	/* Reset the adapter. */
-
-		tangent_wait_reset(ioaddr);
-                outb(0, ioaddr+TANG_CLEAR_INT);
-        }
-        if(lp->board==DAYNA)
-        {
-                outb(0, ioaddr+DAYNA_RESET);	/* Assert the reset port */
-                inb(ioaddr+DAYNA_RESET);	/* Clear the reset */
-		if (sleep)
-			msleep(333);
-		else
-			mdelay(333);
-        }
-
-	netif_wake_queue(dev);
-}
-
-static void cops_load (struct net_device *dev)
-{
-        struct ifreq ifr;
-        struct ltfirmware *ltf= (struct ltfirmware *)&ifr.ifr_ifru;
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr=dev->base_addr;
-	int length, i = 0;
-
-        strcpy(ifr.ifr_name,"lt0");
-
-        /* Get card's firmware code and do some checks on it. */
-#ifdef CONFIG_COPS_DAYNA        
-        if(lp->board==DAYNA)
-        {
-                ltf->length=sizeof(ffdrv_code);
-                ltf->data=ffdrv_code;
-        }
-        else
-#endif        
-#ifdef CONFIG_COPS_TANGENT
-        if(lp->board==TANGENT)
-        {
-                ltf->length=sizeof(ltdrv_code);
-                ltf->data=ltdrv_code;
-        }
-        else
-#endif
-	{
-		printk(KERN_INFO "%s; unsupported board type.\n", dev->name);
-		return;
-	}
-	
-        /* Check to make sure firmware is correct length. */
-        if(lp->board==DAYNA && ltf->length!=5983)
-        {
-                printk(KERN_WARNING "%s: Firmware is not length of FFDRV.BIN.\n", dev->name);
-                return;
-        }
-        if(lp->board==TANGENT && ltf->length!=2501)
-        {
-                printk(KERN_WARNING "%s: Firmware is not length of DRVCODE.BIN.\n", dev->name);
-                return;
-        }
-
-        if(lp->board==DAYNA)
-        {
-                /*
-                 *      We must wait for a status response
-                 *      with the DAYNA board.
-                 */
-                while(++i<65536)
-                {
-                       if((inb(ioaddr+DAYNA_CARD_STATUS)&3)==1)
-                                break;
-                }
-
-                if(i==65536)
-                        return;
-        }
-
-        /*
-         *      Upload the firmware and kick. Byte-by-byte works nicely here.
-         */
-	i=0;
-        length = ltf->length;
-        while(length--)
-        {
-                outb(ltf->data[i], ioaddr);
-                i++;
-        }
-
-	if(cops_debug > 1)
-		printk("%s: Uploaded firmware - %d bytes of %d bytes.\n", 
-			dev->name, i, ltf->length);
-
-        if(lp->board==DAYNA) 	/* Tell Dayna to run the firmware code. */
-                outb(1, ioaddr+DAYNA_INT_CARD);
-	else			/* Tell Tang to run the firmware code. */
-		inb(ioaddr);
-
-        if(lp->board==TANGENT)
-        {
-                tangent_wait_reset(ioaddr);
-                inb(ioaddr);	/* Clear initial ready signal. */
-        }
-}
-
-/*
- * 	Get the LocalTalk Nodeid from the card. We can suggest
- *	any nodeid 1-254. The card will try and get that exact
- *	address else we can specify 0 as the nodeid and the card
- *	will autoprobe for a nodeid.
- */
-static int cops_nodeid (struct net_device *dev, int nodeid)
-{
-	struct cops_local *lp = netdev_priv(dev);
-	int ioaddr = dev->base_addr;
-
-	if(lp->board == DAYNA)
-        {
-        	/* Empty any pending adapter responses. */
-                while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
-                {
-			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupts. */
-        		if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
-                		cops_rx(dev);	/* Kick any packets waiting. */
-			schedule();
-                }
-
-                outb(2, ioaddr);       	/* Output command packet length as 2. */
-                outb(0, ioaddr);
-                outb(LAP_INIT, ioaddr);	/* Send LAP_INIT command byte. */
-                outb(nodeid, ioaddr);  	/* Suggest node address. */
-        }
-
-	if(lp->board == TANGENT)
-        {
-                /* Empty any pending adapter responses. */
-                while(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
-                {
-			outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear interrupt. */
-                	cops_rx(dev);          	/* Kick out packets waiting. */
-			schedule();
-                }
-
-		/* Not sure what Tangent does if nodeid picked is used. */
-                if(nodeid == 0)	         		/* Seed. */
-                	nodeid = jiffies&0xFF;		/* Get a random try */
-                outb(2, ioaddr);        		/* Command length LSB */
-                outb(0, ioaddr);       			/* Command length MSB */
-                outb(LAP_INIT, ioaddr); 		/* Send LAP_INIT byte */
-                outb(nodeid, ioaddr); 		  	/* LAP address hint. */
-                outb(0xFF, ioaddr);     		/* Int. level to use */
-        }
-
-	lp->node_acquire=0;		/* Set nodeid holder to 0. */
-        while(lp->node_acquire==0)	/* Get *True* nodeid finally. */
-	{
-		outb(0, ioaddr+COPS_CLEAR_INT);	/* Clear any interrupt. */
-
-		if(lp->board == DAYNA)
-		{
-                	if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST)
-                		cops_rx(dev);	/* Grab the nodeid put in lp->node_acquire. */
-		}
-		if(lp->board == TANGENT)
-		{	
-			if(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY)
-                                cops_rx(dev);   /* Grab the nodeid put in lp->node_acquire. */
-		}
-		schedule();
-	}
-
-	if(cops_debug > 1)
-		printk(KERN_DEBUG "%s: Node ID %d has been acquired.\n", 
-			dev->name, lp->node_acquire);
-
-	lp->nodeid=1;	/* Set got nodeid to 1. */
-
-        return 0;
-}
-
-/*
- *	Poll the Tangent type cards to see if we have work.
- */
- 
-static void cops_poll(unsigned long ltdev)
-{
-	int ioaddr, status;
-	int boguscount = 0;
-
-	struct net_device *dev = (struct net_device *)ltdev;
-
-	del_timer(&cops_timer);
-
-	if(dev == NULL)
-		return;	/* We've been downed */
-
-	ioaddr = dev->base_addr;
-	do {
-		status=inb(ioaddr+TANG_CARD_STATUS);
-		if(status & TANG_RX_READY)
-			cops_rx(dev);
-		if(status & TANG_TX_READY)
-			netif_wake_queue(dev);
-		status = inb(ioaddr+TANG_CARD_STATUS);
-	} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
-
-	/* poll 20 times per second */
-	cops_timer.expires = jiffies + HZ/20;
-	add_timer(&cops_timer);
-}
-
-/*
- *      The typical workload of the driver:
- *      Handle the network interface interrupts.
- */
-static irqreturn_t cops_interrupt(int irq, void *dev_id)
-{
-        struct net_device *dev = dev_id;
-        struct cops_local *lp;
-        int ioaddr, status;
-        int boguscount = 0;
-
-        ioaddr = dev->base_addr;
-        lp = netdev_priv(dev);
-
-	if(lp->board==DAYNA)
-	{
-		do {
-			outb(0, ioaddr + COPS_CLEAR_INT);
-                       	status=inb(ioaddr+DAYNA_CARD_STATUS);
-                       	if((status&0x03)==DAYNA_RX_REQUEST)
-                       	        cops_rx(dev);
-                	netif_wake_queue(dev);
-		} while(++boguscount < 20);
-	}
-	else
-	{
-		do {
-                       	status=inb(ioaddr+TANG_CARD_STATUS);
-			if(status & TANG_RX_READY)
-				cops_rx(dev);
-			if(status & TANG_TX_READY)
-				netif_wake_queue(dev);
-			status=inb(ioaddr+TANG_CARD_STATUS);
-		} while((++boguscount < 20) && (status&(TANG_RX_READY|TANG_TX_READY)));
-	}
-
-        return IRQ_HANDLED;
-}
-
-/*
- *      We have a good packet(s), get it/them out of the buffers.
- */
-static void cops_rx(struct net_device *dev)
-{
-        int pkt_len = 0;
-        int rsp_type = 0;
-        struct sk_buff *skb = NULL;
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr = dev->base_addr;
-        int boguscount = 0;
-        unsigned long flags;
-
-
-	spin_lock_irqsave(&lp->lock, flags);
-	
-        if(lp->board==DAYNA)
-        {
-                outb(0, ioaddr);                /* Send out Zero length. */
-                outb(0, ioaddr);
-                outb(DATA_READ, ioaddr);        /* Send read command out. */
-
-                /* Wait for DMA to turn around. */
-                while(++boguscount<1000000)
-                {
-			barrier();
-                        if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_READY)
-                                break;
-                }
-
-                if(boguscount==1000000)
-                {
-                        printk(KERN_WARNING "%s: DMA timed out.\n",dev->name);
-			spin_unlock_irqrestore(&lp->lock, flags);
-                        return;
-                }
-        }
-
-        /* Get response length. */
-	if(lp->board==DAYNA)
-        	pkt_len = inb(ioaddr) & 0xFF;
-	else
-		pkt_len = inb(ioaddr) & 0x00FF;
-        pkt_len |= (inb(ioaddr) << 8);
-        /* Input IO code. */
-        rsp_type=inb(ioaddr);
-
-        /* Malloc up new buffer. */
-        skb = dev_alloc_skb(pkt_len);
-        if(skb == NULL)
-        {
-                printk(KERN_WARNING "%s: Memory squeeze, dropping packet.\n",
-			dev->name);
-                dev->stats.rx_dropped++;
-                while(pkt_len--)        /* Discard packet */
-                        inb(ioaddr);
-                spin_unlock_irqrestore(&lp->lock, flags);
-                return;
-        }
-        skb->dev = dev;
-        skb_put(skb, pkt_len);
-        skb->protocol = htons(ETH_P_LOCALTALK);
-
-        insb(ioaddr, skb->data, pkt_len);               /* Eat the Data */
-
-        if(lp->board==DAYNA)
-                outb(1, ioaddr+DAYNA_INT_CARD);         /* Interrupt the card */
-
-        spin_unlock_irqrestore(&lp->lock, flags);  /* Restore interrupts. */
-
-        /* Check for bad response length */
-        if(pkt_len < 0 || pkt_len > MAX_LLAP_SIZE)
-        {
-		printk(KERN_WARNING "%s: Bad packet length of %d bytes.\n", 
-			dev->name, pkt_len);
-                dev->stats.tx_errors++;
-                dev_kfree_skb_any(skb);
-                return;
-        }
-
-        /* Set nodeid and then get out. */
-        if(rsp_type == LAP_INIT_RSP)
-        {	/* Nodeid taken from received packet. */
-                lp->node_acquire = skb->data[0];
-                dev_kfree_skb_any(skb);
-                return;
-        }
-
-        /* One last check to make sure we have a good packet. */
-        if(rsp_type != LAP_RESPONSE)
-        {
-                printk(KERN_WARNING "%s: Bad packet type %d.\n", dev->name, rsp_type);
-                dev->stats.tx_errors++;
-                dev_kfree_skb_any(skb);
-                return;
-        }
-
-        skb_reset_mac_header(skb);    /* Point to entire packet. */
-        skb_pull(skb,3);
-        skb_reset_transport_header(skb);    /* Point to data (Skip header). */
-
-        /* Update the counters. */
-        dev->stats.rx_packets++;
-        dev->stats.rx_bytes += skb->len;
-
-        /* Send packet to a higher place. */
-        netif_rx(skb);
-}
-
-static void cops_timeout(struct net_device *dev)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr = dev->base_addr;
-
-	dev->stats.tx_errors++;
-        if(lp->board==TANGENT)
-        {
-		if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-               		printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name);
-	}
-	printk(KERN_WARNING "%s: Transmit timed out.\n", dev->name);
-	cops_jumpstart(dev);	/* Restart the card. */
-	dev->trans_start = jiffies; /* prevent tx timeout */
-	netif_wake_queue(dev);
-}
-
-
-/*
- *	Make the card transmit a LocalTalk packet.
- */
-
-static netdev_tx_t cops_send_packet(struct sk_buff *skb,
-					  struct net_device *dev)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        int ioaddr = dev->base_addr;
-        unsigned long flags;
-
-        /*
-         * Block a timer-based transmit from overlapping. 
-	 */
-	 
-	netif_stop_queue(dev);
-
-	spin_lock_irqsave(&lp->lock, flags);
-	if(lp->board == DAYNA)	 /* Wait for adapter transmit buffer. */
-		while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0)
-			cpu_relax();
-	if(lp->board == TANGENT) /* Wait for adapter transmit buffer. */
-		while((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0)
-			cpu_relax();
-
-	/* Output IO length. */
-	outb(skb->len, ioaddr);
-	if(lp->board == DAYNA)
-               	outb(skb->len >> 8, ioaddr);
-	else
-		outb((skb->len >> 8)&0x0FF, ioaddr);
-
-	/* Output IO code. */
-	outb(LAP_WRITE, ioaddr);
-
-	if(lp->board == DAYNA)	/* Check the transmit buffer again. */
-        	while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0);
-
-	outsb(ioaddr, skb->data, skb->len);	/* Send out the data. */
-
-	if(lp->board==DAYNA)	/* Dayna requires you kick the card */
-		outb(1, ioaddr+DAYNA_INT_CARD);
-
-	spin_unlock_irqrestore(&lp->lock, flags);	/* Restore interrupts. */
-
-	/* Done sending packet, update counters and cleanup. */
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-	dev_kfree_skb (skb);
-	return NETDEV_TX_OK;
-}
-
-/*
- *	Dummy function to keep the Appletalk layer happy.
- */
- 
-static void set_multicast_list(struct net_device *dev)
-{
-        if(cops_debug >= 3)
-		printk("%s: set_multicast_list executed\n", dev->name);
-}
-
-/*
- *      System ioctls for the COPS LocalTalk card.
- */
- 
-static int cops_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-        struct cops_local *lp = netdev_priv(dev);
-        struct sockaddr_at *sa = (struct sockaddr_at *)&ifr->ifr_addr;
-        struct atalk_addr *aa = (struct atalk_addr *)&lp->node_addr;
-
-        switch(cmd)
-        {
-                case SIOCSIFADDR:
-			/* Get and set the nodeid and network # atalkd wants. */
-			cops_nodeid(dev, sa->sat_addr.s_node);
-			aa->s_net               = sa->sat_addr.s_net;
-                        aa->s_node              = lp->node_acquire;
-
-			/* Set broardcast address. */
-                        dev->broadcast[0]       = 0xFF;
-			
-			/* Set hardware address. */
-                        dev->dev_addr[0]        = aa->s_node;
-                        dev->addr_len           = 1;
-                        return 0;
-
-                case SIOCGIFADDR:
-                        sa->sat_addr.s_net      = aa->s_net;
-                        sa->sat_addr.s_node     = aa->s_node;
-                        return 0;
-
-                default:
-                        return -EOPNOTSUPP;
-        }
-}
-
-/*
- *	The inverse routine to cops_open().
- */
- 
-static int cops_close(struct net_device *dev)
-{
-	struct cops_local *lp = netdev_priv(dev);
-
-	/* If we were running polled, yank the timer.
-	 */
-	if(lp->board==TANGENT && dev->irq==0)
-		del_timer(&cops_timer);
-
-	netif_stop_queue(dev);
-        return 0;
-}
-
-
-#ifdef MODULE
-static struct net_device *cops_dev;
-
-MODULE_LICENSE("GPL");
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(board_type, int, 0);
-
-static int __init cops_module_init(void)
-{
-	if (io == 0)
-		printk(KERN_WARNING "%s: You shouldn't autoprobe with insmod\n",
-			cardname);
-	cops_dev = cops_probe(-1);
-	if (IS_ERR(cops_dev))
-		return PTR_ERR(cops_dev);
-        return 0;
-}
-
-static void __exit cops_module_exit(void)
-{
-	unregister_netdev(cops_dev);
-	cleanup_card(cops_dev);
-	free_netdev(cops_dev);
-}
-module_init(cops_module_init);
-module_exit(cops_module_exit);
-#endif /* MODULE */
diff --git a/drivers/staging/appletalk/cops.h b/drivers/staging/appletalk/cops.h
deleted file mode 100644
index fd2750b269c8..000000000000
--- a/drivers/staging/appletalk/cops.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*      cops.h: LocalTalk driver for Linux.
- *
- *      Authors:
- *      - Jay Schulist <jschlst@samba.org>
- */
-
-#ifndef __LINUX_COPSLTALK_H
-#define __LINUX_COPSLTALK_H
-
-#ifdef __KERNEL__
-
-/* Max LLAP size we will accept. */
-#define MAX_LLAP_SIZE		603
-
-/* Tangent */
-#define TANG_CARD_STATUS        1
-#define TANG_CLEAR_INT          1
-#define TANG_RESET              3
-
-#define TANG_TX_READY           1
-#define TANG_RX_READY           2
-
-/* Dayna */
-#define DAYNA_CMD_DATA          0
-#define DAYNA_CLEAR_INT         1
-#define DAYNA_CARD_STATUS       2
-#define DAYNA_INT_CARD          3
-#define DAYNA_RESET             4
-
-#define DAYNA_RX_READY          0
-#define DAYNA_TX_READY          1
-#define DAYNA_RX_REQUEST        3
-
-/* Same on both card types */
-#define COPS_CLEAR_INT  1
-
-/* LAP response codes received from the cards. */
-#define LAP_INIT        1       /* Init cmd */
-#define LAP_INIT_RSP    2       /* Init response */
-#define LAP_WRITE       3       /* Write cmd */
-#define DATA_READ       4       /* Data read */
-#define LAP_RESPONSE    4       /* Received ALAP frame response */
-#define LAP_GETSTAT     5       /* Get LAP and HW status */
-#define LAP_RSPSTAT     6       /* Status response */
-
-#endif
-
-/*
- *	Structure to hold the firmware information.
- */
-struct ltfirmware
-{
-        unsigned int length;
-        const unsigned char *data;
-};
-
-#define DAYNA 1
-#define TANGENT 2
-
-#endif
diff --git a/drivers/staging/appletalk/cops_ffdrv.h b/drivers/staging/appletalk/cops_ffdrv.h
deleted file mode 100644
index b02005087c1b..000000000000
--- a/drivers/staging/appletalk/cops_ffdrv.h
+++ /dev/null
@@ -1,532 +0,0 @@
-
-/*
- *	The firmware this driver downloads into the Localtalk card is a
- *	separate program and is not GPL'd source code, even though the Linux
- *	side driver and the routine that loads this data into the card are.
- *	
- *	It is taken from the COPS SDK and is under the following license
- *
- *	This material is licensed to you strictly for use in conjunction with
- *	the use of COPS LocalTalk adapters.
- *	There is no charge for this SDK. And no waranty express or implied
- *	about its fitness for any purpose. However, we will cheerefully
- *	refund every penny you paid for this SDK...
- *	Regards,
- *
- *	Thomas F. Divine
- *	Chief Scientist
- */
-
-
-/*      cops_ffdrv.h: LocalTalk driver firmware dump for Linux.
- *
- *      Authors:
- *      - Jay Schulist <jschlst@samba.org>
- */
-
-
-#ifdef CONFIG_COPS_DAYNA
-
-static const unsigned char ffdrv_code[] = {
-	58,3,0,50,228,149,33,255,255,34,226,149,
-	249,17,40,152,33,202,154,183,237,82,77,68,
-	11,107,98,19,54,0,237,176,175,50,80,0,
-	62,128,237,71,62,32,237,57,51,62,12,237,
-	57,50,237,57,54,62,6,237,57,52,62,12,
-	237,57,49,33,107,137,34,32,128,33,83,130,
-	34,40,128,33,86,130,34,42,128,33,112,130,
-	34,36,128,33,211,130,34,38,128,62,0,237,
-	57,16,33,63,148,34,34,128,237,94,205,15,
-	130,251,205,168,145,24,141,67,111,112,121,114,
-	105,103,104,116,32,40,67,41,32,49,57,56,
-	56,32,45,32,68,97,121,110,97,32,67,111,
-	109,109,117,110,105,99,97,116,105,111,110,115,
-	32,32,32,65,108,108,32,114,105,103,104,116,
-	115,32,114,101,115,101,114,118,101,100,46,32,
-	32,40,68,40,68,7,16,8,34,7,22,6,
-	16,5,12,4,8,3,6,140,0,16,39,128,
-	0,4,96,10,224,6,0,7,126,2,64,11,
-	118,12,6,13,0,14,193,15,0,5,96,3,
-	192,1,64,9,8,62,9,211,66,62,192,211,
-	66,62,100,61,32,253,6,28,33,205,129,14,
-	66,237,163,194,253,129,6,28,33,205,129,14,
-	64,237,163,194,9,130,201,62,47,50,71,152,
-	62,47,211,68,58,203,129,237,57,20,58,204,
-	129,237,57,21,33,77,152,54,132,205,233,129,
-	58,228,149,254,209,40,6,56,4,62,0,24,
-	2,219,96,33,233,149,119,230,62,33,232,149,
-	119,213,33,8,152,17,7,0,25,119,19,25,
-	119,209,201,251,237,77,245,197,213,229,221,229,
-	205,233,129,62,1,50,106,137,205,158,139,221,
-	225,225,209,193,241,251,237,77,245,197,213,219,
-	72,237,56,16,230,46,237,57,16,237,56,12,
-	58,72,152,183,32,26,6,20,17,128,2,237,
-	56,46,187,32,35,237,56,47,186,32,29,219,
-	72,230,1,32,3,5,32,232,175,50,72,152,
-	229,221,229,62,1,50,106,137,205,158,139,221,
-	225,225,24,25,62,1,50,72,152,58,201,129,
-	237,57,12,58,202,129,237,57,13,237,56,16,
-	246,17,237,57,16,209,193,241,251,237,77,245,
-	197,229,213,221,229,237,56,16,230,17,237,57,
-	16,237,56,20,58,34,152,246,16,246,8,211,
-	68,62,6,61,32,253,58,34,152,246,8,211,
-	68,58,203,129,237,57,20,58,204,129,237,57,
-	21,237,56,16,246,34,237,57,16,221,225,209,
-	225,193,241,251,237,77,33,2,0,57,126,230,
-	3,237,100,1,40,2,246,128,230,130,245,62,
-	5,211,64,241,211,64,201,229,213,243,237,56,
-	16,230,46,237,57,16,237,56,12,251,70,35,
-	35,126,254,175,202,77,133,254,129,202,15,133,
-	230,128,194,191,132,43,58,44,152,119,33,76,
-	152,119,35,62,132,119,120,254,255,40,4,58,
-	49,152,119,219,72,43,43,112,17,3,0,237,
-	56,52,230,248,237,57,52,219,72,230,1,194,
-	141,131,209,225,237,56,52,246,6,237,57,52,
-	62,1,55,251,201,62,3,211,66,62,192,211,
-	66,62,48,211,66,0,0,219,66,230,1,40,
-	4,219,67,24,240,205,203,135,58,75,152,254,
-	255,202,128,132,58,49,152,254,161,250,207,131,
-	58,34,152,211,68,62,10,211,66,62,128,211,
-	66,62,11,211,66,62,6,211,66,24,0,62,
-	14,211,66,62,33,211,66,62,1,211,66,62,
-	64,211,66,62,3,211,66,62,209,211,66,62,
-	100,71,219,66,230,1,32,6,5,32,247,195,
-	248,132,219,67,71,58,44,152,184,194,248,132,
-	62,100,71,219,66,230,1,32,6,5,32,247,
-	195,248,132,219,67,62,100,71,219,66,230,1,
-	32,6,5,32,247,195,248,132,219,67,254,133,
-	32,7,62,0,50,74,152,24,17,254,173,32,
-	7,62,1,50,74,152,24,6,254,141,194,248,
-	132,71,209,225,58,49,152,254,132,32,10,62,
-	50,205,2,134,205,144,135,24,27,254,140,32,
-	15,62,110,205,2,134,62,141,184,32,5,205,
-	144,135,24,8,62,10,205,2,134,205,8,134,
-	62,1,50,106,137,205,158,139,237,56,52,246,
-	6,237,57,52,175,183,251,201,62,20,135,237,
-	57,20,175,237,57,21,237,56,16,246,2,237,
-	57,16,237,56,20,95,237,56,21,123,254,10,
-	48,244,237,56,16,230,17,237,57,16,209,225,
-	205,144,135,62,1,50,106,137,205,158,139,237,
-	56,52,246,6,237,57,52,175,183,251,201,209,
-	225,243,219,72,230,1,40,13,62,10,211,66,
-	0,0,219,66,230,192,202,226,132,237,56,52,
-	246,6,237,57,52,62,1,55,251,201,205,203,
-	135,62,1,50,106,137,205,158,139,237,56,52,
-	246,6,237,57,52,183,251,201,209,225,62,1,
-	50,106,137,205,158,139,237,56,52,246,6,237,
-	57,52,62,2,55,251,201,209,225,243,219,72,
-	230,1,202,213,132,62,10,211,66,0,0,219,
-	66,230,192,194,213,132,229,62,1,50,106,137,
-	42,40,152,205,65,143,225,17,3,0,205,111,
-	136,62,6,211,66,58,44,152,211,66,237,56,
-	52,246,6,237,57,52,183,251,201,209,197,237,
-	56,52,230,248,237,57,52,219,72,230,1,32,
-	15,193,225,237,56,52,246,6,237,57,52,62,
-	1,55,251,201,14,23,58,37,152,254,0,40,
-	14,14,2,254,1,32,5,62,140,119,24,3,
-	62,132,119,43,43,197,205,203,135,193,62,1,
-	211,66,62,64,211,66,62,3,211,66,62,193,
-	211,66,62,100,203,39,71,219,66,230,1,32,
-	6,5,32,247,195,229,133,33,238,151,219,67,
-	71,58,44,152,184,194,229,133,119,62,100,71,
-	219,66,230,1,32,6,5,32,247,195,229,133,
-	219,67,35,119,13,32,234,193,225,62,1,50,
-	106,137,205,158,139,237,56,52,246,6,237,57,
-	52,175,183,251,201,33,234,151,35,35,62,255,
-	119,193,225,62,1,50,106,137,205,158,139,237,
-	56,52,246,6,237,57,52,175,251,201,243,61,
-	32,253,251,201,62,3,211,66,62,192,211,66,
-	58,49,152,254,140,32,19,197,229,213,17,181,
-	129,33,185,129,1,2,0,237,176,209,225,193,
-	24,27,229,213,33,187,129,58,49,152,230,15,
-	87,30,2,237,92,25,17,181,129,126,18,19,
-	35,126,18,209,225,58,34,152,246,8,211,68,
-	58,49,152,254,165,40,14,254,164,40,10,62,
-	10,211,66,62,224,211,66,24,25,58,74,152,
-	254,0,40,10,62,10,211,66,62,160,211,66,
-	24,8,62,10,211,66,62,128,211,66,62,11,
-	211,66,62,6,211,66,205,147,143,62,5,211,
-	66,62,224,211,66,62,5,211,66,62,96,211,
-	66,62,5,61,32,253,62,5,211,66,62,224,
-	211,66,62,14,61,32,253,62,5,211,66,62,
-	233,211,66,62,128,211,66,58,181,129,61,32,
-	253,62,1,211,66,62,192,211,66,1,254,19,
-	237,56,46,187,32,6,13,32,247,195,226,134,
-	62,192,211,66,0,0,219,66,203,119,40,250,
-	219,66,203,87,40,250,243,237,56,16,230,17,
-	237,57,16,237,56,20,251,62,5,211,66,62,
-	224,211,66,58,182,129,61,32,253,229,33,181,
-	129,58,183,129,203,63,119,35,58,184,129,119,
-	225,62,10,211,66,62,224,211,66,62,11,211,
-	66,62,118,211,66,62,47,211,68,62,5,211,
-	66,62,233,211,66,58,181,129,61,32,253,62,
-	5,211,66,62,224,211,66,58,182,129,61,32,
-	253,62,5,211,66,62,96,211,66,201,229,213,
-	58,50,152,230,15,87,30,2,237,92,33,187,
-	129,25,17,181,129,126,18,35,19,126,18,209,
-	225,58,71,152,246,8,211,68,58,50,152,254,
-	165,40,14,254,164,40,10,62,10,211,66,62,
-	224,211,66,24,8,62,10,211,66,62,128,211,
-	66,62,11,211,66,62,6,211,66,195,248,135,
-	62,3,211,66,62,192,211,66,197,229,213,17,
-	181,129,33,183,129,1,2,0,237,176,209,225,
-	193,62,47,211,68,62,10,211,66,62,224,211,
-	66,62,11,211,66,62,118,211,66,62,1,211,
-	66,62,0,211,66,205,147,143,195,16,136,62,
-	3,211,66,62,192,211,66,197,229,213,17,181,
-	129,33,183,129,1,2,0,237,176,209,225,193,
-	62,47,211,68,62,10,211,66,62,224,211,66,
-	62,11,211,66,62,118,211,66,205,147,143,62,
-	5,211,66,62,224,211,66,62,5,211,66,62,
-	96,211,66,62,5,61,32,253,62,5,211,66,
-	62,224,211,66,62,14,61,32,253,62,5,211,
-	66,62,233,211,66,62,128,211,66,58,181,129,
-	61,32,253,62,1,211,66,62,192,211,66,1,
-	254,19,237,56,46,187,32,6,13,32,247,195,
-	88,136,62,192,211,66,0,0,219,66,203,119,
-	40,250,219,66,203,87,40,250,62,5,211,66,
-	62,224,211,66,58,182,129,61,32,253,62,5,
-	211,66,62,96,211,66,201,197,14,67,6,0,
-	62,3,211,66,62,192,211,66,62,48,211,66,
-	0,0,219,66,230,1,40,4,219,67,24,240,
-	62,5,211,66,62,233,211,66,62,128,211,66,
-	58,181,129,61,32,253,237,163,29,62,192,211,
-	66,219,66,230,4,40,250,237,163,29,32,245,
-	219,66,230,4,40,250,62,255,71,219,66,230,
-	4,40,3,5,32,247,219,66,230,4,40,250,
-	62,5,211,66,62,224,211,66,58,182,129,61,
-	32,253,62,5,211,66,62,96,211,66,58,71,
-	152,254,1,202,18,137,62,16,211,66,62,56,
-	211,66,62,14,211,66,62,33,211,66,62,1,
-	211,66,62,248,211,66,237,56,48,246,153,230,
-	207,237,57,48,62,3,211,66,62,221,211,66,
-	193,201,58,71,152,211,68,62,10,211,66,62,
-	128,211,66,62,11,211,66,62,6,211,66,62,
-	6,211,66,58,44,152,211,66,62,16,211,66,
-	62,56,211,66,62,48,211,66,0,0,62,14,
-	211,66,62,33,211,66,62,1,211,66,62,248,
-	211,66,237,56,48,246,145,246,8,230,207,237,
-	57,48,62,3,211,66,62,221,211,66,193,201,
-	44,3,1,0,70,69,1,245,197,213,229,175,
-	50,72,152,237,56,16,230,46,237,57,16,237,
-	56,12,62,1,211,66,0,0,219,66,95,230,
-	160,32,3,195,20,139,123,230,96,194,72,139,
-	62,48,211,66,62,1,211,66,62,64,211,66,
-	237,91,40,152,205,207,143,25,43,55,237,82,
-	218,70,139,34,42,152,98,107,58,44,152,190,
-	194,210,138,35,35,62,130,190,194,200,137,62,
-	1,50,48,152,62,175,190,202,82,139,62,132,
-	190,32,44,50,50,152,62,47,50,71,152,229,
-	175,50,106,137,42,40,152,205,65,143,225,54,
-	133,43,70,58,44,152,119,43,112,17,3,0,
-	62,10,205,2,134,205,111,136,195,158,138,62,
-	140,190,32,19,50,50,152,58,233,149,230,4,
-	202,222,138,62,1,50,71,152,195,219,137,126,
-	254,160,250,185,138,254,166,242,185,138,50,50,
-	152,43,126,35,229,213,33,234,149,95,22,0,
-	25,126,254,132,40,18,254,140,40,14,58,50,
-	152,230,15,87,126,31,21,242,65,138,56,2,
-	175,119,58,50,152,230,15,87,58,233,149,230,
-	62,31,21,242,85,138,218,98,138,209,225,195,
-	20,139,58,50,152,33,100,137,230,15,95,22,
-	0,25,126,50,71,152,209,225,58,50,152,254,
-	164,250,135,138,58,73,152,254,0,40,4,54,
-	173,24,2,54,133,43,70,58,44,152,119,43,
-	112,17,3,0,205,70,135,175,50,106,137,205,
-	208,139,58,199,129,237,57,12,58,200,129,237,
-	57,13,237,56,16,246,17,237,57,16,225,209,
-	193,241,251,237,77,62,129,190,194,227,138,54,
-	130,43,70,58,44,152,119,43,112,17,3,0,
-	205,144,135,195,20,139,35,35,126,254,132,194,
-	227,138,175,50,106,137,205,158,139,24,42,58,
-	201,154,254,1,40,7,62,1,50,106,137,24,
-	237,58,106,137,254,1,202,222,138,62,128,166,
-	194,222,138,221,229,221,33,67,152,205,127,142,
-	205,109,144,221,225,225,209,193,241,251,237,77,
-	58,106,137,254,1,202,44,139,58,50,152,254,
-	164,250,44,139,58,73,152,238,1,50,73,152,
-	221,229,221,33,51,152,205,127,142,221,225,62,
-	1,50,106,137,205,158,139,195,13,139,24,208,
-	24,206,24,204,230,64,40,3,195,20,139,195,
-	20,139,43,126,33,8,152,119,35,58,44,152,
-	119,43,237,91,35,152,205,203,135,205,158,139,
-	195,13,139,175,50,78,152,62,3,211,66,62,
-	192,211,66,201,197,33,4,0,57,126,35,102,
-	111,62,1,50,106,137,219,72,205,141,139,193,
-	201,62,1,50,78,152,34,40,152,54,0,35,
-	35,54,0,195,163,139,58,78,152,183,200,229,
-	33,181,129,58,183,129,119,35,58,184,129,119,
-	225,62,47,211,68,62,14,211,66,62,193,211,
-	66,62,10,211,66,62,224,211,66,62,11,211,
-	66,62,118,211,66,195,3,140,58,78,152,183,
-	200,58,71,152,211,68,254,69,40,4,254,70,
-	32,17,58,73,152,254,0,40,10,62,10,211,
-	66,62,160,211,66,24,8,62,10,211,66,62,
-	128,211,66,62,11,211,66,62,6,211,66,62,
-	6,211,66,58,44,152,211,66,62,16,211,66,
-	62,56,211,66,62,48,211,66,0,0,219,66,
-	230,1,40,4,219,67,24,240,62,14,211,66,
-	62,33,211,66,42,40,152,205,65,143,62,1,
-	211,66,62,248,211,66,237,56,48,246,145,246,
-	8,230,207,237,57,48,62,3,211,66,62,221,
-	211,66,201,62,16,211,66,62,56,211,66,62,
-	48,211,66,0,0,219,66,230,1,40,4,219,
-	67,24,240,62,14,211,66,62,33,211,66,62,
-	1,211,66,62,248,211,66,237,56,48,246,153,
-	230,207,237,57,48,62,3,211,66,62,221,211,
-	66,201,229,213,33,234,149,95,22,0,25,126,
-	254,132,40,4,254,140,32,2,175,119,123,209,
-	225,201,6,8,14,0,31,48,1,12,16,250,
-	121,201,33,4,0,57,94,35,86,33,2,0,
-	57,126,35,102,111,221,229,34,89,152,237,83,
-	91,152,221,33,63,152,205,127,142,58,81,152,
-	50,82,152,58,80,152,135,50,80,152,205,162,
-	140,254,3,56,16,58,81,152,135,60,230,15,
-	50,81,152,175,50,80,152,24,23,58,79,152,
-	205,162,140,254,3,48,13,58,81,152,203,63,
-	50,81,152,62,255,50,79,152,58,81,152,50,
-	82,152,58,79,152,135,50,79,152,62,32,50,
-	83,152,50,84,152,237,56,16,230,17,237,57,
-	16,219,72,62,192,50,93,152,62,93,50,94,
-	152,58,93,152,61,50,93,152,32,9,58,94,
-	152,61,50,94,152,40,44,62,170,237,57,20,
-	175,237,57,21,237,56,16,246,2,237,57,16,
-	219,72,230,1,202,29,141,237,56,20,71,237,
-	56,21,120,254,10,48,237,237,56,16,230,17,
-	237,57,16,243,62,14,211,66,62,65,211,66,
-	251,58,39,152,23,23,60,50,39,152,71,58,
-	82,152,160,230,15,40,22,71,14,10,219,66,
-	230,16,202,186,141,219,72,230,1,202,186,141,
-	13,32,239,16,235,42,89,152,237,91,91,152,
-	205,47,131,48,7,61,202,186,141,195,227,141,
-	221,225,33,0,0,201,221,33,55,152,205,127,
-	142,58,84,152,61,50,84,152,40,19,58,82,
-	152,246,1,50,82,152,58,79,152,246,1,50,
-	79,152,195,29,141,221,225,33,1,0,201,221,
-	33,59,152,205,127,142,58,80,152,246,1,50,
-	80,152,58,82,152,135,246,1,50,82,152,58,
-	83,152,61,50,83,152,194,29,141,221,225,33,
-	2,0,201,221,229,33,0,0,57,17,4,0,
-	25,126,50,44,152,230,128,50,85,152,58,85,
-	152,183,40,6,221,33,88,2,24,4,221,33,
-	150,0,58,44,152,183,40,53,60,40,50,60,
-	40,47,61,61,33,86,152,119,35,119,35,54,
-	129,175,50,48,152,221,43,221,229,225,124,181,
-	40,42,33,86,152,17,3,0,205,189,140,17,
-	232,3,27,123,178,32,251,58,48,152,183,40,
-	224,58,44,152,71,62,7,128,230,127,71,58,
-	85,152,176,50,44,152,24,162,221,225,201,183,
-	221,52,0,192,221,52,1,192,221,52,2,192,
-	221,52,3,192,55,201,245,62,1,211,100,241,
-	201,245,62,1,211,96,241,201,33,2,0,57,
-	126,35,102,111,237,56,48,230,175,237,57,48,
-	62,48,237,57,49,125,237,57,32,124,237,57,
-	33,62,0,237,57,34,62,88,237,57,35,62,
-	0,237,57,36,237,57,37,33,128,2,125,237,
-	57,38,124,237,57,39,237,56,48,246,97,230,
-	207,237,57,48,62,0,237,57,0,62,0,211,
-	96,211,100,201,33,2,0,57,126,35,102,111,
-	237,56,48,230,175,237,57,48,62,12,237,57,
-	49,62,76,237,57,32,62,0,237,57,33,237,
-	57,34,125,237,57,35,124,237,57,36,62,0,
-	237,57,37,33,128,2,125,237,57,38,124,237,
-	57,39,237,56,48,246,97,230,207,237,57,48,
-	62,1,211,96,201,33,2,0,57,126,35,102,
-	111,229,237,56,48,230,87,237,57,48,125,237,
-	57,40,124,237,57,41,62,0,237,57,42,62,
-	67,237,57,43,62,0,237,57,44,58,106,137,
-	254,1,32,5,33,6,0,24,3,33,128,2,
-	125,237,57,46,124,237,57,47,237,56,50,230,
-	252,246,2,237,57,50,225,201,33,4,0,57,
-	94,35,86,33,2,0,57,126,35,102,111,237,
-	56,48,230,87,237,57,48,125,237,57,40,124,
-	237,57,41,62,0,237,57,42,62,67,237,57,
-	43,62,0,237,57,44,123,237,57,46,122,237,
-	57,47,237,56,50,230,244,246,0,237,57,50,
-	237,56,48,246,145,230,207,237,57,48,201,213,
-	237,56,46,95,237,56,47,87,237,56,46,111,
-	237,56,47,103,183,237,82,32,235,33,128,2,
-	183,237,82,209,201,213,237,56,38,95,237,56,
-	39,87,237,56,38,111,237,56,39,103,183,237,
-	82,32,235,33,128,2,183,237,82,209,201,245,
-	197,1,52,0,237,120,230,253,237,121,193,241,
-	201,245,197,1,52,0,237,120,246,2,237,121,
-	193,241,201,33,2,0,57,126,35,102,111,126,
-	35,110,103,201,33,0,0,34,102,152,34,96,
-	152,34,98,152,33,202,154,34,104,152,237,91,
-	104,152,42,226,149,183,237,82,17,0,255,25,
-	34,100,152,203,124,40,6,33,0,125,34,100,
-	152,42,104,152,35,35,35,229,205,120,139,193,
-	201,205,186,149,229,42,40,152,35,35,35,229,
-	205,39,144,193,124,230,3,103,221,117,254,221,
-	116,255,237,91,42,152,35,35,35,183,237,82,
-	32,12,17,5,0,42,42,152,205,171,149,242,
-	169,144,42,40,152,229,205,120,139,193,195,198,
-	149,237,91,42,152,42,98,152,25,34,98,152,
-	19,19,19,42,102,152,25,34,102,152,237,91,
-	100,152,33,158,253,25,237,91,102,152,205,171,
-	149,242,214,144,33,0,0,34,102,152,62,1,
-	50,95,152,205,225,144,195,198,149,58,95,152,
-	183,200,237,91,96,152,42,102,152,205,171,149,
-	242,5,145,237,91,102,152,33,98,2,25,237,
-	91,96,152,205,171,149,250,37,145,237,91,96,
-	152,42,102,152,183,237,82,32,7,42,98,152,
-	125,180,40,13,237,91,102,152,42,96,152,205,
-	171,149,242,58,145,237,91,104,152,42,102,152,
-	25,35,35,35,229,205,120,139,193,175,50,95,
-	152,201,195,107,139,205,206,149,250,255,243,205,
-	225,144,251,58,230,149,183,194,198,149,17,1,
-	0,42,98,152,205,171,149,250,198,149,62,1,
-	50,230,149,237,91,96,152,42,104,152,25,221,
-	117,252,221,116,253,237,91,104,152,42,96,152,
-	25,35,35,35,221,117,254,221,116,255,35,35,
-	35,229,205,39,144,124,230,3,103,35,35,35,
-	221,117,250,221,116,251,235,221,110,252,221,102,
-	253,115,35,114,35,54,4,62,1,211,100,211,
-	84,195,198,149,33,0,0,34,102,152,34,96,
-	152,34,98,152,33,202,154,34,104,152,237,91,
-	104,152,42,226,149,183,237,82,17,0,255,25,
-	34,100,152,33,109,152,54,0,33,107,152,229,
-	205,240,142,193,62,47,50,34,152,62,132,50,
-	49,152,205,241,145,205,61,145,58,39,152,60,
-	50,39,152,24,241,205,206,149,251,255,33,109,
-	152,126,183,202,198,149,110,221,117,251,33,109,
-	152,54,0,221,126,251,254,1,40,28,254,3,
-	40,101,254,4,202,190,147,254,5,202,147,147,
-	254,8,40,87,33,107,152,229,205,240,142,195,
-	198,149,58,201,154,183,32,21,33,111,152,126,
-	50,229,149,205,52,144,33,110,152,110,38,0,
-	229,205,11,142,193,237,91,96,152,42,104,152,
-	25,221,117,254,221,116,255,35,35,54,2,17,
-	2,0,43,43,115,35,114,58,44,152,35,35,
-	119,58,228,149,35,119,62,1,211,100,211,84,
-	62,1,50,201,154,24,169,205,153,142,58,231,
-	149,183,40,250,175,50,231,149,33,110,152,126,
-	254,255,40,91,58,233,149,230,63,183,40,83,
-	94,22,0,33,234,149,25,126,183,40,13,33,
-	110,152,94,33,234,150,25,126,254,3,32,36,
-	205,81,148,125,180,33,110,152,94,22,0,40,
-	17,33,234,149,25,54,0,33,107,152,229,205,
-	240,142,193,195,198,149,33,234,150,25,54,0,
-	33,110,152,94,22,0,33,234,149,25,126,50,
-	49,152,254,132,32,37,62,47,50,34,152,42,
-	107,152,229,33,110,152,229,205,174,140,193,193,
-	125,180,33,110,152,94,22,0,33,234,150,202,
-	117,147,25,52,195,120,147,58,49,152,254,140,
-	32,7,62,1,50,34,152,24,210,62,32,50,
-	106,152,24,19,58,49,152,95,58,106,152,163,
-	183,58,106,152,32,11,203,63,50,106,152,58,
-	106,152,183,32,231,254,2,40,51,254,4,40,
-	38,254,8,40,26,254,16,40,13,254,32,32,
-	158,62,165,50,49,152,62,69,24,190,62,164,
-	50,49,152,62,70,24,181,62,163,50,49,152,
-	175,24,173,62,162,50,49,152,62,1,24,164,
-	62,161,50,49,152,62,3,24,155,25,54,0,
-	221,126,251,254,8,40,7,58,230,149,183,202,
-	32,146,33,107,152,229,205,240,142,193,211,84,
-	195,198,149,237,91,96,152,42,104,152,25,221,
-	117,254,221,116,255,35,35,54,6,17,2,0,
-	43,43,115,35,114,58,228,149,35,35,119,58,
-	233,149,35,119,205,146,142,195,32,146,237,91,
-	96,152,42,104,152,25,229,205,160,142,193,58,
-	231,149,183,40,250,175,50,231,149,243,237,91,
-	96,152,42,104,152,25,221,117,254,221,116,255,
-	78,35,70,221,113,252,221,112,253,89,80,42,
-	98,152,183,237,82,34,98,152,203,124,40,19,
-	33,0,0,34,98,152,34,102,152,34,96,152,
-	62,1,50,95,152,24,40,221,94,252,221,86,
-	253,19,19,19,42,96,152,25,34,96,152,237,
-	91,100,152,33,158,253,25,237,91,96,152,205,
-	171,149,242,55,148,33,0,0,34,96,152,175,
-	50,230,149,251,195,32,146,245,62,1,50,231,
-	149,62,16,237,57,0,211,80,241,251,237,77,
-	201,205,186,149,229,229,33,0,0,34,37,152,
-	33,110,152,126,50,234,151,58,44,152,33,235,
-	151,119,221,54,253,0,221,54,254,0,195,230,
-	148,33,236,151,54,175,33,3,0,229,33,234,
-	151,229,205,174,140,193,193,33,236,151,126,254,
-	255,40,74,33,245,151,110,221,117,255,33,249,
-	151,126,221,166,255,221,119,255,33,253,151,126,
-	221,166,255,221,119,255,58,232,149,95,221,126,
-	255,163,221,119,255,183,40,15,230,191,33,110,
-	152,94,22,0,33,234,149,25,119,24,12,33,
-	110,152,94,22,0,33,234,149,25,54,132,33,
-	0,0,195,198,149,221,110,253,221,102,254,35,
-	221,117,253,221,116,254,17,32,0,221,110,253,
-	221,102,254,205,171,149,250,117,148,58,233,149,
-	203,87,40,84,33,1,0,34,37,152,221,54,
-	253,0,221,54,254,0,24,53,33,236,151,54,
-	175,33,3,0,229,33,234,151,229,205,174,140,
-	193,193,33,236,151,126,254,255,40,14,33,110,
-	152,94,22,0,33,234,149,25,54,140,24,159,
-	221,110,253,221,102,254,35,221,117,253,221,116,
-	254,17,32,0,221,110,253,221,102,254,205,171,
-	149,250,12,149,33,2,0,34,37,152,221,54,
-	253,0,221,54,254,0,24,54,33,236,151,54,
-	175,33,3,0,229,33,234,151,229,205,174,140,
-	193,193,33,236,151,126,254,255,40,15,33,110,
-	152,94,22,0,33,234,149,25,54,132,195,211,
-	148,221,110,253,221,102,254,35,221,117,253,221,
-	116,254,17,32,0,221,110,253,221,102,254,205,
-	171,149,250,96,149,33,1,0,195,198,149,124,
-	170,250,179,149,237,82,201,124,230,128,237,82,
-	60,201,225,253,229,221,229,221,33,0,0,221,
-	57,233,221,249,221,225,253,225,201,233,225,253,
-	229,221,229,221,33,0,0,221,57,94,35,86,
-	35,235,57,249,235,233,0,0,0,0,0,0,
-	62,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	175,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,133,1,0,0,0,63,
-	255,255,255,255,0,0,0,63,0,0,0,0,
-	0,0,0,0,0,0,0,24,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0
-	} ;
-
-#endif
diff --git a/drivers/staging/appletalk/cops_ltdrv.h b/drivers/staging/appletalk/cops_ltdrv.h
deleted file mode 100644
index c699b1ad31da..000000000000
--- a/drivers/staging/appletalk/cops_ltdrv.h
+++ /dev/null
@@ -1,241 +0,0 @@
-/*
- *	The firmware this driver downloads into the Localtalk card is a
- *	separate program and is not GPL'd source code, even though the Linux
- *	side driver and the routine that loads this data into the card are.
- *	
- *	It is taken from the COPS SDK and is under the following license
- *
- *	This material is licensed to you strictly for use in conjunction with
- *	the use of COPS LocalTalk adapters.
- *	There is no charge for this SDK. And no waranty express or implied
- *	about its fitness for any purpose. However, we will cheerefully
- *	refund every penny you paid for this SDK...
- *	Regards,
- *
- *	Thomas F. Divine
- *	Chief Scientist
- */
-
-
-/*      cops_ltdrv.h: LocalTalk driver firmware dump for Linux.
- *
- *      Authors:
- *      - Jay Schulist <jschlst@samba.org>
- */
- 
-
-#ifdef CONFIG_COPS_TANGENT
-
-static const unsigned char ltdrv_code[] = {
-	58,3,0,50,148,10,33,143,15,62,85,119,
-	190,32,9,62,170,119,190,32,3,35,24,241,
-	34,146,10,249,17,150,10,33,143,15,183,237,
-	82,77,68,11,107,98,19,54,0,237,176,62,
-	16,237,57,51,62,0,237,57,50,237,57,54,
-	62,12,237,57,49,62,195,33,39,2,50,56,
-	0,34,57,0,237,86,205,30,2,251,205,60,
-	10,24,169,67,111,112,121,114,105,103,104,116,
-	32,40,99,41,32,49,57,56,56,45,49,57,
-	57,50,44,32,80,114,105,110,116,105,110,103,
-	32,67,111,109,109,117,110,105,99,97,116,105,
-	111,110,115,32,65,115,115,111,99,105,97,116,
-	101,115,44,32,73,110,99,46,65,108,108,32,
-	114,105,103,104,116,115,32,114,101,115,101,114,
-	118,101,100,46,32,32,4,4,22,40,255,60,
-	4,96,10,224,6,0,7,126,2,64,11,246,
-	12,6,13,0,14,193,15,0,5,96,3,192,
-	1,0,9,8,62,3,211,82,62,192,211,82,
-	201,62,3,211,82,62,213,211,82,201,62,5,
-	211,82,62,224,211,82,201,62,5,211,82,62,
-	224,211,82,201,62,5,211,82,62,96,211,82,
-	201,6,28,33,180,1,14,82,237,163,194,4,
-	2,33,39,2,34,64,0,58,3,0,230,1,
-	192,62,11,237,121,62,118,237,121,201,33,182,
-	10,54,132,205,253,1,201,245,197,213,229,42,
-	150,10,14,83,17,98,2,67,20,237,162,58,
-	179,1,95,219,82,230,1,32,6,29,32,247,
-	195,17,3,62,1,211,82,219,82,95,230,160,
-	32,10,237,162,32,225,21,32,222,195,15,3,
-	237,162,123,230,96,194,21,3,62,48,211,82,
-	62,1,211,82,175,211,82,237,91,150,10,43,
-	55,237,82,218,19,3,34,152,10,98,107,58,
-	154,10,190,32,81,62,1,50,158,10,35,35,
-	62,132,190,32,44,54,133,43,70,58,154,10,
-	119,43,112,17,3,0,205,137,3,62,16,211,
-	82,62,56,211,82,205,217,1,42,150,10,14,
-	83,17,98,2,67,20,58,178,1,95,195,59,
-	2,62,129,190,194,227,2,54,130,43,70,58,
-	154,10,119,43,112,17,3,0,205,137,3,195,
-	254,2,35,35,126,254,132,194,227,2,205,61,
-	3,24,20,62,128,166,194,222,2,221,229,221,
-	33,175,10,205,93,6,205,144,7,221,225,225,
-	209,193,241,251,237,77,221,229,221,33,159,10,
-	205,93,6,221,225,205,61,3,195,247,2,24,
-	237,24,235,24,233,230,64,40,2,24,227,24,
-	225,175,50,179,10,205,208,1,201,197,33,4,
-	0,57,126,35,102,111,205,51,3,193,201,62,
-	1,50,179,10,34,150,10,54,0,58,179,10,
-	183,200,62,14,211,82,62,193,211,82,62,10,
-	211,82,62,224,211,82,62,6,211,82,58,154,
-	10,211,82,62,16,211,82,62,56,211,82,62,
-	48,211,82,219,82,230,1,40,4,219,83,24,
-	242,62,14,211,82,62,33,211,82,62,1,211,
-	82,62,9,211,82,62,32,211,82,205,217,1,
-	201,14,83,205,208,1,24,23,14,83,205,208,
-	1,205,226,1,58,174,1,61,32,253,205,244,
-	1,58,174,1,61,32,253,205,226,1,58,175,
-	1,61,32,253,62,5,211,82,62,233,211,82,
-	62,128,211,82,58,176,1,61,32,253,237,163,
-	27,62,192,211,82,219,82,230,4,40,250,237,
-	163,27,122,179,32,243,219,82,230,4,40,250,
-	58,178,1,71,219,82,230,4,40,3,5,32,
-	247,219,82,230,4,40,250,205,235,1,58,177,
-	1,61,32,253,205,244,1,201,229,213,35,35,
-	126,230,128,194,145,4,43,58,154,10,119,43,
-	70,33,181,10,119,43,112,17,3,0,243,62,
-	10,211,82,219,82,230,128,202,41,4,209,225,
-	62,1,55,251,201,205,144,3,58,180,10,254,
-	255,202,127,4,205,217,1,58,178,1,71,219,
-	82,230,1,32,6,5,32,247,195,173,4,219,
-	83,71,58,154,10,184,194,173,4,58,178,1,
-	71,219,82,230,1,32,6,5,32,247,195,173,
-	4,219,83,58,178,1,71,219,82,230,1,32,
-	6,5,32,247,195,173,4,219,83,254,133,194,
-	173,4,58,179,1,24,4,58,179,1,135,61,
-	32,253,209,225,205,137,3,205,61,3,183,251,
-	201,209,225,243,62,10,211,82,219,82,230,128,
-	202,164,4,62,1,55,251,201,205,144,3,205,
-	61,3,183,251,201,209,225,62,2,55,251,201,
-	243,62,14,211,82,62,33,211,82,251,201,33,
-	4,0,57,94,35,86,33,2,0,57,126,35,
-	102,111,221,229,34,193,10,237,83,195,10,221,
-	33,171,10,205,93,6,58,185,10,50,186,10,
-	58,184,10,135,50,184,10,205,112,6,254,3,
-	56,16,58,185,10,135,60,230,15,50,185,10,
-	175,50,184,10,24,23,58,183,10,205,112,6,
-	254,3,48,13,58,185,10,203,63,50,185,10,
-	62,255,50,183,10,58,185,10,50,186,10,58,
-	183,10,135,50,183,10,62,32,50,187,10,50,
-	188,10,6,255,219,82,230,16,32,3,5,32,
-	247,205,180,4,6,40,219,82,230,16,40,3,
-	5,32,247,62,10,211,82,219,82,230,128,194,
-	46,5,219,82,230,16,40,214,237,95,71,58,
-	186,10,160,230,15,40,32,71,14,10,62,10,
-	211,82,219,82,230,128,202,119,5,205,180,4,
-	195,156,5,219,82,230,16,202,156,5,13,32,
-	229,16,225,42,193,10,237,91,195,10,205,252,
-	3,48,7,61,202,156,5,195,197,5,221,225,
-	33,0,0,201,221,33,163,10,205,93,6,58,
-	188,10,61,50,188,10,40,19,58,186,10,246,
-	1,50,186,10,58,183,10,246,1,50,183,10,
-	195,46,5,221,225,33,1,0,201,221,33,167,
-	10,205,93,6,58,184,10,246,1,50,184,10,
-	58,186,10,135,246,1,50,186,10,58,187,10,
-	61,50,187,10,194,46,5,221,225,33,2,0,
-	201,221,229,33,0,0,57,17,4,0,25,126,
-	50,154,10,230,128,50,189,10,58,189,10,183,
-	40,6,221,33,88,2,24,4,221,33,150,0,
-	58,154,10,183,40,49,60,40,46,61,33,190,
-	10,119,35,119,35,54,129,175,50,158,10,221,
-	43,221,229,225,124,181,40,42,33,190,10,17,
-	3,0,205,206,4,17,232,3,27,123,178,32,
-	251,58,158,10,183,40,224,58,154,10,71,62,
-	7,128,230,127,71,58,189,10,176,50,154,10,
-	24,166,221,225,201,183,221,52,0,192,221,52,
-	1,192,221,52,2,192,221,52,3,192,55,201,
-	6,8,14,0,31,48,1,12,16,250,121,201,
-	33,2,0,57,94,35,86,35,78,35,70,35,
-	126,35,102,105,79,120,68,103,237,176,201,33,
-	2,0,57,126,35,102,111,62,17,237,57,48,
-	125,237,57,40,124,237,57,41,62,0,237,57,
-	42,62,64,237,57,43,62,0,237,57,44,33,
-	128,2,125,237,57,46,124,237,57,47,62,145,
-	237,57,48,211,68,58,149,10,211,66,201,33,
-	2,0,57,126,35,102,111,62,33,237,57,48,
-	62,64,237,57,32,62,0,237,57,33,237,57,
-	34,125,237,57,35,124,237,57,36,62,0,237,
-	57,37,33,128,2,125,237,57,38,124,237,57,
-	39,62,97,237,57,48,211,67,58,149,10,211,
-	66,201,237,56,46,95,237,56,47,87,237,56,
-	46,111,237,56,47,103,183,237,82,32,235,33,
-	128,2,183,237,82,201,237,56,38,95,237,56,
-	39,87,237,56,38,111,237,56,39,103,183,237,
-	82,32,235,33,128,2,183,237,82,201,205,106,
-	10,221,110,6,221,102,7,126,35,110,103,195,
-	118,10,205,106,10,33,0,0,34,205,10,34,
-	198,10,34,200,10,33,143,15,34,207,10,237,
-	91,207,10,42,146,10,183,237,82,17,0,255,
-	25,34,203,10,203,124,40,6,33,0,125,34,
-	203,10,42,207,10,229,205,37,3,195,118,10,
-	205,106,10,229,42,150,10,35,35,35,229,205,
-	70,7,193,124,230,3,103,221,117,254,221,116,
-	255,237,91,152,10,35,35,35,183,237,82,32,
-	12,17,5,0,42,152,10,205,91,10,242,203,
-	7,42,150,10,229,205,37,3,195,118,10,237,
-	91,152,10,42,200,10,25,34,200,10,42,205,
-	10,25,34,205,10,237,91,203,10,33,158,253,
-	25,237,91,205,10,205,91,10,242,245,7,33,
-	0,0,34,205,10,62,1,50,197,10,205,5,
-	8,33,0,0,57,249,195,118,10,205,106,10,
-	58,197,10,183,202,118,10,237,91,198,10,42,
-	205,10,205,91,10,242,46,8,237,91,205,10,
-	33,98,2,25,237,91,198,10,205,91,10,250,
-	78,8,237,91,198,10,42,205,10,183,237,82,
-	32,7,42,200,10,125,180,40,13,237,91,205,
-	10,42,198,10,205,91,10,242,97,8,237,91,
-	207,10,42,205,10,25,229,205,37,3,175,50,
-	197,10,195,118,10,205,29,3,33,0,0,57,
-	249,195,118,10,205,106,10,58,202,10,183,40,
-	22,205,14,7,237,91,209,10,19,19,19,205,
-	91,10,242,139,8,33,1,0,195,118,10,33,
-	0,0,195,118,10,205,126,10,252,255,205,108,
-	8,125,180,194,118,10,237,91,200,10,33,0,
-	0,205,91,10,242,118,10,237,91,207,10,42,
-	198,10,25,221,117,254,221,116,255,35,35,35,
-	229,205,70,7,193,124,230,3,103,35,35,35,
-	221,117,252,221,116,253,229,221,110,254,221,102,
-	255,229,33,212,10,229,205,124,6,193,193,221,
-	110,252,221,102,253,34,209,10,33,211,10,54,
-	4,33,209,10,227,205,147,6,193,62,1,50,
-	202,10,243,221,94,252,221,86,253,42,200,10,
-	183,237,82,34,200,10,203,124,40,17,33,0,
-	0,34,200,10,34,205,10,34,198,10,50,197,
-	10,24,37,221,94,252,221,86,253,42,198,10,
-	25,34,198,10,237,91,203,10,33,158,253,25,
-	237,91,198,10,205,91,10,242,68,9,33,0,
-	0,34,198,10,205,5,8,33,0,0,57,249,
-	251,195,118,10,205,106,10,33,49,13,126,183,
-	40,16,205,42,7,237,91,47,13,19,19,19,
-	205,91,10,242,117,9,58,142,15,198,1,50,
-	142,15,195,118,10,33,49,13,126,254,1,40,
-	25,254,3,202,7,10,254,5,202,21,10,33,
-	49,13,54,0,33,47,13,229,205,207,6,195,
-	118,10,58,141,15,183,32,72,33,51,13,126,
-	50,149,10,205,86,7,33,50,13,126,230,127,
-	183,32,40,58,142,15,230,127,50,142,15,183,
-	32,5,198,1,50,142,15,33,50,13,126,111,
-	23,159,103,203,125,58,142,15,40,5,198,128,
-	50,142,15,33,50,13,119,33,50,13,126,111,
-	23,159,103,229,205,237,5,193,33,211,10,54,
-	2,33,2,0,34,209,10,58,154,10,33,212,
-	10,119,58,148,10,33,213,10,119,33,209,10,
-	229,205,147,6,193,24,128,42,47,13,229,33,
-	50,13,229,205,191,4,193,24,239,33,211,10,
-	54,6,33,3,0,34,209,10,58,154,10,33,
-	212,10,119,58,148,10,33,213,10,119,33,214,
-	10,54,5,33,209,10,229,205,147,6,24,200,
-	205,106,10,33,49,13,54,0,33,47,13,229,
-	205,207,6,33,209,10,227,205,147,6,193,205,
-	80,9,205,145,8,24,248,124,170,250,99,10,
-	237,82,201,124,230,128,237,82,60,201,225,253,
-	229,221,229,221,33,0,0,221,57,233,221,249,
-	221,225,253,225,201,233,225,253,229,221,229,221,
-	33,0,0,221,57,94,35,86,35,235,57,249,
-	235,233,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0,0,0,0,0,0,0,0,
-	0,0,0,0,0
-	} ;
-
-#endif
diff --git a/drivers/staging/appletalk/ddp.c b/drivers/staging/appletalk/ddp.c
deleted file mode 100644
index 940dd1908339..000000000000
--- a/drivers/staging/appletalk/ddp.c
+++ /dev/null
@@ -1,1981 +0,0 @@
-/*
- *	DDP:	An implementation of the AppleTalk DDP protocol for
- *		Ethernet 'ELAP'.
- *
- *		Alan Cox  <alan@lxorguk.ukuu.org.uk>
- *
- *		With more than a little assistance from
- *
- *		Wesley Craig <netatalk@umich.edu>
- *
- *	Fixes:
- *		Neil Horman		:	Added missing device ioctls
- *		Michael Callahan	:	Made routing work
- *		Wesley Craig		:	Fix probing to listen to a
- *						passed node id.
- *		Alan Cox		:	Added send/recvmsg support
- *		Alan Cox		:	Moved at. to protinfo in
- *						socket.
- *		Alan Cox		:	Added firewall hooks.
- *		Alan Cox		:	Supports new ARPHRD_LOOPBACK
- *		Christer Weinigel	: 	Routing and /proc fixes.
- *		Bradford Johnson	:	LocalTalk.
- *		Tom Dyas		:	Module support.
- *		Alan Cox		:	Hooks for PPP (based on the
- *						LocalTalk hook).
- *		Alan Cox		:	Posix bits
- *		Alan Cox/Mike Freeman	:	Possible fix to NBP problems
- *		Bradford Johnson	:	IP-over-DDP (experimental)
- *		Jay Schulist		:	Moved IP-over-DDP to its own
- *						driver file. (ipddp.c & ipddp.h)
- *		Jay Schulist		:	Made work as module with
- *						AppleTalk drivers, cleaned it.
- *		Rob Newberry		:	Added proxy AARP and AARP
- *						procfs, moved probing to AARP
- *						module.
- *              Adrian Sun/
- *              Michael Zuelsdorff      :       fix for net.0 packets. don't
- *                                              allow illegal ether/tokentalk
- *                                              port assignment. we lose a
- *                                              valid localtalk port as a
- *                                              result.
- *		Arnaldo C. de Melo	:	Cleanup, in preparation for
- *						shared skb support 8)
- *		Arnaldo C. de Melo	:	Move proc stuff to atalk_proc.c,
- *						use seq_file
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/capability.h>
-#include <linux/module.h>
-#include <linux/if_arp.h>
-#include <linux/smp_lock.h>
-#include <linux/termios.h>	/* For TIOCOUTQ/INQ */
-#include <linux/compat.h>
-#include <linux/slab.h>
-#include <net/datalink.h>
-#include <net/psnap.h>
-#include <net/sock.h>
-#include <net/tcp_states.h>
-#include <net/route.h>
-#include "atalk.h"
-#include "../../net/core/kmap_skb.h"
-
-struct datalink_proto *ddp_dl, *aarp_dl;
-static const struct proto_ops atalk_dgram_ops;
-
-/**************************************************************************\
-*                                                                          *
-* Handlers for the socket list.                                            *
-*                                                                          *
-\**************************************************************************/
-
-HLIST_HEAD(atalk_sockets);
-DEFINE_RWLOCK(atalk_sockets_lock);
-
-static inline void __atalk_insert_socket(struct sock *sk)
-{
-	sk_add_node(sk, &atalk_sockets);
-}
-
-static inline void atalk_remove_socket(struct sock *sk)
-{
-	write_lock_bh(&atalk_sockets_lock);
-	sk_del_node_init(sk);
-	write_unlock_bh(&atalk_sockets_lock);
-}
-
-static struct sock *atalk_search_socket(struct sockaddr_at *to,
-					struct atalk_iface *atif)
-{
-	struct sock *s;
-	struct hlist_node *node;
-
-	read_lock_bh(&atalk_sockets_lock);
-	sk_for_each(s, node, &atalk_sockets) {
-		struct atalk_sock *at = at_sk(s);
-
-		if (to->sat_port != at->src_port)
-			continue;
-
-		if (to->sat_addr.s_net == ATADDR_ANYNET &&
-		    to->sat_addr.s_node == ATADDR_BCAST)
-			goto found;
-
-		if (to->sat_addr.s_net == at->src_net &&
-		    (to->sat_addr.s_node == at->src_node ||
-		     to->sat_addr.s_node == ATADDR_BCAST ||
-		     to->sat_addr.s_node == ATADDR_ANYNODE))
-			goto found;
-
-		/* XXXX.0 -- we got a request for this router. make sure
-		 * that the node is appropriately set. */
-		if (to->sat_addr.s_node == ATADDR_ANYNODE &&
-		    to->sat_addr.s_net != ATADDR_ANYNET &&
-		    atif->address.s_node == at->src_node) {
-			to->sat_addr.s_node = atif->address.s_node;
-			goto found;
-		}
-	}
-	s = NULL;
-found:
-	read_unlock_bh(&atalk_sockets_lock);
-	return s;
-}
-
-/**
- * atalk_find_or_insert_socket - Try to find a socket matching ADDR
- * @sk - socket to insert in the list if it is not there already
- * @sat - address to search for
- *
- * Try to find a socket matching ADDR in the socket list, if found then return
- * it. If not, insert SK into the socket list.
- *
- * This entire operation must execute atomically.
- */
-static struct sock *atalk_find_or_insert_socket(struct sock *sk,
-						struct sockaddr_at *sat)
-{
-	struct sock *s;
-	struct hlist_node *node;
-	struct atalk_sock *at;
-
-	write_lock_bh(&atalk_sockets_lock);
-	sk_for_each(s, node, &atalk_sockets) {
-		at = at_sk(s);
-
-		if (at->src_net == sat->sat_addr.s_net &&
-		    at->src_node == sat->sat_addr.s_node &&
-		    at->src_port == sat->sat_port)
-			goto found;
-	}
-	s = NULL;
-	__atalk_insert_socket(sk); /* Wheee, it's free, assign and insert. */
-found:
-	write_unlock_bh(&atalk_sockets_lock);
-	return s;
-}
-
-static void atalk_destroy_timer(unsigned long data)
-{
-	struct sock *sk = (struct sock *)data;
-
-	if (sk_has_allocations(sk)) {
-		sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME;
-		add_timer(&sk->sk_timer);
-	} else
-		sock_put(sk);
-}
-
-static inline void atalk_destroy_socket(struct sock *sk)
-{
-	atalk_remove_socket(sk);
-	skb_queue_purge(&sk->sk_receive_queue);
-
-	if (sk_has_allocations(sk)) {
-		setup_timer(&sk->sk_timer, atalk_destroy_timer,
-				(unsigned long)sk);
-		sk->sk_timer.expires	= jiffies + SOCK_DESTROY_TIME;
-		add_timer(&sk->sk_timer);
-	} else
-		sock_put(sk);
-}
-
-/**************************************************************************\
-*                                                                          *
-* Routing tables for the AppleTalk socket layer.                           *
-*                                                                          *
-\**************************************************************************/
-
-/* Anti-deadlock ordering is atalk_routes_lock --> iface_lock -DaveM */
-struct atalk_route *atalk_routes;
-DEFINE_RWLOCK(atalk_routes_lock);
-
-struct atalk_iface *atalk_interfaces;
-DEFINE_RWLOCK(atalk_interfaces_lock);
-
-/* For probing devices or in a routerless network */
-struct atalk_route atrtr_default;
-
-/* AppleTalk interface control */
-/*
- * Drop a device. Doesn't drop any of its routes - that is the caller's
- * problem. Called when we down the interface or delete the address.
- */
-static void atif_drop_device(struct net_device *dev)
-{
-	struct atalk_iface **iface = &atalk_interfaces;
-	struct atalk_iface *tmp;
-
-	write_lock_bh(&atalk_interfaces_lock);
-	while ((tmp = *iface) != NULL) {
-		if (tmp->dev == dev) {
-			*iface = tmp->next;
-			dev_put(dev);
-			kfree(tmp);
-			dev->atalk_ptr = NULL;
-		} else
-			iface = &tmp->next;
-	}
-	write_unlock_bh(&atalk_interfaces_lock);
-}
-
-static struct atalk_iface *atif_add_device(struct net_device *dev,
-					   struct atalk_addr *sa)
-{
-	struct atalk_iface *iface = kzalloc(sizeof(*iface), GFP_KERNEL);
-
-	if (!iface)
-		goto out;
-
-	dev_hold(dev);
-	iface->dev = dev;
-	dev->atalk_ptr = iface;
-	iface->address = *sa;
-	iface->status = 0;
-
-	write_lock_bh(&atalk_interfaces_lock);
-	iface->next = atalk_interfaces;
-	atalk_interfaces = iface;
-	write_unlock_bh(&atalk_interfaces_lock);
-out:
-	return iface;
-}
-
-/* Perform phase 2 AARP probing on our tentative address */
-static int atif_probe_device(struct atalk_iface *atif)
-{
-	int netrange = ntohs(atif->nets.nr_lastnet) -
-			ntohs(atif->nets.nr_firstnet) + 1;
-	int probe_net = ntohs(atif->address.s_net);
-	int probe_node = atif->address.s_node;
-	int netct, nodect;
-
-	/* Offset the network we start probing with */
-	if (probe_net == ATADDR_ANYNET) {
-		probe_net = ntohs(atif->nets.nr_firstnet);
-		if (netrange)
-			probe_net += jiffies % netrange;
-	}
-	if (probe_node == ATADDR_ANYNODE)
-		probe_node = jiffies & 0xFF;
-
-	/* Scan the networks */
-	atif->status |= ATIF_PROBE;
-	for (netct = 0; netct <= netrange; netct++) {
-		/* Sweep the available nodes from a given start */
-		atif->address.s_net = htons(probe_net);
-		for (nodect = 0; nodect < 256; nodect++) {
-			atif->address.s_node = (nodect + probe_node) & 0xFF;
-			if (atif->address.s_node > 0 &&
-			    atif->address.s_node < 254) {
-				/* Probe a proposed address */
-				aarp_probe_network(atif);
-
-				if (!(atif->status & ATIF_PROBE_FAIL)) {
-					atif->status &= ~ATIF_PROBE;
-					return 0;
-				}
-			}
-			atif->status &= ~ATIF_PROBE_FAIL;
-		}
-		probe_net++;
-		if (probe_net > ntohs(atif->nets.nr_lastnet))
-			probe_net = ntohs(atif->nets.nr_firstnet);
-	}
-	atif->status &= ~ATIF_PROBE;
-
-	return -EADDRINUSE;	/* Network is full... */
-}
-
-
-/* Perform AARP probing for a proxy address */
-static int atif_proxy_probe_device(struct atalk_iface *atif,
-				   struct atalk_addr* proxy_addr)
-{
-	int netrange = ntohs(atif->nets.nr_lastnet) -
-			ntohs(atif->nets.nr_firstnet) + 1;
-	/* we probe the interface's network */
-	int probe_net = ntohs(atif->address.s_net);
-	int probe_node = ATADDR_ANYNODE;	    /* we'll take anything */
-	int netct, nodect;
-
-	/* Offset the network we start probing with */
-	if (probe_net == ATADDR_ANYNET) {
-		probe_net = ntohs(atif->nets.nr_firstnet);
-		if (netrange)
-			probe_net += jiffies % netrange;
-	}
-
-	if (probe_node == ATADDR_ANYNODE)
-		probe_node = jiffies & 0xFF;
-
-	/* Scan the networks */
-	for (netct = 0; netct <= netrange; netct++) {
-		/* Sweep the available nodes from a given start */
-		proxy_addr->s_net = htons(probe_net);
-		for (nodect = 0; nodect < 256; nodect++) {
-			proxy_addr->s_node = (nodect + probe_node) & 0xFF;
-			if (proxy_addr->s_node > 0 &&
-			    proxy_addr->s_node < 254) {
-				/* Tell AARP to probe a proposed address */
-				int ret = aarp_proxy_probe_network(atif,
-								    proxy_addr);
-
-				if (ret != -EADDRINUSE)
-					return ret;
-			}
-		}
-		probe_net++;
-		if (probe_net > ntohs(atif->nets.nr_lastnet))
-			probe_net = ntohs(atif->nets.nr_firstnet);
-	}
-
-	return -EADDRINUSE;	/* Network is full... */
-}
-
-
-struct atalk_addr *atalk_find_dev_addr(struct net_device *dev)
-{
-	struct atalk_iface *iface = dev->atalk_ptr;
-	return iface ? &iface->address : NULL;
-}
-
-static struct atalk_addr *atalk_find_primary(void)
-{
-	struct atalk_iface *fiface = NULL;
-	struct atalk_addr *retval;
-	struct atalk_iface *iface;
-
-	/*
-	 * Return a point-to-point interface only if
-	 * there is no non-ptp interface available.
-	 */
-	read_lock_bh(&atalk_interfaces_lock);
-	for (iface = atalk_interfaces; iface; iface = iface->next) {
-		if (!fiface && !(iface->dev->flags & IFF_LOOPBACK))
-			fiface = iface;
-		if (!(iface->dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))) {
-			retval = &iface->address;
-			goto out;
-		}
-	}
-
-	if (fiface)
-		retval = &fiface->address;
-	else if (atalk_interfaces)
-		retval = &atalk_interfaces->address;
-	else
-		retval = NULL;
-out:
-	read_unlock_bh(&atalk_interfaces_lock);
-	return retval;
-}
-
-/*
- * Find a match for 'any network' - ie any of our interfaces with that
- * node number will do just nicely.
- */
-static struct atalk_iface *atalk_find_anynet(int node, struct net_device *dev)
-{
-	struct atalk_iface *iface = dev->atalk_ptr;
-
-	if (!iface || iface->status & ATIF_PROBE)
-		goto out_err;
-
-	if (node != ATADDR_BCAST &&
-	    iface->address.s_node != node &&
-	    node != ATADDR_ANYNODE)
-		goto out_err;
-out:
-	return iface;
-out_err:
-	iface = NULL;
-	goto out;
-}
-
-/* Find a match for a specific network:node pair */
-static struct atalk_iface *atalk_find_interface(__be16 net, int node)
-{
-	struct atalk_iface *iface;
-
-	read_lock_bh(&atalk_interfaces_lock);
-	for (iface = atalk_interfaces; iface; iface = iface->next) {
-		if ((node == ATADDR_BCAST ||
-		     node == ATADDR_ANYNODE ||
-		     iface->address.s_node == node) &&
-		    iface->address.s_net == net &&
-		    !(iface->status & ATIF_PROBE))
-			break;
-
-		/* XXXX.0 -- net.0 returns the iface associated with net */
-		if (node == ATADDR_ANYNODE && net != ATADDR_ANYNET &&
-		    ntohs(iface->nets.nr_firstnet) <= ntohs(net) &&
-		    ntohs(net) <= ntohs(iface->nets.nr_lastnet))
-			break;
-	}
-	read_unlock_bh(&atalk_interfaces_lock);
-	return iface;
-}
-
-
-/*
- * Find a route for an AppleTalk packet. This ought to get cached in
- * the socket (later on...). We know about host routes and the fact
- * that a route must be direct to broadcast.
- */
-static struct atalk_route *atrtr_find(struct atalk_addr *target)
-{
-	/*
-	 * we must search through all routes unless we find a
-	 * host route, because some host routes might overlap
-	 * network routes
-	 */
-	struct atalk_route *net_route = NULL;
-	struct atalk_route *r;
-
-	read_lock_bh(&atalk_routes_lock);
-	for (r = atalk_routes; r; r = r->next) {
-		if (!(r->flags & RTF_UP))
-			continue;
-
-		if (r->target.s_net == target->s_net) {
-			if (r->flags & RTF_HOST) {
-				/*
-				 * if this host route is for the target,
-				 * the we're done
-				 */
-				if (r->target.s_node == target->s_node)
-					goto out;
-			} else
-				/*
-				 * this route will work if there isn't a
-				 * direct host route, so cache it
-				 */
-				net_route = r;
-		}
-	}
-
-	/*
-	 * if we found a network route but not a direct host
-	 * route, then return it
-	 */
-	if (net_route)
-		r = net_route;
-	else if (atrtr_default.dev)
-		r = &atrtr_default;
-	else /* No route can be found */
-		r = NULL;
-out:
-	read_unlock_bh(&atalk_routes_lock);
-	return r;
-}
-
-
-/*
- * Given an AppleTalk network, find the device to use. This can be
- * a simple lookup.
- */
-struct net_device *atrtr_get_dev(struct atalk_addr *sa)
-{
-	struct atalk_route *atr = atrtr_find(sa);
-	return atr ? atr->dev : NULL;
-}
-
-/* Set up a default router */
-static void atrtr_set_default(struct net_device *dev)
-{
-	atrtr_default.dev	     = dev;
-	atrtr_default.flags	     = RTF_UP;
-	atrtr_default.gateway.s_net  = htons(0);
-	atrtr_default.gateway.s_node = 0;
-}
-
-/*
- * Add a router. Basically make sure it looks valid and stuff the
- * entry in the list. While it uses netranges we always set them to one
- * entry to work like netatalk.
- */
-static int atrtr_create(struct rtentry *r, struct net_device *devhint)
-{
-	struct sockaddr_at *ta = (struct sockaddr_at *)&r->rt_dst;
-	struct sockaddr_at *ga = (struct sockaddr_at *)&r->rt_gateway;
-	struct atalk_route *rt;
-	struct atalk_iface *iface, *riface;
-	int retval = -EINVAL;
-
-	/*
-	 * Fixme: Raise/Lower a routing change semaphore for these
-	 * operations.
-	 */
-
-	/* Validate the request */
-	if (ta->sat_family != AF_APPLETALK ||
-	    (!devhint && ga->sat_family != AF_APPLETALK))
-		goto out;
-
-	/* Now walk the routing table and make our decisions */
-	write_lock_bh(&atalk_routes_lock);
-	for (rt = atalk_routes; rt; rt = rt->next) {
-		if (r->rt_flags != rt->flags)
-			continue;
-
-		if (ta->sat_addr.s_net == rt->target.s_net) {
-			if (!(rt->flags & RTF_HOST))
-				break;
-			if (ta->sat_addr.s_node == rt->target.s_node)
-				break;
-		}
-	}
-
-	if (!devhint) {
-		riface = NULL;
-
-		read_lock_bh(&atalk_interfaces_lock);
-		for (iface = atalk_interfaces; iface; iface = iface->next) {
-			if (!riface &&
-			    ntohs(ga->sat_addr.s_net) >=
-					ntohs(iface->nets.nr_firstnet) &&
-			    ntohs(ga->sat_addr.s_net) <=
-					ntohs(iface->nets.nr_lastnet))
-				riface = iface;
-
-			if (ga->sat_addr.s_net == iface->address.s_net &&
-			    ga->sat_addr.s_node == iface->address.s_node)
-				riface = iface;
-		}
-		read_unlock_bh(&atalk_interfaces_lock);
-
-		retval = -ENETUNREACH;
-		if (!riface)
-			goto out_unlock;
-
-		devhint = riface->dev;
-	}
-
-	if (!rt) {
-		rt = kzalloc(sizeof(*rt), GFP_ATOMIC);
-
-		retval = -ENOBUFS;
-		if (!rt)
-			goto out_unlock;
-
-		rt->next = atalk_routes;
-		atalk_routes = rt;
-	}
-
-	/* Fill in the routing entry */
-	rt->target  = ta->sat_addr;
-	dev_hold(devhint);
-	rt->dev     = devhint;
-	rt->flags   = r->rt_flags;
-	rt->gateway = ga->sat_addr;
-
-	retval = 0;
-out_unlock:
-	write_unlock_bh(&atalk_routes_lock);
-out:
-	return retval;
-}
-
-/* Delete a route. Find it and discard it */
-static int atrtr_delete(struct atalk_addr * addr)
-{
-	struct atalk_route **r = &atalk_routes;
-	int retval = 0;
-	struct atalk_route *tmp;
-
-	write_lock_bh(&atalk_routes_lock);
-	while ((tmp = *r) != NULL) {
-		if (tmp->target.s_net == addr->s_net &&
-		    (!(tmp->flags&RTF_GATEWAY) ||
-		     tmp->target.s_node == addr->s_node)) {
-			*r = tmp->next;
-			dev_put(tmp->dev);
-			kfree(tmp);
-			goto out;
-		}
-		r = &tmp->next;
-	}
-	retval = -ENOENT;
-out:
-	write_unlock_bh(&atalk_routes_lock);
-	return retval;
-}
-
-/*
- * Called when a device is downed. Just throw away any routes
- * via it.
- */
-static void atrtr_device_down(struct net_device *dev)
-{
-	struct atalk_route **r = &atalk_routes;
-	struct atalk_route *tmp;
-
-	write_lock_bh(&atalk_routes_lock);
-	while ((tmp = *r) != NULL) {
-		if (tmp->dev == dev) {
-			*r = tmp->next;
-			dev_put(dev);
-			kfree(tmp);
-		} else
-			r = &tmp->next;
-	}
-	write_unlock_bh(&atalk_routes_lock);
-
-	if (atrtr_default.dev == dev)
-		atrtr_set_default(NULL);
-}
-
-/* Actually down the interface */
-static inline void atalk_dev_down(struct net_device *dev)
-{
-	atrtr_device_down(dev);	/* Remove all routes for the device */
-	aarp_device_down(dev);	/* Remove AARP entries for the device */
-	atif_drop_device(dev);	/* Remove the device */
-}
-
-/*
- * A device event has occurred. Watch for devices going down and
- * delete our use of them (iface and route).
- */
-static int ddp_device_event(struct notifier_block *this, unsigned long event,
-			    void *ptr)
-{
-	struct net_device *dev = ptr;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
-	if (event == NETDEV_DOWN)
-		/* Discard any use of this */
-		atalk_dev_down(dev);
-
-	return NOTIFY_DONE;
-}
-
-/* ioctl calls. Shouldn't even need touching */
-/* Device configuration ioctl calls */
-static int atif_ioctl(int cmd, void __user *arg)
-{
-	static char aarp_mcast[6] = { 0x09, 0x00, 0x00, 0xFF, 0xFF, 0xFF };
-	struct ifreq atreq;
-	struct atalk_netrange *nr;
-	struct sockaddr_at *sa;
-	struct net_device *dev;
-	struct atalk_iface *atif;
-	int ct;
-	int limit;
-	struct rtentry rtdef;
-	int add_route;
-
-	if (copy_from_user(&atreq, arg, sizeof(atreq)))
-		return -EFAULT;
-
-	dev = __dev_get_by_name(&init_net, atreq.ifr_name);
-	if (!dev)
-		return -ENODEV;
-
-	sa = (struct sockaddr_at *)&atreq.ifr_addr;
-	atif = atalk_find_dev(dev);
-
-	switch (cmd) {
-		case SIOCSIFADDR:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			if (dev->type != ARPHRD_ETHER &&
-			    dev->type != ARPHRD_LOOPBACK &&
-			    dev->type != ARPHRD_LOCALTLK &&
-			    dev->type != ARPHRD_PPP)
-				return -EPROTONOSUPPORT;
-
-			nr = (struct atalk_netrange *)&sa->sat_zero[0];
-			add_route = 1;
-
-			/*
-			 * if this is a point-to-point iface, and we already
-			 * have an iface for this AppleTalk address, then we
-			 * should not add a route
-			 */
-			if ((dev->flags & IFF_POINTOPOINT) &&
-			    atalk_find_interface(sa->sat_addr.s_net,
-						 sa->sat_addr.s_node)) {
-				printk(KERN_DEBUG "AppleTalk: point-to-point "
-						  "interface added with "
-						  "existing address\n");
-				add_route = 0;
-			}
-
-			/*
-			 * Phase 1 is fine on LocalTalk but we don't do
-			 * EtherTalk phase 1. Anyone wanting to add it go ahead.
-			 */
-			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
-				return -EPROTONOSUPPORT;
-			if (sa->sat_addr.s_node == ATADDR_BCAST ||
-			    sa->sat_addr.s_node == 254)
-				return -EINVAL;
-			if (atif) {
-				/* Already setting address */
-				if (atif->status & ATIF_PROBE)
-					return -EBUSY;
-
-				atif->address.s_net  = sa->sat_addr.s_net;
-				atif->address.s_node = sa->sat_addr.s_node;
-				atrtr_device_down(dev);	/* Flush old routes */
-			} else {
-				atif = atif_add_device(dev, &sa->sat_addr);
-				if (!atif)
-					return -ENOMEM;
-			}
-			atif->nets = *nr;
-
-			/*
-			 * Check if the chosen address is used. If so we
-			 * error and atalkd will try another.
-			 */
-
-			if (!(dev->flags & IFF_LOOPBACK) &&
-			    !(dev->flags & IFF_POINTOPOINT) &&
-			    atif_probe_device(atif) < 0) {
-				atif_drop_device(dev);
-				return -EADDRINUSE;
-			}
-
-			/* Hey it worked - add the direct routes */
-			sa = (struct sockaddr_at *)&rtdef.rt_gateway;
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_net  = atif->address.s_net;
-			sa->sat_addr.s_node = atif->address.s_node;
-			sa = (struct sockaddr_at *)&rtdef.rt_dst;
-			rtdef.rt_flags = RTF_UP;
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_node = ATADDR_ANYNODE;
-			if (dev->flags & IFF_LOOPBACK ||
-			    dev->flags & IFF_POINTOPOINT)
-				rtdef.rt_flags |= RTF_HOST;
-
-			/* Routerless initial state */
-			if (nr->nr_firstnet == htons(0) &&
-			    nr->nr_lastnet == htons(0xFFFE)) {
-				sa->sat_addr.s_net = atif->address.s_net;
-				atrtr_create(&rtdef, dev);
-				atrtr_set_default(dev);
-			} else {
-				limit = ntohs(nr->nr_lastnet);
-				if (limit - ntohs(nr->nr_firstnet) > 4096) {
-					printk(KERN_WARNING "Too many routes/"
-							    "iface.\n");
-					return -EINVAL;
-				}
-				if (add_route)
-					for (ct = ntohs(nr->nr_firstnet);
-					     ct <= limit; ct++) {
-						sa->sat_addr.s_net = htons(ct);
-						atrtr_create(&rtdef, dev);
-					}
-			}
-			dev_mc_add_global(dev, aarp_mcast);
-			return 0;
-
-		case SIOCGIFADDR:
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr = atif->address;
-			break;
-
-		case SIOCGIFBRDADDR:
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			sa->sat_family = AF_APPLETALK;
-			sa->sat_addr.s_net = atif->address.s_net;
-			sa->sat_addr.s_node = ATADDR_BCAST;
-			break;
-
-		case SIOCATALKDIFADDR:
-		case SIOCDIFADDR:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			atalk_dev_down(dev);
-			break;
-
-		case SIOCSARP:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			/*
-			 * for now, we only support proxy AARP on ELAP;
-			 * we should be able to do it for LocalTalk, too.
-			 */
-			if (dev->type != ARPHRD_ETHER)
-				return -EPROTONOSUPPORT;
-
-			/*
-			 * atif points to the current interface on this network;
-			 * we aren't concerned about its current status (at
-			 * least for now), but it has all the settings about
-			 * the network we're going to probe. Consequently, it
-			 * must exist.
-			 */
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			nr = (struct atalk_netrange *)&(atif->nets);
-			/*
-			 * Phase 1 is fine on Localtalk but we don't do
-			 * Ethertalk phase 1. Anyone wanting to add it go ahead.
-			 */
-			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
-				return -EPROTONOSUPPORT;
-
-			if (sa->sat_addr.s_node == ATADDR_BCAST ||
-			    sa->sat_addr.s_node == 254)
-				return -EINVAL;
-
-			/*
-			 * Check if the chosen address is used. If so we
-			 * error and ATCP will try another.
-			 */
-			if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0)
-				return -EADDRINUSE;
-
-			/*
-			 * We now have an address on the local network, and
-			 * the AARP code will defend it for us until we take it
-			 * down. We don't set up any routes right now, because
-			 * ATCP will install them manually via SIOCADDRT.
-			 */
-			break;
-
-		case SIOCDARP:
-			if (!capable(CAP_NET_ADMIN))
-				return -EPERM;
-			if (sa->sat_family != AF_APPLETALK)
-				return -EINVAL;
-			if (!atif)
-				return -EADDRNOTAVAIL;
-
-			/* give to aarp module to remove proxy entry */
-			aarp_proxy_remove(atif->dev, &(sa->sat_addr));
-			return 0;
-	}
-
-	return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0;
-}
-
-/* Routing ioctl() calls */
-static int atrtr_ioctl(unsigned int cmd, void __user *arg)
-{
-	struct rtentry rt;
-
-	if (copy_from_user(&rt, arg, sizeof(rt)))
-		return -EFAULT;
-
-	switch (cmd) {
-		case SIOCDELRT:
-			if (rt.rt_dst.sa_family != AF_APPLETALK)
-				return -EINVAL;
-			return atrtr_delete(&((struct sockaddr_at *)
-						&rt.rt_dst)->sat_addr);
-
-		case SIOCADDRT: {
-			struct net_device *dev = NULL;
-			if (rt.rt_dev) {
-				char name[IFNAMSIZ];
-				if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1))
-					return -EFAULT;
-				name[IFNAMSIZ-1] = '\0';
-				dev = __dev_get_by_name(&init_net, name);
-				if (!dev)
-					return -ENODEV;
-			}
-			return atrtr_create(&rt, dev);
-		}
-	}
-	return -EINVAL;
-}
-
-/**************************************************************************\
-*                                                                          *
-* Handling for system calls applied via the various interfaces to an       *
-* AppleTalk socket object.                                                 *
-*                                                                          *
-\**************************************************************************/
-
-/*
- * Checksum: This is 'optional'. It's quite likely also a good
- * candidate for assembler hackery 8)
- */
-static unsigned long atalk_sum_partial(const unsigned char *data,
-				       int len, unsigned long sum)
-{
-	/* This ought to be unwrapped neatly. I'll trust gcc for now */
-	while (len--) {
-		sum += *data++;
-		sum = rol16(sum, 1);
-	}
-	return sum;
-}
-
-/*  Checksum skb data --  similar to skb_checksum  */
-static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
-				   int len, unsigned long sum)
-{
-	int start = skb_headlen(skb);
-	struct sk_buff *frag_iter;
-	int i, copy;
-
-	/* checksum stuff in header space */
-	if ( (copy = start - offset) > 0) {
-		if (copy > len)
-			copy = len;
-		sum = atalk_sum_partial(skb->data + offset, copy, sum);
-		if ( (len -= copy) == 0)
-			return sum;
-
-		offset += copy;
-	}
-
-	/* checksum stuff in frags */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_shinfo(skb)->frags[i].size;
-		if ((copy = end - offset) > 0) {
-			u8 *vaddr;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-			if (copy > len)
-				copy = len;
-			vaddr = kmap_skb_frag(frag);
-			sum = atalk_sum_partial(vaddr + frag->page_offset +
-						  offset - start, copy, sum);
-			kunmap_skb_frag(vaddr);
-
-			if (!(len -= copy))
-				return sum;
-			offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			if (copy > len)
-				copy = len;
-			sum = atalk_sum_skb(frag_iter, offset - start,
-					    copy, sum);
-			if ((len -= copy) == 0)
-				return sum;
-			offset += copy;
-		}
-		start = end;
-	}
-
-	BUG_ON(len > 0);
-
-	return sum;
-}
-
-static __be16 atalk_checksum(const struct sk_buff *skb, int len)
-{
-	unsigned long sum;
-
-	/* skip header 4 bytes */
-	sum = atalk_sum_skb(skb, 4, len-4, 0);
-
-	/* Use 0xFFFF for 0. 0 itself means none */
-	return sum ? htons((unsigned short)sum) : htons(0xFFFF);
-}
-
-static struct proto ddp_proto = {
-	.name	  = "DDP",
-	.owner	  = THIS_MODULE,
-	.obj_size = sizeof(struct atalk_sock),
-};
-
-/*
- * Create a socket. Initialise the socket, blank the addresses
- * set the state.
- */
-static int atalk_create(struct net *net, struct socket *sock, int protocol,
-			int kern)
-{
-	struct sock *sk;
-	int rc = -ESOCKTNOSUPPORT;
-
-	if (!net_eq(net, &init_net))
-		return -EAFNOSUPPORT;
-
-	/*
-	 * We permit SOCK_DGRAM and RAW is an extension. It is trivial to do
-	 * and gives you the full ELAP frame. Should be handy for CAP 8)
-	 */
-	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
-		goto out;
-	rc = -ENOMEM;
-	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto);
-	if (!sk)
-		goto out;
-	rc = 0;
-	sock->ops = &atalk_dgram_ops;
-	sock_init_data(sock, sk);
-
-	/* Checksums on by default */
-	sock_set_flag(sk, SOCK_ZAPPED);
-out:
-	return rc;
-}
-
-/* Free a socket. No work needed */
-static int atalk_release(struct socket *sock)
-{
-	struct sock *sk = sock->sk;
-
-	lock_kernel();
-	if (sk) {
-		sock_orphan(sk);
-		sock->sk = NULL;
-		atalk_destroy_socket(sk);
-	}
-	unlock_kernel();
-	return 0;
-}
-
-/**
- * atalk_pick_and_bind_port - Pick a source port when one is not given
- * @sk - socket to insert into the tables
- * @sat - address to search for
- *
- * Pick a source port when one is not given. If we can find a suitable free
- * one, we insert the socket into the tables using it.
- *
- * This whole operation must be atomic.
- */
-static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat)
-{
-	int retval;
-
-	write_lock_bh(&atalk_sockets_lock);
-
-	for (sat->sat_port = ATPORT_RESERVED;
-	     sat->sat_port < ATPORT_LAST;
-	     sat->sat_port++) {
-		struct sock *s;
-		struct hlist_node *node;
-
-		sk_for_each(s, node, &atalk_sockets) {
-			struct atalk_sock *at = at_sk(s);
-
-			if (at->src_net == sat->sat_addr.s_net &&
-			    at->src_node == sat->sat_addr.s_node &&
-			    at->src_port == sat->sat_port)
-				goto try_next_port;
-		}
-
-		/* Wheee, it's free, assign and insert. */
-		__atalk_insert_socket(sk);
-		at_sk(sk)->src_port = sat->sat_port;
-		retval = 0;
-		goto out;
-
-try_next_port:;
-	}
-
-	retval = -EBUSY;
-out:
-	write_unlock_bh(&atalk_sockets_lock);
-	return retval;
-}
-
-static int atalk_autobind(struct sock *sk)
-{
-	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at sat;
-	struct atalk_addr *ap = atalk_find_primary();
-	int n = -EADDRNOTAVAIL;
-
-	if (!ap || ap->s_net == htons(ATADDR_ANYNET))
-		goto out;
-
-	at->src_net  = sat.sat_addr.s_net  = ap->s_net;
-	at->src_node = sat.sat_addr.s_node = ap->s_node;
-
-	n = atalk_pick_and_bind_port(sk, &sat);
-	if (!n)
-		sock_reset_flag(sk, SOCK_ZAPPED);
-out:
-	return n;
-}
-
-/* Set the address 'our end' of the connection */
-static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
-{
-	struct sockaddr_at *addr = (struct sockaddr_at *)uaddr;
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	int err;
-
-	if (!sock_flag(sk, SOCK_ZAPPED) ||
-	    addr_len != sizeof(struct sockaddr_at))
-		return -EINVAL;
-
-	if (addr->sat_family != AF_APPLETALK)
-		return -EAFNOSUPPORT;
-
-	lock_kernel();
-	if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) {
-		struct atalk_addr *ap = atalk_find_primary();
-
-		err = -EADDRNOTAVAIL;
-		if (!ap)
-			goto out;
-
-		at->src_net  = addr->sat_addr.s_net = ap->s_net;
-		at->src_node = addr->sat_addr.s_node= ap->s_node;
-	} else {
-		err = -EADDRNOTAVAIL;
-		if (!atalk_find_interface(addr->sat_addr.s_net,
-					  addr->sat_addr.s_node))
-			goto out;
-
-		at->src_net  = addr->sat_addr.s_net;
-		at->src_node = addr->sat_addr.s_node;
-	}
-
-	if (addr->sat_port == ATADDR_ANYPORT) {
-		err = atalk_pick_and_bind_port(sk, addr);
-
-		if (err < 0)
-			goto out;
-	} else {
-		at->src_port = addr->sat_port;
-
-		err = -EADDRINUSE;
-		if (atalk_find_or_insert_socket(sk, addr))
-			goto out;
-	}
-
-	sock_reset_flag(sk, SOCK_ZAPPED);
-	err = 0;
-out:
-	unlock_kernel();
-	return err;
-}
-
-/* Set the address we talk to */
-static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
-			 int addr_len, int flags)
-{
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at *addr;
-	int err;
-
-	sk->sk_state   = TCP_CLOSE;
-	sock->state = SS_UNCONNECTED;
-
-	if (addr_len != sizeof(*addr))
-		return -EINVAL;
-
-	addr = (struct sockaddr_at *)uaddr;
-
-	if (addr->sat_family != AF_APPLETALK)
-		return -EAFNOSUPPORT;
-
-	if (addr->sat_addr.s_node == ATADDR_BCAST &&
-	    !sock_flag(sk, SOCK_BROADCAST)) {
-#if 1
-		printk(KERN_WARNING "%s is broken and did not set "
-				    "SO_BROADCAST. It will break when 2.2 is "
-				    "released.\n",
-			current->comm);
-#else
-		return -EACCES;
-#endif
-	}
-
-	lock_kernel();
-	err = -EBUSY;
-	if (sock_flag(sk, SOCK_ZAPPED))
-		if (atalk_autobind(sk) < 0)
-			goto out;
-
-	err = -ENETUNREACH;
-	if (!atrtr_get_dev(&addr->sat_addr))
-		goto out;
-
-	at->dest_port = addr->sat_port;
-	at->dest_net  = addr->sat_addr.s_net;
-	at->dest_node = addr->sat_addr.s_node;
-
-	sock->state  = SS_CONNECTED;
-	sk->sk_state = TCP_ESTABLISHED;
-	err = 0;
-out:
-	unlock_kernel();
-	return err;
-}
-
-/*
- * Find the name of an AppleTalk socket. Just copy the right
- * fields into the sockaddr.
- */
-static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
-			 int *uaddr_len, int peer)
-{
-	struct sockaddr_at sat;
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	int err;
-
-	lock_kernel();
-	err = -ENOBUFS;
-	if (sock_flag(sk, SOCK_ZAPPED))
-		if (atalk_autobind(sk) < 0)
-			goto out;
-
-	*uaddr_len = sizeof(struct sockaddr_at);
-	memset(&sat.sat_zero, 0, sizeof(sat.sat_zero));
-
-	if (peer) {
-		err = -ENOTCONN;
-		if (sk->sk_state != TCP_ESTABLISHED)
-			goto out;
-
-		sat.sat_addr.s_net  = at->dest_net;
-		sat.sat_addr.s_node = at->dest_node;
-		sat.sat_port	    = at->dest_port;
-	} else {
-		sat.sat_addr.s_net  = at->src_net;
-		sat.sat_addr.s_node = at->src_node;
-		sat.sat_port	    = at->src_port;
-	}
-
-	err = 0;
-	sat.sat_family = AF_APPLETALK;
-	memcpy(uaddr, &sat, sizeof(sat));
-
-out:
-	unlock_kernel();
-	return err;
-}
-
-static unsigned int atalk_poll(struct file *file, struct socket *sock,
-			   poll_table *wait)
-{
-	int err;
-	lock_kernel();
-	err = datagram_poll(file, sock, wait);
-	unlock_kernel();
-	return err;
-}
-
-#if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE)
-static __inline__ int is_ip_over_ddp(struct sk_buff *skb)
-{
-	return skb->data[12] == 22;
-}
-
-static int handle_ip_over_ddp(struct sk_buff *skb)
-{
-	struct net_device *dev = __dev_get_by_name(&init_net, "ipddp0");
-	struct net_device_stats *stats;
-
-	/* This needs to be able to handle ipddp"N" devices */
-	if (!dev) {
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
-
-	skb->protocol = htons(ETH_P_IP);
-	skb_pull(skb, 13);
-	skb->dev   = dev;
-	skb_reset_transport_header(skb);
-
-	stats = netdev_priv(dev);
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len + 13;
-	return netif_rx(skb);  /* Send the SKB up to a higher place. */
-}
-#else
-/* make it easy for gcc to optimize this test out, i.e. kill the code */
-#define is_ip_over_ddp(skb) 0
-#define handle_ip_over_ddp(skb) 0
-#endif
-
-static int atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
-			      struct ddpehdr *ddp, __u16 len_hops, int origlen)
-{
-	struct atalk_route *rt;
-	struct atalk_addr ta;
-
-	/*
-	 * Don't route multicast, etc., packets, or packets sent to "this
-	 * network"
-	 */
-	if (skb->pkt_type != PACKET_HOST || !ddp->deh_dnet) {
-		/*
-		 * FIXME:
-		 *
-		 * Can it ever happen that a packet is from a PPP iface and
-		 * needs to be broadcast onto the default network?
-		 */
-		if (dev->type == ARPHRD_PPP)
-			printk(KERN_DEBUG "AppleTalk: didn't forward broadcast "
-					  "packet received from PPP iface\n");
-		goto free_it;
-	}
-
-	ta.s_net  = ddp->deh_dnet;
-	ta.s_node = ddp->deh_dnode;
-
-	/* Route the packet */
-	rt = atrtr_find(&ta);
-	/* increment hops count */
-	len_hops += 1 << 10;
-	if (!rt || !(len_hops & (15 << 10)))
-		goto free_it;
-
-	/* FIXME: use skb->cb to be able to use shared skbs */
-
-	/*
-	 * Route goes through another gateway, so set the target to the
-	 * gateway instead.
-	 */
-
-	if (rt->flags & RTF_GATEWAY) {
-		ta.s_net  = rt->gateway.s_net;
-		ta.s_node = rt->gateway.s_node;
-	}
-
-	/* Fix up skb->len field */
-	skb_trim(skb, min_t(unsigned int, origlen,
-			    (rt->dev->hard_header_len +
-			     ddp_dl->header_length + (len_hops & 1023))));
-
-	/* FIXME: use skb->cb to be able to use shared skbs */
-	ddp->deh_len_hops = htons(len_hops);
-
-	/*
-	 * Send the buffer onwards
-	 *
-	 * Now we must always be careful. If it's come from LocalTalk to
-	 * EtherTalk it might not fit
-	 *
-	 * Order matters here: If a packet has to be copied to make a new
-	 * headroom (rare hopefully) then it won't need unsharing.
-	 *
-	 * Note. ddp-> becomes invalid at the realloc.
-	 */
-	if (skb_headroom(skb) < 22) {
-		/* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */
-		struct sk_buff *nskb = skb_realloc_headroom(skb, 32);
-		kfree_skb(skb);
-		skb = nskb;
-	} else
-		skb = skb_unshare(skb, GFP_ATOMIC);
-
-	/*
-	 * If the buffer didn't vanish into the lack of space bitbucket we can
-	 * send it.
-	 */
-	if (skb == NULL)
-		goto drop;
-
-	if (aarp_send_ddp(rt->dev, skb, &ta, NULL) == NET_XMIT_DROP)
-		return NET_RX_DROP;
-	return NET_RX_SUCCESS;
-free_it:
-	kfree_skb(skb);
-drop:
-	return NET_RX_DROP;
-}
-
-/**
- *	atalk_rcv - Receive a packet (in skb) from device dev
- *	@skb - packet received
- *	@dev - network device where the packet comes from
- *	@pt - packet type
- *
- *	Receive a packet (in skb) from device dev. This has come from the SNAP
- *	decoder, and on entry skb->transport_header is the DDP header, skb->len
- *	is the DDP header, skb->len is the DDP length. The physical headers
- *	have been extracted. PPP should probably pass frames marked as for this
- *	layer.  [ie ARPHRD_ETHERTALK]
- */
-static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
-		     struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct ddpehdr *ddp;
-	struct sock *sock;
-	struct atalk_iface *atif;
-	struct sockaddr_at tosat;
-	int origlen;
-	__u16 len_hops;
-
-	if (!net_eq(dev_net(dev), &init_net))
-		goto drop;
-
-	/* Don't mangle buffer if shared */
-	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
-		goto out;
-
-	/* Size check and make sure header is contiguous */
-	if (!pskb_may_pull(skb, sizeof(*ddp)))
-		goto drop;
-
-	ddp = ddp_hdr(skb);
-
-	len_hops = ntohs(ddp->deh_len_hops);
-
-	/* Trim buffer in case of stray trailing data */
-	origlen = skb->len;
-	skb_trim(skb, min_t(unsigned int, skb->len, len_hops & 1023));
-
-	/*
-	 * Size check to see if ddp->deh_len was crap
-	 * (Otherwise we'll detonate most spectacularly
-	 * in the middle of atalk_checksum() or recvmsg()).
-	 */
-	if (skb->len < sizeof(*ddp) || skb->len < (len_hops & 1023)) {
-		pr_debug("AppleTalk: dropping corrupted frame (deh_len=%u, "
-			 "skb->len=%u)\n", len_hops & 1023, skb->len);
-		goto drop;
-	}
-
-	/*
-	 * Any checksums. Note we don't do htons() on this == is assumed to be
-	 * valid for net byte orders all over the networking code...
-	 */
-	if (ddp->deh_sum &&
-	    atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum)
-		/* Not a valid AppleTalk frame - dustbin time */
-		goto drop;
-
-	/* Check the packet is aimed at us */
-	if (!ddp->deh_dnet)	/* Net 0 is 'this network' */
-		atif = atalk_find_anynet(ddp->deh_dnode, dev);
-	else
-		atif = atalk_find_interface(ddp->deh_dnet, ddp->deh_dnode);
-
-	if (!atif) {
-		/* Not ours, so we route the packet via the correct
-		 * AppleTalk iface
-		 */
-		return atalk_route_packet(skb, dev, ddp, len_hops, origlen);
-	}
-
-	/* if IP over DDP is not selected this code will be optimized out */
-	if (is_ip_over_ddp(skb))
-		return handle_ip_over_ddp(skb);
-	/*
-	 * Which socket - atalk_search_socket() looks for a *full match*
-	 * of the <net, node, port> tuple.
-	 */
-	tosat.sat_addr.s_net  = ddp->deh_dnet;
-	tosat.sat_addr.s_node = ddp->deh_dnode;
-	tosat.sat_port	      = ddp->deh_dport;
-
-	sock = atalk_search_socket(&tosat, atif);
-	if (!sock) /* But not one of our sockets */
-		goto drop;
-
-	/* Queue packet (standard) */
-	skb->sk = sock;
-
-	if (sock_queue_rcv_skb(sock, skb) < 0)
-		goto drop;
-
-	return NET_RX_SUCCESS;
-
-drop:
-	kfree_skb(skb);
-out:
-	return NET_RX_DROP;
-
-}
-
-/*
- * Receive a LocalTalk frame. We make some demands on the caller here.
- * Caller must provide enough headroom on the packet to pull the short
- * header and append a long one.
- */
-static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
-		     struct packet_type *pt, struct net_device *orig_dev)
-{
-	if (!net_eq(dev_net(dev), &init_net))
-		goto freeit;
-
-	/* Expand any short form frames */
-	if (skb_mac_header(skb)[2] == 1) {
-		struct ddpehdr *ddp;
-		/* Find our address */
-		struct atalk_addr *ap = atalk_find_dev_addr(dev);
-
-		if (!ap || skb->len < sizeof(__be16) || skb->len > 1023)
-			goto freeit;
-
-		/* Don't mangle buffer if shared */
-		if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
-			return 0;
-
-		/*
-		 * The push leaves us with a ddephdr not an shdr, and
-		 * handily the port bytes in the right place preset.
-		 */
-		ddp = (struct ddpehdr *) skb_push(skb, sizeof(*ddp) - 4);
-
-		/* Now fill in the long header */
-
-		/*
-		 * These two first. The mac overlays the new source/dest
-		 * network information so we MUST copy these before
-		 * we write the network numbers !
-		 */
-
-		ddp->deh_dnode = skb_mac_header(skb)[0];     /* From physical header */
-		ddp->deh_snode = skb_mac_header(skb)[1];     /* From physical header */
-
-		ddp->deh_dnet  = ap->s_net;	/* Network number */
-		ddp->deh_snet  = ap->s_net;
-		ddp->deh_sum   = 0;		/* No checksum */
-		/*
-		 * Not sure about this bit...
-		 */
-		/* Non routable, so force a drop if we slip up later */
-		ddp->deh_len_hops = htons(skb->len + (DDP_MAXHOPS << 10));
-	}
-	skb_reset_transport_header(skb);
-
-	return atalk_rcv(skb, dev, pt, orig_dev);
-freeit:
-	kfree_skb(skb);
-	return 0;
-}
-
-static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-			 size_t len)
-{
-	struct sock *sk = sock->sk;
-	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name;
-	int flags = msg->msg_flags;
-	int loopback = 0;
-	struct sockaddr_at local_satalk, gsat;
-	struct sk_buff *skb;
-	struct net_device *dev;
-	struct ddpehdr *ddp;
-	int size;
-	struct atalk_route *rt;
-	int err;
-
-	if (flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
-		return -EINVAL;
-
-	if (len > DDP_MAXSZ)
-		return -EMSGSIZE;
-
-	lock_kernel();
-	if (usat) {
-		err = -EBUSY;
-		if (sock_flag(sk, SOCK_ZAPPED))
-			if (atalk_autobind(sk) < 0)
-				goto out;
-
-		err = -EINVAL;
-		if (msg->msg_namelen < sizeof(*usat) ||
-		    usat->sat_family != AF_APPLETALK)
-			goto out;
-
-		err = -EPERM;
-		/* netatalk didn't implement this check */
-		if (usat->sat_addr.s_node == ATADDR_BCAST &&
-		    !sock_flag(sk, SOCK_BROADCAST)) {
-			goto out;
-		}
-	} else {
-		err = -ENOTCONN;
-		if (sk->sk_state != TCP_ESTABLISHED)
-			goto out;
-		usat = &local_satalk;
-		usat->sat_family      = AF_APPLETALK;
-		usat->sat_port	      = at->dest_port;
-		usat->sat_addr.s_node = at->dest_node;
-		usat->sat_addr.s_net  = at->dest_net;
-	}
-
-	/* Build a packet */
-	SOCK_DEBUG(sk, "SK %p: Got address.\n", sk);
-
-	/* For headers */
-	size = sizeof(struct ddpehdr) + len + ddp_dl->header_length;
-
-	if (usat->sat_addr.s_net || usat->sat_addr.s_node == ATADDR_ANYNODE) {
-		rt = atrtr_find(&usat->sat_addr);
-	} else {
-		struct atalk_addr at_hint;
-
-		at_hint.s_node = 0;
-		at_hint.s_net  = at->src_net;
-
-		rt = atrtr_find(&at_hint);
-	}
-	err = ENETUNREACH;
-	if (!rt)
-		goto out;
-
-	dev = rt->dev;
-
-	SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n",
-			sk, size, dev->name);
-
-	size += dev->hard_header_len;
-	skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err);
-	if (!skb)
-		goto out;
-
-	skb->sk = sk;
-	skb_reserve(skb, ddp_dl->header_length);
-	skb_reserve(skb, dev->hard_header_len);
-	skb->dev = dev;
-
-	SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk);
-
-	ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr));
-	ddp->deh_len_hops  = htons(len + sizeof(*ddp));
-	ddp->deh_dnet  = usat->sat_addr.s_net;
-	ddp->deh_snet  = at->src_net;
-	ddp->deh_dnode = usat->sat_addr.s_node;
-	ddp->deh_snode = at->src_node;
-	ddp->deh_dport = usat->sat_port;
-	ddp->deh_sport = at->src_port;
-
-	SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len);
-
-	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
-	if (err) {
-		kfree_skb(skb);
-		err = -EFAULT;
-		goto out;
-	}
-
-	if (sk->sk_no_check == 1)
-		ddp->deh_sum = 0;
-	else
-		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
-
-	/*
-	 * Loopback broadcast packets to non gateway targets (ie routes
-	 * to group we are in)
-	 */
-	if (ddp->deh_dnode == ATADDR_BCAST &&
-	    !(rt->flags & RTF_GATEWAY) && !(dev->flags & IFF_LOOPBACK)) {
-		struct sk_buff *skb2 = skb_copy(skb, GFP_KERNEL);
-
-		if (skb2) {
-			loopback = 1;
-			SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk);
-			/*
-			 * If it fails it is queued/sent above in the aarp queue
-			 */
-			aarp_send_ddp(dev, skb2, &usat->sat_addr, NULL);
-		}
-	}
-
-	if (dev->flags & IFF_LOOPBACK || loopback) {
-		SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk);
-		/* loop back */
-		skb_orphan(skb);
-		if (ddp->deh_dnode == ATADDR_BCAST) {
-			struct atalk_addr at_lo;
-
-			at_lo.s_node = 0;
-			at_lo.s_net  = 0;
-
-			rt = atrtr_find(&at_lo);
-			if (!rt) {
-				kfree_skb(skb);
-				err = -ENETUNREACH;
-				goto out;
-			}
-			dev = rt->dev;
-			skb->dev = dev;
-		}
-		ddp_dl->request(ddp_dl, skb, dev->dev_addr);
-	} else {
-		SOCK_DEBUG(sk, "SK %p: send out.\n", sk);
-		if (rt->flags & RTF_GATEWAY) {
-		    gsat.sat_addr = rt->gateway;
-		    usat = &gsat;
-		}
-
-		/*
-		 * If it fails it is queued/sent above in the aarp queue
-		 */
-		aarp_send_ddp(dev, skb, &usat->sat_addr, NULL);
-	}
-	SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len);
-
-out:
-	unlock_kernel();
-	return err ? : len;
-}
-
-static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
-			 size_t size, int flags)
-{
-	struct sock *sk = sock->sk;
-	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
-	struct ddpehdr *ddp;
-	int copied = 0;
-	int offset = 0;
-	int err = 0;
-	struct sk_buff *skb;
-
-	lock_kernel();
-	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
-						flags & MSG_DONTWAIT, &err);
-	if (!skb)
-		goto out;
-
-	/* FIXME: use skb->cb to be able to use shared skbs */
-	ddp = ddp_hdr(skb);
-	copied = ntohs(ddp->deh_len_hops) & 1023;
-
-	if (sk->sk_type != SOCK_RAW) {
-		offset = sizeof(*ddp);
-		copied -= offset;
-	}
-
-	if (copied > size) {
-		copied = size;
-		msg->msg_flags |= MSG_TRUNC;
-	}
-	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
-
-	if (!err) {
-		if (sat) {
-			sat->sat_family      = AF_APPLETALK;
-			sat->sat_port        = ddp->deh_sport;
-			sat->sat_addr.s_node = ddp->deh_snode;
-			sat->sat_addr.s_net  = ddp->deh_snet;
-		}
-		msg->msg_namelen = sizeof(*sat);
-	}
-
-	skb_free_datagram(sk, skb);	/* Free the datagram. */
-
-out:
-	unlock_kernel();
-	return err ? : copied;
-}
-
-
-/*
- * AppleTalk ioctl calls.
- */
-static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
-{
-	int rc = -ENOIOCTLCMD;
-	struct sock *sk = sock->sk;
-	void __user *argp = (void __user *)arg;
-
-	switch (cmd) {
-		/* Protocol layer */
-		case TIOCOUTQ: {
-			long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
-
-			if (amount < 0)
-				amount = 0;
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case TIOCINQ: {
-			/*
-			 * These two are safe on a single CPU system as only
-			 * user tasks fiddle here
-			 */
-			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-			long amount = 0;
-
-			if (skb)
-				amount = skb->len - sizeof(struct ddpehdr);
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case SIOCGSTAMP:
-			rc = sock_get_timestamp(sk, argp);
-			break;
-		case SIOCGSTAMPNS:
-			rc = sock_get_timestampns(sk, argp);
-			break;
-		/* Routing */
-		case SIOCADDRT:
-		case SIOCDELRT:
-			rc = -EPERM;
-			if (capable(CAP_NET_ADMIN))
-				rc = atrtr_ioctl(cmd, argp);
-			break;
-		/* Interface */
-		case SIOCGIFADDR:
-		case SIOCSIFADDR:
-		case SIOCGIFBRDADDR:
-		case SIOCATALKDIFADDR:
-		case SIOCDIFADDR:
-		case SIOCSARP:		/* proxy AARP */
-		case SIOCDARP:		/* proxy AARP */
-			rtnl_lock();
-			rc = atif_ioctl(cmd, argp);
-			rtnl_unlock();
-			break;
-	}
-
-	return rc;
-}
-
-
-#ifdef CONFIG_COMPAT
-static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
-{
-	/*
-	 * SIOCATALKDIFADDR is a SIOCPROTOPRIVATE ioctl number, so we
-	 * cannot handle it in common code. The data we access if ifreq
-	 * here is compatible, so we can simply call the native
-	 * handler.
-	 */
-	if (cmd == SIOCATALKDIFADDR)
-		return atalk_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
-
-	return -ENOIOCTLCMD;
-}
-#endif
-
-
-static const struct net_proto_family atalk_family_ops = {
-	.family		= PF_APPLETALK,
-	.create		= atalk_create,
-	.owner		= THIS_MODULE,
-};
-
-static const struct proto_ops atalk_dgram_ops = {
-	.family		= PF_APPLETALK,
-	.owner		= THIS_MODULE,
-	.release	= atalk_release,
-	.bind		= atalk_bind,
-	.connect	= atalk_connect,
-	.socketpair	= sock_no_socketpair,
-	.accept		= sock_no_accept,
-	.getname	= atalk_getname,
-	.poll		= atalk_poll,
-	.ioctl		= atalk_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= atalk_compat_ioctl,
-#endif
-	.listen		= sock_no_listen,
-	.shutdown	= sock_no_shutdown,
-	.setsockopt	= sock_no_setsockopt,
-	.getsockopt	= sock_no_getsockopt,
-	.sendmsg	= atalk_sendmsg,
-	.recvmsg	= atalk_recvmsg,
-	.mmap		= sock_no_mmap,
-	.sendpage	= sock_no_sendpage,
-};
-
-static struct notifier_block ddp_notifier = {
-	.notifier_call	= ddp_device_event,
-};
-
-static struct packet_type ltalk_packet_type __read_mostly = {
-	.type		= cpu_to_be16(ETH_P_LOCALTALK),
-	.func		= ltalk_rcv,
-};
-
-static struct packet_type ppptalk_packet_type __read_mostly = {
-	.type		= cpu_to_be16(ETH_P_PPPTALK),
-	.func		= atalk_rcv,
-};
-
-static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B };
-
-/* Export symbols for use by drivers when AppleTalk is a module */
-EXPORT_SYMBOL(atrtr_get_dev);
-EXPORT_SYMBOL(atalk_find_dev_addr);
-
-static const char atalk_err_snap[] __initconst =
-	KERN_CRIT "Unable to register DDP with SNAP.\n";
-
-/* Called by proto.c on kernel start up */
-static int __init atalk_init(void)
-{
-	int rc = proto_register(&ddp_proto, 0);
-
-	if (rc != 0)
-		goto out;
-
-	(void)sock_register(&atalk_family_ops);
-	ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
-	if (!ddp_dl)
-		printk(atalk_err_snap);
-
-	dev_add_pack(&ltalk_packet_type);
-	dev_add_pack(&ppptalk_packet_type);
-
-	register_netdevice_notifier(&ddp_notifier);
-	aarp_proto_init();
-	atalk_proc_init();
-	atalk_register_sysctl();
-out:
-	return rc;
-}
-module_init(atalk_init);
-
-/*
- * No explicit module reference count manipulation is needed in the
- * protocol. Socket layer sets module reference count for us
- * and interfaces reference counting is done
- * by the network device layer.
- *
- * Ergo, before the AppleTalk module can be removed, all AppleTalk
- * sockets be closed from user space.
- */
-static void __exit atalk_exit(void)
-{
-#ifdef CONFIG_SYSCTL
-	atalk_unregister_sysctl();
-#endif /* CONFIG_SYSCTL */
-	atalk_proc_exit();
-	aarp_cleanup_module();	/* General aarp clean-up. */
-	unregister_netdevice_notifier(&ddp_notifier);
-	dev_remove_pack(&ltalk_packet_type);
-	dev_remove_pack(&ppptalk_packet_type);
-	unregister_snap_client(ddp_dl);
-	sock_unregister(PF_APPLETALK);
-	proto_unregister(&ddp_proto);
-}
-module_exit(atalk_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alan Cox <alan@lxorguk.ukuu.org.uk>");
-MODULE_DESCRIPTION("AppleTalk 0.20\n");
-MODULE_ALIAS_NETPROTO(PF_APPLETALK);
diff --git a/drivers/staging/appletalk/dev.c b/drivers/staging/appletalk/dev.c
deleted file mode 100644
index 6c8016f61866..000000000000
--- a/drivers/staging/appletalk/dev.c
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Moved here from drivers/net/net_init.c, which is:
- *	Written 1993,1994,1995 by Donald Becker.
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/if_arp.h>
-#include <linux/if_ltalk.h>
-
-static void ltalk_setup(struct net_device *dev)
-{
-	/* Fill in the fields of the device structure with localtalk-generic values. */
-
-	dev->type		= ARPHRD_LOCALTLK;
-	dev->hard_header_len 	= LTALK_HLEN;
-	dev->mtu		= LTALK_MTU;
-	dev->addr_len		= LTALK_ALEN;
-	dev->tx_queue_len	= 10;
-
-	dev->broadcast[0]	= 0xFF;
-
-	dev->flags		= IFF_BROADCAST|IFF_MULTICAST|IFF_NOARP;
-}
-
-/**
- * alloc_ltalkdev - Allocates and sets up an localtalk device
- * @sizeof_priv: Size of additional driver-private structure to be allocated
- *	for this localtalk device
- *
- * Fill in the fields of the device structure with localtalk-generic
- * values. Basically does everything except registering the device.
- *
- * Constructs a new net device, complete with a private data area of
- * size @sizeof_priv.  A 32-byte (not bit) alignment is enforced for
- * this private data area.
- */
-
-struct net_device *alloc_ltalkdev(int sizeof_priv)
-{
-	return alloc_netdev(sizeof_priv, "lt%d", ltalk_setup);
-}
-EXPORT_SYMBOL(alloc_ltalkdev);
diff --git a/drivers/staging/appletalk/ipddp.c b/drivers/staging/appletalk/ipddp.c
deleted file mode 100644
index 58b4e6098ad4..000000000000
--- a/drivers/staging/appletalk/ipddp.c
+++ /dev/null
@@ -1,335 +0,0 @@
-/*
- *	ipddp.c: IP to Appletalk-IP Encapsulation driver for Linux
- *		 Appletalk-IP to IP Decapsulation driver for Linux
- *
- *	Authors:
- *      - DDP-IP Encap by: Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *	- DDP-IP Decap by: Jay Schulist <jschlst@samba.org>
- *
- *	Derived from:
- *	- Almost all code already existed in net/appletalk/ddp.c I just
- *	  moved/reorginized it into a driver file. Original IP-over-DDP code
- *	  was done by Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *      - skeleton.c: A network driver outline for linux.
- *        Written 1993-94 by Donald Becker.
- *	- dummy.c: A dummy net driver. By Nick Holloway.
- *	- MacGate: A user space Daemon for Appletalk-IP Decap for
- *	  Linux by Jay Schulist <jschlst@samba.org>
- *
- *      Copyright 1993 United States Government as represented by the
- *      Director, National Security Agency.
- *
- *      This software may be used and distributed according to the terms
- *      of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/ip.h>
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <net/route.h>
-#include <asm/uaccess.h>
-
-#include "atalk.h"
-#include "ipddp.h"		/* Our stuff */
-
-static const char version[] = KERN_INFO "ipddp.c:v0.01 8/28/97 Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n";
-
-static struct ipddp_route *ipddp_route_list;
-static DEFINE_SPINLOCK(ipddp_route_lock);
-
-#ifdef CONFIG_IPDDP_ENCAP
-static int ipddp_mode = IPDDP_ENCAP;
-#else
-static int ipddp_mode = IPDDP_DECAP;
-#endif
-
-/* Index to functions, as function prototypes. */
-static netdev_tx_t ipddp_xmit(struct sk_buff *skb,
-				    struct net_device *dev);
-static int ipddp_create(struct ipddp_route *new_rt);
-static int ipddp_delete(struct ipddp_route *rt);
-static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt);
-static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
-
-static const struct net_device_ops ipddp_netdev_ops = {
-	.ndo_start_xmit		= ipddp_xmit,
-	.ndo_do_ioctl   	= ipddp_ioctl,
-	.ndo_change_mtu		= eth_change_mtu,
-	.ndo_set_mac_address 	= eth_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
-};
-
-static struct net_device * __init ipddp_init(void)
-{
-	static unsigned version_printed;
-	struct net_device *dev;
-	int err;
-
-	dev = alloc_etherdev(0);
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
-	strcpy(dev->name, "ipddp%d");
-
-	if (version_printed++ == 0)
-                printk(version);
-
-	/* Initialize the device structure. */
-	dev->netdev_ops = &ipddp_netdev_ops;
-
-        dev->type = ARPHRD_IPDDP;       	/* IP over DDP tunnel */
-        dev->mtu = 585;
-        dev->flags |= IFF_NOARP;
-
-        /*
-         *      The worst case header we will need is currently a
-         *      ethernet header (14 bytes) and a ddp header (sizeof ddpehdr+1)
-         *      We send over SNAP so that takes another 8 bytes.
-         */
-        dev->hard_header_len = 14+8+sizeof(struct ddpehdr)+1;
-
-	err = register_netdev(dev);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
-
-	/* Let the user now what mode we are in */
-	if(ipddp_mode == IPDDP_ENCAP)
-		printk("%s: Appletalk-IP Encap. mode by Bradford W. Johnson <johns393@maroon.tc.umn.edu>\n", 
-			dev->name);
-	if(ipddp_mode == IPDDP_DECAP)
-		printk("%s: Appletalk-IP Decap. mode by Jay Schulist <jschlst@samba.org>\n", 
-			dev->name);
-
-        return dev;
-}
-
-
-/*
- * Transmit LLAP/ELAP frame using aarp_send_ddp.
- */
-static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	__be32 paddr = skb_rtable(skb)->rt_gateway;
-        struct ddpehdr *ddp;
-        struct ipddp_route *rt;
-        struct atalk_addr *our_addr;
-
-	spin_lock(&ipddp_route_lock);
-
-	/*
-         * Find appropriate route to use, based only on IP number.
-         */
-        for(rt = ipddp_route_list; rt != NULL; rt = rt->next)
-        {
-                if(rt->ip == paddr)
-                        break;
-        }
-        if(rt == NULL) {
-		spin_unlock(&ipddp_route_lock);
-                return NETDEV_TX_OK;
-	}
-
-        our_addr = atalk_find_dev_addr(rt->dev);
-
-	if(ipddp_mode == IPDDP_DECAP)
-		/* 
-		 * Pull off the excess room that should not be there.
-		 * This is due to a hard-header problem. This is the
-		 * quick fix for now though, till it breaks.
-		 */
-		skb_pull(skb, 35-(sizeof(struct ddpehdr)+1));
-
-	/* Create the Extended DDP header */
-	ddp = (struct ddpehdr *)skb->data;
-        ddp->deh_len_hops = htons(skb->len + (1<<10));
-        ddp->deh_sum = 0;
-
-	/*
-         * For Localtalk we need aarp_send_ddp to strip the
-         * long DDP header and place a shot DDP header on it.
-         */
-        if(rt->dev->type == ARPHRD_LOCALTLK)
-        {
-                ddp->deh_dnet  = 0;   /* FIXME more hops?? */
-                ddp->deh_snet  = 0;
-        }
-        else
-        {
-                ddp->deh_dnet  = rt->at.s_net;   /* FIXME more hops?? */
-                ddp->deh_snet  = our_addr->s_net;
-        }
-        ddp->deh_dnode = rt->at.s_node;
-        ddp->deh_snode = our_addr->s_node;
-        ddp->deh_dport = 72;
-        ddp->deh_sport = 72;
-
-        *((__u8 *)(ddp+1)) = 22;        	/* ddp type = IP */
-
-        skb->protocol = htons(ETH_P_ATALK);     /* Protocol has changed */
-
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	aarp_send_ddp(rt->dev, skb, &rt->at, NULL);
-
-	spin_unlock(&ipddp_route_lock);
-
-        return NETDEV_TX_OK;
-}
-
-/*
- * Create a routing entry. We first verify that the
- * record does not already exist. If it does we return -EEXIST
- */
-static int ipddp_create(struct ipddp_route *new_rt)
-{
-        struct ipddp_route *rt = kmalloc(sizeof(*rt), GFP_KERNEL);
-
-        if (rt == NULL)
-                return -ENOMEM;
-
-        rt->ip = new_rt->ip;
-        rt->at = new_rt->at;
-        rt->next = NULL;
-        if ((rt->dev = atrtr_get_dev(&rt->at)) == NULL) {
-		kfree(rt);
-                return -ENETUNREACH;
-        }
-
-	spin_lock_bh(&ipddp_route_lock);
-	if (__ipddp_find_route(rt)) {
-		spin_unlock_bh(&ipddp_route_lock);
-		kfree(rt);
-		return -EEXIST;
-	}
-
-        rt->next = ipddp_route_list;
-        ipddp_route_list = rt;
-
-	spin_unlock_bh(&ipddp_route_lock);
-
-        return 0;
-}
-
-/*
- * Delete a route, we only delete a FULL match.
- * If route does not exist we return -ENOENT.
- */
-static int ipddp_delete(struct ipddp_route *rt)
-{
-        struct ipddp_route **r = &ipddp_route_list;
-        struct ipddp_route *tmp;
-
-	spin_lock_bh(&ipddp_route_lock);
-        while((tmp = *r) != NULL)
-        {
-                if(tmp->ip == rt->ip &&
-		   tmp->at.s_net == rt->at.s_net &&
-		   tmp->at.s_node == rt->at.s_node)
-                {
-                        *r = tmp->next;
-			spin_unlock_bh(&ipddp_route_lock);
-                        kfree(tmp);
-                        return 0;
-                }
-                r = &tmp->next;
-        }
-
-	spin_unlock_bh(&ipddp_route_lock);
-        return -ENOENT;
-}
-
-/*
- * Find a routing entry, we only return a FULL match
- */
-static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt)
-{
-        struct ipddp_route *f;
-
-        for(f = ipddp_route_list; f != NULL; f = f->next)
-        {
-                if(f->ip == rt->ip &&
-		   f->at.s_net == rt->at.s_net &&
-		   f->at.s_node == rt->at.s_node)
-                        return f;
-        }
-
-        return NULL;
-}
-
-static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-        struct ipddp_route __user *rt = ifr->ifr_data;
-        struct ipddp_route rcp, rcp2, *rp;
-
-        if(!capable(CAP_NET_ADMIN))
-                return -EPERM;
-
-	if(copy_from_user(&rcp, rt, sizeof(rcp)))
-		return -EFAULT;
-
-        switch(cmd)
-        {
-		case SIOCADDIPDDPRT:
-                        return ipddp_create(&rcp);
-
-                case SIOCFINDIPDDPRT:
-			spin_lock_bh(&ipddp_route_lock);
-			rp = __ipddp_find_route(&rcp);
-			if (rp)
-				memcpy(&rcp2, rp, sizeof(rcp2));
-			spin_unlock_bh(&ipddp_route_lock);
-
-			if (rp) {
-				if (copy_to_user(rt, &rcp2,
-						 sizeof(struct ipddp_route)))
-					return -EFAULT;
-				return 0;
-			} else
-				return -ENOENT;
-
-                case SIOCDELIPDDPRT:
-                        return ipddp_delete(&rcp);
-
-                default:
-                        return -EINVAL;
-        }
-}
-
-static struct net_device *dev_ipddp;
-
-MODULE_LICENSE("GPL");
-module_param(ipddp_mode, int, 0);
-
-static int __init ipddp_init_module(void)
-{
-	dev_ipddp = ipddp_init();
-        if (IS_ERR(dev_ipddp))
-                return PTR_ERR(dev_ipddp);
-	return 0;
-}
-
-static void __exit ipddp_cleanup_module(void)
-{
-        struct ipddp_route *p;
-
-	unregister_netdev(dev_ipddp);
-        free_netdev(dev_ipddp);
-
-        while (ipddp_route_list) {
-                p = ipddp_route_list->next;
-                kfree(ipddp_route_list);
-                ipddp_route_list = p;
-        }
-}
-
-module_init(ipddp_init_module);
-module_exit(ipddp_cleanup_module);
diff --git a/drivers/staging/appletalk/ipddp.h b/drivers/staging/appletalk/ipddp.h
deleted file mode 100644
index 531519da99a3..000000000000
--- a/drivers/staging/appletalk/ipddp.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- *	ipddp.h: Header for IP-over-DDP driver for Linux.
- */
-
-#ifndef __LINUX_IPDDP_H
-#define __LINUX_IPDDP_H
-
-#ifdef __KERNEL__
-
-#define SIOCADDIPDDPRT   (SIOCDEVPRIVATE)
-#define SIOCDELIPDDPRT   (SIOCDEVPRIVATE+1)
-#define SIOCFINDIPDDPRT  (SIOCDEVPRIVATE+2)
-
-struct ipddp_route
-{
-        struct net_device *dev;             /* Carrier device */
-        __be32 ip;                       /* IP address */
-        struct atalk_addr at;              /* Gateway appletalk address */
-        int flags;
-        struct ipddp_route *next;
-};
-
-#define IPDDP_ENCAP	1
-#define IPDDP_DECAP	2
-
-#endif	/* __KERNEL__ */
-#endif	/* __LINUX_IPDDP_H */
diff --git a/drivers/staging/appletalk/ltpc.c b/drivers/staging/appletalk/ltpc.c
deleted file mode 100644
index 60caf892695e..000000000000
--- a/drivers/staging/appletalk/ltpc.c
+++ /dev/null
@@ -1,1288 +0,0 @@
-/***    ltpc.c -- a driver for the LocalTalk PC card.
- *
- *      Copyright (c) 1995,1996 Bradford W. Johnson <johns393@maroon.tc.umn.edu>
- *
- *      This software may be used and distributed according to the terms
- *      of the GNU General Public License, incorporated herein by reference.
- *
- *      This is ALPHA code at best.  It may not work for you.  It may
- *      damage your equipment.  It may damage your relations with other
- *      users of your network.  Use it at your own risk!
- *
- *      Based in part on:
- *      skeleton.c      by Donald Becker
- *      dummy.c         by Nick Holloway and Alan Cox
- *      loopback.c      by Ross Biro, Fred van Kampen, Donald Becker
- *      the netatalk source code (UMICH)
- *      lots of work on the card...
- *
- *      I do not have access to the (proprietary) SDK that goes with the card.
- *      If you do, I don't want to know about it, and you can probably write
- *      a better driver yourself anyway.  This does mean that the pieces that
- *      talk to the card are guesswork on my part, so use at your own risk!
- *
- *      This is my first try at writing Linux networking code, and is also
- *      guesswork.  Again, use at your own risk!  (Although on this part, I'd
- *      welcome suggestions)
- *
- *      This is a loadable kernel module which seems to work at my site
- *      consisting of a 1.2.13 linux box running netatalk 1.3.3, and with
- *      the kernel support from 1.3.3b2 including patches routing.patch
- *      and ddp.disappears.from.chooser.  In order to run it, you will need
- *      to patch ddp.c and aarp.c in the kernel, but only a little...
- *
- *      I'm fairly confident that while this is arguably badly written, the
- *      problems that people experience will be "higher level", that is, with
- *      complications in the netatalk code.  The driver itself doesn't do
- *      anything terribly complicated -- it pretends to be an ether device
- *      as far as netatalk is concerned, strips the DDP data out of the ether
- *      frame and builds a LLAP packet to send out the card.  In the other
- *      direction, it receives LLAP frames from the card and builds a fake
- *      ether packet that it then tosses up to the networking code.  You can
- *      argue (correctly) that this is an ugly way to do things, but it
- *      requires a minimal amount of fooling with the code in ddp.c and aarp.c.
- *
- *      The card will do a lot more than is used here -- I *think* it has the
- *      layers up through ATP.  Even if you knew how that part works (which I
- *      don't) it would be a big job to carve up the kernel ddp code to insert
- *      things at a higher level, and probably a bad idea...
- *
- *      There are a number of other cards that do LocalTalk on the PC.  If
- *      nobody finds any insurmountable (at the netatalk level) problems
- *      here, this driver should encourage people to put some work into the
- *      other cards (some of which I gather are still commercially available)
- *      and also to put hooks for LocalTalk into the official ddp code.
- *
- *      I welcome comments and suggestions.  This is my first try at Linux
- *      networking stuff, and there are probably lots of things that I did
- *      suboptimally.  
- *
- ***/
-
-/***
- *
- * $Log: ltpc.c,v $
- * Revision 1.1.2.1  2000/03/01 05:35:07  jgarzik
- * at and tr cleanup
- *
- * Revision 1.8  1997/01/28 05:44:54  bradford
- * Clean up for non-module a little.
- * Hacked about a bit to clean things up - Alan Cox 
- * Probably broken it from the origina 1.8
- *
-
- * 1998/11/09: David Huggins-Daines <dhd@debian.org>
- * Cleaned up the initialization code to use the standard autoirq methods,
-   and to probe for things in the standard order of i/o, irq, dma.  This
-   removes the "reset the reset" hack, because I couldn't figure out an
-   easy way to get the card to trigger an interrupt after it.
- * Added support for passing configuration parameters on the kernel command
-   line and through insmod
- * Changed the device name from "ltalk0" to "lt0", both to conform with the
-   other localtalk driver, and to clear up the inconsistency between the
-   module and the non-module versions of the driver :-)
- * Added a bunch of comments (I was going to make some enums for the state
-   codes and the register offsets, but I'm still not sure exactly what their
-   semantics are)
- * Don't poll anymore in interrupt-driven mode
- * It seems to work as a module now (as of 2.1.127), but I don't think
-   I'm responsible for that...
-
- *
- * Revision 1.7  1996/12/12 03:42:33  bradford
- * DMA alloc cribbed from 3c505.c.
- *
- * Revision 1.6  1996/12/12 03:18:58  bradford
- * Added virt_to_bus; works in 2.1.13.
- *
- * Revision 1.5  1996/12/12 03:13:22  root
- * xmitQel initialization -- think through better though.
- *
- * Revision 1.4  1996/06/18 14:55:55  root
- * Change names to ltpc. Tabs. Took a shot at dma alloc,
- * although more needs to be done eventually.
- *
- * Revision 1.3  1996/05/22 14:59:39  root
- * Change dev->open, dev->close to track dummy.c in 1.99.(around 7)
- *
- * Revision 1.2  1996/05/22 14:58:24  root
- * Change tabs mostly.
- *
- * Revision 1.1  1996/04/23 04:45:09  root
- * Initial revision
- *
- * Revision 0.16  1996/03/05 15:59:56  root
- * Change ARPHRD_LOCALTLK definition to the "real" one.
- *
- * Revision 0.15  1996/03/05 06:28:30  root
- * Changes for kernel 1.3.70.  Still need a few patches to kernel, but
- * it's getting closer.
- *
- * Revision 0.14  1996/02/25 17:38:32  root
- * More cleanups.  Removed query to card on get_stats.
- *
- * Revision 0.13  1996/02/21  16:27:40  root
- * Refix debug_print_skb.  Fix mac.raw gotcha that appeared in 1.3.65.
- * Clean up receive code a little.
- *
- * Revision 0.12  1996/02/19  16:34:53  root
- * Fix debug_print_skb.  Kludge outgoing snet to 0 when using startup
- * range.  Change debug to mask: 1 for verbose, 2 for higher level stuff
- * including packet printing, 4 for lower level (card i/o) stuff.
- *
- * Revision 0.11  1996/02/12  15:53:38  root
- * Added router sends (requires new aarp.c patch)
- *
- * Revision 0.10  1996/02/11  00:19:35  root
- * Change source LTALK_LOGGING debug switch to insmod ... debug=2.
- *
- * Revision 0.9  1996/02/10  23:59:35  root
- * Fixed those fixes for 1.2 -- DANGER!  The at.h that comes with netatalk
- * has a *different* definition of struct sockaddr_at than the Linux kernel
- * does.  This is an "insidious and invidious" bug...
- * (Actually the preceding comment is false -- it's the atalk.h in the
- * ancient atalk-0.06 that's the problem)
- *
- * Revision 0.8  1996/02/10 19:09:00  root
- * Merge 1.3 changes.  Tested OK under 1.3.60.
- *
- * Revision 0.7  1996/02/10 17:56:56  root
- * Added debug=1 parameter on insmod for debugging prints.  Tried
- * to fix timer unload on rmmod, but I don't think that's the problem.
- *
- * Revision 0.6  1995/12/31  19:01:09  root
- * Clean up rmmod, irq comments per feedback from Corin Anderson (Thanks Corey!)
- * Clean up initial probing -- sometimes the card wakes up latched in reset.
- *
- * Revision 0.5  1995/12/22  06:03:44  root
- * Added comments in front and cleaned up a bit.
- * This version sent out to people.
- *
- * Revision 0.4  1995/12/18  03:46:44  root
- * Return shortDDP to longDDP fake to 0/0.  Added command structs.
- *
- ***/
-
-/* ltpc jumpers are:
-*
-*	Interrupts -- set at most one.  If none are set, the driver uses
-*	polled mode.  Because the card was developed in the XT era, the
-*	original documentation refers to IRQ2.  Since you'll be running
-*	this on an AT (or later) class machine, that really means IRQ9.
-*
-*	SW1	IRQ 4
-*	SW2	IRQ 3
-*	SW3	IRQ 9 (2 in original card documentation only applies to XT)
-*
-*
-*	DMA -- choose DMA 1 or 3, and set both corresponding switches.
-*
-*	SW4	DMA 3
-*	SW5	DMA 1
-*	SW6	DMA 3
-*	SW7	DMA 1
-*
-*
-*	I/O address -- choose one.  
-*
-*	SW8	220 / 240
-*/
-
-/*	To have some stuff logged, do 
-*	insmod ltpc.o debug=1
-*
-*	For a whole bunch of stuff, use higher numbers.
-*
-*	The default is 0, i.e. no messages except for the probe results.
-*/
-
-/* insmod-tweakable variables */
-static int debug;
-#define DEBUG_VERBOSE 1
-#define DEBUG_UPPER 2
-#define DEBUG_LOWER 4
-
-static int io;
-static int irq;
-static int dma;
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/spinlock.h>
-#include <linux/in.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_ltalk.h>
-#include <linux/delay.h>
-#include <linux/timer.h>
-#include <linux/bitops.h>
-#include <linux/gfp.h>
-
-#include <asm/system.h>
-#include <asm/dma.h>
-#include <asm/io.h>
-
-/* our stuff */
-#include "atalk.h"
-#include "ltpc.h"
-
-static DEFINE_SPINLOCK(txqueue_lock);
-static DEFINE_SPINLOCK(mbox_lock);
-
-/* function prototypes */
-static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
-	void *dbuf, int dbuflen);
-static int sendup_buffer (struct net_device *dev);
-
-/* Dma Memory related stuff, cribbed directly from 3c505.c */
-
-static unsigned long dma_mem_alloc(int size)
-{
-        int order = get_order(size);
-
-        return __get_dma_pages(GFP_KERNEL, order);
-}
-
-/* DMA data buffer, DMA command buffer */
-static unsigned char *ltdmabuf;
-static unsigned char *ltdmacbuf;
-
-/* private struct, holds our appletalk address */
-
-struct ltpc_private
-{
-	struct atalk_addr my_addr;
-};
-
-/* transmit queue element struct */
-
-struct xmitQel {
-	struct xmitQel *next;
-	/* command buffer */
-	unsigned char *cbuf;
-	short cbuflen;
-	/* data buffer */
-	unsigned char *dbuf;
-	short dbuflen;
-	unsigned char QWrite;	/* read or write data */
-	unsigned char mailbox;
-};
-
-/* the transmit queue itself */
-
-static struct xmitQel *xmQhd, *xmQtl;
-
-static void enQ(struct xmitQel *qel)
-{
-	unsigned long flags;
-	qel->next = NULL;
-	
-	spin_lock_irqsave(&txqueue_lock, flags);
-	if (xmQtl) {
-		xmQtl->next = qel;
-	} else {
-		xmQhd = qel;
-	}
-	xmQtl = qel;
-	spin_unlock_irqrestore(&txqueue_lock, flags);
-
-	if (debug & DEBUG_LOWER)
-		printk("enqueued a 0x%02x command\n",qel->cbuf[0]);
-}
-
-static struct xmitQel *deQ(void)
-{
-	unsigned long flags;
-	int i;
-	struct xmitQel *qel=NULL;
-	
-	spin_lock_irqsave(&txqueue_lock, flags);
-	if (xmQhd) {
-		qel = xmQhd;
-		xmQhd = qel->next;
-		if(!xmQhd) xmQtl = NULL;
-	}
-	spin_unlock_irqrestore(&txqueue_lock, flags);
-
-	if ((debug & DEBUG_LOWER) && qel) {
-		int n;
-		printk(KERN_DEBUG "ltpc: dequeued command ");
-		n = qel->cbuflen;
-		if (n>100) n=100;
-		for(i=0;i<n;i++) printk("%02x ",qel->cbuf[i]);
-		printk("\n");
-	}
-
-	return qel;
-}
-
-/* and... the queue elements we'll be using */
-static struct xmitQel qels[16];
-
-/* and their corresponding mailboxes */
-static unsigned char mailbox[16];
-static unsigned char mboxinuse[16] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};
-
-static int wait_timeout(struct net_device *dev, int c)
-{
-	/* returns true if it stayed c */
-	/* this uses base+6, but it's ok */
-	int i;
-
-	/* twenty second or so total */
-
-	for(i=0;i<200000;i++) {
-		if ( c != inb_p(dev->base_addr+6) ) return 0;
-		udelay(100);
-	}
-	return 1; /* timed out */
-}
-
-/* get the first free mailbox */
-
-static int getmbox(void)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&mbox_lock, flags);
-	for(i=1;i<16;i++) if(!mboxinuse[i]) {
-		mboxinuse[i]=1;
-		spin_unlock_irqrestore(&mbox_lock, flags);
-		return i;
-	}
-	spin_unlock_irqrestore(&mbox_lock, flags);
-	return 0;
-}
-
-/* read a command from the card */
-static void handlefc(struct net_device *dev)
-{
-	/* called *only* from idle, non-reentrant */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
-	set_dma_count(dma,50);
-	enable_dma(dma);
-	release_dma_lock(flags);
-
-	inb_p(base+3);
-	inb_p(base+2);
-
-	if ( wait_timeout(dev,0xfc) ) printk("timed out in handlefc\n");
-}
-
-/* read data from the card */
-static void handlefd(struct net_device *dev)
-{
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,800);
-	enable_dma(dma);
-	release_dma_lock(flags);
-
-	inb_p(base+3);
-	inb_p(base+2);
-
-	if ( wait_timeout(dev,0xfd) ) printk("timed out in handlefd\n");
-	sendup_buffer(dev);
-} 
-
-static void handlewrite(struct net_device *dev)
-{
-	/* called *only* from idle, non-reentrant */
-	/* on entry, 0xfb and ltdmabuf holds data */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-	
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_WRITE);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,800);
-	enable_dma(dma);
-	release_dma_lock(flags);
-	
-	inb_p(base+3);
-	inb_p(base+2);
-
-	if ( wait_timeout(dev,0xfb) ) {
-		flags=claim_dma_lock();
-		printk("timed out in handlewrite, dma res %d\n",
-			get_dma_residue(dev->dma) );
-		release_dma_lock(flags);
-	}
-}
-
-static void handleread(struct net_device *dev)
-{
-	/* on entry, 0xfb */
-	/* on exit, ltdmabuf holds data */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-	
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,800);
-	enable_dma(dma);
-	release_dma_lock(flags);
-
-	inb_p(base+3);
-	inb_p(base+2);
-	if ( wait_timeout(dev,0xfb) ) printk("timed out in handleread\n");
-}
-
-static void handlecommand(struct net_device *dev)
-{
-	/* on entry, 0xfa and ltdmacbuf holds command */
-	int dma = dev->dma;
-	int base = dev->base_addr;
-	unsigned long flags;
-
-	flags=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_WRITE);
-	set_dma_addr(dma,virt_to_bus(ltdmacbuf));
-	set_dma_count(dma,50);
-	enable_dma(dma);
-	release_dma_lock(flags);
-	inb_p(base+3);
-	inb_p(base+2);
-	if ( wait_timeout(dev,0xfa) ) printk("timed out in handlecommand\n");
-} 
-
-/* ready made command for getting the result from the card */
-static unsigned char rescbuf[2] = {LT_GETRESULT,0};
-static unsigned char resdbuf[2];
-
-static int QInIdle;
-
-/* idle expects to be called with the IRQ line high -- either because of
- * an interrupt, or because the line is tri-stated
- */
-
-static void idle(struct net_device *dev)
-{
-	unsigned long flags;
-	int state;
-	/* FIXME This is initialized to shut the warning up, but I need to
-	 * think this through again.
-	 */
-	struct xmitQel *q = NULL;
-	int oops;
-	int i;
-	int base = dev->base_addr;
-
-	spin_lock_irqsave(&txqueue_lock, flags);
-	if(QInIdle) {
-		spin_unlock_irqrestore(&txqueue_lock, flags);
-		return;
-	}
-	QInIdle = 1;
-	spin_unlock_irqrestore(&txqueue_lock, flags);
-
-	/* this tri-states the IRQ line */
-	(void) inb_p(base+6);
-
-	oops = 100;
-
-loop:
-	if (0>oops--) { 
-		printk("idle: looped too many times\n");
-		goto done;
-	}
-
-	state = inb_p(base+6);
-	if (state != inb_p(base+6)) goto loop;
-
-	switch(state) {
-		case 0xfc:
-			/* incoming command */
-			if (debug & DEBUG_LOWER) printk("idle: fc\n");
-			handlefc(dev); 
-			break;
-		case 0xfd:
-			/* incoming data */
-			if(debug & DEBUG_LOWER) printk("idle: fd\n");
-			handlefd(dev); 
-			break;
-		case 0xf9:
-			/* result ready */
-			if (debug & DEBUG_LOWER) printk("idle: f9\n");
-			if(!mboxinuse[0]) {
-				mboxinuse[0] = 1;
-				qels[0].cbuf = rescbuf;
-				qels[0].cbuflen = 2;
-				qels[0].dbuf = resdbuf;
-				qels[0].dbuflen = 2;
-				qels[0].QWrite = 0;
-				qels[0].mailbox = 0;
-				enQ(&qels[0]);
-			}
-			inb_p(dev->base_addr+1);
-			inb_p(dev->base_addr+0);
-			if( wait_timeout(dev,0xf9) )
-				printk("timed out idle f9\n");
-			break;
-		case 0xf8:
-			/* ?? */
-			if (xmQhd) {
-				inb_p(dev->base_addr+1);
-				inb_p(dev->base_addr+0);
-				if(wait_timeout(dev,0xf8) )
-					printk("timed out idle f8\n");
-			} else {
-				goto done;
-			}
-			break;
-		case 0xfa:
-			/* waiting for command */
-			if(debug & DEBUG_LOWER) printk("idle: fa\n");
-			if (xmQhd) {
-				q=deQ();
-				memcpy(ltdmacbuf,q->cbuf,q->cbuflen);
-				ltdmacbuf[1] = q->mailbox;
-				if (debug>1) { 
-					int n;
-					printk("ltpc: sent command     ");
-					n = q->cbuflen;
-					if (n>100) n=100;
-					for(i=0;i<n;i++)
-						printk("%02x ",ltdmacbuf[i]);
-					printk("\n");
-				}
-				handlecommand(dev);
-					if(0xfa==inb_p(base+6)) {
-						/* we timed out, so return */
-						goto done;
-					} 
-			} else {
-				/* we don't seem to have a command */
-				if (!mboxinuse[0]) {
-					mboxinuse[0] = 1;
-					qels[0].cbuf = rescbuf;
-					qels[0].cbuflen = 2;
-					qels[0].dbuf = resdbuf;
-					qels[0].dbuflen = 2;
-					qels[0].QWrite = 0;
-					qels[0].mailbox = 0;
-					enQ(&qels[0]);
-				} else {
-					printk("trouble: response command already queued\n");
-					goto done;
-				}
-			} 
-			break;
-		case 0Xfb:
-			/* data transfer ready */
-			if(debug & DEBUG_LOWER) printk("idle: fb\n");
-			if(q->QWrite) {
-				memcpy(ltdmabuf,q->dbuf,q->dbuflen);
-				handlewrite(dev);
-			} else {
-				handleread(dev);
-				/* non-zero mailbox numbers are for
-				   commmands, 0 is for GETRESULT
-				   requests */
-				if(q->mailbox) {
-					memcpy(q->dbuf,ltdmabuf,q->dbuflen);
-				} else { 
-					/* this was a result */
-					mailbox[ 0x0f & ltdmabuf[0] ] = ltdmabuf[1];
-					mboxinuse[0]=0;
-				}
-			}
-			break;
-	}
-	goto loop;
-
-done:
-	QInIdle=0;
-
-	/* now set the interrupts back as appropriate */
-	/* the first read takes it out of tri-state (but still high) */
-	/* the second resets it */
-	/* note that after this point, any read of base+6 will
-	   trigger an interrupt */
-
-	if (dev->irq) {
-		inb_p(base+7);
-		inb_p(base+7);
-	}
-}
-
-
-static int do_write(struct net_device *dev, void *cbuf, int cbuflen,
-	void *dbuf, int dbuflen)
-{
-
-	int i = getmbox();
-	int ret;
-
-	if(i) {
-		qels[i].cbuf = (unsigned char *) cbuf;
-		qels[i].cbuflen = cbuflen;
-		qels[i].dbuf = (unsigned char *) dbuf;
-		qels[i].dbuflen = dbuflen;
-		qels[i].QWrite = 1;
-		qels[i].mailbox = i;  /* this should be initted rather */
-		enQ(&qels[i]);
-		idle(dev);
-		ret = mailbox[i];
-		mboxinuse[i]=0;
-		return ret;
-	}
-	printk("ltpc: could not allocate mbox\n");
-	return -1;
-}
-
-static int do_read(struct net_device *dev, void *cbuf, int cbuflen,
-	void *dbuf, int dbuflen)
-{
-
-	int i = getmbox();
-	int ret;
-
-	if(i) {
-		qels[i].cbuf = (unsigned char *) cbuf;
-		qels[i].cbuflen = cbuflen;
-		qels[i].dbuf = (unsigned char *) dbuf;
-		qels[i].dbuflen = dbuflen;
-		qels[i].QWrite = 0;
-		qels[i].mailbox = i;  /* this should be initted rather */
-		enQ(&qels[i]);
-		idle(dev);
-		ret = mailbox[i];
-		mboxinuse[i]=0;
-		return ret;
-	}
-	printk("ltpc: could not allocate mbox\n");
-	return -1;
-}
-
-/* end of idle handlers -- what should be seen is do_read, do_write */
-
-static struct timer_list ltpc_timer;
-
-static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev);
-
-static int read_30 ( struct net_device *dev)
-{
-	lt_command c;
-	c.getflags.command = LT_GETFLAGS;
-	return do_read(dev, &c, sizeof(c.getflags),&c,0);
-}
-
-static int set_30 (struct net_device *dev,int x)
-{
-	lt_command c;
-	c.setflags.command = LT_SETFLAGS;
-	c.setflags.flags = x;
-	return do_write(dev, &c, sizeof(c.setflags),&c,0);
-}
-
-/* LLAP to DDP translation */
-
-static int sendup_buffer (struct net_device *dev)
-{
-	/* on entry, command is in ltdmacbuf, data in ltdmabuf */
-	/* called from idle, non-reentrant */
-
-	int dnode, snode, llaptype, len; 
-	int sklen;
-	struct sk_buff *skb;
-	struct lt_rcvlap *ltc = (struct lt_rcvlap *) ltdmacbuf;
-
-	if (ltc->command != LT_RCVLAP) {
-		printk("unknown command 0x%02x from ltpc card\n",ltc->command);
-		return -1;
-	}
-	dnode = ltc->dnode;
-	snode = ltc->snode;
-	llaptype = ltc->laptype;
-	len = ltc->length; 
-
-	sklen = len;
-	if (llaptype == 1) 
-		sklen += 8;  /* correct for short ddp */
-	if(sklen > 800) {
-		printk(KERN_INFO "%s: nonsense length in ltpc command 0x14: 0x%08x\n",
-			dev->name,sklen);
-		return -1;
-	}
-
-	if ( (llaptype==0) || (llaptype>2) ) {
-		printk(KERN_INFO "%s: unknown LLAP type: %d\n",dev->name,llaptype);
-		return -1;
-	}
-
-
-	skb = dev_alloc_skb(3+sklen);
-	if (skb == NULL) 
-	{
-		printk("%s: dropping packet due to memory squeeze.\n",
-			dev->name);
-		return -1;
-	}
-	skb->dev = dev;
-
-	if (sklen > len)
-		skb_reserve(skb,8);
-	skb_put(skb,len+3);
-	skb->protocol = htons(ETH_P_LOCALTALK);
-	/* add LLAP header */
-	skb->data[0] = dnode;
-	skb->data[1] = snode;
-	skb->data[2] = llaptype;
-	skb_reset_mac_header(skb);	/* save pointer to llap header */
-	skb_pull(skb,3);
-
-	/* copy ddp(s,e)hdr + contents */
-	skb_copy_to_linear_data(skb, ltdmabuf, len);
-
-	skb_reset_transport_header(skb);
-
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += skb->len;
-
-	/* toss it onwards */
-	netif_rx(skb);
-	return 0;
-}
-
-/* the handler for the board interrupt */
- 
-static irqreturn_t
-ltpc_interrupt(int irq, void *dev_id)
-{
-	struct net_device *dev = dev_id;
-
-	if (dev==NULL) {
-		printk("ltpc_interrupt: unknown device.\n");
-		return IRQ_NONE;
-	}
-
-	inb_p(dev->base_addr+6);  /* disable further interrupts from board */
-
-	idle(dev); /* handle whatever is coming in */
- 
-	/* idle re-enables interrupts from board */ 
-
-	return IRQ_HANDLED;
-}
-
-/***
- *
- *    The ioctls that the driver responds to are:
- *
- *    SIOCSIFADDR -- do probe using the passed node hint.
- *    SIOCGIFADDR -- return net, node.
- *
- *    some of this stuff should be done elsewhere.
- *
- ***/
-
-static int ltpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct sockaddr_at *sa = (struct sockaddr_at *) &ifr->ifr_addr;
-	/* we'll keep the localtalk node address in dev->pa_addr */
-	struct ltpc_private *ltpc_priv = netdev_priv(dev);
-	struct atalk_addr *aa = &ltpc_priv->my_addr;
-	struct lt_init c;
-	int ltflags;
-
-	if(debug & DEBUG_VERBOSE) printk("ltpc_ioctl called\n");
-
-	switch(cmd) {
-		case SIOCSIFADDR:
-
-			aa->s_net  = sa->sat_addr.s_net;
-      
-			/* this does the probe and returns the node addr */
-			c.command = LT_INIT;
-			c.hint = sa->sat_addr.s_node;
-
-			aa->s_node = do_read(dev,&c,sizeof(c),&c,0);
-
-			/* get all llap frames raw */
-			ltflags = read_30(dev);
-			ltflags |= LT_FLAG_ALLLAP;
-			set_30 (dev,ltflags);  
-
-			dev->broadcast[0] = 0xFF;
-			dev->dev_addr[0] = aa->s_node;
-
-			dev->addr_len=1;
-   
-			return 0;
-
-		case SIOCGIFADDR:
-
-			sa->sat_addr.s_net = aa->s_net;
-			sa->sat_addr.s_node = aa->s_node;
-
-			return 0;
-
-		default: 
-			return -EINVAL;
-	}
-}
-
-static void set_multicast_list(struct net_device *dev)
-{
-	/* This needs to be present to keep netatalk happy. */
-	/* Actually netatalk needs fixing! */
-}
-
-static int ltpc_poll_counter;
-
-static void ltpc_poll(unsigned long l)
-{
-	struct net_device *dev = (struct net_device *) l;
-
-	del_timer(&ltpc_timer);
-
-	if(debug & DEBUG_VERBOSE) {
-		if (!ltpc_poll_counter) {
-			ltpc_poll_counter = 50;
-			printk("ltpc poll is alive\n");
-		}
-		ltpc_poll_counter--;
-	}
-  
-	if (!dev)
-		return;  /* we've been downed */
-
-	/* poll 20 times per second */
-	idle(dev);
-	ltpc_timer.expires = jiffies + HZ/20;
-	
-	add_timer(&ltpc_timer);
-}
-
-/* DDP to LLAP translation */
-
-static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	/* in kernel 1.3.xx, on entry skb->data points to ddp header,
-	 * and skb->len is the length of the ddp data + ddp header
-	 */
-	int i;
-	struct lt_sendlap cbuf;
-	unsigned char *hdr;
-
-	cbuf.command = LT_SENDLAP;
-	cbuf.dnode = skb->data[0];
-	cbuf.laptype = skb->data[2];
-	skb_pull(skb,3);	/* skip past LLAP header */
-	cbuf.length = skb->len;	/* this is host order */
-	skb_reset_transport_header(skb);
-
-	if(debug & DEBUG_UPPER) {
-		printk("command ");
-		for(i=0;i<6;i++)
-			printk("%02x ",((unsigned char *)&cbuf)[i]);
-		printk("\n");
-	}
-
-	hdr = skb_transport_header(skb);
-	do_write(dev, &cbuf, sizeof(cbuf), hdr, skb->len);
-
-	if(debug & DEBUG_UPPER) {
-		printk("sent %d ddp bytes\n",skb->len);
-		for (i = 0; i < skb->len; i++)
-			printk("%02x ", hdr[i]);
-		printk("\n");
-	}
-
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-}
-
-/* initialization stuff */
-  
-static int __init ltpc_probe_dma(int base, int dma)
-{
-	int want = (dma == 3) ? 2 : (dma == 1) ? 1 : 3;
-  	unsigned long timeout;
-  	unsigned long f;
-  
-  	if (want & 1) {
-		if (request_dma(1,"ltpc")) {
-			want &= ~1;
-		} else {
-			f=claim_dma_lock();
-			disable_dma(1);
-			clear_dma_ff(1);
-			set_dma_mode(1,DMA_MODE_WRITE);
-			set_dma_addr(1,virt_to_bus(ltdmabuf));
-			set_dma_count(1,sizeof(struct lt_mem));
-			enable_dma(1);
-			release_dma_lock(f);
-		}
-	}
-	if (want & 2) {
-		if (request_dma(3,"ltpc")) {
-			want &= ~2;
-		} else {
-			f=claim_dma_lock();
-			disable_dma(3);
-			clear_dma_ff(3);
-			set_dma_mode(3,DMA_MODE_WRITE);
-			set_dma_addr(3,virt_to_bus(ltdmabuf));
-			set_dma_count(3,sizeof(struct lt_mem));
-			enable_dma(3);
-			release_dma_lock(f);
-		}
-	}
-	/* set up request */
-
-	/* FIXME -- do timings better! */
-
-	ltdmabuf[0] = LT_READMEM;
-	ltdmabuf[1] = 1;  /* mailbox */
-	ltdmabuf[2] = 0; ltdmabuf[3] = 0;  /* address */
-	ltdmabuf[4] = 0; ltdmabuf[5] = 1;  /* read 0x0100 bytes */
-	ltdmabuf[6] = 0; /* dunno if this is necessary */
-
-	inb_p(io+1);
-	inb_p(io+0);
-	timeout = jiffies+100*HZ/100;
-	while(time_before(jiffies, timeout)) {
-		if ( 0xfa == inb_p(io+6) ) break;
-	}
-
-	inb_p(io+3);
-	inb_p(io+2);
-	while(time_before(jiffies, timeout)) {
-		if ( 0xfb == inb_p(io+6) ) break;
-	}
-
-	/* release the other dma channel (if we opened both of them) */
-
-	if ((want & 2) && (get_dma_residue(3)==sizeof(struct lt_mem))) {
-		want &= ~2;
-		free_dma(3);
-	}
-
-	if ((want & 1) && (get_dma_residue(1)==sizeof(struct lt_mem))) {
-		want &= ~1;
-		free_dma(1);
-	}
-
-	if (!want)
-		return 0;
-
-	return (want & 2) ? 3 : 1;
-}
-
-static const struct net_device_ops ltpc_netdev = {
-	.ndo_start_xmit		= ltpc_xmit,
-	.ndo_do_ioctl		= ltpc_ioctl,
-	.ndo_set_multicast_list = set_multicast_list,
-};
-
-struct net_device * __init ltpc_probe(void)
-{
-	struct net_device *dev;
-	int err = -ENOMEM;
-	int x=0,y=0;
-	int autoirq;
-	unsigned long f;
-	unsigned long timeout;
-
-	dev = alloc_ltalkdev(sizeof(struct ltpc_private));
-	if (!dev)
-		goto out;
-
-	/* probe for the I/O port address */
-	
-	if (io != 0x240 && request_region(0x220,8,"ltpc")) {
-		x = inb_p(0x220+6);
-		if ( (x!=0xff) && (x>=0xf0) ) {
-			io = 0x220;
-			goto got_port;
-		}
-		release_region(0x220,8);
-	}
-	if (io != 0x220 && request_region(0x240,8,"ltpc")) {
-		y = inb_p(0x240+6);
-		if ( (y!=0xff) && (y>=0xf0) ){ 
-			io = 0x240;
-			goto got_port;
-		}
-		release_region(0x240,8);
-	} 
-
-	/* give up in despair */
-	printk(KERN_ERR "LocalTalk card not found; 220 = %02x, 240 = %02x.\n", x,y);
-	err = -ENODEV;
-	goto out1;
-
- got_port:
-	/* probe for the IRQ line */
-	if (irq < 2) {
-		unsigned long irq_mask;
-
-		irq_mask = probe_irq_on();
-		/* reset the interrupt line */
-		inb_p(io+7);
-		inb_p(io+7);
-		/* trigger an interrupt (I hope) */
-		inb_p(io+6);
-		mdelay(2);
-		autoirq = probe_irq_off(irq_mask);
-
-		if (autoirq == 0) {
-			printk(KERN_ERR "ltpc: probe at %#x failed to detect IRQ line.\n", io);
-		} else {
-			irq = autoirq;
-		}
-	}
-
-	/* allocate a DMA buffer */
-	ltdmabuf = (unsigned char *) dma_mem_alloc(1000);
-	if (!ltdmabuf) {
-		printk(KERN_ERR "ltpc: mem alloc failed\n");
-		err = -ENOMEM;
-		goto out2;
-	}
-
-	ltdmacbuf = &ltdmabuf[800];
-
-	if(debug & DEBUG_VERBOSE) {
-		printk("ltdmabuf pointer %08lx\n",(unsigned long) ltdmabuf);
-	}
-
-	/* reset the card */
-
-	inb_p(io+1);
-	inb_p(io+3);
-
-	msleep(20);
-
-	inb_p(io+0);
-	inb_p(io+2);
-	inb_p(io+7); /* clear reset */
-	inb_p(io+4); 
-	inb_p(io+5);
-	inb_p(io+5); /* enable dma */
-	inb_p(io+6); /* tri-state interrupt line */
-
-	ssleep(1);
-	
-	/* now, figure out which dma channel we're using, unless it's
-	   already been specified */
-	/* well, 0 is a legal DMA channel, but the LTPC card doesn't
-	   use it... */
-	dma = ltpc_probe_dma(io, dma);
-	if (!dma) {  /* no dma channel */
-		printk(KERN_ERR "No DMA channel found on ltpc card.\n");
-		err = -ENODEV;
-		goto out3;
-	}
-
-	/* print out friendly message */
-	if(irq)
-		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, IR%d, DMA%d.\n",io,irq,dma);
-	else
-		printk(KERN_INFO "Apple/Farallon LocalTalk-PC card at %03x, DMA%d.  Using polled mode.\n",io,dma);
-
-	dev->netdev_ops = &ltpc_netdev;
-	dev->base_addr = io;
-	dev->irq = irq;
-	dev->dma = dma;
-
-	/* the card will want to send a result at this point */
-	/* (I think... leaving out this part makes the kernel crash,
-           so I put it back in...) */
-
-	f=claim_dma_lock();
-	disable_dma(dma);
-	clear_dma_ff(dma);
-	set_dma_mode(dma,DMA_MODE_READ);
-	set_dma_addr(dma,virt_to_bus(ltdmabuf));
-	set_dma_count(dma,0x100);
-	enable_dma(dma);
-	release_dma_lock(f);
-
-	(void) inb_p(io+3);
-	(void) inb_p(io+2);
-	timeout = jiffies+100*HZ/100;
-
-	while(time_before(jiffies, timeout)) {
-		if( 0xf9 == inb_p(io+6))
-			break;
-		schedule();
-	}
-
-	if(debug & DEBUG_VERBOSE) {
-		printk("setting up timer and irq\n");
-	}
-
-	/* grab it and don't let go :-) */
-	if (irq && request_irq( irq, ltpc_interrupt, 0, "ltpc", dev) >= 0)
-	{
-		(void) inb_p(io+7);  /* enable interrupts from board */
-		(void) inb_p(io+7);  /* and reset irq line */
-	} else {
-		if( irq )
-			printk(KERN_ERR "ltpc: IRQ already in use, using polled mode.\n");
-		dev->irq = 0;
-		/* polled mode -- 20 times per second */
-		/* this is really, really slow... should it poll more often? */
-		init_timer(&ltpc_timer);
-		ltpc_timer.function=ltpc_poll;
-		ltpc_timer.data = (unsigned long) dev;
-
-		ltpc_timer.expires = jiffies + HZ/20;
-		add_timer(&ltpc_timer);
-	}
-	err = register_netdev(dev);
-	if (err)
-		goto out4;
-
-	return NULL;
-out4:
-	del_timer_sync(&ltpc_timer);
-	if (dev->irq)
-		free_irq(dev->irq, dev);
-out3:
-	free_pages((unsigned long)ltdmabuf, get_order(1000));
-out2:
-	release_region(io, 8);
-out1:
-	free_netdev(dev);
-out:
-	return ERR_PTR(err);
-}
-
-#ifndef MODULE
-/* handles "ltpc=io,irq,dma" kernel command lines */
-static int __init ltpc_setup(char *str)
-{
-	int ints[5];
-
-	str = get_options(str, ARRAY_SIZE(ints), ints);
-
-	if (ints[0] == 0) {
-		if (str && !strncmp(str, "auto", 4)) {
-			/* do nothing :-) */
-		}
-		else {
-			/* usage message */
-			printk (KERN_ERR
-				"ltpc: usage: ltpc=auto|iobase[,irq[,dma]]\n");
-			return 0;
-		}
-	} else {
-		io = ints[1];
-		if (ints[0] > 1) {
-			irq = ints[2];
-		}
-		if (ints[0] > 2) {
-			dma = ints[3];
-		}
-		/* ignore any other parameters */
-	}
-	return 1;
-}
-
-__setup("ltpc=", ltpc_setup);
-#endif /* MODULE */
-
-static struct net_device *dev_ltpc;
-
-#ifdef MODULE
-
-MODULE_LICENSE("GPL");
-module_param(debug, int, 0);
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(dma, int, 0);
-
-
-static int __init ltpc_module_init(void)
-{
-        if(io == 0)
-		printk(KERN_NOTICE
-		       "ltpc: Autoprobing is not recommended for modules\n");
-
-	dev_ltpc = ltpc_probe();
-	if (IS_ERR(dev_ltpc))
-		return PTR_ERR(dev_ltpc);
-	return 0;
-}
-module_init(ltpc_module_init);
-#endif
-
-static void __exit ltpc_cleanup(void)
-{
-
-	if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n");
-	unregister_netdev(dev_ltpc);
-
-	ltpc_timer.data = 0;  /* signal the poll routine that we're done */
-
-	del_timer_sync(&ltpc_timer);
-
-	if(debug & DEBUG_VERBOSE) printk("freeing irq\n");
-
-	if (dev_ltpc->irq)
-		free_irq(dev_ltpc->irq, dev_ltpc);
-
-	if(debug & DEBUG_VERBOSE) printk("freeing dma\n");
-
-	if (dev_ltpc->dma)
-		free_dma(dev_ltpc->dma);
-
-	if(debug & DEBUG_VERBOSE) printk("freeing ioaddr\n");
-
-	if (dev_ltpc->base_addr)
-		release_region(dev_ltpc->base_addr,8);
-
-	free_netdev(dev_ltpc);
-
-	if(debug & DEBUG_VERBOSE) printk("free_pages\n");
-
-	free_pages( (unsigned long) ltdmabuf, get_order(1000));
-
-	if(debug & DEBUG_VERBOSE) printk("returning from cleanup_module\n");
-}
-
-module_exit(ltpc_cleanup);
diff --git a/drivers/staging/appletalk/ltpc.h b/drivers/staging/appletalk/ltpc.h
deleted file mode 100644
index cd30544a3729..000000000000
--- a/drivers/staging/appletalk/ltpc.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/***   ltpc.h
- *
- *
- ***/
-
-#define LT_GETRESULT  0x00
-#define LT_WRITEMEM   0x01
-#define LT_READMEM    0x02
-#define LT_GETFLAGS   0x04
-#define LT_SETFLAGS   0x05
-#define LT_INIT       0x10
-#define LT_SENDLAP    0x13
-#define LT_RCVLAP     0x14
-
-/* the flag that we care about */
-#define LT_FLAG_ALLLAP 0x04
-
-struct lt_getresult {
-	unsigned char command;
-	unsigned char mailbox;
-};
-
-struct lt_mem {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned short addr;	/* host order */
-	unsigned short length;	/* host order */
-};
-
-struct lt_setflags {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned char flags;
-};
-
-struct lt_getflags {
-	unsigned char command;
-	unsigned char mailbox;
-};
-
-struct lt_init {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned char hint;
-};
-
-struct lt_sendlap {
-	unsigned char command;
-	unsigned char mailbox;
-	unsigned char dnode;
-	unsigned char laptype;
-	unsigned short length;	/* host order */
-};
-
-struct lt_rcvlap {
-	unsigned char command;
-	unsigned char dnode;
-	unsigned char snode;
-	unsigned char laptype;
-	unsigned short length;	/* host order */
-};
-
-union lt_command {
-	struct lt_getresult getresult;
-	struct lt_mem mem;
-	struct lt_setflags setflags;
-	struct lt_getflags getflags;
-	struct lt_init init;
-	struct lt_sendlap sendlap;
-	struct lt_rcvlap rcvlap;
-};
-typedef union lt_command lt_command;
-
diff --git a/drivers/staging/appletalk/sysctl_net_atalk.c b/drivers/staging/appletalk/sysctl_net_atalk.c
deleted file mode 100644
index 4c896b625b2b..000000000000
--- a/drivers/staging/appletalk/sysctl_net_atalk.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * sysctl_net_atalk.c: sysctl interface to net AppleTalk subsystem.
- *
- * Begun April 1, 1996, Mike Shaver.
- * Added /proc/sys/net/atalk directory entry (empty =) ). [MS]
- * Dynamic registration, added aarp entries. (5/30/97 Chris Horn)
- */
-
-#include <linux/sysctl.h>
-#include <net/sock.h>
-#include "atalk.h"
-
-static struct ctl_table atalk_table[] = {
-	{
-		.procname	= "aarp-expiry-time",
-		.data		= &sysctl_aarp_expiry_time,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "aarp-tick-time",
-		.data		= &sysctl_aarp_tick_time,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "aarp-retransmit-limit",
-		.data		= &sysctl_aarp_retransmit_limit,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "aarp-resolve-time",
-		.data		= &sysctl_aarp_resolve_time,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{ },
-};
-
-static struct ctl_path atalk_path[] = {
-	{ .procname = "net", },
-	{ .procname = "appletalk", },
-	{ }
-};
-
-static struct ctl_table_header *atalk_table_header;
-
-void atalk_register_sysctl(void)
-{
-	atalk_table_header = register_sysctl_paths(atalk_path, atalk_table);
-}
-
-void atalk_unregister_sysctl(void)
-{
-	unregister_sysctl_table(atalk_table_header);
-}
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 86a2d7d905c0..61abb638b4bf 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -56,6 +56,7 @@
 #include <linux/syscalls.h>
 #include <linux/i2c.h>
 #include <linux/i2c-dev.h>
+#include <linux/atalk.h>
 #include <linux/gfp.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 362041b73a2f..2296d8b1931f 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -43,6 +43,7 @@ header-y += agpgart.h
 header-y += aio_abi.h
 header-y += apm_bios.h
 header-y += arcfb.h
+header-y += atalk.h
 header-y += atm.h
 header-y += atm_eni.h
 header-y += atm_he.h
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
new file mode 100644
index 000000000000..d34c187432ed
--- /dev/null
+++ b/include/linux/atalk.h
@@ -0,0 +1,208 @@
+#ifndef __LINUX_ATALK_H__
+#define __LINUX_ATALK_H__
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/*
+ * AppleTalk networking structures
+ *
+ * The following are directly referenced from the University Of Michigan
+ * netatalk for compatibility reasons.
+ */
+#define ATPORT_FIRST	1
+#define ATPORT_RESERVED	128
+#define ATPORT_LAST	254		/* 254 is only legal on localtalk */ 
+#define ATADDR_ANYNET	(__u16)0
+#define ATADDR_ANYNODE	(__u8)0
+#define ATADDR_ANYPORT  (__u8)0
+#define ATADDR_BCAST	(__u8)255
+#define DDP_MAXSZ	587
+#define DDP_MAXHOPS     15		/* 4 bits of hop counter */
+
+#define SIOCATALKDIFADDR       (SIOCPROTOPRIVATE + 0)
+
+struct atalk_addr {
+	__be16	s_net;
+	__u8	s_node;
+};
+
+struct sockaddr_at {
+	sa_family_t	  sat_family;
+	__u8		  sat_port;
+	struct atalk_addr sat_addr;
+	char		  sat_zero[8];
+};
+
+struct atalk_netrange {
+	__u8	nr_phase;
+	__be16	nr_firstnet;
+	__be16	nr_lastnet;
+};
+
+#ifdef __KERNEL__
+
+#include <net/sock.h>
+
+struct atalk_route {
+	struct net_device  *dev;
+	struct atalk_addr  target;
+	struct atalk_addr  gateway;
+	int		   flags;
+	struct atalk_route *next;
+};
+
+/**
+ *	struct atalk_iface - AppleTalk Interface
+ *	@dev - Network device associated with this interface
+ *	@address - Our address
+ *	@status - What are we doing?
+ *	@nets - Associated direct netrange
+ *	@next - next element in the list of interfaces
+ */
+struct atalk_iface {
+	struct net_device	*dev;
+	struct atalk_addr	address;
+	int			status;
+#define ATIF_PROBE	1		/* Probing for an address */
+#define ATIF_PROBE_FAIL	2		/* Probe collided */
+	struct atalk_netrange	nets;
+	struct atalk_iface	*next;
+};
+	
+struct atalk_sock {
+	/* struct sock has to be the first member of atalk_sock */
+	struct sock	sk;
+	__be16		dest_net;
+	__be16		src_net;
+	unsigned char	dest_node;
+	unsigned char	src_node;
+	unsigned char	dest_port;
+	unsigned char	src_port;
+};
+
+static inline struct atalk_sock *at_sk(struct sock *sk)
+{
+	return (struct atalk_sock *)sk;
+}
+
+struct ddpehdr {
+	__be16	deh_len_hops;	/* lower 10 bits are length, next 4 - hops */
+	__be16	deh_sum;
+	__be16	deh_dnet;
+	__be16	deh_snet;
+	__u8	deh_dnode;
+	__u8	deh_snode;
+	__u8	deh_dport;
+	__u8	deh_sport;
+	/* And netatalk apps expect to stick the type in themselves */
+};
+
+static __inline__ struct ddpehdr *ddp_hdr(struct sk_buff *skb)
+{
+	return (struct ddpehdr *)skb_transport_header(skb);
+}
+
+/* AppleTalk AARP headers */
+struct elapaarp {
+	__be16	hw_type;
+#define AARP_HW_TYPE_ETHERNET		1
+#define AARP_HW_TYPE_TOKENRING		2
+	__be16	pa_type;
+	__u8	hw_len;
+	__u8	pa_len;
+#define AARP_PA_ALEN			4
+	__be16	function;
+#define AARP_REQUEST			1
+#define AARP_REPLY			2
+#define AARP_PROBE			3
+	__u8	hw_src[ETH_ALEN];
+	__u8	pa_src_zero;
+	__be16	pa_src_net;
+	__u8	pa_src_node;
+	__u8	hw_dst[ETH_ALEN];
+	__u8	pa_dst_zero;
+	__be16	pa_dst_net;
+	__u8	pa_dst_node;
+} __attribute__ ((packed));
+
+static __inline__ struct elapaarp *aarp_hdr(struct sk_buff *skb)
+{
+	return (struct elapaarp *)skb_transport_header(skb);
+}
+
+/* Not specified - how long till we drop a resolved entry */
+#define AARP_EXPIRY_TIME	(5 * 60 * HZ)
+/* Size of hash table */
+#define AARP_HASH_SIZE		16
+/* Fast retransmission timer when resolving */
+#define AARP_TICK_TIME		(HZ / 5)
+/* Send 10 requests then give up (2 seconds) */
+#define AARP_RETRANSMIT_LIMIT	10
+/*
+ * Some value bigger than total retransmit time + a bit for last reply to
+ * appear and to stop continual requests
+ */
+#define AARP_RESOLVE_TIME	(10 * HZ)
+
+extern struct datalink_proto *ddp_dl, *aarp_dl;
+extern void aarp_proto_init(void);
+
+/* Inter module exports */
+
+/* Give a device find its atif control structure */
+static inline struct atalk_iface *atalk_find_dev(struct net_device *dev)
+{
+	return dev->atalk_ptr;
+}
+
+extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev);
+extern struct net_device *atrtr_get_dev(struct atalk_addr *sa);
+extern int		 aarp_send_ddp(struct net_device *dev,
+				       struct sk_buff *skb,
+				       struct atalk_addr *sa, void *hwaddr);
+extern void		 aarp_device_down(struct net_device *dev);
+extern void		 aarp_probe_network(struct atalk_iface *atif);
+extern int 		 aarp_proxy_probe_network(struct atalk_iface *atif,
+				     struct atalk_addr *sa);
+extern void		 aarp_proxy_remove(struct net_device *dev,
+					   struct atalk_addr *sa);
+
+extern void		aarp_cleanup_module(void);
+
+extern struct hlist_head atalk_sockets;
+extern rwlock_t atalk_sockets_lock;
+
+extern struct atalk_route *atalk_routes;
+extern rwlock_t atalk_routes_lock;
+
+extern struct atalk_iface *atalk_interfaces;
+extern rwlock_t atalk_interfaces_lock;
+
+extern struct atalk_route atrtr_default;
+
+extern const struct file_operations atalk_seq_arp_fops;
+
+extern int sysctl_aarp_expiry_time;
+extern int sysctl_aarp_tick_time;
+extern int sysctl_aarp_retransmit_limit;
+extern int sysctl_aarp_resolve_time;
+
+#ifdef CONFIG_SYSCTL
+extern void atalk_register_sysctl(void);
+extern void atalk_unregister_sysctl(void);
+#else
+#define atalk_register_sysctl()		do { } while(0)
+#define atalk_unregister_sysctl()	do { } while(0)
+#endif
+
+#ifdef CONFIG_PROC_FS
+extern int atalk_proc_init(void);
+extern void atalk_proc_exit(void);
+#else
+#define atalk_proc_init()	({ 0; })
+#define atalk_proc_exit()	do { } while(0)
+#endif /* CONFIG_PROC_FS */
+
+#endif /* __KERNEL__ */
+#endif /* __LINUX_ATALK_H__ */
diff --git a/net/Kconfig b/net/Kconfig
index 082c8bc977e1..72840626284b 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -204,6 +204,7 @@ source "net/8021q/Kconfig"
 source "net/decnet/Kconfig"
 source "net/llc/Kconfig"
 source "net/ipx/Kconfig"
+source "drivers/net/appletalk/Kconfig"
 source "net/x25/Kconfig"
 source "net/lapb/Kconfig"
 source "net/econet/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 16d9947b4b95..a3330ebe2c53 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
 obj-$(CONFIG_NET_DSA)		+= dsa/
 obj-$(CONFIG_IPX)		+= ipx/
+obj-$(CONFIG_ATALK)		+= appletalk/
 obj-$(CONFIG_WAN_ROUTER)	+= wanrouter/
 obj-$(CONFIG_X25)		+= x25/
 obj-$(CONFIG_LAPB)		+= lapb/
diff --git a/net/appletalk/Makefile b/net/appletalk/Makefile
new file mode 100644
index 000000000000..5cda56edef57
--- /dev/null
+++ b/net/appletalk/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for the Linux AppleTalk layer.
+#
+
+obj-$(CONFIG_ATALK) += appletalk.o
+
+appletalk-y			:= aarp.o ddp.o dev.o
+appletalk-$(CONFIG_PROC_FS)	+= atalk_proc.o
+appletalk-$(CONFIG_SYSCTL)	+= sysctl_net_atalk.o
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
new file mode 100644
index 000000000000..50dce7981321
--- /dev/null
+++ b/net/appletalk/aarp.c
@@ -0,0 +1,1063 @@
+/*
+ *	AARP:		An implementation of the AppleTalk AARP protocol for
+ *			Ethernet 'ELAP'.
+ *
+ *		Alan Cox  <Alan.Cox@linux.org>
+ *
+ *	This doesn't fit cleanly with the IP arp. Potentially we can use
+ *	the generic neighbour discovery code to clean this up.
+ *
+ *	FIXME:
+ *		We ought to handle the retransmits with a single list and a
+ *	separate fast timer for when it is needed.
+ *		Use neighbour discovery code.
+ *		Token Ring Support.
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ *
+ *	References:
+ *		Inside AppleTalk (2nd Ed).
+ *	Fixes:
+ *		Jaume Grau	-	flush caches on AARP_PROBE
+ *		Rob Newberry	-	Added proxy AARP and AARP proc fs,
+ *					moved probing from DDP module.
+ *		Arnaldo C. Melo -	don't mangle rx packets
+ *
+ */
+
+#include <linux/if_arp.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/datalink.h>
+#include <net/psnap.h>
+#include <linux/atalk.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
+int sysctl_aarp_tick_time = AARP_TICK_TIME;
+int sysctl_aarp_retransmit_limit = AARP_RETRANSMIT_LIMIT;
+int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
+
+/* Lists of aarp entries */
+/**
+ *	struct aarp_entry - AARP entry
+ *	@last_sent - Last time we xmitted the aarp request
+ *	@packet_queue - Queue of frames wait for resolution
+ *	@status - Used for proxy AARP
+ *	expires_at - Entry expiry time
+ *	target_addr - DDP Address
+ *	dev - Device to use
+ *	hwaddr - Physical i/f address of target/router
+ *	xmit_count - When this hits 10 we give up
+ *	next - Next entry in chain
+ */
+struct aarp_entry {
+	/* These first two are only used for unresolved entries */
+	unsigned long		last_sent;
+	struct sk_buff_head	packet_queue;
+	int			status;
+	unsigned long		expires_at;
+	struct atalk_addr	target_addr;
+	struct net_device	*dev;
+	char			hwaddr[6];
+	unsigned short		xmit_count;
+	struct aarp_entry	*next;
+};
+
+/* Hashed list of resolved, unresolved and proxy entries */
+static struct aarp_entry *resolved[AARP_HASH_SIZE];
+static struct aarp_entry *unresolved[AARP_HASH_SIZE];
+static struct aarp_entry *proxies[AARP_HASH_SIZE];
+static int unresolved_count;
+
+/* One lock protects it all. */
+static DEFINE_RWLOCK(aarp_lock);
+
+/* Used to walk the list and purge/kick entries.  */
+static struct timer_list aarp_timer;
+
+/*
+ *	Delete an aarp queue
+ *
+ *	Must run under aarp_lock.
+ */
+static void __aarp_expire(struct aarp_entry *a)
+{
+	skb_queue_purge(&a->packet_queue);
+	kfree(a);
+}
+
+/*
+ *	Send an aarp queue entry request
+ *
+ *	Must run under aarp_lock.
+ */
+static void __aarp_send_query(struct aarp_entry *a)
+{
+	static unsigned char aarp_eth_multicast[ETH_ALEN] =
+					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
+	struct net_device *dev = a->dev;
+	struct elapaarp *eah;
+	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
+	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
+	struct atalk_addr *sat = atalk_find_dev_addr(dev);
+
+	if (!skb)
+		return;
+
+	if (!sat) {
+		kfree_skb(skb);
+		return;
+	}
+
+	/* Set up the buffer */
+	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
+	skb->protocol    = htons(ETH_P_ATALK);
+	skb->dev	 = dev;
+	eah		 = aarp_hdr(skb);
+
+	/* Set up the ARP */
+	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
+	eah->pa_type	 = htons(ETH_P_ATALK);
+	eah->hw_len	 = ETH_ALEN;
+	eah->pa_len	 = AARP_PA_ALEN;
+	eah->function	 = htons(AARP_REQUEST);
+
+	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+
+	eah->pa_src_zero = 0;
+	eah->pa_src_net	 = sat->s_net;
+	eah->pa_src_node = sat->s_node;
+
+	memset(eah->hw_dst, '\0', ETH_ALEN);
+
+	eah->pa_dst_zero = 0;
+	eah->pa_dst_net	 = a->target_addr.s_net;
+	eah->pa_dst_node = a->target_addr.s_node;
+
+	/* Send it */
+	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
+	/* Update the sending count */
+	a->xmit_count++;
+	a->last_sent = jiffies;
+}
+
+/* This runs under aarp_lock and in softint context, so only atomic memory
+ * allocations can be used. */
+static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
+			    struct atalk_addr *them, unsigned char *sha)
+{
+	struct elapaarp *eah;
+	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
+	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
+
+	if (!skb)
+		return;
+
+	/* Set up the buffer */
+	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
+	skb->protocol    = htons(ETH_P_ATALK);
+	skb->dev	 = dev;
+	eah		 = aarp_hdr(skb);
+
+	/* Set up the ARP */
+	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
+	eah->pa_type	 = htons(ETH_P_ATALK);
+	eah->hw_len	 = ETH_ALEN;
+	eah->pa_len	 = AARP_PA_ALEN;
+	eah->function	 = htons(AARP_REPLY);
+
+	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+
+	eah->pa_src_zero = 0;
+	eah->pa_src_net	 = us->s_net;
+	eah->pa_src_node = us->s_node;
+
+	if (!sha)
+		memset(eah->hw_dst, '\0', ETH_ALEN);
+	else
+		memcpy(eah->hw_dst, sha, ETH_ALEN);
+
+	eah->pa_dst_zero = 0;
+	eah->pa_dst_net	 = them->s_net;
+	eah->pa_dst_node = them->s_node;
+
+	/* Send it */
+	aarp_dl->request(aarp_dl, skb, sha);
+}
+
+/*
+ *	Send probe frames. Called from aarp_probe_network and
+ *	aarp_proxy_probe_network.
+ */
+
+static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
+{
+	struct elapaarp *eah;
+	int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length;
+	struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC);
+	static unsigned char aarp_eth_multicast[ETH_ALEN] =
+					{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
+
+	if (!skb)
+		return;
+
+	/* Set up the buffer */
+	skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_put(skb, sizeof(*eah));
+	skb->protocol    = htons(ETH_P_ATALK);
+	skb->dev	 = dev;
+	eah		 = aarp_hdr(skb);
+
+	/* Set up the ARP */
+	eah->hw_type	 = htons(AARP_HW_TYPE_ETHERNET);
+	eah->pa_type	 = htons(ETH_P_ATALK);
+	eah->hw_len	 = ETH_ALEN;
+	eah->pa_len	 = AARP_PA_ALEN;
+	eah->function	 = htons(AARP_PROBE);
+
+	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+
+	eah->pa_src_zero = 0;
+	eah->pa_src_net	 = us->s_net;
+	eah->pa_src_node = us->s_node;
+
+	memset(eah->hw_dst, '\0', ETH_ALEN);
+
+	eah->pa_dst_zero = 0;
+	eah->pa_dst_net	 = us->s_net;
+	eah->pa_dst_node = us->s_node;
+
+	/* Send it */
+	aarp_dl->request(aarp_dl, skb, aarp_eth_multicast);
+}
+
+/*
+ *	Handle an aarp timer expire
+ *
+ *	Must run under the aarp_lock.
+ */
+
+static void __aarp_expire_timer(struct aarp_entry **n)
+{
+	struct aarp_entry *t;
+
+	while (*n)
+		/* Expired ? */
+		if (time_after(jiffies, (*n)->expires_at)) {
+			t = *n;
+			*n = (*n)->next;
+			__aarp_expire(t);
+		} else
+			n = &((*n)->next);
+}
+
+/*
+ *	Kick all pending requests 5 times a second.
+ *
+ *	Must run under the aarp_lock.
+ */
+static void __aarp_kick(struct aarp_entry **n)
+{
+	struct aarp_entry *t;
+
+	while (*n)
+		/* Expired: if this will be the 11th tx, we delete instead. */
+		if ((*n)->xmit_count >= sysctl_aarp_retransmit_limit) {
+			t = *n;
+			*n = (*n)->next;
+			__aarp_expire(t);
+		} else {
+			__aarp_send_query(*n);
+			n = &((*n)->next);
+		}
+}
+
+/*
+ *	A device has gone down. Take all entries referring to the device
+ *	and remove them.
+ *
+ *	Must run under the aarp_lock.
+ */
+static void __aarp_expire_device(struct aarp_entry **n, struct net_device *dev)
+{
+	struct aarp_entry *t;
+
+	while (*n)
+		if ((*n)->dev == dev) {
+			t = *n;
+			*n = (*n)->next;
+			__aarp_expire(t);
+		} else
+			n = &((*n)->next);
+}
+
+/* Handle the timer event */
+static void aarp_expire_timeout(unsigned long unused)
+{
+	int ct;
+
+	write_lock_bh(&aarp_lock);
+
+	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+		__aarp_expire_timer(&resolved[ct]);
+		__aarp_kick(&unresolved[ct]);
+		__aarp_expire_timer(&unresolved[ct]);
+		__aarp_expire_timer(&proxies[ct]);
+	}
+
+	write_unlock_bh(&aarp_lock);
+	mod_timer(&aarp_timer, jiffies +
+			       (unresolved_count ? sysctl_aarp_tick_time :
+				sysctl_aarp_expiry_time));
+}
+
+/* Network device notifier chain handler. */
+static int aarp_device_event(struct notifier_block *this, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *dev = ptr;
+	int ct;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_DOWN) {
+		write_lock_bh(&aarp_lock);
+
+		for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+			__aarp_expire_device(&resolved[ct], dev);
+			__aarp_expire_device(&unresolved[ct], dev);
+			__aarp_expire_device(&proxies[ct], dev);
+		}
+
+		write_unlock_bh(&aarp_lock);
+	}
+	return NOTIFY_DONE;
+}
+
+/* Expire all entries in a hash chain */
+static void __aarp_expire_all(struct aarp_entry **n)
+{
+	struct aarp_entry *t;
+
+	while (*n) {
+		t = *n;
+		*n = (*n)->next;
+		__aarp_expire(t);
+	}
+}
+
+/* Cleanup all hash chains -- module unloading */
+static void aarp_purge(void)
+{
+	int ct;
+
+	write_lock_bh(&aarp_lock);
+	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+		__aarp_expire_all(&resolved[ct]);
+		__aarp_expire_all(&unresolved[ct]);
+		__aarp_expire_all(&proxies[ct]);
+	}
+	write_unlock_bh(&aarp_lock);
+}
+
+/*
+ *	Create a new aarp entry.  This must use GFP_ATOMIC because it
+ *	runs while holding spinlocks.
+ */
+static struct aarp_entry *aarp_alloc(void)
+{
+	struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC);
+
+	if (a)
+		skb_queue_head_init(&a->packet_queue);
+	return a;
+}
+
+/*
+ * Find an entry. We might return an expired but not yet purged entry. We
+ * don't care as it will do no harm.
+ *
+ * This must run under the aarp_lock.
+ */
+static struct aarp_entry *__aarp_find_entry(struct aarp_entry *list,
+					    struct net_device *dev,
+					    struct atalk_addr *sat)
+{
+	while (list) {
+		if (list->target_addr.s_net == sat->s_net &&
+		    list->target_addr.s_node == sat->s_node &&
+		    list->dev == dev)
+			break;
+		list = list->next;
+	}
+
+	return list;
+}
+
+/* Called from the DDP code, and thus must be exported. */
+void aarp_proxy_remove(struct net_device *dev, struct atalk_addr *sa)
+{
+	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
+	struct aarp_entry *a;
+
+	write_lock_bh(&aarp_lock);
+
+	a = __aarp_find_entry(proxies[hash], dev, sa);
+	if (a)
+		a->expires_at = jiffies - 1;
+
+	write_unlock_bh(&aarp_lock);
+}
+
+/* This must run under aarp_lock. */
+static struct atalk_addr *__aarp_proxy_find(struct net_device *dev,
+					    struct atalk_addr *sa)
+{
+	int hash = sa->s_node % (AARP_HASH_SIZE - 1);
+	struct aarp_entry *a = __aarp_find_entry(proxies[hash], dev, sa);
+
+	return a ? sa : NULL;
+}
+
+/*
+ * Probe a Phase 1 device or a device that requires its Net:Node to
+ * be set via an ioctl.
+ */
+static void aarp_send_probe_phase1(struct atalk_iface *iface)
+{
+	struct ifreq atreq;
+	struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr;
+	const struct net_device_ops *ops = iface->dev->netdev_ops;
+
+	sa->sat_addr.s_node = iface->address.s_node;
+	sa->sat_addr.s_net = ntohs(iface->address.s_net);
+
+	/* We pass the Net:Node to the drivers/cards by a Device ioctl. */
+	if (!(ops->ndo_do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) {
+		ops->ndo_do_ioctl(iface->dev, &atreq, SIOCGIFADDR);
+		if (iface->address.s_net != htons(sa->sat_addr.s_net) ||
+		    iface->address.s_node != sa->sat_addr.s_node)
+			iface->status |= ATIF_PROBE_FAIL;
+
+		iface->address.s_net  = htons(sa->sat_addr.s_net);
+		iface->address.s_node = sa->sat_addr.s_node;
+	}
+}
+
+
+void aarp_probe_network(struct atalk_iface *atif)
+{
+	if (atif->dev->type == ARPHRD_LOCALTLK ||
+	    atif->dev->type == ARPHRD_PPP)
+		aarp_send_probe_phase1(atif);
+	else {
+		unsigned int count;
+
+		for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
+			aarp_send_probe(atif->dev, &atif->address);
+
+			/* Defer 1/10th */
+			msleep(100);
+
+			if (atif->status & ATIF_PROBE_FAIL)
+				break;
+		}
+	}
+}
+
+int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa)
+{
+	int hash, retval = -EPROTONOSUPPORT;
+	struct aarp_entry *entry;
+	unsigned int count;
+
+	/*
+	 * we don't currently support LocalTalk or PPP for proxy AARP;
+	 * if someone wants to try and add it, have fun
+	 */
+	if (atif->dev->type == ARPHRD_LOCALTLK ||
+	    atif->dev->type == ARPHRD_PPP)
+		goto out;
+
+	/*
+	 * create a new AARP entry with the flags set to be published --
+	 * we need this one to hang around even if it's in use
+	 */
+	entry = aarp_alloc();
+	retval = -ENOMEM;
+	if (!entry)
+		goto out;
+
+	entry->expires_at = -1;
+	entry->status = ATIF_PROBE;
+	entry->target_addr.s_node = sa->s_node;
+	entry->target_addr.s_net = sa->s_net;
+	entry->dev = atif->dev;
+
+	write_lock_bh(&aarp_lock);
+
+	hash = sa->s_node % (AARP_HASH_SIZE - 1);
+	entry->next = proxies[hash];
+	proxies[hash] = entry;
+
+	for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) {
+		aarp_send_probe(atif->dev, sa);
+
+		/* Defer 1/10th */
+		write_unlock_bh(&aarp_lock);
+		msleep(100);
+		write_lock_bh(&aarp_lock);
+
+		if (entry->status & ATIF_PROBE_FAIL)
+			break;
+	}
+
+	if (entry->status & ATIF_PROBE_FAIL) {
+		entry->expires_at = jiffies - 1; /* free the entry */
+		retval = -EADDRINUSE; /* return network full */
+	} else { /* clear the probing flag */
+		entry->status &= ~ATIF_PROBE;
+		retval = 1;
+	}
+
+	write_unlock_bh(&aarp_lock);
+out:
+	return retval;
+}
+
+/* Send a DDP frame */
+int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb,
+		  struct atalk_addr *sa, void *hwaddr)
+{
+	static char ddp_eth_multicast[ETH_ALEN] =
+		{ 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF };
+	int hash;
+	struct aarp_entry *a;
+
+	skb_reset_network_header(skb);
+
+	/* Check for LocalTalk first */
+	if (dev->type == ARPHRD_LOCALTLK) {
+		struct atalk_addr *at = atalk_find_dev_addr(dev);
+		struct ddpehdr *ddp = (struct ddpehdr *)skb->data;
+		int ft = 2;
+
+		/*
+		 * Compressible ?
+		 *
+		 * IFF: src_net == dest_net == device_net
+		 * (zero matches anything)
+		 */
+
+		if ((!ddp->deh_snet || at->s_net == ddp->deh_snet) &&
+		    (!ddp->deh_dnet || at->s_net == ddp->deh_dnet)) {
+			skb_pull(skb, sizeof(*ddp) - 4);
+
+			/*
+			 *	The upper two remaining bytes are the port
+			 *	numbers	we just happen to need. Now put the
+			 *	length in the lower two.
+			 */
+			*((__be16 *)skb->data) = htons(skb->len);
+			ft = 1;
+		}
+		/*
+		 * Nice and easy. No AARP type protocols occur here so we can
+		 * just shovel it out with a 3 byte LLAP header
+		 */
+
+		skb_push(skb, 3);
+		skb->data[0] = sa->s_node;
+		skb->data[1] = at->s_node;
+		skb->data[2] = ft;
+		skb->dev     = dev;
+		goto sendit;
+	}
+
+	/* On a PPP link we neither compress nor aarp.  */
+	if (dev->type == ARPHRD_PPP) {
+		skb->protocol = htons(ETH_P_PPPTALK);
+		skb->dev = dev;
+		goto sendit;
+	}
+
+	/* Non ELAP we cannot do. */
+	if (dev->type != ARPHRD_ETHER)
+		goto free_it;
+
+	skb->dev = dev;
+	skb->protocol = htons(ETH_P_ATALK);
+	hash = sa->s_node % (AARP_HASH_SIZE - 1);
+
+	/* Do we have a resolved entry? */
+	if (sa->s_node == ATADDR_BCAST) {
+		/* Send it */
+		ddp_dl->request(ddp_dl, skb, ddp_eth_multicast);
+		goto sent;
+	}
+
+	write_lock_bh(&aarp_lock);
+	a = __aarp_find_entry(resolved[hash], dev, sa);
+
+	if (a) { /* Return 1 and fill in the address */
+		a->expires_at = jiffies + (sysctl_aarp_expiry_time * 10);
+		ddp_dl->request(ddp_dl, skb, a->hwaddr);
+		write_unlock_bh(&aarp_lock);
+		goto sent;
+	}
+
+	/* Do we have an unresolved entry: This is the less common path */
+	a = __aarp_find_entry(unresolved[hash], dev, sa);
+	if (a) { /* Queue onto the unresolved queue */
+		skb_queue_tail(&a->packet_queue, skb);
+		goto out_unlock;
+	}
+
+	/* Allocate a new entry */
+	a = aarp_alloc();
+	if (!a) {
+		/* Whoops slipped... good job it's an unreliable protocol 8) */
+		write_unlock_bh(&aarp_lock);
+		goto free_it;
+	}
+
+	/* Set up the queue */
+	skb_queue_tail(&a->packet_queue, skb);
+	a->expires_at	 = jiffies + sysctl_aarp_resolve_time;
+	a->dev		 = dev;
+	a->next		 = unresolved[hash];
+	a->target_addr	 = *sa;
+	a->xmit_count	 = 0;
+	unresolved[hash] = a;
+	unresolved_count++;
+
+	/* Send an initial request for the address */
+	__aarp_send_query(a);
+
+	/*
+	 * Switch to fast timer if needed (That is if this is the first
+	 * unresolved entry to get added)
+	 */
+
+	if (unresolved_count == 1)
+		mod_timer(&aarp_timer, jiffies + sysctl_aarp_tick_time);
+
+	/* Now finally, it is safe to drop the lock. */
+out_unlock:
+	write_unlock_bh(&aarp_lock);
+
+	/* Tell the ddp layer we have taken over for this frame. */
+	goto sent;
+
+sendit:
+	if (skb->sk)
+		skb->priority = skb->sk->sk_priority;
+	if (dev_queue_xmit(skb))
+		goto drop;
+sent:
+	return NET_XMIT_SUCCESS;
+free_it:
+	kfree_skb(skb);
+drop:
+	return NET_XMIT_DROP;
+}
+EXPORT_SYMBOL(aarp_send_ddp);
+
+/*
+ *	An entry in the aarp unresolved queue has become resolved. Send
+ *	all the frames queued under it.
+ *
+ *	Must run under aarp_lock.
+ */
+static void __aarp_resolved(struct aarp_entry **list, struct aarp_entry *a,
+			    int hash)
+{
+	struct sk_buff *skb;
+
+	while (*list)
+		if (*list == a) {
+			unresolved_count--;
+			*list = a->next;
+
+			/* Move into the resolved list */
+			a->next = resolved[hash];
+			resolved[hash] = a;
+
+			/* Kick frames off */
+			while ((skb = skb_dequeue(&a->packet_queue)) != NULL) {
+				a->expires_at = jiffies +
+						sysctl_aarp_expiry_time * 10;
+				ddp_dl->request(ddp_dl, skb, a->hwaddr);
+			}
+		} else
+			list = &((*list)->next);
+}
+
+/*
+ *	This is called by the SNAP driver whenever we see an AARP SNAP
+ *	frame. We currently only support Ethernet.
+ */
+static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
+		    struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct elapaarp *ea = aarp_hdr(skb);
+	int hash, ret = 0;
+	__u16 function;
+	struct aarp_entry *a;
+	struct atalk_addr sa, *ma, da;
+	struct atalk_iface *ifa;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		goto out0;
+
+	/* We only do Ethernet SNAP AARP. */
+	if (dev->type != ARPHRD_ETHER)
+		goto out0;
+
+	/* Frame size ok? */
+	if (!skb_pull(skb, sizeof(*ea)))
+		goto out0;
+
+	function = ntohs(ea->function);
+
+	/* Sanity check fields. */
+	if (function < AARP_REQUEST || function > AARP_PROBE ||
+	    ea->hw_len != ETH_ALEN || ea->pa_len != AARP_PA_ALEN ||
+	    ea->pa_src_zero || ea->pa_dst_zero)
+		goto out0;
+
+	/* Looks good. */
+	hash = ea->pa_src_node % (AARP_HASH_SIZE - 1);
+
+	/* Build an address. */
+	sa.s_node = ea->pa_src_node;
+	sa.s_net = ea->pa_src_net;
+
+	/* Process the packet. Check for replies of me. */
+	ifa = atalk_find_dev(dev);
+	if (!ifa)
+		goto out1;
+
+	if (ifa->status & ATIF_PROBE &&
+	    ifa->address.s_node == ea->pa_dst_node &&
+	    ifa->address.s_net == ea->pa_dst_net) {
+		ifa->status |= ATIF_PROBE_FAIL; /* Fail the probe (in use) */
+		goto out1;
+	}
+
+	/* Check for replies of proxy AARP entries */
+	da.s_node = ea->pa_dst_node;
+	da.s_net  = ea->pa_dst_net;
+
+	write_lock_bh(&aarp_lock);
+	a = __aarp_find_entry(proxies[hash], dev, &da);
+
+	if (a && a->status & ATIF_PROBE) {
+		a->status |= ATIF_PROBE_FAIL;
+		/*
+		 * we do not respond to probe or request packets for
+		 * this address while we are probing this address
+		 */
+		goto unlock;
+	}
+
+	switch (function) {
+		case AARP_REPLY:
+			if (!unresolved_count)	/* Speed up */
+				break;
+
+			/* Find the entry.  */
+			a = __aarp_find_entry(unresolved[hash], dev, &sa);
+			if (!a || dev != a->dev)
+				break;
+
+			/* We can fill one in - this is good. */
+			memcpy(a->hwaddr, ea->hw_src, ETH_ALEN);
+			__aarp_resolved(&unresolved[hash], a, hash);
+			if (!unresolved_count)
+				mod_timer(&aarp_timer,
+					  jiffies + sysctl_aarp_expiry_time);
+			break;
+
+		case AARP_REQUEST:
+		case AARP_PROBE:
+
+			/*
+			 * If it is my address set ma to my address and reply.
+			 * We can treat probe and request the same.  Probe
+			 * simply means we shouldn't cache the querying host,
+			 * as in a probe they are proposing an address not
+			 * using one.
+			 *
+			 * Support for proxy-AARP added. We check if the
+			 * address is one of our proxies before we toss the
+			 * packet out.
+			 */
+
+			sa.s_node = ea->pa_dst_node;
+			sa.s_net  = ea->pa_dst_net;
+
+			/* See if we have a matching proxy. */
+			ma = __aarp_proxy_find(dev, &sa);
+			if (!ma)
+				ma = &ifa->address;
+			else { /* We need to make a copy of the entry. */
+				da.s_node = sa.s_node;
+				da.s_net = sa.s_net;
+				ma = &da;
+			}
+
+			if (function == AARP_PROBE) {
+				/*
+				 * A probe implies someone trying to get an
+				 * address. So as a precaution flush any
+				 * entries we have for this address.
+				 */
+				a = __aarp_find_entry(resolved[sa.s_node %
+							  (AARP_HASH_SIZE - 1)],
+						      skb->dev, &sa);
+
+				/*
+				 * Make it expire next tick - that avoids us
+				 * getting into a probe/flush/learn/probe/
+				 * flush/learn cycle during probing of a slow
+				 * to respond host addr.
+				 */
+				if (a) {
+					a->expires_at = jiffies - 1;
+					mod_timer(&aarp_timer, jiffies +
+							sysctl_aarp_tick_time);
+				}
+			}
+
+			if (sa.s_node != ma->s_node)
+				break;
+
+			if (sa.s_net && ma->s_net && sa.s_net != ma->s_net)
+				break;
+
+			sa.s_node = ea->pa_src_node;
+			sa.s_net = ea->pa_src_net;
+
+			/* aarp_my_address has found the address to use for us.
+			*/
+			aarp_send_reply(dev, ma, &sa, ea->hw_src);
+			break;
+	}
+
+unlock:
+	write_unlock_bh(&aarp_lock);
+out1:
+	ret = 1;
+out0:
+	kfree_skb(skb);
+	return ret;
+}
+
+static struct notifier_block aarp_notifier = {
+	.notifier_call = aarp_device_event,
+};
+
+static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 };
+
+void __init aarp_proto_init(void)
+{
+	aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv);
+	if (!aarp_dl)
+		printk(KERN_CRIT "Unable to register AARP with SNAP.\n");
+	setup_timer(&aarp_timer, aarp_expire_timeout, 0);
+	aarp_timer.expires  = jiffies + sysctl_aarp_expiry_time;
+	add_timer(&aarp_timer);
+	register_netdevice_notifier(&aarp_notifier);
+}
+
+/* Remove the AARP entries associated with a device. */
+void aarp_device_down(struct net_device *dev)
+{
+	int ct;
+
+	write_lock_bh(&aarp_lock);
+
+	for (ct = 0; ct < AARP_HASH_SIZE; ct++) {
+		__aarp_expire_device(&resolved[ct], dev);
+		__aarp_expire_device(&unresolved[ct], dev);
+		__aarp_expire_device(&proxies[ct], dev);
+	}
+
+	write_unlock_bh(&aarp_lock);
+}
+
+#ifdef CONFIG_PROC_FS
+struct aarp_iter_state {
+	int bucket;
+	struct aarp_entry **table;
+};
+
+/*
+ * Get the aarp entry that is in the chain described
+ * by the iterator.
+ * If pos is set then skip till that index.
+ * pos = 1 is the first entry
+ */
+static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
+{
+	int ct = iter->bucket;
+	struct aarp_entry **table = iter->table;
+	loff_t off = 0;
+	struct aarp_entry *entry;
+
+ rescan:
+	while(ct < AARP_HASH_SIZE) {
+		for (entry = table[ct]; entry; entry = entry->next) {
+			if (!pos || ++off == *pos) {
+				iter->table = table;
+				iter->bucket = ct;
+				return entry;
+			}
+		}
+		++ct;
+	}
+
+	if (table == resolved) {
+		ct = 0;
+		table = unresolved;
+		goto rescan;
+	}
+	if (table == unresolved) {
+		ct = 0;
+		table = proxies;
+		goto rescan;
+	}
+	return NULL;
+}
+
+static void *aarp_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(aarp_lock)
+{
+	struct aarp_iter_state *iter = seq->private;
+
+	read_lock_bh(&aarp_lock);
+	iter->table     = resolved;
+	iter->bucket    = 0;
+
+	return *pos ? iter_next(iter, pos) : SEQ_START_TOKEN;
+}
+
+static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct aarp_entry *entry = v;
+	struct aarp_iter_state *iter = seq->private;
+
+	++*pos;
+
+	/* first line after header */
+	if (v == SEQ_START_TOKEN)
+		entry = iter_next(iter, NULL);
+
+	/* next entry in current bucket */
+	else if (entry->next)
+		entry = entry->next;
+
+	/* next bucket or table */
+	else {
+		++iter->bucket;
+		entry = iter_next(iter, NULL);
+	}
+	return entry;
+}
+
+static void aarp_seq_stop(struct seq_file *seq, void *v)
+	__releases(aarp_lock)
+{
+	read_unlock_bh(&aarp_lock);
+}
+
+static const char *dt2str(unsigned long ticks)
+{
+	static char buf[32];
+
+	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
+
+	return buf;
+}
+
+static int aarp_seq_show(struct seq_file *seq, void *v)
+{
+	struct aarp_iter_state *iter = seq->private;
+	struct aarp_entry *entry = v;
+	unsigned long now = jiffies;
+
+	if (v == SEQ_START_TOKEN)
+		seq_puts(seq,
+			 "Address  Interface   Hardware Address"
+			 "   Expires LastSend  Retry Status\n");
+	else {
+		seq_printf(seq, "%04X:%02X  %-12s",
+			   ntohs(entry->target_addr.s_net),
+			   (unsigned int) entry->target_addr.s_node,
+			   entry->dev ? entry->dev->name : "????");
+		seq_printf(seq, "%pM", entry->hwaddr);
+		seq_printf(seq, " %8s",
+			   dt2str((long)entry->expires_at - (long)now));
+		if (iter->table == unresolved)
+			seq_printf(seq, " %8s %6hu",
+				   dt2str(now - entry->last_sent),
+				   entry->xmit_count);
+		else
+			seq_puts(seq, "                ");
+		seq_printf(seq, " %s\n",
+			   (iter->table == resolved) ? "resolved"
+			   : (iter->table == unresolved) ? "unresolved"
+			   : (iter->table == proxies) ? "proxies"
+			   : "unknown");
+	}
+	return 0;
+}
+
+static const struct seq_operations aarp_seq_ops = {
+	.start  = aarp_seq_start,
+	.next   = aarp_seq_next,
+	.stop   = aarp_seq_stop,
+	.show   = aarp_seq_show,
+};
+
+static int aarp_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open_private(file, &aarp_seq_ops,
+			sizeof(struct aarp_iter_state));
+}
+
+const struct file_operations atalk_seq_arp_fops = {
+	.owner		= THIS_MODULE,
+	.open           = aarp_seq_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release	= seq_release_private,
+};
+#endif
+
+/* General module cleanup. Called from cleanup_module() in ddp.c. */
+void aarp_cleanup_module(void)
+{
+	del_timer_sync(&aarp_timer);
+	unregister_netdevice_notifier(&aarp_notifier);
+	unregister_snap_client(aarp_dl);
+	aarp_purge();
+}
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
new file mode 100644
index 000000000000..6ef0e761e5de
--- /dev/null
+++ b/net/appletalk/atalk_proc.c
@@ -0,0 +1,301 @@
+/*
+ * 	atalk_proc.c - proc support for Appletalk
+ *
+ * 	Copyright(c) Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ *	This program is free software; you can redistribute it and/or modify it
+ *	under the terms of the GNU General Public License as published by the
+ *	Free Software Foundation, version 2.
+ */
+
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <linux/atalk.h>
+
+
+static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos)
+{
+	struct atalk_iface *i;
+
+	for (i = atalk_interfaces; pos && i; i = i->next)
+		--pos;
+
+	return i;
+}
+
+static void *atalk_seq_interface_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_interfaces_lock)
+{
+	loff_t l = *pos;
+
+	read_lock_bh(&atalk_interfaces_lock);
+	return l ? atalk_get_interface_idx(--l) : SEQ_START_TOKEN;
+}
+
+static void *atalk_seq_interface_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct atalk_iface *i;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN) {
+		i = NULL;
+		if (atalk_interfaces)
+			i = atalk_interfaces;
+		goto out;
+	}
+	i = v;
+	i = i->next;
+out:
+	return i;
+}
+
+static void atalk_seq_interface_stop(struct seq_file *seq, void *v)
+	__releases(atalk_interfaces_lock)
+{
+	read_unlock_bh(&atalk_interfaces_lock);
+}
+
+static int atalk_seq_interface_show(struct seq_file *seq, void *v)
+{
+	struct atalk_iface *iface;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Interface        Address   Networks  "
+			      "Status\n");
+		goto out;
+	}
+
+	iface = v;
+	seq_printf(seq, "%-16s %04X:%02X  %04X-%04X  %d\n",
+		   iface->dev->name, ntohs(iface->address.s_net),
+		   iface->address.s_node, ntohs(iface->nets.nr_firstnet),
+		   ntohs(iface->nets.nr_lastnet), iface->status);
+out:
+	return 0;
+}
+
+static __inline__ struct atalk_route *atalk_get_route_idx(loff_t pos)
+{
+	struct atalk_route *r;
+
+	for (r = atalk_routes; pos && r; r = r->next)
+		--pos;
+
+	return r;
+}
+
+static void *atalk_seq_route_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_routes_lock)
+{
+	loff_t l = *pos;
+
+	read_lock_bh(&atalk_routes_lock);
+	return l ? atalk_get_route_idx(--l) : SEQ_START_TOKEN;
+}
+
+static void *atalk_seq_route_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct atalk_route *r;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN) {
+		r = NULL;
+		if (atalk_routes)
+			r = atalk_routes;
+		goto out;
+	}
+	r = v;
+	r = r->next;
+out:
+	return r;
+}
+
+static void atalk_seq_route_stop(struct seq_file *seq, void *v)
+	__releases(atalk_routes_lock)
+{
+	read_unlock_bh(&atalk_routes_lock);
+}
+
+static int atalk_seq_route_show(struct seq_file *seq, void *v)
+{
+	struct atalk_route *rt;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Target        Router  Flags Dev\n");
+		goto out;
+	}
+
+	if (atrtr_default.dev) {
+		rt = &atrtr_default;
+		seq_printf(seq, "Default     %04X:%02X  %-4d  %s\n",
+			       ntohs(rt->gateway.s_net), rt->gateway.s_node,
+			       rt->flags, rt->dev->name);
+	}
+
+	rt = v;
+	seq_printf(seq, "%04X:%02X     %04X:%02X  %-4d  %s\n",
+		   ntohs(rt->target.s_net), rt->target.s_node,
+		   ntohs(rt->gateway.s_net), rt->gateway.s_node,
+		   rt->flags, rt->dev->name);
+out:
+	return 0;
+}
+
+static void *atalk_seq_socket_start(struct seq_file *seq, loff_t *pos)
+	__acquires(atalk_sockets_lock)
+{
+	read_lock_bh(&atalk_sockets_lock);
+	return seq_hlist_start_head(&atalk_sockets, *pos);
+}
+
+static void *atalk_seq_socket_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	return seq_hlist_next(v, &atalk_sockets, pos);
+}
+
+static void atalk_seq_socket_stop(struct seq_file *seq, void *v)
+	__releases(atalk_sockets_lock)
+{
+	read_unlock_bh(&atalk_sockets_lock);
+}
+
+static int atalk_seq_socket_show(struct seq_file *seq, void *v)
+{
+	struct sock *s;
+	struct atalk_sock *at;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_printf(seq, "Type Local_addr  Remote_addr Tx_queue "
+				"Rx_queue St UID\n");
+		goto out;
+	}
+
+	s = sk_entry(v);
+	at = at_sk(s);
+
+	seq_printf(seq, "%02X   %04X:%02X:%02X  %04X:%02X:%02X  %08X:%08X "
+			"%02X %d\n",
+		   s->sk_type, ntohs(at->src_net), at->src_node, at->src_port,
+		   ntohs(at->dest_net), at->dest_node, at->dest_port,
+		   sk_wmem_alloc_get(s),
+		   sk_rmem_alloc_get(s),
+		   s->sk_state, SOCK_INODE(s->sk_socket)->i_uid);
+out:
+	return 0;
+}
+
+static const struct seq_operations atalk_seq_interface_ops = {
+	.start  = atalk_seq_interface_start,
+	.next   = atalk_seq_interface_next,
+	.stop   = atalk_seq_interface_stop,
+	.show   = atalk_seq_interface_show,
+};
+
+static const struct seq_operations atalk_seq_route_ops = {
+	.start  = atalk_seq_route_start,
+	.next   = atalk_seq_route_next,
+	.stop   = atalk_seq_route_stop,
+	.show   = atalk_seq_route_show,
+};
+
+static const struct seq_operations atalk_seq_socket_ops = {
+	.start  = atalk_seq_socket_start,
+	.next   = atalk_seq_socket_next,
+	.stop   = atalk_seq_socket_stop,
+	.show   = atalk_seq_socket_show,
+};
+
+static int atalk_seq_interface_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &atalk_seq_interface_ops);
+}
+
+static int atalk_seq_route_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &atalk_seq_route_ops);
+}
+
+static int atalk_seq_socket_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &atalk_seq_socket_ops);
+}
+
+static const struct file_operations atalk_seq_interface_fops = {
+	.owner		= THIS_MODULE,
+	.open		= atalk_seq_interface_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static const struct file_operations atalk_seq_route_fops = {
+	.owner		= THIS_MODULE,
+	.open		= atalk_seq_route_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static const struct file_operations atalk_seq_socket_fops = {
+	.owner		= THIS_MODULE,
+	.open		= atalk_seq_socket_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static struct proc_dir_entry *atalk_proc_dir;
+
+int __init atalk_proc_init(void)
+{
+	struct proc_dir_entry *p;
+	int rc = -ENOMEM;
+
+	atalk_proc_dir = proc_mkdir("atalk", init_net.proc_net);
+	if (!atalk_proc_dir)
+		goto out;
+
+	p = proc_create("interface", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_interface_fops);
+	if (!p)
+		goto out_interface;
+
+	p = proc_create("route", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_route_fops);
+	if (!p)
+		goto out_route;
+
+	p = proc_create("socket", S_IRUGO, atalk_proc_dir,
+			&atalk_seq_socket_fops);
+	if (!p)
+		goto out_socket;
+
+	p = proc_create("arp", S_IRUGO, atalk_proc_dir, &atalk_seq_arp_fops);
+	if (!p)
+		goto out_arp;
+
+	rc = 0;
+out:
+	return rc;
+out_arp:
+	remove_proc_entry("socket", atalk_proc_dir);
+out_socket:
+	remove_proc_entry("route", atalk_proc_dir);
+out_route:
+	remove_proc_entry("interface", atalk_proc_dir);
+out_interface:
+	remove_proc_entry("atalk", init_net.proc_net);
+	goto out;
+}
+
+void __exit atalk_proc_exit(void)
+{
+	remove_proc_entry("interface", atalk_proc_dir);
+	remove_proc_entry("route", atalk_proc_dir);
+	remove_proc_entry("socket", atalk_proc_dir);
+	remove_proc_entry("arp", atalk_proc_dir);
+	remove_proc_entry("atalk", init_net.proc_net);
+}
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
new file mode 100644
index 000000000000..c410b93fda2e
--- /dev/null
+++ b/net/appletalk/ddp.c
@@ -0,0 +1,1981 @@
+/*
+ *	DDP:	An implementation of the AppleTalk DDP protocol for
+ *		Ethernet 'ELAP'.
+ *
+ *		Alan Cox  <alan@lxorguk.ukuu.org.uk>
+ *
+ *		With more than a little assistance from
+ *
+ *		Wesley Craig <netatalk@umich.edu>
+ *
+ *	Fixes:
+ *		Neil Horman		:	Added missing device ioctls
+ *		Michael Callahan	:	Made routing work
+ *		Wesley Craig		:	Fix probing to listen to a
+ *						passed node id.
+ *		Alan Cox		:	Added send/recvmsg support
+ *		Alan Cox		:	Moved at. to protinfo in
+ *						socket.
+ *		Alan Cox		:	Added firewall hooks.
+ *		Alan Cox		:	Supports new ARPHRD_LOOPBACK
+ *		Christer Weinigel	: 	Routing and /proc fixes.
+ *		Bradford Johnson	:	LocalTalk.
+ *		Tom Dyas		:	Module support.
+ *		Alan Cox		:	Hooks for PPP (based on the
+ *						LocalTalk hook).
+ *		Alan Cox		:	Posix bits
+ *		Alan Cox/Mike Freeman	:	Possible fix to NBP problems
+ *		Bradford Johnson	:	IP-over-DDP (experimental)
+ *		Jay Schulist		:	Moved IP-over-DDP to its own
+ *						driver file. (ipddp.c & ipddp.h)
+ *		Jay Schulist		:	Made work as module with
+ *						AppleTalk drivers, cleaned it.
+ *		Rob Newberry		:	Added proxy AARP and AARP
+ *						procfs, moved probing to AARP
+ *						module.
+ *              Adrian Sun/
+ *              Michael Zuelsdorff      :       fix for net.0 packets. don't
+ *                                              allow illegal ether/tokentalk
+ *                                              port assignment. we lose a
+ *                                              valid localtalk port as a
+ *                                              result.
+ *		Arnaldo C. de Melo	:	Cleanup, in preparation for
+ *						shared skb support 8)
+ *		Arnaldo C. de Melo	:	Move proc stuff to atalk_proc.c,
+ *						use seq_file
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/smp_lock.h>
+#include <linux/termios.h>	/* For TIOCOUTQ/INQ */
+#include <linux/compat.h>
+#include <linux/slab.h>
+#include <net/datalink.h>
+#include <net/psnap.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+#include <net/route.h>
+#include <linux/atalk.h>
+#include "../core/kmap_skb.h"
+
+struct datalink_proto *ddp_dl, *aarp_dl;
+static const struct proto_ops atalk_dgram_ops;
+
+/**************************************************************************\
+*                                                                          *
+* Handlers for the socket list.                                            *
+*                                                                          *
+\**************************************************************************/
+
+HLIST_HEAD(atalk_sockets);
+DEFINE_RWLOCK(atalk_sockets_lock);
+
+static inline void __atalk_insert_socket(struct sock *sk)
+{
+	sk_add_node(sk, &atalk_sockets);
+}
+
+static inline void atalk_remove_socket(struct sock *sk)
+{
+	write_lock_bh(&atalk_sockets_lock);
+	sk_del_node_init(sk);
+	write_unlock_bh(&atalk_sockets_lock);
+}
+
+static struct sock *atalk_search_socket(struct sockaddr_at *to,
+					struct atalk_iface *atif)
+{
+	struct sock *s;
+	struct hlist_node *node;
+
+	read_lock_bh(&atalk_sockets_lock);
+	sk_for_each(s, node, &atalk_sockets) {
+		struct atalk_sock *at = at_sk(s);
+
+		if (to->sat_port != at->src_port)
+			continue;
+
+		if (to->sat_addr.s_net == ATADDR_ANYNET &&
+		    to->sat_addr.s_node == ATADDR_BCAST)
+			goto found;
+
+		if (to->sat_addr.s_net == at->src_net &&
+		    (to->sat_addr.s_node == at->src_node ||
+		     to->sat_addr.s_node == ATADDR_BCAST ||
+		     to->sat_addr.s_node == ATADDR_ANYNODE))
+			goto found;
+
+		/* XXXX.0 -- we got a request for this router. make sure
+		 * that the node is appropriately set. */
+		if (to->sat_addr.s_node == ATADDR_ANYNODE &&
+		    to->sat_addr.s_net != ATADDR_ANYNET &&
+		    atif->address.s_node == at->src_node) {
+			to->sat_addr.s_node = atif->address.s_node;
+			goto found;
+		}
+	}
+	s = NULL;
+found:
+	read_unlock_bh(&atalk_sockets_lock);
+	return s;
+}
+
+/**
+ * atalk_find_or_insert_socket - Try to find a socket matching ADDR
+ * @sk - socket to insert in the list if it is not there already
+ * @sat - address to search for
+ *
+ * Try to find a socket matching ADDR in the socket list, if found then return
+ * it. If not, insert SK into the socket list.
+ *
+ * This entire operation must execute atomically.
+ */
+static struct sock *atalk_find_or_insert_socket(struct sock *sk,
+						struct sockaddr_at *sat)
+{
+	struct sock *s;
+	struct hlist_node *node;
+	struct atalk_sock *at;
+
+	write_lock_bh(&atalk_sockets_lock);
+	sk_for_each(s, node, &atalk_sockets) {
+		at = at_sk(s);
+
+		if (at->src_net == sat->sat_addr.s_net &&
+		    at->src_node == sat->sat_addr.s_node &&
+		    at->src_port == sat->sat_port)
+			goto found;
+	}
+	s = NULL;
+	__atalk_insert_socket(sk); /* Wheee, it's free, assign and insert. */
+found:
+	write_unlock_bh(&atalk_sockets_lock);
+	return s;
+}
+
+static void atalk_destroy_timer(unsigned long data)
+{
+	struct sock *sk = (struct sock *)data;
+
+	if (sk_has_allocations(sk)) {
+		sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME;
+		add_timer(&sk->sk_timer);
+	} else
+		sock_put(sk);
+}
+
+static inline void atalk_destroy_socket(struct sock *sk)
+{
+	atalk_remove_socket(sk);
+	skb_queue_purge(&sk->sk_receive_queue);
+
+	if (sk_has_allocations(sk)) {
+		setup_timer(&sk->sk_timer, atalk_destroy_timer,
+				(unsigned long)sk);
+		sk->sk_timer.expires	= jiffies + SOCK_DESTROY_TIME;
+		add_timer(&sk->sk_timer);
+	} else
+		sock_put(sk);
+}
+
+/**************************************************************************\
+*                                                                          *
+* Routing tables for the AppleTalk socket layer.                           *
+*                                                                          *
+\**************************************************************************/
+
+/* Anti-deadlock ordering is atalk_routes_lock --> iface_lock -DaveM */
+struct atalk_route *atalk_routes;
+DEFINE_RWLOCK(atalk_routes_lock);
+
+struct atalk_iface *atalk_interfaces;
+DEFINE_RWLOCK(atalk_interfaces_lock);
+
+/* For probing devices or in a routerless network */
+struct atalk_route atrtr_default;
+
+/* AppleTalk interface control */
+/*
+ * Drop a device. Doesn't drop any of its routes - that is the caller's
+ * problem. Called when we down the interface or delete the address.
+ */
+static void atif_drop_device(struct net_device *dev)
+{
+	struct atalk_iface **iface = &atalk_interfaces;
+	struct atalk_iface *tmp;
+
+	write_lock_bh(&atalk_interfaces_lock);
+	while ((tmp = *iface) != NULL) {
+		if (tmp->dev == dev) {
+			*iface = tmp->next;
+			dev_put(dev);
+			kfree(tmp);
+			dev->atalk_ptr = NULL;
+		} else
+			iface = &tmp->next;
+	}
+	write_unlock_bh(&atalk_interfaces_lock);
+}
+
+static struct atalk_iface *atif_add_device(struct net_device *dev,
+					   struct atalk_addr *sa)
+{
+	struct atalk_iface *iface = kzalloc(sizeof(*iface), GFP_KERNEL);
+
+	if (!iface)
+		goto out;
+
+	dev_hold(dev);
+	iface->dev = dev;
+	dev->atalk_ptr = iface;
+	iface->address = *sa;
+	iface->status = 0;
+
+	write_lock_bh(&atalk_interfaces_lock);
+	iface->next = atalk_interfaces;
+	atalk_interfaces = iface;
+	write_unlock_bh(&atalk_interfaces_lock);
+out:
+	return iface;
+}
+
+/* Perform phase 2 AARP probing on our tentative address */
+static int atif_probe_device(struct atalk_iface *atif)
+{
+	int netrange = ntohs(atif->nets.nr_lastnet) -
+			ntohs(atif->nets.nr_firstnet) + 1;
+	int probe_net = ntohs(atif->address.s_net);
+	int probe_node = atif->address.s_node;
+	int netct, nodect;
+
+	/* Offset the network we start probing with */
+	if (probe_net == ATADDR_ANYNET) {
+		probe_net = ntohs(atif->nets.nr_firstnet);
+		if (netrange)
+			probe_net += jiffies % netrange;
+	}
+	if (probe_node == ATADDR_ANYNODE)
+		probe_node = jiffies & 0xFF;
+
+	/* Scan the networks */
+	atif->status |= ATIF_PROBE;
+	for (netct = 0; netct <= netrange; netct++) {
+		/* Sweep the available nodes from a given start */
+		atif->address.s_net = htons(probe_net);
+		for (nodect = 0; nodect < 256; nodect++) {
+			atif->address.s_node = (nodect + probe_node) & 0xFF;
+			if (atif->address.s_node > 0 &&
+			    atif->address.s_node < 254) {
+				/* Probe a proposed address */
+				aarp_probe_network(atif);
+
+				if (!(atif->status & ATIF_PROBE_FAIL)) {
+					atif->status &= ~ATIF_PROBE;
+					return 0;
+				}
+			}
+			atif->status &= ~ATIF_PROBE_FAIL;
+		}
+		probe_net++;
+		if (probe_net > ntohs(atif->nets.nr_lastnet))
+			probe_net = ntohs(atif->nets.nr_firstnet);
+	}
+	atif->status &= ~ATIF_PROBE;
+
+	return -EADDRINUSE;	/* Network is full... */
+}
+
+
+/* Perform AARP probing for a proxy address */
+static int atif_proxy_probe_device(struct atalk_iface *atif,
+				   struct atalk_addr* proxy_addr)
+{
+	int netrange = ntohs(atif->nets.nr_lastnet) -
+			ntohs(atif->nets.nr_firstnet) + 1;
+	/* we probe the interface's network */
+	int probe_net = ntohs(atif->address.s_net);
+	int probe_node = ATADDR_ANYNODE;	    /* we'll take anything */
+	int netct, nodect;
+
+	/* Offset the network we start probing with */
+	if (probe_net == ATADDR_ANYNET) {
+		probe_net = ntohs(atif->nets.nr_firstnet);
+		if (netrange)
+			probe_net += jiffies % netrange;
+	}
+
+	if (probe_node == ATADDR_ANYNODE)
+		probe_node = jiffies & 0xFF;
+
+	/* Scan the networks */
+	for (netct = 0; netct <= netrange; netct++) {
+		/* Sweep the available nodes from a given start */
+		proxy_addr->s_net = htons(probe_net);
+		for (nodect = 0; nodect < 256; nodect++) {
+			proxy_addr->s_node = (nodect + probe_node) & 0xFF;
+			if (proxy_addr->s_node > 0 &&
+			    proxy_addr->s_node < 254) {
+				/* Tell AARP to probe a proposed address */
+				int ret = aarp_proxy_probe_network(atif,
+								    proxy_addr);
+
+				if (ret != -EADDRINUSE)
+					return ret;
+			}
+		}
+		probe_net++;
+		if (probe_net > ntohs(atif->nets.nr_lastnet))
+			probe_net = ntohs(atif->nets.nr_firstnet);
+	}
+
+	return -EADDRINUSE;	/* Network is full... */
+}
+
+
+struct atalk_addr *atalk_find_dev_addr(struct net_device *dev)
+{
+	struct atalk_iface *iface = dev->atalk_ptr;
+	return iface ? &iface->address : NULL;
+}
+
+static struct atalk_addr *atalk_find_primary(void)
+{
+	struct atalk_iface *fiface = NULL;
+	struct atalk_addr *retval;
+	struct atalk_iface *iface;
+
+	/*
+	 * Return a point-to-point interface only if
+	 * there is no non-ptp interface available.
+	 */
+	read_lock_bh(&atalk_interfaces_lock);
+	for (iface = atalk_interfaces; iface; iface = iface->next) {
+		if (!fiface && !(iface->dev->flags & IFF_LOOPBACK))
+			fiface = iface;
+		if (!(iface->dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))) {
+			retval = &iface->address;
+			goto out;
+		}
+	}
+
+	if (fiface)
+		retval = &fiface->address;
+	else if (atalk_interfaces)
+		retval = &atalk_interfaces->address;
+	else
+		retval = NULL;
+out:
+	read_unlock_bh(&atalk_interfaces_lock);
+	return retval;
+}
+
+/*
+ * Find a match for 'any network' - ie any of our interfaces with that
+ * node number will do just nicely.
+ */
+static struct atalk_iface *atalk_find_anynet(int node, struct net_device *dev)
+{
+	struct atalk_iface *iface = dev->atalk_ptr;
+
+	if (!iface || iface->status & ATIF_PROBE)
+		goto out_err;
+
+	if (node != ATADDR_BCAST &&
+	    iface->address.s_node != node &&
+	    node != ATADDR_ANYNODE)
+		goto out_err;
+out:
+	return iface;
+out_err:
+	iface = NULL;
+	goto out;
+}
+
+/* Find a match for a specific network:node pair */
+static struct atalk_iface *atalk_find_interface(__be16 net, int node)
+{
+	struct atalk_iface *iface;
+
+	read_lock_bh(&atalk_interfaces_lock);
+	for (iface = atalk_interfaces; iface; iface = iface->next) {
+		if ((node == ATADDR_BCAST ||
+		     node == ATADDR_ANYNODE ||
+		     iface->address.s_node == node) &&
+		    iface->address.s_net == net &&
+		    !(iface->status & ATIF_PROBE))
+			break;
+
+		/* XXXX.0 -- net.0 returns the iface associated with net */
+		if (node == ATADDR_ANYNODE && net != ATADDR_ANYNET &&
+		    ntohs(iface->nets.nr_firstnet) <= ntohs(net) &&
+		    ntohs(net) <= ntohs(iface->nets.nr_lastnet))
+			break;
+	}
+	read_unlock_bh(&atalk_interfaces_lock);
+	return iface;
+}
+
+
+/*
+ * Find a route for an AppleTalk packet. This ought to get cached in
+ * the socket (later on...). We know about host routes and the fact
+ * that a route must be direct to broadcast.
+ */
+static struct atalk_route *atrtr_find(struct atalk_addr *target)
+{
+	/*
+	 * we must search through all routes unless we find a
+	 * host route, because some host routes might overlap
+	 * network routes
+	 */
+	struct atalk_route *net_route = NULL;
+	struct atalk_route *r;
+
+	read_lock_bh(&atalk_routes_lock);
+	for (r = atalk_routes; r; r = r->next) {
+		if (!(r->flags & RTF_UP))
+			continue;
+
+		if (r->target.s_net == target->s_net) {
+			if (r->flags & RTF_HOST) {
+				/*
+				 * if this host route is for the target,
+				 * the we're done
+				 */
+				if (r->target.s_node == target->s_node)
+					goto out;
+			} else
+				/*
+				 * this route will work if there isn't a
+				 * direct host route, so cache it
+				 */
+				net_route = r;
+		}
+	}
+
+	/*
+	 * if we found a network route but not a direct host
+	 * route, then return it
+	 */
+	if (net_route)
+		r = net_route;
+	else if (atrtr_default.dev)
+		r = &atrtr_default;
+	else /* No route can be found */
+		r = NULL;
+out:
+	read_unlock_bh(&atalk_routes_lock);
+	return r;
+}
+
+
+/*
+ * Given an AppleTalk network, find the device to use. This can be
+ * a simple lookup.
+ */
+struct net_device *atrtr_get_dev(struct atalk_addr *sa)
+{
+	struct atalk_route *atr = atrtr_find(sa);
+	return atr ? atr->dev : NULL;
+}
+
+/* Set up a default router */
+static void atrtr_set_default(struct net_device *dev)
+{
+	atrtr_default.dev	     = dev;
+	atrtr_default.flags	     = RTF_UP;
+	atrtr_default.gateway.s_net  = htons(0);
+	atrtr_default.gateway.s_node = 0;
+}
+
+/*
+ * Add a router. Basically make sure it looks valid and stuff the
+ * entry in the list. While it uses netranges we always set them to one
+ * entry to work like netatalk.
+ */
+static int atrtr_create(struct rtentry *r, struct net_device *devhint)
+{
+	struct sockaddr_at *ta = (struct sockaddr_at *)&r->rt_dst;
+	struct sockaddr_at *ga = (struct sockaddr_at *)&r->rt_gateway;
+	struct atalk_route *rt;
+	struct atalk_iface *iface, *riface;
+	int retval = -EINVAL;
+
+	/*
+	 * Fixme: Raise/Lower a routing change semaphore for these
+	 * operations.
+	 */
+
+	/* Validate the request */
+	if (ta->sat_family != AF_APPLETALK ||
+	    (!devhint && ga->sat_family != AF_APPLETALK))
+		goto out;
+
+	/* Now walk the routing table and make our decisions */
+	write_lock_bh(&atalk_routes_lock);
+	for (rt = atalk_routes; rt; rt = rt->next) {
+		if (r->rt_flags != rt->flags)
+			continue;
+
+		if (ta->sat_addr.s_net == rt->target.s_net) {
+			if (!(rt->flags & RTF_HOST))
+				break;
+			if (ta->sat_addr.s_node == rt->target.s_node)
+				break;
+		}
+	}
+
+	if (!devhint) {
+		riface = NULL;
+
+		read_lock_bh(&atalk_interfaces_lock);
+		for (iface = atalk_interfaces; iface; iface = iface->next) {
+			if (!riface &&
+			    ntohs(ga->sat_addr.s_net) >=
+					ntohs(iface->nets.nr_firstnet) &&
+			    ntohs(ga->sat_addr.s_net) <=
+					ntohs(iface->nets.nr_lastnet))
+				riface = iface;
+
+			if (ga->sat_addr.s_net == iface->address.s_net &&
+			    ga->sat_addr.s_node == iface->address.s_node)
+				riface = iface;
+		}
+		read_unlock_bh(&atalk_interfaces_lock);
+
+		retval = -ENETUNREACH;
+		if (!riface)
+			goto out_unlock;
+
+		devhint = riface->dev;
+	}
+
+	if (!rt) {
+		rt = kzalloc(sizeof(*rt), GFP_ATOMIC);
+
+		retval = -ENOBUFS;
+		if (!rt)
+			goto out_unlock;
+
+		rt->next = atalk_routes;
+		atalk_routes = rt;
+	}
+
+	/* Fill in the routing entry */
+	rt->target  = ta->sat_addr;
+	dev_hold(devhint);
+	rt->dev     = devhint;
+	rt->flags   = r->rt_flags;
+	rt->gateway = ga->sat_addr;
+
+	retval = 0;
+out_unlock:
+	write_unlock_bh(&atalk_routes_lock);
+out:
+	return retval;
+}
+
+/* Delete a route. Find it and discard it */
+static int atrtr_delete(struct atalk_addr * addr)
+{
+	struct atalk_route **r = &atalk_routes;
+	int retval = 0;
+	struct atalk_route *tmp;
+
+	write_lock_bh(&atalk_routes_lock);
+	while ((tmp = *r) != NULL) {
+		if (tmp->target.s_net == addr->s_net &&
+		    (!(tmp->flags&RTF_GATEWAY) ||
+		     tmp->target.s_node == addr->s_node)) {
+			*r = tmp->next;
+			dev_put(tmp->dev);
+			kfree(tmp);
+			goto out;
+		}
+		r = &tmp->next;
+	}
+	retval = -ENOENT;
+out:
+	write_unlock_bh(&atalk_routes_lock);
+	return retval;
+}
+
+/*
+ * Called when a device is downed. Just throw away any routes
+ * via it.
+ */
+static void atrtr_device_down(struct net_device *dev)
+{
+	struct atalk_route **r = &atalk_routes;
+	struct atalk_route *tmp;
+
+	write_lock_bh(&atalk_routes_lock);
+	while ((tmp = *r) != NULL) {
+		if (tmp->dev == dev) {
+			*r = tmp->next;
+			dev_put(dev);
+			kfree(tmp);
+		} else
+			r = &tmp->next;
+	}
+	write_unlock_bh(&atalk_routes_lock);
+
+	if (atrtr_default.dev == dev)
+		atrtr_set_default(NULL);
+}
+
+/* Actually down the interface */
+static inline void atalk_dev_down(struct net_device *dev)
+{
+	atrtr_device_down(dev);	/* Remove all routes for the device */
+	aarp_device_down(dev);	/* Remove AARP entries for the device */
+	atif_drop_device(dev);	/* Remove the device */
+}
+
+/*
+ * A device event has occurred. Watch for devices going down and
+ * delete our use of them (iface and route).
+ */
+static int ddp_device_event(struct notifier_block *this, unsigned long event,
+			    void *ptr)
+{
+	struct net_device *dev = ptr;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_DOWN)
+		/* Discard any use of this */
+		atalk_dev_down(dev);
+
+	return NOTIFY_DONE;
+}
+
+/* ioctl calls. Shouldn't even need touching */
+/* Device configuration ioctl calls */
+static int atif_ioctl(int cmd, void __user *arg)
+{
+	static char aarp_mcast[6] = { 0x09, 0x00, 0x00, 0xFF, 0xFF, 0xFF };
+	struct ifreq atreq;
+	struct atalk_netrange *nr;
+	struct sockaddr_at *sa;
+	struct net_device *dev;
+	struct atalk_iface *atif;
+	int ct;
+	int limit;
+	struct rtentry rtdef;
+	int add_route;
+
+	if (copy_from_user(&atreq, arg, sizeof(atreq)))
+		return -EFAULT;
+
+	dev = __dev_get_by_name(&init_net, atreq.ifr_name);
+	if (!dev)
+		return -ENODEV;
+
+	sa = (struct sockaddr_at *)&atreq.ifr_addr;
+	atif = atalk_find_dev(dev);
+
+	switch (cmd) {
+		case SIOCSIFADDR:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			if (dev->type != ARPHRD_ETHER &&
+			    dev->type != ARPHRD_LOOPBACK &&
+			    dev->type != ARPHRD_LOCALTLK &&
+			    dev->type != ARPHRD_PPP)
+				return -EPROTONOSUPPORT;
+
+			nr = (struct atalk_netrange *)&sa->sat_zero[0];
+			add_route = 1;
+
+			/*
+			 * if this is a point-to-point iface, and we already
+			 * have an iface for this AppleTalk address, then we
+			 * should not add a route
+			 */
+			if ((dev->flags & IFF_POINTOPOINT) &&
+			    atalk_find_interface(sa->sat_addr.s_net,
+						 sa->sat_addr.s_node)) {
+				printk(KERN_DEBUG "AppleTalk: point-to-point "
+						  "interface added with "
+						  "existing address\n");
+				add_route = 0;
+			}
+
+			/*
+			 * Phase 1 is fine on LocalTalk but we don't do
+			 * EtherTalk phase 1. Anyone wanting to add it go ahead.
+			 */
+			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
+				return -EPROTONOSUPPORT;
+			if (sa->sat_addr.s_node == ATADDR_BCAST ||
+			    sa->sat_addr.s_node == 254)
+				return -EINVAL;
+			if (atif) {
+				/* Already setting address */
+				if (atif->status & ATIF_PROBE)
+					return -EBUSY;
+
+				atif->address.s_net  = sa->sat_addr.s_net;
+				atif->address.s_node = sa->sat_addr.s_node;
+				atrtr_device_down(dev);	/* Flush old routes */
+			} else {
+				atif = atif_add_device(dev, &sa->sat_addr);
+				if (!atif)
+					return -ENOMEM;
+			}
+			atif->nets = *nr;
+
+			/*
+			 * Check if the chosen address is used. If so we
+			 * error and atalkd will try another.
+			 */
+
+			if (!(dev->flags & IFF_LOOPBACK) &&
+			    !(dev->flags & IFF_POINTOPOINT) &&
+			    atif_probe_device(atif) < 0) {
+				atif_drop_device(dev);
+				return -EADDRINUSE;
+			}
+
+			/* Hey it worked - add the direct routes */
+			sa = (struct sockaddr_at *)&rtdef.rt_gateway;
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr.s_net  = atif->address.s_net;
+			sa->sat_addr.s_node = atif->address.s_node;
+			sa = (struct sockaddr_at *)&rtdef.rt_dst;
+			rtdef.rt_flags = RTF_UP;
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr.s_node = ATADDR_ANYNODE;
+			if (dev->flags & IFF_LOOPBACK ||
+			    dev->flags & IFF_POINTOPOINT)
+				rtdef.rt_flags |= RTF_HOST;
+
+			/* Routerless initial state */
+			if (nr->nr_firstnet == htons(0) &&
+			    nr->nr_lastnet == htons(0xFFFE)) {
+				sa->sat_addr.s_net = atif->address.s_net;
+				atrtr_create(&rtdef, dev);
+				atrtr_set_default(dev);
+			} else {
+				limit = ntohs(nr->nr_lastnet);
+				if (limit - ntohs(nr->nr_firstnet) > 4096) {
+					printk(KERN_WARNING "Too many routes/"
+							    "iface.\n");
+					return -EINVAL;
+				}
+				if (add_route)
+					for (ct = ntohs(nr->nr_firstnet);
+					     ct <= limit; ct++) {
+						sa->sat_addr.s_net = htons(ct);
+						atrtr_create(&rtdef, dev);
+					}
+			}
+			dev_mc_add_global(dev, aarp_mcast);
+			return 0;
+
+		case SIOCGIFADDR:
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr = atif->address;
+			break;
+
+		case SIOCGIFBRDADDR:
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			sa->sat_family = AF_APPLETALK;
+			sa->sat_addr.s_net = atif->address.s_net;
+			sa->sat_addr.s_node = ATADDR_BCAST;
+			break;
+
+		case SIOCATALKDIFADDR:
+		case SIOCDIFADDR:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			atalk_dev_down(dev);
+			break;
+
+		case SIOCSARP:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			/*
+			 * for now, we only support proxy AARP on ELAP;
+			 * we should be able to do it for LocalTalk, too.
+			 */
+			if (dev->type != ARPHRD_ETHER)
+				return -EPROTONOSUPPORT;
+
+			/*
+			 * atif points to the current interface on this network;
+			 * we aren't concerned about its current status (at
+			 * least for now), but it has all the settings about
+			 * the network we're going to probe. Consequently, it
+			 * must exist.
+			 */
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			nr = (struct atalk_netrange *)&(atif->nets);
+			/*
+			 * Phase 1 is fine on Localtalk but we don't do
+			 * Ethertalk phase 1. Anyone wanting to add it go ahead.
+			 */
+			if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2)
+				return -EPROTONOSUPPORT;
+
+			if (sa->sat_addr.s_node == ATADDR_BCAST ||
+			    sa->sat_addr.s_node == 254)
+				return -EINVAL;
+
+			/*
+			 * Check if the chosen address is used. If so we
+			 * error and ATCP will try another.
+			 */
+			if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0)
+				return -EADDRINUSE;
+
+			/*
+			 * We now have an address on the local network, and
+			 * the AARP code will defend it for us until we take it
+			 * down. We don't set up any routes right now, because
+			 * ATCP will install them manually via SIOCADDRT.
+			 */
+			break;
+
+		case SIOCDARP:
+			if (!capable(CAP_NET_ADMIN))
+				return -EPERM;
+			if (sa->sat_family != AF_APPLETALK)
+				return -EINVAL;
+			if (!atif)
+				return -EADDRNOTAVAIL;
+
+			/* give to aarp module to remove proxy entry */
+			aarp_proxy_remove(atif->dev, &(sa->sat_addr));
+			return 0;
+	}
+
+	return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0;
+}
+
+/* Routing ioctl() calls */
+static int atrtr_ioctl(unsigned int cmd, void __user *arg)
+{
+	struct rtentry rt;
+
+	if (copy_from_user(&rt, arg, sizeof(rt)))
+		return -EFAULT;
+
+	switch (cmd) {
+		case SIOCDELRT:
+			if (rt.rt_dst.sa_family != AF_APPLETALK)
+				return -EINVAL;
+			return atrtr_delete(&((struct sockaddr_at *)
+						&rt.rt_dst)->sat_addr);
+
+		case SIOCADDRT: {
+			struct net_device *dev = NULL;
+			if (rt.rt_dev) {
+				char name[IFNAMSIZ];
+				if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1))
+					return -EFAULT;
+				name[IFNAMSIZ-1] = '\0';
+				dev = __dev_get_by_name(&init_net, name);
+				if (!dev)
+					return -ENODEV;
+			}
+			return atrtr_create(&rt, dev);
+		}
+	}
+	return -EINVAL;
+}
+
+/**************************************************************************\
+*                                                                          *
+* Handling for system calls applied via the various interfaces to an       *
+* AppleTalk socket object.                                                 *
+*                                                                          *
+\**************************************************************************/
+
+/*
+ * Checksum: This is 'optional'. It's quite likely also a good
+ * candidate for assembler hackery 8)
+ */
+static unsigned long atalk_sum_partial(const unsigned char *data,
+				       int len, unsigned long sum)
+{
+	/* This ought to be unwrapped neatly. I'll trust gcc for now */
+	while (len--) {
+		sum += *data++;
+		sum = rol16(sum, 1);
+	}
+	return sum;
+}
+
+/*  Checksum skb data --  similar to skb_checksum  */
+static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
+				   int len, unsigned long sum)
+{
+	int start = skb_headlen(skb);
+	struct sk_buff *frag_iter;
+	int i, copy;
+
+	/* checksum stuff in header space */
+	if ( (copy = start - offset) > 0) {
+		if (copy > len)
+			copy = len;
+		sum = atalk_sum_partial(skb->data + offset, copy, sum);
+		if ( (len -= copy) == 0)
+			return sum;
+
+		offset += copy;
+	}
+
+	/* checksum stuff in frags */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			u8 *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap_skb_frag(frag);
+			sum = atalk_sum_partial(vaddr + frag->page_offset +
+						  offset - start, copy, sum);
+			kunmap_skb_frag(vaddr);
+
+			if (!(len -= copy))
+				return sum;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			sum = atalk_sum_skb(frag_iter, offset - start,
+					    copy, sum);
+			if ((len -= copy) == 0)
+				return sum;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	BUG_ON(len > 0);
+
+	return sum;
+}
+
+static __be16 atalk_checksum(const struct sk_buff *skb, int len)
+{
+	unsigned long sum;
+
+	/* skip header 4 bytes */
+	sum = atalk_sum_skb(skb, 4, len-4, 0);
+
+	/* Use 0xFFFF for 0. 0 itself means none */
+	return sum ? htons((unsigned short)sum) : htons(0xFFFF);
+}
+
+static struct proto ddp_proto = {
+	.name	  = "DDP",
+	.owner	  = THIS_MODULE,
+	.obj_size = sizeof(struct atalk_sock),
+};
+
+/*
+ * Create a socket. Initialise the socket, blank the addresses
+ * set the state.
+ */
+static int atalk_create(struct net *net, struct socket *sock, int protocol,
+			int kern)
+{
+	struct sock *sk;
+	int rc = -ESOCKTNOSUPPORT;
+
+	if (!net_eq(net, &init_net))
+		return -EAFNOSUPPORT;
+
+	/*
+	 * We permit SOCK_DGRAM and RAW is an extension. It is trivial to do
+	 * and gives you the full ELAP frame. Should be handy for CAP 8)
+	 */
+	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
+		goto out;
+	rc = -ENOMEM;
+	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto);
+	if (!sk)
+		goto out;
+	rc = 0;
+	sock->ops = &atalk_dgram_ops;
+	sock_init_data(sock, sk);
+
+	/* Checksums on by default */
+	sock_set_flag(sk, SOCK_ZAPPED);
+out:
+	return rc;
+}
+
+/* Free a socket. No work needed */
+static int atalk_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	lock_kernel();
+	if (sk) {
+		sock_orphan(sk);
+		sock->sk = NULL;
+		atalk_destroy_socket(sk);
+	}
+	unlock_kernel();
+	return 0;
+}
+
+/**
+ * atalk_pick_and_bind_port - Pick a source port when one is not given
+ * @sk - socket to insert into the tables
+ * @sat - address to search for
+ *
+ * Pick a source port when one is not given. If we can find a suitable free
+ * one, we insert the socket into the tables using it.
+ *
+ * This whole operation must be atomic.
+ */
+static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat)
+{
+	int retval;
+
+	write_lock_bh(&atalk_sockets_lock);
+
+	for (sat->sat_port = ATPORT_RESERVED;
+	     sat->sat_port < ATPORT_LAST;
+	     sat->sat_port++) {
+		struct sock *s;
+		struct hlist_node *node;
+
+		sk_for_each(s, node, &atalk_sockets) {
+			struct atalk_sock *at = at_sk(s);
+
+			if (at->src_net == sat->sat_addr.s_net &&
+			    at->src_node == sat->sat_addr.s_node &&
+			    at->src_port == sat->sat_port)
+				goto try_next_port;
+		}
+
+		/* Wheee, it's free, assign and insert. */
+		__atalk_insert_socket(sk);
+		at_sk(sk)->src_port = sat->sat_port;
+		retval = 0;
+		goto out;
+
+try_next_port:;
+	}
+
+	retval = -EBUSY;
+out:
+	write_unlock_bh(&atalk_sockets_lock);
+	return retval;
+}
+
+static int atalk_autobind(struct sock *sk)
+{
+	struct atalk_sock *at = at_sk(sk);
+	struct sockaddr_at sat;
+	struct atalk_addr *ap = atalk_find_primary();
+	int n = -EADDRNOTAVAIL;
+
+	if (!ap || ap->s_net == htons(ATADDR_ANYNET))
+		goto out;
+
+	at->src_net  = sat.sat_addr.s_net  = ap->s_net;
+	at->src_node = sat.sat_addr.s_node = ap->s_node;
+
+	n = atalk_pick_and_bind_port(sk, &sat);
+	if (!n)
+		sock_reset_flag(sk, SOCK_ZAPPED);
+out:
+	return n;
+}
+
+/* Set the address 'our end' of the connection */
+static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	struct sockaddr_at *addr = (struct sockaddr_at *)uaddr;
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	int err;
+
+	if (!sock_flag(sk, SOCK_ZAPPED) ||
+	    addr_len != sizeof(struct sockaddr_at))
+		return -EINVAL;
+
+	if (addr->sat_family != AF_APPLETALK)
+		return -EAFNOSUPPORT;
+
+	lock_kernel();
+	if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) {
+		struct atalk_addr *ap = atalk_find_primary();
+
+		err = -EADDRNOTAVAIL;
+		if (!ap)
+			goto out;
+
+		at->src_net  = addr->sat_addr.s_net = ap->s_net;
+		at->src_node = addr->sat_addr.s_node= ap->s_node;
+	} else {
+		err = -EADDRNOTAVAIL;
+		if (!atalk_find_interface(addr->sat_addr.s_net,
+					  addr->sat_addr.s_node))
+			goto out;
+
+		at->src_net  = addr->sat_addr.s_net;
+		at->src_node = addr->sat_addr.s_node;
+	}
+
+	if (addr->sat_port == ATADDR_ANYPORT) {
+		err = atalk_pick_and_bind_port(sk, addr);
+
+		if (err < 0)
+			goto out;
+	} else {
+		at->src_port = addr->sat_port;
+
+		err = -EADDRINUSE;
+		if (atalk_find_or_insert_socket(sk, addr))
+			goto out;
+	}
+
+	sock_reset_flag(sk, SOCK_ZAPPED);
+	err = 0;
+out:
+	unlock_kernel();
+	return err;
+}
+
+/* Set the address we talk to */
+static int atalk_connect(struct socket *sock, struct sockaddr *uaddr,
+			 int addr_len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	struct sockaddr_at *addr;
+	int err;
+
+	sk->sk_state   = TCP_CLOSE;
+	sock->state = SS_UNCONNECTED;
+
+	if (addr_len != sizeof(*addr))
+		return -EINVAL;
+
+	addr = (struct sockaddr_at *)uaddr;
+
+	if (addr->sat_family != AF_APPLETALK)
+		return -EAFNOSUPPORT;
+
+	if (addr->sat_addr.s_node == ATADDR_BCAST &&
+	    !sock_flag(sk, SOCK_BROADCAST)) {
+#if 1
+		printk(KERN_WARNING "%s is broken and did not set "
+				    "SO_BROADCAST. It will break when 2.2 is "
+				    "released.\n",
+			current->comm);
+#else
+		return -EACCES;
+#endif
+	}
+
+	lock_kernel();
+	err = -EBUSY;
+	if (sock_flag(sk, SOCK_ZAPPED))
+		if (atalk_autobind(sk) < 0)
+			goto out;
+
+	err = -ENETUNREACH;
+	if (!atrtr_get_dev(&addr->sat_addr))
+		goto out;
+
+	at->dest_port = addr->sat_port;
+	at->dest_net  = addr->sat_addr.s_net;
+	at->dest_node = addr->sat_addr.s_node;
+
+	sock->state  = SS_CONNECTED;
+	sk->sk_state = TCP_ESTABLISHED;
+	err = 0;
+out:
+	unlock_kernel();
+	return err;
+}
+
+/*
+ * Find the name of an AppleTalk socket. Just copy the right
+ * fields into the sockaddr.
+ */
+static int atalk_getname(struct socket *sock, struct sockaddr *uaddr,
+			 int *uaddr_len, int peer)
+{
+	struct sockaddr_at sat;
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	int err;
+
+	lock_kernel();
+	err = -ENOBUFS;
+	if (sock_flag(sk, SOCK_ZAPPED))
+		if (atalk_autobind(sk) < 0)
+			goto out;
+
+	*uaddr_len = sizeof(struct sockaddr_at);
+	memset(&sat.sat_zero, 0, sizeof(sat.sat_zero));
+
+	if (peer) {
+		err = -ENOTCONN;
+		if (sk->sk_state != TCP_ESTABLISHED)
+			goto out;
+
+		sat.sat_addr.s_net  = at->dest_net;
+		sat.sat_addr.s_node = at->dest_node;
+		sat.sat_port	    = at->dest_port;
+	} else {
+		sat.sat_addr.s_net  = at->src_net;
+		sat.sat_addr.s_node = at->src_node;
+		sat.sat_port	    = at->src_port;
+	}
+
+	err = 0;
+	sat.sat_family = AF_APPLETALK;
+	memcpy(uaddr, &sat, sizeof(sat));
+
+out:
+	unlock_kernel();
+	return err;
+}
+
+static unsigned int atalk_poll(struct file *file, struct socket *sock,
+			   poll_table *wait)
+{
+	int err;
+	lock_kernel();
+	err = datagram_poll(file, sock, wait);
+	unlock_kernel();
+	return err;
+}
+
+#if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE)
+static __inline__ int is_ip_over_ddp(struct sk_buff *skb)
+{
+	return skb->data[12] == 22;
+}
+
+static int handle_ip_over_ddp(struct sk_buff *skb)
+{
+	struct net_device *dev = __dev_get_by_name(&init_net, "ipddp0");
+	struct net_device_stats *stats;
+
+	/* This needs to be able to handle ipddp"N" devices */
+	if (!dev) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb->protocol = htons(ETH_P_IP);
+	skb_pull(skb, 13);
+	skb->dev   = dev;
+	skb_reset_transport_header(skb);
+
+	stats = netdev_priv(dev);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len + 13;
+	return netif_rx(skb);  /* Send the SKB up to a higher place. */
+}
+#else
+/* make it easy for gcc to optimize this test out, i.e. kill the code */
+#define is_ip_over_ddp(skb) 0
+#define handle_ip_over_ddp(skb) 0
+#endif
+
+static int atalk_route_packet(struct sk_buff *skb, struct net_device *dev,
+			      struct ddpehdr *ddp, __u16 len_hops, int origlen)
+{
+	struct atalk_route *rt;
+	struct atalk_addr ta;
+
+	/*
+	 * Don't route multicast, etc., packets, or packets sent to "this
+	 * network"
+	 */
+	if (skb->pkt_type != PACKET_HOST || !ddp->deh_dnet) {
+		/*
+		 * FIXME:
+		 *
+		 * Can it ever happen that a packet is from a PPP iface and
+		 * needs to be broadcast onto the default network?
+		 */
+		if (dev->type == ARPHRD_PPP)
+			printk(KERN_DEBUG "AppleTalk: didn't forward broadcast "
+					  "packet received from PPP iface\n");
+		goto free_it;
+	}
+
+	ta.s_net  = ddp->deh_dnet;
+	ta.s_node = ddp->deh_dnode;
+
+	/* Route the packet */
+	rt = atrtr_find(&ta);
+	/* increment hops count */
+	len_hops += 1 << 10;
+	if (!rt || !(len_hops & (15 << 10)))
+		goto free_it;
+
+	/* FIXME: use skb->cb to be able to use shared skbs */
+
+	/*
+	 * Route goes through another gateway, so set the target to the
+	 * gateway instead.
+	 */
+
+	if (rt->flags & RTF_GATEWAY) {
+		ta.s_net  = rt->gateway.s_net;
+		ta.s_node = rt->gateway.s_node;
+	}
+
+	/* Fix up skb->len field */
+	skb_trim(skb, min_t(unsigned int, origlen,
+			    (rt->dev->hard_header_len +
+			     ddp_dl->header_length + (len_hops & 1023))));
+
+	/* FIXME: use skb->cb to be able to use shared skbs */
+	ddp->deh_len_hops = htons(len_hops);
+
+	/*
+	 * Send the buffer onwards
+	 *
+	 * Now we must always be careful. If it's come from LocalTalk to
+	 * EtherTalk it might not fit
+	 *
+	 * Order matters here: If a packet has to be copied to make a new
+	 * headroom (rare hopefully) then it won't need unsharing.
+	 *
+	 * Note. ddp-> becomes invalid at the realloc.
+	 */
+	if (skb_headroom(skb) < 22) {
+		/* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */
+		struct sk_buff *nskb = skb_realloc_headroom(skb, 32);
+		kfree_skb(skb);
+		skb = nskb;
+	} else
+		skb = skb_unshare(skb, GFP_ATOMIC);
+
+	/*
+	 * If the buffer didn't vanish into the lack of space bitbucket we can
+	 * send it.
+	 */
+	if (skb == NULL)
+		goto drop;
+
+	if (aarp_send_ddp(rt->dev, skb, &ta, NULL) == NET_XMIT_DROP)
+		return NET_RX_DROP;
+	return NET_RX_SUCCESS;
+free_it:
+	kfree_skb(skb);
+drop:
+	return NET_RX_DROP;
+}
+
+/**
+ *	atalk_rcv - Receive a packet (in skb) from device dev
+ *	@skb - packet received
+ *	@dev - network device where the packet comes from
+ *	@pt - packet type
+ *
+ *	Receive a packet (in skb) from device dev. This has come from the SNAP
+ *	decoder, and on entry skb->transport_header is the DDP header, skb->len
+ *	is the DDP header, skb->len is the DDP length. The physical headers
+ *	have been extracted. PPP should probably pass frames marked as for this
+ *	layer.  [ie ARPHRD_ETHERTALK]
+ */
+static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
+		     struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct ddpehdr *ddp;
+	struct sock *sock;
+	struct atalk_iface *atif;
+	struct sockaddr_at tosat;
+	int origlen;
+	__u16 len_hops;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		goto drop;
+
+	/* Don't mangle buffer if shared */
+	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
+		goto out;
+
+	/* Size check and make sure header is contiguous */
+	if (!pskb_may_pull(skb, sizeof(*ddp)))
+		goto drop;
+
+	ddp = ddp_hdr(skb);
+
+	len_hops = ntohs(ddp->deh_len_hops);
+
+	/* Trim buffer in case of stray trailing data */
+	origlen = skb->len;
+	skb_trim(skb, min_t(unsigned int, skb->len, len_hops & 1023));
+
+	/*
+	 * Size check to see if ddp->deh_len was crap
+	 * (Otherwise we'll detonate most spectacularly
+	 * in the middle of atalk_checksum() or recvmsg()).
+	 */
+	if (skb->len < sizeof(*ddp) || skb->len < (len_hops & 1023)) {
+		pr_debug("AppleTalk: dropping corrupted frame (deh_len=%u, "
+			 "skb->len=%u)\n", len_hops & 1023, skb->len);
+		goto drop;
+	}
+
+	/*
+	 * Any checksums. Note we don't do htons() on this == is assumed to be
+	 * valid for net byte orders all over the networking code...
+	 */
+	if (ddp->deh_sum &&
+	    atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum)
+		/* Not a valid AppleTalk frame - dustbin time */
+		goto drop;
+
+	/* Check the packet is aimed at us */
+	if (!ddp->deh_dnet)	/* Net 0 is 'this network' */
+		atif = atalk_find_anynet(ddp->deh_dnode, dev);
+	else
+		atif = atalk_find_interface(ddp->deh_dnet, ddp->deh_dnode);
+
+	if (!atif) {
+		/* Not ours, so we route the packet via the correct
+		 * AppleTalk iface
+		 */
+		return atalk_route_packet(skb, dev, ddp, len_hops, origlen);
+	}
+
+	/* if IP over DDP is not selected this code will be optimized out */
+	if (is_ip_over_ddp(skb))
+		return handle_ip_over_ddp(skb);
+	/*
+	 * Which socket - atalk_search_socket() looks for a *full match*
+	 * of the <net, node, port> tuple.
+	 */
+	tosat.sat_addr.s_net  = ddp->deh_dnet;
+	tosat.sat_addr.s_node = ddp->deh_dnode;
+	tosat.sat_port	      = ddp->deh_dport;
+
+	sock = atalk_search_socket(&tosat, atif);
+	if (!sock) /* But not one of our sockets */
+		goto drop;
+
+	/* Queue packet (standard) */
+	skb->sk = sock;
+
+	if (sock_queue_rcv_skb(sock, skb) < 0)
+		goto drop;
+
+	return NET_RX_SUCCESS;
+
+drop:
+	kfree_skb(skb);
+out:
+	return NET_RX_DROP;
+
+}
+
+/*
+ * Receive a LocalTalk frame. We make some demands on the caller here.
+ * Caller must provide enough headroom on the packet to pull the short
+ * header and append a long one.
+ */
+static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev,
+		     struct packet_type *pt, struct net_device *orig_dev)
+{
+	if (!net_eq(dev_net(dev), &init_net))
+		goto freeit;
+
+	/* Expand any short form frames */
+	if (skb_mac_header(skb)[2] == 1) {
+		struct ddpehdr *ddp;
+		/* Find our address */
+		struct atalk_addr *ap = atalk_find_dev_addr(dev);
+
+		if (!ap || skb->len < sizeof(__be16) || skb->len > 1023)
+			goto freeit;
+
+		/* Don't mangle buffer if shared */
+		if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
+			return 0;
+
+		/*
+		 * The push leaves us with a ddephdr not an shdr, and
+		 * handily the port bytes in the right place preset.
+		 */
+		ddp = (struct ddpehdr *) skb_push(skb, sizeof(*ddp) - 4);
+
+		/* Now fill in the long header */
+
+		/*
+		 * These two first. The mac overlays the new source/dest
+		 * network information so we MUST copy these before
+		 * we write the network numbers !
+		 */
+
+		ddp->deh_dnode = skb_mac_header(skb)[0];     /* From physical header */
+		ddp->deh_snode = skb_mac_header(skb)[1];     /* From physical header */
+
+		ddp->deh_dnet  = ap->s_net;	/* Network number */
+		ddp->deh_snet  = ap->s_net;
+		ddp->deh_sum   = 0;		/* No checksum */
+		/*
+		 * Not sure about this bit...
+		 */
+		/* Non routable, so force a drop if we slip up later */
+		ddp->deh_len_hops = htons(skb->len + (DDP_MAXHOPS << 10));
+	}
+	skb_reset_transport_header(skb);
+
+	return atalk_rcv(skb, dev, pt, orig_dev);
+freeit:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+			 size_t len)
+{
+	struct sock *sk = sock->sk;
+	struct atalk_sock *at = at_sk(sk);
+	struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name;
+	int flags = msg->msg_flags;
+	int loopback = 0;
+	struct sockaddr_at local_satalk, gsat;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	struct ddpehdr *ddp;
+	int size;
+	struct atalk_route *rt;
+	int err;
+
+	if (flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT))
+		return -EINVAL;
+
+	if (len > DDP_MAXSZ)
+		return -EMSGSIZE;
+
+	lock_kernel();
+	if (usat) {
+		err = -EBUSY;
+		if (sock_flag(sk, SOCK_ZAPPED))
+			if (atalk_autobind(sk) < 0)
+				goto out;
+
+		err = -EINVAL;
+		if (msg->msg_namelen < sizeof(*usat) ||
+		    usat->sat_family != AF_APPLETALK)
+			goto out;
+
+		err = -EPERM;
+		/* netatalk didn't implement this check */
+		if (usat->sat_addr.s_node == ATADDR_BCAST &&
+		    !sock_flag(sk, SOCK_BROADCAST)) {
+			goto out;
+		}
+	} else {
+		err = -ENOTCONN;
+		if (sk->sk_state != TCP_ESTABLISHED)
+			goto out;
+		usat = &local_satalk;
+		usat->sat_family      = AF_APPLETALK;
+		usat->sat_port	      = at->dest_port;
+		usat->sat_addr.s_node = at->dest_node;
+		usat->sat_addr.s_net  = at->dest_net;
+	}
+
+	/* Build a packet */
+	SOCK_DEBUG(sk, "SK %p: Got address.\n", sk);
+
+	/* For headers */
+	size = sizeof(struct ddpehdr) + len + ddp_dl->header_length;
+
+	if (usat->sat_addr.s_net || usat->sat_addr.s_node == ATADDR_ANYNODE) {
+		rt = atrtr_find(&usat->sat_addr);
+	} else {
+		struct atalk_addr at_hint;
+
+		at_hint.s_node = 0;
+		at_hint.s_net  = at->src_net;
+
+		rt = atrtr_find(&at_hint);
+	}
+	err = ENETUNREACH;
+	if (!rt)
+		goto out;
+
+	dev = rt->dev;
+
+	SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n",
+			sk, size, dev->name);
+
+	size += dev->hard_header_len;
+	skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err);
+	if (!skb)
+		goto out;
+
+	skb->sk = sk;
+	skb_reserve(skb, ddp_dl->header_length);
+	skb_reserve(skb, dev->hard_header_len);
+	skb->dev = dev;
+
+	SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk);
+
+	ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr));
+	ddp->deh_len_hops  = htons(len + sizeof(*ddp));
+	ddp->deh_dnet  = usat->sat_addr.s_net;
+	ddp->deh_snet  = at->src_net;
+	ddp->deh_dnode = usat->sat_addr.s_node;
+	ddp->deh_snode = at->src_node;
+	ddp->deh_dport = usat->sat_port;
+	ddp->deh_sport = at->src_port;
+
+	SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len);
+
+	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+	if (err) {
+		kfree_skb(skb);
+		err = -EFAULT;
+		goto out;
+	}
+
+	if (sk->sk_no_check == 1)
+		ddp->deh_sum = 0;
+	else
+		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
+
+	/*
+	 * Loopback broadcast packets to non gateway targets (ie routes
+	 * to group we are in)
+	 */
+	if (ddp->deh_dnode == ATADDR_BCAST &&
+	    !(rt->flags & RTF_GATEWAY) && !(dev->flags & IFF_LOOPBACK)) {
+		struct sk_buff *skb2 = skb_copy(skb, GFP_KERNEL);
+
+		if (skb2) {
+			loopback = 1;
+			SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk);
+			/*
+			 * If it fails it is queued/sent above in the aarp queue
+			 */
+			aarp_send_ddp(dev, skb2, &usat->sat_addr, NULL);
+		}
+	}
+
+	if (dev->flags & IFF_LOOPBACK || loopback) {
+		SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk);
+		/* loop back */
+		skb_orphan(skb);
+		if (ddp->deh_dnode == ATADDR_BCAST) {
+			struct atalk_addr at_lo;
+
+			at_lo.s_node = 0;
+			at_lo.s_net  = 0;
+
+			rt = atrtr_find(&at_lo);
+			if (!rt) {
+				kfree_skb(skb);
+				err = -ENETUNREACH;
+				goto out;
+			}
+			dev = rt->dev;
+			skb->dev = dev;
+		}
+		ddp_dl->request(ddp_dl, skb, dev->dev_addr);
+	} else {
+		SOCK_DEBUG(sk, "SK %p: send out.\n", sk);
+		if (rt->flags & RTF_GATEWAY) {
+		    gsat.sat_addr = rt->gateway;
+		    usat = &gsat;
+		}
+
+		/*
+		 * If it fails it is queued/sent above in the aarp queue
+		 */
+		aarp_send_ddp(dev, skb, &usat->sat_addr, NULL);
+	}
+	SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len);
+
+out:
+	unlock_kernel();
+	return err ? : len;
+}
+
+static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+			 size_t size, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
+	struct ddpehdr *ddp;
+	int copied = 0;
+	int offset = 0;
+	int err = 0;
+	struct sk_buff *skb;
+
+	lock_kernel();
+	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
+						flags & MSG_DONTWAIT, &err);
+	if (!skb)
+		goto out;
+
+	/* FIXME: use skb->cb to be able to use shared skbs */
+	ddp = ddp_hdr(skb);
+	copied = ntohs(ddp->deh_len_hops) & 1023;
+
+	if (sk->sk_type != SOCK_RAW) {
+		offset = sizeof(*ddp);
+		copied -= offset;
+	}
+
+	if (copied > size) {
+		copied = size;
+		msg->msg_flags |= MSG_TRUNC;
+	}
+	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
+
+	if (!err) {
+		if (sat) {
+			sat->sat_family      = AF_APPLETALK;
+			sat->sat_port        = ddp->deh_sport;
+			sat->sat_addr.s_node = ddp->deh_snode;
+			sat->sat_addr.s_net  = ddp->deh_snet;
+		}
+		msg->msg_namelen = sizeof(*sat);
+	}
+
+	skb_free_datagram(sk, skb);	/* Free the datagram. */
+
+out:
+	unlock_kernel();
+	return err ? : copied;
+}
+
+
+/*
+ * AppleTalk ioctl calls.
+ */
+static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	int rc = -ENOIOCTLCMD;
+	struct sock *sk = sock->sk;
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+		/* Protocol layer */
+		case TIOCOUTQ: {
+			long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
+
+			if (amount < 0)
+				amount = 0;
+			rc = put_user(amount, (int __user *)argp);
+			break;
+		}
+		case TIOCINQ: {
+			/*
+			 * These two are safe on a single CPU system as only
+			 * user tasks fiddle here
+			 */
+			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+			long amount = 0;
+
+			if (skb)
+				amount = skb->len - sizeof(struct ddpehdr);
+			rc = put_user(amount, (int __user *)argp);
+			break;
+		}
+		case SIOCGSTAMP:
+			rc = sock_get_timestamp(sk, argp);
+			break;
+		case SIOCGSTAMPNS:
+			rc = sock_get_timestampns(sk, argp);
+			break;
+		/* Routing */
+		case SIOCADDRT:
+		case SIOCDELRT:
+			rc = -EPERM;
+			if (capable(CAP_NET_ADMIN))
+				rc = atrtr_ioctl(cmd, argp);
+			break;
+		/* Interface */
+		case SIOCGIFADDR:
+		case SIOCSIFADDR:
+		case SIOCGIFBRDADDR:
+		case SIOCATALKDIFADDR:
+		case SIOCDIFADDR:
+		case SIOCSARP:		/* proxy AARP */
+		case SIOCDARP:		/* proxy AARP */
+			rtnl_lock();
+			rc = atif_ioctl(cmd, argp);
+			rtnl_unlock();
+			break;
+	}
+
+	return rc;
+}
+
+
+#ifdef CONFIG_COMPAT
+static int atalk_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	/*
+	 * SIOCATALKDIFADDR is a SIOCPROTOPRIVATE ioctl number, so we
+	 * cannot handle it in common code. The data we access if ifreq
+	 * here is compatible, so we can simply call the native
+	 * handler.
+	 */
+	if (cmd == SIOCATALKDIFADDR)
+		return atalk_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+
+	return -ENOIOCTLCMD;
+}
+#endif
+
+
+static const struct net_proto_family atalk_family_ops = {
+	.family		= PF_APPLETALK,
+	.create		= atalk_create,
+	.owner		= THIS_MODULE,
+};
+
+static const struct proto_ops atalk_dgram_ops = {
+	.family		= PF_APPLETALK,
+	.owner		= THIS_MODULE,
+	.release	= atalk_release,
+	.bind		= atalk_bind,
+	.connect	= atalk_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= sock_no_accept,
+	.getname	= atalk_getname,
+	.poll		= atalk_poll,
+	.ioctl		= atalk_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= atalk_compat_ioctl,
+#endif
+	.listen		= sock_no_listen,
+	.shutdown	= sock_no_shutdown,
+	.setsockopt	= sock_no_setsockopt,
+	.getsockopt	= sock_no_getsockopt,
+	.sendmsg	= atalk_sendmsg,
+	.recvmsg	= atalk_recvmsg,
+	.mmap		= sock_no_mmap,
+	.sendpage	= sock_no_sendpage,
+};
+
+static struct notifier_block ddp_notifier = {
+	.notifier_call	= ddp_device_event,
+};
+
+static struct packet_type ltalk_packet_type __read_mostly = {
+	.type		= cpu_to_be16(ETH_P_LOCALTALK),
+	.func		= ltalk_rcv,
+};
+
+static struct packet_type ppptalk_packet_type __read_mostly = {
+	.type		= cpu_to_be16(ETH_P_PPPTALK),
+	.func		= atalk_rcv,
+};
+
+static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B };
+
+/* Export symbols for use by drivers when AppleTalk is a module */
+EXPORT_SYMBOL(atrtr_get_dev);
+EXPORT_SYMBOL(atalk_find_dev_addr);
+
+static const char atalk_err_snap[] __initconst =
+	KERN_CRIT "Unable to register DDP with SNAP.\n";
+
+/* Called by proto.c on kernel start up */
+static int __init atalk_init(void)
+{
+	int rc = proto_register(&ddp_proto, 0);
+
+	if (rc != 0)
+		goto out;
+
+	(void)sock_register(&atalk_family_ops);
+	ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
+	if (!ddp_dl)
+		printk(atalk_err_snap);
+
+	dev_add_pack(&ltalk_packet_type);
+	dev_add_pack(&ppptalk_packet_type);
+
+	register_netdevice_notifier(&ddp_notifier);
+	aarp_proto_init();
+	atalk_proc_init();
+	atalk_register_sysctl();
+out:
+	return rc;
+}
+module_init(atalk_init);
+
+/*
+ * No explicit module reference count manipulation is needed in the
+ * protocol. Socket layer sets module reference count for us
+ * and interfaces reference counting is done
+ * by the network device layer.
+ *
+ * Ergo, before the AppleTalk module can be removed, all AppleTalk
+ * sockets be closed from user space.
+ */
+static void __exit atalk_exit(void)
+{
+#ifdef CONFIG_SYSCTL
+	atalk_unregister_sysctl();
+#endif /* CONFIG_SYSCTL */
+	atalk_proc_exit();
+	aarp_cleanup_module();	/* General aarp clean-up. */
+	unregister_netdevice_notifier(&ddp_notifier);
+	dev_remove_pack(&ltalk_packet_type);
+	dev_remove_pack(&ppptalk_packet_type);
+	unregister_snap_client(ddp_dl);
+	sock_unregister(PF_APPLETALK);
+	proto_unregister(&ddp_proto);
+}
+module_exit(atalk_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alan Cox <alan@lxorguk.ukuu.org.uk>");
+MODULE_DESCRIPTION("AppleTalk 0.20\n");
+MODULE_ALIAS_NETPROTO(PF_APPLETALK);
diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c
new file mode 100644
index 000000000000..6c8016f61866
--- /dev/null
+++ b/net/appletalk/dev.c
@@ -0,0 +1,44 @@
+/*
+ * Moved here from drivers/net/net_init.c, which is:
+ *	Written 1993,1994,1995 by Donald Becker.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_ltalk.h>
+
+static void ltalk_setup(struct net_device *dev)
+{
+	/* Fill in the fields of the device structure with localtalk-generic values. */
+
+	dev->type		= ARPHRD_LOCALTLK;
+	dev->hard_header_len 	= LTALK_HLEN;
+	dev->mtu		= LTALK_MTU;
+	dev->addr_len		= LTALK_ALEN;
+	dev->tx_queue_len	= 10;
+
+	dev->broadcast[0]	= 0xFF;
+
+	dev->flags		= IFF_BROADCAST|IFF_MULTICAST|IFF_NOARP;
+}
+
+/**
+ * alloc_ltalkdev - Allocates and sets up an localtalk device
+ * @sizeof_priv: Size of additional driver-private structure to be allocated
+ *	for this localtalk device
+ *
+ * Fill in the fields of the device structure with localtalk-generic
+ * values. Basically does everything except registering the device.
+ *
+ * Constructs a new net device, complete with a private data area of
+ * size @sizeof_priv.  A 32-byte (not bit) alignment is enforced for
+ * this private data area.
+ */
+
+struct net_device *alloc_ltalkdev(int sizeof_priv)
+{
+	return alloc_netdev(sizeof_priv, "lt%d", ltalk_setup);
+}
+EXPORT_SYMBOL(alloc_ltalkdev);
diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c
new file mode 100644
index 000000000000..04e9c0da7aa9
--- /dev/null
+++ b/net/appletalk/sysctl_net_atalk.c
@@ -0,0 +1,61 @@
+/*
+ * sysctl_net_atalk.c: sysctl interface to net AppleTalk subsystem.
+ *
+ * Begun April 1, 1996, Mike Shaver.
+ * Added /proc/sys/net/atalk directory entry (empty =) ). [MS]
+ * Dynamic registration, added aarp entries. (5/30/97 Chris Horn)
+ */
+
+#include <linux/sysctl.h>
+#include <net/sock.h>
+#include <linux/atalk.h>
+
+static struct ctl_table atalk_table[] = {
+	{
+		.procname	= "aarp-expiry-time",
+		.data		= &sysctl_aarp_expiry_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "aarp-tick-time",
+		.data		= &sysctl_aarp_tick_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "aarp-retransmit-limit",
+		.data		= &sysctl_aarp_retransmit_limit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "aarp-resolve-time",
+		.data		= &sysctl_aarp_resolve_time,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ },
+};
+
+static struct ctl_path atalk_path[] = {
+	{ .procname = "net", },
+	{ .procname = "appletalk", },
+	{ }
+};
+
+static struct ctl_table_header *atalk_table_header;
+
+void atalk_register_sysctl(void)
+{
+	atalk_table_header = register_sysctl_paths(atalk_path, atalk_table);
+}
+
+void atalk_unregister_sysctl(void)
+{
+	unregister_sysctl_table(atalk_table_header);
+}
diff --git a/net/socket.c b/net/socket.c
index 26f7bcf36810..ac2219f90d5d 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -103,6 +103,7 @@
 #include <linux/ipv6_route.h>
 #include <linux/route.h>
 #include <linux/sockios.h>
+#include <linux/atalk.h>
 
 static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
 static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
-- 
cgit v1.2.3


From 5b4704419cbd0b7597a91c19f9e8e8b17c1af071 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 31 Jan 2011 16:10:03 -0800
Subject: ipv4: Remember FIB alias list head and table in lookup results.

This will be used later to implement fib_select_default() in a
completely generic manner, instead of the current situation where the
default route is re-looked up in the TRIE/HASH table and then the
available aliases are analyzed.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 3 +++
 net/ipv4/fib_hash.c      | 2 +-
 net/ipv4/fib_lookup.h    | 2 +-
 net/ipv4/fib_semantics.c | 7 +++++--
 net/ipv4/fib_trie.c      | 8 ++++----
 5 files changed, 14 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 2c0508a6e07c..f5199b08ba53 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -96,12 +96,15 @@ struct fib_info {
 struct fib_rule;
 #endif
 
+struct fib_table;
 struct fib_result {
 	unsigned char	prefixlen;
 	unsigned char	nh_sel;
 	unsigned char	type;
 	unsigned char	scope;
 	struct fib_info *fi;
+	struct fib_table *table;
+	struct list_head *fa_head;
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rule	*r;
 #endif
diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c
index b3acb0417b21..0a88866ad1e5 100644
--- a/net/ipv4/fib_hash.c
+++ b/net/ipv4/fib_hash.c
@@ -288,7 +288,7 @@ int fib_table_lookup(struct fib_table *tb,
 				if (f->fn_key != k)
 					continue;
 
-				err = fib_semantic_match(&f->fn_alias,
+				err = fib_semantic_match(tb, &f->fn_alias,
 						 flp, res,
 						 fz->fz_order, fib_flags);
 				if (err <= 0)
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c079cc0ec651..d5c40d8f6632 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -25,7 +25,7 @@ static inline void fib_alias_accessed(struct fib_alias *fa)
 }
 
 /* Exported by fib_semantics.c */
-extern int fib_semantic_match(struct list_head *head,
+extern int fib_semantic_match(struct fib_table *tb, struct list_head *head,
 			      const struct flowi *flp,
 			      struct fib_result *res, int prefixlen, int fib_flags);
 extern void fib_release_info(struct fib_info *);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 48e93a560077..1bf6fb906cfc 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -889,8 +889,9 @@ failure:
 }
 
 /* Note! fib_semantic_match intentionally uses  RCU list functions. */
-int fib_semantic_match(struct list_head *head, const struct flowi *flp,
-		       struct fib_result *res, int prefixlen, int fib_flags)
+int fib_semantic_match(struct fib_table *tb, struct list_head *head,
+		       const struct flowi *flp, struct fib_result *res,
+		       int prefixlen, int fib_flags)
 {
 	struct fib_alias *fa;
 	int nh_sel = 0;
@@ -954,6 +955,8 @@ out_fill_res:
 	res->type = fa->fa_type;
 	res->scope = fa->fa_scope;
 	res->fi = fa->fa_info;
+	res->table = tb;
+	res->fa_head = head;
 	if (!(fib_flags & FIB_LOOKUP_NOREF))
 		atomic_inc(&res->fi->fib_clntref);
 	return 0;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 0f280348e0fd..8cee5c8848ed 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1340,7 +1340,7 @@ err:
 }
 
 /* should be called with rcu_read_lock */
-static int check_leaf(struct trie *t, struct leaf *l,
+static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 		      t_key key,  const struct flowi *flp,
 		      struct fib_result *res, int fib_flags)
 {
@@ -1356,7 +1356,7 @@ static int check_leaf(struct trie *t, struct leaf *l,
 		if (l->key != (key & ntohl(mask)))
 			continue;
 
-		err = fib_semantic_match(&li->falh, flp, res, plen, fib_flags);
+		err = fib_semantic_match(tb, &li->falh, flp, res, plen, fib_flags);
 
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 		if (err <= 0)
@@ -1398,7 +1398,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
 
 	/* Just a leaf? */
 	if (IS_LEAF(n)) {
-		ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags);
+		ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags);
 		goto found;
 	}
 
@@ -1423,7 +1423,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
 		}
 
 		if (IS_LEAF(n)) {
-			ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags);
+			ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags);
 			if (ret > 0)
 				goto backtrace;
 			goto found;
-- 
cgit v1.2.3


From 0c838ff1ade71162775afffd9e5c6478a60bdca6 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 31 Jan 2011 16:16:50 -0800
Subject: ipv4: Consolidate all default route selection implementations.

Both fib_trie and fib_hash have a local implementation of
fib_table_select_default().  This is completely unnecessary
code duplication.

Since we now remember the fib_table and the head of the fib
alias list of the default route, we can implement one single
generic version of this routine.

Looking at the fib_hash implementation you may get the impression
that it's possible for there to be multiple top-level routes in
the table for the default route.  The truth is, it isn't, the
insert code will only allow one entry to exist in the zero
prefix hash table, because all keys evaluate to zero and all
keys in a hash table must be unique.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  6 +---
 net/ipv4/fib_frontend.c  | 15 ----------
 net/ipv4/fib_hash.c      | 72 ----------------------------------------------
 net/ipv4/fib_semantics.c | 56 ++++++++++++++++++++++++++++++++++++
 net/ipv4/fib_trie.c      | 74 ------------------------------------------------
 net/ipv4/route.c         |  2 +-
 6 files changed, 58 insertions(+), 167 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f5199b08ba53..819d61ca25cb 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -158,9 +158,6 @@ extern int fib_table_delete(struct fib_table *, struct fib_config *);
 extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 			  struct netlink_callback *cb);
 extern int fib_table_flush(struct fib_table *table);
-extern void fib_table_select_default(struct fib_table *table,
-				     const struct flowi *flp,
-				     struct fib_result *res);
 extern void fib_free_table(struct fib_table *tb);
 
 
@@ -221,8 +218,7 @@ extern void		ip_fib_init(void);
 extern int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 			       struct net_device *dev, __be32 *spec_dst,
 			       u32 *itag, u32 mark);
-extern void fib_select_default(struct net *net, const struct flowi *flp,
-			       struct fib_result *res);
+extern void fib_select_default(struct fib_result *res);
 
 /* Exported by fib_semantics.c */
 extern int ip_fib_check_default(__be32 gw, struct net_device *dev);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1d2cdd43a878..930768ba49af 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -114,21 +114,6 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 }
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
-void fib_select_default(struct net *net,
-			const struct flowi *flp, struct fib_result *res)
-{
-	struct fib_table *tb;
-	int table = RT_TABLE_MAIN;
-#ifdef CONFIG_IP_MULTIPLE_TABLES
-	if (res->r == NULL || res->r->action != FR_ACT_TO_TBL)
-		return;
-	table = res->r->table;
-#endif
-	tb = fib_get_table(net, table);
-	if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
-		fib_table_select_default(tb, flp, res);
-}
-
 static void fib_flush(struct net *net)
 {
 	int flushed = 0;
diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c
index 0a88866ad1e5..fadb6024de27 100644
--- a/net/ipv4/fib_hash.c
+++ b/net/ipv4/fib_hash.c
@@ -302,78 +302,6 @@ out:
 	return err;
 }
 
-void fib_table_select_default(struct fib_table *tb,
-			      const struct flowi *flp, struct fib_result *res)
-{
-	int order, last_idx;
-	struct hlist_node *node;
-	struct fib_node *f;
-	struct fib_info *fi = NULL;
-	struct fib_info *last_resort;
-	struct fn_hash *t = (struct fn_hash *)tb->tb_data;
-	struct fn_zone *fz = t->fn_zones[0];
-	struct hlist_head *head;
-
-	if (fz == NULL)
-		return;
-
-	last_idx = -1;
-	last_resort = NULL;
-	order = -1;
-
-	rcu_read_lock();
-	head = rcu_dereference(fz->fz_hash);
-	hlist_for_each_entry_rcu(f, node, head, fn_hash) {
-		struct fib_alias *fa;
-
-		list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) {
-			struct fib_info *next_fi = fa->fa_info;
-
-			if (fa->fa_scope != res->scope ||
-			    fa->fa_type != RTN_UNICAST)
-				continue;
-
-			if (next_fi->fib_priority > res->fi->fib_priority)
-				break;
-			if (!next_fi->fib_nh[0].nh_gw ||
-			    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
-				continue;
-
-			fib_alias_accessed(fa);
-
-			if (fi == NULL) {
-				if (next_fi != res->fi)
-					break;
-			} else if (!fib_detect_death(fi, order, &last_resort,
-						&last_idx, tb->tb_default)) {
-				fib_result_assign(res, fi);
-				tb->tb_default = order;
-				goto out;
-			}
-			fi = next_fi;
-			order++;
-		}
-	}
-
-	if (order <= 0 || fi == NULL) {
-		tb->tb_default = -1;
-		goto out;
-	}
-
-	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
-				tb->tb_default)) {
-		fib_result_assign(res, fi);
-		tb->tb_default = order;
-		goto out;
-	}
-
-	if (last_idx >= 0)
-		fib_result_assign(res, last_resort);
-	tb->tb_default = last_idx;
-out:
-	rcu_read_unlock();
-}
-
 /* Insert node F to FZ. */
 static inline void fib_insert_node(struct fn_zone *fz, struct fib_node *f)
 {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1bf6fb906cfc..b15857d2b77e 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1136,6 +1136,62 @@ int fib_sync_down_dev(struct net_device *dev, int force)
 	return ret;
 }
 
+/* Must be invoked inside of an RCU protected region.  */
+void fib_select_default(struct fib_result *res)
+{
+	struct fib_info *fi = NULL, *last_resort = NULL;
+	struct list_head *fa_head = res->fa_head;
+	struct fib_table *tb = res->table;
+	int order = -1, last_idx = -1;
+	struct fib_alias *fa;
+
+	list_for_each_entry_rcu(fa, fa_head, fa_list) {
+		struct fib_info *next_fi = fa->fa_info;
+
+		if (fa->fa_scope != res->scope ||
+		    fa->fa_type != RTN_UNICAST)
+			continue;
+
+		if (next_fi->fib_priority > res->fi->fib_priority)
+			break;
+		if (!next_fi->fib_nh[0].nh_gw ||
+		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
+			continue;
+
+		fib_alias_accessed(fa);
+
+		if (fi == NULL) {
+			if (next_fi != res->fi)
+				break;
+		} else if (!fib_detect_death(fi, order, &last_resort,
+					     &last_idx, tb->tb_default)) {
+			fib_result_assign(res, fi);
+			tb->tb_default = order;
+			goto out;
+		}
+		fi = next_fi;
+		order++;
+	}
+
+	if (order <= 0 || fi == NULL) {
+		tb->tb_default = -1;
+		goto out;
+	}
+
+	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
+				tb->tb_default)) {
+		fib_result_assign(res, fi);
+		tb->tb_default = order;
+		goto out;
+	}
+
+	if (last_idx >= 0)
+		fib_result_assign(res, last_resort);
+	tb->tb_default = last_idx;
+out:
+	rcu_read_unlock();
+}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 /*
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 8cee5c8848ed..16d589c70a92 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1802,80 +1802,6 @@ void fib_free_table(struct fib_table *tb)
 	kfree(tb);
 }
 
-void fib_table_select_default(struct fib_table *tb,
-			      const struct flowi *flp,
-			      struct fib_result *res)
-{
-	struct trie *t = (struct trie *) tb->tb_data;
-	int order, last_idx;
-	struct fib_info *fi = NULL;
-	struct fib_info *last_resort;
-	struct fib_alias *fa = NULL;
-	struct list_head *fa_head;
-	struct leaf *l;
-
-	last_idx = -1;
-	last_resort = NULL;
-	order = -1;
-
-	rcu_read_lock();
-
-	l = fib_find_node(t, 0);
-	if (!l)
-		goto out;
-
-	fa_head = get_fa_head(l, 0);
-	if (!fa_head)
-		goto out;
-
-	if (list_empty(fa_head))
-		goto out;
-
-	list_for_each_entry_rcu(fa, fa_head, fa_list) {
-		struct fib_info *next_fi = fa->fa_info;
-
-		if (fa->fa_scope != res->scope ||
-		    fa->fa_type != RTN_UNICAST)
-			continue;
-
-		if (next_fi->fib_priority > res->fi->fib_priority)
-			break;
-		if (!next_fi->fib_nh[0].nh_gw ||
-		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
-			continue;
-
-		fib_alias_accessed(fa);
-
-		if (fi == NULL) {
-			if (next_fi != res->fi)
-				break;
-		} else if (!fib_detect_death(fi, order, &last_resort,
-					     &last_idx, tb->tb_default)) {
-			fib_result_assign(res, fi);
-			tb->tb_default = order;
-			goto out;
-		}
-		fi = next_fi;
-		order++;
-	}
-	if (order <= 0 || fi == NULL) {
-		tb->tb_default = -1;
-		goto out;
-	}
-
-	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
-				tb->tb_default)) {
-		fib_result_assign(res, fi);
-		tb->tb_default = order;
-		goto out;
-	}
-	if (last_idx >= 0)
-		fib_result_assign(res, last_resort);
-	tb->tb_default = last_idx;
-out:
-	rcu_read_unlock();
-}
-
 static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah,
 			   struct fib_table *tb,
 			   struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b1e5d3ac3460..242a3de83fbb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2711,7 +2711,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 	else
 #endif
 	if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
-		fib_select_default(net, &fl, &res);
+		fib_select_default(&res);
 
 	if (!fl.fl4_src)
 		fl.fl4_src = FIB_RES_PREFSRC(res);
-- 
cgit v1.2.3


From f703651ef870bd6b94ddc98ae07488b7d3fd9335 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 1 Feb 2011 15:20:14 +0100
Subject: netfilter: NFNL_SUBSYS_IPSET id and NLA_PUT_NET* macros

The patch adds the NFNL_SUBSYS_IPSET id and NLA_PUT_NET* macros to the
vanilla kernel.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nfnetlink.h | 3 ++-
 include/net/netlink.h               | 9 +++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 361d6b5630ee..2b11fc1a86be 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -47,7 +47,8 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_QUEUE		3
 #define NFNL_SUBSYS_ULOG		4
 #define NFNL_SUBSYS_OSF			5
-#define NFNL_SUBSYS_COUNT		6
+#define NFNL_SUBSYS_IPSET		6
+#define NFNL_SUBSYS_COUNT		7
 
 #ifdef __KERNEL__
 
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 373f1a900cf4..8a3906a08f5f 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -856,18 +856,27 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype,
 #define NLA_PUT_BE16(skb, attrtype, value) \
 	NLA_PUT_TYPE(skb, __be16, attrtype, value)
 
+#define NLA_PUT_NET16(skb, attrtype, value) \
+	NLA_PUT_BE16(skb, attrtype | NLA_F_NET_BYTEORDER, value)
+
 #define NLA_PUT_U32(skb, attrtype, value) \
 	NLA_PUT_TYPE(skb, u32, attrtype, value)
 
 #define NLA_PUT_BE32(skb, attrtype, value) \
 	NLA_PUT_TYPE(skb, __be32, attrtype, value)
 
+#define NLA_PUT_NET32(skb, attrtype, value) \
+	NLA_PUT_BE32(skb, attrtype | NLA_F_NET_BYTEORDER, value)
+
 #define NLA_PUT_U64(skb, attrtype, value) \
 	NLA_PUT_TYPE(skb, u64, attrtype, value)
 
 #define NLA_PUT_BE64(skb, attrtype, value) \
 	NLA_PUT_TYPE(skb, __be64, attrtype, value)
 
+#define NLA_PUT_NET64(skb, attrtype, value) \
+	NLA_PUT_BE64(skb, attrtype | NLA_F_NET_BYTEORDER, value)
+
 #define NLA_PUT_STRING(skb, attrtype, value) \
 	NLA_PUT(skb, attrtype, strlen(value) + 1, value)
 
-- 
cgit v1.2.3


From a7b4f989a629493bb4ec4a354def784d440b32c4 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 1 Feb 2011 15:28:35 +0100
Subject: netfilter: ipset: IP set core support

The patch adds the IP set core support to the kernel.

The IP set core implements a netlink (nfnetlink) based protocol by which
one can create, destroy, flush, rename, swap, list, save, restore sets,
and add, delete, test elements from userspace. For simplicity (and backward
compatibilty and for not to force ip(6)tables to be linked with a netlink
library) reasons a small getsockopt-based protocol is also kept in order
to communicate with the ip(6)tables match and target.

The netlink protocol passes all u16, etc values in network order with
NLA_F_NET_BYTEORDER flag. The protocol enforces the proper use of the
NLA_F_NESTED and NLA_F_NET_BYTEORDER flags.

For other kernel subsystems (netfilter match and target) the API contains
the functions to add, delete and test elements in sets and the required calls
to get/put refereces to the sets before those operations can be performed.

The set types (which are implemented in independent modules) are stored
in a simple RCU protected list. A set type may have variants: for example
without timeout or with timeout support, for IPv4 or for IPv6. The sets
(i.e. the pointers to the sets) are stored in an array. The sets are
identified by their index in the array, which makes possible easy and
fast swapping of sets. The array is protected indirectly by the nfnl
mutex from nfnetlink. The content of the sets are protected by the rwlock
of the set.

There are functional differences between the add/del/test functions
for the kernel and userspace:

- kernel add/del/test: works on the current packet (i.e. one element)
- kernel test: may trigger an "add" operation  in order to fill
  out unspecified parts of the element from the packet (like MAC address)
- userspace add/del: works on the netlink message and thus possibly
  on multiple elements from the IPSET_ATTR_ADT container attribute.
- userspace add: may trigger resizing of a set

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/ipset/ip_set.h         |  452 +++++++
 include/linux/netfilter/ipset/ip_set_getport.h |   11 +
 include/linux/netfilter/ipset/pfxlen.h         |   35 +
 net/netfilter/Kconfig                          |    2 +
 net/netfilter/Makefile                         |    3 +
 net/netfilter/ipset/Kconfig                    |   26 +
 net/netfilter/ipset/Makefile                   |    8 +
 net/netfilter/ipset/ip_set_core.c              | 1662 ++++++++++++++++++++++++
 net/netfilter/ipset/ip_set_getport.c           |  136 ++
 net/netfilter/ipset/pfxlen.c                   |  291 +++++
 10 files changed, 2626 insertions(+)
 create mode 100644 include/linux/netfilter/ipset/ip_set.h
 create mode 100644 include/linux/netfilter/ipset/ip_set_getport.h
 create mode 100644 include/linux/netfilter/ipset/pfxlen.h
 create mode 100644 net/netfilter/ipset/Kconfig
 create mode 100644 net/netfilter/ipset/Makefile
 create mode 100644 net/netfilter/ipset/ip_set_core.c
 create mode 100644 net/netfilter/ipset/ip_set_getport.c
 create mode 100644 net/netfilter/ipset/pfxlen.c

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
new file mode 100644
index 000000000000..ec333d83f3b4
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -0,0 +1,452 @@
+#ifndef _IP_SET_H
+#define _IP_SET_H
+
+/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
+ *                         Patrick Schaaf <bof@bof.de>
+ *                         Martin Josefsson <gandalf@wlug.westbo.se>
+ * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* The protocol version */
+#define IPSET_PROTOCOL		6
+
+/* The max length of strings including NUL: set and type identifiers */
+#define IPSET_MAXNAMELEN	32
+
+/* Message types and commands */
+enum ipset_cmd {
+	IPSET_CMD_NONE,
+	IPSET_CMD_PROTOCOL,	/* 1: Return protocol version */
+	IPSET_CMD_CREATE,	/* 2: Create a new (empty) set */
+	IPSET_CMD_DESTROY,	/* 3: Destroy a (empty) set */
+	IPSET_CMD_FLUSH,	/* 4: Remove all elements from a set */
+	IPSET_CMD_RENAME,	/* 5: Rename a set */
+	IPSET_CMD_SWAP,		/* 6: Swap two sets */
+	IPSET_CMD_LIST,		/* 7: List sets */
+	IPSET_CMD_SAVE,		/* 8: Save sets */
+	IPSET_CMD_ADD,		/* 9: Add an element to a set */
+	IPSET_CMD_DEL,		/* 10: Delete an element from a set */
+	IPSET_CMD_TEST,		/* 11: Test an element in a set */
+	IPSET_CMD_HEADER,	/* 12: Get set header data only */
+	IPSET_CMD_TYPE,		/* 13: Get set type */
+	IPSET_MSG_MAX,		/* Netlink message commands */
+
+	/* Commands in userspace: */
+	IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 14: Enter restore mode */
+	IPSET_CMD_HELP,		/* 15: Get help */
+	IPSET_CMD_VERSION,	/* 16: Get program version */
+	IPSET_CMD_QUIT,		/* 17: Quit from interactive mode */
+
+	IPSET_CMD_MAX,
+
+	IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 18: Commit buffered commands */
+};
+
+/* Attributes at command level */
+enum {
+	IPSET_ATTR_UNSPEC,
+	IPSET_ATTR_PROTOCOL,	/* 1: Protocol version */
+	IPSET_ATTR_SETNAME,	/* 2: Name of the set */
+	IPSET_ATTR_TYPENAME,	/* 3: Typename */
+	IPSET_ATTR_SETNAME2 = IPSET_ATTR_TYPENAME, /* Setname at rename/swap */
+	IPSET_ATTR_REVISION,	/* 4: Settype revision */
+	IPSET_ATTR_FAMILY,	/* 5: Settype family */
+	IPSET_ATTR_FLAGS,	/* 6: Flags at command level */
+	IPSET_ATTR_DATA,	/* 7: Nested attributes */
+	IPSET_ATTR_ADT,		/* 8: Multiple data containers */
+	IPSET_ATTR_LINENO,	/* 9: Restore lineno */
+	IPSET_ATTR_PROTOCOL_MIN, /* 10: Minimal supported version number */
+	IPSET_ATTR_REVISION_MIN	= IPSET_ATTR_PROTOCOL_MIN, /* type rev min */
+	__IPSET_ATTR_CMD_MAX,
+};
+#define IPSET_ATTR_CMD_MAX	(__IPSET_ATTR_CMD_MAX - 1)
+
+/* CADT specific attributes */
+enum {
+	IPSET_ATTR_IP = IPSET_ATTR_UNSPEC + 1,
+	IPSET_ATTR_IP_FROM = IPSET_ATTR_IP,
+	IPSET_ATTR_IP_TO,	/* 2 */
+	IPSET_ATTR_CIDR,	/* 3 */
+	IPSET_ATTR_PORT,	/* 4 */
+	IPSET_ATTR_PORT_FROM = IPSET_ATTR_PORT,
+	IPSET_ATTR_PORT_TO,	/* 5 */
+	IPSET_ATTR_TIMEOUT,	/* 6 */
+	IPSET_ATTR_PROTO,	/* 7 */
+	IPSET_ATTR_CADT_FLAGS,	/* 8 */
+	IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO,	/* 9 */
+	/* Reserve empty slots */
+	IPSET_ATTR_CADT_MAX = 16,
+	/* Create-only specific attributes */
+	IPSET_ATTR_GC,
+	IPSET_ATTR_HASHSIZE,
+	IPSET_ATTR_MAXELEM,
+	IPSET_ATTR_NETMASK,
+	IPSET_ATTR_PROBES,
+	IPSET_ATTR_RESIZE,
+	IPSET_ATTR_SIZE,
+	/* Kernel-only */
+	IPSET_ATTR_ELEMENTS,
+	IPSET_ATTR_REFERENCES,
+	IPSET_ATTR_MEMSIZE,
+
+	__IPSET_ATTR_CREATE_MAX,
+};
+#define IPSET_ATTR_CREATE_MAX	(__IPSET_ATTR_CREATE_MAX - 1)
+
+/* ADT specific attributes */
+enum {
+	IPSET_ATTR_ETHER = IPSET_ATTR_CADT_MAX + 1,
+	IPSET_ATTR_NAME,
+	IPSET_ATTR_NAMEREF,
+	IPSET_ATTR_IP2,
+	IPSET_ATTR_CIDR2,
+	__IPSET_ATTR_ADT_MAX,
+};
+#define IPSET_ATTR_ADT_MAX	(__IPSET_ATTR_ADT_MAX - 1)
+
+/* IP specific attributes */
+enum {
+	IPSET_ATTR_IPADDR_IPV4 = IPSET_ATTR_UNSPEC + 1,
+	IPSET_ATTR_IPADDR_IPV6,
+	__IPSET_ATTR_IPADDR_MAX,
+};
+#define IPSET_ATTR_IPADDR_MAX	(__IPSET_ATTR_IPADDR_MAX - 1)
+
+/* Error codes */
+enum ipset_errno {
+	IPSET_ERR_PRIVATE = 4096,
+	IPSET_ERR_PROTOCOL,
+	IPSET_ERR_FIND_TYPE,
+	IPSET_ERR_MAX_SETS,
+	IPSET_ERR_BUSY,
+	IPSET_ERR_EXIST_SETNAME2,
+	IPSET_ERR_TYPE_MISMATCH,
+	IPSET_ERR_EXIST,
+	IPSET_ERR_INVALID_CIDR,
+	IPSET_ERR_INVALID_NETMASK,
+	IPSET_ERR_INVALID_FAMILY,
+	IPSET_ERR_TIMEOUT,
+	IPSET_ERR_REFERENCED,
+	IPSET_ERR_IPADDR_IPV4,
+	IPSET_ERR_IPADDR_IPV6,
+
+	/* Type specific error codes */
+	IPSET_ERR_TYPE_SPECIFIC = 4352,
+};
+
+/* Flags at command level */
+enum ipset_cmd_flags {
+	IPSET_FLAG_BIT_EXIST	= 0,
+	IPSET_FLAG_EXIST	= (1 << IPSET_FLAG_BIT_EXIST),
+};
+
+/* Flags at CADT attribute level */
+enum ipset_cadt_flags {
+	IPSET_FLAG_BIT_BEFORE	= 0,
+	IPSET_FLAG_BEFORE	= (1 << IPSET_FLAG_BIT_BEFORE),
+};
+
+/* Commands with settype-specific attributes */
+enum ipset_adt {
+	IPSET_ADD,
+	IPSET_DEL,
+	IPSET_TEST,
+	IPSET_ADT_MAX,
+	IPSET_CREATE = IPSET_ADT_MAX,
+	IPSET_CADT_MAX,
+};
+
+#ifdef __KERNEL__
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/vmalloc.h>
+#include <net/netlink.h>
+
+/* Sets are identified by an index in kernel space. Tweak with ip_set_id_t
+ * and IPSET_INVALID_ID if you want to increase the max number of sets.
+ */
+typedef u16 ip_set_id_t;
+
+#define IPSET_INVALID_ID		65535
+
+enum ip_set_dim {
+	IPSET_DIM_ZERO = 0,
+	IPSET_DIM_ONE,
+	IPSET_DIM_TWO,
+	IPSET_DIM_THREE,
+	/* Max dimension in elements.
+	 * If changed, new revision of iptables match/target is required.
+	 */
+	IPSET_DIM_MAX = 6,
+};
+
+/* Option flags for kernel operations */
+enum ip_set_kopt {
+	IPSET_INV_MATCH = (1 << IPSET_DIM_ZERO),
+	IPSET_DIM_ONE_SRC = (1 << IPSET_DIM_ONE),
+	IPSET_DIM_TWO_SRC = (1 << IPSET_DIM_TWO),
+	IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE),
+};
+
+/* Set features */
+enum ip_set_feature {
+	IPSET_TYPE_IP_FLAG = 0,
+	IPSET_TYPE_IP = (1 << IPSET_TYPE_IP_FLAG),
+	IPSET_TYPE_PORT_FLAG = 1,
+	IPSET_TYPE_PORT = (1 << IPSET_TYPE_PORT_FLAG),
+	IPSET_TYPE_MAC_FLAG = 2,
+	IPSET_TYPE_MAC = (1 << IPSET_TYPE_MAC_FLAG),
+	IPSET_TYPE_IP2_FLAG = 3,
+	IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG),
+	IPSET_TYPE_NAME_FLAG = 4,
+	IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG),
+	/* Strictly speaking not a feature, but a flag for dumping:
+	 * this settype must be dumped last */
+	IPSET_DUMP_LAST_FLAG = 7,
+	IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG),
+};
+
+struct ip_set;
+
+typedef int (*ipset_adtfn)(struct ip_set *set, void *value, u32 timeout);
+
+/* Set type, variant-specific part */
+struct ip_set_type_variant {
+	/* Kernelspace: test/add/del entries
+	 *		returns negative error code,
+	 *			zero for no match/success to add/delete
+	 *			positive for matching element */
+	int (*kadt)(struct ip_set *set, const struct sk_buff * skb,
+		    enum ipset_adt adt, u8 pf, u8 dim, u8 flags);
+
+	/* Userspace: test/add/del entries
+	 *		returns negative error code,
+	 *			zero for no match/success to add/delete
+	 *			positive for matching element */
+	int (*uadt)(struct ip_set *set, struct nlattr *tb[],
+		    enum ipset_adt adt, u32 *lineno, u32 flags);
+
+	/* Low level add/del/test functions */
+	ipset_adtfn adt[IPSET_ADT_MAX];
+
+	/* When adding entries and set is full, try to resize the set */
+	int (*resize)(struct ip_set *set, bool retried);
+	/* Destroy the set */
+	void (*destroy)(struct ip_set *set);
+	/* Flush the elements */
+	void (*flush)(struct ip_set *set);
+	/* Expire entries before listing */
+	void (*expire)(struct ip_set *set);
+	/* List set header data */
+	int (*head)(struct ip_set *set, struct sk_buff *skb);
+	/* List elements */
+	int (*list)(const struct ip_set *set, struct sk_buff *skb,
+		    struct netlink_callback *cb);
+
+	/* Return true if "b" set is the same as "a"
+	 * according to the create set parameters */
+	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+};
+
+/* The core set type structure */
+struct ip_set_type {
+	struct list_head list;
+
+	/* Typename */
+	char name[IPSET_MAXNAMELEN];
+	/* Protocol version */
+	u8 protocol;
+	/* Set features to control swapping */
+	u8 features;
+	/* Set type dimension */
+	u8 dimension;
+	/* Supported family: may be AF_UNSPEC for both AF_INET/AF_INET6 */
+	u8 family;
+	/* Type revision */
+	u8 revision;
+
+	/* Create set */
+	int (*create)(struct ip_set *set, struct nlattr *tb[], u32 flags);
+
+	/* Attribute policies */
+	const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1];
+	const struct nla_policy adt_policy[IPSET_ATTR_ADT_MAX + 1];
+
+	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
+	struct module *me;
+};
+
+/* register and unregister set type */
+extern int ip_set_type_register(struct ip_set_type *set_type);
+extern void ip_set_type_unregister(struct ip_set_type *set_type);
+
+/* A generic IP set */
+struct ip_set {
+	/* The name of the set */
+	char name[IPSET_MAXNAMELEN];
+	/* Lock protecting the set data */
+	rwlock_t lock;
+	/* References to the set */
+	atomic_t ref;
+	/* The core set type */
+	struct ip_set_type *type;
+	/* The type variant doing the real job */
+	const struct ip_set_type_variant *variant;
+	/* The actual INET family of the set */
+	u8 family;
+	/* The type specific data */
+	void *data;
+};
+
+/* register and unregister set references */
+extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set);
+extern void ip_set_put_byindex(ip_set_id_t index);
+extern const char * ip_set_name_byindex(ip_set_id_t index);
+extern ip_set_id_t ip_set_nfnl_get(const char *name);
+extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index);
+extern void ip_set_nfnl_put(ip_set_id_t index);
+
+/* API for iptables set match, and SET target */
+extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb,
+		      u8 family, u8 dim, u8 flags);
+extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb,
+		      u8 family, u8 dim, u8 flags);
+extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb,
+		       u8 family, u8 dim, u8 flags);
+
+/* Utility functions */
+extern void * ip_set_alloc(size_t size);
+extern void ip_set_free(void *members);
+extern int ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr);
+extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr);
+
+static inline int
+ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr)
+{
+	__be32 ip;
+	int ret = ip_set_get_ipaddr4(nla, &ip);
+	
+	if (ret)
+		return ret;
+	*ipaddr = ntohl(ip);
+	return 0;
+}
+
+/* Ignore IPSET_ERR_EXIST errors if asked to do so? */
+static inline bool
+ip_set_eexist(int ret, u32 flags)
+{
+	return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST);
+}
+
+/* Check the NLA_F_NET_BYTEORDER flag */
+static inline bool
+ip_set_attr_netorder(struct nlattr *tb[], int type)
+{
+	return tb[type] && (tb[type]->nla_type & NLA_F_NET_BYTEORDER);
+}
+
+static inline bool
+ip_set_optattr_netorder(struct nlattr *tb[], int type)
+{
+	return !tb[type] || (tb[type]->nla_type & NLA_F_NET_BYTEORDER);
+}
+
+/* Useful converters */
+static inline u32
+ip_set_get_h32(const struct nlattr *attr)
+{
+	return ntohl(nla_get_be32(attr));
+}
+
+static inline u16
+ip_set_get_h16(const struct nlattr *attr)
+{
+	return ntohs(nla_get_be16(attr));
+}
+
+#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED)
+#define ipset_nest_end(skb, start)  nla_nest_end(skb, start)
+
+#define NLA_PUT_IPADDR4(skb, type, ipaddr)			\
+do {								\
+	struct nlattr *__nested = ipset_nest_start(skb, type);	\
+								\
+	if (!__nested)						\
+		goto nla_put_failure;				\
+	NLA_PUT_NET32(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr);	\
+	ipset_nest_end(skb, __nested);				\
+} while (0)
+
+#define NLA_PUT_IPADDR6(skb, type, ipaddrptr)			\
+do {								\
+	struct nlattr *__nested = ipset_nest_start(skb, type);	\
+								\
+	if (!__nested)						\
+		goto nla_put_failure;				\
+	NLA_PUT(skb, IPSET_ATTR_IPADDR_IPV6,			\
+		sizeof(struct in6_addr), ipaddrptr);		\
+	ipset_nest_end(skb, __nested);				\
+} while (0)
+
+/* Get address from skbuff */
+static inline __be32
+ip4addr(const struct sk_buff *skb, bool src)
+{
+	return src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr;
+}
+
+static inline void
+ip4addrptr(const struct sk_buff *skb, bool src, __be32 *addr)
+{
+	*addr = src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr;
+}
+
+static inline void
+ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr)
+{
+	memcpy(addr, src ? &ipv6_hdr(skb)->saddr : &ipv6_hdr(skb)->daddr,
+	       sizeof(*addr));
+}
+
+/* Calculate the bytes required to store the inclusive range of a-b */
+static inline int
+bitmap_bytes(u32 a, u32 b)
+{
+	return 4 * ((((b - a + 8) / 8) + 3) / 4);
+}
+
+/* Interface to iptables/ip6tables */
+
+#define SO_IP_SET		83
+
+union ip_set_name_index {
+	char name[IPSET_MAXNAMELEN];
+	ip_set_id_t index;
+};
+
+#define IP_SET_OP_GET_BYNAME	0x00000006	/* Get set index by name */
+struct ip_set_req_get_set {
+	unsigned op;
+	unsigned version;
+	union ip_set_name_index set;
+};
+
+#define IP_SET_OP_GET_BYINDEX	0x00000007	/* Get set name by index */
+/* Uses ip_set_req_get_set */
+
+#define IP_SET_OP_VERSION	0x00000100	/* Ask kernel version */
+struct ip_set_req_version {
+	unsigned op;
+	unsigned version;
+};
+
+#endif	/* __KERNEL__ */
+
+#endif /*_IP_SET_H */
diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h
new file mode 100644
index 000000000000..694c433298b8
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_getport.h
@@ -0,0 +1,11 @@
+#ifndef _IP_SET_GETPORT_H
+#define _IP_SET_GETPORT_H
+
+extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
+				__be16 *port, u8 *proto);
+extern bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
+				__be16 *port, u8 *proto);
+extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src,
+				__be16 *port);
+
+#endif /*_IP_SET_GETPORT_H*/
diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h
new file mode 100644
index 000000000000..0e1fb50da562
--- /dev/null
+++ b/include/linux/netfilter/ipset/pfxlen.h
@@ -0,0 +1,35 @@
+#ifndef _PFXLEN_H
+#define _PFXLEN_H
+
+#include <asm/byteorder.h>
+#include <linux/netfilter.h> 
+
+/* Prefixlen maps, by Jan Engelhardt  */
+extern const union nf_inet_addr ip_set_netmask_map[];
+extern const union nf_inet_addr ip_set_hostmask_map[];
+
+static inline __be32
+ip_set_netmask(u8 pfxlen)
+{
+	return ip_set_netmask_map[pfxlen].ip;
+}
+
+static inline const __be32 *
+ip_set_netmask6(u8 pfxlen)
+{
+	return &ip_set_netmask_map[pfxlen].ip6[0];
+}
+
+static inline u32
+ip_set_hostmask(u8 pfxlen)
+{
+	return (__force u32) ip_set_hostmask_map[pfxlen].ip;
+}
+
+static inline const __be32 *
+ip_set_hostmask6(u8 pfxlen)
+{
+	return &ip_set_hostmask_map[pfxlen].ip6[0];
+}
+
+#endif /*_PFXLEN_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index faf7412ea453..351abf8ace13 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1052,4 +1052,6 @@ endif # NETFILTER_XTABLES
 
 endmenu
 
+source "net/netfilter/ipset/Kconfig"
+
 source "net/netfilter/ipvs/Kconfig"
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 9ae6878a85b1..510b586ccb7f 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -105,5 +105,8 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_U32) += xt_u32.o
 
+# ipset
+obj-$(CONFIG_IP_SET) += ipset/
+
 # IPVS
 obj-$(CONFIG_IP_VS) += ipvs/
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
new file mode 100644
index 000000000000..5ade156dd470
--- /dev/null
+++ b/net/netfilter/ipset/Kconfig
@@ -0,0 +1,26 @@
+menuconfig IP_SET
+	tristate "IP set support"
+	depends on INET && NETFILTER
+	help
+	  This option adds IP set support to the kernel.
+	  In order to define and use the sets, you need the userspace utility
+	  ipset(8). You can use the sets in netfilter via the "set" match
+	  and "SET" target.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+if IP_SET
+
+config IP_SET_MAX
+	int "Maximum number of IP sets"
+	default 256
+	range 2 65534
+	depends on IP_SET
+	help
+	  You can define here default value of the maximum number 
+	  of IP sets for the kernel.
+
+	  The value can be overriden by the 'max_sets' module
+	  parameter of the 'ip_set' module.
+
+endif # IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
new file mode 100644
index 000000000000..910cd425c067
--- /dev/null
+++ b/net/netfilter/ipset/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for the ipset modules
+#
+
+ip_set-y := ip_set_core.o ip_set_getport.o pfxlen.o
+
+# ipset core
+obj-$(CONFIG_IP_SET) += ip_set.o
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
new file mode 100644
index 000000000000..8a736247e85f
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -0,0 +1,1662 @@
+/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
+ *                         Patrick Schaaf <bof@bof.de>
+ * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module for IP set management */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+#include <linux/version.h>
+#include <net/netlink.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/ipset/ip_set.h>
+
+static LIST_HEAD(ip_set_type_list);		/* all registered set types */
+static DEFINE_MUTEX(ip_set_type_mutex);		/* protects ip_set_type_list */
+
+static struct ip_set **ip_set_list;		/* all individual sets */
+static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */
+
+#define STREQ(a, b)	(strncmp(a, b, IPSET_MAXNAMELEN) == 0)
+
+static unsigned int max_sets;
+
+module_param(max_sets, int, 0600);
+MODULE_PARM_DESC(max_sets, "maximal number of sets");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
+MODULE_DESCRIPTION("core IP set support");
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
+
+/*
+ * The set types are implemented in modules and registered set types
+ * can be found in ip_set_type_list. Adding/deleting types is
+ * serialized by ip_set_type_mutex.
+ */
+
+static inline void
+ip_set_type_lock(void)
+{
+	mutex_lock(&ip_set_type_mutex);
+}
+
+static inline void
+ip_set_type_unlock(void)
+{
+	mutex_unlock(&ip_set_type_mutex);
+}
+
+/* Register and deregister settype */
+
+static struct ip_set_type *
+find_set_type(const char *name, u8 family, u8 revision)
+{
+	struct ip_set_type *type;
+
+	list_for_each_entry_rcu(type, &ip_set_type_list, list)
+		if (STREQ(type->name, name) &&
+		    (type->family == family || type->family == AF_UNSPEC) &&
+		    type->revision == revision)
+			return type;
+	return NULL;
+}
+
+/* Unlock, try to load a set type module and lock again */
+static int
+try_to_load_type(const char *name)
+{
+	nfnl_unlock();
+	pr_debug("try to load ip_set_%s\n", name);
+	if (request_module("ip_set_%s", name) < 0) {
+		pr_warning("Can't find ip_set type %s\n", name);
+		nfnl_lock();
+		return -IPSET_ERR_FIND_TYPE;
+	}
+	nfnl_lock();
+	return -EAGAIN;
+}
+
+/* Find a set type and reference it */
+static int
+find_set_type_get(const char *name, u8 family, u8 revision,
+		  struct ip_set_type **found)
+{
+	rcu_read_lock();
+	*found = find_set_type(name, family, revision);
+	if (*found) {
+		int err = !try_module_get((*found)->me);
+		rcu_read_unlock();
+		return err ? -EFAULT : 0;
+	}
+	rcu_read_unlock();
+
+	return try_to_load_type(name);
+}
+
+/* Find a given set type by name and family.
+ * If we succeeded, the supported minimal and maximum revisions are
+ * filled out.
+ */
+static int
+find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max)
+{
+	struct ip_set_type *type;
+	bool found = false;
+
+	*min = *max = 0;
+	rcu_read_lock();
+	list_for_each_entry_rcu(type, &ip_set_type_list, list)
+		if (STREQ(type->name, name) &&
+		    (type->family == family || type->family == AF_UNSPEC)) {
+			found = true;
+			if (type->revision < *min)
+				*min = type->revision;
+			else if (type->revision > *max)
+				*max = type->revision;
+		}
+	rcu_read_unlock();
+	if (found)
+		return 0;
+
+	return try_to_load_type(name);
+}
+
+#define family_name(f)	((f) == AF_INET ? "inet" : \
+			 (f) == AF_INET6 ? "inet6" : "any")
+
+/* Register a set type structure. The type is identified by
+ * the unique triple of name, family and revision.
+ */
+int
+ip_set_type_register(struct ip_set_type *type)
+{
+	int ret = 0;
+
+	if (type->protocol != IPSET_PROTOCOL) {
+		pr_warning("ip_set type %s, family %s, revision %u uses "
+			   "wrong protocol version %u (want %u)\n",
+			   type->name, family_name(type->family),
+			   type->revision, type->protocol, IPSET_PROTOCOL);
+		return -EINVAL;
+	}
+
+	ip_set_type_lock();
+	if (find_set_type(type->name, type->family, type->revision)) {
+		/* Duplicate! */
+		pr_warning("ip_set type %s, family %s, revision %u "
+			   "already registered!\n", type->name,
+			   family_name(type->family), type->revision);
+		ret = -EINVAL;
+		goto unlock;
+	}
+	list_add_rcu(&type->list, &ip_set_type_list);
+	pr_debug("type %s, family %s, revision %u registered.\n",
+		 type->name, family_name(type->family), type->revision);
+unlock:
+	ip_set_type_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ip_set_type_register);
+
+/* Unregister a set type. There's a small race with ip_set_create */
+void
+ip_set_type_unregister(struct ip_set_type *type)
+{
+	ip_set_type_lock();
+	if (!find_set_type(type->name, type->family, type->revision)) {
+		pr_warning("ip_set type %s, family %s, revision %u "
+			   "not registered\n", type->name,
+			   family_name(type->family), type->revision);
+		goto unlock;
+	}
+	list_del_rcu(&type->list);
+	pr_debug("type %s, family %s, revision %u unregistered.\n",
+		 type->name, family_name(type->family), type->revision);
+unlock:
+	ip_set_type_unlock();
+
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(ip_set_type_unregister);
+
+/* Utility functions */
+void *
+ip_set_alloc(size_t size)
+{
+	void *members = NULL;
+
+	if (size < KMALLOC_MAX_SIZE)
+		members = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+
+	if (members) {
+		pr_debug("%p: allocated with kmalloc\n", members);
+		return members;
+	}
+
+	members = vzalloc(size);
+	if (!members)
+		return NULL;
+	pr_debug("%p: allocated with vmalloc\n", members);
+
+	return members;
+}
+EXPORT_SYMBOL_GPL(ip_set_alloc);
+
+void
+ip_set_free(void *members)
+{
+	pr_debug("%p: free with %s\n", members,
+		 is_vmalloc_addr(members) ? "vfree" : "kfree");
+	if (is_vmalloc_addr(members))
+		vfree(members);
+	else
+		kfree(members);
+}
+EXPORT_SYMBOL_GPL(ip_set_free);
+
+static inline bool
+flag_nested(const struct nlattr *nla)
+{
+	return nla->nla_type & NLA_F_NESTED;
+}
+
+static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = {
+	[IPSET_ATTR_IPADDR_IPV4]	= { .type = NLA_U32 },
+	[IPSET_ATTR_IPADDR_IPV6]	= { .type = NLA_BINARY,
+					    .len = sizeof(struct in6_addr) },
+};
+
+int
+ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr)
+{
+	struct nlattr *tb[IPSET_ATTR_IPADDR_MAX+1];
+
+	if (unlikely(!flag_nested(nla)))
+		return -IPSET_ERR_PROTOCOL;
+	if (nla_parse(tb, IPSET_ATTR_IPADDR_MAX, nla_data(nla), nla_len(nla),
+		      ipaddr_policy))
+		return -IPSET_ERR_PROTOCOL;
+	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4)))
+		return -IPSET_ERR_PROTOCOL;
+
+	*ipaddr = nla_get_be32(tb[IPSET_ATTR_IPADDR_IPV4]);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ip_set_get_ipaddr4);
+
+int
+ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
+{
+	struct nlattr *tb[IPSET_ATTR_IPADDR_MAX+1];
+
+	if (unlikely(!flag_nested(nla)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (nla_parse(tb, IPSET_ATTR_IPADDR_MAX, nla_data(nla), nla_len(nla),
+		      ipaddr_policy))
+		return -IPSET_ERR_PROTOCOL;
+	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6)))
+		return -IPSET_ERR_PROTOCOL;
+
+	memcpy(ipaddr, nla_data(tb[IPSET_ATTR_IPADDR_IPV6]),
+		sizeof(struct in6_addr));
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
+
+/*
+ * Creating/destroying/renaming/swapping affect the existence and
+ * the properties of a set. All of these can be executed from userspace
+ * only and serialized by the nfnl mutex indirectly from nfnetlink.
+ *
+ * Sets are identified by their index in ip_set_list and the index
+ * is used by the external references (set/SET netfilter modules).
+ *
+ * The set behind an index may change by swapping only, from userspace.
+ */
+
+static inline void
+__ip_set_get(ip_set_id_t index)
+{
+	atomic_inc(&ip_set_list[index]->ref);
+}
+
+static inline void
+__ip_set_put(ip_set_id_t index)
+{
+	atomic_dec(&ip_set_list[index]->ref);
+}
+
+/*
+ * Add, del and test set entries from kernel.
+ *
+ * The set behind the index must exist and must be referenced
+ * so it can't be destroyed (or changed) under our foot.
+ */
+
+int
+ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
+	    u8 family, u8 dim, u8 flags)
+{
+	struct ip_set *set = ip_set_list[index];
+	int ret = 0;
+
+	BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+	pr_debug("set %s, index %u\n", set->name, index);
+
+	if (dim < set->type->dimension ||
+	    !(family == set->family || set->family == AF_UNSPEC))
+		return 0;
+
+	read_lock_bh(&set->lock);
+	ret = set->variant->kadt(set, skb, IPSET_TEST, family, dim, flags);
+	read_unlock_bh(&set->lock);
+
+	if (ret == -EAGAIN) {
+		/* Type requests element to be completed */
+		pr_debug("element must be competed, ADD is triggered\n");
+		write_lock_bh(&set->lock);
+		set->variant->kadt(set, skb, IPSET_ADD, family, dim, flags);
+		write_unlock_bh(&set->lock);
+		ret = 1;
+	}
+
+	/* Convert error codes to nomatch */
+	return (ret < 0 ? 0 : ret);
+}
+EXPORT_SYMBOL_GPL(ip_set_test);
+
+int
+ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
+	   u8 family, u8 dim, u8 flags)
+{
+	struct ip_set *set = ip_set_list[index];
+	int ret;
+
+	BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+	pr_debug("set %s, index %u\n", set->name, index);
+
+	if (dim < set->type->dimension ||
+	    !(family == set->family || set->family == AF_UNSPEC))
+		return 0;
+
+	write_lock_bh(&set->lock);
+	ret = set->variant->kadt(set, skb, IPSET_ADD, family, dim, flags);
+	write_unlock_bh(&set->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ip_set_add);
+
+int
+ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
+	   u8 family, u8 dim, u8 flags)
+{
+	struct ip_set *set = ip_set_list[index];
+	int ret = 0;
+
+	BUG_ON(set == NULL || atomic_read(&set->ref) == 0);
+	pr_debug("set %s, index %u\n", set->name, index);
+
+	if (dim < set->type->dimension ||
+	    !(family == set->family || set->family == AF_UNSPEC))
+		return 0;
+
+	write_lock_bh(&set->lock);
+	ret = set->variant->kadt(set, skb, IPSET_DEL, family, dim, flags);
+	write_unlock_bh(&set->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ip_set_del);
+
+/*
+ * Find set by name, reference it once. The reference makes sure the
+ * thing pointed to, does not go away under our feet.
+ *
+ * The nfnl mutex must already be activated.
+ */
+ip_set_id_t
+ip_set_get_byname(const char *name, struct ip_set **set)
+{
+	ip_set_id_t i, index = IPSET_INVALID_ID;
+	struct ip_set *s;
+
+	for (i = 0; i < ip_set_max; i++) {
+		s = ip_set_list[i];
+		if (s != NULL && STREQ(s->name, name)) {
+			__ip_set_get(i);
+			index = i;
+			*set = s;
+		}
+	}
+
+	return index;
+}
+EXPORT_SYMBOL_GPL(ip_set_get_byname);
+
+/*
+ * If the given set pointer points to a valid set, decrement
+ * reference count by 1. The caller shall not assume the index
+ * to be valid, after calling this function.
+ *
+ * The nfnl mutex must already be activated.
+ */
+void
+ip_set_put_byindex(ip_set_id_t index)
+{
+	if (ip_set_list[index] != NULL) {
+		BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0);
+		__ip_set_put(index);
+	}
+}
+EXPORT_SYMBOL_GPL(ip_set_put_byindex);
+
+/*
+ * Get the name of a set behind a set index.
+ * We assume the set is referenced, so it does exist and
+ * can't be destroyed. The set cannot be renamed due to
+ * the referencing either.
+ *
+ * The nfnl mutex must already be activated.
+ */
+const char *
+ip_set_name_byindex(ip_set_id_t index)
+{
+	const struct ip_set *set = ip_set_list[index];
+
+	BUG_ON(set == NULL);
+	BUG_ON(atomic_read(&set->ref) == 0);
+
+	/* Referenced, so it's safe */
+	return set->name;
+}
+EXPORT_SYMBOL_GPL(ip_set_name_byindex);
+
+/*
+ * Routines to call by external subsystems, which do not
+ * call nfnl_lock for us.
+ */
+
+/*
+ * Find set by name, reference it once. The reference makes sure the
+ * thing pointed to, does not go away under our feet.
+ *
+ * The nfnl mutex is used in the function.
+ */
+ip_set_id_t
+ip_set_nfnl_get(const char *name)
+{
+	struct ip_set *s;
+	ip_set_id_t index;
+
+	nfnl_lock();
+	index = ip_set_get_byname(name, &s);
+	nfnl_unlock();
+
+	return index;
+}
+EXPORT_SYMBOL_GPL(ip_set_nfnl_get);
+
+/*
+ * Find set by index, reference it once. The reference makes sure the
+ * thing pointed to, does not go away under our feet.
+ *
+ * The nfnl mutex is used in the function.
+ */
+ip_set_id_t
+ip_set_nfnl_get_byindex(ip_set_id_t index)
+{
+	if (index > ip_set_max)
+		return IPSET_INVALID_ID;
+
+	nfnl_lock();
+	if (ip_set_list[index])
+		__ip_set_get(index);
+	else
+		index = IPSET_INVALID_ID;
+	nfnl_unlock();
+
+	return index;
+}
+EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex);
+
+/*
+ * If the given set pointer points to a valid set, decrement
+ * reference count by 1. The caller shall not assume the index
+ * to be valid, after calling this function.
+ *
+ * The nfnl mutex is used in the function.
+ */
+void
+ip_set_nfnl_put(ip_set_id_t index)
+{
+	nfnl_lock();
+	if (ip_set_list[index] != NULL) {
+		BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0);
+		__ip_set_put(index);
+	}
+	nfnl_unlock();
+}
+EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
+
+/*
+ * Communication protocol with userspace over netlink.
+ *
+ * We already locked by nfnl_lock.
+ */
+
+static inline bool
+protocol_failed(const struct nlattr * const tb[])
+{
+	return !tb[IPSET_ATTR_PROTOCOL] ||
+	       nla_get_u8(tb[IPSET_ATTR_PROTOCOL]) != IPSET_PROTOCOL;
+}
+
+static inline u32
+flag_exist(const struct nlmsghdr *nlh)
+{
+	return nlh->nlmsg_flags & NLM_F_EXCL ? 0 : IPSET_FLAG_EXIST;
+}
+
+static struct nlmsghdr *
+start_msg(struct sk_buff *skb, u32 pid, u32 seq, unsigned int flags,
+	  enum ipset_cmd cmd)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+
+	nlh = nlmsg_put(skb, pid, seq, cmd | (NFNL_SUBSYS_IPSET << 8),
+			sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		return NULL;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family = AF_INET;
+	nfmsg->version = NFNETLINK_V0;
+	nfmsg->res_id = 0;
+
+	return nlh;
+}
+
+/* Create a set */
+
+static const struct nla_policy ip_set_create_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_SETNAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+	[IPSET_ATTR_TYPENAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1},
+	[IPSET_ATTR_REVISION]	= { .type = NLA_U8 },
+	[IPSET_ATTR_FAMILY]	= { .type = NLA_U8 },
+	[IPSET_ATTR_DATA]	= { .type = NLA_NESTED },
+};
+
+static ip_set_id_t
+find_set_id(const char *name)
+{
+	ip_set_id_t i, index = IPSET_INVALID_ID;
+	const struct ip_set *set;
+
+	for (i = 0; index == IPSET_INVALID_ID && i < ip_set_max; i++) {
+		set = ip_set_list[i];
+		if (set != NULL && STREQ(set->name, name))
+			index = i;
+	}
+	return index;
+}
+
+static inline struct ip_set *
+find_set(const char *name)
+{
+	ip_set_id_t index = find_set_id(name);
+
+	return index == IPSET_INVALID_ID ? NULL : ip_set_list[index];
+}
+
+static int
+find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set)
+{
+	ip_set_id_t i;
+
+	*index = IPSET_INVALID_ID;
+	for (i = 0;  i < ip_set_max; i++) {
+		if (ip_set_list[i] == NULL) {
+			if (*index == IPSET_INVALID_ID)
+				*index = i;
+		} else if (STREQ(name, ip_set_list[i]->name)) {
+			/* Name clash */
+			*set = ip_set_list[i];
+			return -EEXIST;
+		}
+	}
+	if (*index == IPSET_INVALID_ID)
+		/* No free slot remained */
+		return -IPSET_ERR_MAX_SETS;
+	return 0;
+}
+
+static int
+ip_set_create(struct sock *ctnl, struct sk_buff *skb,
+	      const struct nlmsghdr *nlh,
+	      const struct nlattr * const attr[])
+{
+	struct ip_set *set, *clash;
+	ip_set_id_t index = IPSET_INVALID_ID;
+	struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {};
+	const char *name, *typename;
+	u8 family, revision;
+	u32 flags = flag_exist(nlh);
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL ||
+		     attr[IPSET_ATTR_TYPENAME] == NULL ||
+		     attr[IPSET_ATTR_REVISION] == NULL ||
+		     attr[IPSET_ATTR_FAMILY] == NULL ||
+		     (attr[IPSET_ATTR_DATA] != NULL &&
+		      !flag_nested(attr[IPSET_ATTR_DATA]))))
+		return -IPSET_ERR_PROTOCOL;
+
+	name = nla_data(attr[IPSET_ATTR_SETNAME]);
+	typename = nla_data(attr[IPSET_ATTR_TYPENAME]);
+	family = nla_get_u8(attr[IPSET_ATTR_FAMILY]);
+	revision = nla_get_u8(attr[IPSET_ATTR_REVISION]);
+	pr_debug("setname: %s, typename: %s, family: %s, revision: %u\n",
+		 name, typename, family_name(family), revision);
+
+	/*
+	 * First, and without any locks, allocate and initialize
+	 * a normal base set structure.
+	 */
+	set = kzalloc(sizeof(struct ip_set), GFP_KERNEL);
+	if (!set)
+		return -ENOMEM;
+	rwlock_init(&set->lock);
+	strlcpy(set->name, name, IPSET_MAXNAMELEN);
+	atomic_set(&set->ref, 0);
+	set->family = family;
+
+	/*
+	 * Next, check that we know the type, and take
+	 * a reference on the type, to make sure it stays available
+	 * while constructing our new set.
+	 *
+	 * After referencing the type, we try to create the type
+	 * specific part of the set without holding any locks.
+	 */
+	ret = find_set_type_get(typename, family, revision, &(set->type));
+	if (ret)
+		goto out;
+
+	/*
+	 * Without holding any locks, create private part.
+	 */
+	if (attr[IPSET_ATTR_DATA] &&
+	    nla_parse(tb, IPSET_ATTR_CREATE_MAX,
+	    	      nla_data(attr[IPSET_ATTR_DATA]),
+	    	      nla_len(attr[IPSET_ATTR_DATA]),
+	    	      set->type->create_policy)) {
+	    	ret = -IPSET_ERR_PROTOCOL;
+	    	goto put_out;
+	}
+
+	ret = set->type->create(set, tb, flags);
+	if (ret != 0)
+		goto put_out;
+
+	/* BTW, ret==0 here. */
+
+	/*
+	 * Here, we have a valid, constructed set and we are protected
+	 * by nfnl_lock. Find the first free index in ip_set_list and
+	 * check clashing.
+	 */
+	if ((ret = find_free_id(set->name, &index, &clash)) != 0) {
+		/* If this is the same set and requested, ignore error */
+		if (ret == -EEXIST &&
+		    (flags & IPSET_FLAG_EXIST) &&
+		    STREQ(set->type->name, clash->type->name) &&
+		    set->type->family == clash->type->family &&
+		    set->type->revision == clash->type->revision &&
+		    set->variant->same_set(set, clash))
+			ret = 0;
+		goto cleanup;
+	}
+
+	/*
+	 * Finally! Add our shiny new set to the list, and be done.
+	 */
+	pr_debug("create: '%s' created with index %u!\n", set->name, index);
+	ip_set_list[index] = set;
+
+	return ret;
+
+cleanup:
+	set->variant->destroy(set);
+put_out:
+	module_put(set->type->me);
+out:
+	kfree(set);
+	return ret;
+}
+
+/* Destroy sets */
+
+static const struct nla_policy
+ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_SETNAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+};
+
+static void
+ip_set_destroy_set(ip_set_id_t index)
+{
+	struct ip_set *set = ip_set_list[index];
+
+	pr_debug("set: %s\n",  set->name);
+	ip_set_list[index] = NULL;
+
+	/* Must call it without holding any lock */
+	set->variant->destroy(set);
+	module_put(set->type->me);
+	kfree(set);
+}
+
+static int
+ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
+	       const struct nlmsghdr *nlh,
+	       const struct nlattr * const attr[])
+{
+	ip_set_id_t i;
+
+	if (unlikely(protocol_failed(attr)))
+		return -IPSET_ERR_PROTOCOL;
+
+	/* References are protected by the nfnl mutex */
+	if (!attr[IPSET_ATTR_SETNAME]) {
+		for (i = 0; i < ip_set_max; i++) {
+			if (ip_set_list[i] != NULL &&
+			    (atomic_read(&ip_set_list[i]->ref)))
+				return -IPSET_ERR_BUSY;
+		}
+		for (i = 0; i < ip_set_max; i++) {
+			if (ip_set_list[i] != NULL)
+				ip_set_destroy_set(i);
+		}
+	} else {
+		i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME]));
+		if (i == IPSET_INVALID_ID)
+			return -ENOENT;
+		else if (atomic_read(&ip_set_list[i]->ref))
+			return -IPSET_ERR_BUSY;
+
+		ip_set_destroy_set(i);
+	}
+	return 0;
+}
+
+/* Flush sets */
+
+static void
+ip_set_flush_set(struct ip_set *set)
+{
+	pr_debug("set: %s\n",  set->name);
+
+	write_lock_bh(&set->lock);
+	set->variant->flush(set);
+	write_unlock_bh(&set->lock);
+}
+
+static int
+ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
+	     const struct nlmsghdr *nlh,
+	     const struct nlattr * const attr[])
+{
+	ip_set_id_t i;
+
+	if (unlikely(protocol_failed(attr)))
+		return -EPROTO;
+
+	if (!attr[IPSET_ATTR_SETNAME]) {
+		for (i = 0; i < ip_set_max; i++)
+			if (ip_set_list[i] != NULL)
+				ip_set_flush_set(ip_set_list[i]);
+	} else {
+		i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME]));
+		if (i == IPSET_INVALID_ID)
+			return -ENOENT;
+
+		ip_set_flush_set(ip_set_list[i]);
+	}
+
+	return 0;
+}
+
+/* Rename a set */
+
+static const struct nla_policy
+ip_set_setname2_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_SETNAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+	[IPSET_ATTR_SETNAME2]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+};
+
+static int
+ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
+	      const struct nlmsghdr *nlh,
+	      const struct nlattr * const attr[])
+{
+	struct ip_set *set;
+	const char *name2;
+	ip_set_id_t i;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL ||
+		     attr[IPSET_ATTR_SETNAME2] == NULL))
+		return -IPSET_ERR_PROTOCOL;
+
+	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	if (set == NULL)
+		return -ENOENT;
+	if (atomic_read(&set->ref) != 0)
+		return -IPSET_ERR_REFERENCED;
+
+	name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
+	for (i = 0; i < ip_set_max; i++) {
+		if (ip_set_list[i] != NULL &&
+		    STREQ(ip_set_list[i]->name, name2))
+			return -IPSET_ERR_EXIST_SETNAME2;
+	}
+	strncpy(set->name, name2, IPSET_MAXNAMELEN);
+
+	return 0;
+}
+
+/* Swap two sets so that name/index points to the other.
+ * References and set names are also swapped.
+ *
+ * We are protected by the nfnl mutex and references are
+ * manipulated only by holding the mutex. The kernel interfaces
+ * do not hold the mutex but the pointer settings are atomic
+ * so the ip_set_list always contains valid pointers to the sets.
+ */
+
+static int
+ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
+	    const struct nlmsghdr *nlh,
+	    const struct nlattr * const attr[])
+{
+	struct ip_set *from, *to;
+	ip_set_id_t from_id, to_id;
+	char from_name[IPSET_MAXNAMELEN];
+	u32 from_ref;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL ||
+		     attr[IPSET_ATTR_SETNAME2] == NULL))
+		return -IPSET_ERR_PROTOCOL;
+
+	from_id = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME]));
+	if (from_id == IPSET_INVALID_ID)
+		return -ENOENT;
+
+	to_id = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME2]));
+	if (to_id == IPSET_INVALID_ID)
+		return -IPSET_ERR_EXIST_SETNAME2;
+
+	from = ip_set_list[from_id];
+	to = ip_set_list[to_id];
+
+	/* Features must not change.
+	 * Not an artifical restriction anymore, as we must prevent
+	 * possible loops created by swapping in setlist type of sets. */
+	if (!(from->type->features == to->type->features &&
+	      from->type->family == to->type->family))
+		return -IPSET_ERR_TYPE_MISMATCH;
+
+	/* No magic here: ref munging protected by the nfnl_lock */
+	strncpy(from_name, from->name, IPSET_MAXNAMELEN);
+	from_ref = atomic_read(&from->ref);
+
+	strncpy(from->name, to->name, IPSET_MAXNAMELEN);
+	atomic_set(&from->ref, atomic_read(&to->ref));
+	strncpy(to->name, from_name, IPSET_MAXNAMELEN);
+	atomic_set(&to->ref, from_ref);
+
+	ip_set_list[from_id] = to;
+	ip_set_list[to_id] = from;
+
+	return 0;
+}
+
+/* List/save set data */
+
+#define DUMP_INIT	0L
+#define DUMP_ALL	1L
+#define DUMP_ONE	2L
+#define DUMP_LAST	3L
+
+static int
+ip_set_dump_done(struct netlink_callback *cb)
+{
+	if (cb->args[2]) {
+		pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name);
+		__ip_set_put((ip_set_id_t) cb->args[1]);
+	}
+	return 0;
+}
+
+static inline void
+dump_attrs(struct nlmsghdr *nlh)
+{
+	const struct nlattr *attr;
+	int rem;
+
+	pr_debug("dump nlmsg\n");
+	nlmsg_for_each_attr(attr, nlh, sizeof(struct nfgenmsg), rem) {
+		pr_debug("type: %u, len %u\n", nla_type(attr), attr->nla_len);
+	}
+}
+
+static int
+dump_init(struct netlink_callback *cb)
+{
+	struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
+	int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+	struct nlattr *cda[IPSET_ATTR_CMD_MAX+1];
+	struct nlattr *attr = (void *)nlh + min_len;
+	ip_set_id_t index;
+
+	/* Second pass, so parser can't fail */
+	nla_parse(cda, IPSET_ATTR_CMD_MAX,
+		  attr, nlh->nlmsg_len - min_len, ip_set_setname_policy);
+
+	/* cb->args[0] : dump single set/all sets
+	 *         [1] : set index
+	 *         [..]: type specific
+	 */
+
+	if (!cda[IPSET_ATTR_SETNAME]) {
+		cb->args[0] = DUMP_ALL;
+		return 0;
+	}
+
+	index = find_set_id(nla_data(cda[IPSET_ATTR_SETNAME]));
+	if (index == IPSET_INVALID_ID)
+		return -ENOENT;
+
+	cb->args[0] = DUMP_ONE;
+	cb->args[1] = index;
+	return 0;
+}
+
+static int
+ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	ip_set_id_t index = IPSET_INVALID_ID, max;
+	struct ip_set *set = NULL;
+	struct nlmsghdr *nlh = NULL;
+	unsigned int flags = NETLINK_CB(cb->skb).pid ? NLM_F_MULTI : 0;
+	int ret = 0;
+
+	if (cb->args[0] == DUMP_INIT) {
+		ret = dump_init(cb);
+		if (ret < 0) {
+			nlh = nlmsg_hdr(cb->skb);
+			/* We have to create and send the error message
+			 * manually :-( */
+			if (nlh->nlmsg_flags & NLM_F_ACK)
+				netlink_ack(cb->skb, nlh, ret);
+			return ret;
+		}
+	}
+
+	if (cb->args[1] >= ip_set_max)
+		goto out;
+
+	pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]);
+	max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max;
+	for (; cb->args[1] < max; cb->args[1]++) {
+		index = (ip_set_id_t) cb->args[1];
+		set = ip_set_list[index];
+		if (set == NULL) {
+			if (cb->args[0] == DUMP_ONE) {
+				ret = -ENOENT;
+				goto out;
+			}
+			continue;
+		}
+		/* When dumping all sets, we must dump "sorted"
+		 * so that lists (unions of sets) are dumped last.
+		 */
+		if (cb->args[0] != DUMP_ONE &&
+		    !((cb->args[0] == DUMP_ALL) ^
+		      (set->type->features & IPSET_DUMP_LAST)))
+			continue;
+		pr_debug("List set: %s\n", set->name);
+		if (!cb->args[2]) {
+			/* Start listing: make sure set won't be destroyed */
+			pr_debug("reference set\n");
+			__ip_set_get(index);
+		}
+		nlh = start_msg(skb, NETLINK_CB(cb->skb).pid,
+				cb->nlh->nlmsg_seq, flags,
+				IPSET_CMD_LIST);
+		if (!nlh) {
+			ret = -EMSGSIZE;
+			goto release_refcount;
+		}
+		NLA_PUT_U8(skb, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL);
+		NLA_PUT_STRING(skb, IPSET_ATTR_SETNAME, set->name);
+		switch (cb->args[2]) {
+		case 0:
+			/* Core header data */
+			NLA_PUT_STRING(skb, IPSET_ATTR_TYPENAME,
+				       set->type->name);
+			NLA_PUT_U8(skb, IPSET_ATTR_FAMILY,
+				   set->family);
+			NLA_PUT_U8(skb, IPSET_ATTR_REVISION,
+				   set->type->revision);
+			ret = set->variant->head(set, skb);
+			if (ret < 0)
+				goto release_refcount;
+			/* Fall through and add elements */
+		default:
+			read_lock_bh(&set->lock);
+			ret = set->variant->list(set, skb, cb);
+			read_unlock_bh(&set->lock);
+			if (!cb->args[2]) {
+				/* Set is done, proceed with next one */
+				if (cb->args[0] == DUMP_ONE)
+					cb->args[1] = IPSET_INVALID_ID;
+				else
+					cb->args[1]++;
+			}
+			goto release_refcount;
+		}
+	}
+	goto out;
+
+nla_put_failure:
+	ret = -EFAULT;
+release_refcount:
+	/* If there was an error or set is done, release set */
+	if (ret || !cb->args[2]) {
+		pr_debug("release set %s\n", ip_set_list[index]->name);
+		__ip_set_put(index);
+	}
+
+	/* If we dump all sets, continue with dumping last ones */
+	if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2])
+		cb->args[0] = DUMP_LAST;
+
+out:
+	if (nlh) {
+		nlmsg_end(skb, nlh);
+		pr_debug("nlmsg_len: %u\n", nlh->nlmsg_len);
+		dump_attrs(nlh);
+	}
+
+	return ret < 0 ? ret : skb->len;
+}
+
+static int
+ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
+	    const struct nlmsghdr *nlh,
+	    const struct nlattr * const attr[])
+{
+	if (unlikely(protocol_failed(attr)))
+		return -IPSET_ERR_PROTOCOL;
+
+	return netlink_dump_start(ctnl, skb, nlh,
+				  ip_set_dump_start,
+				  ip_set_dump_done);
+}
+
+/* Add, del and test */
+
+static const struct nla_policy ip_set_adt_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_SETNAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+	[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+	[IPSET_ATTR_DATA]	= { .type = NLA_NESTED },
+	[IPSET_ATTR_ADT]	= { .type = NLA_NESTED },
+};
+
+static int
+call_ad(struct sk_buff *skb, struct ip_set *set,
+	struct nlattr *tb[], enum ipset_adt adt,
+	u32 flags, bool use_lineno)
+{
+	int ret, retried = 0;
+	u32 lineno = 0;
+	bool eexist = flags & IPSET_FLAG_EXIST;
+
+	do {
+		write_lock_bh(&set->lock);
+		ret = set->variant->uadt(set, tb, adt, &lineno, flags);
+		write_unlock_bh(&set->lock);
+	} while (ret == -EAGAIN &&
+		 set->variant->resize &&
+		 (ret = set->variant->resize(set, retried++)) == 0);
+
+	if (!ret || (ret == -IPSET_ERR_EXIST && eexist))
+		return 0;
+	if (lineno && use_lineno) {
+		/* Error in restore/batch mode: send back lineno */
+		struct nlmsghdr *nlh = nlmsg_hdr(skb);
+		int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+		struct nlattr *cda[IPSET_ATTR_CMD_MAX+1];
+		struct nlattr *cmdattr = (void *)nlh + min_len;
+		u32 *errline;
+
+		nla_parse(cda, IPSET_ATTR_CMD_MAX,
+			  cmdattr, nlh->nlmsg_len - min_len,
+			  ip_set_adt_policy);
+
+		errline = nla_data(cda[IPSET_ATTR_LINENO]);
+
+		*errline = lineno;
+	}
+
+	return ret;
+}
+
+static int
+ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
+	    const struct nlmsghdr *nlh,
+	    const struct nlattr * const attr[])
+{
+	struct ip_set *set;
+	struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
+	const struct nlattr *nla;
+	u32 flags = flag_exist(nlh);
+	bool use_lineno;
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL ||
+		     !((attr[IPSET_ATTR_DATA] != NULL) ^
+		       (attr[IPSET_ATTR_ADT] != NULL)) ||
+		     (attr[IPSET_ATTR_DATA] != NULL &&
+		      !flag_nested(attr[IPSET_ATTR_DATA])) ||
+		     (attr[IPSET_ATTR_ADT] != NULL &&
+		      (!flag_nested(attr[IPSET_ATTR_ADT]) ||
+		       attr[IPSET_ATTR_LINENO] == NULL))))
+		return -IPSET_ERR_PROTOCOL;
+
+	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	if (set == NULL)
+		return -ENOENT;
+
+	use_lineno = !!attr[IPSET_ATTR_LINENO];
+	if (attr[IPSET_ATTR_DATA]) {
+		if (nla_parse(tb, IPSET_ATTR_ADT_MAX,
+			      nla_data(attr[IPSET_ATTR_DATA]),
+			      nla_len(attr[IPSET_ATTR_DATA]),
+			      set->type->adt_policy))
+			return -IPSET_ERR_PROTOCOL;
+		ret = call_ad(skb, set, tb, IPSET_ADD, flags, use_lineno);
+	} else {
+		int nla_rem;
+
+		nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) {
+			memset(tb, 0, sizeof(tb));
+			if (nla_type(nla) != IPSET_ATTR_DATA ||
+			    !flag_nested(nla) ||
+			    nla_parse(tb, IPSET_ATTR_ADT_MAX,
+			    	      nla_data(nla), nla_len(nla),
+			    	      set->type->adt_policy))
+				return -IPSET_ERR_PROTOCOL;
+			ret = call_ad(skb, set, tb, IPSET_ADD,
+				      flags, use_lineno);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return ret;
+}
+
+static int
+ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
+	    const struct nlmsghdr *nlh,
+	    const struct nlattr * const attr[])
+{
+	struct ip_set *set;
+	struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
+	const struct nlattr *nla;
+	u32 flags = flag_exist(nlh);
+	bool use_lineno;
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL ||
+		     !((attr[IPSET_ATTR_DATA] != NULL) ^
+		       (attr[IPSET_ATTR_ADT] != NULL)) ||
+		     (attr[IPSET_ATTR_DATA] != NULL &&
+		      !flag_nested(attr[IPSET_ATTR_DATA])) ||
+		     (attr[IPSET_ATTR_ADT] != NULL &&
+		      (!flag_nested(attr[IPSET_ATTR_ADT]) ||
+		       attr[IPSET_ATTR_LINENO] == NULL))))
+		return -IPSET_ERR_PROTOCOL;
+
+	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	if (set == NULL)
+		return -ENOENT;
+
+	use_lineno = !!attr[IPSET_ATTR_LINENO];
+	if (attr[IPSET_ATTR_DATA]) {
+		if (nla_parse(tb, IPSET_ATTR_ADT_MAX,
+			      nla_data(attr[IPSET_ATTR_DATA]),
+			      nla_len(attr[IPSET_ATTR_DATA]),
+			      set->type->adt_policy))
+			return -IPSET_ERR_PROTOCOL;
+		ret = call_ad(skb, set, tb, IPSET_DEL, flags, use_lineno);
+	} else {
+		int nla_rem;
+
+		nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) {
+			memset(tb, 0, sizeof(*tb));
+			if (nla_type(nla) != IPSET_ATTR_DATA ||
+			    !flag_nested(nla) ||
+			    nla_parse(tb, IPSET_ATTR_ADT_MAX,
+			    	      nla_data(nla), nla_len(nla),
+			    	      set->type->adt_policy))
+				return -IPSET_ERR_PROTOCOL;
+			ret = call_ad(skb, set, tb, IPSET_DEL,
+				      flags, use_lineno);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return ret;
+}
+
+static int
+ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
+	     const struct nlmsghdr *nlh,
+	     const struct nlattr * const attr[])
+{
+	struct ip_set *set;
+	struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL ||
+		     attr[IPSET_ATTR_DATA] == NULL ||
+		     !flag_nested(attr[IPSET_ATTR_DATA])))
+		return -IPSET_ERR_PROTOCOL;
+
+	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	if (set == NULL)
+		return -ENOENT;
+
+	if (nla_parse(tb, IPSET_ATTR_ADT_MAX,
+		      nla_data(attr[IPSET_ATTR_DATA]),
+		      nla_len(attr[IPSET_ATTR_DATA]),
+		      set->type->adt_policy))
+		return -IPSET_ERR_PROTOCOL;
+
+	read_lock_bh(&set->lock);
+	ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0);
+	read_unlock_bh(&set->lock);
+	/* Userspace can't trigger element to be re-added */
+	if (ret == -EAGAIN)
+		ret = 1;
+
+	return ret < 0 ? ret : ret > 0 ? 0 : -IPSET_ERR_EXIST;
+}
+
+/* Get headed data of a set */
+
+static int
+ip_set_header(struct sock *ctnl, struct sk_buff *skb,
+	      const struct nlmsghdr *nlh,
+	      const struct nlattr * const attr[])
+{
+	const struct ip_set *set;
+	struct sk_buff *skb2;
+	struct nlmsghdr *nlh2;
+	ip_set_id_t index;
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_SETNAME] == NULL))
+		return -IPSET_ERR_PROTOCOL;
+
+	index = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME]));
+	if (index == IPSET_INVALID_ID)
+		return -ENOENT;
+	set = ip_set_list[index];
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		return -ENOMEM;
+
+	nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0,
+			 IPSET_CMD_HEADER);
+	if (!nlh2)
+		goto nlmsg_failure;
+	NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL);
+	NLA_PUT_STRING(skb2, IPSET_ATTR_SETNAME, set->name);
+	NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, set->type->name);
+	NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, set->family);
+	NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, set->type->revision);
+	nlmsg_end(skb2, nlh2);
+
+	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb2, nlh2);
+nlmsg_failure:
+	kfree_skb(skb2);
+	return -EMSGSIZE;
+}
+
+/* Get type data */
+
+static const struct nla_policy ip_set_type_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_TYPENAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+	[IPSET_ATTR_FAMILY]	= { .type = NLA_U8 },
+};
+
+static int
+ip_set_type(struct sock *ctnl, struct sk_buff *skb,
+	    const struct nlmsghdr *nlh,
+	    const struct nlattr * const attr[])
+{
+	struct sk_buff *skb2;
+	struct nlmsghdr *nlh2;
+	u8 family, min, max;
+	const char *typename;
+	int ret = 0;
+
+	if (unlikely(protocol_failed(attr) ||
+		     attr[IPSET_ATTR_TYPENAME] == NULL ||
+		     attr[IPSET_ATTR_FAMILY] == NULL))
+		return -IPSET_ERR_PROTOCOL;
+
+	family = nla_get_u8(attr[IPSET_ATTR_FAMILY]);
+	typename = nla_data(attr[IPSET_ATTR_TYPENAME]);
+	ret = find_set_type_minmax(typename, family, &min, &max);
+	if (ret)
+		return ret;
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		return -ENOMEM;
+
+	nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0,
+			 IPSET_CMD_TYPE);
+	if (!nlh2)
+		goto nlmsg_failure;
+	NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL);
+	NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, typename);
+	NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, family);
+	NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, max);
+	NLA_PUT_U8(skb2, IPSET_ATTR_REVISION_MIN, min);
+	nlmsg_end(skb2, nlh2);
+
+	pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len);
+	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb2, nlh2);
+nlmsg_failure:
+	kfree_skb(skb2);
+	return -EMSGSIZE;
+}
+
+/* Get protocol version */
+
+static const struct nla_policy
+ip_set_protocol_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+};
+
+static int
+ip_set_protocol(struct sock *ctnl, struct sk_buff *skb,
+		const struct nlmsghdr *nlh,
+		const struct nlattr * const attr[])
+{
+	struct sk_buff *skb2;
+	struct nlmsghdr *nlh2;
+	int ret = 0;
+
+	if (unlikely(attr[IPSET_ATTR_PROTOCOL] == NULL))
+		return -IPSET_ERR_PROTOCOL;
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		return -ENOMEM;
+
+	nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0,
+			 IPSET_CMD_PROTOCOL);
+	if (!nlh2)
+		goto nlmsg_failure;
+	NLA_PUT_U8(skb2, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL);
+	nlmsg_end(skb2, nlh2);
+
+	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb2, nlh2);
+nlmsg_failure:
+	kfree_skb(skb2);
+	return -EMSGSIZE;
+}
+
+static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = {
+	[IPSET_CMD_CREATE]	= {
+		.call		= ip_set_create,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_create_policy,
+	},
+	[IPSET_CMD_DESTROY]	= {
+		.call		= ip_set_destroy,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname_policy,
+	},
+	[IPSET_CMD_FLUSH]	= {
+		.call		= ip_set_flush,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname_policy,
+	},
+	[IPSET_CMD_RENAME]	= {
+		.call		= ip_set_rename,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname2_policy,
+	},
+	[IPSET_CMD_SWAP]	= {
+		.call		= ip_set_swap,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname2_policy,
+	},
+	[IPSET_CMD_LIST]	= {
+		.call		= ip_set_dump,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname_policy,
+	},
+	[IPSET_CMD_SAVE]	= {
+		.call		= ip_set_dump,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname_policy,
+	},
+	[IPSET_CMD_ADD]	= {
+		.call		= ip_set_uadd,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_adt_policy,
+	},
+	[IPSET_CMD_DEL]	= {
+		.call		= ip_set_udel,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_adt_policy,
+	},
+	[IPSET_CMD_TEST]	= {
+		.call		= ip_set_utest,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_adt_policy,
+	},
+	[IPSET_CMD_HEADER]	= {
+		.call		= ip_set_header,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_setname_policy,
+	},
+	[IPSET_CMD_TYPE]	= {
+		.call		= ip_set_type,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_type_policy,
+	},
+	[IPSET_CMD_PROTOCOL]	= {
+		.call		= ip_set_protocol,
+		.attr_count	= IPSET_ATTR_CMD_MAX,
+		.policy		= ip_set_protocol_policy,
+	},
+};
+
+static struct nfnetlink_subsystem ip_set_netlink_subsys __read_mostly = {
+	.name		= "ip_set",
+	.subsys_id	= NFNL_SUBSYS_IPSET,
+	.cb_count	= IPSET_MSG_MAX,
+	.cb		= ip_set_netlink_subsys_cb,
+};
+
+/* Interface to iptables/ip6tables */
+
+static int
+ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
+{
+	unsigned *op;
+	void *data;
+	int copylen = *len, ret = 0;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+	if (optval != SO_IP_SET)
+		return -EBADF;
+	if (*len < sizeof(unsigned))
+		return -EINVAL;
+
+	data = vmalloc(*len);
+	if (!data)
+		return -ENOMEM;
+	if (copy_from_user(data, user, *len) != 0) {
+		ret = -EFAULT;
+		goto done;
+	}
+	op = (unsigned *) data;
+
+	if (*op < IP_SET_OP_VERSION) {
+		/* Check the version at the beginning of operations */
+		struct ip_set_req_version *req_version = data;
+		if (req_version->version != IPSET_PROTOCOL) {
+			ret = -EPROTO;
+			goto done;
+		}
+	}
+
+	switch (*op) {
+	case IP_SET_OP_VERSION: {
+		struct ip_set_req_version *req_version = data;
+
+		if (*len != sizeof(struct ip_set_req_version)) {
+			ret = -EINVAL;
+			goto done;
+		}
+
+		req_version->version = IPSET_PROTOCOL;
+		ret = copy_to_user(user, req_version,
+				   sizeof(struct ip_set_req_version));
+		goto done;
+	}
+	case IP_SET_OP_GET_BYNAME: {
+		struct ip_set_req_get_set *req_get = data;
+
+		if (*len != sizeof(struct ip_set_req_get_set)) {
+			ret = -EINVAL;
+			goto done;
+		}
+		req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
+		nfnl_lock();
+		req_get->set.index = find_set_id(req_get->set.name);
+		nfnl_unlock();
+		goto copy;
+	}
+	case IP_SET_OP_GET_BYINDEX: {
+		struct ip_set_req_get_set *req_get = data;
+
+		if (*len != sizeof(struct ip_set_req_get_set) ||
+		    req_get->set.index >= ip_set_max) {
+			ret = -EINVAL;
+			goto done;
+		}
+		nfnl_lock();
+		strncpy(req_get->set.name,
+			ip_set_list[req_get->set.index]
+				? ip_set_list[req_get->set.index]->name : "",
+			IPSET_MAXNAMELEN);
+		nfnl_unlock();
+		goto copy;
+	}
+	default:
+		ret = -EBADMSG;
+		goto done;
+	}	/* end of switch(op) */
+
+copy:
+	ret = copy_to_user(user, data, copylen);
+
+done:
+	vfree(data);
+	if (ret > 0)
+		ret = 0;
+	return ret;
+}
+
+static struct nf_sockopt_ops so_set __read_mostly = {
+	.pf		= PF_INET,
+	.get_optmin	= SO_IP_SET,
+	.get_optmax	= SO_IP_SET + 1,
+	.get		= &ip_set_sockfn_get,
+	.owner		= THIS_MODULE,
+};
+
+static int __init
+ip_set_init(void)
+{
+	int ret;
+
+	if (max_sets)
+		ip_set_max = max_sets;
+	if (ip_set_max >= IPSET_INVALID_ID)
+		ip_set_max = IPSET_INVALID_ID - 1;
+
+	ip_set_list = kzalloc(sizeof(struct ip_set *) * ip_set_max,
+			      GFP_KERNEL);
+	if (!ip_set_list) {
+		pr_err("ip_set: Unable to create ip_set_list\n");
+		return -ENOMEM;
+	}
+
+	ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+	if (ret != 0) {
+		pr_err("ip_set: cannot register with nfnetlink.\n");
+		kfree(ip_set_list);
+		return ret;
+	}
+	ret = nf_register_sockopt(&so_set);
+	if (ret != 0) {
+		pr_err("SO_SET registry failed: %d\n", ret);
+		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+		kfree(ip_set_list);
+		return ret;
+	}
+
+	pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
+	return 0;
+}
+
+static void __exit
+ip_set_fini(void)
+{
+	/* There can't be any existing set */
+	nf_unregister_sockopt(&so_set);
+	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+	kfree(ip_set_list);
+	pr_debug("these are the famous last words\n");
+}
+
+module_init(ip_set_init);
+module_exit(ip_set_fini);
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
new file mode 100644
index 000000000000..76737bba28ee
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -0,0 +1,136 @@
+/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Get Layer-4 data from the packets */
+
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <net/ip.h>
+
+#include <linux/netfilter/ipset/ip_set_getport.h>
+
+/* We must handle non-linear skbs */
+static bool
+get_port(const struct sk_buff *skb, int protocol, unsigned int protooff,
+	 bool src, __be16 *port, u8 *proto)
+{
+	switch (protocol) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph;
+		const struct tcphdr *th;
+
+		th = skb_header_pointer(skb, protooff, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			/* No choice either */
+			return false;
+
+		*port = src ? th->source : th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr _udph;
+		const struct udphdr *uh;
+
+		uh = skb_header_pointer(skb, protooff, sizeof(_udph), &_udph);
+		if (uh == NULL)
+			/* No choice either */
+			return false;
+
+		*port = src ? uh->source : uh->dest;
+		break;
+	}
+	case IPPROTO_ICMP: {
+		struct icmphdr _ich;
+		const struct icmphdr *ic;
+
+		ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich);
+		if (ic == NULL)
+			return false;
+
+		*port = (__force __be16)htons((ic->type << 8) | ic->code);
+		break;
+	}
+	case IPPROTO_ICMPV6: {
+		struct icmp6hdr _ich;
+		const struct icmp6hdr *ic;
+
+		ic = skb_header_pointer(skb, protooff, sizeof(_ich), &_ich);
+		if (ic == NULL)
+			return false;
+
+		*port = (__force __be16)
+			htons((ic->icmp6_type << 8) | ic->icmp6_code);
+		break;
+	}
+	default:
+		break;
+	}
+	*proto = protocol;
+
+	return true;
+}
+
+bool
+ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
+		    __be16 *port, u8 *proto)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	unsigned int protooff = ip_hdrlen(skb);
+	int protocol = iph->protocol;
+
+	/* See comments at tcp_match in ip_tables.c */
+	if (protocol <= 0 || (ntohs(iph->frag_off) & IP_OFFSET))
+		return false;
+
+	return get_port(skb, protocol, protooff, src, port, proto);
+}
+EXPORT_SYMBOL_GPL(ip_set_get_ip4_port);
+
+bool
+ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
+		    __be16 *port, u8 *proto)
+{
+	unsigned int protooff = 0;
+	int protocol;
+	unsigned short fragoff;
+
+	protocol = ipv6_find_hdr(skb, &protooff, -1, &fragoff);
+	if (protocol <= 0 || fragoff)
+		return false;
+
+	return get_port(skb, protocol, protooff, src, port, proto);
+}
+EXPORT_SYMBOL_GPL(ip_set_get_ip6_port);
+
+bool
+ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port)
+{
+	bool ret;
+	u8 proto;
+
+	switch (pf) {
+	case AF_INET:
+		ret = ip_set_get_ip4_port(skb, src, port, &proto);
+	case AF_INET6:
+		ret = ip_set_get_ip6_port(skb, src, port, &proto);
+	default:
+		return false;
+	}
+	if (!ret)
+		return ret;
+	switch (proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		return true;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(ip_set_get_ip_port);
diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c
new file mode 100644
index 000000000000..23f8c8162214
--- /dev/null
+++ b/net/netfilter/ipset/pfxlen.c
@@ -0,0 +1,291 @@
+#include <linux/netfilter/ipset/pfxlen.h>
+
+/*
+ * Prefixlen maps for fast conversions, by Jan Engelhardt.
+ */
+
+#define E(a, b, c, d) \
+	{.ip6 = { \
+		__constant_htonl(a), __constant_htonl(b), \
+		__constant_htonl(c), __constant_htonl(d), \
+	} }
+
+/*
+ * This table works for both IPv4 and IPv6;
+ * just use prefixlen_netmask_map[prefixlength].ip.
+ */
+const union nf_inet_addr ip_set_netmask_map[] = {
+	E(0x00000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0x80000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xC0000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xE0000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xF0000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xF8000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFC000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFE000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFF000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFF800000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF),
+};
+EXPORT_SYMBOL_GPL(ip_set_netmask_map);
+
+#undef  E
+#define E(a, b, c, d) 						\
+	{.ip6 = { (__force __be32) a, (__force __be32) b,	\
+		  (__force __be32) c, (__force __be32) d,	\
+	} }
+
+/*
+ * This table works for both IPv4 and IPv6;
+ * just use prefixlen_hostmask_map[prefixlength].ip.
+ */
+const union nf_inet_addr ip_set_hostmask_map[] = {
+	E(0x00000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0x80000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xC0000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xE0000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xF0000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xF8000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFC000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFE000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFF000000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFF800000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE),
+	E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF),
+};
+EXPORT_SYMBOL_GPL(ip_set_hostmask_map);
-- 
cgit v1.2.3


From 72205fc68bd13109576aa6c4c12c740962d28a6c Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 1 Feb 2011 15:33:17 +0100
Subject: netfilter: ipset: bitmap:ip set type support

The module implements the bitmap:ip set type in two flavours, without
and with timeout support. In this kind of set one can store IPv4
addresses (or network addresses) from a given range.

In order not to waste memory, the timeout version does not rely on
the kernel timer for every element to be timed out but on garbage
collection. All set types use this mechanism.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/ipset/ip_set_bitmap.h  |  31 ++
 include/linux/netfilter/ipset/ip_set_timeout.h | 127 ++++++
 net/netfilter/ipset/Kconfig                    |   9 +
 net/netfilter/ipset/Makefile                   |   3 +
 net/netfilter/ipset/ip_set_bitmap_ip.c         | 588 +++++++++++++++++++++++++
 5 files changed, 758 insertions(+)
 create mode 100644 include/linux/netfilter/ipset/ip_set_bitmap.h
 create mode 100644 include/linux/netfilter/ipset/ip_set_timeout.h
 create mode 100644 net/netfilter/ipset/ip_set_bitmap_ip.c

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h
new file mode 100644
index 000000000000..61a9e8746c83
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_bitmap.h
@@ -0,0 +1,31 @@
+#ifndef __IP_SET_BITMAP_H
+#define __IP_SET_BITMAP_H
+
+/* Bitmap type specific error codes */
+enum {
+	/* The element is out of the range of the set */
+	IPSET_ERR_BITMAP_RANGE = IPSET_ERR_TYPE_SPECIFIC,
+	/* The range exceeds the size limit of the set type */
+	IPSET_ERR_BITMAP_RANGE_SIZE,
+};
+
+#ifdef __KERNEL__
+#define IPSET_BITMAP_MAX_RANGE	0x0000FFFF
+
+/* Common functions */
+
+static inline u32
+range_to_mask(u32 from, u32 to, u8 *bits)
+{
+	u32 mask = 0xFFFFFFFE;
+
+	*bits = 32;
+	while (--(*bits) > 0 && mask && (to & mask) != from)
+		mask <<= 1;
+
+	return mask;
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* __IP_SET_BITMAP_H */
diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h
new file mode 100644
index 000000000000..9f30c5f2ec1c
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_timeout.h
@@ -0,0 +1,127 @@
+#ifndef _IP_SET_TIMEOUT_H
+#define _IP_SET_TIMEOUT_H
+
+/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifdef __KERNEL__
+
+/* How often should the gc be run by default */
+#define IPSET_GC_TIME			(3 * 60)
+
+/* Timeout period depending on the timeout value of the given set */
+#define IPSET_GC_PERIOD(timeout) \
+	((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1)
+
+/* Set is defined without timeout support: timeout value may be 0 */
+#define IPSET_NO_TIMEOUT	UINT_MAX
+
+#define with_timeout(timeout)	((timeout) != IPSET_NO_TIMEOUT)
+
+static inline unsigned int
+ip_set_timeout_uget(struct nlattr *tb)
+{
+	unsigned int timeout = ip_set_get_h32(tb);
+
+	/* Userspace supplied TIMEOUT parameter: adjust crazy size */
+	return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout;
+}
+
+#ifdef IP_SET_BITMAP_TIMEOUT
+
+/* Bitmap specific timeout constants and macros for the entries */
+
+/* Bitmap entry is unset */
+#define IPSET_ELEM_UNSET	0
+/* Bitmap entry is set with no timeout value */
+#define IPSET_ELEM_PERMANENT	(UINT_MAX/2)
+
+static inline bool
+ip_set_timeout_test(unsigned long timeout)
+{
+	return timeout != IPSET_ELEM_UNSET &&
+	       (timeout == IPSET_ELEM_PERMANENT ||
+		time_after(timeout, jiffies));
+}
+
+static inline bool
+ip_set_timeout_expired(unsigned long timeout)
+{
+	return timeout != IPSET_ELEM_UNSET &&
+	       timeout != IPSET_ELEM_PERMANENT &&
+	       time_before(timeout, jiffies);
+}
+
+static inline unsigned long
+ip_set_timeout_set(u32 timeout)
+{
+	unsigned long t;
+
+	if (!timeout)
+		return IPSET_ELEM_PERMANENT;
+
+	t = timeout * HZ + jiffies;
+	if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT)
+		/* Bingo! */
+		t++;
+
+	return t;
+}
+
+static inline u32
+ip_set_timeout_get(unsigned long timeout)
+{
+	return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ;
+}
+
+#else
+
+/* Hash specific timeout constants and macros for the entries */
+
+/* Hash entry is set with no timeout value */
+#define IPSET_ELEM_PERMANENT	0
+
+static inline bool
+ip_set_timeout_test(unsigned long timeout)
+{
+	return timeout == IPSET_ELEM_PERMANENT ||
+	       time_after(timeout, jiffies);
+}
+
+static inline bool
+ip_set_timeout_expired(unsigned long timeout)
+{
+	return timeout != IPSET_ELEM_PERMANENT &&
+	       time_before(timeout, jiffies);
+}
+
+static inline unsigned long
+ip_set_timeout_set(u32 timeout)
+{
+	unsigned long t;
+
+	if (!timeout)
+		return IPSET_ELEM_PERMANENT;
+
+	t = timeout * HZ + jiffies;
+	if (t == IPSET_ELEM_PERMANENT)
+		/* Bingo! :-) */
+		t++;
+
+	return t;
+}
+
+static inline u32
+ip_set_timeout_get(unsigned long timeout)
+{
+	return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ;
+}
+#endif /* ! IP_SET_BITMAP_TIMEOUT */
+
+#endif	/* __KERNEL__ */
+
+#endif /* _IP_SET_TIMEOUT_H */
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index 5ade156dd470..b63a8eea183c 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -23,4 +23,13 @@ config IP_SET_MAX
 	  The value can be overriden by the 'max_sets' module
 	  parameter of the 'ip_set' module.
 
+config IP_SET_BITMAP_IP
+	tristate "bitmap:ip set support"
+	depends on IP_SET
+	help
+	  This option adds the bitmap:ip set type support, by which one
+	  can store IPv4 addresses (or network addresse) from a range.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 endif # IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 910cd425c067..ea1c85e28af1 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -6,3 +6,6 @@ ip_set-y := ip_set_core.o ip_set_getport.o pfxlen.o
 
 # ipset core
 obj-$(CONFIG_IP_SET) += ip_set.o
+
+# bitmap types
+obj-$(CONFIG_IP_SET_BITMAP_IP) += ip_set_bitmap_ip.o
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
new file mode 100644
index 000000000000..047440085509
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -0,0 +1,588 @@
+/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
+ *                         Patrick Schaaf <bof@bof.de>
+ * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the bitmap:ip type */
+
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/uaccess.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/netlink.h>
+#include <linux/jiffies.h>
+#include <linux/timer.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_bitmap.h>
+#define IP_SET_BITMAP_TIMEOUT
+#include <linux/netfilter/ipset/ip_set_timeout.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
+MODULE_DESCRIPTION("bitmap:ip type of IP sets");
+MODULE_ALIAS("ip_set_bitmap:ip");
+
+/* Type structure */
+struct bitmap_ip {
+	void *members;		/* the set members */
+	u32 first_ip;		/* host byte order, included in range */
+	u32 last_ip;		/* host byte order, included in range */
+	u32 elements;		/* number of max elements in the set */
+	u32 hosts;		/* number of hosts in a subnet */
+	size_t memsize;		/* members size */
+	u8 netmask;		/* subnet netmask */
+	u32 timeout;		/* timeout parameter */
+	struct timer_list gc;	/* garbage collection */
+};
+
+/* Base variant */
+
+static inline u32
+ip_to_id(const struct bitmap_ip *m, u32 ip)
+{
+	return ((ip & ip_set_hostmask(m->netmask)) - m->first_ip)/m->hosts;
+}
+
+static int
+bitmap_ip_test(struct ip_set *set, void *value, u32 timeout)
+{
+	const struct bitmap_ip *map = set->data;
+	u16 id = *(u16 *)value;
+
+	return !!test_bit(id, map->members);
+}
+
+static int
+bitmap_ip_add(struct ip_set *set, void *value, u32 timeout)
+{
+	struct bitmap_ip *map = set->data;
+	u16 id = *(u16 *)value;
+
+	if (test_and_set_bit(id, map->members))
+		return -IPSET_ERR_EXIST;
+
+	return 0;
+}
+
+static int
+bitmap_ip_del(struct ip_set *set, void *value, u32 timeout)
+{
+	struct bitmap_ip *map = set->data;
+	u16 id = *(u16 *)value;
+
+	if (!test_and_clear_bit(id, map->members))
+		return -IPSET_ERR_EXIST;
+
+	return 0;
+}
+
+static int
+bitmap_ip_list(const struct ip_set *set,
+	       struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct bitmap_ip *map = set->data;
+	struct nlattr *atd, *nested;
+	u32 id, first = cb->args[2];
+
+	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	if (!atd)
+		return -EMSGSIZE;
+	for (; cb->args[2] < map->elements; cb->args[2]++) {
+		id = cb->args[2];
+		if (!test_bit(id, map->members))
+			continue;
+		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+		if (!nested) {
+			if (id == first) {
+				nla_nest_cancel(skb, atd);
+				return -EMSGSIZE;
+			} else
+				goto nla_put_failure;
+		}
+		NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP,
+				htonl(map->first_ip + id * map->hosts));
+		ipset_nest_end(skb, nested);
+	}
+	ipset_nest_end(skb, atd);
+	/* Set listing finished */
+	cb->args[2] = 0;
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nested);
+	ipset_nest_end(skb, atd);
+	if (unlikely(id == first)) {
+		cb->args[2] = 0;
+		return -EMSGSIZE;
+	}
+	return 0;
+}
+
+/* Timeout variant */
+
+static int
+bitmap_ip_ttest(struct ip_set *set, void *value, u32 timeout)
+{
+	const struct bitmap_ip *map = set->data;
+	const unsigned long *members = map->members;
+	u16 id = *(u16 *)value;
+
+	return ip_set_timeout_test(members[id]);
+}
+
+static int
+bitmap_ip_tadd(struct ip_set *set, void *value, u32 timeout)
+{
+	struct bitmap_ip *map = set->data;
+	unsigned long *members = map->members;
+	u16 id = *(u16 *)value;
+
+	if (ip_set_timeout_test(members[id]))
+		return -IPSET_ERR_EXIST;
+
+	members[id] = ip_set_timeout_set(timeout);
+
+	return 0;
+}
+
+static int
+bitmap_ip_tdel(struct ip_set *set, void *value, u32 timeout)
+{
+	struct bitmap_ip *map = set->data;
+	unsigned long *members = map->members;
+	u16 id = *(u16 *)value;
+	int ret = -IPSET_ERR_EXIST;
+
+	if (ip_set_timeout_test(members[id]))
+		ret = 0;
+
+	members[id] = IPSET_ELEM_UNSET;
+	return ret;
+}
+
+static int
+bitmap_ip_tlist(const struct ip_set *set,
+		struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct bitmap_ip *map = set->data;
+	struct nlattr *adt, *nested;
+	u32 id, first = cb->args[2];
+	const unsigned long *members = map->members;
+
+	adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	if (!adt)
+		return -EMSGSIZE;
+	for (; cb->args[2] < map->elements; cb->args[2]++) {
+		id = cb->args[2];
+		if (!ip_set_timeout_test(members[id]))
+			continue;
+		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+		if (!nested) {
+			if (id == first) {
+				nla_nest_cancel(skb, adt);
+				return -EMSGSIZE;
+			} else
+				goto nla_put_failure;
+		}
+		NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP,
+				htonl(map->first_ip + id * map->hosts));
+		NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT,
+			      htonl(ip_set_timeout_get(members[id])));
+		ipset_nest_end(skb, nested);
+	}
+	ipset_nest_end(skb, adt);
+
+	/* Set listing finished */
+	cb->args[2] = 0;
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nested);
+	ipset_nest_end(skb, adt);
+	if (unlikely(id == first)) {
+		cb->args[2] = 0;
+		return -EMSGSIZE;
+	}
+	return 0;
+}
+
+static int
+bitmap_ip_kadt(struct ip_set *set, const struct sk_buff *skb,
+	       enum ipset_adt adt, u8 pf, u8 dim, u8 flags)
+{
+	struct bitmap_ip *map = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	u32 ip;
+
+	ip = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC));
+	if (ip < map->first_ip || ip > map->last_ip)
+		return -IPSET_ERR_BITMAP_RANGE;
+
+	ip = ip_to_id(map, ip);
+
+	return adtfn(set, &ip, map->timeout);
+}
+
+static int
+bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[],
+	       enum ipset_adt adt, u32 *lineno, u32 flags)
+{
+	struct bitmap_ip *map = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	u32 timeout = map->timeout;
+	u32 ip, ip_to, id;
+	int ret = 0;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+	if (ret)
+		return ret;
+
+	if (ip < map->first_ip || ip > map->last_ip)
+		return -IPSET_ERR_BITMAP_RANGE;
+
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		if (!with_timeout(map->timeout))
+			return -IPSET_ERR_TIMEOUT;
+		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+	}
+
+	if (adt == IPSET_TEST) {
+		id = ip_to_id(map, ip);
+		return adtfn(set, &id, timeout);
+	}
+
+	if (tb[IPSET_ATTR_IP_TO]) {
+		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+		if (ret)
+			return ret;
+		if (ip > ip_to) {
+			swap(ip, ip_to);
+			if (ip < map->first_ip)
+				return -IPSET_ERR_BITMAP_RANGE;
+		}
+	} else if (tb[IPSET_ATTR_CIDR]) {
+		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+		if (cidr > 32)
+			return -IPSET_ERR_INVALID_CIDR;
+		ip &= ip_set_hostmask(cidr);
+		ip_to = ip | ~ip_set_hostmask(cidr);
+	} else
+		ip_to = ip;
+
+	if (ip_to > map->last_ip)
+		return -IPSET_ERR_BITMAP_RANGE;
+
+	for (; !before(ip_to, ip); ip += map->hosts) {
+		id = ip_to_id(map, ip);
+		ret = adtfn(set, &id, timeout);;
+
+		if (ret && !ip_set_eexist(ret, flags))
+			return ret;
+		else
+			ret = 0;
+	}
+	return ret;
+}
+
+static void
+bitmap_ip_destroy(struct ip_set *set)
+{
+	struct bitmap_ip *map = set->data;
+
+	if (with_timeout(map->timeout))
+		del_timer_sync(&map->gc);
+
+	ip_set_free(map->members);
+	kfree(map);
+
+	set->data = NULL;
+}
+
+static void
+bitmap_ip_flush(struct ip_set *set)
+{
+	struct bitmap_ip *map = set->data;
+
+	memset(map->members, 0, map->memsize);
+}
+
+static int
+bitmap_ip_head(struct ip_set *set, struct sk_buff *skb)
+{
+	const struct bitmap_ip *map = set->data;
+	struct nlattr *nested;
+
+	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+	if (!nested)
+		goto nla_put_failure;
+	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip));
+	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip));
+	if (map->netmask != 32)
+		NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask);
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
+		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
+		      htonl(sizeof(*map) + map->memsize));
+	if (with_timeout(map->timeout))
+		NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout));
+	ipset_nest_end(skb, nested);
+
+	return 0;
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static bool
+bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
+{
+	const struct bitmap_ip *x = a->data;
+	const struct bitmap_ip *y = b->data;
+
+	return x->first_ip == y->first_ip &&
+	       x->last_ip == y->last_ip &&
+	       x->netmask == y->netmask &&
+	       x->timeout == y->timeout;
+}
+
+static const struct ip_set_type_variant bitmap_ip = {
+	.kadt	= bitmap_ip_kadt,
+	.uadt	= bitmap_ip_uadt,
+	.adt	= {
+		[IPSET_ADD] = bitmap_ip_add,
+		[IPSET_DEL] = bitmap_ip_del,
+		[IPSET_TEST] = bitmap_ip_test,
+	},
+	.destroy = bitmap_ip_destroy,
+	.flush	= bitmap_ip_flush,
+	.head	= bitmap_ip_head,
+	.list	= bitmap_ip_list,
+	.same_set = bitmap_ip_same_set,
+};
+
+static const struct ip_set_type_variant bitmap_tip = {
+	.kadt	= bitmap_ip_kadt,
+	.uadt	= bitmap_ip_uadt,
+	.adt	= {
+		[IPSET_ADD] = bitmap_ip_tadd,
+		[IPSET_DEL] = bitmap_ip_tdel,
+		[IPSET_TEST] = bitmap_ip_ttest,
+	},
+	.destroy = bitmap_ip_destroy,
+	.flush	= bitmap_ip_flush,
+	.head	= bitmap_ip_head,
+	.list	= bitmap_ip_tlist,
+	.same_set = bitmap_ip_same_set,
+};
+
+static void
+bitmap_ip_gc(unsigned long ul_set)
+{
+	struct ip_set *set = (struct ip_set *) ul_set;
+	struct bitmap_ip *map = set->data;
+	unsigned long *table = map->members;
+	u32 id;
+
+	/* We run parallel with other readers (test element)
+	 * but adding/deleting new entries is locked out */
+	read_lock_bh(&set->lock);
+	for (id = 0; id < map->elements; id++)
+		if (ip_set_timeout_expired(table[id]))
+			table[id] = IPSET_ELEM_UNSET;
+	read_unlock_bh(&set->lock);
+
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	add_timer(&map->gc);
+}
+
+static void
+bitmap_ip_gc_init(struct ip_set *set)
+{
+	struct bitmap_ip *map = set->data;
+
+	init_timer(&map->gc);
+	map->gc.data = (unsigned long) set;
+	map->gc.function = bitmap_ip_gc;
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	add_timer(&map->gc);
+}
+
+/* Create bitmap:ip type of sets */
+
+static bool
+init_map_ip(struct ip_set *set, struct bitmap_ip *map,
+	    u32 first_ip, u32 last_ip,
+	    u32 elements, u32 hosts, u8 netmask)
+{
+	map->members = ip_set_alloc(map->memsize);
+	if (!map->members)
+		return false;
+	map->first_ip = first_ip;
+	map->last_ip = last_ip;
+	map->elements = elements;
+	map->hosts = hosts;
+	map->netmask = netmask;
+	map->timeout = IPSET_NO_TIMEOUT;
+
+	set->data = map;
+	set->family = AF_INET;
+
+	return true;
+}
+
+static int
+bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+{
+	struct bitmap_ip *map;
+	u32 first_ip, last_ip, hosts, elements;
+	u8 netmask = 32;
+	int ret;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+		return -IPSET_ERR_PROTOCOL;
+
+	ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &first_ip);
+	if (ret)
+		return ret;
+
+	if (tb[IPSET_ATTR_IP_TO]) {
+		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &last_ip);
+		if (ret)
+			return ret;
+		if (first_ip > last_ip) {
+			u32 tmp = first_ip;
+
+			first_ip = last_ip;
+			last_ip = tmp;
+		}
+	} else if (tb[IPSET_ATTR_CIDR]) {
+		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+		if (cidr >= 32)
+			return -IPSET_ERR_INVALID_CIDR;
+		last_ip = first_ip | ~ip_set_hostmask(cidr);
+	} else
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_NETMASK]) {
+		netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]);
+
+		if (netmask > 32)
+			return -IPSET_ERR_INVALID_NETMASK;
+
+		first_ip &= ip_set_hostmask(netmask);
+		last_ip |= ~ip_set_hostmask(netmask);
+	}
+
+	if (netmask == 32) {
+		hosts = 1;
+		elements = last_ip - first_ip + 1;
+	} else {
+		u8 mask_bits;
+		u32 mask;
+
+		mask = range_to_mask(first_ip, last_ip, &mask_bits);
+
+		if ((!mask && (first_ip || last_ip != 0xFFFFFFFF)) ||
+		    netmask <= mask_bits)
+			return -IPSET_ERR_BITMAP_RANGE;
+
+		pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask);
+		hosts = 2 << (32 - netmask - 1);
+		elements = 2 << (netmask - mask_bits - 1);
+	}
+	if (elements > IPSET_BITMAP_MAX_RANGE + 1)
+		return -IPSET_ERR_BITMAP_RANGE_SIZE;
+
+	pr_debug("hosts %u, elements %u\n", hosts, elements);
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		map->memsize = elements * sizeof(unsigned long);
+
+		if (!init_map_ip(set, map, first_ip, last_ip,
+				 elements, hosts, netmask)) {
+			kfree(map);
+			return -ENOMEM;
+		}
+
+		map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+		set->variant = &bitmap_tip;
+
+		bitmap_ip_gc_init(set);
+	} else {
+		map->memsize = bitmap_bytes(0, elements - 1);
+
+		if (!init_map_ip(set, map, first_ip, last_ip,
+				 elements, hosts, netmask)) {
+			kfree(map);
+			return -ENOMEM;
+		}
+
+		set->variant = &bitmap_ip;
+	}
+	return 0;
+}
+
+static struct ip_set_type bitmap_ip_type __read_mostly = {
+	.name		= "bitmap:ip",
+	.protocol	= IPSET_PROTOCOL,
+	.features	= IPSET_TYPE_IP,
+	.dimension	= IPSET_DIM_ONE,
+	.family		= AF_INET,
+	.revision	= 0,
+	.create		= bitmap_ip_create,
+	.create_policy	= {
+		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
+		[IPSET_ATTR_IP_TO]	= { .type = NLA_NESTED },
+		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
+		[IPSET_ATTR_NETMASK]	= { .type = NLA_U8  },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+	},
+	.adt_policy	= {
+		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
+		[IPSET_ATTR_IP_TO]	= { .type = NLA_NESTED },
+		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init
+bitmap_ip_init(void)
+{
+	return ip_set_type_register(&bitmap_ip_type);
+}
+
+static void __exit
+bitmap_ip_fini(void)
+{
+	ip_set_type_unregister(&bitmap_ip_type);
+}
+
+module_init(bitmap_ip_init);
+module_exit(bitmap_ip_fini);
-- 
cgit v1.2.3


From 6c027889696a7a694b0e2f6e3cabadefec7553b6 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 1 Feb 2011 15:38:36 +0100
Subject: netfilter: ipset: hash:ip set type support

The module implements the hash:ip type support in four flavours:
for IPv4 or IPv6, both without and with timeout support.

All the hash types are based on the "array hash" or ahash structure
and functions as a good compromise between minimal memory footprint
and speed. The hashing uses arrays to resolve clashes. The hash table
is resized (doubled) when searching becomes too long. Resizing can be
triggered by userspace add commands only and those are serialized by
the nfnl mutex. During resizing the set is read-locked, so the only
possible concurrent operations are the kernel side readers. Those are
protected by RCU locking.

Because of the four flavours and the other hash types, the functions
are implemented in general forms in the ip_set_ahash.h header file
and the real functions are generated before compiling by macro expansion.
Thus the dereferencing of low-level functions and void pointer arguments
could be avoided: the low-level functions are inlined, the function
arguments are pointers of type-specific structures.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/ipset/ip_set_ahash.h | 1074 ++++++++++++++++++++++++++
 include/linux/netfilter/ipset/ip_set_hash.h  |   26 +
 net/netfilter/ipset/Kconfig                  |   10 +
 net/netfilter/ipset/Makefile                 |    3 +
 net/netfilter/ipset/ip_set_hash_ip.c         |  467 +++++++++++
 5 files changed, 1580 insertions(+)
 create mode 100644 include/linux/netfilter/ipset/ip_set_ahash.h
 create mode 100644 include/linux/netfilter/ipset/ip_set_hash.h
 create mode 100644 net/netfilter/ipset/ip_set_hash_ip.c

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
new file mode 100644
index 000000000000..ec9d9bea1e37
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -0,0 +1,1074 @@
+#ifndef _IP_SET_AHASH_H
+#define _IP_SET_AHASH_H
+
+#include <linux/rcupdate.h>
+#include <linux/jhash.h>
+#include <linux/netfilter/ipset/ip_set_timeout.h>
+
+/* Hashing which uses arrays to resolve clashing. The hash table is resized
+ * (doubled) when searching becomes too long.
+ * Internally jhash is used with the assumption that the size of the
+ * stored data is a multiple of sizeof(u32). If storage supports timeout,
+ * the timeout field must be the last one in the data structure - that field
+ * is ignored when computing the hash key.
+ *
+ * Readers and resizing
+ *
+ * Resizing can be triggered by userspace command only, and those
+ * are serialized by the nfnl mutex. During resizing the set is
+ * read-locked, so the only possible concurrent operations are
+ * the kernel side readers. Those must be protected by proper RCU locking.
+ */
+
+/* Number of elements to store in an initial array block */
+#define AHASH_INIT_SIZE			4
+/* Max number of elements to store in an array block */
+#define AHASH_MAX_SIZE			(3*4)
+
+/* A hash bucket */
+struct hbucket {
+	void *value;		/* the array of the values */
+	u8 size;		/* size of the array */
+	u8 pos;			/* position of the first free entry */
+};
+
+/* The hash table: the table size stored here in order to make resizing easy */
+struct htable {
+	u8 htable_bits;		/* size of hash table == 2^htable_bits */
+	struct hbucket bucket[0]; /* hashtable buckets */
+};
+
+#define hbucket(h, i)		&((h)->bucket[i])
+
+/* Book-keeping of the prefixes added to the set */
+struct ip_set_hash_nets {
+	u8 cidr;		/* the different cidr values in the set */
+	u32 nets;		/* number of elements per cidr */
+};
+
+/* The generic ip_set hash structure */
+struct ip_set_hash {
+	struct htable *table;	/* the hash table */
+	u32 maxelem;		/* max elements in the hash */
+	u32 elements;		/* current element (vs timeout) */
+	u32 initval;		/* random jhash init value */
+	u32 timeout;		/* timeout value, if enabled */
+	struct timer_list gc;	/* garbage collection when timeout enabled */
+#ifdef IP_SET_HASH_WITH_NETMASK
+	u8 netmask;		/* netmask value for subnets to store */
+#endif
+#ifdef IP_SET_HASH_WITH_NETS
+	struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */
+#endif
+};
+
+/* Compute htable_bits from the user input parameter hashsize */
+static u8
+htable_bits(u32 hashsize)
+{
+	/* Assume that hashsize == 2^htable_bits */
+	u8 bits = fls(hashsize - 1);
+	if (jhash_size(bits) != hashsize)
+		/* Round up to the first 2^n value */
+		bits = fls(hashsize);
+
+	return bits;
+}
+
+#ifdef IP_SET_HASH_WITH_NETS
+
+#define SET_HOST_MASK(family)	(family == AF_INET ? 32 : 128)
+
+/* Network cidr size book keeping when the hash stores different
+ * sized networks */
+static void
+add_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask)
+{
+	u8 i;
+
+	++h->nets[cidr-1].nets;
+
+	pr_debug("add_cidr added %u: %u\n", cidr, h->nets[cidr-1].nets);
+
+	if (h->nets[cidr-1].nets > 1)
+		return;
+
+	/* New cidr size */
+	for (i = 0; i < host_mask && h->nets[i].cidr; i++) {
+		/* Add in increasing prefix order, so larger cidr first */
+		if (h->nets[i].cidr < cidr)
+			swap(h->nets[i].cidr, cidr);
+	}
+	if (i < host_mask)
+		h->nets[i].cidr = cidr;
+}
+
+static void
+del_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask)
+{
+	u8 i;
+
+	--h->nets[cidr-1].nets;
+
+	pr_debug("del_cidr deleted %u: %u\n", cidr, h->nets[cidr-1].nets);
+
+	if (h->nets[cidr-1].nets != 0)
+		return;
+
+	/* All entries with this cidr size deleted, so cleanup h->cidr[] */
+	for (i = 0; i < host_mask - 1 && h->nets[i].cidr; i++) {
+		if (h->nets[i].cidr == cidr)
+			h->nets[i].cidr = cidr = h->nets[i+1].cidr;
+	}
+	h->nets[i - 1].cidr = 0;
+}
+#endif
+
+/* Destroy the hashtable part of the set */
+static void
+ahash_destroy(struct htable *t)
+{
+	struct hbucket *n;
+	u32 i;
+
+	for (i = 0; i < jhash_size(t->htable_bits); i++) {
+		n = hbucket(t, i);
+		if (n->size)
+			/* FIXME: use slab cache */
+			kfree(n->value);
+	}
+
+	ip_set_free(t);
+}
+
+/* Calculate the actual memory size of the set data */
+static size_t
+ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 host_mask)
+{
+	u32 i;
+	struct htable *t = h->table;
+	size_t memsize = sizeof(*h)
+			 + sizeof(*t)
+#ifdef IP_SET_HASH_WITH_NETS
+			 + sizeof(struct ip_set_hash_nets) * host_mask
+#endif
+			 + jhash_size(t->htable_bits) * sizeof(struct hbucket);
+
+	for (i = 0; i < jhash_size(t->htable_bits); i++)
+			memsize += t->bucket[i].size * dsize;
+
+	return memsize;
+}
+
+/* Flush a hash type of set: destroy all elements */
+static void
+ip_set_hash_flush(struct ip_set *set)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	struct hbucket *n;
+	u32 i;
+
+	for (i = 0; i < jhash_size(t->htable_bits); i++) {
+		n = hbucket(t, i);
+		if (n->size) {
+			n->size = n->pos = 0;
+			/* FIXME: use slab cache */
+			kfree(n->value);
+		}
+	}
+#ifdef IP_SET_HASH_WITH_NETS
+	memset(h->nets, 0, sizeof(struct ip_set_hash_nets)
+			   * SET_HOST_MASK(set->family));
+#endif
+	h->elements = 0;
+}
+
+/* Destroy a hash type of set */
+static void
+ip_set_hash_destroy(struct ip_set *set)
+{
+	struct ip_set_hash *h = set->data;
+
+	if (with_timeout(h->timeout))
+		del_timer_sync(&h->gc);
+
+	ahash_destroy(h->table);
+	kfree(h);
+
+	set->data = NULL;
+}
+
+#define HKEY(data, initval, htable_bits)				 \
+(jhash2((u32 *)(data), sizeof(struct type_pf_elem)/sizeof(u32), initval) \
+	& jhash_mask(htable_bits))
+
+#endif /* _IP_SET_AHASH_H */
+
+#define CONCAT(a, b, c)		a##b##c
+#define TOKEN(a, b, c)		CONCAT(a, b, c)
+
+/* Type/family dependent function prototypes */
+
+#define type_pf_data_equal	TOKEN(TYPE, PF, _data_equal)
+#define type_pf_data_isnull	TOKEN(TYPE, PF, _data_isnull)
+#define type_pf_data_copy	TOKEN(TYPE, PF, _data_copy)
+#define type_pf_data_zero_out	TOKEN(TYPE, PF, _data_zero_out)
+#define type_pf_data_netmask	TOKEN(TYPE, PF, _data_netmask)
+#define type_pf_data_list	TOKEN(TYPE, PF, _data_list)
+#define type_pf_data_tlist	TOKEN(TYPE, PF, _data_tlist)
+
+#define type_pf_elem		TOKEN(TYPE, PF, _elem)
+#define type_pf_telem		TOKEN(TYPE, PF, _telem)
+#define type_pf_data_timeout	TOKEN(TYPE, PF, _data_timeout)
+#define type_pf_data_expired	TOKEN(TYPE, PF, _data_expired)
+#define type_pf_data_timeout_set TOKEN(TYPE, PF, _data_timeout_set)
+
+#define type_pf_elem_add	TOKEN(TYPE, PF, _elem_add)
+#define type_pf_add		TOKEN(TYPE, PF, _add)
+#define type_pf_del		TOKEN(TYPE, PF, _del)
+#define type_pf_test_cidrs	TOKEN(TYPE, PF, _test_cidrs)
+#define type_pf_test		TOKEN(TYPE, PF, _test)
+
+#define type_pf_elem_tadd	TOKEN(TYPE, PF, _elem_tadd)
+#define type_pf_del_telem	TOKEN(TYPE, PF, _ahash_del_telem)
+#define type_pf_expire		TOKEN(TYPE, PF, _expire)
+#define type_pf_tadd		TOKEN(TYPE, PF, _tadd)
+#define type_pf_tdel		TOKEN(TYPE, PF, _tdel)
+#define type_pf_ttest_cidrs	TOKEN(TYPE, PF, _ahash_ttest_cidrs)
+#define type_pf_ttest		TOKEN(TYPE, PF, _ahash_ttest)
+
+#define type_pf_resize		TOKEN(TYPE, PF, _resize)
+#define type_pf_tresize		TOKEN(TYPE, PF, _tresize)
+#define type_pf_flush		ip_set_hash_flush
+#define type_pf_destroy		ip_set_hash_destroy
+#define type_pf_head		TOKEN(TYPE, PF, _head)
+#define type_pf_list		TOKEN(TYPE, PF, _list)
+#define type_pf_tlist		TOKEN(TYPE, PF, _tlist)
+#define type_pf_same_set	TOKEN(TYPE, PF, _same_set)
+#define type_pf_kadt		TOKEN(TYPE, PF, _kadt)
+#define type_pf_uadt		TOKEN(TYPE, PF, _uadt)
+#define type_pf_gc		TOKEN(TYPE, PF, _gc)
+#define type_pf_gc_init		TOKEN(TYPE, PF, _gc_init)
+#define type_pf_variant		TOKEN(TYPE, PF, _variant)
+#define type_pf_tvariant	TOKEN(TYPE, PF, _tvariant)
+
+/* Flavour without timeout */
+
+/* Get the ith element from the array block n */
+#define ahash_data(n, i)	\
+	((struct type_pf_elem *)((n)->value) + (i))
+
+/* Add an element to the hash table when resizing the set:
+ * we spare the maintenance of the internal counters. */
+static int
+type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value)
+{
+	if (n->pos >= n->size) {
+		void *tmp;
+
+		if (n->size >= AHASH_MAX_SIZE)
+			/* Trigger rehashing */
+			return -EAGAIN;
+
+		tmp = kzalloc((n->size + AHASH_INIT_SIZE)
+			      * sizeof(struct type_pf_elem),
+			      GFP_ATOMIC);
+		if (!tmp)
+			return -ENOMEM;
+		if (n->size) {
+			memcpy(tmp, n->value,
+			       sizeof(struct type_pf_elem) * n->size);
+			kfree(n->value);
+		}
+		n->value = tmp;
+		n->size += AHASH_INIT_SIZE;
+	}
+	type_pf_data_copy(ahash_data(n, n->pos++), value);
+	return 0;
+}
+
+/* Resize a hash: create a new hash table with doubling the hashsize
+ * and inserting the elements to it. Repeat until we succeed or
+ * fail due to memory pressures. */
+static int
+type_pf_resize(struct ip_set *set, bool retried)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t, *orig = h->table;
+	u8 htable_bits = orig->htable_bits;
+	const struct type_pf_elem *data;
+	struct hbucket *n, *m;
+	u32 i, j;
+	int ret;
+
+retry:
+	ret = 0;
+	htable_bits++;
+	pr_debug("attempt to resize set %s from %u to %u, t %p\n",
+		 set->name, orig->htable_bits, htable_bits, orig);
+	if (!htable_bits)
+		/* In case we have plenty of memory :-) */
+		return -IPSET_ERR_HASH_FULL;
+	t = ip_set_alloc(sizeof(*t)
+			 + jhash_size(htable_bits) * sizeof(struct hbucket));
+	if (!t)
+		return -ENOMEM;
+	t->htable_bits = htable_bits;
+
+	read_lock_bh(&set->lock);
+	for (i = 0; i < jhash_size(orig->htable_bits); i++) {
+		n = hbucket(orig, i);
+		for (j = 0; j < n->pos; j++) {
+			data = ahash_data(n, j);
+			m = hbucket(t, HKEY(data, h->initval, htable_bits));
+			ret = type_pf_elem_add(m, data);
+			if (ret < 0) {
+				read_unlock_bh(&set->lock);
+				ahash_destroy(t);
+				if (ret == -EAGAIN)
+					goto retry;
+				return ret;
+			}
+		}
+	}
+
+	rcu_assign_pointer(h->table, t);
+	read_unlock_bh(&set->lock);
+
+	/* Give time to other readers of the set */
+	synchronize_rcu_bh();
+
+	pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
+		 orig->htable_bits, orig, t->htable_bits, t);
+	ahash_destroy(orig);
+
+	return 0;
+}
+
+/* Add an element to a hash and update the internal counters when succeeded,
+ * otherwise report the proper error code. */
+static int
+type_pf_add(struct ip_set *set, void *value, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t;
+	const struct type_pf_elem *d = value;
+	struct hbucket *n;
+	int i, ret = 0;
+	u32 key;
+
+	if (h->elements >= h->maxelem)
+		return -IPSET_ERR_HASH_FULL;
+
+	rcu_read_lock_bh();
+	t = rcu_dereference_bh(h->table);
+	key = HKEY(value, h->initval, t->htable_bits);
+	n = hbucket(t, key);
+	for (i = 0; i < n->pos; i++)
+		if (type_pf_data_equal(ahash_data(n, i), d)) {
+			ret = -IPSET_ERR_EXIST;
+			goto out;
+		}
+
+	ret = type_pf_elem_add(n, value);
+	if (ret != 0)
+		goto out;
+
+#ifdef IP_SET_HASH_WITH_NETS
+	add_cidr(h, d->cidr, HOST_MASK);
+#endif
+	h->elements++;
+out:
+	rcu_read_unlock_bh();
+	return ret;
+}
+
+/* Delete an element from the hash: swap it with the last element
+ * and free up space if possible.
+ */
+static int
+type_pf_del(struct ip_set *set, void *value, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	const struct type_pf_elem *d = value;
+	struct hbucket *n;
+	int i;
+	struct type_pf_elem *data;
+	u32 key;
+
+	key = HKEY(value, h->initval, t->htable_bits);
+	n = hbucket(t, key);
+	for (i = 0; i < n->pos; i++) {
+		data = ahash_data(n, i);
+		if (!type_pf_data_equal(data, d))
+			continue;
+		if (i != n->pos - 1)
+			/* Not last one */
+			type_pf_data_copy(data, ahash_data(n, n->pos - 1));
+
+		n->pos--;
+		h->elements--;
+#ifdef IP_SET_HASH_WITH_NETS
+		del_cidr(h, d->cidr, HOST_MASK);
+#endif
+		if (n->pos + AHASH_INIT_SIZE < n->size) {
+			void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
+					    * sizeof(struct type_pf_elem),
+					    GFP_ATOMIC);
+			if (!tmp)
+				return 0;
+			n->size -= AHASH_INIT_SIZE;
+			memcpy(tmp, n->value,
+			       n->size * sizeof(struct type_pf_elem));
+			kfree(n->value);
+			n->value = tmp;
+		}
+		return 0;
+	}
+
+	return -IPSET_ERR_EXIST;
+}
+
+#ifdef IP_SET_HASH_WITH_NETS
+
+/* Special test function which takes into account the different network
+ * sizes added to the set */
+static int
+type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	struct hbucket *n;
+	const struct type_pf_elem *data;
+	int i, j = 0;
+	u32 key;
+	u8 host_mask = SET_HOST_MASK(set->family);
+
+	pr_debug("test by nets\n");
+	for (; j < host_mask && h->nets[j].cidr; j++) {
+		type_pf_data_netmask(d, h->nets[j].cidr);
+		key = HKEY(d, h->initval, t->htable_bits);
+		n = hbucket(t, key);
+		for (i = 0; i < n->pos; i++) {
+			data = ahash_data(n, i);
+			if (type_pf_data_equal(data, d))
+				return 1;
+		}
+	}
+	return 0;
+}
+#endif
+
+/* Test whether the element is added to the set */
+static int
+type_pf_test(struct ip_set *set, void *value, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	struct type_pf_elem *d = value;
+	struct hbucket *n;
+	const struct type_pf_elem *data;
+	int i;
+	u32 key;
+
+#ifdef IP_SET_HASH_WITH_NETS
+	/* If we test an IP address and not a network address,
+	 * try all possible network sizes */
+	if (d->cidr == SET_HOST_MASK(set->family))
+		return type_pf_test_cidrs(set, d, timeout);
+#endif
+
+	key = HKEY(d, h->initval, t->htable_bits);
+	n = hbucket(t, key);
+	for (i = 0; i < n->pos; i++) {
+		data = ahash_data(n, i);
+		if (type_pf_data_equal(data, d))
+			return 1;
+	}
+	return 0;
+}
+
+/* Reply a HEADER request: fill out the header part of the set */
+static int
+type_pf_head(struct ip_set *set, struct sk_buff *skb)
+{
+	const struct ip_set_hash *h = set->data;
+	struct nlattr *nested;
+	size_t memsize;
+
+	read_lock_bh(&set->lock);
+	memsize = ahash_memsize(h, with_timeout(h->timeout)
+					? sizeof(struct type_pf_telem)
+					: sizeof(struct type_pf_elem),
+				set->family == AF_INET ? 32 : 128);
+	read_unlock_bh(&set->lock);
+
+	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+	if (!nested)
+		goto nla_put_failure;
+	NLA_PUT_NET32(skb, IPSET_ATTR_HASHSIZE,
+		      htonl(jhash_size(h->table->htable_bits)));
+	NLA_PUT_NET32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem));
+#ifdef IP_SET_HASH_WITH_NETMASK
+	if (h->netmask != HOST_MASK)
+		NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask);
+#endif
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
+		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize));
+	if (with_timeout(h->timeout))
+		NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout));
+	ipset_nest_end(skb, nested);
+
+	return 0;
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+/* Reply a LIST/SAVE request: dump the elements of the specified set */
+static int
+type_pf_list(const struct ip_set *set,
+	     struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct ip_set_hash *h = set->data;
+	const struct htable *t = h->table;
+	struct nlattr *atd, *nested;
+	const struct hbucket *n;
+	const struct type_pf_elem *data;
+	u32 first = cb->args[2];
+	/* We assume that one hash bucket fills into one page */
+	void *incomplete;
+	int i;
+
+	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	if (!atd)
+		return -EMSGSIZE;
+	pr_debug("list hash set %s\n", set->name);
+	for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) {
+		incomplete = skb_tail_pointer(skb);
+		n = hbucket(t, cb->args[2]);
+		pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n);
+		for (i = 0; i < n->pos; i++) {
+			data = ahash_data(n, i);
+			pr_debug("list hash %lu hbucket %p i %u, data %p\n",
+				 cb->args[2], n, i, data);
+			nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+			if (!nested) {
+				if (cb->args[2] == first) {
+					nla_nest_cancel(skb, atd);
+					return -EMSGSIZE;
+				} else
+					goto nla_put_failure;
+			}
+			if (type_pf_data_list(skb, data))
+				goto nla_put_failure;
+			ipset_nest_end(skb, nested);
+		}
+	}
+	ipset_nest_end(skb, atd);
+	/* Set listing finished */
+	cb->args[2] = 0;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_trim(skb, incomplete);
+	ipset_nest_end(skb, atd);
+	if (unlikely(first == cb->args[2])) {
+		pr_warning("Can't list set %s: one bucket does not fit into "
+			   "a message. Please report it!\n", set->name);
+		cb->args[2] = 0;
+		return -EMSGSIZE;
+	}
+	return 0;
+}
+
+static int
+type_pf_kadt(struct ip_set *set, const struct sk_buff * skb,
+	     enum ipset_adt adt, u8 pf, u8 dim, u8 flags);
+static int
+type_pf_uadt(struct ip_set *set, struct nlattr *tb[],
+	     enum ipset_adt adt, u32 *lineno, u32 flags);
+
+static const struct ip_set_type_variant type_pf_variant = {
+	.kadt	= type_pf_kadt,
+	.uadt	= type_pf_uadt,
+	.adt	= {
+		[IPSET_ADD] = type_pf_add,
+		[IPSET_DEL] = type_pf_del,
+		[IPSET_TEST] = type_pf_test,
+	},
+	.destroy = type_pf_destroy,
+	.flush	= type_pf_flush,
+	.head	= type_pf_head,
+	.list	= type_pf_list,
+	.resize	= type_pf_resize,
+	.same_set = type_pf_same_set,
+};
+
+/* Flavour with timeout support */
+
+#define ahash_tdata(n, i) \
+	(struct type_pf_elem *)((struct type_pf_telem *)((n)->value) + (i))
+
+static inline u32
+type_pf_data_timeout(const struct type_pf_elem *data)
+{
+	const struct type_pf_telem *tdata =
+		(const struct type_pf_telem *) data;
+
+	return tdata->timeout;
+}
+
+static inline bool
+type_pf_data_expired(const struct type_pf_elem *data)
+{
+	const struct type_pf_telem *tdata =
+		(const struct type_pf_telem *) data;
+
+	return ip_set_timeout_expired(tdata->timeout);
+}
+
+static inline void
+type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout)
+{
+	struct type_pf_telem *tdata = (struct type_pf_telem *) data;
+
+	tdata->timeout = ip_set_timeout_set(timeout);
+}
+
+static int
+type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value,
+		  u32 timeout)
+{
+	struct type_pf_elem *data;
+
+	if (n->pos >= n->size) {
+		void *tmp;
+
+		if (n->size >= AHASH_MAX_SIZE)
+			/* Trigger rehashing */
+			return -EAGAIN;
+
+		tmp = kzalloc((n->size + AHASH_INIT_SIZE)
+			      * sizeof(struct type_pf_telem),
+			      GFP_ATOMIC);
+		if (!tmp)
+			return -ENOMEM;
+		if (n->size) {
+			memcpy(tmp, n->value,
+			       sizeof(struct type_pf_telem) * n->size);
+			kfree(n->value);
+		}
+		n->value = tmp;
+		n->size += AHASH_INIT_SIZE;
+	}
+	data = ahash_tdata(n, n->pos++);
+	type_pf_data_copy(data, value);
+	type_pf_data_timeout_set(data, timeout);
+	return 0;
+}
+
+/* Delete expired elements from the hashtable */
+static void
+type_pf_expire(struct ip_set_hash *h)
+{
+	struct htable *t = h->table;
+	struct hbucket *n;
+	struct type_pf_elem *data;
+	u32 i;
+	int j;
+
+	for (i = 0; i < jhash_size(t->htable_bits); i++) {
+		n = hbucket(t, i);
+		for (j = 0; j < n->pos; j++) {
+			data = ahash_tdata(n, j);
+			if (type_pf_data_expired(data)) {
+				pr_debug("expired %u/%u\n", i, j);
+#ifdef IP_SET_HASH_WITH_NETS
+				del_cidr(h, data->cidr, HOST_MASK);
+#endif
+				if (j != n->pos - 1)
+					/* Not last one */
+					type_pf_data_copy(data,
+						ahash_tdata(n, n->pos - 1));
+				n->pos--;
+				h->elements--;
+			}
+		}
+		if (n->pos + AHASH_INIT_SIZE < n->size) {
+			void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
+					    * sizeof(struct type_pf_telem),
+					    GFP_ATOMIC);
+			if (!tmp)
+				/* Still try to delete expired elements */
+				continue;
+			n->size -= AHASH_INIT_SIZE;
+			memcpy(tmp, n->value,
+			       n->size * sizeof(struct type_pf_telem));
+			kfree(n->value);
+			n->value = tmp;
+		}
+	}
+}
+
+static int
+type_pf_tresize(struct ip_set *set, bool retried)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t, *orig = h->table;
+	u8 htable_bits = orig->htable_bits;
+	const struct type_pf_elem *data;
+	struct hbucket *n, *m;
+	u32 i, j;
+	int ret;
+
+	/* Try to cleanup once */
+	if (!retried) {
+		i = h->elements;
+		write_lock_bh(&set->lock);
+		type_pf_expire(set->data);
+		write_unlock_bh(&set->lock);
+		if (h->elements <  i)
+			return 0;
+	}
+
+retry:
+	ret = 0;
+	htable_bits++;
+	if (!htable_bits)
+		/* In case we have plenty of memory :-) */
+		return -IPSET_ERR_HASH_FULL;
+	t = ip_set_alloc(sizeof(*t)
+			 + jhash_size(htable_bits) * sizeof(struct hbucket));
+	if (!t)
+		return -ENOMEM;
+	t->htable_bits = htable_bits;
+
+	read_lock_bh(&set->lock);
+	for (i = 0; i < jhash_size(orig->htable_bits); i++) {
+		n = hbucket(orig, i);
+		for (j = 0; j < n->pos; j++) {
+			data = ahash_tdata(n, j);
+			m = hbucket(t, HKEY(data, h->initval, htable_bits));
+			ret = type_pf_elem_tadd(m, data,
+						type_pf_data_timeout(data));
+			if (ret < 0) {
+				read_unlock_bh(&set->lock);
+				ahash_destroy(t);
+				if (ret == -EAGAIN)
+					goto retry;
+				return ret;
+			}
+		}
+	}
+
+	rcu_assign_pointer(h->table, t);
+	read_unlock_bh(&set->lock);
+
+	/* Give time to other readers of the set */
+	synchronize_rcu_bh();
+
+	ahash_destroy(orig);
+
+	return 0;
+}
+
+static int
+type_pf_tadd(struct ip_set *set, void *value, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	const struct type_pf_elem *d = value;
+	struct hbucket *n;
+	struct type_pf_elem *data;
+	int ret = 0, i, j = AHASH_MAX_SIZE + 1;
+	u32 key;
+
+	if (h->elements >= h->maxelem)
+		/* FIXME: when set is full, we slow down here */
+		type_pf_expire(h);
+	if (h->elements >= h->maxelem)
+		return -IPSET_ERR_HASH_FULL;
+
+	rcu_read_lock_bh();
+	t = rcu_dereference_bh(h->table);
+	key = HKEY(d, h->initval, t->htable_bits);
+	n = hbucket(t, key);
+	for (i = 0; i < n->pos; i++) {
+		data = ahash_tdata(n, i);
+		if (type_pf_data_equal(data, d)) {
+			if (type_pf_data_expired(data))
+				j = i;
+			else {
+				ret = -IPSET_ERR_EXIST;
+				goto out;
+			}
+		} else if (j == AHASH_MAX_SIZE + 1 &&
+			   type_pf_data_expired(data))
+			j = i;
+	}
+	if (j != AHASH_MAX_SIZE + 1) {
+		data = ahash_tdata(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+		del_cidr(h, data->cidr, HOST_MASK);
+		add_cidr(h, d->cidr, HOST_MASK);
+#endif
+		type_pf_data_copy(data, d);
+		type_pf_data_timeout_set(data, timeout);
+		goto out;
+	}
+	ret = type_pf_elem_tadd(n, d, timeout);
+	if (ret != 0)
+		goto out;
+
+#ifdef IP_SET_HASH_WITH_NETS
+	add_cidr(h, d->cidr, HOST_MASK);
+#endif
+	h->elements++;
+out:
+	rcu_read_unlock_bh();
+	return ret;
+}
+
+static int
+type_pf_tdel(struct ip_set *set, void *value, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	const struct type_pf_elem *d = value;
+	struct hbucket *n;
+	int i, ret = 0;
+	struct type_pf_elem *data;
+	u32 key;
+
+	key = HKEY(value, h->initval, t->htable_bits);
+	n = hbucket(t, key);
+	for (i = 0; i < n->pos; i++) {
+		data = ahash_tdata(n, i);
+		if (!type_pf_data_equal(data, d))
+			continue;
+		if (type_pf_data_expired(data))
+			ret = -IPSET_ERR_EXIST;
+		if (i != n->pos - 1)
+			/* Not last one */
+			type_pf_data_copy(data, ahash_tdata(n, n->pos - 1));
+
+		n->pos--;
+		h->elements--;
+#ifdef IP_SET_HASH_WITH_NETS
+		del_cidr(h, d->cidr, HOST_MASK);
+#endif
+		if (n->pos + AHASH_INIT_SIZE < n->size) {
+			void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
+					    * sizeof(struct type_pf_telem),
+					    GFP_ATOMIC);
+			if (!tmp)
+				return 0;
+			n->size -= AHASH_INIT_SIZE;
+			memcpy(tmp, n->value,
+			       n->size * sizeof(struct type_pf_telem));
+			kfree(n->value);
+			n->value = tmp;
+		}
+		return 0;
+	}
+
+	return -IPSET_ERR_EXIST;
+}
+
+#ifdef IP_SET_HASH_WITH_NETS
+static int
+type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	struct type_pf_elem *data;
+	struct hbucket *n;
+	int i, j = 0;
+	u32 key;
+	u8 host_mask = SET_HOST_MASK(set->family);
+
+	for (; j < host_mask && h->nets[j].cidr; j++) {
+		type_pf_data_netmask(d, h->nets[j].cidr);
+		key = HKEY(d, h->initval, t->htable_bits);
+		n = hbucket(t, key);
+		for (i = 0; i < n->pos; i++) {
+			data = ahash_tdata(n, i);
+			if (type_pf_data_equal(data, d))
+				return !type_pf_data_expired(data);
+		}
+	}
+	return 0;
+}
+#endif
+
+static int
+type_pf_ttest(struct ip_set *set, void *value, u32 timeout)
+{
+	struct ip_set_hash *h = set->data;
+	struct htable *t = h->table;
+	struct type_pf_elem *data, *d = value;
+	struct hbucket *n;
+	int i;
+	u32 key;
+
+#ifdef IP_SET_HASH_WITH_NETS
+	if (d->cidr == SET_HOST_MASK(set->family))
+		return type_pf_ttest_cidrs(set, d, timeout);
+#endif
+	key = HKEY(d, h->initval, t->htable_bits);
+	n = hbucket(t, key);
+	for (i = 0; i < n->pos; i++) {
+		data = ahash_tdata(n, i);
+		if (type_pf_data_equal(data, d))
+			return !type_pf_data_expired(data);
+	}
+	return 0;
+}
+
+static int
+type_pf_tlist(const struct ip_set *set,
+	      struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct ip_set_hash *h = set->data;
+	const struct htable *t = h->table;
+	struct nlattr *atd, *nested;
+	const struct hbucket *n;
+	const struct type_pf_elem *data;
+	u32 first = cb->args[2];
+	/* We assume that one hash bucket fills into one page */
+	void *incomplete;
+	int i;
+
+	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	if (!atd)
+		return -EMSGSIZE;
+	for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) {
+		incomplete = skb_tail_pointer(skb);
+		n = hbucket(t, cb->args[2]);
+		for (i = 0; i < n->pos; i++) {
+			data = ahash_tdata(n, i);
+			pr_debug("list %p %u\n", n, i);
+			if (type_pf_data_expired(data))
+				continue;
+			pr_debug("do list %p %u\n", n, i);
+			nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+			if (!nested) {
+				if (cb->args[2] == first) {
+					nla_nest_cancel(skb, atd);
+					return -EMSGSIZE;
+				} else
+					goto nla_put_failure;
+			}
+			if (type_pf_data_tlist(skb, data))
+				goto nla_put_failure;
+			ipset_nest_end(skb, nested);
+		}
+	}
+	ipset_nest_end(skb, atd);
+	/* Set listing finished */
+	cb->args[2] = 0;
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_trim(skb, incomplete);
+	ipset_nest_end(skb, atd);
+	if (unlikely(first == cb->args[2])) {
+		pr_warning("Can't list set %s: one bucket does not fit into "
+			   "a message. Please report it!\n", set->name);
+		cb->args[2] = 0;
+		return -EMSGSIZE;
+	}
+	return 0;
+}
+
+static const struct ip_set_type_variant type_pf_tvariant = {
+	.kadt	= type_pf_kadt,
+	.uadt	= type_pf_uadt,
+	.adt	= {
+		[IPSET_ADD] = type_pf_tadd,
+		[IPSET_DEL] = type_pf_tdel,
+		[IPSET_TEST] = type_pf_ttest,
+	},
+	.destroy = type_pf_destroy,
+	.flush	= type_pf_flush,
+	.head	= type_pf_head,
+	.list	= type_pf_tlist,
+	.resize	= type_pf_tresize,
+	.same_set = type_pf_same_set,
+};
+
+static void
+type_pf_gc(unsigned long ul_set)
+{
+	struct ip_set *set = (struct ip_set *) ul_set;
+	struct ip_set_hash *h = set->data;
+
+	pr_debug("called\n");
+	write_lock_bh(&set->lock);
+	type_pf_expire(h);
+	write_unlock_bh(&set->lock);
+
+	h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
+	add_timer(&h->gc);
+}
+
+static void
+type_pf_gc_init(struct ip_set *set)
+{
+	struct ip_set_hash *h = set->data;
+
+	init_timer(&h->gc);
+	h->gc.data = (unsigned long) set;
+	h->gc.function = type_pf_gc;
+	h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
+	add_timer(&h->gc);
+	pr_debug("gc initialized, run in every %u\n",
+		 IPSET_GC_PERIOD(h->timeout));
+}
+
+#undef type_pf_data_equal
+#undef type_pf_data_isnull
+#undef type_pf_data_copy
+#undef type_pf_data_zero_out
+#undef type_pf_data_list
+#undef type_pf_data_tlist
+
+#undef type_pf_elem
+#undef type_pf_telem
+#undef type_pf_data_timeout
+#undef type_pf_data_expired
+#undef type_pf_data_netmask
+#undef type_pf_data_timeout_set
+
+#undef type_pf_elem_add
+#undef type_pf_add
+#undef type_pf_del
+#undef type_pf_test_cidrs
+#undef type_pf_test
+
+#undef type_pf_elem_tadd
+#undef type_pf_expire
+#undef type_pf_tadd
+#undef type_pf_tdel
+#undef type_pf_ttest_cidrs
+#undef type_pf_ttest
+
+#undef type_pf_resize
+#undef type_pf_tresize
+#undef type_pf_flush
+#undef type_pf_destroy
+#undef type_pf_head
+#undef type_pf_list
+#undef type_pf_tlist
+#undef type_pf_same_set
+#undef type_pf_kadt
+#undef type_pf_uadt
+#undef type_pf_gc
+#undef type_pf_gc_init
+#undef type_pf_variant
+#undef type_pf_tvariant
diff --git a/include/linux/netfilter/ipset/ip_set_hash.h b/include/linux/netfilter/ipset/ip_set_hash.h
new file mode 100644
index 000000000000..b86f15c04524
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_hash.h
@@ -0,0 +1,26 @@
+#ifndef __IP_SET_HASH_H
+#define __IP_SET_HASH_H
+
+/* Hash type specific error codes */
+enum {
+	/* Hash is full */
+	IPSET_ERR_HASH_FULL = IPSET_ERR_TYPE_SPECIFIC,
+	/* Null-valued element */
+	IPSET_ERR_HASH_ELEM,
+	/* Invalid protocol */
+	IPSET_ERR_INVALID_PROTO,
+	/* Protocol missing but must be specified */
+	IPSET_ERR_MISSING_PROTO,
+};
+
+#ifdef __KERNEL__
+
+#define IPSET_DEFAULT_HASHSIZE		1024
+#define IPSET_MIMINAL_HASHSIZE		64
+#define IPSET_DEFAULT_MAXELEM		65536
+#define IPSET_DEFAULT_PROBES		4
+#define IPSET_DEFAULT_RESIZE		100
+
+#endif /* __KERNEL__ */
+
+#endif /* __IP_SET_HASH_H */
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index f401e9112703..194d89caeb3d 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -50,4 +50,14 @@ config IP_SET_BITMAP_PORT
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config IP_SET_HASH_IP
+	tristate "hash:ip set support"
+	depends on IP_SET
+	help
+	  This option adds the hash:ip set type support, by which one
+	  can store arbitrary IPv4 or IPv6 addresses (or network addresses)
+	  in a set.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 endif # IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 40866e267752..5cbf00c41a98 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -11,3 +11,6 @@ obj-$(CONFIG_IP_SET) += ip_set.o
 obj-$(CONFIG_IP_SET_BITMAP_IP) += ip_set_bitmap_ip.o
 obj-$(CONFIG_IP_SET_BITMAP_IPMAC) += ip_set_bitmap_ipmac.o
 obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o
+
+# hash types
+obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
new file mode 100644
index 000000000000..53964bc831aa
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -0,0 +1,467 @@
+/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/uaccess.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_timeout.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
+MODULE_DESCRIPTION("hash:ip type of IP sets");
+MODULE_ALIAS("ip_set_hash:ip");
+
+/* Type specific function prefix */
+#define TYPE		hash_ip
+
+static bool
+hash_ip_same_set(const struct ip_set *a, const struct ip_set *b);
+
+#define hash_ip4_same_set	hash_ip_same_set
+#define hash_ip6_same_set	hash_ip_same_set
+
+/* The type variant functions: IPv4 */
+
+/* Member elements without timeout */
+struct hash_ip4_elem {
+	__be32 ip;
+};
+
+/* Member elements with timeout support */
+struct hash_ip4_telem {
+	__be32 ip;
+	unsigned long timeout;
+};
+
+static inline bool
+hash_ip4_data_equal(const struct hash_ip4_elem *ip1,
+		    const struct hash_ip4_elem *ip2)
+{
+	return ip1->ip == ip2->ip;
+}
+
+static inline bool
+hash_ip4_data_isnull(const struct hash_ip4_elem *elem)
+{
+	return elem->ip == 0;
+}
+
+static inline void
+hash_ip4_data_copy(struct hash_ip4_elem *dst, const struct hash_ip4_elem *src)
+{
+	dst->ip = src->ip;
+}
+
+/* Zero valued IP addresses cannot be stored */
+static inline void
+hash_ip4_data_zero_out(struct hash_ip4_elem *elem)
+{
+	elem->ip = 0;
+}
+
+static inline bool
+hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *data)
+{
+	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip);
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+static bool
+hash_ip4_data_tlist(struct sk_buff *skb, const struct hash_ip4_elem *data)
+{
+	const struct hash_ip4_telem *tdata =
+		(const struct hash_ip4_telem *)data;
+
+	NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, tdata->ip);
+	NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT,
+		      htonl(ip_set_timeout_get(tdata->timeout)));
+
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+#define IP_SET_HASH_WITH_NETMASK
+#define PF		4
+#define HOST_MASK	32
+#include <linux/netfilter/ipset/ip_set_ahash.h>
+
+static int
+hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb,
+	      enum ipset_adt adt, u8 pf, u8 dim, u8 flags)
+{
+	const struct ip_set_hash *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	__be32 ip;
+
+	ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &ip);
+	ip &= ip_set_netmask(h->netmask);
+	if (ip == 0)
+		return -EINVAL;
+
+	return adtfn(set, &ip, h->timeout);
+}
+
+static int
+hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
+	      enum ipset_adt adt, u32 *lineno, u32 flags)
+{
+	const struct ip_set_hash *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	u32 ip, ip_to, hosts, timeout = h->timeout;
+	__be32 nip;
+	int ret = 0;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+	if (ret)
+		return ret;
+
+	ip &= ip_set_hostmask(h->netmask);
+
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		if (!with_timeout(h->timeout))
+			return -IPSET_ERR_TIMEOUT;
+		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+	}
+
+	if (adt == IPSET_TEST) {
+		nip = htonl(ip);
+		if (nip == 0)
+			return -IPSET_ERR_HASH_ELEM;
+		return adtfn(set, &nip, timeout);
+	}
+
+	if (tb[IPSET_ATTR_IP_TO]) {
+		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+		if (ret)
+			return ret;
+		if (ip > ip_to)
+			swap(ip, ip_to);
+	} else if (tb[IPSET_ATTR_CIDR]) {
+		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+		if (cidr > 32)
+			return -IPSET_ERR_INVALID_CIDR;
+		ip &= ip_set_hostmask(cidr);
+		ip_to = ip | ~ip_set_hostmask(cidr);
+	} else
+		ip_to = ip;
+
+	hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
+
+	for (; !before(ip_to, ip); ip += hosts) {
+		nip = htonl(ip);
+		if (nip == 0)
+			return -IPSET_ERR_HASH_ELEM;
+		ret = adtfn(set, &nip, timeout);
+
+		if (ret && !ip_set_eexist(ret, flags))
+			return ret;
+		else
+			ret = 0;
+	}
+	return ret;
+}
+
+static bool
+hash_ip_same_set(const struct ip_set *a, const struct ip_set *b)
+{
+	const struct ip_set_hash *x = a->data;
+	const struct ip_set_hash *y = b->data;
+
+	/* Resizing changes htable_bits, so we ignore it */
+	return x->maxelem == y->maxelem &&
+	       x->timeout == y->timeout &&
+	       x->netmask == y->netmask;
+}
+
+/* The type variant functions: IPv6 */
+
+struct hash_ip6_elem {
+	union nf_inet_addr ip;
+};
+
+struct hash_ip6_telem {
+	union nf_inet_addr ip;
+	unsigned long timeout;
+};
+
+static inline bool
+hash_ip6_data_equal(const struct hash_ip6_elem *ip1,
+		    const struct hash_ip6_elem *ip2)
+{
+	return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0;
+}
+
+static inline bool
+hash_ip6_data_isnull(const struct hash_ip6_elem *elem)
+{
+	return ipv6_addr_any(&elem->ip.in6);
+}
+
+static inline void
+hash_ip6_data_copy(struct hash_ip6_elem *dst, const struct hash_ip6_elem *src)
+{
+	ipv6_addr_copy(&dst->ip.in6, &src->ip.in6);
+}
+
+static inline void
+hash_ip6_data_zero_out(struct hash_ip6_elem *elem)
+{
+	ipv6_addr_set(&elem->ip.in6, 0, 0, 0, 0);
+}
+
+static inline void
+ip6_netmask(union nf_inet_addr *ip, u8 prefix)
+{
+	ip->ip6[0] &= ip_set_netmask6(prefix)[0];
+	ip->ip6[1] &= ip_set_netmask6(prefix)[1];
+	ip->ip6[2] &= ip_set_netmask6(prefix)[2];
+	ip->ip6[3] &= ip_set_netmask6(prefix)[3];
+}
+
+static bool
+hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *data)
+{
+	NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip);
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+static bool
+hash_ip6_data_tlist(struct sk_buff *skb, const struct hash_ip6_elem *data)
+{
+	const struct hash_ip6_telem *e =
+		(const struct hash_ip6_telem *)data;
+
+	NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip);
+	NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT,
+		      htonl(ip_set_timeout_get(e->timeout)));
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+#undef PF
+#undef HOST_MASK
+
+#define PF		6
+#define HOST_MASK	128
+#include <linux/netfilter/ipset/ip_set_ahash.h>
+
+static int
+hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb,
+	      enum ipset_adt adt, u8 pf, u8 dim, u8 flags)
+{
+	const struct ip_set_hash *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	union nf_inet_addr ip;
+
+	ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &ip.in6);
+	ip6_netmask(&ip, h->netmask);
+	if (ipv6_addr_any(&ip.in6))
+		return -EINVAL;
+
+	return adtfn(set, &ip, h->timeout);
+}
+
+static const struct nla_policy hash_ip6_adt_policy[IPSET_ATTR_ADT_MAX + 1] = {
+	[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
+	[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+	[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+};
+
+static int
+hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[],
+	      enum ipset_adt adt, u32 *lineno, u32 flags)
+{
+	const struct ip_set_hash *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	union nf_inet_addr ip;
+	u32 timeout = h->timeout;
+	int ret;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+		     tb[IPSET_ATTR_IP_TO] ||
+		     tb[IPSET_ATTR_CIDR]))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &ip);
+	if (ret)
+		return ret;
+
+	ip6_netmask(&ip, h->netmask);
+	if (ipv6_addr_any(&ip.in6))
+		return -IPSET_ERR_HASH_ELEM;
+
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		if (!with_timeout(h->timeout))
+			return -IPSET_ERR_TIMEOUT;
+		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+	}
+
+	ret = adtfn(set, &ip, timeout);
+
+	return ip_set_eexist(ret, flags) ? 0 : ret;
+}
+
+/* Create hash:ip type of sets */
+
+static int
+hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+{
+	u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
+	u8 netmask, hbits;
+	struct ip_set_hash *h;
+
+	if (!(set->family == AF_INET || set->family == AF_INET6))
+		return -IPSET_ERR_INVALID_FAMILY;
+	netmask = set->family == AF_INET ? 32 : 128;
+	pr_debug("Create set %s with family %s\n",
+		 set->name, set->family == AF_INET ? "inet" : "inet6");
+
+	if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_HASHSIZE]) {
+		hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
+		if (hashsize < IPSET_MIMINAL_HASHSIZE)
+			hashsize = IPSET_MIMINAL_HASHSIZE;
+	}
+
+	if (tb[IPSET_ATTR_MAXELEM])
+		maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
+
+	if (tb[IPSET_ATTR_NETMASK]) {
+		netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]);
+
+		if ((set->family == AF_INET && netmask > 32) ||
+		    (set->family == AF_INET6 && netmask > 128) ||
+		    netmask == 0)
+			return -IPSET_ERR_INVALID_NETMASK;
+	}
+
+	h = kzalloc(sizeof(*h), GFP_KERNEL);
+	if (!h)
+		return -ENOMEM;
+
+	h->maxelem = maxelem;
+	h->netmask = netmask;
+	get_random_bytes(&h->initval, sizeof(h->initval));
+	h->timeout = IPSET_NO_TIMEOUT;
+
+	hbits = htable_bits(hashsize);
+	h->table = ip_set_alloc(
+			sizeof(struct htable)
+			+ jhash_size(hbits) * sizeof(struct hbucket));
+	if (!h->table) {
+		kfree(h);
+		return -ENOMEM;
+	}
+	h->table->htable_bits = hbits;
+
+	set->data = h;
+
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+
+		set->variant = set->family == AF_INET
+			? &hash_ip4_tvariant : &hash_ip6_tvariant;
+
+		if (set->family == AF_INET)
+			hash_ip4_gc_init(set);
+		else
+			hash_ip6_gc_init(set);
+	} else {
+		set->variant = set->family == AF_INET
+			? &hash_ip4_variant : &hash_ip6_variant;
+	}
+
+	pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
+		 set->name, jhash_size(h->table->htable_bits),
+		 h->table->htable_bits, h->maxelem, set->data, h->table);
+
+	return 0;
+}
+
+static struct ip_set_type hash_ip_type __read_mostly = {
+	.name		= "hash:ip",
+	.protocol	= IPSET_PROTOCOL,
+	.features	= IPSET_TYPE_IP,
+	.dimension	= IPSET_DIM_ONE,
+	.family		= AF_UNSPEC,
+	.revision	= 0,
+	.create		= hash_ip_create,
+	.create_policy	= {
+		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
+		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
+		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_NETMASK]	= { .type = NLA_U8  },
+	},
+	.adt_policy	= {
+		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
+		[IPSET_ATTR_IP_TO]	= { .type = NLA_NESTED },
+		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init
+hash_ip_init(void)
+{
+	return ip_set_type_register(&hash_ip_type);
+}
+
+static void __exit
+hash_ip_fini(void)
+{
+	ip_set_type_unregister(&hash_ip_type);
+}
+
+module_init(hash_ip_init);
+module_exit(hash_ip_fini);
-- 
cgit v1.2.3


From f830837f0eed0f9e371b8fd65169365780814bb1 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 1 Feb 2011 15:54:59 +0100
Subject: netfilter: ipset: list:set set type support

The module implements the list:set type support in two flavours:
without and with timeout. The sets has two sides: for the userspace,
they store the names of other (non list:set type of) sets: one can add,
delete and test set names. For the kernel, it forms an ordered union of
the member sets: the members sets are tried in order when elements are
added, deleted and tested and the process stops at the first success.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/ipset/ip_set_list.h |  27 ++
 net/netfilter/ipset/Kconfig                 |  10 +
 net/netfilter/ipset/Makefile                |   3 +
 net/netfilter/ipset/ip_set_list_set.c       | 584 ++++++++++++++++++++++++++++
 4 files changed, 624 insertions(+)
 create mode 100644 include/linux/netfilter/ipset/ip_set_list.h
 create mode 100644 net/netfilter/ipset/ip_set_list_set.c

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set_list.h b/include/linux/netfilter/ipset/ip_set_list.h
new file mode 100644
index 000000000000..40a63f302613
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_list.h
@@ -0,0 +1,27 @@
+#ifndef __IP_SET_LIST_H
+#define __IP_SET_LIST_H
+
+/* List type specific error codes */
+enum {
+	/* Set name to be added/deleted/tested does not exist. */
+	IPSET_ERR_NAME = IPSET_ERR_TYPE_SPECIFIC,
+	/* list:set type is not permitted to add */
+	IPSET_ERR_LOOP,
+	/* Missing reference set */
+	IPSET_ERR_BEFORE,
+	/* Reference set does not exist */
+	IPSET_ERR_NAMEREF,
+	/* Set is full */
+	IPSET_ERR_LIST_FULL,
+	/* Reference set is not added to the set */
+	IPSET_ERR_REF_EXIST,
+};
+
+#ifdef __KERNEL__
+
+#define IP_SET_LIST_DEFAULT_SIZE	8
+#define IP_SET_LIST_MIN_SIZE		4
+
+#endif /* __KERNEL__ */
+
+#endif /* __IP_SET_LIST_H */
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index 2512e7b82d12..3b970d343023 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -108,4 +108,14 @@ config IP_SET_HASH_NETPORT
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config IP_SET_LIST_SET
+	tristate "list:set set support"
+	depends on IP_SET
+	help
+	  This option adds the list:set set type support. In this
+	  kind of set one can store the name of other sets and it forms
+	  an ordered union of the member sets.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 endif # IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index fbbebd62bb2a..5adbdab67bd2 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -19,3 +19,6 @@ obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o
 obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o
 obj-$(CONFIG_IP_SET_HASH_NET) += ip_set_hash_net.o
 obj-$(CONFIG_IP_SET_HASH_NETPORT) += ip_set_hash_netport.o
+
+# list types
+obj-$(CONFIG_IP_SET_LIST_SET) += ip_set_list_set.o
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
new file mode 100644
index 000000000000..a47c32982f06
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -0,0 +1,584 @@
+/* Copyright (C) 2008-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the list:set type */
+
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_timeout.h>
+#include <linux/netfilter/ipset/ip_set_list.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
+MODULE_DESCRIPTION("list:set type of IP sets");
+MODULE_ALIAS("ip_set_list:set");
+
+/* Member elements without and with timeout */
+struct set_elem {
+	ip_set_id_t id;
+};
+
+struct set_telem {
+	ip_set_id_t id;
+	unsigned long timeout;
+};
+
+/* Type structure */
+struct list_set {
+	size_t dsize;		/* element size */
+	u32 size;		/* size of set list array */
+	u32 timeout;		/* timeout value */
+	struct timer_list gc;	/* garbage collection */
+	struct set_elem members[0]; /* the set members */
+};
+
+static inline struct set_elem *
+list_set_elem(const struct list_set *map, u32 id)
+{
+	return (struct set_elem *)((char *)map->members + id * map->dsize);
+}
+
+static inline bool
+list_set_timeout(const struct list_set *map, u32 id)
+{
+	const struct set_telem *elem =
+		(const struct set_telem *) list_set_elem(map, id);
+
+	return ip_set_timeout_test(elem->timeout);
+}
+
+static inline bool
+list_set_expired(const struct list_set *map, u32 id)
+{
+	const struct set_telem *elem =
+		(const struct set_telem *) list_set_elem(map, id);
+
+	return ip_set_timeout_expired(elem->timeout);
+}
+
+static inline int
+list_set_exist(const struct set_telem *elem)
+{
+	return elem->id != IPSET_INVALID_ID &&
+	       !ip_set_timeout_expired(elem->timeout);
+}
+
+/* Set list without and with timeout */
+
+static int
+list_set_kadt(struct ip_set *set, const struct sk_buff *skb,
+	      enum ipset_adt adt, u8 pf, u8 dim, u8 flags)
+{
+	struct list_set *map = set->data;
+	struct set_elem *elem;
+	u32 i;
+	int ret;
+
+	for (i = 0; i < map->size; i++) {
+		elem = list_set_elem(map, i);
+		if (elem->id == IPSET_INVALID_ID)
+			return 0;
+		if (with_timeout(map->timeout) && list_set_expired(map, i))
+			continue;
+		switch (adt) {
+		case IPSET_TEST:
+			ret = ip_set_test(elem->id, skb, pf, dim, flags);
+			if (ret > 0)
+				return ret;
+			break;
+		case IPSET_ADD:
+			ret = ip_set_add(elem->id, skb, pf, dim, flags);
+			if (ret == 0)
+				return ret;
+			break;
+		case IPSET_DEL:
+			ret = ip_set_del(elem->id, skb, pf, dim, flags);
+			if (ret == 0)
+				return ret;
+			break;
+		default:
+			break;
+		}
+	}
+	return -EINVAL;
+}
+
+static bool
+next_id_eq(const struct list_set *map, u32 i, ip_set_id_t id)
+{
+	const struct set_elem *elem;
+
+	if (i + 1 < map->size) {
+		elem = list_set_elem(map, i + 1);
+		return !!(elem->id == id &&
+			  !(with_timeout(map->timeout) &&
+			    list_set_expired(map, i + 1)));
+	}
+
+	return 0;
+}
+
+static void
+list_elem_add(struct list_set *map, u32 i, ip_set_id_t id)
+{
+	struct set_elem *e;
+
+	for (; i < map->size; i++) {
+		e = list_set_elem(map, i);
+		swap(e->id, id);
+		if (e->id == IPSET_INVALID_ID)
+			break;
+	}
+}
+
+static void
+list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id,
+	       unsigned long timeout)
+{
+	struct set_telem *e;
+
+	for (; i < map->size; i++) {
+		e = (struct set_telem *)list_set_elem(map, i);
+		swap(e->id, id);
+		if (e->id == IPSET_INVALID_ID)
+			break;
+		swap(e->timeout, timeout);
+	}
+}
+
+static int
+list_set_add(struct list_set *map, u32 i, ip_set_id_t id,
+	     unsigned long timeout)
+{
+	const struct set_elem *e = list_set_elem(map, i);
+
+	if (i == map->size - 1 && e->id != IPSET_INVALID_ID)
+		/* Last element replaced: e.g. add new,before,last */
+		ip_set_put_byindex(e->id);
+	if (with_timeout(map->timeout))
+		list_elem_tadd(map, i, id, timeout);
+	else
+		list_elem_add(map, i, id);
+
+	return 0;
+}
+
+static int
+list_set_del(struct list_set *map, ip_set_id_t id, u32 i)
+{
+	struct set_elem *a = list_set_elem(map, i), *b;
+
+	ip_set_put_byindex(id);
+
+	for (; i < map->size - 1; i++) {
+		b = list_set_elem(map, i + 1);
+		a->id = b->id;
+		if (with_timeout(map->timeout))
+			((struct set_telem *)a)->timeout =
+				((struct set_telem *)b)->timeout;
+		a = b;
+		if (a->id == IPSET_INVALID_ID)
+			break;
+	}
+	/* Last element */
+	a->id = IPSET_INVALID_ID;
+	return 0;
+}
+
+static int
+list_set_uadt(struct ip_set *set, struct nlattr *tb[],
+	      enum ipset_adt adt, u32 *lineno, u32 flags)
+{
+	struct list_set *map = set->data;
+	bool with_timeout = with_timeout(map->timeout);
+	int before = 0;
+	u32 timeout = map->timeout;
+	ip_set_id_t id, refid = IPSET_INVALID_ID;
+	const struct set_elem *elem;
+	struct ip_set *s;
+	u32 i;
+	int ret = 0;
+
+	if (unlikely(!tb[IPSET_ATTR_NAME] ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	id = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAME]), &s);
+	if (id == IPSET_INVALID_ID)
+		return -IPSET_ERR_NAME;
+	/* "Loop detection" */
+	if (s->type->features & IPSET_TYPE_NAME) {
+		ret = -IPSET_ERR_LOOP;
+		goto finish;
+	}
+
+	if (tb[IPSET_ATTR_CADT_FLAGS]) {
+		u32 f = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+		before = f & IPSET_FLAG_BEFORE;
+	}
+
+	if (before && !tb[IPSET_ATTR_NAMEREF]) {
+		ret = -IPSET_ERR_BEFORE;
+		goto finish;
+	}
+
+	if (tb[IPSET_ATTR_NAMEREF]) {
+		refid = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAMEREF]),
+					  &s);
+		if (refid == IPSET_INVALID_ID) {
+			ret = -IPSET_ERR_NAMEREF;
+			goto finish;
+		}
+		if (!before)
+			before = -1;
+	}
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		if (!with_timeout) {
+			ret = -IPSET_ERR_TIMEOUT;
+			goto finish;
+		}
+		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+	}
+
+	switch (adt) {
+	case IPSET_TEST:
+		for (i = 0; i < map->size && !ret; i++) {
+			elem = list_set_elem(map, i);
+			if (elem->id == IPSET_INVALID_ID ||
+			    (before != 0 && i + 1 >= map->size))
+				break;
+			else if (with_timeout && list_set_expired(map, i))
+				continue;
+			else if (before > 0 && elem->id == id)
+				ret = next_id_eq(map, i, refid);
+			else if (before < 0 && elem->id == refid)
+				ret = next_id_eq(map, i, id);
+			else if (before == 0 && elem->id == id)
+				ret = 1;
+		}
+		break;
+	case IPSET_ADD:
+		for (i = 0; i < map->size && !ret; i++) {
+			elem = list_set_elem(map, i);
+			if (elem->id == id &&
+			    !(with_timeout && list_set_expired(map, i)))
+				ret = -IPSET_ERR_EXIST;
+		}
+		if (ret == -IPSET_ERR_EXIST)
+			break;
+		ret = -IPSET_ERR_LIST_FULL;
+		for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) {
+			elem = list_set_elem(map, i);
+			if (elem->id == IPSET_INVALID_ID)
+				ret = before != 0 ? -IPSET_ERR_REF_EXIST
+					: list_set_add(map, i, id, timeout);
+			else if (elem->id != refid)
+				continue;
+			else if (with_timeout && list_set_expired(map, i))
+				ret = -IPSET_ERR_REF_EXIST;
+			else if (before)
+				ret = list_set_add(map, i, id, timeout);
+			else if (i + 1 < map->size)
+				ret = list_set_add(map, i + 1, id, timeout);
+		}
+		break;
+	case IPSET_DEL:
+		ret = -IPSET_ERR_EXIST;
+		for (i = 0; i < map->size && ret == -IPSET_ERR_EXIST; i++) {
+			elem = list_set_elem(map, i);
+			if (elem->id == IPSET_INVALID_ID) {
+				ret = before != 0 ? -IPSET_ERR_REF_EXIST
+						  : -IPSET_ERR_EXIST;
+				break;
+			} else if (with_timeout && list_set_expired(map, i))
+				continue;
+			else if (elem->id == id &&
+				 (before == 0 ||
+				  (before > 0 &&
+				   next_id_eq(map, i, refid))))
+				ret = list_set_del(map, id, i);
+			else if (before < 0 &&
+				 elem->id == refid &&
+				 next_id_eq(map, i, id))
+				ret = list_set_del(map, id, i + 1);
+		}
+		break;
+	default:
+		break;
+	}
+
+finish:
+	if (refid != IPSET_INVALID_ID)
+		ip_set_put_byindex(refid);
+	if (adt != IPSET_ADD || ret)
+		ip_set_put_byindex(id);
+
+	return ip_set_eexist(ret, flags) ? 0 : ret;
+}
+
+static void
+list_set_flush(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+	struct set_elem *elem;
+	u32 i;
+
+	for (i = 0; i < map->size; i++) {
+		elem = list_set_elem(map, i);
+		if (elem->id != IPSET_INVALID_ID) {
+			ip_set_put_byindex(elem->id);
+			elem->id = IPSET_INVALID_ID;
+		}
+	}
+}
+
+static void
+list_set_destroy(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+
+	if (with_timeout(map->timeout))
+		del_timer_sync(&map->gc);
+	list_set_flush(set);
+	kfree(map);
+
+	set->data = NULL;
+}
+
+static int
+list_set_head(struct ip_set *set, struct sk_buff *skb)
+{
+	const struct list_set *map = set->data;
+	struct nlattr *nested;
+
+	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+	if (!nested)
+		goto nla_put_failure;
+	NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size));
+	if (with_timeout(map->timeout))
+		NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout));
+	NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES,
+		      htonl(atomic_read(&set->ref) - 1));
+	NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE,
+		      htonl(sizeof(*map) + map->size * map->dsize));
+	ipset_nest_end(skb, nested);
+
+	return 0;
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int
+list_set_list(const struct ip_set *set,
+	      struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct list_set *map = set->data;
+	struct nlattr *atd, *nested;
+	u32 i, first = cb->args[2];
+	const struct set_elem *e;
+
+	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	if (!atd)
+		return -EMSGSIZE;
+	for (; cb->args[2] < map->size; cb->args[2]++) {
+		i = cb->args[2];
+		e = list_set_elem(map, i);
+		if (e->id == IPSET_INVALID_ID)
+			goto finish;
+		if (with_timeout(map->timeout) && list_set_expired(map, i))
+			continue;
+		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+		if (!nested) {
+			if (i == first) {
+				nla_nest_cancel(skb, atd);
+				return -EMSGSIZE;
+			} else
+				goto nla_put_failure;
+		}
+		NLA_PUT_STRING(skb, IPSET_ATTR_NAME,
+			       ip_set_name_byindex(e->id));
+		if (with_timeout(map->timeout)) {
+			const struct set_telem *te =
+				(const struct set_telem *) e;
+			NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT,
+				      htonl(ip_set_timeout_get(te->timeout)));
+		}
+		ipset_nest_end(skb, nested);
+	}
+finish:
+	ipset_nest_end(skb, atd);
+	/* Set listing finished */
+	cb->args[2] = 0;
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nested);
+	ipset_nest_end(skb, atd);
+	if (unlikely(i == first)) {
+		cb->args[2] = 0;
+		return -EMSGSIZE;
+	}
+	return 0;
+}
+
+static bool
+list_set_same_set(const struct ip_set *a, const struct ip_set *b)
+{
+	const struct list_set *x = a->data;
+	const struct list_set *y = b->data;
+
+	return x->size == y->size &&
+	       x->timeout == y->timeout;
+}
+
+static const struct ip_set_type_variant list_set = {
+	.kadt	= list_set_kadt,
+	.uadt	= list_set_uadt,
+	.destroy = list_set_destroy,
+	.flush	= list_set_flush,
+	.head	= list_set_head,
+	.list	= list_set_list,
+	.same_set = list_set_same_set,
+};
+
+static void
+list_set_gc(unsigned long ul_set)
+{
+	struct ip_set *set = (struct ip_set *) ul_set;
+	struct list_set *map = set->data;
+	struct set_telem *e;
+	u32 i;
+
+	/* We run parallel with other readers (test element)
+	 * but adding/deleting new entries is locked out */
+	read_lock_bh(&set->lock);
+	for (i = map->size - 1; i >= 0; i--) {
+		e = (struct set_telem *) list_set_elem(map, i);
+		if (e->id != IPSET_INVALID_ID &&
+		    list_set_expired(map, i))
+			list_set_del(map, e->id, i);
+	}
+	read_unlock_bh(&set->lock);
+
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	add_timer(&map->gc);
+}
+
+static void
+list_set_gc_init(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+
+	init_timer(&map->gc);
+	map->gc.data = (unsigned long) set;
+	map->gc.function = list_set_gc;
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	add_timer(&map->gc);
+}
+
+/* Create list:set type of sets */
+
+static bool
+init_list_set(struct ip_set *set, u32 size, size_t dsize,
+	      unsigned long timeout)
+{
+	struct list_set *map;
+	struct set_elem *e;
+	u32 i;
+
+	map = kzalloc(sizeof(*map) + size * dsize, GFP_KERNEL);
+	if (!map)
+		return false;
+
+	map->size = size;
+	map->dsize = dsize;
+	map->timeout = timeout;
+	set->data = map;
+
+	for (i = 0; i < size; i++) {
+		e = list_set_elem(map, i);
+		e->id = IPSET_INVALID_ID;
+	}
+
+	return true;
+}
+
+static int
+list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+{
+	u32 size = IP_SET_LIST_DEFAULT_SIZE;
+
+	if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_SIZE])
+		size = ip_set_get_h32(tb[IPSET_ATTR_SIZE]);
+	if (size < IP_SET_LIST_MIN_SIZE)
+		size = IP_SET_LIST_MIN_SIZE;
+
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		if (!init_list_set(set, size, sizeof(struct set_telem),
+				   ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT])))
+			return -ENOMEM;
+
+		list_set_gc_init(set);
+	} else {
+		if (!init_list_set(set, size, sizeof(struct set_elem),
+				   IPSET_NO_TIMEOUT))
+			return -ENOMEM;
+	}
+	set->variant = &list_set;
+	return 0;
+}
+
+static struct ip_set_type list_set_type __read_mostly = {
+	.name		= "list:set",
+	.protocol	= IPSET_PROTOCOL,
+	.features	= IPSET_TYPE_NAME | IPSET_DUMP_LAST,
+	.dimension	= IPSET_DIM_ONE,
+	.family		= AF_UNSPEC,
+	.revision	= 0,
+	.create		= list_set_create,
+	.create_policy	= {
+		[IPSET_ATTR_SIZE]	= { .type = NLA_U32 },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+	},
+	.adt_policy	= {
+		[IPSET_ATTR_NAME]	= { .type = NLA_STRING,
+					    .len = IPSET_MAXNAMELEN },
+		[IPSET_ATTR_NAMEREF]	= { .type = NLA_STRING,
+					    .len = IPSET_MAXNAMELEN },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init
+list_set_init(void)
+{
+	return ip_set_type_register(&list_set_type);
+}
+
+static void __exit
+list_set_fini(void)
+{
+	ip_set_type_unregister(&list_set_type);
+}
+
+module_init(list_set_init);
+module_exit(list_set_fini);
-- 
cgit v1.2.3


From d956798d82d2d331c031301965d69e17a1a48a2b Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 1 Feb 2011 15:56:00 +0100
Subject: netfilter: xtables: "set" match and "SET" target support

The patch adds the combined module of the "SET" target and "set" match
to netfilter. Both the previous and the current revisions are supported.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_set.h |  55 ++++++
 net/netfilter/Kconfig            |  12 ++
 net/netfilter/Makefile           |   1 +
 net/netfilter/xt_set.c           | 359 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 427 insertions(+)
 create mode 100644 include/linux/netfilter/xt_set.h
 create mode 100644 net/netfilter/xt_set.c

(limited to 'include')

diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h
new file mode 100644
index 000000000000..69b2bd1fb818
--- /dev/null
+++ b/include/linux/netfilter/xt_set.h
@@ -0,0 +1,55 @@
+#ifndef _XT_SET_H
+#define _XT_SET_H
+
+#include <linux/netfilter/ipset/ip_set.h>
+
+/* Revision 0 interface: backward compatible with netfilter/iptables */
+
+/*
+ * Option flags for kernel operations (xt_set_info_v0)
+ */
+#define IPSET_SRC		0x01	/* Source match/add */
+#define IPSET_DST		0x02	/* Destination match/add */
+#define IPSET_MATCH_INV		0x04	/* Inverse matching */
+
+struct xt_set_info_v0 {
+	ip_set_id_t index;
+	union {
+		__u32 flags[IPSET_DIM_MAX + 1];
+		struct {
+			__u32 __flags[IPSET_DIM_MAX];
+			__u8 dim;
+			__u8 flags;
+		} compat;
+	} u;
+};
+
+/* match and target infos */
+struct xt_set_info_match_v0 {
+	struct xt_set_info_v0 match_set;
+};
+
+struct xt_set_info_target_v0 {
+	struct xt_set_info_v0 add_set;
+	struct xt_set_info_v0 del_set;
+};
+
+/* Revision 1: current interface to netfilter/iptables */
+
+struct xt_set_info {
+	ip_set_id_t index;
+	__u8 dim;
+	__u8 flags;
+};
+
+/* match and target infos */
+struct xt_set_info_match {
+	struct xt_set_info match_set;
+};
+
+struct xt_set_info_target {
+	struct xt_set_info add_set;
+	struct xt_set_info del_set;
+};
+
+#endif /*_XT_SET_H*/
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 351abf8ace13..06fa9e4e45c7 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -352,6 +352,18 @@ config NETFILTER_XT_CONNMARK
 	ctmark), similarly to the packet mark (nfmark). Using this
 	target and match, you can set and match on this mark.
 
+config NETFILTER_XT_SET
+	tristate 'set target and match support'
+	depends on IP_SET
+	depends on NETFILTER_ADVANCED
+	help
+	  This option adds the "SET" target and "set" match.
+
+	  Using this target and match, you can add/delete and match
+	  elements in the sets created by ipset(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 # alphabetically ordered list of targets
 
 comment "Xtables targets"
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 510b586ccb7f..1148643559cb 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
 # combos
 obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
+obj-$(CONFIG_NETFILTER_XT_SET) += xt_set.o
 
 # targets
 obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
new file mode 100644
index 000000000000..061d48cec137
--- /dev/null
+++ b/net/netfilter/xt_set.c
@@ -0,0 +1,359 @@
+/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
+ *                         Patrick Schaaf <bof@bof.de>
+ *                         Martin Josefsson <gandalf@wlug.westbo.se>
+ * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module which implements the set match and SET target
+ * for netfilter/iptables. */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/version.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_set.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
+MODULE_DESCRIPTION("Xtables: IP set match and target module");
+MODULE_ALIAS("xt_SET");
+MODULE_ALIAS("ipt_set");
+MODULE_ALIAS("ip6t_set");
+MODULE_ALIAS("ipt_SET");
+MODULE_ALIAS("ip6t_SET");
+
+static inline int
+match_set(ip_set_id_t index, const struct sk_buff *skb,
+	  u8 pf, u8 dim, u8 flags, int inv)
+{
+	if (ip_set_test(index, skb, pf, dim, flags))
+		inv = !inv;
+	return inv;
+}
+
+/* Revision 0 interface: backward compatible with netfilter/iptables */
+
+static bool
+set_match_v0(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_set_info_match_v0 *info = par->matchinfo;
+
+	return match_set(info->match_set.index, skb, par->family,
+			 info->match_set.u.compat.dim,
+			 info->match_set.u.compat.flags,
+			 info->match_set.u.compat.flags & IPSET_INV_MATCH);
+}
+
+static void
+compat_flags(struct xt_set_info_v0 *info)
+{
+	u_int8_t i;
+
+	/* Fill out compatibility data according to enum ip_set_kopt */
+	info->u.compat.dim = IPSET_DIM_ZERO;
+	if (info->u.flags[0] & IPSET_MATCH_INV)
+		info->u.compat.flags |= IPSET_INV_MATCH;
+	for (i = 0; i < IPSET_DIM_MAX-1 && info->u.flags[i]; i++) {
+		info->u.compat.dim++;
+		if (info->u.flags[i] & IPSET_SRC)
+			info->u.compat.flags |= (1<<info->u.compat.dim);
+	}
+}
+
+static int
+set_match_v0_checkentry(const struct xt_mtchk_param *par)
+{
+	struct xt_set_info_match_v0 *info = par->matchinfo;
+	ip_set_id_t index;
+
+	index = ip_set_nfnl_get_byindex(info->match_set.index);
+
+	if (index == IPSET_INVALID_ID) {
+		pr_warning("Cannot find set indentified by id %u to match\n",
+			   info->match_set.index);
+		return -ENOENT;
+	}
+	if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) {
+		pr_warning("Protocol error: set match dimension "
+			   "is over the limit!\n");
+		return -ERANGE;
+	}
+
+	/* Fill out compatibility data */
+	compat_flags(&info->match_set);
+
+	return 0;
+}
+
+static void
+set_match_v0_destroy(const struct xt_mtdtor_param *par)
+{
+	struct xt_set_info_match_v0 *info = par->matchinfo;
+
+	ip_set_nfnl_put(info->match_set.index);
+}
+
+static unsigned int
+set_target_v0(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct xt_set_info_target_v0 *info = par->targinfo;
+
+	if (info->add_set.index != IPSET_INVALID_ID)
+		ip_set_add(info->add_set.index, skb, par->family,
+			   info->add_set.u.compat.dim,
+			   info->add_set.u.compat.flags);
+	if (info->del_set.index != IPSET_INVALID_ID)
+		ip_set_del(info->del_set.index, skb, par->family,
+			   info->del_set.u.compat.dim,
+			   info->del_set.u.compat.flags);
+
+	return XT_CONTINUE;
+}
+
+static int
+set_target_v0_checkentry(const struct xt_tgchk_param *par)
+{
+	struct xt_set_info_target_v0 *info = par->targinfo;
+	ip_set_id_t index;
+
+	if (info->add_set.index != IPSET_INVALID_ID) {
+		index = ip_set_nfnl_get_byindex(info->add_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warning("Cannot find add_set index %u as target\n",
+				   info->add_set.index);
+			return -ENOENT;
+		}
+	}
+
+	if (info->del_set.index != IPSET_INVALID_ID) {
+		index = ip_set_nfnl_get_byindex(info->del_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warning("Cannot find del_set index %u as target\n",
+				   info->del_set.index);
+			return -ENOENT;
+		}
+	}
+	if (info->add_set.u.flags[IPSET_DIM_MAX-1] != 0 ||
+	    info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) {
+		pr_warning("Protocol error: SET target dimension "
+			   "is over the limit!\n");
+		return -ERANGE;
+	}
+
+	/* Fill out compatibility data */
+	compat_flags(&info->add_set);
+	compat_flags(&info->del_set);
+
+	return 0;
+}
+
+static void
+set_target_v0_destroy(const struct xt_tgdtor_param *par)
+{
+	const struct xt_set_info_target_v0 *info = par->targinfo;
+
+	if (info->add_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(info->add_set.index);
+	if (info->del_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(info->del_set.index);
+}
+
+/* Revision 1: current interface to netfilter/iptables */
+
+static bool
+set_match(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_set_info_match *info = par->matchinfo;
+
+	return match_set(info->match_set.index, skb, par->family,
+			 info->match_set.dim,
+			 info->match_set.flags,
+			 info->match_set.flags & IPSET_INV_MATCH);
+}
+
+static int
+set_match_checkentry(const struct xt_mtchk_param *par)
+{
+	struct xt_set_info_match *info = par->matchinfo;
+	ip_set_id_t index;
+
+	index = ip_set_nfnl_get_byindex(info->match_set.index);
+
+	if (index == IPSET_INVALID_ID) {
+		pr_warning("Cannot find set indentified by id %u to match\n",
+			   info->match_set.index);
+		return -ENOENT;
+	}
+	if (info->match_set.dim > IPSET_DIM_MAX) {
+		pr_warning("Protocol error: set match dimension "
+			   "is over the limit!\n");
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static void
+set_match_destroy(const struct xt_mtdtor_param *par)
+{
+	struct xt_set_info_match *info = par->matchinfo;
+
+	ip_set_nfnl_put(info->match_set.index);
+}
+
+static unsigned int
+set_target(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct xt_set_info_target *info = par->targinfo;
+
+	if (info->add_set.index != IPSET_INVALID_ID)
+		ip_set_add(info->add_set.index,
+			   skb, par->family,
+			   info->add_set.dim,
+			   info->add_set.flags);
+	if (info->del_set.index != IPSET_INVALID_ID)
+		ip_set_del(info->del_set.index,
+			   skb, par->family,
+			   info->add_set.dim,
+			   info->del_set.flags);
+
+	return XT_CONTINUE;
+}
+
+static int
+set_target_checkentry(const struct xt_tgchk_param *par)
+{
+	const struct xt_set_info_target *info = par->targinfo;
+	ip_set_id_t index;
+
+	if (info->add_set.index != IPSET_INVALID_ID) {
+		index = ip_set_nfnl_get_byindex(info->add_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warning("Cannot find add_set index %u as target\n",
+				   info->add_set.index);
+			return -ENOENT;
+		}
+	}
+
+	if (info->del_set.index != IPSET_INVALID_ID) {
+		index = ip_set_nfnl_get_byindex(info->del_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warning("Cannot find del_set index %u as target\n",
+				   info->del_set.index);
+			return -ENOENT;
+		}
+	}
+	if (info->add_set.dim > IPSET_DIM_MAX ||
+	    info->del_set.flags > IPSET_DIM_MAX) {
+		pr_warning("Protocol error: SET target dimension "
+			   "is over the limit!\n");
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static void
+set_target_destroy(const struct xt_tgdtor_param *par)
+{
+	const struct xt_set_info_target *info = par->targinfo;
+
+	if (info->add_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(info->add_set.index);
+	if (info->del_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(info->del_set.index);
+}
+
+static struct xt_match set_matches[] __read_mostly = {
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV4,
+		.revision	= 0,
+		.match		= set_match_v0,
+		.matchsize	= sizeof(struct xt_set_info_match_v0),
+		.checkentry	= set_match_v0_checkentry,
+		.destroy	= set_match_v0_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV4,
+		.revision	= 1,
+		.match		= set_match,
+		.matchsize	= sizeof(struct xt_set_info_match),
+		.checkentry	= set_match_checkentry,
+		.destroy	= set_match_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "set",
+		.family		= NFPROTO_IPV6,
+		.revision	= 1,
+		.match		= set_match,
+		.matchsize	= sizeof(struct xt_set_info_match),
+		.checkentry	= set_match_checkentry,
+		.destroy	= set_match_destroy,
+		.me		= THIS_MODULE
+	},
+};
+
+static struct xt_target set_targets[] __read_mostly = {
+	{
+		.name		= "SET",
+		.revision	= 0,
+		.family		= NFPROTO_IPV4,
+		.target		= set_target_v0,
+		.targetsize	= sizeof(struct xt_set_info_target_v0),
+		.checkentry	= set_target_v0_checkentry,
+		.destroy	= set_target_v0_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "SET",
+		.revision	= 1,
+		.family		= NFPROTO_IPV4,
+		.target		= set_target,
+		.targetsize	= sizeof(struct xt_set_info_target),
+		.checkentry	= set_target_checkentry,
+		.destroy	= set_target_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "SET",
+		.revision	= 1,
+		.family		= NFPROTO_IPV6,
+		.target		= set_target,
+		.targetsize	= sizeof(struct xt_set_info_target),
+		.checkentry	= set_target_checkentry,
+		.destroy	= set_target_destroy,
+		.me		= THIS_MODULE
+	},
+};
+
+static int __init xt_set_init(void)
+{
+	int ret = xt_register_matches(set_matches, ARRAY_SIZE(set_matches));
+
+	if (!ret) {
+		ret = xt_register_targets(set_targets,
+					  ARRAY_SIZE(set_targets));
+		if (ret)
+			xt_unregister_matches(set_matches,
+					      ARRAY_SIZE(set_matches));
+	}
+	return ret;
+}
+
+static void __exit xt_set_fini(void)
+{
+	xt_unregister_matches(set_matches, ARRAY_SIZE(set_matches));
+	xt_unregister_targets(set_targets, ARRAY_SIZE(set_targets));
+}
+
+module_init(xt_set_init);
+module_exit(xt_set_fini);
-- 
cgit v1.2.3


From 2a7dba391e5628ad665ce84ef9a6648da541ebab Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 1 Feb 2011 11:05:39 -0500
Subject: fs/vfs/security: pass last path component to LSM on inode creation

SELinux would like to implement a new labeling behavior of newly created
inodes.  We currently label new inodes based on the parent and the creating
process.  This new behavior would also take into account the name of the
new object when deciding the new label.  This is not the (supposed) full path,
just the last component of the path.

This is very useful because creating /etc/shadow is different than creating
/etc/passwd but the kernel hooks are unable to differentiate these
operations.  We currently require that userspace realize it is doing some
difficult operation like that and than userspace jumps through SELinux hoops
to get things set up correctly.  This patch does not implement new
behavior, that is obviously contained in a seperate SELinux patch, but it
does pass the needed name down to the correct LSM hook.  If no such name
exists it is fine to pass NULL.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 fs/btrfs/inode.c               | 13 +++++++------
 fs/btrfs/xattr.c               |  6 ++++--
 fs/btrfs/xattr.h               |  3 ++-
 fs/ext2/ext2.h                 |  2 +-
 fs/ext2/ialloc.c               |  5 +++--
 fs/ext2/namei.c                |  8 ++++----
 fs/ext2/xattr.h                |  6 ++++--
 fs/ext2/xattr_security.c       |  5 +++--
 fs/ext3/ialloc.c               |  5 +++--
 fs/ext3/namei.c                |  8 ++++----
 fs/ext3/xattr.h                |  4 ++--
 fs/ext3/xattr_security.c       |  5 +++--
 fs/ext4/ialloc.c               |  2 +-
 fs/ext4/xattr.h                |  4 ++--
 fs/ext4/xattr_security.c       |  5 +++--
 fs/gfs2/inode.c                |  7 ++++---
 fs/jffs2/dir.c                 |  9 ++++-----
 fs/jffs2/nodelist.h            |  2 +-
 fs/jffs2/security.c            |  5 +++--
 fs/jffs2/write.c               | 18 ++++++++++--------
 fs/jffs2/xattr.h               |  5 +++--
 fs/jfs/jfs_xattr.h             |  5 +++--
 fs/jfs/namei.c                 |  8 ++++----
 fs/jfs/xattr.c                 |  6 ++++--
 fs/ocfs2/namei.c               |  4 ++--
 fs/ocfs2/refcounttree.c        |  3 ++-
 fs/ocfs2/xattr.c               | 10 ++++++----
 fs/ocfs2/xattr.h               |  4 +++-
 fs/reiserfs/namei.c            |  9 +++++----
 fs/reiserfs/xattr_security.c   |  3 ++-
 fs/xfs/linux-2.6/xfs_iops.c    |  9 +++++----
 include/linux/ext3_fs.h        |  3 ++-
 include/linux/reiserfs_xattr.h |  2 ++
 include/linux/security.h       |  9 +++++++--
 mm/shmem.c                     |  9 +++++----
 security/capability.c          |  3 ++-
 security/security.c            |  6 ++++--
 security/selinux/hooks.c       |  5 +++--
 security/smack/smack_lsm.c     |  5 ++++-
 39 files changed, 136 insertions(+), 94 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a0ff46a47895..49c04bec6a9d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -90,13 +90,14 @@ static noinline int cow_file_range(struct inode *inode,
 				   unsigned long *nr_written, int unlock);
 
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
-				     struct inode *inode,  struct inode *dir)
+				     struct inode *inode,  struct inode *dir,
+				     const struct qstr *qstr)
 {
 	int err;
 
 	err = btrfs_init_acl(trans, inode, dir);
 	if (!err)
-		err = btrfs_xattr_security_init(trans, inode, dir);
+		err = btrfs_xattr_security_init(trans, inode, dir, qstr);
 	return err;
 }
 
@@ -4675,7 +4676,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		goto out_unlock;
 
-	err = btrfs_init_inode_security(trans, inode, dir);
+	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err) {
 		drop_inode = 1;
 		goto out_unlock;
@@ -4736,7 +4737,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		goto out_unlock;
 
-	err = btrfs_init_inode_security(trans, inode, dir);
+	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err) {
 		drop_inode = 1;
 		goto out_unlock;
@@ -4864,7 +4865,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
 	drop_on_err = 1;
 
-	err = btrfs_init_inode_security(trans, inode, dir);
+	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
 		goto out_fail;
 
@@ -6946,7 +6947,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		goto out_unlock;
 
-	err = btrfs_init_inode_security(trans, inode, dir);
+	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err) {
 		drop_inode = 1;
 		goto out_unlock;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 698fdd2c739c..3338a7e61d25 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -352,7 +352,8 @@ int btrfs_removexattr(struct dentry *dentry, const char *name)
 }
 
 int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
-			      struct inode *inode, struct inode *dir)
+			      struct inode *inode, struct inode *dir,
+			      const struct qstr *qstr)
 {
 	int err;
 	size_t len;
@@ -360,7 +361,8 @@ int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
 	char *suffix;
 	char *name;
 
-	err = security_inode_init_security(inode, dir, &suffix, &value, &len);
+	err = security_inode_init_security(inode, dir, qstr, &suffix, &value,
+					   &len);
 	if (err) {
 		if (err == -EOPNOTSUPP)
 			return 0;
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 7a43fd640bbb..b3cc8039134b 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -37,6 +37,7 @@ extern int btrfs_setxattr(struct dentry *dentry, const char *name,
 extern int btrfs_removexattr(struct dentry *dentry, const char *name);
 
 extern int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
-				     struct inode *inode, struct inode *dir);
+				     struct inode *inode, struct inode *dir,
+				     const struct qstr *qstr);
 
 #endif /* __XATTR__ */
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 6346a2acf326..1b48c3370872 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -110,7 +110,7 @@ extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
 extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int);
 
 /* ialloc.c */
-extern struct inode * ext2_new_inode (struct inode *, int);
+extern struct inode * ext2_new_inode (struct inode *, int, const struct qstr *);
 extern void ext2_free_inode (struct inode *);
 extern unsigned long ext2_count_free_inodes (struct super_block *);
 extern void ext2_check_inodes_bitmap (struct super_block *);
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index ad70479aabff..ee9ed31948e1 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -429,7 +429,8 @@ found:
 	return group;
 }
 
-struct inode *ext2_new_inode(struct inode *dir, int mode)
+struct inode *ext2_new_inode(struct inode *dir, int mode,
+			     const struct qstr *qstr)
 {
 	struct super_block *sb;
 	struct buffer_head *bitmap_bh = NULL;
@@ -585,7 +586,7 @@ got:
 	if (err)
 		goto fail_free_drop;
 
-	err = ext2_init_security(inode,dir);
+	err = ext2_init_security(inode, dir, qstr);
 	if (err)
 		goto fail_free_drop;
 
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index f8aecd2e3297..368d7049ac89 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -104,7 +104,7 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, int mode, st
 
 	dquot_initialize(dir);
 
-	inode = ext2_new_inode(dir, mode);
+	inode = ext2_new_inode(dir, mode, &dentry->d_name);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
@@ -133,7 +133,7 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, dev_
 
 	dquot_initialize(dir);
 
-	inode = ext2_new_inode (dir, mode);
+	inode = ext2_new_inode (dir, mode, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
@@ -159,7 +159,7 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry,
 
 	dquot_initialize(dir);
 
-	inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO);
+	inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out;
@@ -230,7 +230,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
 
 	inode_inc_link_count(dir);
 
-	inode = ext2_new_inode (dir, S_IFDIR | mode);
+	inode = ext2_new_inode(dir, S_IFDIR | mode, &dentry->d_name);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_dir;
diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h
index a1a1c2184616..5e41cccff762 100644
--- a/fs/ext2/xattr.h
+++ b/fs/ext2/xattr.h
@@ -116,9 +116,11 @@ exit_ext2_xattr(void)
 # endif  /* CONFIG_EXT2_FS_XATTR */
 
 #ifdef CONFIG_EXT2_FS_SECURITY
-extern int ext2_init_security(struct inode *inode, struct inode *dir);
+extern int ext2_init_security(struct inode *inode, struct inode *dir,
+			      const struct qstr *qstr);
 #else
-static inline int ext2_init_security(struct inode *inode, struct inode *dir)
+static inline int ext2_init_security(struct inode *inode, struct inode *dir,
+				     const struct qstr *qstr)
 {
 	return 0;
 }
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index 3004e15d5da5..5d979b4347b0 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -47,14 +47,15 @@ ext2_xattr_security_set(struct dentry *dentry, const char *name,
 }
 
 int
-ext2_init_security(struct inode *inode, struct inode *dir)
+ext2_init_security(struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
 {
 	int err;
 	size_t len;
 	void *value;
 	char *name;
 
-	err = security_inode_init_security(inode, dir, &name, &value, &len);
+	err = security_inode_init_security(inode, dir, qstr, &name, &value, &len);
 	if (err) {
 		if (err == -EOPNOTSUPP)
 			return 0;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 9724aef22460..bfc2dc43681d 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -404,7 +404,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent)
  * For other inodes, search forward from the parent directory's block
  * group to find a free inode.
  */
-struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
+struct inode *ext3_new_inode(handle_t *handle, struct inode * dir,
+			     const struct qstr *qstr, int mode)
 {
 	struct super_block *sb;
 	struct buffer_head *bitmap_bh = NULL;
@@ -589,7 +590,7 @@ got:
 	if (err)
 		goto fail_free_drop;
 
-	err = ext3_init_security(handle,inode, dir);
+	err = ext3_init_security(handle, inode, dir, qstr);
 	if (err)
 		goto fail_free_drop;
 
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index bce9dce639b8..a900033efcce 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1707,7 +1707,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext3_new_inode (handle, dir, mode);
+	inode = ext3_new_inode (handle, dir, &dentry->d_name, mode);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext3_file_inode_operations;
@@ -1743,7 +1743,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext3_new_inode (handle, dir, mode);
+	inode = ext3_new_inode (handle, dir, &dentry->d_name, mode);
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
@@ -1781,7 +1781,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext3_new_inode (handle, dir, S_IFDIR | mode);
+	inode = ext3_new_inode (handle, dir, &dentry->d_name, S_IFDIR | mode);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
@@ -2195,7 +2195,7 @@ retry:
 	if (IS_DIRSYNC(dir))
 		handle->h_sync = 1;
 
-	inode = ext3_new_inode (handle, dir, S_IFLNK|S_IRWXUGO);
+	inode = ext3_new_inode (handle, dir, &dentry->d_name, S_IFLNK|S_IRWXUGO);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
 		goto out_stop;
diff --git a/fs/ext3/xattr.h b/fs/ext3/xattr.h
index 377fe7201169..2be4f69bfa64 100644
--- a/fs/ext3/xattr.h
+++ b/fs/ext3/xattr.h
@@ -128,10 +128,10 @@ exit_ext3_xattr(void)
 
 #ifdef CONFIG_EXT3_FS_SECURITY
 extern int ext3_init_security(handle_t *handle, struct inode *inode,
-				struct inode *dir);
+			      struct inode *dir, const struct qstr *qstr);
 #else
 static inline int ext3_init_security(handle_t *handle, struct inode *inode,
-				struct inode *dir)
+				     struct inode *dir, const struct qstr *qstr)
 {
 	return 0;
 }
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 03a99bfc59f9..b8d9f83aa5c5 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -49,14 +49,15 @@ ext3_xattr_security_set(struct dentry *dentry, const char *name,
 }
 
 int
-ext3_init_security(handle_t *handle, struct inode *inode, struct inode *dir)
+ext3_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
 {
 	int err;
 	size_t len;
 	void *value;
 	char *name;
 
-	err = security_inode_init_security(inode, dir, &name, &value, &len);
+	err = security_inode_init_security(inode, dir, qstr, &name, &value, &len);
 	if (err) {
 		if (err == -EOPNOTSUPP)
 			return 0;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 1ce240a23ebb..49b6cfd1fc47 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1042,7 +1042,7 @@ got:
 	if (err)
 		goto fail_free_drop;
 
-	err = ext4_init_security(handle, inode, dir);
+	err = ext4_init_security(handle, inode, dir, qstr);
 	if (err)
 		goto fail_free_drop;
 
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 1ef16520b950..25b7387ff183 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -145,10 +145,10 @@ ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 
 #ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,
-				struct inode *dir);
+			      struct inode *dir, const struct qstr *qstr);
 #else
 static inline int ext4_init_security(handle_t *handle, struct inode *inode,
-				struct inode *dir)
+				     struct inode *dir, const struct qstr *qstr)
 {
 	return 0;
 }
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 9b21268e121c..007c3bfbf094 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -49,14 +49,15 @@ ext4_xattr_security_set(struct dentry *dentry, const char *name,
 }
 
 int
-ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir)
+ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
 {
 	int err;
 	size_t len;
 	void *value;
 	char *name;
 
-	err = security_inode_init_security(inode, dir, &name, &value, &len);
+	err = security_inode_init_security(inode, dir, qstr, &name, &value, &len);
 	if (err) {
 		if (err == -EOPNOTSUPP)
 			return 0;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 2232b3c780bd..de35ca7d7980 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -791,14 +791,15 @@ fail:
 	return error;
 }
 
-static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
+static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
+			      const struct qstr *qstr)
 {
 	int err;
 	size_t len;
 	void *value;
 	char *name;
 
-	err = security_inode_init_security(&ip->i_inode, &dip->i_inode,
+	err = security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
 					   &name, &value, &len);
 
 	if (err) {
@@ -882,7 +883,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 	if (error)
 		goto fail_gunlock2;
 
-	error = gfs2_security_init(dip, GFS2_I(inode));
+	error = gfs2_security_init(dip, GFS2_I(inode), name);
 	if (error)
 		goto fail_gunlock2;
 
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 92978658ed18..82faddd1f321 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -215,8 +215,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry, int mode,
 	   no chance of AB-BA deadlock involving its f->sem). */
 	mutex_unlock(&f->sem);
 
-	ret = jffs2_do_create(c, dir_f, f, ri,
-			      dentry->d_name.name, dentry->d_name.len);
+	ret = jffs2_do_create(c, dir_f, f, ri, &dentry->d_name);
 	if (ret)
 		goto fail;
 
@@ -386,7 +385,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 
 	jffs2_complete_reservation(c);
 
-	ret = jffs2_init_security(inode, dir_i);
+	ret = jffs2_init_security(inode, dir_i, &dentry->d_name);
 	if (ret)
 		goto fail;
 
@@ -530,7 +529,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode)
 
 	jffs2_complete_reservation(c);
 
-	ret = jffs2_init_security(inode, dir_i);
+	ret = jffs2_init_security(inode, dir_i, &dentry->d_name);
 	if (ret)
 		goto fail;
 
@@ -703,7 +702,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, int mode, de
 
 	jffs2_complete_reservation(c);
 
-	ret = jffs2_init_security(inode, dir_i);
+	ret = jffs2_init_security(inode, dir_i, &dentry->d_name);
 	if (ret)
 		goto fail;
 
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index 5a53d9bdb2b5..e4619b00f7c5 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -401,7 +401,7 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 			    struct jffs2_raw_inode *ri, unsigned char *buf,
 			    uint32_t offset, uint32_t writelen, uint32_t *retlen);
 int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f, struct jffs2_inode_info *f,
-		    struct jffs2_raw_inode *ri, const char *name, int namelen);
+		    struct jffs2_raw_inode *ri, const struct qstr *qstr);
 int jffs2_do_unlink(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f, const char *name,
 		    int namelen, struct jffs2_inode_info *dead_f, uint32_t time);
 int jffs2_do_link(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f, uint32_t ino,
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index 239f51216a68..cfeb7164b085 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -23,14 +23,15 @@
 #include "nodelist.h"
 
 /* ---- Initial Security Label Attachment -------------- */
-int jffs2_init_security(struct inode *inode, struct inode *dir)
+int jffs2_init_security(struct inode *inode, struct inode *dir,
+			const struct qstr *qstr)
 {
 	int rc;
 	size_t len;
 	void *value;
 	char *name;
 
-	rc = security_inode_init_security(inode, dir, &name, &value, &len);
+	rc = security_inode_init_security(inode, dir, qstr, &name, &value, &len);
 	if (rc) {
 		if (rc == -EOPNOTSUPP)
 			return 0;
diff --git a/fs/jffs2/write.c b/fs/jffs2/write.c
index c819eb0e982d..30d175b6d290 100644
--- a/fs/jffs2/write.c
+++ b/fs/jffs2/write.c
@@ -424,7 +424,9 @@ int jffs2_write_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 	return ret;
 }
 
-int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f, struct jffs2_inode_info *f, struct jffs2_raw_inode *ri, const char *name, int namelen)
+int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f,
+		    struct jffs2_inode_info *f, struct jffs2_raw_inode *ri,
+		    const struct qstr *qstr)
 {
 	struct jffs2_raw_dirent *rd;
 	struct jffs2_full_dnode *fn;
@@ -466,15 +468,15 @@ int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f, str
 	mutex_unlock(&f->sem);
 	jffs2_complete_reservation(c);
 
-	ret = jffs2_init_security(&f->vfs_inode, &dir_f->vfs_inode);
+	ret = jffs2_init_security(&f->vfs_inode, &dir_f->vfs_inode, qstr);
 	if (ret)
 		return ret;
 	ret = jffs2_init_acl_post(&f->vfs_inode);
 	if (ret)
 		return ret;
 
-	ret = jffs2_reserve_space(c, sizeof(*rd)+namelen, &alloclen,
-				ALLOC_NORMAL, JFFS2_SUMMARY_DIRENT_SIZE(namelen));
+	ret = jffs2_reserve_space(c, sizeof(*rd)+qstr->len, &alloclen,
+				ALLOC_NORMAL, JFFS2_SUMMARY_DIRENT_SIZE(qstr->len));
 
 	if (ret) {
 		/* Eep. */
@@ -493,19 +495,19 @@ int jffs2_do_create(struct jffs2_sb_info *c, struct jffs2_inode_info *dir_f, str
 
 	rd->magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
 	rd->nodetype = cpu_to_je16(JFFS2_NODETYPE_DIRENT);
-	rd->totlen = cpu_to_je32(sizeof(*rd) + namelen);
+	rd->totlen = cpu_to_je32(sizeof(*rd) + qstr->len);
 	rd->hdr_crc = cpu_to_je32(crc32(0, rd, sizeof(struct jffs2_unknown_node)-4));
 
 	rd->pino = cpu_to_je32(dir_f->inocache->ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = ri->ino;
 	rd->mctime = ri->ctime;
-	rd->nsize = namelen;
+	rd->nsize = qstr->len;
 	rd->type = DT_REG;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
-	rd->name_crc = cpu_to_je32(crc32(0, name, namelen));
+	rd->name_crc = cpu_to_je32(crc32(0, qstr->name, qstr->len));
 
-	fd = jffs2_write_dirent(c, dir_f, rd, name, namelen, ALLOC_NORMAL);
+	fd = jffs2_write_dirent(c, dir_f, rd, qstr->name, qstr->len, ALLOC_NORMAL);
 
 	jffs2_free_raw_dirent(rd);
 
diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h
index cf4f5759b42b..7be4beb306f3 100644
--- a/fs/jffs2/xattr.h
+++ b/fs/jffs2/xattr.h
@@ -121,10 +121,11 @@ extern ssize_t jffs2_listxattr(struct dentry *, char *, size_t);
 #endif /* CONFIG_JFFS2_FS_XATTR */
 
 #ifdef CONFIG_JFFS2_FS_SECURITY
-extern int jffs2_init_security(struct inode *inode, struct inode *dir);
+extern int jffs2_init_security(struct inode *inode, struct inode *dir,
+			       const struct qstr *qstr);
 extern const struct xattr_handler jffs2_security_xattr_handler;
 #else
-#define jffs2_init_security(inode,dir)	(0)
+#define jffs2_init_security(inode,dir,qstr)	(0)
 #endif /* CONFIG_JFFS2_FS_SECURITY */
 
 #endif /* _JFFS2_FS_XATTR_H_ */
diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h
index 88b6cc535bf2..e9e100fd7c09 100644
--- a/fs/jfs/jfs_xattr.h
+++ b/fs/jfs/jfs_xattr.h
@@ -62,10 +62,11 @@ extern ssize_t jfs_listxattr(struct dentry *, char *, size_t);
 extern int jfs_removexattr(struct dentry *, const char *);
 
 #ifdef CONFIG_JFS_SECURITY
-extern int jfs_init_security(tid_t, struct inode *, struct inode *);
+extern int jfs_init_security(tid_t, struct inode *, struct inode *,
+			     const struct qstr *);
 #else
 static inline int jfs_init_security(tid_t tid, struct inode *inode,
-				    struct inode *dir)
+				    struct inode *dir, const struct qstr *qstr)
 {
 	return 0;
 }
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 4414e3a42264..030b9174e416 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -115,7 +115,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, int mode,
 	if (rc)
 		goto out3;
 
-	rc = jfs_init_security(tid, ip, dip);
+	rc = jfs_init_security(tid, ip, dip, &dentry->d_name);
 	if (rc) {
 		txAbort(tid, 0);
 		goto out3;
@@ -253,7 +253,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode)
 	if (rc)
 		goto out3;
 
-	rc = jfs_init_security(tid, ip, dip);
+	rc = jfs_init_security(tid, ip, dip, &dentry->d_name);
 	if (rc) {
 		txAbort(tid, 0);
 		goto out3;
@@ -932,7 +932,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	mutex_lock_nested(&JFS_IP(dip)->commit_mutex, COMMIT_MUTEX_PARENT);
 	mutex_lock_nested(&JFS_IP(ip)->commit_mutex, COMMIT_MUTEX_CHILD);
 
-	rc = jfs_init_security(tid, ip, dip);
+	rc = jfs_init_security(tid, ip, dip, &dentry->d_name);
 	if (rc)
 		goto out3;
 
@@ -1395,7 +1395,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (rc)
 		goto out3;
 
-	rc = jfs_init_security(tid, ip, dir);
+	rc = jfs_init_security(tid, ip, dir, &dentry->d_name);
 	if (rc) {
 		txAbort(tid, 0);
 		goto out3;
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 2d7f165d0f1d..3fa4c32272df 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -1091,7 +1091,8 @@ int jfs_removexattr(struct dentry *dentry, const char *name)
 }
 
 #ifdef CONFIG_JFS_SECURITY
-int jfs_init_security(tid_t tid, struct inode *inode, struct inode *dir)
+int jfs_init_security(tid_t tid, struct inode *inode, struct inode *dir,
+		      const struct qstr *qstr)
 {
 	int rc;
 	size_t len;
@@ -1099,7 +1100,8 @@ int jfs_init_security(tid_t tid, struct inode *inode, struct inode *dir)
 	char *suffix;
 	char *name;
 
-	rc = security_inode_init_security(inode, dir, &suffix, &value, &len);
+	rc = security_inode_init_security(inode, dir, qstr, &suffix, &value,
+					  &len);
 	if (rc) {
 		if (rc == -EOPNOTSUPP)
 			return 0;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index d14cad6e2e41..bd8d6461a68b 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -294,7 +294,7 @@ static int ocfs2_mknod(struct inode *dir,
 	}
 
 	/* get security xattr */
-	status = ocfs2_init_security_get(inode, dir, &si);
+	status = ocfs2_init_security_get(inode, dir, &dentry->d_name, &si);
 	if (status) {
 		if (status == -EOPNOTSUPP)
 			si.enable = 0;
@@ -1665,7 +1665,7 @@ static int ocfs2_symlink(struct inode *dir,
 	}
 
 	/* get security xattr */
-	status = ocfs2_init_security_get(inode, dir, &si);
+	status = ocfs2_init_security_get(inode, dir, &dentry->d_name, &si);
 	if (status) {
 		if (status == -EOPNOTSUPP)
 			si.enable = 0;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index b5f9160e93e9..cd3f5b4832ef 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4325,7 +4325,8 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 
 	/* If the security isn't preserved, we need to re-initialize them. */
 	if (!preserve) {
-		error = ocfs2_init_security_and_acl(dir, new_orphan_inode);
+		error = ocfs2_init_security_and_acl(dir, new_orphan_inode,
+						    &new_dentry->d_name);
 		if (error)
 			mlog_errno(error);
 	}
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 67cd43914641..6bb602486c6b 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7185,7 +7185,8 @@ out:
  * must not hold any lock expect i_mutex.
  */
 int ocfs2_init_security_and_acl(struct inode *dir,
-				struct inode *inode)
+				struct inode *inode,
+				const struct qstr *qstr)
 {
 	int ret = 0;
 	struct buffer_head *dir_bh = NULL;
@@ -7193,7 +7194,7 @@ int ocfs2_init_security_and_acl(struct inode *dir,
 		.enable = 1,
 	};
 
-	ret = ocfs2_init_security_get(inode, dir, &si);
+	ret = ocfs2_init_security_get(inode, dir, qstr, &si);
 	if (!ret) {
 		ret = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY,
 				      si.name, si.value, si.value_len,
@@ -7261,13 +7262,14 @@ static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name,
 
 int ocfs2_init_security_get(struct inode *inode,
 			    struct inode *dir,
+			    const struct qstr *qstr,
 			    struct ocfs2_security_xattr_info *si)
 {
 	/* check whether ocfs2 support feature xattr */
 	if (!ocfs2_supports_xattr(OCFS2_SB(dir->i_sb)))
 		return -EOPNOTSUPP;
-	return security_inode_init_security(inode, dir, &si->name, &si->value,
-					    &si->value_len);
+	return security_inode_init_security(inode, dir, qstr, &si->name,
+					    &si->value, &si->value_len);
 }
 
 int ocfs2_init_security_set(handle_t *handle,
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index aa64bb37a65b..d63cfb72316b 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -57,6 +57,7 @@ int ocfs2_has_inline_xattr_value_outside(struct inode *inode,
 					 struct ocfs2_dinode *di);
 int ocfs2_xattr_remove(struct inode *, struct buffer_head *);
 int ocfs2_init_security_get(struct inode *, struct inode *,
+			    const struct qstr *,
 			    struct ocfs2_security_xattr_info *);
 int ocfs2_init_security_set(handle_t *, struct inode *,
 			    struct buffer_head *,
@@ -94,5 +95,6 @@ int ocfs2_reflink_xattrs(struct inode *old_inode,
 			 struct buffer_head *new_bh,
 			 bool preserve_security);
 int ocfs2_init_security_and_acl(struct inode *dir,
-				struct inode *inode);
+				struct inode *inode,
+				const struct qstr *qstr);
 #endif /* OCFS2_XATTR_H */
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index ba5f51ec3458..d5b22ed06779 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -593,7 +593,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	new_inode_init(inode, dir, mode);
 
 	jbegin_count += reiserfs_cache_default_acl(dir);
-	retval = reiserfs_security_init(dir, inode, &security);
+	retval = reiserfs_security_init(dir, inode, &dentry->d_name, &security);
 	if (retval < 0) {
 		drop_new_inode(inode);
 		return retval;
@@ -667,7 +667,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
 	new_inode_init(inode, dir, mode);
 
 	jbegin_count += reiserfs_cache_default_acl(dir);
-	retval = reiserfs_security_init(dir, inode, &security);
+	retval = reiserfs_security_init(dir, inode, &dentry->d_name, &security);
 	if (retval < 0) {
 		drop_new_inode(inode);
 		return retval;
@@ -747,7 +747,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	new_inode_init(inode, dir, mode);
 
 	jbegin_count += reiserfs_cache_default_acl(dir);
-	retval = reiserfs_security_init(dir, inode, &security);
+	retval = reiserfs_security_init(dir, inode, &dentry->d_name, &security);
 	if (retval < 0) {
 		drop_new_inode(inode);
 		return retval;
@@ -1032,7 +1032,8 @@ static int reiserfs_symlink(struct inode *parent_dir,
 	}
 	new_inode_init(inode, parent_dir, mode);
 
-	retval = reiserfs_security_init(parent_dir, inode, &security);
+	retval = reiserfs_security_init(parent_dir, inode, &dentry->d_name,
+					&security);
 	if (retval < 0) {
 		drop_new_inode(inode);
 		return retval;
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index 237c6928d3c6..ef66c18a9332 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -54,6 +54,7 @@ static size_t security_list(struct dentry *dentry, char *list, size_t list_len,
  * of blocks needed for the transaction. If successful, reiserfs_security
  * must be released using reiserfs_security_free when the caller is done. */
 int reiserfs_security_init(struct inode *dir, struct inode *inode,
+			   const struct qstr *qstr,
 			   struct reiserfs_security_handle *sec)
 {
 	int blocks = 0;
@@ -65,7 +66,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode,
 	if (IS_PRIVATE(dir))
 		return 0;
 
-	error = security_inode_init_security(inode, dir, &sec->name,
+	error = security_inode_init_security(inode, dir, qstr, &sec->name,
 					     &sec->value, &sec->length);
 	if (error) {
 		if (error == -EOPNOTSUPP)
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 94d5fd6a2973..d9298cf60266 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -103,7 +103,8 @@ xfs_mark_inode_dirty(
 STATIC int
 xfs_init_security(
 	struct inode	*inode,
-	struct inode	*dir)
+	struct inode	*dir,
+	const struct qstr *qstr)
 {
 	struct xfs_inode *ip = XFS_I(inode);
 	size_t		length;
@@ -111,7 +112,7 @@ xfs_init_security(
 	unsigned char	*name;
 	int		error;
 
-	error = security_inode_init_security(inode, dir, (char **)&name,
+	error = security_inode_init_security(inode, dir, qstr, (char **)&name,
 					     &value, &length);
 	if (error) {
 		if (error == -EOPNOTSUPP)
@@ -195,7 +196,7 @@ xfs_vn_mknod(
 
 	inode = VFS_I(ip);
 
-	error = xfs_init_security(inode, dir);
+	error = xfs_init_security(inode, dir, &dentry->d_name);
 	if (unlikely(error))
 		goto out_cleanup_inode;
 
@@ -368,7 +369,7 @@ xfs_vn_symlink(
 
 	inode = VFS_I(cip);
 
-	error = xfs_init_security(inode, dir);
+	error = xfs_init_security(inode, dir, &dentry->d_name);
 	if (unlikely(error))
 		goto out_cleanup_inode;
 
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 6ce1bca01724..87312a81daba 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -874,7 +874,8 @@ extern int ext3fs_dirhash(const char *name, int len, struct
 			  dx_hash_info *hinfo);
 
 /* ialloc.c */
-extern struct inode * ext3_new_inode (handle_t *, struct inode *, int);
+extern struct inode * ext3_new_inode (handle_t *, struct inode *,
+				      const struct qstr *, int);
 extern void ext3_free_inode (handle_t *, struct inode *);
 extern struct inode * ext3_orphan_get (struct super_block *, unsigned long);
 extern unsigned long ext3_count_free_inodes (struct super_block *);
diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h
index 3b94c91f20a6..6deef5dc95fb 100644
--- a/include/linux/reiserfs_xattr.h
+++ b/include/linux/reiserfs_xattr.h
@@ -63,6 +63,7 @@ extern const struct xattr_handler reiserfs_xattr_trusted_handler;
 extern const struct xattr_handler reiserfs_xattr_security_handler;
 #ifdef CONFIG_REISERFS_FS_SECURITY
 int reiserfs_security_init(struct inode *dir, struct inode *inode,
+			   const struct qstr *qstr,
 			   struct reiserfs_security_handle *sec);
 int reiserfs_security_write(struct reiserfs_transaction_handle *th,
 			    struct inode *inode,
@@ -130,6 +131,7 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
 #ifndef CONFIG_REISERFS_FS_SECURITY
 static inline int reiserfs_security_init(struct inode *dir,
 					 struct inode *inode,
+					 const struct qstr *qstr,
 					 struct reiserfs_security_handle *sec)
 {
 	return 0;
diff --git a/include/linux/security.h b/include/linux/security.h
index c642bb8b8f5a..05dd5a64aa76 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -25,6 +25,7 @@
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/binfmts.h>
+#include <linux/dcache.h>
 #include <linux/signal.h>
 #include <linux/resource.h>
 #include <linux/sem.h>
@@ -315,6 +316,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	then it should return -EOPNOTSUPP to skip this processing.
  *	@inode contains the inode structure of the newly created inode.
  *	@dir contains the inode structure of the parent directory.
+ *	@qstr contains the last path component of the new object
  *	@name will be set to the allocated name suffix (e.g. selinux).
  *	@value will be set to the allocated attribute value.
  *	@len will be set to the length of the value.
@@ -1435,7 +1437,8 @@ struct security_operations {
 	int (*inode_alloc_security) (struct inode *inode);
 	void (*inode_free_security) (struct inode *inode);
 	int (*inode_init_security) (struct inode *inode, struct inode *dir,
-				    char **name, void **value, size_t *len);
+				    const struct qstr *qstr, char **name,
+				    void **value, size_t *len);
 	int (*inode_create) (struct inode *dir,
 			     struct dentry *dentry, int mode);
 	int (*inode_link) (struct dentry *old_dentry,
@@ -1696,7 +1699,8 @@ int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts);
 int security_inode_alloc(struct inode *inode);
 void security_inode_free(struct inode *inode);
 int security_inode_init_security(struct inode *inode, struct inode *dir,
-				  char **name, void **value, size_t *len);
+				 const struct qstr *qstr, char **name,
+				 void **value, size_t *len);
 int security_inode_create(struct inode *dir, struct dentry *dentry, int mode);
 int security_inode_link(struct dentry *old_dentry, struct inode *dir,
 			 struct dentry *new_dentry);
@@ -2023,6 +2027,7 @@ static inline void security_inode_free(struct inode *inode)
 
 static inline int security_inode_init_security(struct inode *inode,
 						struct inode *dir,
+						const struct qstr *qstr,
 						char **name,
 						void **value,
 						size_t *len)
diff --git a/mm/shmem.c b/mm/shmem.c
index 5ee67c990602..7c9cdc6fe137 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1843,8 +1843,9 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 
 	inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);
 	if (inode) {
-		error = security_inode_init_security(inode, dir, NULL, NULL,
-						     NULL);
+		error = security_inode_init_security(inode, dir,
+						     &dentry->d_name, NULL,
+						     NULL, NULL);
 		if (error) {
 			if (error != -EOPNOTSUPP) {
 				iput(inode);
@@ -1983,8 +1984,8 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	if (!inode)
 		return -ENOSPC;
 
-	error = security_inode_init_security(inode, dir, NULL, NULL,
-					     NULL);
+	error = security_inode_init_security(inode, dir, &dentry->d_name, NULL,
+					     NULL, NULL);
 	if (error) {
 		if (error != -EOPNOTSUPP) {
 			iput(inode);
diff --git a/security/capability.c b/security/capability.c
index 2a5df2b7da83..383d14dc12ef 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -118,7 +118,8 @@ static void cap_inode_free_security(struct inode *inode)
 }
 
 static int cap_inode_init_security(struct inode *inode, struct inode *dir,
-				   char **name, void **value, size_t *len)
+				   const struct qstr *qstr, char **name,
+				   void **value, size_t *len)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/security/security.c b/security/security.c
index b84a89dd59c6..4830f36e1ab5 100644
--- a/security/security.c
+++ b/security/security.c
@@ -336,11 +336,13 @@ void security_inode_free(struct inode *inode)
 }
 
 int security_inode_init_security(struct inode *inode, struct inode *dir,
-				  char **name, void **value, size_t *len)
+				 const struct qstr *qstr, char **name,
+				 void **value, size_t *len)
 {
 	if (unlikely(IS_PRIVATE(inode)))
 		return -EOPNOTSUPP;
-	return security_ops->inode_init_security(inode, dir, name, value, len);
+	return security_ops->inode_init_security(inode, dir, qstr, name, value,
+						 len);
 }
 EXPORT_SYMBOL(security_inode_init_security);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index e276eb468536..099bbd07732f 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -39,6 +39,7 @@
 #include <linux/swap.h>
 #include <linux/spinlock.h>
 #include <linux/syscalls.h>
+#include <linux/dcache.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/namei.h>
@@ -2509,8 +2510,8 @@ static void selinux_inode_free_security(struct inode *inode)
 }
 
 static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
-				       char **name, void **value,
-				       size_t *len)
+				       const struct qstr *qstr, char **name,
+				       void **value, size_t *len)
 {
 	const struct task_security_struct *tsec = current_security();
 	struct inode_security_struct *dsec;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 123a499ded37..0c91a906b3f4 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -33,6 +33,7 @@
 #include <net/cipso_ipv4.h>
 #include <linux/audit.h>
 #include <linux/magic.h>
+#include <linux/dcache.h>
 #include "smack.h"
 
 #define task_security(task)	(task_cred_xxx((task), security))
@@ -501,6 +502,7 @@ static void smack_inode_free_security(struct inode *inode)
  * smack_inode_init_security - copy out the smack from an inode
  * @inode: the inode
  * @dir: unused
+ * @qstr: unused
  * @name: where to put the attribute name
  * @value: where to put the attribute value
  * @len: where to put the length of the attribute
@@ -508,7 +510,8 @@ static void smack_inode_free_security(struct inode *inode)
  * Returns 0 if it all works out, -ENOMEM if there's no memory
  */
 static int smack_inode_init_security(struct inode *inode, struct inode *dir,
-				     char **name, void **value, size_t *len)
+				     const struct qstr *qstr, char **name,
+				     void **value, size_t *len)
 {
 	char *isp = smk_of_inode(inode);
 	char *dsp = smk_of_inode(dir);
-- 
cgit v1.2.3


From 4916ca401e3051dad326ddd69765bd0e3f32fb9b Mon Sep 17 00:00:00 2001
From: Lucian Adrian Grijincu <lucian.grijincu@gmail.com>
Date: Tue, 1 Feb 2011 18:44:56 +0200
Subject: security: remove unused security_sysctl hook

The only user for this hook was selinux. sysctl routes every call
through /proc/sys/. Selinux and other security modules use the file
system checks for sysctl too, so no need for this hook any more.

Signed-off-by: Lucian Adrian Grijincu <lucian.grijincu@gmail.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/security.h | 13 -------------
 kernel/sysctl.c          |  5 -----
 security/capability.c    |  6 ------
 security/security.c      |  5 -----
 4 files changed, 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 05dd5a64aa76..14167f2eb35a 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1259,12 +1259,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@cap contains the capability <include/linux/capability.h>.
  *	@audit: Whether to write an audit message or not
  *	Return 0 if the capability is granted for @tsk.
- * @sysctl:
- *	Check permission before accessing the @table sysctl variable in the
- *	manner specified by @op.
- *	@table contains the ctl_table structure for the sysctl variable.
- *	@op contains the operation (001 = search, 002 = write, 004 = read).
- *	Return 0 if permission is granted.
  * @syslog:
  *	Check permission before accessing the kernel message ring or changing
  *	logging to the console.
@@ -1385,7 +1379,6 @@ struct security_operations {
 		       const kernel_cap_t *permitted);
 	int (*capable) (struct task_struct *tsk, const struct cred *cred,
 			int cap, int audit);
-	int (*sysctl) (struct ctl_table *table, int op);
 	int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
 	int (*quota_on) (struct dentry *dentry);
 	int (*syslog) (int type);
@@ -1668,7 +1661,6 @@ int security_capset(struct cred *new, const struct cred *old,
 int security_capable(int cap);
 int security_real_capable(struct task_struct *tsk, int cap);
 int security_real_capable_noaudit(struct task_struct *tsk, int cap);
-int security_sysctl(struct ctl_table *table, int op);
 int security_quotactl(int cmds, int type, int id, struct super_block *sb);
 int security_quota_on(struct dentry *dentry);
 int security_syslog(int type);
@@ -1887,11 +1879,6 @@ int security_real_capable_noaudit(struct task_struct *tsk, int cap)
 	return ret;
 }
 
-static inline int security_sysctl(struct ctl_table *table, int op)
-{
-	return 0;
-}
-
 static inline int security_quotactl(int cmds, int type, int id,
 				     struct super_block *sb)
 {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ae5cbb1e3ced..e24254c27eaf 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1691,13 +1691,8 @@ static int test_perm(int mode, int op)
 
 int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
 {
-	int error;
 	int mode;
 
-	error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
-	if (error)
-		return error;
-
 	if (root->permissions)
 		mode = root->permissions(root, current->nsproxy, table);
 	else
diff --git a/security/capability.c b/security/capability.c
index 383d14dc12ef..85b67c8632df 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -12,11 +12,6 @@
 
 #include <linux/security.h>
 
-static int cap_sysctl(ctl_table *table, int op)
-{
-	return 0;
-}
-
 static int cap_syslog(int type)
 {
 	return 0;
@@ -881,7 +876,6 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, capable);
 	set_to_cap_if_null(ops, quotactl);
 	set_to_cap_if_null(ops, quota_on);
-	set_to_cap_if_null(ops, sysctl);
 	set_to_cap_if_null(ops, syslog);
 	set_to_cap_if_null(ops, settime);
 	set_to_cap_if_null(ops, vm_enough_memory);
diff --git a/security/security.c b/security/security.c
index 4830f36e1ab5..8f28685ee0d9 100644
--- a/security/security.c
+++ b/security/security.c
@@ -182,11 +182,6 @@ int security_real_capable_noaudit(struct task_struct *tsk, int cap)
 	return ret;
 }
 
-int security_sysctl(struct ctl_table *table, int op)
-{
-	return security_ops->sysctl(table, op);
-}
-
 int security_quotactl(int cmds, int type, int id, struct super_block *sb)
 {
 	return security_ops->quotactl(cmds, type, id, sb);
-- 
cgit v1.2.3


From a13676476e289ba03a23e27df130c7f33ab00e2f Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Tue, 1 Feb 2011 18:27:51 +0100
Subject: IPVS: Remove unused variables

These variables are unused as a result of the recent netns work.

Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Tested-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/ip_vs.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b23bea62f708..5d75feadf4f4 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1109,8 +1109,6 @@ extern int ip_vs_icmp_xmit_v6
  *	we are loaded. Just set ip_vs_drop_rate to 'n' and
  *	we start to drop 1/rate of the packets
  */
-extern int ip_vs_drop_rate;
-extern int ip_vs_drop_counter;
 
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 {
-- 
cgit v1.2.3


From e3e241b2769b27669d05f0a05083acd21b4faa2c Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Tue, 1 Feb 2011 18:52:42 +0100
Subject: netfilter: ipset: install ipset related header files

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/Kbuild       | 3 +++
 include/linux/netfilter/ipset/Kbuild | 4 ++++
 include/linux/netfilter/xt_set.h     | 1 +
 3 files changed, 8 insertions(+)
 create mode 100644 include/linux/netfilter/ipset/Kbuild

(limited to 'include')

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 89c0d1e20d72..ba19544cce94 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -1,3 +1,5 @@
+header-y += ipset/
+
 header-y += nf_conntrack_common.h
 header-y += nf_conntrack_ftp.h
 header-y += nf_conntrack_sctp.h
@@ -55,6 +57,7 @@ header-y += xt_quota.h
 header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
+header-y += xt_set.h
 header-y += xt_sctp.h
 header-y += xt_socket.h
 header-y += xt_state.h
diff --git a/include/linux/netfilter/ipset/Kbuild b/include/linux/netfilter/ipset/Kbuild
new file mode 100644
index 000000000000..601fe71d34d5
--- /dev/null
+++ b/include/linux/netfilter/ipset/Kbuild
@@ -0,0 +1,4 @@
+header-y += ip_set.h
+header-y += ip_set_bitmap.h
+header-y += ip_set_hash.h
+header-y += ip_set_list.h
diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h
index 69b2bd1fb818..081f1ded2842 100644
--- a/include/linux/netfilter/xt_set.h
+++ b/include/linux/netfilter/xt_set.h
@@ -1,6 +1,7 @@
 #ifndef _XT_SET_H
 #define _XT_SET_H
 
+#include <linux/types.h>
 #include <linux/netfilter/ipset/ip_set.h>
 
 /* Revision 0 interface: backward compatible with netfilter/iptables */
-- 
cgit v1.2.3


From 5348ba85a02ffe80a8af33a524b6610966760d3d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Feb 2011 15:30:56 -0800
Subject: ipv4: Update some fib_hash centric interface names.

fib_hash_init() --> fib_trie_init()
fib_hash_table() --> fib_trie_table()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h    | 6 +++---
 net/ipv4/fib_frontend.c | 8 ++++----
 net/ipv4/fib_trie.c     | 5 ++---
 3 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 819d61ca25cb..08b46b8c3031 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -228,9 +228,9 @@ extern int fib_sync_up(struct net_device *dev);
 extern __be32  __fib_res_prefsrc(struct fib_result *res);
 extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res);
 
-/* Exported by fib_{hash|trie}.c */
-extern void fib_hash_init(void);
-extern struct fib_table *fib_hash_table(u32 id);
+/* Exported by fib_trie.c */
+extern void fib_trie_init(void);
+extern struct fib_table *fib_trie_table(u32 id);
 
 static inline void fib_combine_itag(u32 *itag, struct fib_result *res)
 {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 930768ba49af..2a49c061b34c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -51,11 +51,11 @@ static int __net_init fib4_rules_init(struct net *net)
 {
 	struct fib_table *local_table, *main_table;
 
-	local_table = fib_hash_table(RT_TABLE_LOCAL);
+	local_table = fib_trie_table(RT_TABLE_LOCAL);
 	if (local_table == NULL)
 		return -ENOMEM;
 
-	main_table  = fib_hash_table(RT_TABLE_MAIN);
+	main_table  = fib_trie_table(RT_TABLE_MAIN);
 	if (main_table == NULL)
 		goto fail;
 
@@ -82,7 +82,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	if (tb)
 		return tb;
 
-	tb = fib_hash_table(id);
+	tb = fib_trie_table(id);
 	if (!tb)
 		return NULL;
 	h = id & (FIB_TABLE_HASHSZ - 1);
@@ -1086,5 +1086,5 @@ void __init ip_fib_init(void)
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_hash_init();
+	fib_trie_init();
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 16d589c70a92..73cb98475ce6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1916,7 +1916,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	return skb->len;
 }
 
-void __init fib_hash_init(void)
+void __init fib_trie_init(void)
 {
 	fn_alias_kmem = kmem_cache_create("ip_fib_alias",
 					  sizeof(struct fib_alias),
@@ -1929,8 +1929,7 @@ void __init fib_hash_init(void)
 }
 
 
-/* Fix more generic FIB names for init later */
-struct fib_table *fib_hash_table(u32 id)
+struct fib_table *fib_trie_table(u32 id)
 {
 	struct fib_table *tb;
 	struct trie *t;
-- 
cgit v1.2.3


From 1e6d767924c74929c0cfe839ae8f37bcee9e544e Mon Sep 17 00:00:00 2001
From: Richard Cochran <richard.cochran@omicron.at>
Date: Tue, 1 Feb 2011 13:50:58 +0000
Subject: time: Correct the *settime* parameters

Both settimeofday() and clock_settime() promise with a 'const'
attribute not to alter the arguments passed in. This patch adds the
missing 'const' attribute into the various kernel functions
implementing these calls.

Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134417.545698637@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/char/mmtimer.c       | 2 +-
 include/linux/posix-timers.h | 5 +++--
 include/linux/security.h     | 9 +++++----
 include/linux/time.h         | 5 +++--
 kernel/posix-timers.c        | 4 ++--
 kernel/time.c                | 2 +-
 kernel/time/timekeeping.c    | 2 +-
 security/commoncap.c         | 2 +-
 security/security.c          | 2 +-
 9 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index e6d75627c6c8..ecd0082502ef 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -487,7 +487,7 @@ static int sgi_clock_get(clockid_t clockid, struct timespec *tp)
 	return 0;
 };
 
-static int sgi_clock_set(clockid_t clockid, struct timespec *tp)
+static int sgi_clock_set(const clockid_t clockid, const struct timespec *tp)
 {
 
 	u64 nsec;
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 3e23844a6990..b2c14cbd47a6 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -69,7 +69,8 @@ struct k_itimer {
 struct k_clock {
 	int res;		/* in nanoseconds */
 	int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
-	int (*clock_set) (const clockid_t which_clock, struct timespec * tp);
+	int (*clock_set) (const clockid_t which_clock,
+			  const struct timespec *tp);
 	int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
 	int (*timer_create) (struct k_itimer *timer);
 	int (*nsleep) (const clockid_t which_clock, int flags,
@@ -89,7 +90,7 @@ void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
 /* error handlers for timer_create, nanosleep and settime */
 int do_posix_clock_nonanosleep(const clockid_t, int flags, struct timespec *,
 			       struct timespec __user *);
-int do_posix_clock_nosettime(const clockid_t, struct timespec *tp);
+int do_posix_clock_nosettime(const clockid_t, const struct timespec *tp);
 
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
diff --git a/include/linux/security.h b/include/linux/security.h
index c642bb8b8f5a..c096aa6fca60 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -53,7 +53,7 @@ struct audit_krule;
  */
 extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
 		       int cap, int audit);
-extern int cap_settime(struct timespec *ts, struct timezone *tz);
+extern int cap_settime(const struct timespec *ts, const struct timezone *tz);
 extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode);
 extern int cap_ptrace_traceme(struct task_struct *parent);
 extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
@@ -1387,7 +1387,7 @@ struct security_operations {
 	int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
 	int (*quota_on) (struct dentry *dentry);
 	int (*syslog) (int type);
-	int (*settime) (struct timespec *ts, struct timezone *tz);
+	int (*settime) (const struct timespec *ts, const struct timezone *tz);
 	int (*vm_enough_memory) (struct mm_struct *mm, long pages);
 
 	int (*bprm_set_creds) (struct linux_binprm *bprm);
@@ -1669,7 +1669,7 @@ int security_sysctl(struct ctl_table *table, int op);
 int security_quotactl(int cmds, int type, int id, struct super_block *sb);
 int security_quota_on(struct dentry *dentry);
 int security_syslog(int type);
-int security_settime(struct timespec *ts, struct timezone *tz);
+int security_settime(const struct timespec *ts, const struct timezone *tz);
 int security_vm_enough_memory(long pages);
 int security_vm_enough_memory_mm(struct mm_struct *mm, long pages);
 int security_vm_enough_memory_kern(long pages);
@@ -1904,7 +1904,8 @@ static inline int security_syslog(int type)
 	return 0;
 }
 
-static inline int security_settime(struct timespec *ts, struct timezone *tz)
+static inline int security_settime(const struct timespec *ts,
+				   const struct timezone *tz)
 {
 	return cap_settime(ts, tz);
 }
diff --git a/include/linux/time.h b/include/linux/time.h
index 38c5206c2673..7c44e7778033 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -145,8 +145,9 @@ static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
 extern void do_gettimeofday(struct timeval *tv);
-extern int do_settimeofday(struct timespec *tv);
-extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
+extern int do_settimeofday(const struct timespec *tv);
+extern int do_sys_settimeofday(const struct timespec *tv,
+			       const struct timezone *tz);
 #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags);
 struct itimerval;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 93bd2eb2bc53..21b7ca205f38 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -192,7 +192,7 @@ static int common_clock_get(clockid_t which_clock, struct timespec *tp)
 }
 
 static inline int common_clock_set(const clockid_t which_clock,
-				   struct timespec *tp)
+				   const struct timespec *tp)
 {
 	return do_sys_settimeofday(tp, NULL);
 }
@@ -928,7 +928,7 @@ void exit_itimers(struct signal_struct *sig)
 }
 
 /* Not available / possible... functions */
-int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp)
+int do_posix_clock_nosettime(const clockid_t clockid, const struct timespec *tp)
 {
 	return -EINVAL;
 }
diff --git a/kernel/time.c b/kernel/time.c
index a31b51220ac6..5cb80533d8b5 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -150,7 +150,7 @@ static inline void warp_clock(void)
  * various programs will get confused when the clock gets warped.
  */
 
-int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
+int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
 {
 	static int firsttime = 1;
 	int error = 0;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 02c13a313d15..4f9f65b91323 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -353,7 +353,7 @@ EXPORT_SYMBOL(do_gettimeofday);
  *
  * Sets the time of day to the new time and update NTP and notify hrtimers
  */
-int do_settimeofday(struct timespec *tv)
+int do_settimeofday(const struct timespec *tv)
 {
 	struct timespec ts_delta;
 	unsigned long flags;
diff --git a/security/commoncap.c b/security/commoncap.c
index 64c2ed9c9015..dbfdaed4cc66 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -93,7 +93,7 @@ int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
  * Determine whether the current process may set the system clock and timezone
  * information, returning 0 if permission granted, -ve if denied.
  */
-int cap_settime(struct timespec *ts, struct timezone *tz)
+int cap_settime(const struct timespec *ts, const struct timezone *tz)
 {
 	if (!capable(CAP_SYS_TIME))
 		return -EPERM;
diff --git a/security/security.c b/security/security.c
index 739e40362f44..b995428f1c96 100644
--- a/security/security.c
+++ b/security/security.c
@@ -202,7 +202,7 @@ int security_syslog(int type)
 	return security_ops->syslog(type);
 }
 
-int security_settime(struct timespec *ts, struct timezone *tz)
+int security_settime(const struct timespec *ts, const struct timezone *tz)
 {
 	return security_ops->settime(ts, tz);
 }
-- 
cgit v1.2.3


From 1976945eeaab5fa461735a6225a82c3cf1e65d62 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Feb 2011 13:51:06 +0000
Subject: posix-timers: Introduce clock_posix_cpu

The CLOCK_DISPATCH() macro is a horrible magic. We call common
functions if a function pointer is not set. That's just backwards.

To support dynamic file decriptor based clocks we need to cleanup that
dispatch logic.

Create a k_clock struct clock_posix_cpu which has all the
posix-cpu-timer functions filled in. After the cleanup the functions
can be made static.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.841974553@linutronix.de>
---
 include/linux/posix-timers.h |  2 ++
 kernel/posix-cpu-timers.c    | 12 ++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index b2c14cbd47a6..1330ff331526 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -85,6 +85,8 @@ struct k_clock {
 			   struct itimerspec * cur_setting);
 };
 
+extern struct k_clock clock_posix_cpu;
+
 void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
 
 /* error handlers for timer_create, nanosleep and settime */
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 11b91dc0992b..816cd49a5ad9 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1604,6 +1604,18 @@ static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
 	return -EINVAL;
 }
 
+struct k_clock clock_posix_cpu = {
+	.clock_getres	= posix_cpu_clock_getres,
+	.clock_set	= posix_cpu_clock_set,
+	.clock_get	= posix_cpu_clock_get,
+	.timer_create	= posix_cpu_timer_create,
+	.nsleep		= posix_cpu_nsleep,
+	.nsleep_restart	= posix_cpu_nsleep_restart,
+	.timer_set	= posix_cpu_timer_set,
+	.timer_del	= posix_cpu_timer_del,
+	.timer_get	= posix_cpu_timer_get,
+};
+
 static __init int init_posix_cpu_timers(void)
 {
 	struct k_clock process = {
-- 
cgit v1.2.3


From a5cd2880106cb2c79b3fe24f1c53dadba6a542a0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Feb 2011 13:51:11 +0000
Subject: posix-timers: Convert clock_nanosleep to clockid_to_kclock()

Use the new kclock decoding function in clock_nanosleep and cleanup all
kclocks which use the default functions.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.034175556@linutronix.de>
---
 drivers/char/mmtimer.c       |  1 -
 include/linux/posix-timers.h |  2 --
 kernel/posix-timers.c        | 26 +++++++-------------------
 3 files changed, 7 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index fd51cd8ee063..262d10453cb8 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -768,7 +768,6 @@ static struct k_clock sgi_clock = {
 	.clock_set	= sgi_clock_set,
 	.clock_get	= sgi_clock_get,
 	.timer_create	= sgi_timer_create,
-	.nsleep		= do_posix_clock_nonanosleep,
 	.timer_set	= sgi_timer_set,
 	.timer_del	= sgi_timer_del,
 	.timer_get	= sgi_timer_get
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 1330ff331526..cd6da067bce1 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -90,8 +90,6 @@ extern struct k_clock clock_posix_cpu;
 void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
 
 /* error handlers for timer_create, nanosleep and settime */
-int do_posix_clock_nonanosleep(const clockid_t, int flags, struct timespec *,
-			       struct timespec __user *);
 int do_posix_clock_nosettime(const clockid_t, const struct timespec *tp);
 
 /* function to call to trigger timer event */
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 14b0a70ffb1e..ee69b216d5c3 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -216,12 +216,6 @@ static int no_timer_create(struct k_itimer *new_timer)
 	return -EOPNOTSUPP;
 }
 
-static int no_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *tsave, struct timespec __user *rmtp)
-{
-	return -EOPNOTSUPP;
-}
-
 /*
  * Return nonzero if we know a priori this clockid_t value is bogus.
  */
@@ -282,32 +276,31 @@ static __init int init_posix_timers(void)
 {
 	struct k_clock clock_realtime = {
 		.clock_getres	= hrtimer_get_res,
+		.nsleep		= common_nsleep,
 	};
 	struct k_clock clock_monotonic = {
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_ktime_get_ts,
 		.clock_set	= do_posix_clock_nosettime,
+		.nsleep		= common_nsleep,
 	};
 	struct k_clock clock_monotonic_raw = {
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_get_monotonic_raw,
 		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= no_timer_create,
-		.nsleep		= no_nsleep,
 	};
 	struct k_clock clock_realtime_coarse = {
 		.clock_getres	= posix_get_coarse_res,
 		.clock_get	= posix_get_realtime_coarse,
 		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= no_timer_create,
-		.nsleep		= no_nsleep,
 	};
 	struct k_clock clock_monotonic_coarse = {
 		.clock_getres	= posix_get_coarse_res,
 		.clock_get	= posix_get_monotonic_coarse,
 		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= no_timer_create,
-		.nsleep		= no_nsleep,
 	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
@@ -952,13 +945,6 @@ int do_posix_clock_nosettime(const clockid_t clockid, const struct timespec *tp)
 }
 EXPORT_SYMBOL_GPL(do_posix_clock_nosettime);
 
-int do_posix_clock_nonanosleep(const clockid_t clock, int flags,
-			       struct timespec *t, struct timespec __user *r)
-{
-	return -ENANOSLEEP_NOTSUP;
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep);
-
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
@@ -1023,10 +1009,13 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		const struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec t;
 
-	if (invalid_clockid(which_clock))
+	if (!kc)
 		return -EINVAL;
+	if (!kc->nsleep)
+		return -ENANOSLEEP_NOTSUP;
 
 	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
 		return -EFAULT;
@@ -1034,8 +1023,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!timespec_valid(&t))
 		return -EINVAL;
 
-	return CLOCK_DISPATCH(which_clock, nsleep,
-			      (which_clock, flags, &t, rmtp));
+	return kc->nsleep(which_clock, flags, &t, rmtp);
 }
 
 /*
-- 
cgit v1.2.3


From d608c18203a969e5d14572a9861c646d0bb66872 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Feb 2011 13:51:43 +0000
Subject: thread_info: Remove legacy arg0-3 from restart_block

posix timers were the last users of the legacy arg0-3 members of
restart_block. Remove the cruft.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.326209775@linutronix.de>
---
 include/linux/thread_info.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index c90696544176..20fc303947d3 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -18,9 +18,6 @@ struct compat_timespec;
 struct restart_block {
 	long (*fn)(struct restart_block *);
 	union {
-		struct {
-			unsigned long arg0, arg1, arg2, arg3;
-		};
 		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
 			u32 __user *uaddr;
-- 
cgit v1.2.3


From 26f9a4796af330173d790c8d2b5e2efcc489e755 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Feb 2011 13:51:48 +0000
Subject: posix-timers: Convert clock_settime to clockid_to_kclock()

Use the new kclock decoding function in clock_settime and cleanup all
kclocks which use the default functions. Rename the misnomed
common_clock_set() to posix_clock_realtime_set().

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.518851246@linutronix.de>
---
 include/linux/posix-timers.h |  3 ---
 kernel/posix-cpu-timers.c    |  2 --
 kernel/posix-timers.c        | 31 ++++++++++++-------------------
 3 files changed, 12 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index cd6da067bce1..4aaf0c5c7cea 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -89,9 +89,6 @@ extern struct k_clock clock_posix_cpu;
 
 void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
 
-/* error handlers for timer_create, nanosleep and settime */
-int do_posix_clock_nosettime(const clockid_t, const struct timespec *tp);
-
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
 
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 8dc4cd7faf89..504fbab10b82 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1604,7 +1604,6 @@ static __init int init_posix_cpu_timers(void)
 	struct k_clock process = {
 		.clock_getres	= process_cpu_clock_getres,
 		.clock_get	= process_cpu_clock_get,
-		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= process_cpu_timer_create,
 		.nsleep		= process_cpu_nsleep,
 		.nsleep_restart	= process_cpu_nsleep_restart,
@@ -1612,7 +1611,6 @@ static __init int init_posix_cpu_timers(void)
 	struct k_clock thread = {
 		.clock_getres	= thread_cpu_clock_getres,
 		.clock_get	= thread_cpu_clock_get,
-		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= thread_cpu_timer_create,
 	};
 	struct timespec ts;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 4762986814c8..49f358c37708 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -199,12 +199,6 @@ static int common_clock_get(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
-static inline int common_clock_set(const clockid_t which_clock,
-				   const struct timespec *tp)
-{
-	return do_sys_settimeofday(tp, NULL);
-}
-
 static int common_timer_create(struct k_itimer *new_timer)
 {
 	hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
@@ -232,6 +226,13 @@ static inline int invalid_clockid(const clockid_t which_clock)
 	return 1;
 }
 
+/* Set clock_realtime */
+static int posix_clock_realtime_set(const clockid_t which_clock,
+				    const struct timespec *tp)
+{
+	return do_sys_settimeofday(tp, NULL);
+}
+
 /*
  * Get monotonic time for posix timers
  */
@@ -276,32 +277,29 @@ static __init int init_posix_timers(void)
 {
 	struct k_clock clock_realtime = {
 		.clock_getres	= hrtimer_get_res,
+		.clock_set	= posix_clock_realtime_set,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
 	};
 	struct k_clock clock_monotonic = {
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_ktime_get_ts,
-		.clock_set	= do_posix_clock_nosettime,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
 	};
 	struct k_clock clock_monotonic_raw = {
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_get_monotonic_raw,
-		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= no_timer_create,
 	};
 	struct k_clock clock_realtime_coarse = {
 		.clock_getres	= posix_get_coarse_res,
 		.clock_get	= posix_get_realtime_coarse,
-		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= no_timer_create,
 	};
 	struct k_clock clock_monotonic_coarse = {
 		.clock_getres	= posix_get_coarse_res,
 		.clock_get	= posix_get_monotonic_coarse,
-		.clock_set	= do_posix_clock_nosettime,
 		.timer_create	= no_timer_create,
 	};
 
@@ -940,24 +938,19 @@ void exit_itimers(struct signal_struct *sig)
 	}
 }
 
-/* Not available / possible... functions */
-int do_posix_clock_nosettime(const clockid_t clockid, const struct timespec *tp)
-{
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(do_posix_clock_nosettime);
-
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
+	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec new_tp;
 
-	if (invalid_clockid(which_clock))
+	if (!kc || !kc->clock_set)
 		return -EINVAL;
+
 	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
 		return -EFAULT;
 
-	return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp));
+	return kc->clock_set(which_clock, &new_tp);
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
-- 
cgit v1.2.3


From ebaac757acae0431e2c79c00e09f1debdabbddd7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Feb 2011 13:51:56 +0000
Subject: posix-timers: Remove useless res field from k_clock

The res member of kclock is only used by mmtimer.c, but even there it
contains redundant information. Remove the field and fixup mmtimer.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.808714587@linutronix.de>
---
 drivers/char/mmtimer.c       | 5 ++---
 include/linux/posix-timers.h | 1 -
 kernel/posix-timers.c        | 2 --
 3 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index 141ffaeb976c..ff41eb3eec92 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -768,12 +768,11 @@ static int sgi_timer_set(struct k_itimer *timr, int flags,
 static int sgi_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
 	tp->tv_sec = 0;
-	tp->tv_nsec = sgi_clock.res;
+	tp->tv_nsec = sgi_clock_period;
 	return 0;
 }
 
 static struct k_clock sgi_clock = {
-	.res = 0,
 	.clock_set	= sgi_clock_set,
 	.clock_get	= sgi_clock_get,
 	.clock_getres	= sgi_clock_getres,
@@ -840,7 +839,7 @@ static int __init mmtimer_init(void)
 			(unsigned long) node);
 	}
 
-	sgi_clock_period = sgi_clock.res = NSEC_PER_SEC / sn_rtc_cycles_per_second;
+	sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second;
 	register_posix_clock(CLOCK_SGI_CYCLE, &sgi_clock);
 
 	printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION,
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 4aaf0c5c7cea..ef574d177fb6 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -67,7 +67,6 @@ struct k_itimer {
 };
 
 struct k_clock {
-	int res;		/* in nanoseconds */
 	int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
 	int (*clock_set) (const clockid_t which_clock,
 			  const struct timespec *tp);
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 748497fffd0f..f9142a99b5cb 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -204,8 +204,6 @@ static inline int invalid_clockid(const clockid_t which_clock)
 		return 1;
 	if (posix_clocks[which_clock].clock_getres != NULL)
 		return 0;
-	if (posix_clocks[which_clock].res != 0)
-		return 0;
 	return 1;
 }
 
-- 
cgit v1.2.3


From bc2c8ea483d73e95fc88f1fc9e7755180f89b892 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Feb 2011 13:52:12 +0000
Subject: posix-timers: Make posix-cpu-timers functions static

All functions are accessed via clock_posix_cpu now. So make them static.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.389755466@linutronix.de>
---
 include/linux/posix-timers.h | 12 ------------
 kernel/posix-cpu-timers.c    | 27 +++++++++++++++------------
 2 files changed, 15 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index ef574d177fb6..8206255a547c 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -91,18 +91,6 @@ void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
 
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *ts);
-int posix_cpu_timer_create(struct k_itimer *timer);
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp);
-long posix_cpu_nsleep_restart(struct restart_block *restart_block);
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-			struct itimerspec *new, struct itimerspec *old);
-int posix_cpu_timer_del(struct k_itimer *timer);
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp);
-
 void posix_cpu_timer_schedule(struct k_itimer *timer);
 
 void run_posix_cpu_timers(struct task_struct *task);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 504fbab10b82..609e187f43e7 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -176,7 +176,8 @@ static inline cputime_t virt_ticks(struct task_struct *p)
 	return p->utime;
 }
 
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
 	int error = check_clock(which_clock);
 	if (!error) {
@@ -194,7 +195,8 @@ int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 	return error;
 }
 
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
 {
 	/*
 	 * You can never reset a CPU clock, but we check for other errors
@@ -317,7 +319,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 }
 
 
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
 	int error = -EINVAL;
@@ -379,7 +381,7 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
  * This is called from sys_timer_create() and do_cpu_nanosleep() with the
  * new timer already all-zeros initialized.
  */
-int posix_cpu_timer_create(struct k_itimer *new_timer)
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
 {
 	int ret = 0;
 	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
@@ -425,7 +427,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_del(struct k_itimer *timer)
+static int posix_cpu_timer_del(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
@@ -665,8 +667,8 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-			struct itimerspec *new, struct itimerspec *old)
+static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+			       struct itimerspec *new, struct itimerspec *old)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	union cpu_time_count old_expires, new_expires, old_incr, val;
@@ -820,7 +822,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	return ret;
 }
 
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
 	union cpu_time_count now;
 	struct task_struct *p = timer->it.cpu.task;
@@ -1481,8 +1483,10 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 	return error;
 }
 
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
 	struct restart_block *restart_block =
 		&current_thread_info()->restart_block;
@@ -1517,7 +1521,7 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 	return error;
 }
 
-long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 {
 	clockid_t which_clock = restart_block->nanosleep.index;
 	struct timespec t;
@@ -1542,7 +1546,6 @@ long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 
 }
 
-
 #define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
 #define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
 
-- 
cgit v1.2.3


From c528f7c6c208f1fae6b4025957173dec045e5f21 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 1 Feb 2011 13:52:17 +0000
Subject: time: Introduce timekeeping_inject_offset

This adds a kernel-internal timekeeping interface to add or subtract
a fixed amount from CLOCK_REALTIME. This makes it so kernel users or
interfaces trying to do so do not have to read the time, then add an
offset and then call settimeofday(), which adds some extra error in
comparision to just simply adding the offset in the kernel timekeeping
core.

Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.584311693@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/time.h      |  1 +
 kernel/time/timekeeping.c | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index 7c44e7778033..379b9037b5b4 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -166,6 +166,7 @@ extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
 extern void timekeeping_leap_insert(int leapsecond);
+extern int timekeeping_inject_offset(struct timespec *ts);
 
 struct tms;
 extern void do_sys_times(struct tms *);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4f9f65b91323..6262c1d18397 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -387,6 +387,42 @@ int do_settimeofday(const struct timespec *tv)
 
 EXPORT_SYMBOL(do_settimeofday);
 
+
+/**
+ * timekeeping_inject_offset - Adds or subtracts from the current time.
+ * @tv:		pointer to the timespec variable containing the offset
+ *
+ * Adds or subtracts an offset value from the current time.
+ */
+int timekeeping_inject_offset(struct timespec *ts)
+{
+	unsigned long flags;
+
+	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+		return -EINVAL;
+
+	write_seqlock_irqsave(&xtime_lock, flags);
+
+	timekeeping_forward_now();
+
+	xtime = timespec_add(xtime, *ts);
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
+
+	timekeeper.ntp_error = 0;
+	ntp_clear();
+
+	update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+				timekeeper.mult);
+
+	write_sequnlock_irqrestore(&xtime_lock, flags);
+
+	/* signal hrtimers about time change */
+	clock_was_set();
+
+	return 0;
+}
+EXPORT_SYMBOL(timekeeping_inject_offset);
+
 /**
  * change_clocksource - Swaps clocksources if a new one is available
  *
-- 
cgit v1.2.3


From 094aa1881fdc1b8889b442eb3511b31f3ec2b762 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Tue, 1 Feb 2011 13:52:20 +0000
Subject: ntp: Add ADJ_SETOFFSET mode bit

This patch adds a new mode bit into the timex structure. When set, the bit
instructs the kernel to add the given time value to the current time.

Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134320.688829863@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timex.h |  3 ++-
 kernel/time/ntp.c     | 11 +++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/timex.h b/include/linux/timex.h
index d23999f9499d..aa60fe7b6ed6 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -73,7 +73,7 @@ struct timex {
 	long tolerance;		/* clock frequency tolerance (ppm)
 				 * (read only)
 				 */
-	struct timeval time;	/* (read only) */
+	struct timeval time;	/* (read only, except for ADJ_SETOFFSET) */
 	long tick;		/* (modified) usecs between clock ticks */
 
 	long ppsfreq;           /* pps frequency (scaled ppm) (ro) */
@@ -102,6 +102,7 @@ struct timex {
 #define ADJ_STATUS		0x0010	/* clock status */
 #define ADJ_TIMECONST		0x0020	/* pll time constant */
 #define ADJ_TAI			0x0080	/* set TAI offset */
+#define ADJ_SETOFFSET		0x0100  /* add 'time' to current time */
 #define ADJ_MICRO		0x1000	/* select microsecond resolution */
 #define ADJ_NANO		0x2000	/* select nanosecond resolution */
 #define ADJ_TICK		0x4000	/* tick value */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index ed8cfdf16983..5ac593267a26 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -648,6 +648,17 @@ int do_adjtimex(struct timex *txc)
 			hrtimer_cancel(&leap_timer);
 	}
 
+	if (txc->modes & ADJ_SETOFFSET) {
+		struct timespec delta;
+		if ((unsigned long)txc->time.tv_usec >= NSEC_PER_SEC)
+			return -EINVAL;
+		delta.tv_sec  = txc->time.tv_sec;
+		delta.tv_nsec = txc->time.tv_usec;
+		if (!(txc->modes & ADJ_NANO))
+			delta.tv_nsec *= 1000;
+		timekeeping_inject_offset(&delta);
+	}
+
 	getnstimeofday(&ts);
 
 	write_seqlock_irq(&xtime_lock);
-- 
cgit v1.2.3


From f1f1d5ebd10ffa4242bce7a90a56a222d6b7bc77 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Tue, 1 Feb 2011 13:52:26 +0000
Subject: posix-timers: Introduce a syscall for clock tuning.

A new syscall is introduced that allows tuning of a POSIX clock. The
new call, clock_adjtime, takes two parameters, the clock ID and a
pointer to a struct timex. Any ADJTIMEX(2) operation may be requested
via this system call, but various POSIX clocks may or may not support
tuning.

[ tglx: Adapted to the posix-timer cleanup series. Avoid copy_to_user
  	in the error case ]

Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134419.869804645@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/posix-timers.h |  2 ++
 include/linux/syscalls.h     |  2 ++
 kernel/compat.c              | 23 +++++++++++++++++++++++
 kernel/posix-timers.c        | 30 ++++++++++++++++++++++++++++++
 4 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 8206255a547c..79a1cea7f6ed 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -4,6 +4,7 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/sched.h>
+#include <linux/timex.h>
 
 union cpu_time_count {
 	cputime_t cpu;
@@ -71,6 +72,7 @@ struct k_clock {
 	int (*clock_set) (const clockid_t which_clock,
 			  const struct timespec *tp);
 	int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
+	int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
 	int (*timer_create) (struct k_itimer *timer);
 	int (*nsleep) (const clockid_t which_clock, int flags,
 		       struct timespec *, struct timespec __user *);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 18cd0684fc4e..bfacab921239 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -311,6 +311,8 @@ asmlinkage long sys_clock_settime(clockid_t which_clock,
 				const struct timespec __user *tp);
 asmlinkage long sys_clock_gettime(clockid_t which_clock,
 				struct timespec __user *tp);
+asmlinkage long sys_clock_adjtime(clockid_t which_clock,
+				struct timex __user *tx);
 asmlinkage long sys_clock_getres(clockid_t which_clock,
 				struct timespec __user *tp);
 asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
diff --git a/kernel/compat.c b/kernel/compat.c
index 449e853cf41d..38b1d2c1cbe8 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -675,6 +675,29 @@ long compat_sys_clock_gettime(clockid_t which_clock,
 	return err;
 }
 
+long compat_sys_clock_adjtime(clockid_t which_clock,
+		struct compat_timex __user *utp)
+{
+	struct timex txc;
+	mm_segment_t oldfs;
+	int err, ret;
+
+	err = compat_get_timex(&txc, utp);
+	if (err)
+		return err;
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc);
+	set_fs(oldfs);
+
+	err = compat_put_timex(utp, &txc);
+	if (err)
+		return err;
+
+	return ret;
+}
+
 long compat_sys_clock_getres(clockid_t which_clock,
 		struct compat_timespec __user *tp)
 {
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index a3fdfd4be0ec..5a5a4f1c0971 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -170,6 +170,12 @@ static int posix_clock_realtime_set(const clockid_t which_clock,
 	return do_sys_settimeofday(tp, NULL);
 }
 
+static int posix_clock_realtime_adj(const clockid_t which_clock,
+				    struct timex *t)
+{
+	return do_adjtimex(t);
+}
+
 /*
  * Get monotonic time for posix timers
  */
@@ -216,6 +222,7 @@ static __init int init_posix_timers(void)
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_clock_realtime_get,
 		.clock_set	= posix_clock_realtime_set,
+		.clock_adj	= posix_clock_realtime_adj,
 		.nsleep		= common_nsleep,
 		.nsleep_restart	= hrtimer_nanosleep_restart,
 		.timer_create	= common_timer_create,
@@ -948,6 +955,29 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 	return error;
 }
 
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+		struct timex __user *, utx)
+{
+	struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timex ktx;
+	int err;
+
+	if (!kc)
+		return -EINVAL;
+	if (!kc->clock_adj)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&ktx, utx, sizeof(ktx)))
+		return -EFAULT;
+
+	err = kc->clock_adj(which_clock, &ktx);
+
+	if (!err && copy_to_user(utx, &ktx, sizeof(ktx)))
+		return -EFAULT;
+
+	return err;
+}
+
 SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 		struct timespec __user *, tp)
 {
-- 
cgit v1.2.3


From 81e294cba2596f5f10848bbe19d98b344c2a2d5c Mon Sep 17 00:00:00 2001
From: Richard Cochran <richard.cochran@omicron.at>
Date: Tue, 1 Feb 2011 13:52:32 +0000
Subject: posix-timers: Add support for fd based clocks

Extend the negative clockids which are currently used by posix cpu
timers to encode the PID with a file descriptor based type which
encodes the fd in the upper bits.

Originally-from: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134420.062860200@linutronix.de>
---
 include/linux/posix-timers.h | 13 +++++++++++++
 kernel/posix-timers.c        |  2 +-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 79a1cea7f6ed..88b9256169f8 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -18,6 +18,17 @@ struct cpu_timer_list {
 	int firing;
 };
 
+/*
+ * Bit fields within a clockid:
+ *
+ * The most significant 29 bits hold either a pid or a file descriptor.
+ *
+ * Bit 2 indicates whether a cpu clock refers to a thread or a process.
+ *
+ * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
+ *
+ * A clockid is invalid if bits 2, 1, and 0 are all set.
+ */
 #define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
 #define CPUCLOCK_PERTHREAD(clock) \
 	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
@@ -29,6 +40,8 @@ struct cpu_timer_list {
 #define CPUCLOCK_VIRT		1
 #define CPUCLOCK_SCHED		2
 #define CPUCLOCK_MAX		3
+#define CLOCKFD			CPUCLOCK_MAX
+#define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
 
 #define MAKE_PROCESS_CPUCLOCK(pid, clock) \
 	((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 5a5a4f1c0971..df629d853a81 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -488,7 +488,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 static struct k_clock *clockid_to_kclock(const clockid_t id)
 {
 	if (id < 0)
-		return &clock_posix_cpu;
+		return (id & CLOCKFD_MASK) == CLOCKFD ? NULL : &clock_posix_cpu;
 
 	if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
 		return NULL;
-- 
cgit v1.2.3


From 527087374faa488776a789375a7d6ea74fda6f71 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 2 Feb 2011 12:10:09 +0100
Subject: posix-timers: Cleanup namespace

Rename register_posix_clock() to posix_timers_register_clock(). That's
what the function really does. As a side effect this cleans up the
posix_clock namespace for the upcoming dynamic posix_clock
infrastructure.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
Cc: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <alpine.LFD.2.00.1102021222240.31804@localhost6.localdomain6>
---
 drivers/char/mmtimer.c       |  2 +-
 include/linux/posix-timers.h |  2 +-
 kernel/posix-cpu-timers.c    |  4 ++--
 kernel/posix-timers.c        | 15 ++++++++-------
 4 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index ff41eb3eec92..33dc2298af73 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -840,7 +840,7 @@ static int __init mmtimer_init(void)
 	}
 
 	sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second;
-	register_posix_clock(CLOCK_SGI_CYCLE, &sgi_clock);
+	posix_timers_register_clock(CLOCK_SGI_CYCLE, &sgi_clock);
 
 	printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION,
 	       sn_rtc_cycles_per_second/(unsigned long)1E6);
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 88b9256169f8..9d6ffe2c92e5 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -101,7 +101,7 @@ struct k_clock {
 
 extern struct k_clock clock_posix_cpu;
 
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
+void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock);
 
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 609e187f43e7..67fea9d25d55 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1618,8 +1618,8 @@ static __init int init_posix_cpu_timers(void)
 	};
 	struct timespec ts;
 
-	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
-	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+	posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+	posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
 	cputime_to_timespec(cputime_one_jiffy, &ts);
 	onecputick = ts.tv_nsec;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index df629d853a81..af936fd37140 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -253,11 +253,11 @@ static __init int init_posix_timers(void)
 		.clock_get	= posix_get_monotonic_coarse,
 	};
 
-	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
-	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
-	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
-	register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
-	register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
+	posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
+	posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
@@ -433,7 +433,8 @@ static struct pid *good_sigevent(sigevent_t * event)
 	return task_pid(rtn);
 }
 
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
+void posix_timers_register_clock(const clockid_t clock_id,
+				 struct k_clock *new_clock)
 {
 	if ((unsigned) clock_id >= MAX_CLOCKS) {
 		printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
@@ -454,7 +455,7 @@ void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
 
 	posix_clocks[clock_id] = *new_clock;
 }
-EXPORT_SYMBOL_GPL(register_posix_clock);
+EXPORT_SYMBOL_GPL(posix_timers_register_clock);
 
 static struct k_itimer * alloc_posix_timer(void)
 {
-- 
cgit v1.2.3


From 0606f422b453f76c31ab2b1bd52943ff06a2dcf2 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Tue, 1 Feb 2011 13:52:35 +0000
Subject: posix clocks: Introduce dynamic clocks

This patch adds support for adding and removing posix clocks. The
clock lifetime cycle is patterned after usb devices. Each clock is
represented by a standard character device. In addition, the driver
may optionally implement custom character device operations.

The posix clock and timer system calls listed below now work with
dynamic posix clocks, as well as the traditional static clocks.
The following system calls are affected:

   - clock_adjtime (brand new syscall)
   - clock_gettime
   - clock_getres
   - clock_settime
   - timer_create
   - timer_delete
   - timer_gettime
   - timer_settime

[ tglx: Adapted to the posix-timer cleanup. Moved clock_posix_dynamic
  	to posix-clock.c and made all referenced functions static ]

Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134420.164172635@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/posix-clock.h  | 150 +++++++++++++++
 include/linux/posix-timers.h |   6 +-
 kernel/posix-timers.c        |   4 +-
 kernel/time/Makefile         |   3 +-
 kernel/time/posix-clock.c    | 441 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 601 insertions(+), 3 deletions(-)
 create mode 100644 include/linux/posix-clock.h
 create mode 100644 kernel/time/posix-clock.c

(limited to 'include')

diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
new file mode 100644
index 000000000000..369e19d3750b
--- /dev/null
+++ b/include/linux/posix-clock.h
@@ -0,0 +1,150 @@
+/*
+ * posix-clock.h - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef _LINUX_POSIX_CLOCK_H_
+#define _LINUX_POSIX_CLOCK_H_
+
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/posix-timers.h>
+
+struct posix_clock;
+
+/**
+ * struct posix_clock_operations - functional interface to the clock
+ *
+ * Every posix clock is represented by a character device. Drivers may
+ * optionally offer extended capabilities by implementing the
+ * character device methods. The character device file operations are
+ * first handled by the clock device layer, then passed on to the
+ * driver by calling these functions.
+ *
+ * @owner:          The clock driver should set to THIS_MODULE
+ * @clock_adjtime:  Adjust the clock
+ * @clock_gettime:  Read the current time
+ * @clock_getres:   Get the clock resolution
+ * @clock_settime:  Set the current time value
+ * @timer_create:   Create a new timer
+ * @timer_delete:   Remove a previously created timer
+ * @timer_gettime:  Get remaining time and interval of a timer
+ * @timer_setttime: Set a timer's initial expiration and interval
+ * @fasync:         Optional character device fasync method
+ * @mmap:           Optional character device mmap method
+ * @open:           Optional character device open method
+ * @release:        Optional character device release method
+ * @ioctl:          Optional character device ioctl method
+ * @read:           Optional character device read method
+ * @poll:           Optional character device poll method
+ */
+struct posix_clock_operations {
+	struct module *owner;
+
+	int  (*clock_adjtime)(struct posix_clock *pc, struct timex *tx);
+
+	int  (*clock_gettime)(struct posix_clock *pc, struct timespec *ts);
+
+	int  (*clock_getres) (struct posix_clock *pc, struct timespec *ts);
+
+	int  (*clock_settime)(struct posix_clock *pc,
+			      const struct timespec *ts);
+
+	int  (*timer_create) (struct posix_clock *pc, struct k_itimer *kit);
+
+	int  (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit);
+
+	void (*timer_gettime)(struct posix_clock *pc,
+			      struct k_itimer *kit, struct itimerspec *tsp);
+
+	int  (*timer_settime)(struct posix_clock *pc,
+			      struct k_itimer *kit, int flags,
+			      struct itimerspec *tsp, struct itimerspec *old);
+	/*
+	 * Optional character device methods:
+	 */
+	int     (*fasync)  (struct posix_clock *pc,
+			    int fd, struct file *file, int on);
+
+	long    (*ioctl)   (struct posix_clock *pc,
+			    unsigned int cmd, unsigned long arg);
+
+	int     (*mmap)    (struct posix_clock *pc,
+			    struct vm_area_struct *vma);
+
+	int     (*open)    (struct posix_clock *pc, fmode_t f_mode);
+
+	uint    (*poll)    (struct posix_clock *pc,
+			    struct file *file, poll_table *wait);
+
+	int     (*release) (struct posix_clock *pc);
+
+	ssize_t (*read)    (struct posix_clock *pc,
+			    uint flags, char __user *buf, size_t cnt);
+};
+
+/**
+ * struct posix_clock - represents a dynamic posix clock
+ *
+ * @ops:     Functional interface to the clock
+ * @cdev:    Character device instance for this clock
+ * @kref:    Reference count.
+ * @mutex:   Protects the 'zombie' field from concurrent access.
+ * @zombie:  If 'zombie' is true, then the hardware has disappeared.
+ * @release: A function to free the structure when the reference count reaches
+ *           zero. May be NULL if structure is statically allocated.
+ *
+ * Drivers should embed their struct posix_clock within a private
+ * structure, obtaining a reference to it during callbacks using
+ * container_of().
+ */
+struct posix_clock {
+	struct posix_clock_operations ops;
+	struct cdev cdev;
+	struct kref kref;
+	struct mutex mutex;
+	bool zombie;
+	void (*release)(struct posix_clock *clk);
+};
+
+/**
+ * posix_clock_register() - register a new clock
+ * @clk:   Pointer to the clock. Caller must provide 'ops' and 'release'
+ * @devid: Allocated device id
+ *
+ * A clock driver calls this function to register itself with the
+ * clock device subsystem. If 'clk' points to dynamically allocated
+ * memory, then the caller must provide a 'release' function to free
+ * that memory.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+int posix_clock_register(struct posix_clock *clk, dev_t devid);
+
+/**
+ * posix_clock_unregister() - unregister a clock
+ * @clk: Clock instance previously registered via posix_clock_register()
+ *
+ * A clock driver calls this function to remove itself from the clock
+ * device subsystem. The posix_clock itself will remain (in an
+ * inactive state) until its reference count drops to zero, at which
+ * point it will be deallocated with its 'release' method.
+ */
+void posix_clock_unregister(struct posix_clock *clk);
+
+#endif
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 9d6ffe2c92e5..d51243ae0726 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -32,7 +32,7 @@ struct cpu_timer_list {
 #define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
 #define CPUCLOCK_PERTHREAD(clock) \
 	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
-#define CPUCLOCK_PID_MASK	7
+
 #define CPUCLOCK_PERTHREAD_MASK	4
 #define CPUCLOCK_WHICH(clock)	((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
 #define CPUCLOCK_CLOCK_MASK	3
@@ -48,6 +48,9 @@ struct cpu_timer_list {
 #define MAKE_THREAD_CPUCLOCK(tid, clock) \
 	MAKE_PROCESS_CPUCLOCK((tid), (clock) | CPUCLOCK_PERTHREAD_MASK)
 
+#define FD_TO_CLOCKID(fd)	((~(clockid_t) (fd) << 3) | CLOCKFD)
+#define CLOCKID_TO_FD(clk)	((unsigned int) ~((clk) >> 3))
+
 /* POSIX.1b interval timer structure. */
 struct k_itimer {
 	struct list_head list;		/* free/ allocate list */
@@ -100,6 +103,7 @@ struct k_clock {
 };
 
 extern struct k_clock clock_posix_cpu;
+extern struct k_clock clock_posix_dynamic;
 
 void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock);
 
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index af936fd37140..44fcff131b38 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -41,6 +41,7 @@
 #include <linux/init.h>
 #include <linux/compiler.h>
 #include <linux/idr.h>
+#include <linux/posix-clock.h>
 #include <linux/posix-timers.h>
 #include <linux/syscalls.h>
 #include <linux/wait.h>
@@ -489,7 +490,8 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 static struct k_clock *clockid_to_kclock(const clockid_t id)
 {
 	if (id < 0)
-		return (id & CLOCKFD_MASK) == CLOCKFD ? NULL : &clock_posix_cpu;
+		return (id & CLOCKFD_MASK) == CLOCKFD ?
+			&clock_posix_dynamic : &clock_posix_cpu;
 
 	if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
 		return NULL;
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ee266620b06c..b0425991e9ac 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,5 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timeconv.o posix-clock.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
new file mode 100644
index 000000000000..04498cbf6002
--- /dev/null
+++ b/kernel/time/posix-clock.c
@@ -0,0 +1,441 @@
+/*
+ * posix-clock.c - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/mutex.h>
+#include <linux/posix-clock.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+static void delete_clock(struct kref *kref);
+
+/*
+ * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
+ */
+static struct posix_clock *get_posix_clock(struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+
+	mutex_lock(&clk->mutex);
+
+	if (!clk->zombie)
+		return clk;
+
+	mutex_unlock(&clk->mutex);
+
+	return NULL;
+}
+
+static void put_posix_clock(struct posix_clock *clk)
+{
+	mutex_unlock(&clk->mutex);
+}
+
+static ssize_t posix_clock_read(struct file *fp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -EINVAL;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.read)
+		err = clk->ops.read(clk, fp->f_flags, buf, count);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int result = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.poll)
+		result = clk->ops.poll(clk, fp, wait);
+
+	put_posix_clock(clk);
+
+	return result;
+}
+
+static int posix_clock_fasync(int fd, struct file *fp, int on)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = 0;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.fasync)
+		err = clk->ops.fasync(clk, fd, fp, on);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static int posix_clock_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENODEV;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.mmap)
+		err = clk->ops.mmap(clk, vma);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static long posix_clock_ioctl(struct file *fp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+static long posix_clock_compat_ioctl(struct file *fp,
+				     unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(clk, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+#endif
+
+static int posix_clock_open(struct inode *inode, struct file *fp)
+{
+	int err;
+	struct posix_clock *clk =
+		container_of(inode->i_cdev, struct posix_clock, cdev);
+
+	mutex_lock(&clk->mutex);
+
+	if (clk->zombie) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (clk->ops.open)
+		err = clk->ops.open(clk, fp->f_mode);
+	else
+		err = 0;
+
+	if (!err) {
+		kref_get(&clk->kref);
+		fp->private_data = clk;
+	}
+out:
+	mutex_unlock(&clk->mutex);
+	return err;
+}
+
+static int posix_clock_release(struct inode *inode, struct file *fp)
+{
+	struct posix_clock *clk = fp->private_data;
+	int err = 0;
+
+	if (clk->ops.release)
+		err = clk->ops.release(clk);
+
+	kref_put(&clk->kref, delete_clock);
+
+	fp->private_data = NULL;
+
+	return err;
+}
+
+static const struct file_operations posix_clock_file_operations = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= posix_clock_read,
+	.poll		= posix_clock_poll,
+	.unlocked_ioctl	= posix_clock_ioctl,
+	.open		= posix_clock_open,
+	.release	= posix_clock_release,
+	.fasync		= posix_clock_fasync,
+	.mmap		= posix_clock_mmap,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= posix_clock_compat_ioctl,
+#endif
+};
+
+int posix_clock_register(struct posix_clock *clk, dev_t devid)
+{
+	int err;
+
+	kref_init(&clk->kref);
+	mutex_init(&clk->mutex);
+
+	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	clk->cdev.owner = clk->ops.owner;
+	err = cdev_add(&clk->cdev, devid, 1);
+	if (err)
+		goto no_cdev;
+
+	return err;
+no_cdev:
+	mutex_destroy(&clk->mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(posix_clock_register);
+
+static void delete_clock(struct kref *kref)
+{
+	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
+	mutex_destroy(&clk->mutex);
+	if (clk->release)
+		clk->release(clk);
+}
+
+void posix_clock_unregister(struct posix_clock *clk)
+{
+	cdev_del(&clk->cdev);
+
+	mutex_lock(&clk->mutex);
+	clk->zombie = true;
+	mutex_unlock(&clk->mutex);
+
+	kref_put(&clk->kref, delete_clock);
+}
+EXPORT_SYMBOL_GPL(posix_clock_unregister);
+
+struct posix_clock_desc {
+	struct file *fp;
+	struct posix_clock *clk;
+};
+
+static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
+{
+	struct file *fp = fget(CLOCKID_TO_FD(id));
+	int err = -EINVAL;
+
+	if (!fp)
+		return err;
+
+	if (fp->f_op->open != posix_clock_open || !fp->private_data)
+		goto out;
+
+	cd->fp = fp;
+	cd->clk = get_posix_clock(fp);
+
+	err = cd->clk ? 0 : -ENODEV;
+out:
+	if (err)
+		fput(fp);
+	return err;
+}
+
+static void put_clock_desc(struct posix_clock_desc *cd)
+{
+	put_posix_clock(cd->clk);
+	fput(cd->fp);
+}
+
+static int pc_clock_adjtime(clockid_t id, struct timex *tx)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_adjtime)
+		err = cd.clk->ops.clock_adjtime(cd.clk, tx);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_gettime)
+		err = cd.clk->ops.clock_gettime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_getres(clockid_t id, struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_getres)
+		err = cd.clk->ops.clock_getres(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_settime)
+		err = cd.clk->ops.clock_settime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_create(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_create)
+		err = cd.clk->ops.timer_create(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_timer_delete(struct k_itimer *kit)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_delete)
+		err = cd.clk->ops.timer_delete(cd.clk, kit);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+
+	if (get_clock_desc(id, &cd))
+		return;
+
+	if (cd.clk->ops.timer_gettime)
+		cd.clk->ops.timer_gettime(cd.clk, kit, ts);
+
+	put_clock_desc(&cd);
+}
+
+static int pc_timer_settime(struct k_itimer *kit, int flags,
+			    struct itimerspec *ts, struct itimerspec *old)
+{
+	clockid_t id = kit->it_clock;
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.timer_settime)
+		err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+struct k_clock clock_posix_dynamic = {
+	.clock_getres	= pc_clock_getres,
+	.clock_set	= pc_clock_settime,
+	.clock_get	= pc_clock_gettime,
+	.clock_adj	= pc_clock_adjtime,
+	.timer_create	= pc_timer_create,
+	.timer_set	= pc_timer_settime,
+	.timer_del	= pc_timer_delete,
+	.timer_get	= pc_timer_gettime,
+};
-- 
cgit v1.2.3


From 724bab476bcac9f7d0b5204cb06e346216d42166 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Wed, 2 Feb 2011 23:50:01 +0100
Subject: netfilter: ipset: fix linking with CONFIG_IPV6=n

Add a dummy ip_set_get_ip6_port function that unconditionally
returns false for CONFIG_IPV6=n and convert the real function
to ipv6_skip_exthdr() to avoid pulling in the ip6_tables module
when loading ipset.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/ipset/ip_set_getport.h | 10 ++++++++++
 net/netfilter/ipset/ip_set_getport.c           | 15 +++++++++------
 2 files changed, 19 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h
index 694c433298b8..3882a81a3b3c 100644
--- a/include/linux/netfilter/ipset/ip_set_getport.h
+++ b/include/linux/netfilter/ipset/ip_set_getport.h
@@ -3,8 +3,18 @@
 
 extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
 				__be16 *port, u8 *proto);
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
 extern bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
 				__be16 *port, u8 *proto);
+#else
+static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
+				       __be16 *port, u8 *proto)
+{
+	return false;
+}
+#endif
+
 extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src,
 				__be16 *port);
 
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
index 4dd2785a5c72..8d5227212686 100644
--- a/net/netfilter/ipset/ip_set_getport.c
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -13,6 +13,7 @@
 #include <linux/icmpv6.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <net/ip.h>
+#include <net/ipv6.h>
 
 #include <linux/netfilter/ipset/ip_set_getport.h>
 
@@ -93,21 +94,23 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
 }
 EXPORT_SYMBOL_GPL(ip_set_get_ip4_port);
 
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
 bool
 ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
 		    __be16 *port, u8 *proto)
 {
-	unsigned int protooff = 0;
-	int protocol;
-	unsigned short fragoff;
+	int protoff;
+	u8 nexthdr;
 
-	protocol = ipv6_find_hdr(skb, &protooff, -1, &fragoff);
-	if (protocol <= 0 || fragoff)
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+	if (protoff < 0)
 		return false;
 
-	return get_port(skb, protocol, protooff, src, port, proto);
+	return get_port(skb, nexthdr, protoff, src, port, proto);
 }
 EXPORT_SYMBOL_GPL(ip_set_get_ip6_port);
+#endif
 
 bool
 ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port)
-- 
cgit v1.2.3


From 9291747f118d6404e509747b85ff5f6dfec368d2 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 3 Feb 2011 00:05:43 +0100
Subject: netfilter: xtables: add device group match

Add a new 'devgroup' match to match on the device group of the
incoming and outgoing network device of a packet.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/Kbuild        |  1 +
 include/linux/netfilter/xt_devgroup.h | 21 +++++++++
 net/netfilter/Kconfig                 |  9 ++++
 net/netfilter/Makefile                |  1 +
 net/netfilter/xt_devgroup.c           | 82 +++++++++++++++++++++++++++++++++++
 5 files changed, 114 insertions(+)
 create mode 100644 include/linux/netfilter/xt_devgroup.h
 create mode 100644 net/netfilter/xt_devgroup.c

(limited to 'include')

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index ba19544cce94..15e83bf3dd58 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -37,6 +37,7 @@ header-y += xt_connmark.h
 header-y += xt_conntrack.h
 header-y += xt_cpu.h
 header-y += xt_dccp.h
+header-y += xt_devgroup.h
 header-y += xt_dscp.h
 header-y += xt_esp.h
 header-y += xt_hashlimit.h
diff --git a/include/linux/netfilter/xt_devgroup.h b/include/linux/netfilter/xt_devgroup.h
new file mode 100644
index 000000000000..1babde0ec900
--- /dev/null
+++ b/include/linux/netfilter/xt_devgroup.h
@@ -0,0 +1,21 @@
+#ifndef _XT_DEVGROUP_H
+#define _XT_DEVGROUP_H
+
+#include <linux/types.h>
+
+enum xt_devgroup_flags {
+	XT_DEVGROUP_MATCH_SRC	= 0x1,
+	XT_DEVGROUP_INVERT_SRC	= 0x2,
+	XT_DEVGROUP_MATCH_DST	= 0x4,
+	XT_DEVGROUP_INVERT_DST	= 0x8,
+};
+
+struct xt_devgroup_info {
+	__u32	flags;
+	__u32	src_group;
+	__u32	src_mask;
+	__u32	dst_group;
+	__u32	dst_mask;
+};
+
+#endif /* _XT_DEVGROUP_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 06fa9e4e45c7..82a6e0d80f05 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -738,6 +738,15 @@ config NETFILTER_XT_MATCH_DCCP
 	  If you want to compile it as a module, say M here and read
 	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
 
+config NETFILTER_XT_MATCH_DEVGROUP
+	tristate '"devgroup" match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This options adds a `devgroup' match, which allows to match on the
+	  device group a network device is assigned to.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NETFILTER_XT_MATCH_DSCP
 	tristate '"dscp" and "tos" match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 1148643559cb..d57a890eaee5 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -77,6 +77,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_DEVGROUP) += xt_devgroup.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
diff --git a/net/netfilter/xt_devgroup.c b/net/netfilter/xt_devgroup.c
new file mode 100644
index 000000000000..d9202cdd25c9
--- /dev/null
+++ b/net/netfilter/xt_devgroup.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+
+#include <linux/netfilter/xt_devgroup.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: Device group match");
+MODULE_ALIAS("ipt_devgroup");
+MODULE_ALIAS("ip6t_devgroup");
+
+static bool devgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_devgroup_info *info = par->matchinfo;
+
+	if (info->flags & XT_DEVGROUP_MATCH_SRC &&
+	    (((info->src_group ^ par->in->group) & info->src_mask ? 1 : 0) ^
+	     ((info->flags & XT_DEVGROUP_INVERT_SRC) ? 1 : 0)))
+		return false;
+
+	if (info->flags & XT_DEVGROUP_MATCH_DST &&
+	    (((info->dst_group ^ par->out->group) & info->dst_mask ? 1 : 0) ^
+	     ((info->flags & XT_DEVGROUP_INVERT_DST) ? 1 : 0)))
+		return false;
+
+	return true;
+}
+
+static int devgroup_mt_checkentry(const struct xt_mtchk_param *par)
+{
+	const struct xt_devgroup_info *info = par->matchinfo;
+
+	if (info->flags & ~(XT_DEVGROUP_MATCH_SRC | XT_DEVGROUP_INVERT_SRC |
+			    XT_DEVGROUP_MATCH_DST | XT_DEVGROUP_INVERT_DST))
+		return -EINVAL;
+
+	if (info->flags & XT_DEVGROUP_MATCH_SRC &&
+	    par->hook_mask & ~((1 << NF_INET_PRE_ROUTING) |
+			       (1 << NF_INET_LOCAL_IN) |
+			       (1 << NF_INET_FORWARD)))
+		return -EINVAL;
+
+	if (info->flags & XT_DEVGROUP_MATCH_DST &&
+	    par->hook_mask & ~((1 << NF_INET_FORWARD) |
+			       (1 << NF_INET_LOCAL_OUT) |
+			       (1 << NF_INET_POST_ROUTING)))
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct xt_match devgroup_mt_reg __read_mostly = {
+	.name		= "devgroup",
+	.match		= devgroup_mt,
+	.checkentry	= devgroup_mt_checkentry,
+	.matchsize	= sizeof(struct xt_devgroup_info),
+	.family		= NFPROTO_UNSPEC,
+	.me		= THIS_MODULE
+};
+
+static int __init devgroup_mt_init(void)
+{
+	return xt_register_match(&devgroup_mt_reg);
+}
+
+static void __exit devgroup_mt_exit(void)
+{
+	xt_unregister_match(&devgroup_mt_reg);
+}
+
+module_init(devgroup_mt_init);
+module_exit(devgroup_mt_exit);
-- 
cgit v1.2.3


From 442b9635c569fef038d5367a7acd906db4677ae1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 2 Feb 2011 17:05:11 -0800
Subject: tcp: Increase the initial congestion window to 10.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Nandita Dukkipati <nanditad@google.com>
---
 include/net/tcp.h      | 12 +++---------
 net/dccp/ccids/ccid2.c |  9 +++++++++
 net/ipv4/tcp_input.c   |  2 +-
 3 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 917911165e3b..7118668ad534 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* TCP thin-stream limits */
 #define TCP_THIN_LINEAR_RETRIES 6       /* After 6 linear retries, do exp. backoff */
 
+/* TCP initial congestion window */
+#define TCP_INIT_CWND		10
+
 extern struct inet_timewait_death_row tcp_death_row;
 
 /* sysctl variables for tcp */
@@ -799,15 +802,6 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 /* Use define here intentionally to get WARN_ON location shown at the caller */
 #define tcp_verify_left_out(tp)	WARN_ON(tcp_left_out(tp) > tp->packets_out)
 
-/*
- * Convert RFC 3390 larger initial window into an equivalent number of packets.
- * This is based on the numbers specified in RFC 5681, 3.1.
- */
-static inline u32 rfc3390_bytes_to_packets(const u32 smss)
-{
-	return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3);
-}
-
 extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
 extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
 
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index e96d5e810039..fadecd20d75b 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -583,6 +583,15 @@ done:
 	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
+/*
+ * Convert RFC 3390 larger initial window into an equivalent number of packets.
+ * This is based on the numbers specified in RFC 5681, 3.1.
+ */
+static inline u32 rfc3390_bytes_to_packets(const u32 smss)
+{
+	return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3);
+}
+
 static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
 {
 	struct ccid2_hc_tx_sock *hc = ccid_priv(ccid);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eb7f82ebf4a3..2f692cefd3b0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -817,7 +817,7 @@ __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)
 	__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
 
 	if (!cwnd)
-		cwnd = rfc3390_bytes_to_packets(tp->mss_cache);
+		cwnd = TCP_INIT_CWND;
 	return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
 }
 
-- 
cgit v1.2.3


From 45e144339ac59971eb44be32e1282760aaabe861 Mon Sep 17 00:00:00 2001
From: stephen hemminger <shemminger@vyatta.com>
Date: Wed, 2 Feb 2011 15:21:10 +0000
Subject: sched: CHOKe flow scheduler

CHOKe ("CHOose and Kill" or "CHOose and Keep") is an alternative
packet scheduler based on the Random Exponential Drop (RED) algorithm.

The core idea is:
  For every packet arrival:
  	Calculate Qave
	if (Qave < minth)
	     Queue the new packet
	else
	     Select randomly a packet from the queue
	     if (both packets from same flow)
	     then Drop both the packets
	     else if (Qave > maxth)
	          Drop packet
	     else
	       	  Admit packet with proability p (same as RED)

See also:
  Rong Pan, Balaji Prabhakar, Konstantinos Psounis, "CHOKe: a stateless active
   queue management scheme for approximating fair bandwidth allocation",
  Proceeding of INFOCOM'2000, March 2000.

Help from:
     Eric Dumazet <eric.dumazet@gmail.com>
     Patrick McHardy <kaber@trash.net>

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/pkt_sched.h |  29 ++
 net/sched/Kconfig         |  11 +
 net/sched/Makefile        |   2 +
 net/sched/sch_choke.c     | 676 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 718 insertions(+)
 create mode 100644 net/sched/sch_choke.c

(limited to 'include')

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index 776cd93d5f7b..d4bb6f58c90c 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -247,6 +247,35 @@ struct tc_gred_sopt {
 	__u16		pad1;
 };
 
+/* CHOKe section */
+
+enum {
+	TCA_CHOKE_UNSPEC,
+	TCA_CHOKE_PARMS,
+	TCA_CHOKE_STAB,
+	__TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+	__u32		limit;		/* Hard queue length (packets)	*/
+	__u32		qth_min;	/* Min average threshold (packets) */
+	__u32		qth_max;	/* Max average threshold (packets) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;		/* see RED flags */
+};
+
+struct tc_choke_xstats {
+	__u32		early;          /* Early drops */
+	__u32		pdrop;          /* Drops due to queue limits */
+	__u32		other;          /* Drops due to drop() calls */
+	__u32		marked;         /* Marked packets */
+	__u32		matched;	/* Drops due to flow match */
+};
+
 /* HTB section */
 #define TC_HTB_NUMPRIO		8
 #define TC_HTB_MAXDEPTH		8
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index e318f458713e..8c19b6e3201e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -217,6 +217,17 @@ config NET_SCH_MQPRIO
 
 	  If unsure, say N.
 
+config NET_SCH_CHOKE
+	tristate "CHOose and Keep responsive flow scheduler (CHOKE)"
+	help
+	  Say Y here if you want to use the CHOKe packet scheduler (CHOose
+	  and Keep for responsive flows, CHOose and Kill for unresponsive
+	  flows). This is a variation of RED which trys to penalize flows
+	  that monopolize the queue.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_choke.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 26ce681a2c60..06c6cdfd1948 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -33,6 +33,8 @@ obj-$(CONFIG_NET_SCH_ATM)	+= sch_atm.o
 obj-$(CONFIG_NET_SCH_NETEM)	+= sch_netem.o
 obj-$(CONFIG_NET_SCH_DRR)	+= sch_drr.o
 obj-$(CONFIG_NET_SCH_MQPRIO)	+= sch_mqprio.o
+obj-$(CONFIG_NET_SCH_CHOKE)	+= sch_choke.o
+
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
 obj-$(CONFIG_NET_CLS_FW)	+= cls_fw.o
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
new file mode 100644
index 000000000000..a1cec18dd49c
--- /dev/null
+++ b/net/sched/sch_choke.c
@@ -0,0 +1,676 @@
+/*
+ * net/sched/sch_choke.c	CHOKE scheduler
+ *
+ * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com>
+ * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/reciprocal_div.h>
+#include <net/pkt_sched.h>
+#include <net/inet_ecn.h>
+#include <net/red.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+
+/*
+   CHOKe stateless AQM for fair bandwidth allocation
+   =================================================
+
+   CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for
+   unresponsive flows) is a variant of RED that penalizes misbehaving flows but
+   maintains no flow state. The difference from RED is an additional step
+   during the enqueuing process. If average queue size is over the
+   low threshold (qmin), a packet is chosen at random from the queue.
+   If both the new and chosen packet are from the same flow, both
+   are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it
+   needs to access packets in queue randomly. It has a minimal class
+   interface to allow overriding the builtin flow classifier with
+   filters.
+
+   Source:
+   R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless
+   Active Queue Management Scheme for Approximating Fair Bandwidth Allocation",
+   IEEE INFOCOM, 2000.
+
+   A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial
+   Characteristics", IEEE/ACM Transactions on Networking, 2004
+
+ */
+
+/* Upper bound on size of sk_buff table (packets) */
+#define CHOKE_MAX_QUEUE	(128*1024 - 1)
+
+struct choke_sched_data {
+/* Parameters */
+	u32		 limit;
+	unsigned char	 flags;
+
+	struct red_parms parms;
+
+/* Variables */
+	struct tcf_proto *filter_list;
+	struct {
+		u32	prob_drop;	/* Early probability drops */
+		u32	prob_mark;	/* Early probability marks */
+		u32	forced_drop;	/* Forced drops, qavg > max_thresh */
+		u32	forced_mark;	/* Forced marks, qavg > max_thresh */
+		u32	pdrop;          /* Drops due to queue limits */
+		u32	other;          /* Drops due to drop() calls */
+		u32	matched;	/* Drops to flow match */
+	} stats;
+
+	unsigned int	 head;
+	unsigned int	 tail;
+
+	unsigned int	 tab_mask; /* size - 1 */
+
+	struct sk_buff **tab;
+};
+
+/* deliver a random number between 0 and N - 1 */
+static u32 random_N(unsigned int N)
+{
+	return reciprocal_divide(random32(), N);
+}
+
+/* number of elements in queue including holes */
+static unsigned int choke_len(const struct choke_sched_data *q)
+{
+	return (q->tail - q->head) & q->tab_mask;
+}
+
+/* Is ECN parameter configured */
+static int use_ecn(const struct choke_sched_data *q)
+{
+	return q->flags & TC_RED_ECN;
+}
+
+/* Should packets over max just be dropped (versus marked) */
+static int use_harddrop(const struct choke_sched_data *q)
+{
+	return q->flags & TC_RED_HARDDROP;
+}
+
+/* Move head pointer forward to skip over holes */
+static void choke_zap_head_holes(struct choke_sched_data *q)
+{
+	do {
+		q->head = (q->head + 1) & q->tab_mask;
+		if (q->head == q->tail)
+			break;
+	} while (q->tab[q->head] == NULL);
+}
+
+/* Move tail pointer backwards to reuse holes */
+static void choke_zap_tail_holes(struct choke_sched_data *q)
+{
+	do {
+		q->tail = (q->tail - 1) & q->tab_mask;
+		if (q->head == q->tail)
+			break;
+	} while (q->tab[q->tail] == NULL);
+}
+
+/* Drop packet from queue array by creating a "hole" */
+static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb = q->tab[idx];
+
+	q->tab[idx] = NULL;
+
+	if (idx == q->head)
+		choke_zap_head_holes(q);
+	if (idx == q->tail)
+		choke_zap_tail_holes(q);
+
+	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	qdisc_drop(skb, sch);
+	qdisc_tree_decrease_qlen(sch, 1);
+	--sch->q.qlen;
+}
+
+/*
+ * Compare flow of two packets
+ *  Returns true only if source and destination address and port match.
+ *          false for special cases
+ */
+static bool choke_match_flow(struct sk_buff *skb1,
+			     struct sk_buff *skb2)
+{
+	int off1, off2, poff;
+	const u32 *ports1, *ports2;
+	u8 ip_proto;
+	__u32 hash1;
+
+	if (skb1->protocol != skb2->protocol)
+		return false;
+
+	/* Use hash value as quick check
+	 * Assumes that __skb_get_rxhash makes IP header and ports linear
+	 */
+	hash1 = skb_get_rxhash(skb1);
+	if (!hash1 || hash1 != skb_get_rxhash(skb2))
+		return false;
+
+	/* Probably match, but be sure to avoid hash collisions */
+	off1 = skb_network_offset(skb1);
+	off2 = skb_network_offset(skb2);
+
+	switch (skb1->protocol) {
+	case __constant_htons(ETH_P_IP): {
+		const struct iphdr *ip1, *ip2;
+
+		ip1 = (const struct iphdr *) (skb1->data + off1);
+		ip2 = (const struct iphdr *) (skb2->data + off2);
+
+		ip_proto = ip1->protocol;
+		if (ip_proto != ip2->protocol ||
+		    ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr)
+			return false;
+
+		if ((ip1->frag_off | ip2->frag_off) & htons(IP_MF | IP_OFFSET))
+			ip_proto = 0;
+		off1 += ip1->ihl * 4;
+		off2 += ip2->ihl * 4;
+		break;
+	}
+
+	case __constant_htons(ETH_P_IPV6): {
+		const struct ipv6hdr *ip1, *ip2;
+
+		ip1 = (const struct ipv6hdr *) (skb1->data + off1);
+		ip2 = (const struct ipv6hdr *) (skb2->data + off2);
+
+		ip_proto = ip1->nexthdr;
+		if (ip_proto != ip2->nexthdr ||
+		    ipv6_addr_cmp(&ip1->saddr, &ip2->saddr) ||
+		    ipv6_addr_cmp(&ip1->daddr, &ip2->daddr))
+			return false;
+		off1 += 40;
+		off2 += 40;
+	}
+
+	default: /* Maybe compare MAC header here? */
+		return false;
+	}
+
+	poff = proto_ports_offset(ip_proto);
+	if (poff < 0)
+		return true;
+
+	off1 += poff;
+	off2 += poff;
+
+	ports1 = (__force u32 *)(skb1->data + off1);
+	ports2 = (__force u32 *)(skb2->data + off2);
+	return *ports1 == *ports2;
+}
+
+static inline void choke_set_classid(struct sk_buff *skb, u16 classid)
+{
+	*(unsigned int *)(qdisc_skb_cb(skb)->data) = classid;
+}
+
+static u16 choke_get_classid(const struct sk_buff *skb)
+{
+	return *(unsigned int *)(qdisc_skb_cb(skb)->data);
+}
+
+/*
+ * Classify flow using either:
+ *  1. pre-existing classification result in skb
+ *  2. fast internal classification
+ *  3. use TC filter based classification
+ */
+static bool choke_classify(struct sk_buff *skb,
+			   struct Qdisc *sch, int *qerr)
+
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct tcf_result res;
+	int result;
+
+	result = tc_classify(skb, q->filter_list, &res);
+	if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+		switch (result) {
+		case TC_ACT_STOLEN:
+		case TC_ACT_QUEUED:
+			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+		case TC_ACT_SHOT:
+			return false;
+		}
+#endif
+		choke_set_classid(skb, TC_H_MIN(res.classid));
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Select a packet at random from queue
+ * HACK: since queue can have holes from previous deletion; retry several
+ *   times to find a random skb but then just give up and return the head
+ * Will return NULL if queue is empty (q->head == q->tail)
+ */
+static struct sk_buff *choke_peek_random(const struct choke_sched_data *q,
+					 unsigned int *pidx)
+{
+	struct sk_buff *skb;
+	int retrys = 3;
+
+	do {
+		*pidx = (q->head + random_N(choke_len(q))) & q->tab_mask;
+		skb = q->tab[*pidx];
+		if (skb)
+			return skb;
+	} while (--retrys > 0);
+
+	return q->tab[*pidx = q->head];
+}
+
+/*
+ * Compare new packet with random packet in queue
+ * returns true if matched and sets *pidx
+ */
+static bool choke_match_random(const struct choke_sched_data *q,
+			       struct sk_buff *nskb,
+			       unsigned int *pidx)
+{
+	struct sk_buff *oskb;
+
+	if (q->head == q->tail)
+		return false;
+
+	oskb = choke_peek_random(q, pidx);
+	if (q->filter_list)
+		return choke_get_classid(nskb) == choke_get_classid(oskb);
+
+	return choke_match_flow(oskb, nskb);
+}
+
+static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct red_parms *p = &q->parms;
+	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+
+	if (q->filter_list) {
+		/* If using external classifiers, get result and record it. */
+		if (!choke_classify(skb, sch, &ret))
+			goto other_drop;	/* Packet was eaten by filter */
+	}
+
+	/* Compute average queue usage (see RED) */
+	p->qavg = red_calc_qavg(p, sch->q.qlen);
+	if (red_is_idling(p))
+		red_end_of_idle_period(p);
+
+	/* Is queue small? */
+	if (p->qavg <= p->qth_min)
+		p->qcount = -1;
+	else {
+		unsigned int idx;
+
+		/* Draw a packet at random from queue and compare flow */
+		if (choke_match_random(q, skb, &idx)) {
+			q->stats.matched++;
+			choke_drop_by_idx(sch, idx);
+			goto congestion_drop;
+		}
+
+		/* Queue is large, always mark/drop */
+		if (p->qavg > p->qth_max) {
+			p->qcount = -1;
+
+			sch->qstats.overlimits++;
+			if (use_harddrop(q) || !use_ecn(q) ||
+			    !INET_ECN_set_ce(skb)) {
+				q->stats.forced_drop++;
+				goto congestion_drop;
+			}
+
+			q->stats.forced_mark++;
+		} else if (++p->qcount) {
+			if (red_mark_probability(p, p->qavg)) {
+				p->qcount = 0;
+				p->qR = red_random(p);
+
+				sch->qstats.overlimits++;
+				if (!use_ecn(q) || !INET_ECN_set_ce(skb)) {
+					q->stats.prob_drop++;
+					goto congestion_drop;
+				}
+
+				q->stats.prob_mark++;
+			}
+		} else
+			p->qR = red_random(p);
+	}
+
+	/* Admit new packet */
+	if (sch->q.qlen < q->limit) {
+		q->tab[q->tail] = skb;
+		q->tail = (q->tail + 1) & q->tab_mask;
+		++sch->q.qlen;
+		sch->qstats.backlog += qdisc_pkt_len(skb);
+		return NET_XMIT_SUCCESS;
+	}
+
+	q->stats.pdrop++;
+	sch->qstats.drops++;
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+
+ congestion_drop:
+	qdisc_drop(skb, sch);
+	return NET_XMIT_CN;
+
+ other_drop:
+	if (ret & __NET_XMIT_BYPASS)
+		sch->qstats.drops++;
+	kfree_skb(skb);
+	return ret;
+}
+
+static struct sk_buff *choke_dequeue(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+
+	if (q->head == q->tail) {
+		if (!red_is_idling(&q->parms))
+			red_start_of_idle_period(&q->parms);
+		return NULL;
+	}
+
+	skb = q->tab[q->head];
+	q->tab[q->head] = NULL;
+	choke_zap_head_holes(q);
+	--sch->q.qlen;
+	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	qdisc_bstats_update(sch, skb);
+
+	return skb;
+}
+
+static unsigned int choke_drop(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	unsigned int len;
+
+	len = qdisc_queue_drop(sch);
+	if (len > 0)
+		q->stats.other++;
+	else {
+		if (!red_is_idling(&q->parms))
+			red_start_of_idle_period(&q->parms);
+	}
+
+	return len;
+}
+
+static void choke_reset(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	red_restart(&q->parms);
+}
+
+static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
+	[TCA_CHOKE_PARMS]	= { .len = sizeof(struct tc_red_qopt) },
+	[TCA_CHOKE_STAB]	= { .len = RED_STAB_SIZE },
+};
+
+
+static void choke_free(void *addr)
+{
+	if (addr) {
+		if (is_vmalloc_addr(addr))
+			vfree(addr);
+		else
+			kfree(addr);
+	}
+}
+
+static int choke_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_CHOKE_MAX + 1];
+	const struct tc_red_qopt *ctl;
+	int err;
+	struct sk_buff **old = NULL;
+	unsigned int mask;
+
+	if (opt == NULL)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_CHOKE_PARMS] == NULL ||
+	    tb[TCA_CHOKE_STAB] == NULL)
+		return -EINVAL;
+
+	ctl = nla_data(tb[TCA_CHOKE_PARMS]);
+
+	if (ctl->limit > CHOKE_MAX_QUEUE)
+		return -EINVAL;
+
+	mask = roundup_pow_of_two(ctl->limit + 1) - 1;
+	if (mask != q->tab_mask) {
+		struct sk_buff **ntab;
+
+		ntab = kcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL);
+		if (!ntab)
+			ntab = vzalloc((mask + 1) * sizeof(struct sk_buff *));
+		if (!ntab)
+			return -ENOMEM;
+
+		sch_tree_lock(sch);
+		old = q->tab;
+		if (old) {
+			unsigned int oqlen = sch->q.qlen, tail = 0;
+
+			while (q->head != q->tail) {
+				struct sk_buff *skb = q->tab[q->head];
+
+				q->head = (q->head + 1) & q->tab_mask;
+				if (!skb)
+					continue;
+				if (tail < mask) {
+					ntab[tail++] = skb;
+					continue;
+				}
+				sch->qstats.backlog -= qdisc_pkt_len(skb);
+				--sch->q.qlen;
+				qdisc_drop(skb, sch);
+			}
+			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			q->head = 0;
+			q->tail = tail;
+		}
+
+		q->tab_mask = mask;
+		q->tab = ntab;
+	} else
+		sch_tree_lock(sch);
+
+	q->flags = ctl->flags;
+	q->limit = ctl->limit;
+
+	red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
+		      ctl->Plog, ctl->Scell_log,
+		      nla_data(tb[TCA_CHOKE_STAB]));
+
+	if (q->head == q->tail)
+		red_end_of_idle_period(&q->parms);
+
+	sch_tree_unlock(sch);
+	choke_free(old);
+	return 0;
+}
+
+static int choke_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	return choke_change(sch, opt);
+}
+
+static int choke_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts = NULL;
+	struct tc_red_qopt opt = {
+		.limit		= q->limit,
+		.flags		= q->flags,
+		.qth_min	= q->parms.qth_min >> q->parms.Wlog,
+		.qth_max	= q->parms.qth_max >> q->parms.Wlog,
+		.Wlog		= q->parms.Wlog,
+		.Plog		= q->parms.Plog,
+		.Scell_log	= q->parms.Scell_log,
+	};
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	NLA_PUT(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt);
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -EMSGSIZE;
+}
+
+static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+	struct tc_choke_xstats st = {
+		.early	= q->stats.prob_drop + q->stats.forced_drop,
+		.marked	= q->stats.prob_mark + q->stats.forced_mark,
+		.pdrop	= q->stats.pdrop,
+		.other	= q->stats.other,
+		.matched = q->stats.matched,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static void choke_destroy(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	tcf_destroy_chain(&q->filter_list);
+	choke_free(q->tab);
+}
+
+static struct Qdisc *choke_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	return NULL;
+}
+
+static unsigned long choke_get(struct Qdisc *sch, u32 classid)
+{
+	return 0;
+}
+
+static void choke_put(struct Qdisc *q, unsigned long cl)
+{
+}
+
+static unsigned long choke_bind(struct Qdisc *sch, unsigned long parent,
+				u32 classid)
+{
+	return 0;
+}
+
+static struct tcf_proto **choke_find_tcf(struct Qdisc *sch, unsigned long cl)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return &q->filter_list;
+}
+
+static int choke_dump_class(struct Qdisc *sch, unsigned long cl,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static void choke_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	if (!arg->stop) {
+		if (arg->fn(sch, 1, arg) < 0) {
+			arg->stop = 1;
+			return;
+		}
+		arg->count++;
+	}
+}
+
+static const struct Qdisc_class_ops choke_class_ops = {
+	.leaf		=	choke_leaf,
+	.get		=	choke_get,
+	.put		=	choke_put,
+	.tcf_chain	=	choke_find_tcf,
+	.bind_tcf	=	choke_bind,
+	.unbind_tcf	=	choke_put,
+	.dump		=	choke_dump_class,
+	.walk		=	choke_walk,
+};
+
+static struct sk_buff *choke_peek_head(struct Qdisc *sch)
+{
+	struct choke_sched_data *q = qdisc_priv(sch);
+
+	return (q->head != q->tail) ? q->tab[q->head] : NULL;
+}
+
+static struct Qdisc_ops choke_qdisc_ops __read_mostly = {
+	.id		=	"choke",
+	.priv_size	=	sizeof(struct choke_sched_data),
+
+	.enqueue	=	choke_enqueue,
+	.dequeue	=	choke_dequeue,
+	.peek		=	choke_peek_head,
+	.drop		=	choke_drop,
+	.init		=	choke_init,
+	.destroy	=	choke_destroy,
+	.reset		=	choke_reset,
+	.change		=	choke_change,
+	.dump		=	choke_dump,
+	.dump_stats	=	choke_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init choke_module_init(void)
+{
+	return register_qdisc(&choke_qdisc_ops);
+}
+
+static void __exit choke_module_exit(void)
+{
+	unregister_qdisc(&choke_qdisc_ops);
+}
+
+module_init(choke_module_init)
+module_exit(choke_module_exit)
+
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From fe4b04fa31a6dcf4358aa84cf81e5a7fd079469b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 2 Feb 2011 13:19:09 +0100
Subject: perf: Cure task_oncpu_function_call() races

Oleg reported that on architectures with
__ARCH_WANT_INTERRUPTS_ON_CTXSW the IPI from
task_oncpu_function_call() can land before perf_event_task_sched_in()
and cause interesting situations for eg. perf_install_in_context().

This patch reworks the task_oncpu_function_call() interface to give a
more usable primitive as well as rework all its users to hopefully be
more obvious as well as remove the races.

While looking at the code I also found a number of races against
perf_event_task_sched_out() which can flip contexts between tasks so
plug those too.

Reported-and-reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h |   7 --
 kernel/perf_event.c   | 260 ++++++++++++++++++++++++++++++++------------------
 kernel/sched.c        |  29 +-----
 3 files changed, 172 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d747f948b34e..0b40ee3f6d7a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2578,13 +2578,6 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
-/*
- * Call the function if the target task is executing on a CPU right now:
- */
-extern void task_oncpu_function_call(struct task_struct *p,
-				     void (*func) (void *info), void *info);
-
-
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 126a302c481c..7d3faa25e136 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,6 +38,79 @@
 
 #include <asm/irq_regs.h>
 
+struct remote_function_call {
+	struct task_struct *p;
+	int (*func)(void *info);
+	void *info;
+	int ret;
+};
+
+static void remote_function(void *data)
+{
+	struct remote_function_call *tfc = data;
+	struct task_struct *p = tfc->p;
+
+	if (p) {
+		tfc->ret = -EAGAIN;
+		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+			return;
+	}
+
+	tfc->ret = tfc->func(tfc->info);
+}
+
+/**
+ * task_function_call - call a function on the cpu on which a task runs
+ * @p:		the task to evaluate
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ *
+ * returns: @func return value, or
+ *	    -ESRCH  - when the process isn't running
+ *	    -EAGAIN - when the process moved away
+ */
+static int
+task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+{
+	struct remote_function_call data = {
+		.p = p,
+		.func = func,
+		.info = info,
+		.ret = -ESRCH, /* No such (running) process */
+	};
+
+	if (task_curr(p))
+		smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+
+	return data.ret;
+}
+
+/**
+ * cpu_function_call - call a function on the cpu
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func on the remote cpu.
+ *
+ * returns: @func return value or -ENXIO when the cpu is offline
+ */
+static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+{
+	struct remote_function_call data = {
+		.p = NULL,
+		.func = func,
+		.info = info,
+		.ret = -ENXIO, /* No such CPU */
+	};
+
+	smp_call_function_single(cpu, remote_function, &data, 1);
+
+	return data.ret;
+}
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
@@ -254,7 +327,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 	raw_spin_lock_irqsave(&ctx->lock, flags);
 	--ctx->pin_count;
 	raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	put_ctx(ctx);
 }
 
 /*
@@ -618,35 +690,24 @@ __get_cpu_context(struct perf_event_context *ctx)
  * We disable the event on the hardware level first. After that we
  * remove it from the context list.
  */
-static void __perf_event_remove_from_context(void *info)
+static int __perf_remove_from_context(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
-	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
-
 	raw_spin_lock(&ctx->lock);
-
 	event_sched_out(event, cpuctx, ctx);
-
 	list_del_event(event, ctx);
-
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 
 /*
  * Remove the event from a task's (or a CPU's) list of events.
  *
- * Must be called with ctx->mutex held.
- *
  * CPU events are removed with a smp call. For task events we only
  * call when the task is on a CPU.
  *
@@ -657,49 +718,48 @@ static void __perf_event_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_event_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
 
+	lockdep_assert_held(&ctx->mutex);
+
 	if (!task) {
 		/*
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		smp_call_function_single(event->cpu,
-					 __perf_event_remove_from_context,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_remove_from_context, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_event_remove_from_context,
-				 event);
+	if (!task_function_call(task, __perf_remove_from_context, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * If the context is active we need to retry the smp call.
+	 * If we failed to find a running task, but find the context active now
+	 * that we've acquired the ctx->lock, retry.
 	 */
-	if (ctx->nr_active && !list_empty(&event->group_entry)) {
+	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
 		goto retry;
 	}
 
 	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can remove the event safely, if the call above did not
-	 * succeed.
+	 * Since the task isn't running, its safe to remove the event, us
+	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
-	if (!list_empty(&event->group_entry))
-		list_del_event(event, ctx);
+	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
 /*
  * Cross CPU call to disable a performance event
  */
-static void __perf_event_disable(void *info)
+static int __perf_event_disable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -708,9 +768,12 @@ static void __perf_event_disable(void *info)
 	/*
 	 * If this is a per-task event, need to check whether this
 	 * event's task is the current task on this cpu.
+	 *
+	 * Can trigger due to concurrent perf_event_context_sched_out()
+	 * flipping contexts around.
 	 */
 	if (ctx->task && cpuctx->task_ctx != ctx)
-		return;
+		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
 
@@ -729,6 +792,8 @@ static void __perf_event_disable(void *info)
 	}
 
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -753,13 +818,13 @@ void perf_event_disable(struct perf_event *event)
 		/*
 		 * Disable the event on the cpu that it's on
 		 */
-		smp_call_function_single(event->cpu, __perf_event_disable,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_event_disable, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_event_disable, event);
+	if (!task_function_call(task, __perf_event_disable, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
@@ -767,6 +832,11 @@ retry:
 	 */
 	if (event->state == PERF_EVENT_STATE_ACTIVE) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -778,7 +848,6 @@ retry:
 		update_group_times(event);
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -928,12 +997,14 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
+static void perf_event_context_sched_in(struct perf_event_context *ctx);
+
 /*
  * Cross CPU call to install and enable a performance event
  *
  * Must be called with ctx->mutex held
  */
-static void __perf_install_in_context(void *info)
+static int  __perf_install_in_context(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -942,17 +1013,12 @@ static void __perf_install_in_context(void *info)
 	int err;
 
 	/*
-	 * If this is a task context, we need to check whether it is
-	 * the current task context of this cpu. If not it has been
-	 * scheduled out before the smp call arrived.
-	 * Or possibly this is the right context but it isn't
-	 * on this cpu because it had no events.
+	 * In case we're installing a new context to an already running task,
+	 * could also happen before perf_event_task_sched_in() on architectures
+	 * which do context switches with IRQs enabled.
 	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
+	if (ctx->task && !cpuctx->task_ctx)
+		perf_event_context_sched_in(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
@@ -997,6 +1063,8 @@ static void __perf_install_in_context(void *info)
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -1008,8 +1076,6 @@ unlock:
  * If the event is attached to a task which is on a CPU we use a smp
  * call to enable it in the task context. The task might have been
  * scheduled away, but we check this in the smp call again.
- *
- * Must be called with ctx->mutex held.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
@@ -1018,6 +1084,8 @@ perf_install_in_context(struct perf_event_context *ctx,
 {
 	struct task_struct *task = ctx->task;
 
+	lockdep_assert_held(&ctx->mutex);
+
 	event->ctx = ctx;
 
 	if (!task) {
@@ -1025,31 +1093,29 @@ perf_install_in_context(struct perf_event_context *ctx,
 		 * Per cpu events are installed via an smp call and
 		 * the install is always successful.
 		 */
-		smp_call_function_single(cpu, __perf_install_in_context,
-					 event, 1);
+		cpu_function_call(cpu, __perf_install_in_context, event);
 		return;
 	}
 
 retry:
-	task_oncpu_function_call(task, __perf_install_in_context,
-				 event);
+	if (!task_function_call(task, __perf_install_in_context, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * we need to retry the smp call.
+	 * If we failed to find a running task, but find the context active now
+	 * that we've acquired the ctx->lock, retry.
 	 */
-	if (ctx->is_active && list_empty(&event->group_entry)) {
+	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
 		goto retry;
 	}
 
 	/*
-	 * The lock prevents that this context is scheduled in so we
-	 * can add the event safely, if it the call above did not
-	 * succeed.
+	 * Since the task isn't running, its safe to add the event, us holding
+	 * the ctx->lock ensures the task won't get scheduled in.
 	 */
-	if (list_empty(&event->group_entry))
-		add_event_to_ctx(event, ctx);
+	add_event_to_ctx(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -1078,7 +1144,7 @@ static void __perf_event_mark_enabled(struct perf_event *event,
 /*
  * Cross CPU call to enable a performance event
  */
-static void __perf_event_enable(void *info)
+static int __perf_event_enable(void *info)
 {
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
@@ -1086,18 +1152,10 @@ static void __perf_event_enable(void *info)
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
-	/*
-	 * If this is a per-task event, need to check whether this
-	 * event's task is the current task on this cpu.
-	 */
-	if (ctx->task && cpuctx->task_ctx != ctx) {
-		if (cpuctx->task_ctx || ctx->task != current)
-			return;
-		cpuctx->task_ctx = ctx;
-	}
+	if (WARN_ON_ONCE(!ctx->is_active))
+		return -EINVAL;
 
 	raw_spin_lock(&ctx->lock);
-	ctx->is_active = 1;
 	update_context_time(ctx);
 
 	if (event->state >= PERF_EVENT_STATE_INACTIVE)
@@ -1138,6 +1196,8 @@ static void __perf_event_enable(void *info)
 
 unlock:
 	raw_spin_unlock(&ctx->lock);
+
+	return 0;
 }
 
 /*
@@ -1158,8 +1218,7 @@ void perf_event_enable(struct perf_event *event)
 		/*
 		 * Enable the event on the cpu that it's on
 		 */
-		smp_call_function_single(event->cpu, __perf_event_enable,
-					 event, 1);
+		cpu_function_call(event->cpu, __perf_event_enable, event);
 		return;
 	}
 
@@ -1178,8 +1237,15 @@ void perf_event_enable(struct perf_event *event)
 		event->state = PERF_EVENT_STATE_OFF;
 
 retry:
+	if (!ctx->is_active) {
+		__perf_event_mark_enabled(event, ctx);
+		goto out;
+	}
+
 	raw_spin_unlock_irq(&ctx->lock);
-	task_oncpu_function_call(task, __perf_event_enable, event);
+
+	if (!task_function_call(task, __perf_event_enable, event))
+		return;
 
 	raw_spin_lock_irq(&ctx->lock);
 
@@ -1187,15 +1253,14 @@ retry:
 	 * If the context is active and the event is still off,
 	 * we need to retry the cross-call.
 	 */
-	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
+	if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) {
+		/*
+		 * task could have been flipped by a concurrent
+		 * perf_event_context_sched_out()
+		 */
+		task = ctx->task;
 		goto retry;
-
-	/*
-	 * Since we have the lock this context can't be scheduled
-	 * in, so we can change the state safely.
-	 */
-	if (event->state == PERF_EVENT_STATE_OFF)
-		__perf_event_mark_enabled(event, ctx);
+	}
 
 out:
 	raw_spin_unlock_irq(&ctx->lock);
@@ -1339,8 +1404,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
 	}
 }
 
-void perf_event_context_sched_out(struct task_struct *task, int ctxn,
-				  struct task_struct *next)
+static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+					 struct task_struct *next)
 {
 	struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
 	struct perf_event_context *next_ctx;
@@ -1533,7 +1598,7 @@ static void task_ctx_sched_in(struct perf_event_context *ctx,
 {
 	struct perf_cpu_context *cpuctx;
 
-       	cpuctx = __get_cpu_context(ctx);
+	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
 
@@ -1541,7 +1606,7 @@ static void task_ctx_sched_in(struct perf_event_context *ctx,
 	cpuctx->task_ctx = ctx;
 }
 
-void perf_event_context_sched_in(struct perf_event_context *ctx)
+static void perf_event_context_sched_in(struct perf_event_context *ctx)
 {
 	struct perf_cpu_context *cpuctx;
 
@@ -1627,7 +1692,7 @@ static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
 	 * Reduce accuracy by one bit such that @a and @b converge
 	 * to a similar magnitude.
 	 */
-#define REDUCE_FLS(a, b) 		\
+#define REDUCE_FLS(a, b)		\
 do {					\
 	if (a##_fls > b##_fls) {	\
 		a >>= 1;		\
@@ -2213,6 +2278,9 @@ errout:
 
 }
 
+/*
+ * Returns a matching context with refcount and pincount.
+ */
 static struct perf_event_context *
 find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 {
@@ -2237,6 +2305,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
+		++ctx->pin_count;
 
 		return ctx;
 	}
@@ -2250,6 +2319,7 @@ retry:
 	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		unclone_ctx(ctx);
+		++ctx->pin_count;
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
@@ -2271,8 +2341,10 @@ retry:
 			err = -ESRCH;
 		else if (task->perf_event_ctxp[ctxn])
 			err = -EAGAIN;
-		else
+		else {
+			++ctx->pin_count;
 			rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+		}
 		mutex_unlock(&task->perf_event_mutex);
 
 		if (unlikely(err)) {
@@ -5950,10 +6022,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_event_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_event_remove_from_context(sibling);
+			perf_remove_from_context(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);
@@ -5976,6 +6048,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
+	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
@@ -6001,6 +6074,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	return event_fd;
 
 err_context:
+	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
 	free_event(event);
@@ -6051,6 +6125,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	mutex_lock(&ctx->mutex);
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
+	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
 
 	return event;
@@ -6104,7 +6179,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 {
 	struct perf_event *parent_event;
 
-	perf_event_remove_from_context(child_event);
+	perf_remove_from_context(child_event);
 
 	parent_event = child_event->parent;
 	/*
@@ -6411,7 +6486,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		return 0;
 	}
 
-       	child_ctx = child->perf_event_ctxp[ctxn];
+	child_ctx = child->perf_event_ctxp[ctxn];
 	if (!child_ctx) {
 		/*
 		 * This is executed from the parent task context, so
@@ -6526,6 +6601,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
+	put_ctx(parent_ctx);
 
 	return ret;
 }
@@ -6595,9 +6671,9 @@ static void __perf_event_exit_context(void *__info)
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_event_remove_from_context(event);
+		__perf_remove_from_context(event);
 	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
-		__perf_event_remove_from_context(event);
+		__perf_remove_from_context(event);
 }
 
 static void perf_event_exit_cpu_context(int cpu)
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..31cb5d5e1aac 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2265,27 +2265,6 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 #endif /* CONFIG_SMP */
 
-/**
- * task_oncpu_function_call - call a function on the cpu on which a task runs
- * @p:		the task to evaluate
- * @func:	the function to be called
- * @info:	the function call argument
- *
- * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
- */
-void task_oncpu_function_call(struct task_struct *p,
-			      void (*func) (void *info), void *info)
-{
-	int cpu;
-
-	preempt_disable();
-	cpu = task_cpu(p);
-	if (task_curr(p))
-		smp_call_function_single(cpu, func, info, 1);
-	preempt_enable();
-}
-
 #ifdef CONFIG_SMP
 /*
  * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
@@ -2776,9 +2755,12 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
+	sched_info_switch(prev, next);
+	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_lock_switch(rq, next);
 	prepare_arch_switch(next);
+	trace_sched_switch(prev, next);
 }
 
 /**
@@ -2911,7 +2893,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_sched_switch(prev, next);
+
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -3989,9 +3971,6 @@ need_resched_nonpreemptible:
 	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
-		sched_info_switch(prev, next);
-		perf_event_task_sched_out(prev, next);
-
 		rq->nr_switches++;
 		rq->curr = next;
 		++*switch_count;
-- 
cgit v1.2.3


From ac53db596cc08ecb8040cfb6f71ae40c6f2041c4 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Tue, 1 Feb 2011 09:51:03 -0500
Subject: sched: Use a buddy to implement yield_task_fair()

Use the buddy mechanism to implement yield_task_fair.  This
allows us to skip onto the next highest priority se at every
level in the CFS tree, unless doing so would introduce gross
unfairness in CPU time distribution.

We order the buddy selection in pick_next_entity to check
yield first, then last, then next.  We need next to be able
to override yield, because it is possible for the "next" and
"yield" task to be different processen in the same sub-tree
of the CFS tree.  When they are, we need to go into that
sub-tree regardless of the "yield" hint, and pick the correct
entity once we get to the right level.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201095103.3a79e92a@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h |   2 -
 kernel/sched.c        |   2 +-
 kernel/sched_debug.c  |   2 +-
 kernel/sched_fair.c   | 148 ++++++++++++++++++++++++++++++--------------------
 kernel/sysctl.c       |   7 ---
 5 files changed, 90 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0542774914d4..4e9fad271c30 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1942,8 +1942,6 @@ int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
-extern unsigned int sysctl_sched_compat_yield;
-
 #ifdef CONFIG_SCHED_AUTOGROUP
 extern unsigned int sysctl_sched_autogroup_enabled;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 477e1bcc63f9..ae5e1a19b9d6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -324,7 +324,7 @@ struct cfs_rq {
 	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr, *next, *last;
+	struct sched_entity *curr, *next, *last, *skip;
 
 	unsigned int nr_spread_over;
 
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index eb6cb8edd075..7bacd83a4158 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -179,7 +179,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 	if (cfs_rq->rb_leftmost)
-		MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
+		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
 		max_vruntime = last->vruntime;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a785e08202cf..c0fbeb992833 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -68,14 +68,6 @@ static unsigned int sched_nr_latency = 8;
  */
 unsigned int sysctl_sched_child_runs_first __read_mostly;
 
-/*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
 /*
  * SCHED_OTHER wake-up granularity.
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
@@ -419,7 +411,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *left = cfs_rq->rb_leftmost;
 
@@ -429,6 +421,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 	return rb_entry(left, struct sched_entity, run_node);
 }
 
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+	struct rb_node *next = rb_next(&se->run_node);
+
+	if (!next)
+		return NULL;
+
+	return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
 static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
@@ -443,7 +446,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  * Scheduling class statistics methods:
  */
 
-#ifdef CONFIG_SCHED_DEBUG
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -1017,6 +1019,17 @@ static void __clear_buddies_next(struct sched_entity *se)
 	}
 }
 
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->skip == se)
+			cfs_rq->skip = NULL;
+		else
+			break;
+	}
+}
+
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->last == se)
@@ -1024,6 +1037,9 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 	if (cfs_rq->next == se)
 		__clear_buddies_next(se);
+
+	if (cfs_rq->skip == se)
+		__clear_buddies_skip(se);
 }
 
 static void
@@ -1099,7 +1115,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		return;
 
 	if (cfs_rq->nr_running > 1) {
-		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		struct sched_entity *se = __pick_first_entity(cfs_rq);
 		s64 delta = curr->vruntime - se->vruntime;
 
 		if (delta < 0)
@@ -1143,13 +1159,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static int
 wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_next_entity(cfs_rq);
+	struct sched_entity *se = __pick_first_entity(cfs_rq);
 	struct sched_entity *left = se;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
-		se = cfs_rq->next;
+	/*
+	 * Avoid running the skip buddy, if running something else can
+	 * be done without getting too unfair.
+	 */
+	if (cfs_rq->skip == se) {
+		struct sched_entity *second = __pick_next_entity(se);
+		if (second && wakeup_preempt_entity(second, left) < 1)
+			se = second;
+	}
 
 	/*
 	 * Prefer last buddy, try to return the CPU to a preempted task.
@@ -1157,6 +1187,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
 		se = cfs_rq->last;
 
+	/*
+	 * Someone really wants this to run. If it's not unfair, run it.
+	 */
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
+
 	clear_buddies(cfs_rq, se);
 
 	return se;
@@ -1333,52 +1369,6 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	hrtick_update(rq);
 }
 
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
-	struct task_struct *curr = rq->curr;
-	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	struct sched_entity *rightmost, *se = &curr->se;
-
-	/*
-	 * Are we the only task in the tree?
-	 */
-	if (unlikely(rq->nr_running == 1))
-		return;
-
-	clear_buddies(cfs_rq, se);
-
-	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-		update_rq_clock(rq);
-		/*
-		 * Update run-time statistics of the 'current'.
-		 */
-		update_curr(cfs_rq);
-
-		return;
-	}
-	/*
-	 * Find the rightmost entry in the rbtree:
-	 */
-	rightmost = __pick_last_entity(cfs_rq);
-	/*
-	 * Already in the rightmost position?
-	 */
-	if (unlikely(!rightmost || entity_before(rightmost, se)))
-		return;
-
-	/*
-	 * Minimally necessary key value to be last in the tree:
-	 * Upon rescheduling, sched_class::put_prev_task() will place
-	 * 'current' within the tree based on its new key value.
-	 */
-	se->vruntime = rightmost->vruntime + 1;
-}
-
 #ifdef CONFIG_SMP
 
 static void task_waking_fair(struct rq *rq, struct task_struct *p)
@@ -1849,6 +1839,14 @@ static void set_next_buddy(struct sched_entity *se)
 	}
 }
 
+static void set_skip_buddy(struct sched_entity *se)
+{
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->skip = se;
+	}
+}
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -1947,6 +1945,36 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	struct sched_entity *se = &curr->se;
+
+	/*
+	 * Are we the only task in the tree?
+	 */
+	if (unlikely(rq->nr_running == 1))
+		return;
+
+	clear_buddies(cfs_rq, se);
+
+	if (curr->policy != SCHED_BATCH) {
+		update_rq_clock(rq);
+		/*
+		 * Update run-time statistics of the 'current'.
+		 */
+		update_curr(cfs_rq);
+	}
+
+	set_skip_buddy(se);
+}
+
 #ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bc86bb32e126..cbfda7e2416e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -360,13 +360,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rt_handler,
 	},
-	{
-		.procname	= "sched_compat_yield",
-		.data		= &sysctl_sched_compat_yield,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",
-- 
cgit v1.2.3


From d95f412200652694e63e64bfd49f0ae274a54479 Mon Sep 17 00:00:00 2001
From: Mike Galbraith <efault@gmx.de>
Date: Tue, 1 Feb 2011 09:50:51 -0500
Subject: sched: Add yield_to(task, preempt) functionality

Currently only implemented for fair class tasks.

Add a yield_to_task method() to the fair scheduling class. allowing the
caller of yield_to() to accelerate another thread in it's thread group,
task group.

Implemented via a scheduler hint, using cfs_rq->next to encourage the
target being selected.  We can rely on pick_next_entity to keep things
fair, so noone can accelerate a thread that has already used its fair
share of CPU time.

This also means callers should only call yield_to when they really
mean it.  Calling it too often can result in the scheduler just
ignoring the hint.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201095051.4ddb7738@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h |  2 ++
 kernel/sched.c        | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched_fair.c   | 20 ++++++++++++
 3 files changed, 107 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4e9fad271c30..c88b3bfbd09e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1058,6 +1058,7 @@ struct sched_class {
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task) (struct rq *rq);
+	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
@@ -1972,6 +1973,7 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 # define rt_mutex_adjust_pi(p)		do { } while (0)
 #endif
 
+extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 extern int task_nice(const struct task_struct *p);
diff --git a/kernel/sched.c b/kernel/sched.c
index ae5e1a19b9d6..2effcb71a478 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1686,6 +1686,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 		__release(rq2->lock);
 }
 
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	BUG_ON(rq1 != rq2);
+	raw_spin_lock(&rq1->lock);
+	__acquire(rq2->lock);	/* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	BUG_ON(rq1 != rq2);
+	raw_spin_unlock(&rq1->lock);
+	__release(rq2->lock);
+}
+
 #endif
 
 static void calc_load_account_idle(struct rq *this_rq);
@@ -5448,6 +5481,58 @@ void __sched yield(void)
 }
 EXPORT_SYMBOL(yield);
 
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+	struct task_struct *curr = current;
+	struct rq *rq, *p_rq;
+	unsigned long flags;
+	bool yielded = 0;
+
+	local_irq_save(flags);
+	rq = this_rq();
+
+again:
+	p_rq = task_rq(p);
+	double_rq_lock(rq, p_rq);
+	while (task_rq(p) != p_rq) {
+		double_rq_unlock(rq, p_rq);
+		goto again;
+	}
+
+	if (!curr->sched_class->yield_to_task)
+		goto out;
+
+	if (curr->sched_class != p->sched_class)
+		goto out;
+
+	if (task_running(p_rq, p) || p->state)
+		goto out;
+
+	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	if (yielded)
+		schedstat_inc(rq, yld_count);
+
+out:
+	double_rq_unlock(rq, p_rq);
+	local_irq_restore(flags);
+
+	if (yielded)
+		schedule();
+
+	return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c0fbeb992833..027024694043 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1975,6 +1975,25 @@ static void yield_task_fair(struct rq *rq)
 	set_skip_buddy(se);
 }
 
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+	struct sched_entity *se = &p->se;
+
+	if (!se->on_rq)
+		return false;
+
+	/* Tell the scheduler that we'd really like pse to run next. */
+	set_next_buddy(se);
+
+	/* Make p's CPU reschedule; pick_next_entity takes care of fairness. */
+	if (preempt)
+		resched_task(rq->curr);
+
+	yield_task_fair(rq);
+
+	return true;
+}
+
 #ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
@@ -4243,6 +4262,7 @@ static const struct sched_class fair_sched_class = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
+	.yield_to_task		= yield_to_task_fair,
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
-- 
cgit v1.2.3


From 2f1522eccb09188f0008168f75420bc2fedc9cae Mon Sep 17 00:00:00 2001
From: Russ Gorby <russ.gorby@intel.com>
Date: Wed, 2 Feb 2011 12:56:58 -0800
Subject: serial: ifx6x60: expanded info available from platform data

Some platform attributes (e.g. max_hz, use_dma) were being intuited
from the modem type. These things should be specified by the platform
data.

Added max_hz, use_dma to ifx_modem_platform_data definition,
replaced is_6160 w/ modem_type, and changed clients accordingly

Signed-off-by: Russ Gorby <russ.gorby@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/tty/serial/ifx6x60.c  | 33 +++++++++++++++++----------------
 drivers/tty/serial/ifx6x60.h  |  4 +++-
 include/linux/spi/ifx_modem.h | 19 ++++++++++++-------
 3 files changed, 32 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c
index ab93763862d5..c42de7152eea 100644
--- a/drivers/tty/serial/ifx6x60.c
+++ b/drivers/tty/serial/ifx6x60.c
@@ -8,7 +8,7 @@
  *		      Jan Dumon <j.dumon@option.com>
  *
  * Copyright (C) 2009, 2010 Intel Corp
- * Russ Gorby <richardx.r.gorby@intel.com>
+ * Russ Gorby <russ.gorby@intel.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -732,7 +732,7 @@ static void ifx_spi_io(unsigned long data)
 		/*
 		 * setup dma pointers
 		 */
-		if (ifx_dev->is_6160) {
+		if (ifx_dev->use_dma) {
 			ifx_dev->spi_msg.is_dma_mapped = 1;
 			ifx_dev->tx_dma = ifx_dev->tx_bus;
 			ifx_dev->rx_dma = ifx_dev->rx_bus;
@@ -960,7 +960,7 @@ static int ifx_spi_spi_probe(struct spi_device *spi)
 {
 	int ret;
 	int srdy;
-	struct ifx_modem_platform_data *pl_data = NULL;
+	struct ifx_modem_platform_data *pl_data;
 	struct ifx_spi_device *ifx_dev;
 
 	if (saved_ifx_dev) {
@@ -968,6 +968,12 @@ static int ifx_spi_spi_probe(struct spi_device *spi)
 		return -ENODEV;
 	}
 
+	pl_data = (struct ifx_modem_platform_data *)spi->dev.platform_data;
+	if (!pl_data) {
+		dev_err(&spi->dev, "missing platform data!");
+		return -ENODEV;
+	}
+
 	/* initialize structure to hold our device variables */
 	ifx_dev = kzalloc(sizeof(struct ifx_spi_device), GFP_KERNEL);
 	if (!ifx_dev) {
@@ -983,7 +989,9 @@ static int ifx_spi_spi_probe(struct spi_device *spi)
 	init_timer(&ifx_dev->spi_timer);
 	ifx_dev->spi_timer.function = ifx_spi_timeout;
 	ifx_dev->spi_timer.data = (unsigned long)ifx_dev;
-	ifx_dev->is_6160 = pl_data->is_6160;
+	ifx_dev->modem = pl_data->modem_type;
+	ifx_dev->use_dma = pl_data->use_dma;
+	ifx_dev->max_hz = pl_data->max_hz;
 
 	/* ensure SPI protocol flags are initialized to enable transfer */
 	ifx_dev->spi_more = 0;
@@ -1025,18 +1033,11 @@ static int ifx_spi_spi_probe(struct spi_device *spi)
 		goto error_ret;
 	}
 
-	pl_data = (struct ifx_modem_platform_data *)spi->dev.platform_data;
-	if (pl_data) {
-		ifx_dev->gpio.reset = pl_data->rst_pmu;
-		ifx_dev->gpio.po = pl_data->pwr_on;
-		ifx_dev->gpio.mrdy = pl_data->mrdy;
-		ifx_dev->gpio.srdy = pl_data->srdy;
-		ifx_dev->gpio.reset_out = pl_data->rst_out;
-	} else {
-		dev_err(&spi->dev, "missing platform data!");
-		ret = -ENODEV;
-		goto error_ret;
-	}
+	ifx_dev->gpio.reset = pl_data->rst_pmu;
+	ifx_dev->gpio.po = pl_data->pwr_on;
+	ifx_dev->gpio.mrdy = pl_data->mrdy;
+	ifx_dev->gpio.srdy = pl_data->srdy;
+	ifx_dev->gpio.reset_out = pl_data->rst_out;
 
 	dev_info(&spi->dev, "gpios %d, %d, %d, %d, %d",
 		 ifx_dev->gpio.reset, ifx_dev->gpio.po, ifx_dev->gpio.mrdy,
diff --git a/drivers/tty/serial/ifx6x60.h b/drivers/tty/serial/ifx6x60.h
index deb7b8d977dc..0ec39b58ccc4 100644
--- a/drivers/tty/serial/ifx6x60.h
+++ b/drivers/tty/serial/ifx6x60.h
@@ -88,7 +88,9 @@ struct ifx_spi_device {
 	dma_addr_t rx_dma;
 	dma_addr_t tx_dma;
 
-	int is_6160;				/* Modem type */
+	int modem;		/* Modem type */
+	int use_dma;		/* provide dma-able addrs in SPI msg */
+	long max_hz;		/* max SPI frequency */
 
 	spinlock_t write_lock;
 	int write_pending;
diff --git a/include/linux/spi/ifx_modem.h b/include/linux/spi/ifx_modem.h
index a68f3b19d112..394fec9e7722 100644
--- a/include/linux/spi/ifx_modem.h
+++ b/include/linux/spi/ifx_modem.h
@@ -2,13 +2,18 @@
 #define LINUX_IFX_MODEM_H
 
 struct ifx_modem_platform_data {
-	unsigned short rst_out; /* modem reset out */
-	unsigned short pwr_on;  /* power on */
-	unsigned short rst_pmu; /* reset modem */
-	unsigned short tx_pwr;  /* modem power threshold */
-	unsigned short srdy;    /* SRDY */
-	unsigned short mrdy;    /* MRDY */
-	unsigned short is_6160;	/* Modem type */
+	unsigned short rst_out;		/* modem reset out */
+	unsigned short pwr_on;		/* power on */
+	unsigned short rst_pmu;		/* reset modem */
+	unsigned short tx_pwr;		/* modem power threshold */
+	unsigned short srdy;		/* SRDY */
+	unsigned short mrdy;		/* MRDY */
+	unsigned char modem_type;	/* Modem type */
+	unsigned long max_hz;		/* max SPI frequency */
+	unsigned short use_dma:1;	/* spi protocol driver supplies
+					   dma-able addrs */
 };
+#define IFX_MODEM_6160	1
+#define IFX_MODEM_6260	2
 
 #endif
-- 
cgit v1.2.3


From d057e5a381cbaec5632117bf62ba49438ab16214 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Mon, 31 Jan 2011 22:29:13 +0200
Subject: mac80211: add HW flag for disabling auto link-PS in AP mode

When operating in AP mode the wl1271 hardware filters out null-data
packets as well as management packets. This makes it impossible for
mac80211 to monitor the PS mode by using the PM bit of incoming frames.

Implement a HW flag to indicate that mac80211 should ignore the PM bit.
In addition, expose ieee80211_sta_ps_transition() to make low-level
drivers capable of controlling PS-mode.

Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/mac80211.h  | 54 ++++++++++++++++++++++++++++++++++++++++++++++++-
 net/mac80211/rx.c       | 27 +++++++++++++++++++++++--
 net/mac80211/sta_info.c |  3 ++-
 net/mac80211/status.c   |  4 ++++
 4 files changed, 84 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d6b0045788ce..0396cecd1d62 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1069,6 +1069,13 @@ enum ieee80211_tkip_key_type {
  *	to decrypt group addressed frames, then IBSS RSN support is still
  *	possible but software crypto will be used. Advertise the wiphy flag
  *	only in that case.
+ *
+ * @IEEE80211_HW_AP_LINK_PS: When operating in AP mode the device
+ *	autonomously manages the PS status of connected stations. When
+ *	this flag is set mac80211 will not trigger PS mode for connected
+ *	stations based on the PM bit of incoming frames.
+ *	Use ieee80211_start_ps()/ieee8021_end_ps() to manually configure
+ *	the PS mode of connected stations.
  */
 enum ieee80211_hw_flags {
 	IEEE80211_HW_HAS_RATE_CONTROL			= 1<<0,
@@ -1093,6 +1100,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_CONNECTION_MONITOR			= 1<<19,
 	IEEE80211_HW_SUPPORTS_CQM_RSSI			= 1<<20,
 	IEEE80211_HW_SUPPORTS_PER_STA_GTK		= 1<<21,
+	IEEE80211_HW_AP_LINK_PS				= 1<<22,
 };
 
 /**
@@ -1701,7 +1709,9 @@ enum ieee80211_ampdu_mlme_action {
  *	station, AP, IBSS/WDS/mesh peer etc. This callback can sleep.
  *
  * @sta_notify: Notifies low level driver about power state transition of an
- *	associated station, AP,  IBSS/WDS/mesh peer etc. Must be atomic.
+ *	associated station, AP,  IBSS/WDS/mesh peer etc. For a VIF operating
+ *	in AP mode, this callback will not be called when the flag
+ *	%IEEE80211_HW_AP_LINK_PS is set. Must be atomic.
  *
  * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max),
  *	bursting) for a hardware TX queue.
@@ -2131,6 +2141,48 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw,
 	local_bh_enable();
 }
 
+/**
+ * ieee80211_sta_ps_transition - PS transition for connected sta
+ *
+ * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS
+ * flag set, use this function to inform mac80211 about a connected station
+ * entering/leaving PS mode.
+ *
+ * This function may not be called in IRQ context or with softirqs enabled.
+ *
+ * Calls to this function for a single hardware must be synchronized against
+ * each other.
+ *
+ * The function returns -EINVAL when the requested PS mode is already set.
+ *
+ * @sta: currently connected sta
+ * @start: start or stop PS
+ */
+int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start);
+
+/**
+ * ieee80211_sta_ps_transition_ni - PS transition for connected sta
+ *                                  (in process context)
+ *
+ * Like ieee80211_sta_ps_transition() but can be called in process context
+ * (internally disables bottom halves). Concurrent call restriction still
+ * applies.
+ *
+ * @sta: currently connected sta
+ * @start: start or stop PS
+ */
+static inline int ieee80211_sta_ps_transition_ni(struct ieee80211_sta *sta,
+						  bool start)
+{
+	int ret;
+
+	local_bh_disable();
+	ret = ieee80211_sta_ps_transition(sta, start);
+	local_bh_enable();
+
+	return ret;
+}
+
 /*
  * The TX headroom reserved by mac80211 for its own tx_status functions.
  * This is enough for the radiotap header.
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 7185c9316be2..d78d6fc333d2 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1105,7 +1105,8 @@ static void ap_sta_ps_start(struct sta_info *sta)
 
 	atomic_inc(&sdata->bss->num_sta_ps);
 	set_sta_flags(sta, WLAN_STA_PS_STA);
-	drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta);
+	if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS))
+		drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta);
 #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG
 	printk(KERN_DEBUG "%s: STA %pM aid %d enters power save mode\n",
 	       sdata->name, sta->sta.addr, sta->sta.aid);
@@ -1134,6 +1135,27 @@ static void ap_sta_ps_end(struct sta_info *sta)
 	ieee80211_sta_ps_deliver_wakeup(sta);
 }
 
+int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start)
+{
+	struct sta_info *sta_inf = container_of(sta, struct sta_info, sta);
+	bool in_ps;
+
+	WARN_ON(!(sta_inf->local->hw.flags & IEEE80211_HW_AP_LINK_PS));
+
+	/* Don't let the same PS state be set twice */
+	in_ps = test_sta_flags(sta_inf, WLAN_STA_PS_STA);
+	if ((start && in_ps) || (!start && !in_ps))
+		return -EINVAL;
+
+	if (start)
+		ap_sta_ps_start(sta_inf);
+	else
+		ap_sta_ps_end(sta_inf);
+
+	return 0;
+}
+EXPORT_SYMBOL(ieee80211_sta_ps_transition);
+
 static ieee80211_rx_result debug_noinline
 ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 {
@@ -1178,7 +1200,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 	 * Change STA power saving mode only at the end of a frame
 	 * exchange sequence.
 	 */
-	if (!ieee80211_has_morefrags(hdr->frame_control) &&
+	if (!(sta->local->hw.flags & IEEE80211_HW_AP_LINK_PS) &&
+	    !ieee80211_has_morefrags(hdr->frame_control) &&
 	    !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) &&
 	    (rx->sdata->vif.type == NL80211_IFTYPE_AP ||
 	     rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) {
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index c426504ed1cf..5a11078827ab 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -899,7 +899,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	struct ieee80211_local *local = sdata->local;
 	int sent, buffered;
 
-	drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta);
+	if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS))
+		drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta);
 
 	if (!skb_queue_empty(&sta->ps_tx_buf))
 		sta_info_clear_tim_bit(sta);
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 38a797217a91..ffb0de9bc2fa 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -98,6 +98,10 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
 	 *  (b) always process RX events before TX status events if ordering
 	 *      can be unknown, for example with different interrupt status
 	 *	bits.
+	 *  (c) if PS mode transitions are manual (i.e. the flag
+	 *      %IEEE80211_HW_AP_LINK_PS is set), always process PS state
+	 *      changes before calling TX status events if ordering can be
+	 *	unknown.
 	 */
 	if (test_sta_flags(sta, WLAN_STA_PS_STA) &&
 	    skb_queue_len(&sta->tx_filtered) < STA_MAX_TX_BUFFER) {
-- 
cgit v1.2.3


From 681d119047761cc59a15c0bb86891f3a878997cf Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni.malinen@atheros.com>
Date: Thu, 3 Feb 2011 18:35:19 +0200
Subject: mac80211: Add testing functionality for TKIP

TKIP countermeasures depend on devices being able to detect Michael
MIC failures on received frames and for stations to report errors to
the AP. In order to test that behavior, it is useful to be able to
send out TKIP frames with incorrect Michael MIC. This testing behavior
has minimal effect on the TX path, so it can be added to mac80211 for
convenient use.

The interface for using this functionality is a file in mac80211
netdev debugfs (tkip_mic_test). Writing a MAC address to the file
makes mac80211 generate a dummy data frame that will be sent out using
invalid Michael MIC value. In AP mode, the address needs to be for one
of the associated stations or ff:ff:ff:ff:ff:ff to use a broadcast
frame. In station mode, the address can be anything, e.g., the current
BSSID. It should be noted that this functionality works correctly only
when associated and using TKIP.

Signed-off-by: Jouni Malinen <jouni.malinen@atheros.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/mac80211.h        |   4 ++
 net/mac80211/debugfs_netdev.c | 102 +++++++++++++++++++++++++++++++++++++++++-
 net/mac80211/wpa.c            |   7 +++
 3 files changed, 112 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 0396cecd1d62..8fcd1691cfb7 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -341,6 +341,9 @@ struct ieee80211_bss_conf {
  *	the off-channel channel when a remain-on-channel offload is done
  *	in hardware -- normal packets still flow and are expected to be
  *	handled properly by the device.
+ * @IEEE80211_TX_INTFL_TKIP_MIC_FAILURE: Marks this packet to be used for TKIP
+ *	testing. It will be sent out with incorrect Michael MIC key to allow
+ *	TKIP countermeasures to be tested.
  *
  * Note: If you have to add new flags to the enumeration, then don't
  *	 forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary.
@@ -370,6 +373,7 @@ enum mac80211_tx_control_flags {
 	IEEE80211_TX_CTL_LDPC			= BIT(22),
 	IEEE80211_TX_CTL_STBC			= BIT(23) | BIT(24),
 	IEEE80211_TX_CTL_TX_OFFCHAN		= BIT(25),
+	IEEE80211_TX_INTFL_TKIP_MIC_FAILURE	= BIT(26),
 };
 
 #define IEEE80211_TX_CTL_STBC_SHIFT		23
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 4cffbf65cccd..dacace6b1393 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -36,7 +36,7 @@ static ssize_t ieee80211_if_read(
 		ret = (*format)(sdata, buf, sizeof(buf));
 	read_unlock(&dev_base_lock);
 
-	if (ret != -EINVAL)
+	if (ret >= 0)
 		ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret);
 
 	return ret;
@@ -221,6 +221,104 @@ static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata,
 
 __IEEE80211_IF_FILE_W(smps);
 
+static ssize_t ieee80211_if_fmt_tkip_mic_test(
+	const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hwaddr_aton(const char *txt, u8 *addr)
+{
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		int a, b;
+
+		a = hex_to_bin(*txt++);
+		if (a < 0)
+			return -1;
+		b = hex_to_bin(*txt++);
+		if (b < 0)
+			return -1;
+		*addr++ = (a << 4) | b;
+		if (i < 5 && *txt++ != ':')
+			return -1;
+	}
+
+	return 0;
+}
+
+static ssize_t ieee80211_if_parse_tkip_mic_test(
+	struct ieee80211_sub_if_data *sdata, const char *buf, int buflen)
+{
+	struct ieee80211_local *local = sdata->local;
+	u8 addr[ETH_ALEN];
+	struct sk_buff *skb;
+	struct ieee80211_hdr *hdr;
+	__le16 fc;
+
+	/*
+	 * Assume colon-delimited MAC address with possible white space
+	 * following.
+	 */
+	if (buflen < 3 * ETH_ALEN - 1)
+		return -EINVAL;
+	if (hwaddr_aton(buf, addr) < 0)
+		return -EINVAL;
+
+	if (!ieee80211_sdata_running(sdata))
+		return -ENOTCONN;
+
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24 + 100);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, local->hw.extra_tx_headroom);
+
+	hdr = (struct ieee80211_hdr *) skb_put(skb, 24);
+	memset(hdr, 0, 24);
+	fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA);
+
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_AP:
+		fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS);
+		/* DA BSSID SA */
+		memcpy(hdr->addr1, addr, ETH_ALEN);
+		memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
+		memcpy(hdr->addr3, sdata->vif.addr, ETH_ALEN);
+		break;
+	case NL80211_IFTYPE_STATION:
+		fc |= cpu_to_le16(IEEE80211_FCTL_TODS);
+		/* BSSID SA DA */
+		if (sdata->vif.bss_conf.bssid == NULL) {
+			dev_kfree_skb(skb);
+			return -ENOTCONN;
+		}
+		memcpy(hdr->addr1, sdata->vif.bss_conf.bssid, ETH_ALEN);
+		memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
+		memcpy(hdr->addr3, addr, ETH_ALEN);
+		break;
+	default:
+		dev_kfree_skb(skb);
+		return -EOPNOTSUPP;
+	}
+	hdr->frame_control = fc;
+
+	/*
+	 * Add some length to the test frame to make it look bit more valid.
+	 * The exact contents does not matter since the recipient is required
+	 * to drop this because of the Michael MIC failure.
+	 */
+	memset(skb_put(skb, 50), 0, 50);
+
+	IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_TKIP_MIC_FAILURE;
+
+	ieee80211_tx_skb(sdata, skb);
+
+	return buflen;
+}
+
+__IEEE80211_IF_FILE_W(tkip_mic_test);
+
 /* AP attributes */
 IEEE80211_IF_FILE(num_sta_ps, u.ap.num_sta_ps, ATOMIC);
 IEEE80211_IF_FILE(dtim_count, u.ap.dtim_count, DEC);
@@ -299,6 +397,7 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata)
 	DEBUGFS_ADD(last_beacon);
 	DEBUGFS_ADD(ave_beacon);
 	DEBUGFS_ADD_MODE(smps, 0600);
+	DEBUGFS_ADD_MODE(tkip_mic_test, 0200);
 }
 
 static void add_ap_files(struct ieee80211_sub_if_data *sdata)
@@ -313,6 +412,7 @@ static void add_ap_files(struct ieee80211_sub_if_data *sdata)
 	DEBUGFS_ADD(num_sta_ps);
 	DEBUGFS_ADD(dtim_count);
 	DEBUGFS_ADD(num_buffered_multicast);
+	DEBUGFS_ADD_MODE(tkip_mic_test, 0200);
 }
 
 static void add_wds_files(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index cd5e730873a8..f1765de2f4bf 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -46,6 +46,11 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx)
 	data = skb->data + hdrlen;
 	data_len = skb->len - hdrlen;
 
+	if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) {
+		/* Need to use software crypto for the test */
+		info->control.hw_key = NULL;
+	}
+
 	if (info->control.hw_key &&
 	    !(tx->flags & IEEE80211_TX_FRAGMENTED) &&
 	    !(tx->key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) {
@@ -64,6 +69,8 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx)
 	key = &tx->key->conf.key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY];
 	mic = skb_put(skb, MICHAEL_MIC_LEN);
 	michael_mic(key, hdr, data, data_len, mic);
+	if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE))
+		mic[0]++;
 
 	return TX_CONTINUE;
 }
-- 
cgit v1.2.3


From 9b99b7f84ea520d2ecaf816bde247a1ad07e454e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sat, 1 Jan 2011 13:51:52 +0100
Subject: kobject: Add missing format attribute specifications

Several functions in <linux/kobject.h> accept printf-style arguments.
Some of these functions have been annotated with a format attribute
declaration while others have not been annotated. Add a format attribute
specification where it is missing.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/kobject.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 8f6d12151048..15e82c132f78 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -85,11 +85,13 @@ static inline const char *kobject_name(const struct kobject *kobj)
 extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype);
 extern int __must_check kobject_add(struct kobject *kobj,
 				    struct kobject *parent,
-				    const char *fmt, ...);
+				    const char *fmt, ...)
+	__attribute__((format(printf, 3, 4)));
 extern int __must_check kobject_init_and_add(struct kobject *kobj,
 					     struct kobj_type *ktype,
 					     struct kobject *parent,
-					     const char *fmt, ...);
+					     const char *fmt, ...)
+	__attribute__((format(printf, 4, 5)));
 
 extern void kobject_del(struct kobject *kobj);
 
@@ -226,6 +228,7 @@ static inline int kobject_uevent_env(struct kobject *kobj,
 
 static inline int add_uevent_var(struct kobj_uevent_env *env,
 				 const char *format, ...)
+	__attribute__((format(printf, 2, 3)))
 { return 0; }
 
 static inline int kobject_action_type(const char *buf, size_t count,
-- 
cgit v1.2.3


From 8ba6ebf583f12da32036fc0f003ab4043e54692e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sun, 23 Jan 2011 17:17:24 +0100
Subject: Dynamic debug: Add more flags

Add flags that allow the user to specify via debugfs whether or not the
module name, function name, line number and/or thread ID have to be
included in the printed message.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Cc: Greg Banks <gnb@fmeh.org>
Cc: Konrad Rzeszutek Wilk <konrad@darnok.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 Documentation/dynamic-debug-howto.txt | 12 +++++--
 include/linux/dynamic_debug.h         |  8 ++++-
 lib/dynamic_debug.c                   | 60 +++++++++++++++++++++++++++++------
 3 files changed, 68 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/dynamic-debug-howto.txt b/Documentation/dynamic-debug-howto.txt
index 58ea64a96165..e6c4b757025b 100644
--- a/Documentation/dynamic-debug-howto.txt
+++ b/Documentation/dynamic-debug-howto.txt
@@ -205,12 +205,20 @@ of the characters:
 
 The flags are:
 
+f
+    Include the function name in the printed message
+l
+    Include line number in the printed message
+m
+    Include module name in the printed message
 p
     Causes a printk() message to be emitted to dmesg
+t
+    Include thread ID in messages not generated from interrupt context
 
-Note the regexp ^[-+=][scp]+$ matches a flags specification.
+Note the regexp ^[-+=][flmpt]+$ matches a flags specification.
 Note also that there is no convenient syntax to remove all
-the flags at once, you need to use "-psc".
+the flags at once, you need to use "-flmpt".
 
 
 Debug messages during boot process
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 1c70028f81f9..0c9653f11c18 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -31,6 +31,10 @@ struct _ddebug {
 	 * writes commands to <debugfs>/dynamic_debug/control
 	 */
 #define _DPRINTK_FLAGS_PRINT   (1<<0)  /* printk() a message using the format */
+#define _DPRINTK_FLAGS_INCL_MODNAME	(1<<1)
+#define _DPRINTK_FLAGS_INCL_FUNCNAME	(1<<2)
+#define _DPRINTK_FLAGS_INCL_LINENO	(1<<3)
+#define _DPRINTK_FLAGS_INCL_TID		(1<<4)
 #define _DPRINTK_FLAGS_DEFAULT 0
 	unsigned int flags:8;
 	char enabled;
@@ -42,6 +46,8 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 
 #if defined(CONFIG_DYNAMIC_DEBUG)
 extern int ddebug_remove_module(const char *mod_name);
+extern int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
 
 #define dynamic_pr_debug(fmt, ...) do {					\
 	static struct _ddebug descriptor				\
@@ -50,7 +56,7 @@ extern int ddebug_remove_module(const char *mod_name);
 	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
 		_DPRINTK_FLAGS_DEFAULT };				\
 	if (unlikely(descriptor.enabled))				\
-		printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);		\
+		__dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \
 	} while (0)
 
 
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index b335acb43be2..863c83430964 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2008 Jason Baron <jbaron@redhat.com>
  * By Greg Banks <gnb@melbourne.sgi.com>
  * Copyright (c) 2008 Silicon Graphics Inc.  All Rights Reserved.
+ * Copyright (C) 2011 Bart Van Assche.  All Rights Reserved.
  */
 
 #include <linux/kernel.h>
@@ -27,6 +28,7 @@
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/jump_label.h>
+#include <linux/hardirq.h>
 
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
@@ -63,15 +65,25 @@ static inline const char *basename(const char *path)
 	return tail ? tail+1 : path;
 }
 
+static struct { unsigned flag:8; char opt_char; } opt_array[] = {
+	{ _DPRINTK_FLAGS_PRINT, 'p' },
+	{ _DPRINTK_FLAGS_INCL_MODNAME, 'm' },
+	{ _DPRINTK_FLAGS_INCL_FUNCNAME, 'f' },
+	{ _DPRINTK_FLAGS_INCL_LINENO, 'l' },
+	{ _DPRINTK_FLAGS_INCL_TID, 't' },
+};
+
 /* format a string into buf[] which describes the _ddebug's flags */
 static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
 				    size_t maxlen)
 {
 	char *p = buf;
+	int i;
 
 	BUG_ON(maxlen < 4);
-	if (dp->flags & _DPRINTK_FLAGS_PRINT)
-		*p++ = 'p';
+	for (i = 0; i < ARRAY_SIZE(opt_array); ++i)
+		if (dp->flags & opt_array[i].flag)
+			*p++ = opt_array[i].opt_char;
 	if (p == buf)
 		*p++ = '-';
 	*p = '\0';
@@ -343,7 +355,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 			       unsigned int *maskp)
 {
 	unsigned flags = 0;
-	int op = '=';
+	int op = '=', i;
 
 	switch (*str) {
 	case '+':
@@ -358,13 +370,14 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 		printk(KERN_INFO "%s: op='%c'\n", __func__, op);
 
 	for ( ; *str ; ++str) {
-		switch (*str) {
-		case 'p':
-			flags |= _DPRINTK_FLAGS_PRINT;
-			break;
-		default:
-			return -EINVAL;
+		for (i = ARRAY_SIZE(opt_array) - 1; i >= 0; i--) {
+			if (*str == opt_array[i].opt_char) {
+				flags |= opt_array[i].flag;
+				break;
+			}
 		}
+		if (i < 0)
+			return -EINVAL;
 	}
 	if (flags == 0)
 		return -EINVAL;
@@ -413,6 +426,35 @@ static int ddebug_exec_query(char *query_string)
 	return 0;
 }
 
+int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
+{
+	va_list args;
+	int res;
+
+	BUG_ON(!descriptor);
+	BUG_ON(!fmt);
+
+	va_start(args, fmt);
+	res = printk(KERN_DEBUG);
+	if (descriptor->flags & _DPRINTK_FLAGS_INCL_TID) {
+		if (in_interrupt())
+			res += printk(KERN_CONT "<intr> ");
+		else
+			res += printk(KERN_CONT "[%d] ", task_pid_vnr(current));
+	}
+	if (descriptor->flags & _DPRINTK_FLAGS_INCL_MODNAME)
+		res += printk(KERN_CONT "%s:", descriptor->modname);
+	if (descriptor->flags & _DPRINTK_FLAGS_INCL_FUNCNAME)
+		res += printk(KERN_CONT "%s:", descriptor->function);
+	if (descriptor->flags & _DPRINTK_FLAGS_INCL_LINENO)
+		res += printk(KERN_CONT "%d ", descriptor->lineno);
+	res += vprintk(fmt, args);
+	va_end(args);
+
+	return res;
+}
+EXPORT_SYMBOL(__dynamic_pr_debug);
+
 static __initdata char ddebug_setup_string[1024];
 static __init int ddebug_setup_query(char *str)
 {
-- 
cgit v1.2.3


From 072fc8f0a8df9bf36392f15b729044cb2ad27332 Mon Sep 17 00:00:00 2001
From: Bob Liu <lliubbo@gmail.com>
Date: Wed, 26 Jan 2011 18:33:32 +0800
Subject: firmware_classs: change val uevent's type to bool

Some place in firmware_class.c using "int uevent" define, but others use "bool
uevent".
This patch replace all int uevent define to bool.

Signed-off-by: Bob Liu <lliubbo@gmail.com>
Acked-by: Dmitry Torokhov <dtor@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/base/firmware_class.c | 7 +++----
 include/linux/firmware.h      | 4 ++--
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 40af43ebd92d..8c798ef7f13f 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -593,8 +593,7 @@ int
 request_firmware(const struct firmware **firmware_p, const char *name,
                  struct device *device)
 {
-        int uevent = 1;
-        return _request_firmware(firmware_p, name, device, uevent, false);
+        return _request_firmware(firmware_p, name, device, true, false);
 }
 
 /**
@@ -618,7 +617,7 @@ struct firmware_work {
 	struct device *device;
 	void *context;
 	void (*cont)(const struct firmware *fw, void *context);
-	int uevent;
+	bool uevent;
 };
 
 static int request_firmware_work_func(void *arg)
@@ -661,7 +660,7 @@ static int request_firmware_work_func(void *arg)
  **/
 int
 request_firmware_nowait(
-	struct module *module, int uevent,
+	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context))
 {
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index 53d1e6c4f848..21b3e7588abd 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -39,7 +39,7 @@ struct builtin_fw {
 int request_firmware(const struct firmware **fw, const char *name,
 		     struct device *device);
 int request_firmware_nowait(
-	struct module *module, int uevent,
+	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context));
 
@@ -52,7 +52,7 @@ static inline int request_firmware(const struct firmware **fw,
 	return -EINVAL;
 }
 static inline int request_firmware_nowait(
-	struct module *module, int uevent,
+	struct module *module, bool uevent,
 	const char *name, struct device *device, gfp_t gfp, void *context,
 	void (*cont)(const struct firmware *fw, void *context))
 {
-- 
cgit v1.2.3


From d33601644cd3b09afb2edd9474517edc441c8fad Mon Sep 17 00:00:00 2001
From: Nathan Fontenot <nfont@austin.ibm.com>
Date: Thu, 20 Jan 2011 10:44:29 -0600
Subject: memory hotplug: Update phys_index to [start|end]_section_nr

Update the 'phys_index' property of a the memory_block struct to be
called start_section_nr, and add a end_section_nr property.  The
data tracked here is the same but the updated naming is more in line
with what is stored here, namely the first and last section number
that the memory block spans.

The names presented to userspace remain the same, phys_index for
start_section_nr and end_phys_index for end_section_nr, to avoid breaking
anything in userspace.

This also updates the node sysfs code to be aware of the new capability for
a memory block to contain multiple memory sections and be aware of the memory
block structure name changes (start_section_nr).  This requires an additional
parameter to unregister_mem_sect_under_nodes so that we know which memory
section of the memory block to unregister.

Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Reviewed-by: Robin Holt <holt@sgi.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/base/memory.c  | 41 +++++++++++++++++++++++++++++++----------
 drivers/base/node.c    | 12 ++++++++----
 include/linux/memory.h |  3 ++-
 include/linux/node.h   |  6 ++++--
 4 files changed, 45 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 0b7040042587..71b4a32b1710 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -97,7 +97,7 @@ int register_memory(struct memory_block *memory)
 	int error;
 
 	memory->sysdev.cls = &memory_sysdev_class;
-	memory->sysdev.id = memory->phys_index / sections_per_block;
+	memory->sysdev.id = memory->start_section_nr / sections_per_block;
 
 	error = sysdev_register(&memory->sysdev);
 	return error;
@@ -138,12 +138,26 @@ static unsigned long get_memory_block_size(void)
  * uses.
  */
 
-static ssize_t show_mem_phys_index(struct sys_device *dev,
+static ssize_t show_mem_start_phys_index(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
-	return sprintf(buf, "%08lx\n", mem->phys_index / sections_per_block);
+	unsigned long phys_index;
+
+	phys_index = mem->start_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
+}
+
+static ssize_t show_mem_end_phys_index(struct sys_device *dev,
+			struct sysdev_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, sysdev);
+	unsigned long phys_index;
+
+	phys_index = mem->end_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
 }
 
 /*
@@ -158,7 +172,7 @@ static ssize_t show_mem_removable(struct sys_device *dev,
 		container_of(dev, struct memory_block, sysdev);
 
 	for (i = 0; i < sections_per_block; i++) {
-		pfn = section_nr_to_pfn(mem->phys_index + i);
+		pfn = section_nr_to_pfn(mem->start_section_nr + i);
 		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
 	}
 
@@ -275,14 +289,15 @@ static int memory_block_change_state(struct memory_block *mem,
 		mem->state = MEM_GOING_OFFLINE;
 
 	for (i = 0; i < sections_per_block; i++) {
-		ret = memory_section_action(mem->phys_index + i, to_state);
+		ret = memory_section_action(mem->start_section_nr + i,
+					    to_state);
 		if (ret)
 			break;
 	}
 
 	if (ret) {
 		for (i = 0; i < sections_per_block; i++)
-			memory_section_action(mem->phys_index + i,
+			memory_section_action(mem->start_section_nr + i,
 					      from_state_req);
 
 		mem->state = from_state_req;
@@ -330,7 +345,8 @@ static ssize_t show_phys_device(struct sys_device *dev,
 	return sprintf(buf, "%d\n", mem->phys_device);
 }
 
-static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
+static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
 static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
 static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
 static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
@@ -522,16 +538,20 @@ static int init_memory_block(struct memory_block **memory,
 		return -ENOMEM;
 
 	scn_nr = __section_nr(section);
-	mem->phys_index = base_memory_block_id(scn_nr) * sections_per_block;
+	mem->start_section_nr =
+			base_memory_block_id(scn_nr) * sections_per_block;
+	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	mem->section_count++;
 	mutex_init(&mem->state_mutex);
-	start_pfn = section_nr_to_pfn(mem->phys_index);
+	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
 
 	ret = register_memory(mem);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_index);
+	if (!ret)
+		ret = mem_create_simple_file(mem, end_phys_index);
 	if (!ret)
 		ret = mem_create_simple_file(mem, state);
 	if (!ret)
@@ -575,11 +595,12 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
 
 	mutex_lock(&mem_sysfs_mutex);
 	mem = find_memory_block(section);
+	unregister_mem_sect_under_nodes(mem, __section_nr(section));
 
 	mem->section_count--;
 	if (mem->section_count == 0) {
-		unregister_mem_sect_under_nodes(mem);
 		mem_remove_simple_file(mem, phys_index);
+		mem_remove_simple_file(mem, end_phys_index);
 		mem_remove_simple_file(mem, state);
 		mem_remove_simple_file(mem, phys_device);
 		mem_remove_simple_file(mem, removable);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 36b43052001d..b3b72d64e805 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -375,8 +375,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 		return -EFAULT;
 	if (!node_online(nid))
 		return 0;
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
-	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+
+	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+	sect_end_pfn += PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;
 
@@ -400,7 +402,8 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 }
 
 /* unregister memory section under all nodes that it spans */
-int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+				    unsigned long phys_index)
 {
 	NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
@@ -412,7 +415,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 	if (!unlinked_nodes)
 		return -ENOMEM;
 	nodes_clear(*unlinked_nodes);
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+
+	sect_start_pfn = section_nr_to_pfn(phys_index);
 	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int nid;
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 06c1fa0a5c7b..e1e3b2b84f85 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -21,7 +21,8 @@
 #include <linux/mutex.h>
 
 struct memory_block {
-	unsigned long phys_index;
+	unsigned long start_section_nr;
+	unsigned long end_section_nr;
 	unsigned long state;
 	int section_count;
 
diff --git a/include/linux/node.h b/include/linux/node.h
index 1466945cc9ef..92370e22343c 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -39,7 +39,8 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int register_mem_sect_under_node(struct memory_block *mem_blk,
 						int nid);
-extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk);
+extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+					   unsigned long phys_index);
 
 #ifdef CONFIG_HUGETLBFS
 extern void register_hugetlbfs_with_node(node_registration_func_t doregister,
@@ -67,7 +68,8 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk,
 {
 	return 0;
 }
-static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+						  unsigned long phys_index)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 04bea68b2f0eeebb089ecc67b618795925268b4a Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Date: Mon, 24 Jan 2011 09:58:55 +0530
Subject: of/pci: move of_irq_map_pci() into generic code

There is a tiny difference between PPC32 and PPC64. Microblaze uses the
PPC32 variant.

Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
[grant.likely@secretlab.ca: Added comment to #endif, moved documentation
	block to function implementation, fixed for non ppc and microblaze
	compiles]
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/microblaze/include/asm/pci-bridge.h | 12 +++++
 arch/microblaze/include/asm/prom.h       | 15 ------
 arch/microblaze/kernel/prom_parse.c      | 77 ---------------------------
 arch/microblaze/pci/pci-common.c         |  1 +
 arch/powerpc/include/asm/pci-bridge.h    | 10 ++++
 arch/powerpc/include/asm/prom.h          | 15 ------
 arch/powerpc/kernel/pci-common.c         |  1 +
 arch/powerpc/kernel/prom_parse.c         | 84 -----------------------------
 drivers/of/Kconfig                       |  6 +++
 drivers/of/Makefile                      |  1 +
 drivers/of/of_pci.c                      | 91 ++++++++++++++++++++++++++++++++
 include/linux/of_pci.h                   |  9 ++++
 12 files changed, 131 insertions(+), 191 deletions(-)
 create mode 100644 drivers/of/of_pci.c
 create mode 100644 include/linux/of_pci.h

(limited to 'include')

diff --git a/arch/microblaze/include/asm/pci-bridge.h b/arch/microblaze/include/asm/pci-bridge.h
index 0c68764ab547..10717669e0c2 100644
--- a/arch/microblaze/include/asm/pci-bridge.h
+++ b/arch/microblaze/include/asm/pci-bridge.h
@@ -104,11 +104,22 @@ struct pci_controller {
 	int global_number;	/* PCI domain number */
 };
 
+#ifdef CONFIG_PCI
 static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 {
 	return bus->sysdata;
 }
 
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+	struct pci_controller *host;
+
+	if (bus->self)
+		return pci_device_to_OF_node(bus->self);
+	host = pci_bus_to_host(bus);
+	return host ? host->dn : NULL;
+}
+
 static inline int isa_vaddr_is_ioport(void __iomem *address)
 {
 	/* No specific ISA handling on ppc32 at this stage, it
@@ -116,6 +127,7 @@ static inline int isa_vaddr_is_ioport(void __iomem *address)
 	 */
 	return 0;
 }
+#endif /* CONFIG_PCI */
 
 /* These are used for config access before all the PCI probing
    has been done. */
diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h
index 2e72af078b05..d0890d36ef61 100644
--- a/arch/microblaze/include/asm/prom.h
+++ b/arch/microblaze/include/asm/prom.h
@@ -64,21 +64,6 @@ extern void kdump_move_device_tree(void);
 /* CPU OF node matching */
 struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-struct of_irq;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
diff --git a/arch/microblaze/kernel/prom_parse.c b/arch/microblaze/kernel/prom_parse.c
index 9ae24f4b882b..47187cc2cf00 100644
--- a/arch/microblaze/kernel/prom_parse.c
+++ b/arch/microblaze/kernel/prom_parse.c
@@ -2,88 +2,11 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/pci_regs.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
 #include <linux/of_address.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
-
-#ifdef CONFIG_PCI
-int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
-{
-	struct device_node *dn, *ppnode;
-	struct pci_dev *ppdev;
-	u32 lspec;
-	u32 laddr[3];
-	u8 pin;
-	int rc;
-
-	/* Check if we have a device node, if yes, fallback to standard OF
-	 * parsing
-	 */
-	dn = pci_device_to_OF_node(pdev);
-	if (dn)
-		return of_irq_map_one(dn, 0, out_irq);
-
-	/* Ok, we don't, time to have fun. Let's start by building up an
-	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
-	 * for PCI. If you do different, then don't use that routine.
-	 */
-	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
-	if (rc != 0)
-		return rc;
-	/* No pin, exit */
-	if (pin == 0)
-		return -ENODEV;
-
-	/* Now we walk up the PCI tree */
-	lspec = pin;
-	for (;;) {
-		/* Get the pci_dev of our parent */
-		ppdev = pdev->bus->self;
-
-		/* Ouch, it's a host bridge... */
-		if (ppdev == NULL) {
-			struct pci_controller *host;
-			host = pci_bus_to_host(pdev->bus);
-			ppnode = host ? host->dn : NULL;
-			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
-		} else
-			/* We found a P2P bridge, check if it has a node */
-			ppnode = pci_device_to_OF_node(ppdev);
-
-		/* Ok, we have found a parent with a device-node, hand over to
-		 * the OF parsing code.
-		 * We build a unit address from the linux device to be used for
-		 * resolution. Note that we use the linux bus number which may
-		 * not match your firmware bus numbering.
-		 * Fortunately, in most cases, interrupt-map-mask doesn't
-		 * include the bus number as part of the matching.
-		 * You should still be careful about that though if you intend
-		 * to rely on this function (you ship  a firmware that doesn't
-		 * create device nodes for all PCI devices).
-		 */
-		if (ppnode)
-			break;
-
-		/* We can only get here if we hit a P2P bridge with no node,
-		 * let's do standard swizzling and try again
-		 */
-		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
-		pdev = ppdev;
-	}
-
-	laddr[0] = (pdev->bus->number << 16)
-		| (pdev->devfn << 8);
-	laddr[1]  = laddr[2] = 0;
-	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
-}
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
-#endif /* CONFIG_PCI */
 
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index e363615d6798..1e01a1253631 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/of_pci.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 51e9e6f90d12..edeb80fdd2c3 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -171,6 +171,16 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 	return bus->sysdata;
 }
 
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+	struct pci_controller *host;
+
+	if (bus->self)
+		return pci_device_to_OF_node(bus->self);
+	host = pci_bus_to_host(bus);
+	return host ? host->dn : NULL;
+}
+
 static inline int isa_vaddr_is_ioport(void __iomem *address)
 {
 	/* No specific ISA handling on ppc32 at this stage, it
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index d72757585595..c189aa5fe1f4 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -70,21 +70,6 @@ static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 #define of_node_to_nid of_node_to_nid
 
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-struct of_irq;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
 extern void of_instantiate_rtc(void);
 
 /* These includes are put at the bottom because they may contain things
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 10a44e68ef11..eb341be9a4d9 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/of_address.h>
+#include <linux/of_pci.h>
 #include <linux/mm.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index c2b7a07cc3d3..47187cc2cf00 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -2,95 +2,11 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/pci_regs.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
 #include <linux/of_address.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
-
-#ifdef CONFIG_PCI
-int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
-{
-	struct device_node *dn, *ppnode;
-	struct pci_dev *ppdev;
-	u32 lspec;
-	u32 laddr[3];
-	u8 pin;
-	int rc;
-
-	/* Check if we have a device node, if yes, fallback to standard OF
-	 * parsing
-	 */
-	dn = pci_device_to_OF_node(pdev);
-	if (dn) {
-		rc = of_irq_map_one(dn, 0, out_irq);
-		if (!rc)
-			return rc;
-	}
-
-	/* Ok, we don't, time to have fun. Let's start by building up an
-	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
-	 * for PCI. If you do different, then don't use that routine.
-	 */
-	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
-	if (rc != 0)
-		return rc;
-	/* No pin, exit */
-	if (pin == 0)
-		return -ENODEV;
-
-	/* Now we walk up the PCI tree */
-	lspec = pin;
-	for (;;) {
-		/* Get the pci_dev of our parent */
-		ppdev = pdev->bus->self;
-
-		/* Ouch, it's a host bridge... */
-		if (ppdev == NULL) {
-#ifdef CONFIG_PPC64
-			ppnode = pci_bus_to_OF_node(pdev->bus);
-#else
-			struct pci_controller *host;
-			host = pci_bus_to_host(pdev->bus);
-			ppnode = host ? host->dn : NULL;
-#endif
-			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
-		} else
-			/* We found a P2P bridge, check if it has a node */
-			ppnode = pci_device_to_OF_node(ppdev);
-
-		/* Ok, we have found a parent with a device-node, hand over to
-		 * the OF parsing code.
-		 * We build a unit address from the linux device to be used for
-		 * resolution. Note that we use the linux bus number which may
-		 * not match your firmware bus numbering.
-		 * Fortunately, in most cases, interrupt-map-mask doesn't include
-		 * the bus number as part of the matching.
-		 * You should still be careful about that though if you intend
-		 * to rely on this function (you ship  a firmware that doesn't
-		 * create device nodes for all PCI devices).
-		 */
-		if (ppnode)
-			break;
-
-		/* We can only get here if we hit a P2P bridge with no node,
-		 * let's do standard swizzling and try again
-		 */
-		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
-		pdev = ppdev;
-	}
-
-	laddr[0] = (pdev->bus->number << 16)
-		| (pdev->devfn << 8);
-	laddr[1]  = laddr[2] = 0;
-	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
-}
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
-#endif /* CONFIG_PCI */
 
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 3c6e100a3ad0..efabbf9dd607 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -69,4 +69,10 @@ config OF_MDIO
 	help
 	  OpenFirmware MDIO bus (Ethernet PHY) accessors
 
+config OF_PCI
+	def_tristate PCI
+	depends on PCI && (PPC || MICROBLAZE)
+	help
+	  OpenFirmware PCI bus accessors
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 3ab21a0a4907..f7861ed2f287 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_OF_I2C)	+= of_i2c.o
 obj-$(CONFIG_OF_NET)	+= of_net.o
 obj-$(CONFIG_OF_SPI)	+= of_spi.o
 obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
+obj-$(CONFIG_OF_PCI)	+= of_pci.o
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
new file mode 100644
index 000000000000..314535fa32c1
--- /dev/null
+++ b/drivers/of/of_pci.c
@@ -0,0 +1,91 @@
+#include <linux/kernel.h>
+#include <linux/of_pci.h>
+#include <asm/prom.h>
+
+/**
+ * of_irq_map_pci - Resolve the interrupt for a PCI device
+ * @pdev:       the device whose interrupt is to be resolved
+ * @out_irq:    structure of_irq filled by this function
+ *
+ * This function resolves the PCI interrupt for a given PCI device. If a
+ * device-node exists for a given pci_dev, it will use normal OF tree
+ * walking. If not, it will implement standard swizzling and walk up the
+ * PCI tree until an device-node is found, at which point it will finish
+ * resolving using the OF tree walking.
+ */
+int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
+{
+	struct device_node *dn, *ppnode;
+	struct pci_dev *ppdev;
+	u32 lspec;
+	__be32 lspec_be;
+	__be32 laddr[3];
+	u8 pin;
+	int rc;
+
+	/* Check if we have a device node, if yes, fallback to standard
+	 * device tree parsing
+	 */
+	dn = pci_device_to_OF_node(pdev);
+	if (dn) {
+		rc = of_irq_map_one(dn, 0, out_irq);
+		if (!rc)
+			return rc;
+	}
+
+	/* Ok, we don't, time to have fun. Let's start by building up an
+	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
+	 * for PCI. If you do different, then don't use that routine.
+	 */
+	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
+	if (rc != 0)
+		return rc;
+	/* No pin, exit */
+	if (pin == 0)
+		return -ENODEV;
+
+	/* Now we walk up the PCI tree */
+	lspec = pin;
+	for (;;) {
+		/* Get the pci_dev of our parent */
+		ppdev = pdev->bus->self;
+
+		/* Ouch, it's a host bridge... */
+		if (ppdev == NULL) {
+			ppnode = pci_bus_to_OF_node(pdev->bus);
+
+			/* No node for host bridge ? give up */
+			if (ppnode == NULL)
+				return -EINVAL;
+		} else {
+			/* We found a P2P bridge, check if it has a node */
+			ppnode = pci_device_to_OF_node(ppdev);
+		}
+
+		/* Ok, we have found a parent with a device-node, hand over to
+		 * the OF parsing code.
+		 * We build a unit address from the linux device to be used for
+		 * resolution. Note that we use the linux bus number which may
+		 * not match your firmware bus numbering.
+		 * Fortunately, in most cases, interrupt-map-mask doesn't
+		 * include the bus number as part of the matching.
+		 * You should still be careful about that though if you intend
+		 * to rely on this function (you ship  a firmware that doesn't
+		 * create device nodes for all PCI devices).
+		 */
+		if (ppnode)
+			break;
+
+		/* We can only get here if we hit a P2P bridge with no node,
+		 * let's do standard swizzling and try again
+		 */
+		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
+		pdev = ppdev;
+	}
+
+	lspec_be = cpu_to_be32(lspec);
+	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));
+	laddr[1]  = laddr[2] = cpu_to_be32(0);
+	return of_irq_map_raw(ppnode, &lspec_be, 1, laddr, out_irq);
+}
+EXPORT_SYMBOL_GPL(of_irq_map_pci);
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
new file mode 100644
index 000000000000..85a27b650d76
--- /dev/null
+++ b/include/linux/of_pci.h
@@ -0,0 +1,9 @@
+#ifndef __OF_PCI_H
+#define __OF_PCI_H
+
+#include <linux/pci.h>
+
+struct pci_dev;
+struct of_irq;
+int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
+#endif
-- 
cgit v1.2.3


From c8cf203a1d228fa001b95534f639ffb7a23d5386 Mon Sep 17 00:00:00 2001
From: Robert Morell <rmorell@nvidia.com>
Date: Wed, 26 Jan 2011 19:06:47 -0800
Subject: USB: HCD: Add usb_hcd prefix to exported functions

The convention is to prefix symbols exported from the USB HCD core with
"usb_hcd".  This change makes unmap_urb_setup_for_dma() and
unmap_urb_for_dma() consistent with that.

Signed-off-by: Robert Morell <rmorell@nvidia.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/core/hcd.c       | 16 ++++++++--------
 drivers/usb/host/imx21-hcd.c |  5 +++--
 drivers/usb/musb/musb_host.c |  4 ++--
 include/linux/usb/hcd.h      |  4 ++--
 4 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 6a95017fa62b..335c1ddb260d 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1262,7 +1262,7 @@ static void hcd_free_coherent(struct usb_bus *bus, dma_addr_t *dma_handle,
 	*dma_handle = 0;
 }
 
-void unmap_urb_setup_for_dma(struct usb_hcd *hcd, struct urb *urb)
+void usb_hcd_unmap_urb_setup_for_dma(struct usb_hcd *hcd, struct urb *urb)
 {
 	if (urb->transfer_flags & URB_SETUP_MAP_SINGLE)
 		dma_unmap_single(hcd->self.controller,
@@ -1279,13 +1279,13 @@ void unmap_urb_setup_for_dma(struct usb_hcd *hcd, struct urb *urb)
 	/* Make it safe to call this routine more than once */
 	urb->transfer_flags &= ~(URB_SETUP_MAP_SINGLE | URB_SETUP_MAP_LOCAL);
 }
-EXPORT_SYMBOL_GPL(unmap_urb_setup_for_dma);
+EXPORT_SYMBOL_GPL(usb_hcd_unmap_urb_setup_for_dma);
 
-void unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
+void usb_hcd_unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
 {
 	enum dma_data_direction dir;
 
-	unmap_urb_setup_for_dma(hcd, urb);
+	usb_hcd_unmap_urb_setup_for_dma(hcd, urb);
 
 	dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	if (urb->transfer_flags & URB_DMA_MAP_SG)
@@ -1314,7 +1314,7 @@ void unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
 	urb->transfer_flags &= ~(URB_DMA_MAP_SG | URB_DMA_MAP_PAGE |
 			URB_DMA_MAP_SINGLE | URB_MAP_LOCAL);
 }
-EXPORT_SYMBOL_GPL(unmap_urb_for_dma);
+EXPORT_SYMBOL_GPL(usb_hcd_unmap_urb_for_dma);
 
 static int map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 			   gfp_t mem_flags)
@@ -1410,7 +1410,7 @@ static int map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 		}
 		if (ret && (urb->transfer_flags & (URB_SETUP_MAP_SINGLE |
 				URB_SETUP_MAP_LOCAL)))
-			unmap_urb_for_dma(hcd, urb);
+			usb_hcd_unmap_urb_for_dma(hcd, urb);
 	}
 	return ret;
 }
@@ -1451,7 +1451,7 @@ int usb_hcd_submit_urb (struct urb *urb, gfp_t mem_flags)
 		if (likely(status == 0)) {
 			status = hcd->driver->urb_enqueue(hcd, urb, mem_flags);
 			if (unlikely(status))
-				unmap_urb_for_dma(hcd, urb);
+				usb_hcd_unmap_urb_for_dma(hcd, urb);
 		}
 	}
 
@@ -1557,7 +1557,7 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 			!status))
 		status = -EREMOTEIO;
 
-	unmap_urb_for_dma(hcd, urb);
+	usb_hcd_unmap_urb_for_dma(hcd, urb);
 	usbmon_urb_complete(&hcd->self, urb, status);
 	usb_unanchor_urb(urb);
 
diff --git a/drivers/usb/host/imx21-hcd.c b/drivers/usb/host/imx21-hcd.c
index f90d003f2302..b7dfda8a1d51 100644
--- a/drivers/usb/host/imx21-hcd.c
+++ b/drivers/usb/host/imx21-hcd.c
@@ -927,7 +927,8 @@ static void schedule_nonisoc_etd(struct imx21 *imx21, struct urb *urb)
 		if (state == US_CTRL_SETUP) {
 			dir = TD_DIR_SETUP;
 			if (unsuitable_for_dma(urb->setup_dma))
-				unmap_urb_setup_for_dma(imx21->hcd, urb);
+				usb_hcd_unmap_urb_setup_for_dma(imx21->hcd,
+					urb);
 			etd->dma_handle = urb->setup_dma;
 			etd->cpu_buffer = urb->setup_packet;
 			bufround = 0;
@@ -943,7 +944,7 @@ static void schedule_nonisoc_etd(struct imx21 *imx21, struct urb *urb)
 		dir = usb_pipeout(pipe) ? TD_DIR_OUT : TD_DIR_IN;
 		bufround = (dir == TD_DIR_IN) ? 1 : 0;
 		if (unsuitable_for_dma(urb->transfer_dma))
-			unmap_urb_for_dma(imx21->hcd, urb);
+			usb_hcd_unmap_urb_for_dma(imx21->hcd, urb);
 
 		etd->dma_handle = urb->transfer_dma;
 		etd->cpu_buffer = urb->transfer_buffer;
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 4d5bcb4e14d2..4d2f3f79c425 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -1336,7 +1336,7 @@ void musb_host_tx(struct musb *musb, u8 epnum)
 	if (length > qh->maxpacket)
 		length = qh->maxpacket;
 	/* Unmap the buffer so that CPU can use it */
-	unmap_urb_for_dma(musb_to_hcd(musb), urb);
+	usb_hcd_unmap_urb_for_dma(musb_to_hcd(musb), urb);
 	musb_write_fifo(hw_ep, length, urb->transfer_buffer + offset);
 	qh->segsize = length;
 
@@ -1758,7 +1758,7 @@ void musb_host_rx(struct musb *musb, u8 epnum)
 
 		if (!dma) {
 			/* Unmap the buffer so that CPU can use it */
-			unmap_urb_for_dma(musb_to_hcd(musb), urb);
+			usb_hcd_unmap_urb_for_dma(musb_to_hcd(musb), urb);
 			done = musb_host_packet_rx(musb, urb,
 					epnum, iso_err);
 			DBG(6, "read %spacket\n", done ? "last " : "");
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index dd6ee49a0844..395704bdf5cc 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -329,8 +329,8 @@ extern int usb_hcd_submit_urb(struct urb *urb, gfp_t mem_flags);
 extern int usb_hcd_unlink_urb(struct urb *urb, int status);
 extern void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb,
 		int status);
-extern void unmap_urb_setup_for_dma(struct usb_hcd *, struct urb *);
-extern void unmap_urb_for_dma(struct usb_hcd *, struct urb *);
+extern void usb_hcd_unmap_urb_setup_for_dma(struct usb_hcd *, struct urb *);
+extern void usb_hcd_unmap_urb_for_dma(struct usb_hcd *, struct urb *);
 extern void usb_hcd_flush_endpoint(struct usb_device *udev,
 		struct usb_host_endpoint *ep);
 extern void usb_hcd_disable_endpoint(struct usb_device *udev,
-- 
cgit v1.2.3


From 2694a48d9007a8bdf1731c1b97d4942c9cc49296 Mon Sep 17 00:00:00 2001
From: Robert Morell <rmorell@nvidia.com>
Date: Wed, 26 Jan 2011 19:06:48 -0800
Subject: USB: HCD: Add driver hooks for (un)?map_urb_for_dma

Provide optional hooks for the host controller driver to override the
default DMA mapping and unmapping routines.  In general, these shouldn't
be necessary unless the host controller has special DMA requirements,
such as alignment contraints.  If these are not specified, the
general usb_hcd_(un)?map_urb_for_dma functions will be used instead.
Also, pass the status to unmap_urb_for_dma so it can know whether the
DMA buffer has been overwritten.

Finally, add a flag to be used by these implementations if they
allocated a temporary buffer so it can be freed properly when unmapping.

Signed-off-by: Robert Morell <rmorell@nvidia.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/core/hcd.c  | 22 ++++++++++++++++++++--
 include/linux/usb.h     |  1 +
 include/linux/usb/hcd.h | 15 +++++++++++++++
 3 files changed, 36 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 335c1ddb260d..d0b782c4523a 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1281,6 +1281,14 @@ void usb_hcd_unmap_urb_setup_for_dma(struct usb_hcd *hcd, struct urb *urb)
 }
 EXPORT_SYMBOL_GPL(usb_hcd_unmap_urb_setup_for_dma);
 
+static void unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
+{
+	if (hcd->driver->unmap_urb_for_dma)
+		hcd->driver->unmap_urb_for_dma(hcd, urb);
+	else
+		usb_hcd_unmap_urb_for_dma(hcd, urb);
+}
+
 void usb_hcd_unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
 {
 	enum dma_data_direction dir;
@@ -1318,6 +1326,15 @@ EXPORT_SYMBOL_GPL(usb_hcd_unmap_urb_for_dma);
 
 static int map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 			   gfp_t mem_flags)
+{
+	if (hcd->driver->map_urb_for_dma)
+		return hcd->driver->map_urb_for_dma(hcd, urb, mem_flags);
+	else
+		return usb_hcd_map_urb_for_dma(hcd, urb, mem_flags);
+}
+
+int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
+			    gfp_t mem_flags)
 {
 	enum dma_data_direction dir;
 	int ret = 0;
@@ -1414,6 +1431,7 @@ static int map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(usb_hcd_map_urb_for_dma);
 
 /*-------------------------------------------------------------------------*/
 
@@ -1451,7 +1469,7 @@ int usb_hcd_submit_urb (struct urb *urb, gfp_t mem_flags)
 		if (likely(status == 0)) {
 			status = hcd->driver->urb_enqueue(hcd, urb, mem_flags);
 			if (unlikely(status))
-				usb_hcd_unmap_urb_for_dma(hcd, urb);
+				unmap_urb_for_dma(hcd, urb);
 		}
 	}
 
@@ -1557,7 +1575,7 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 			!status))
 		status = -EREMOTEIO;
 
-	usb_hcd_unmap_urb_for_dma(hcd, urb);
+	unmap_urb_for_dma(hcd, urb);
 	usbmon_urb_complete(&hcd->self, urb, status);
 	usb_unanchor_urb(urb);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index bd69b65f3356..e63efeb378e3 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -976,6 +976,7 @@ extern int usb_disabled(void);
 #define URB_SETUP_MAP_SINGLE	0x00100000	/* Setup packet DMA mapped */
 #define URB_SETUP_MAP_LOCAL	0x00200000	/* HCD-local setup packet */
 #define URB_DMA_SG_COMBINED	0x00400000	/* S-G entries were combined */
+#define URB_ALIGNED_TEMP_BUFFER	0x00800000	/* Temp buffer was alloc'd */
 
 struct usb_iso_packet_descriptor {
 	unsigned int offset;
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 395704bdf5cc..92b96fe39307 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -233,6 +233,19 @@ struct hc_driver {
 	int	(*urb_dequeue)(struct usb_hcd *hcd,
 				struct urb *urb, int status);
 
+	/*
+	 * (optional) these hooks allow an HCD to override the default DMA
+	 * mapping and unmapping routines.  In general, they shouldn't be
+	 * necessary unless the host controller has special DMA requirements,
+	 * such as alignment contraints.  If these are not specified, the
+	 * general usb_hcd_(un)?map_urb_for_dma functions will be used instead
+	 * (and it may be a good idea to call these functions in your HCD
+	 * implementation)
+	 */
+	int	(*map_urb_for_dma)(struct usb_hcd *hcd, struct urb *urb,
+				   gfp_t mem_flags);
+	void    (*unmap_urb_for_dma)(struct usb_hcd *hcd, struct urb *urb);
+
 	/* hw synch, freeing endpoint resources that urb_dequeue can't */
 	void	(*endpoint_disable)(struct usb_hcd *hcd,
 			struct usb_host_endpoint *ep);
@@ -329,6 +342,8 @@ extern int usb_hcd_submit_urb(struct urb *urb, gfp_t mem_flags);
 extern int usb_hcd_unlink_urb(struct urb *urb, int status);
 extern void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb,
 		int status);
+extern int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
+		gfp_t mem_flags);
 extern void usb_hcd_unmap_urb_setup_for_dma(struct usb_hcd *, struct urb *);
 extern void usb_hcd_unmap_urb_for_dma(struct usb_hcd *, struct urb *);
 extern void usb_hcd_flush_endpoint(struct usb_device *udev,
-- 
cgit v1.2.3


From 9a1b2e64020d41c577881952734fecd114af75f1 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Fri, 28 Jan 2011 10:23:57 +0100
Subject: USB: gadget: export functionfs.h to the includes available for
 userspace

To compile functionfs userspace driver one needs definitions from
include/linux/usb/functionfs.h. This patch add this file to the list
of includes exported to userspace.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/usb/Kbuild | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/usb/Kbuild b/include/linux/usb/Kbuild
index 51410e0200cf..ed91fb62674b 100644
--- a/include/linux/usb/Kbuild
+++ b/include/linux/usb/Kbuild
@@ -2,6 +2,7 @@ header-y += audio.h
 header-y += cdc.h
 header-y += ch9.h
 header-y += ch11.h
+header-y += functionfs.h
 header-y += gadgetfs.h
 header-y += midi.h
 header-y += g_printer.h
-- 
cgit v1.2.3


From 5c88b02196a99332dacf305c8757674dd7a303ff Mon Sep 17 00:00:00 2001
From: Pavan Savoy <pavan_savoy@ti.com>
Date: Fri, 4 Feb 2011 02:23:09 -0600
Subject: drivers:misc: ti-st: register with channel IDs

The architecture of shared transport had begun with individual
protocols like bluetooth, fm and gps telling the shared transport
what sort of protocol they are and then expecting the ST driver
to parse the incoming data from chip and forward data only
relevant to the protocol drivers.

This change would mean each protocol drivers would also send
information to ST driver as to how to intrepret their protocol
data coming out of the chip.

Signed-off-by: Pavan Savoy <pavan_savoy@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/misc/ti-st/st_core.c | 355 ++++++++++++++-----------------------------
 drivers/misc/ti-st/st_kim.c  |  56 ++++---
 include/linux/ti_wilink_st.h |  40 +++--
 3 files changed, 167 insertions(+), 284 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index f9aad06d1ae5..84d73c5cb74d 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -25,10 +25,9 @@
 #include <linux/init.h>
 #include <linux/tty.h>
 
-/* understand BT, FM and GPS for now */
-#include <net/bluetooth/bluetooth.h>
-#include <net/bluetooth/hci_core.h>
-#include <net/bluetooth/hci.h>
+#include <linux/seq_file.h>
+#include <linux/skbuff.h>
+
 #include <linux/ti_wilink_st.h>
 
 /* function pointer pointing to either,
@@ -38,21 +37,20 @@
 void (*st_recv) (void*, const unsigned char*, long);
 
 /********************************************************************/
-#if 0
-/* internal misc functions */
-bool is_protocol_list_empty(void)
+static void add_channel_to_table(struct st_data_s *st_gdata,
+		struct st_proto_s *new_proto)
 {
-	unsigned char i = 0;
-	pr_debug(" %s ", __func__);
-	for (i = 0; i < ST_MAX; i++) {
-		if (st_gdata->list[i] != NULL)
-			return ST_NOTEMPTY;
-		/* not empty */
-	}
-	/* list empty */
-	return ST_EMPTY;
+	pr_info("%s: id %d\n", __func__, new_proto->chnl_id);
+	/* list now has the channel id as index itself */
+	st_gdata->list[new_proto->chnl_id] = new_proto;
+}
+
+static void remove_channel_from_table(struct st_data_s *st_gdata,
+		struct st_proto_s *proto)
+{
+	pr_info("%s: id %d\n", __func__, proto->chnl_id);
+	st_gdata->list[proto->chnl_id] = NULL;
 }
-#endif
 
 /* can be called in from
  * -- KIM (during fw download)
@@ -82,15 +80,15 @@ int st_int_write(struct st_data_s *st_gdata,
  * push the skb received to relevant
  * protocol stacks
  */
-void st_send_frame(enum proto_type protoid, struct st_data_s *st_gdata)
+void st_send_frame(unsigned char chnl_id, struct st_data_s *st_gdata)
 {
-	pr_info(" %s(prot:%d) ", __func__, protoid);
+	pr_info(" %s(prot:%d) ", __func__, chnl_id);
 
 	if (unlikely
 	    (st_gdata == NULL || st_gdata->rx_skb == NULL
-	     || st_gdata->list[protoid] == NULL)) {
-		pr_err("protocol %d not registered, no data to send?",
-			   protoid);
+	     || st_gdata->list[chnl_id] == NULL)) {
+		pr_err("chnl_id %d not registered, no data to send?",
+			   chnl_id);
 		kfree_skb(st_gdata->rx_skb);
 		return;
 	}
@@ -99,17 +97,17 @@ void st_send_frame(enum proto_type protoid, struct st_data_s *st_gdata)
 	 * - should be just skb_queue_tail for the
 	 *   protocol stack driver
 	 */
-	if (likely(st_gdata->list[protoid]->recv != NULL)) {
+	if (likely(st_gdata->list[chnl_id]->recv != NULL)) {
 		if (unlikely
-			(st_gdata->list[protoid]->recv
-			(st_gdata->list[protoid]->priv_data, st_gdata->rx_skb)
+			(st_gdata->list[chnl_id]->recv
+			(st_gdata->list[chnl_id]->priv_data, st_gdata->rx_skb)
 			     != 0)) {
-			pr_err(" proto stack %d's ->recv failed", protoid);
+			pr_err(" proto stack %d's ->recv failed", chnl_id);
 			kfree_skb(st_gdata->rx_skb);
 			return;
 		}
 	} else {
-		pr_err(" proto stack %d's ->recv null", protoid);
+		pr_err(" proto stack %d's ->recv null", chnl_id);
 		kfree_skb(st_gdata->rx_skb);
 	}
 	return;
@@ -124,7 +122,7 @@ void st_reg_complete(struct st_data_s *st_gdata, char err)
 {
 	unsigned char i = 0;
 	pr_info(" %s ", __func__);
-	for (i = 0; i < ST_MAX; i++) {
+	for (i = 0; i < ST_MAX_CHANNELS; i++) {
 		if (likely(st_gdata != NULL && st_gdata->list[i] != NULL &&
 			   st_gdata->list[i]->reg_complete_cb != NULL))
 			st_gdata->list[i]->reg_complete_cb
@@ -133,7 +131,7 @@ void st_reg_complete(struct st_data_s *st_gdata, char err)
 }
 
 static inline int st_check_data_len(struct st_data_s *st_gdata,
-	int protoid, int len)
+	unsigned char chnl_id, int len)
 {
 	int room = skb_tailroom(st_gdata->rx_skb);
 
@@ -144,7 +142,7 @@ static inline int st_check_data_len(struct st_data_s *st_gdata,
 		 * has zero length payload. So, ask ST CORE to
 		 * forward the packet to protocol driver (BT/FM/GPS)
 		 */
-		st_send_frame(protoid, st_gdata);
+		st_send_frame(chnl_id, st_gdata);
 
 	} else if (len > room) {
 		/* Received packet's payload length is larger.
@@ -157,7 +155,7 @@ static inline int st_check_data_len(struct st_data_s *st_gdata,
 		/* Packet header has non-zero payload length and
 		 * we have enough space in created skb. Lets read
 		 * payload data */
-		st_gdata->rx_state = ST_BT_W4_DATA;
+		st_gdata->rx_state = ST_W4_DATA;
 		st_gdata->rx_count = len;
 		return len;
 	}
@@ -167,6 +165,7 @@ static inline int st_check_data_len(struct st_data_s *st_gdata,
 	st_gdata->rx_state = ST_W4_PACKET_TYPE;
 	st_gdata->rx_skb = NULL;
 	st_gdata->rx_count = 0;
+	st_gdata->rx_chnl = 0;
 
 	return 0;
 }
@@ -208,13 +207,10 @@ void st_int_recv(void *disc_data,
 	const unsigned char *data, long count)
 {
 	char *ptr;
-	struct hci_event_hdr *eh;
-	struct hci_acl_hdr *ah;
-	struct hci_sco_hdr *sh;
-	struct fm_event_hdr *fm;
-	struct gps_event_hdr *gps;
-	int len = 0, type = 0, dlen = 0;
-	static enum proto_type protoid = ST_MAX;
+	struct st_proto_s *proto;
+	unsigned short payload_len = 0;
+	int len = 0, type = 0;
+	unsigned char *plen;
 	struct st_data_s *st_gdata = (struct st_data_s *)disc_data;
 
 	ptr = (char *)data;
@@ -242,64 +238,36 @@ void st_int_recv(void *disc_data,
 
 			/* Check ST RX state machine , where are we? */
 			switch (st_gdata->rx_state) {
-
-				/* Waiting for complete packet ? */
-			case ST_BT_W4_DATA:
+			/* Waiting for complete packet ? */
+			case ST_W4_DATA:
 				pr_debug("Complete pkt received");
-
 				/* Ask ST CORE to forward
 				 * the packet to protocol driver */
-				st_send_frame(protoid, st_gdata);
+				st_send_frame(st_gdata->rx_chnl, st_gdata);
 
 				st_gdata->rx_state = ST_W4_PACKET_TYPE;
 				st_gdata->rx_skb = NULL;
-				protoid = ST_MAX;	/* is this required ? */
-				continue;
-
-				/* Waiting for Bluetooth event header ? */
-			case ST_BT_W4_EVENT_HDR:
-				eh = (struct hci_event_hdr *)st_gdata->rx_skb->
-				    data;
-
-				pr_debug("Event header: evt 0x%2.2x"
-					   "plen %d", eh->evt, eh->plen);
-
-				st_check_data_len(st_gdata, protoid, eh->plen);
-				continue;
-
-				/* Waiting for Bluetooth acl header ? */
-			case ST_BT_W4_ACL_HDR:
-				ah = (struct hci_acl_hdr *)st_gdata->rx_skb->
-				    data;
-				dlen = __le16_to_cpu(ah->dlen);
-
-				pr_info("ACL header: dlen %d", dlen);
-
-				st_check_data_len(st_gdata, protoid, dlen);
-				continue;
-
-				/* Waiting for Bluetooth sco header ? */
-			case ST_BT_W4_SCO_HDR:
-				sh = (struct hci_sco_hdr *)st_gdata->rx_skb->
-				    data;
-
-				pr_info("SCO header: dlen %d", sh->dlen);
-
-				st_check_data_len(st_gdata, protoid, sh->dlen);
-				continue;
-			case ST_FM_W4_EVENT_HDR:
-				fm = (struct fm_event_hdr *)st_gdata->rx_skb->
-				    data;
-				pr_info("FM Header: ");
-				st_check_data_len(st_gdata, ST_FM, fm->plen);
 				continue;
-				/* TODO : Add GPS packet machine logic here */
-			case ST_GPS_W4_EVENT_HDR:
-				/* [0x09 pkt hdr][R/W byte][2 byte len] */
-				gps = (struct gps_event_hdr *)st_gdata->rx_skb->
-				     data;
-				pr_info("GPS Header: ");
-				st_check_data_len(st_gdata, ST_GPS, gps->plen);
+			/* parse the header to know details */
+			case ST_W4_HEADER:
+				proto = st_gdata->list[st_gdata->rx_chnl];
+				plen =
+				&st_gdata->rx_skb->data
+				[proto->offset_len_in_hdr];
+				pr_info("plen pointing to %x\n", *plen);
+				if (proto->len_size == 1)/* 1 byte len field */
+					payload_len = *(unsigned char *)plen;
+				else if (proto->len_size == 2)
+					payload_len =
+					__le16_to_cpu(*(unsigned short *)plen);
+				else
+					pr_info("%s: invalid length "
+					"for id %d\n",
+					__func__, proto->chnl_id);
+				st_check_data_len(st_gdata, proto->chnl_id,
+						payload_len);
+				pr_info("off %d, pay len %d\n",
+					proto->offset_len_in_hdr, payload_len);
 				continue;
 			}	/* end of switch rx_state */
 		}
@@ -308,51 +276,6 @@ void st_int_recv(void *disc_data,
 		/* Check first byte of packet and identify module
 		 * owner (BT/FM/GPS) */
 		switch (*ptr) {
-
-			/* Bluetooth event packet? */
-		case HCI_EVENT_PKT:
-			pr_info("Event packet");
-			st_gdata->rx_state = ST_BT_W4_EVENT_HDR;
-			st_gdata->rx_count = HCI_EVENT_HDR_SIZE;
-			type = HCI_EVENT_PKT;
-			protoid = ST_BT;
-			break;
-
-			/* Bluetooth acl packet? */
-		case HCI_ACLDATA_PKT:
-			pr_info("ACL packet");
-			st_gdata->rx_state = ST_BT_W4_ACL_HDR;
-			st_gdata->rx_count = HCI_ACL_HDR_SIZE;
-			type = HCI_ACLDATA_PKT;
-			protoid = ST_BT;
-			break;
-
-			/* Bluetooth sco packet? */
-		case HCI_SCODATA_PKT:
-			pr_info("SCO packet");
-			st_gdata->rx_state = ST_BT_W4_SCO_HDR;
-			st_gdata->rx_count = HCI_SCO_HDR_SIZE;
-			type = HCI_SCODATA_PKT;
-			protoid = ST_BT;
-			break;
-
-			/* Channel 8(FM) packet? */
-		case ST_FM_CH8_PKT:
-			pr_info("FM CH8 packet");
-			type = ST_FM_CH8_PKT;
-			st_gdata->rx_state = ST_FM_W4_EVENT_HDR;
-			st_gdata->rx_count = FM_EVENT_HDR_SIZE;
-			protoid = ST_FM;
-			break;
-
-			/* Channel 9(GPS) packet? */
-		case 0x9:	/*ST_LL_GPS_CH9_PKT */
-			pr_info("GPS CH9 packet");
-			type = 0x9;	/* ST_LL_GPS_CH9_PKT; */
-			protoid = ST_GPS;
-			st_gdata->rx_state = ST_GPS_W4_EVENT_HDR;
-			st_gdata->rx_count = 3;	/* GPS_EVENT_HDR_SIZE -1*/
-			break;
 		case LL_SLEEP_IND:
 		case LL_SLEEP_ACK:
 		case LL_WAKE_UP_IND:
@@ -373,57 +296,22 @@ void st_int_recv(void *disc_data,
 			continue;
 			/* Unknow packet? */
 		default:
-			pr_err("Unknown packet type %2.2x", (__u8) *ptr);
-			ptr++;
-			count--;
-			continue;
+			type = *ptr;
+			st_gdata->rx_skb = alloc_skb(
+					st_gdata->list[type]->max_frame_size,
+					GFP_ATOMIC);
+			skb_reserve(st_gdata->rx_skb,
+					st_gdata->list[type]->reserve);
+			/* next 2 required for BT only */
+			st_gdata->rx_skb->cb[0] = type; /*pkt_type*/
+			st_gdata->rx_skb->cb[1] = 0; /*incoming*/
+			st_gdata->rx_chnl = *ptr;
+			st_gdata->rx_state = ST_W4_HEADER;
+			st_gdata->rx_count = st_gdata->list[type]->hdr_len;
+			pr_info("rx_count %ld\n", st_gdata->rx_count);
 		};
 		ptr++;
 		count--;
-
-		switch (protoid) {
-		case ST_BT:
-			/* Allocate new packet to hold received data */
-			st_gdata->rx_skb =
-			    bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_ATOMIC);
-			if (!st_gdata->rx_skb) {
-				pr_err("Can't allocate mem for new packet");
-				st_gdata->rx_state = ST_W4_PACKET_TYPE;
-				st_gdata->rx_count = 0;
-				return;
-			}
-			bt_cb(st_gdata->rx_skb)->pkt_type = type;
-			break;
-		case ST_FM:	/* for FM */
-			st_gdata->rx_skb =
-			    alloc_skb(FM_MAX_FRAME_SIZE, GFP_ATOMIC);
-			if (!st_gdata->rx_skb) {
-				pr_err("Can't allocate mem for new packet");
-				st_gdata->rx_state = ST_W4_PACKET_TYPE;
-				st_gdata->rx_count = 0;
-				return;
-			}
-			/* place holder 0x08 */
-			skb_reserve(st_gdata->rx_skb, 1);
-			st_gdata->rx_skb->cb[0] = ST_FM_CH8_PKT;
-			break;
-		case ST_GPS:
-			/* for GPS */
-			st_gdata->rx_skb =
-			    alloc_skb(100 /*GPS_MAX_FRAME_SIZE */ , GFP_ATOMIC);
-			if (!st_gdata->rx_skb) {
-				pr_err("Can't allocate mem for new packet");
-				st_gdata->rx_state = ST_W4_PACKET_TYPE;
-				st_gdata->rx_count = 0;
-				return;
-			}
-			/* place holder 0x09 */
-			skb_reserve(st_gdata->rx_skb, 1);
-			st_gdata->rx_skb->cb[0] = 0x09;	/*ST_GPS_CH9_PKT; */
-			break;
-		case ST_MAX:
-			break;
-		}
 	}
 	pr_debug("done %s", __func__);
 	return;
@@ -565,20 +453,28 @@ long st_register(struct st_proto_s *new_proto)
 	unsigned long flags = 0;
 
 	st_kim_ref(&st_gdata, 0);
-	pr_info("%s(%d) ", __func__, new_proto->type);
+	pr_info("%s(%d) ", __func__, new_proto->chnl_id);
 	if (st_gdata == NULL || new_proto == NULL || new_proto->recv == NULL
 	    || new_proto->reg_complete_cb == NULL) {
 		pr_err("gdata/new_proto/recv or reg_complete_cb not ready");
+		if (st_gdata == NULL)
+			pr_err("error 1\n");
+		if (new_proto == NULL)
+			pr_err("error 2\n");
+		if (new_proto->recv == NULL)
+			pr_err("error 3\n");
+		if (new_proto->reg_complete_cb == NULL)
+			pr_err("erro 4\n");
 		return -1;
 	}
 
-	if (new_proto->type < ST_BT || new_proto->type >= ST_MAX) {
-		pr_err("protocol %d not supported", new_proto->type);
+	if (new_proto->chnl_id >= ST_MAX_CHANNELS) {
+		pr_err("chnl_id %d not supported", new_proto->chnl_id);
 		return -EPROTONOSUPPORT;
 	}
 
-	if (st_gdata->list[new_proto->type] != NULL) {
-		pr_err("protocol %d already registered", new_proto->type);
+	if (st_gdata->list[new_proto->chnl_id] != NULL) {
+		pr_err("chnl_id %d already registered", new_proto->chnl_id);
 		return -EALREADY;
 	}
 
@@ -586,11 +482,11 @@ long st_register(struct st_proto_s *new_proto)
 	spin_lock_irqsave(&st_gdata->lock, flags);
 
 	if (test_bit(ST_REG_IN_PROGRESS, &st_gdata->st_state)) {
-		pr_info(" ST_REG_IN_PROGRESS:%d ", new_proto->type);
+		pr_info(" ST_REG_IN_PROGRESS:%d ", new_proto->chnl_id);
 		/* fw download in progress */
-		st_kim_chip_toggle(new_proto->type, KIM_GPIO_ACTIVE);
+		st_kim_chip_toggle(new_proto->chnl_id, KIM_GPIO_ACTIVE);
 
-		st_gdata->list[new_proto->type] = new_proto;
+		add_channel_to_table(st_gdata, new_proto);
 		st_gdata->protos_registered++;
 		new_proto->write = st_write;
 
@@ -598,7 +494,7 @@ long st_register(struct st_proto_s *new_proto)
 		spin_unlock_irqrestore(&st_gdata->lock, flags);
 		return -EINPROGRESS;
 	} else if (st_gdata->protos_registered == ST_EMPTY) {
-		pr_info(" protocol list empty :%d ", new_proto->type);
+		pr_info(" chnl_id list empty :%d ", new_proto->chnl_id);
 		set_bit(ST_REG_IN_PROGRESS, &st_gdata->st_state);
 		st_recv = st_kim_recv;
 
@@ -622,9 +518,9 @@ long st_register(struct st_proto_s *new_proto)
 			return -1;
 		}
 
-		/* the protocol might require other gpios to be toggled
+		/* the chnl_id might require other gpios to be toggled
 		 */
-		st_kim_chip_toggle(new_proto->type, KIM_GPIO_ACTIVE);
+		st_kim_chip_toggle(new_proto->chnl_id, KIM_GPIO_ACTIVE);
 
 		clear_bit(ST_REG_IN_PROGRESS, &st_gdata->st_state);
 		st_recv = st_int_recv;
@@ -642,14 +538,14 @@ long st_register(struct st_proto_s *new_proto)
 		/* check for already registered once more,
 		 * since the above check is old
 		 */
-		if (st_gdata->list[new_proto->type] != NULL) {
+		if (st_gdata->list[new_proto->chnl_id] != NULL) {
 			pr_err(" proto %d already registered ",
-				   new_proto->type);
+				   new_proto->chnl_id);
 			return -EALREADY;
 		}
 
 		spin_lock_irqsave(&st_gdata->lock, flags);
-		st_gdata->list[new_proto->type] = new_proto;
+		add_channel_to_table(st_gdata, new_proto);
 		st_gdata->protos_registered++;
 		new_proto->write = st_write;
 		spin_unlock_irqrestore(&st_gdata->lock, flags);
@@ -657,22 +553,7 @@ long st_register(struct st_proto_s *new_proto)
 	}
 	/* if fw is already downloaded & new stack registers protocol */
 	else {
-		switch (new_proto->type) {
-		case ST_BT:
-			/* do nothing */
-			break;
-		case ST_FM:
-		case ST_GPS:
-			st_kim_chip_toggle(new_proto->type, KIM_GPIO_ACTIVE);
-			break;
-		case ST_MAX:
-		default:
-			pr_err("%d protocol not supported",
-				   new_proto->type);
-			spin_unlock_irqrestore(&st_gdata->lock, flags);
-			return -EPROTONOSUPPORT;
-		}
-		st_gdata->list[new_proto->type] = new_proto;
+		add_channel_to_table(st_gdata, new_proto);
 		st_gdata->protos_registered++;
 		new_proto->write = st_write;
 
@@ -680,48 +561,48 @@ long st_register(struct st_proto_s *new_proto)
 		spin_unlock_irqrestore(&st_gdata->lock, flags);
 		return err;
 	}
-	pr_debug("done %s(%d) ", __func__, new_proto->type);
+	pr_debug("done %s(%d) ", __func__, new_proto->chnl_id);
 }
 EXPORT_SYMBOL_GPL(st_register);
 
 /* to unregister a protocol -
  * to be called from protocol stack driver
  */
-long st_unregister(enum proto_type type)
+long st_unregister(struct st_proto_s *proto)
 {
 	long err = 0;
 	unsigned long flags = 0;
 	struct st_data_s	*st_gdata;
 
-	pr_debug("%s: %d ", __func__, type);
+	pr_debug("%s: %d ", __func__, proto->chnl_id);
 
 	st_kim_ref(&st_gdata, 0);
-	if (type < ST_BT || type >= ST_MAX) {
-		pr_err(" protocol %d not supported", type);
+	if (proto->chnl_id >= ST_MAX_CHANNELS) {
+		pr_err(" chnl_id %d not supported", proto->chnl_id);
 		return -EPROTONOSUPPORT;
 	}
 
 	spin_lock_irqsave(&st_gdata->lock, flags);
 
-	if (st_gdata->list[type] == NULL) {
-		pr_err(" protocol %d not registered", type);
+	if (st_gdata->list[proto->chnl_id] == NULL) {
+		pr_err(" chnl_id %d not registered", proto->chnl_id);
 		spin_unlock_irqrestore(&st_gdata->lock, flags);
 		return -EPROTONOSUPPORT;
 	}
 
 	st_gdata->protos_registered--;
-	st_gdata->list[type] = NULL;
+	remove_channel_from_table(st_gdata, proto);
 
 	/* kim ignores BT in the below function
 	 * and handles the rest, BT is toggled
 	 * only in kim_start and kim_stop
 	 */
-	st_kim_chip_toggle(type, KIM_GPIO_INACTIVE);
+	st_kim_chip_toggle(proto->chnl_id, KIM_GPIO_INACTIVE);
 	spin_unlock_irqrestore(&st_gdata->lock, flags);
 
 	if ((st_gdata->protos_registered == ST_EMPTY) &&
 	    (!test_bit(ST_REG_PENDING, &st_gdata->st_state))) {
-		pr_info(" all protocols unregistered ");
+		pr_info(" all chnl_ids unregistered ");
 
 		/* stop traffic on tty */
 		if (st_gdata->tty) {
@@ -729,7 +610,7 @@ long st_unregister(enum proto_type type)
 			stop_tty(st_gdata->tty);
 		}
 
-		/* all protocols now unregistered */
+		/* all chnl_ids now unregistered */
 		st_kim_stop(st_gdata->kim_data);
 		/* disable ST LL */
 		st_ll_disable(st_gdata);
@@ -745,7 +626,7 @@ long st_write(struct sk_buff *skb)
 {
 	struct st_data_s *st_gdata;
 #ifdef DEBUG
-	enum proto_type protoid = ST_MAX;
+	unsigned char chnl_id = ST_MAX_CHANNELS;
 #endif
 	long len;
 
@@ -756,22 +637,10 @@ long st_write(struct sk_buff *skb)
 		return -1;
 	}
 #ifdef DEBUG			/* open-up skb to read the 1st byte */
-	switch (skb->data[0]) {
-	case HCI_COMMAND_PKT:
-	case HCI_ACLDATA_PKT:
-	case HCI_SCODATA_PKT:
-		protoid = ST_BT;
-		break;
-	case ST_FM_CH8_PKT:
-		protoid = ST_FM;
-		break;
-	case 0x09:
-		protoid = ST_GPS;
-		break;
-	}
-	if (unlikely(st_gdata->list[protoid] == NULL)) {
-		pr_err(" protocol %d not registered, and writing? ",
-			   protoid);
+	chnl_id = skb->data[0];
+	if (unlikely(st_gdata->list[chnl_id] == NULL)) {
+		pr_err(" chnl_id %d not registered, and writing? ",
+			   chnl_id);
 		return -1;
 	}
 #endif
@@ -824,7 +693,7 @@ static int st_tty_open(struct tty_struct *tty)
 
 static void st_tty_close(struct tty_struct *tty)
 {
-	unsigned char i = ST_MAX;
+	unsigned char i = ST_MAX_CHANNELS;
 	unsigned long flags = 0;
 	struct	st_data_s *st_gdata = tty->disc_data;
 
@@ -835,7 +704,7 @@ static void st_tty_close(struct tty_struct *tty)
 	 * un-installed for some reason - what should be done ?
 	 */
 	spin_lock_irqsave(&st_gdata->lock, flags);
-	for (i = ST_BT; i < ST_MAX; i++) {
+	for (i = ST_BT; i < ST_MAX_CHANNELS; i++) {
 		if (st_gdata->list[i] != NULL)
 			pr_err("%d not un-registered", i);
 		st_gdata->list[i] = NULL;
@@ -869,7 +738,7 @@ static void st_tty_close(struct tty_struct *tty)
 static void st_tty_receive(struct tty_struct *tty, const unsigned char *data,
 			   char *tty_flags, int count)
 {
-
+#define VERBOSE
 #ifdef VERBOSE
 	print_hex_dump(KERN_DEBUG, ">in>", DUMP_PREFIX_NONE,
 		16, 1, data, count, 0);
diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c
index 73b6c8b0e869..707c85826417 100644
--- a/drivers/misc/ti-st/st_kim.c
+++ b/drivers/misc/ti-st/st_kim.c
@@ -32,11 +32,7 @@
 #include <linux/sched.h>
 #include <linux/rfkill.h>
 
-/* understand BT events for fw response */
-#include <net/bluetooth/bluetooth.h>
-#include <net/bluetooth/hci_core.h>
-#include <net/bluetooth/hci.h>
-
+#include <linux/skbuff.h>
 #include <linux/ti_wilink_st.h>
 
 
@@ -134,7 +130,7 @@ static inline int kim_check_data_len(struct kim_data_s *kim_gdata, int len)
 		/* Packet header has non-zero payload length and
 		 * we have enough space in created skb. Lets read
 		 * payload data */
-		kim_gdata->rx_state = ST_BT_W4_DATA;
+		kim_gdata->rx_state = ST_W4_DATA;
 		kim_gdata->rx_count = len;
 		return len;
 	}
@@ -158,8 +154,8 @@ void kim_int_recv(struct kim_data_s *kim_gdata,
 	const unsigned char *data, long count)
 {
 	const unsigned char *ptr;
-	struct hci_event_hdr *eh;
 	int len = 0, type = 0;
+	unsigned char *plen;
 
 	pr_debug("%s", __func__);
 	/* Decode received bytes here */
@@ -183,29 +179,27 @@ void kim_int_recv(struct kim_data_s *kim_gdata,
 			/* Check ST RX state machine , where are we? */
 			switch (kim_gdata->rx_state) {
 				/* Waiting for complete packet ? */
-			case ST_BT_W4_DATA:
+			case ST_W4_DATA:
 				pr_debug("Complete pkt received");
 				validate_firmware_response(kim_gdata);
 				kim_gdata->rx_state = ST_W4_PACKET_TYPE;
 				kim_gdata->rx_skb = NULL;
 				continue;
 				/* Waiting for Bluetooth event header ? */
-			case ST_BT_W4_EVENT_HDR:
-				eh = (struct hci_event_hdr *)kim_gdata->
-				    rx_skb->data;
-				pr_debug("Event header: evt 0x%2.2x"
-					   "plen %d", eh->evt, eh->plen);
-				kim_check_data_len(kim_gdata, eh->plen);
+			case ST_W4_HEADER:
+				plen =
+				(unsigned char *)&kim_gdata->rx_skb->data[1];
+				pr_debug("event hdr: plen 0x%02x\n", *plen);
+				kim_check_data_len(kim_gdata, *plen);
 				continue;
 			}	/* end of switch */
 		}		/* end of if rx_state */
 		switch (*ptr) {
 			/* Bluetooth event packet? */
-		case HCI_EVENT_PKT:
-			pr_info("Event packet");
-			kim_gdata->rx_state = ST_BT_W4_EVENT_HDR;
-			kim_gdata->rx_count = HCI_EVENT_HDR_SIZE;
-			type = HCI_EVENT_PKT;
+		case 0x04:
+			kim_gdata->rx_state = ST_W4_HEADER;
+			kim_gdata->rx_count = 2;
+			type = *ptr;
 			break;
 		default:
 			pr_info("unknown packet");
@@ -216,16 +210,18 @@ void kim_int_recv(struct kim_data_s *kim_gdata,
 		ptr++;
 		count--;
 		kim_gdata->rx_skb =
-		    bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_ATOMIC);
+			alloc_skb(1024+8, GFP_ATOMIC);
 		if (!kim_gdata->rx_skb) {
 			pr_err("can't allocate mem for new packet");
 			kim_gdata->rx_state = ST_W4_PACKET_TYPE;
 			kim_gdata->rx_count = 0;
 			return;
 		}
-		bt_cb(kim_gdata->rx_skb)->pkt_type = type;
+		skb_reserve(kim_gdata->rx_skb, 8);
+		kim_gdata->rx_skb->cb[0] = 4;
+		kim_gdata->rx_skb->cb[1] = 0;
+
 	}
-	pr_info("done %s", __func__);
 	return;
 }
 
@@ -398,7 +394,7 @@ void st_kim_chip_toggle(enum proto_type type, enum kim_gpio_state state)
 			gpio_set_value(kim_gdata->gpios[ST_GPS], GPIO_LOW);
 		break;
 
-	case ST_MAX:
+	case ST_MAX_CHANNELS:
 	default:
 		break;
 	}
@@ -416,7 +412,6 @@ void st_kim_recv(void *disc_data, const unsigned char *data, long count)
 	struct st_data_s	*st_gdata = (struct st_data_s *)disc_data;
 	struct kim_data_s	*kim_gdata = st_gdata->kim_data;
 
-	pr_info(" %s ", __func__);
 	/* copy to local buffer */
 	if (unlikely(data[4] == 0x01 && data[5] == 0x10 && data[0] == 0x04)) {
 		/* must be the read_ver_cmd */
@@ -578,7 +573,7 @@ static int kim_toggle_radio(void *data, bool blocked)
 		else
 			st_kim_chip_toggle(type, KIM_GPIO_ACTIVE);
 	break;
-	case ST_MAX:
+	case ST_MAX_CHANNELS:
 		pr_err(" wrong proto type ");
 	break;
 	}
@@ -664,12 +659,13 @@ static int kim_probe(struct platform_device *pdev)
 	/* refer to itself */
 	kim_gdata->core_data->kim_data = kim_gdata;
 
-	for (proto = 0; proto < ST_MAX; proto++) {
+	for (proto = 0; proto < ST_MAX_CHANNELS; proto++) {
 		kim_gdata->gpios[proto] = gpios[proto];
 		pr_info(" %ld gpio to be requested", gpios[proto]);
 	}
 
-	for (proto = 0; (proto < ST_MAX) && (gpios[proto] != -1); proto++) {
+	for (proto = 0; (proto < ST_MAX_CHANNELS)
+			&& (gpios[proto] != -1); proto++) {
 		/* Claim the Bluetooth/FM/GPIO
 		 * nShutdown gpio from the system
 		 */
@@ -704,7 +700,8 @@ static int kim_probe(struct platform_device *pdev)
 	init_completion(&kim_gdata->kim_rcvd);
 	init_completion(&kim_gdata->ldisc_installed);
 
-	for (proto = 0; (proto < ST_MAX) && (gpios[proto] != -1); proto++) {
+	for (proto = 0; (proto < ST_MAX_CHANNELS)
+			&& (gpios[proto] != -1); proto++) {
 		/* TODO: should all types be rfkill_type_bt ? */
 		kim_gdata->rf_protos[proto] = proto;
 		kim_gdata->rfkill[proto] = rfkill_alloc(protocol_names[proto],
@@ -752,7 +749,8 @@ static int kim_remove(struct platform_device *pdev)
 
 	kim_gdata = dev_get_drvdata(&pdev->dev);
 
-	for (proto = 0; (proto < ST_MAX) && (gpios[proto] != -1); proto++) {
+	for (proto = 0; (proto < ST_MAX_CHANNELS)
+		&& (gpios[proto] != -1); proto++) {
 		/* Claim the Bluetooth/FM/GPIO
 		 * nShutdown gpio from the system
 		 */
diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 4c7be2263011..1674ca7ab86d 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -42,7 +42,7 @@ enum proto_type {
 	ST_BT,
 	ST_FM,
 	ST_GPS,
-	ST_MAX,
+	ST_MAX_CHANNELS = 16,
 };
 
 /**
@@ -62,6 +62,17 @@ enum proto_type {
  * @priv_data: privdate data holder for the protocol drivers, sent
  *	from the protocol drivers during registration, and sent back on
  *	reg_complete_cb and recv.
+ * @chnl_id: channel id the protocol driver is interested in, the channel
+ *	id is nothing but the 1st byte of the packet in UART frame.
+ * @max_frame_size: size of the largest frame the protocol can receive.
+ * @hdr_len: length of the header structure of the protocol.
+ * @offset_len_in_hdr: this provides the offset of the length field in the
+ *	header structure of the protocol header, to assist ST to know
+ *	how much to receive, if the data is split across UART frames.
+ * @len_size: whether the length field inside the header is 2 bytes
+ *	or 1 byte.
+ * @reserve: the number of bytes ST needs to reserve in the skb being
+ *	prepared for the protocol driver.
  */
 struct st_proto_s {
 	enum proto_type type;
@@ -70,10 +81,17 @@ struct st_proto_s {
 	void (*reg_complete_cb) (void *, char data);
 	long (*write) (struct sk_buff *skb);
 	void *priv_data;
+
+	unsigned char chnl_id;
+	unsigned short max_frame_size;
+	unsigned char hdr_len;
+	unsigned char offset_len_in_hdr;
+	unsigned char len_size;
+	unsigned char reserve;
 };
 
 extern long st_register(struct st_proto_s *);
-extern long st_unregister(enum proto_type);
+extern long st_unregister(struct st_proto_s *);
 
 
 /*
@@ -114,6 +132,7 @@ extern long st_unregister(enum proto_type);
  * @rx_skb: the skb where all data for a protocol gets accumulated,
  *	since tty might not call receive when a complete event packet
  *	is received, the states, count and the skb needs to be maintained.
+ * @rx_chnl: the channel ID for which the data is getting accumalated for.
  * @txq: the list of skbs which needs to be sent onto the TTY.
  * @tx_waitq: if the chip is not in AWAKE state, the skbs needs to be queued
  *	up in here, PM(WAKEUP_IND) data needs to be sent and then the skbs
@@ -135,10 +154,11 @@ struct st_data_s {
 #define ST_TX_SENDING	1
 #define ST_TX_WAKEUP	2
 	unsigned long tx_state;
-	struct st_proto_s *list[ST_MAX];
+	struct st_proto_s *list[ST_MAX_CHANNELS];
 	unsigned long rx_state;
 	unsigned long rx_count;
 	struct sk_buff *rx_skb;
+	unsigned char rx_chnl;
 	struct sk_buff_head txq, tx_waitq;
 	spinlock_t lock;
 	unsigned char	protos_registered;
@@ -243,12 +263,12 @@ struct kim_data_s {
 	struct completion kim_rcvd, ldisc_installed;
 	char resp_buffer[30];
 	const struct firmware *fw_entry;
-	long gpios[ST_MAX];
+	long gpios[ST_MAX_CHANNELS];
 	unsigned long rx_state;
 	unsigned long rx_count;
 	struct sk_buff *rx_skb;
-	struct rfkill *rfkill[ST_MAX];
-	enum proto_type rf_protos[ST_MAX];
+	struct rfkill *rfkill[ST_MAX_CHANNELS];
+	enum proto_type rf_protos[ST_MAX_CHANNELS];
 	struct st_data_s *core_data;
 	struct chip_version version;
 };
@@ -338,12 +358,8 @@ struct hci_command {
 
 /* ST LL receiver states */
 #define ST_W4_PACKET_TYPE       0
-#define ST_BT_W4_EVENT_HDR      1
-#define ST_BT_W4_ACL_HDR        2
-#define ST_BT_W4_SCO_HDR        3
-#define ST_BT_W4_DATA           4
-#define ST_FM_W4_EVENT_HDR      5
-#define ST_GPS_W4_EVENT_HDR	6
+#define ST_W4_HEADER		1
+#define ST_W4_DATA		2
 
 /* ST LL state machines */
 #define ST_LL_ASLEEP               0
-- 
cgit v1.2.3


From ec60d0ad20ff8796dc41b30a9dce485478ccd263 Mon Sep 17 00:00:00 2001
From: Pavan Savoy <pavan_savoy@ti.com>
Date: Fri, 4 Feb 2011 02:23:10 -0600
Subject: drivers:misc: ti-st: move from rfkill to sysfs

The communication between ST KIM and UIM was interfaced
over the /dev/rfkill device node.
Move the interface to a simpler less abusive sysfs entry
mechanism and document it in Documentation/ABI/testing/
under sysfs-platform-kim.

Shared transport driver would now read the UART details
originally received by bootloader or firmware as platform
data.
The data read will be shared over sysfs entries for the user-space
UIM or other n/w manager/plugins to be read, and assist the driver
by opening up the UART, setting the baud-rate and installing the
line discipline.

Signed-off-by: Pavan Savoy <pavan_savoy@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 Documentation/ABI/testing/sysfs-platform-kim |  48 ++++++
 drivers/misc/ti-st/st_kim.c                  | 244 +++++++++++++--------------
 include/linux/ti_wilink_st.h                 |  19 ++-
 3 files changed, 186 insertions(+), 125 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-platform-kim

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-platform-kim b/Documentation/ABI/testing/sysfs-platform-kim
new file mode 100644
index 000000000000..c1653271872a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-platform-kim
@@ -0,0 +1,48 @@
+What:		/sys/devices/platform/kim/dev_name
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		Name of the UART device at which the WL128x chip
+		is connected. example: "/dev/ttyS0".
+		The device name flows down to architecture specific board
+		initialization file from the SFI/ATAGS bootloader
+		firmware. The name exposed is read from the user-space
+		dameon and opens the device when install is requested.
+
+What:		/sys/devices/platform/kim/baud_rate
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		The maximum reliable baud-rate the host can support.
+		Different platforms tend to have different high-speed
+		UART configurations, so the baud-rate needs to be set
+		locally and also sent across to the WL128x via a HCI-VS
+		command. The entry is read and made use by the user-space
+		daemon when the ldisc install is requested.
+
+What:		/sys/devices/platform/kim/flow_cntrl
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		The WL128x makes use of flow control mechanism, and this
+		entry most often should be 1, the host's UART is required
+		to have the capability of flow-control, or else this
+		entry can be made use of for exceptions.
+
+What:		/sys/devices/platform/kim/install
+Date:		January 2010
+KernelVersion:	2.6.38
+Contact:	"Pavan Savoy" <pavan_savoy@ti.com>
+Description:
+		When one of the protocols Bluetooth, FM or GPS wants to make
+		use of the shared UART transport, it registers to the shared
+		transport driver, which will signal the user-space for opening,
+		configuring baud and install line discipline via this sysfs
+		entry. This entry would be polled upon by the user-space
+		daemon managing the UART, and is notified about the change
+		by the sysfs_notify. The value would be '1' when UART needs
+		to be opened/ldisc installed, and would be '0' when UART
+		is no more required and needs to be closed.
diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c
index 707c85826417..a7fda8141758 100644
--- a/drivers/misc/ti-st/st_kim.c
+++ b/drivers/misc/ti-st/st_kim.c
@@ -30,46 +30,12 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
-#include <linux/rfkill.h>
+#include <linux/tty.h>
 
 #include <linux/skbuff.h>
 #include <linux/ti_wilink_st.h>
 
 
-static int kim_probe(struct platform_device *pdev);
-static int kim_remove(struct platform_device *pdev);
-
-/* KIM platform device driver structure */
-static struct platform_driver kim_platform_driver = {
-	.probe = kim_probe,
-	.remove = kim_remove,
-	/* TODO: ST driver power management during suspend/resume ?
-	 */
-#if 0
-	.suspend = kim_suspend,
-	.resume = kim_resume,
-#endif
-	.driver = {
-		   .name = "kim",
-		   .owner = THIS_MODULE,
-		   },
-};
-
-static int kim_toggle_radio(void*, bool);
-static const struct rfkill_ops kim_rfkill_ops = {
-	.set_block = kim_toggle_radio,
-};
-
-/* strings to be used for rfkill entries and by
- * ST Core to be used for sysfs debug entry
- */
-#define PROTO_ENTRY(type, name)	name
-const unsigned char *protocol_names[] = {
-	PROTO_ENTRY(ST_BT, "Bluetooth"),
-	PROTO_ENTRY(ST_FM, "FM"),
-	PROTO_ENTRY(ST_GPS, "GPS"),
-};
-
 #define MAX_ST_DEVICES	3	/* Imagine 1 on each UART for now */
 static struct platform_device *st_kim_devices[MAX_ST_DEVICES];
 
@@ -371,8 +337,7 @@ void st_kim_chip_toggle(enum proto_type type, enum kim_gpio_state state)
 	kim_gdata = dev_get_drvdata(&kim_pdev->dev);
 
 	if (kim_gdata->gpios[type] == -1) {
-		pr_info(" gpio not requested for protocol %s",
-			   protocol_names[type]);
+		pr_info("gpio not requested for protocol %d", type);
 		return;
 	}
 	switch (type) {
@@ -450,11 +415,6 @@ long st_kim_start(void *kim_data)
 	pr_info(" %s", __func__);
 
 	do {
-		/* TODO: this is only because rfkill sub-system
-		 * doesn't send events to user-space if the state
-		 * isn't changed
-		 */
-		rfkill_set_hw_state(kim_gdata->rfkill[ST_BT], 1);
 		/* Configure BT nShutdown to HIGH state */
 		gpio_set_value(kim_gdata->gpios[ST_BT], GPIO_LOW);
 		mdelay(5);	/* FIXME: a proper toggle */
@@ -462,22 +422,20 @@ long st_kim_start(void *kim_data)
 		mdelay(100);
 		/* re-initialize the completion */
 		INIT_COMPLETION(kim_gdata->ldisc_installed);
-#if 0 /* older way of signalling user-space UIM */
-		/* send signal to UIM */
-		err = kill_pid(find_get_pid(kim_gdata->uim_pid), SIGUSR2, 0);
-		if (err != 0) {
-			pr_info(" sending SIGUSR2 to uim failed %ld", err);
-			err = -1;
-			continue;
-		}
-#endif
-		/* unblock and send event to UIM via /dev/rfkill */
-		rfkill_set_hw_state(kim_gdata->rfkill[ST_BT], 0);
+		/* send notification to UIM */
+		kim_gdata->ldisc_install = 1;
+		pr_info("ldisc_install = 1");
+		sysfs_notify(&kim_gdata->kim_pdev->dev.kobj,
+				NULL, "install");
 		/* wait for ldisc to be installed */
 		err = wait_for_completion_timeout(&kim_gdata->ldisc_installed,
 				msecs_to_jiffies(LDISC_TIME));
 		if (!err) {	/* timeout */
 			pr_err("line disc installation timed out ");
+			kim_gdata->ldisc_install = 0;
+			pr_info("ldisc_install = 0");
+			sysfs_notify(&kim_gdata->kim_pdev->dev.kobj,
+					NULL, "install");
 			err = -1;
 			continue;
 		} else {
@@ -486,6 +444,10 @@ long st_kim_start(void *kim_data)
 			err = download_firmware(kim_gdata);
 			if (err != 0) {
 				pr_err("download firmware failed");
+				kim_gdata->ldisc_install = 0;
+				pr_info("ldisc_install = 0");
+				sysfs_notify(&kim_gdata->kim_pdev->dev.kobj,
+						NULL, "install");
 				continue;
 			} else {	/* on success don't retry */
 				break;
@@ -505,16 +467,15 @@ long st_kim_stop(void *kim_data)
 	struct kim_data_s	*kim_gdata = (struct kim_data_s *)kim_data;
 
 	INIT_COMPLETION(kim_gdata->ldisc_installed);
-#if 0 /* older way of signalling user-space UIM */
-	/* send signal to UIM */
-	err = kill_pid(find_get_pid(kim_gdata->uim_pid), SIGUSR2, 1);
-	if (err != 0) {
-		pr_err("sending SIGUSR2 to uim failed %ld", err);
-		return -1;
-	}
-#endif
-	/* set BT rfkill to be blocked */
-	err = rfkill_set_hw_state(kim_gdata->rfkill[ST_BT], 1);
+
+	/* Flush any pending characters in the driver and discipline. */
+	tty_ldisc_flush(kim_gdata->core_data->tty);
+	tty_driver_flush_buffer(kim_gdata->core_data->tty);
+
+	/* send uninstall notification to UIM */
+	pr_info("ldisc_install = 0");
+	kim_gdata->ldisc_install = 0;
+	sysfs_notify(&kim_gdata->kim_pdev->dev.kobj, NULL, "install");
 
 	/* wait for ldisc to be un-installed */
 	err = wait_for_completion_timeout(&kim_gdata->ldisc_installed,
@@ -553,33 +514,59 @@ static int show_list(struct seq_file *s, void *unused)
 	return 0;
 }
 
-/* function called from rfkill subsystem, when someone from
- * user space would write 0/1 on the sysfs entry
- * /sys/class/rfkill/rfkill0,1,3/state
- */
-static int kim_toggle_radio(void *data, bool blocked)
+static ssize_t show_install(struct device *dev,
+		struct device_attribute *attr, char *buf)
 {
-	enum proto_type type = *((enum proto_type *)data);
-	pr_debug(" %s: %d ", __func__, type);
+	struct kim_data_s *kim_data = dev_get_drvdata(dev);
+	return sprintf(buf, "%d\n", kim_data->ldisc_install);
+}
 
-	switch (type) {
-	case ST_BT:
-		/* do nothing */
-	break;
-	case ST_FM:
-	case ST_GPS:
-		if (blocked)
-			st_kim_chip_toggle(type, KIM_GPIO_INACTIVE);
-		else
-			st_kim_chip_toggle(type, KIM_GPIO_ACTIVE);
-	break;
-	case ST_MAX_CHANNELS:
-		pr_err(" wrong proto type ");
-	break;
-	}
-	return 0;
+static ssize_t show_dev_name(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct kim_data_s *kim_data = dev_get_drvdata(dev);
+	return sprintf(buf, "%s\n", kim_data->dev_name);
+}
+
+static ssize_t show_baud_rate(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct kim_data_s *kim_data = dev_get_drvdata(dev);
+	return sprintf(buf, "%ld\n", kim_data->baud_rate);
+}
+
+static ssize_t show_flow_cntrl(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct kim_data_s *kim_data = dev_get_drvdata(dev);
+	return sprintf(buf, "%d\n", kim_data->flow_cntrl);
 }
 
+/* structures specific for sysfs entries */
+static struct kobj_attribute ldisc_install =
+__ATTR(install, 0444, (void *)show_install, NULL);
+
+static struct kobj_attribute uart_dev_name =
+__ATTR(dev_name, 0444, (void *)show_dev_name, NULL);
+
+static struct kobj_attribute uart_baud_rate =
+__ATTR(baud_rate, 0444, (void *)show_baud_rate, NULL);
+
+static struct kobj_attribute uart_flow_cntrl =
+__ATTR(flow_cntrl, 0444, (void *)show_flow_cntrl, NULL);
+
+static struct attribute *uim_attrs[] = {
+	&ldisc_install.attr,
+	&uart_dev_name.attr,
+	&uart_baud_rate.attr,
+	&uart_flow_cntrl.attr,
+	NULL,
+};
+
+static struct attribute_group uim_attr_grp = {
+	.attrs = uim_attrs,
+};
+
 /**
  * st_kim_ref - reference the core's data
  *	This references the per-ST platform device in the arch/xx/
@@ -633,8 +620,9 @@ static int kim_probe(struct platform_device *pdev)
 {
 	long status;
 	long proto;
-	long *gpios = pdev->dev.platform_data;
 	struct kim_data_s	*kim_gdata;
+	struct ti_st_plat_data	*pdata = pdev->dev.platform_data;
+	long *gpios = pdata->gpios;
 
 	if ((pdev->id != -1) && (pdev->id < MAX_ST_DEVICES)) {
 		/* multiple devices could exist */
@@ -700,30 +688,18 @@ static int kim_probe(struct platform_device *pdev)
 	init_completion(&kim_gdata->kim_rcvd);
 	init_completion(&kim_gdata->ldisc_installed);
 
-	for (proto = 0; (proto < ST_MAX_CHANNELS)
-			&& (gpios[proto] != -1); proto++) {
-		/* TODO: should all types be rfkill_type_bt ? */
-		kim_gdata->rf_protos[proto] = proto;
-		kim_gdata->rfkill[proto] = rfkill_alloc(protocol_names[proto],
-			&pdev->dev, RFKILL_TYPE_BLUETOOTH,
-			&kim_rfkill_ops, &kim_gdata->rf_protos[proto]);
-		if (kim_gdata->rfkill[proto] == NULL) {
-			pr_err("cannot create rfkill entry for gpio %ld",
-				   gpios[proto]);
-			continue;
-		}
-		/* block upon creation */
-		rfkill_init_sw_state(kim_gdata->rfkill[proto], 1);
-		status = rfkill_register(kim_gdata->rfkill[proto]);
-		if (unlikely(status)) {
-			pr_err("rfkill registration failed for gpio %ld",
-				   gpios[proto]);
-			rfkill_unregister(kim_gdata->rfkill[proto]);
-			continue;
-		}
-		pr_info("rfkill entry created for %ld", gpios[proto]);
+	status = sysfs_create_group(&pdev->dev.kobj, &uim_attr_grp);
+	if (status) {
+		pr_err("failed to create sysfs entries");
+		return status;
 	}
 
+	/* copying platform data */
+	strncpy(kim_gdata->dev_name, pdata->dev_name, UART_DEV_NAME_LEN);
+	kim_gdata->flow_cntrl = pdata->flow_cntrl;
+	kim_gdata->baud_rate = pdata->baud_rate;
+	pr_info("sysfs entries created\n");
+
 	kim_debugfs_dir = debugfs_create_dir("ti-st", NULL);
 	if (IS_ERR(kim_debugfs_dir)) {
 		pr_err(" debugfs entries creation failed ");
@@ -741,9 +717,9 @@ static int kim_probe(struct platform_device *pdev)
 
 static int kim_remove(struct platform_device *pdev)
 {
-	/* free the GPIOs requested
-	 */
-	long *gpios = pdev->dev.platform_data;
+	/* free the GPIOs requested */
+	struct ti_st_plat_data	*pdata = pdev->dev.platform_data;
+	long *gpios = pdata->gpios;
 	long proto;
 	struct kim_data_s	*kim_gdata;
 
@@ -755,12 +731,11 @@ static int kim_remove(struct platform_device *pdev)
 		 * nShutdown gpio from the system
 		 */
 		gpio_free(gpios[proto]);
-		rfkill_unregister(kim_gdata->rfkill[proto]);
-		rfkill_destroy(kim_gdata->rfkill[proto]);
-		kim_gdata->rfkill[proto] = NULL;
 	}
 	pr_info("kim: GPIO Freed");
 	debugfs_remove_recursive(kim_debugfs_dir);
+
+	sysfs_remove_group(&pdev->dev.kobj, &uim_attr_grp);
 	kim_gdata->kim_pdev = NULL;
 	st_core_exit(kim_gdata->core_data);
 
@@ -769,23 +744,46 @@ static int kim_remove(struct platform_device *pdev)
 	return 0;
 }
 
+int kim_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct ti_st_plat_data	*pdata = pdev->dev.platform_data;
+
+	if (pdata->suspend)
+		return pdata->suspend(pdev, state);
+
+	return -EOPNOTSUPP;
+}
+
+int kim_resume(struct platform_device *pdev)
+{
+	struct ti_st_plat_data	*pdata = pdev->dev.platform_data;
+
+	if (pdata->resume)
+		return pdata->resume(pdev);
+
+	return -EOPNOTSUPP;
+}
+
 /**********************************************************************/
 /* entry point for ST KIM module, called in from ST Core */
+static struct platform_driver kim_platform_driver = {
+	.probe = kim_probe,
+	.remove = kim_remove,
+	.suspend = kim_suspend,
+	.resume = kim_resume,
+	.driver = {
+		.name = "kim",
+		.owner = THIS_MODULE,
+	},
+};
 
 static int __init st_kim_init(void)
 {
-	long ret = 0;
-	ret = platform_driver_register(&kim_platform_driver);
-	if (ret != 0) {
-		pr_err("platform drv registration failed");
-		return -1;
-	}
-	return 0;
+	return platform_driver_register(&kim_platform_driver);
 }
 
 static void __exit st_kim_deinit(void)
 {
-	/* the following returns void */
 	platform_driver_unregister(&kim_platform_driver);
 }
 
diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 1674ca7ab86d..010cda7287a0 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -206,8 +206,8 @@ void gps_chrdrv_stub_init(void);
 /* time in msec to wait for
  * line discipline to be installed
  */
-#define LDISC_TIME	500
-#define CMD_RESP_TIME	500
+#define LDISC_TIME	1000
+#define CMD_RESP_TIME	800
 #define MAKEWORD(a, b)  ((unsigned short)(((unsigned char)(a)) \
 	| ((unsigned short)((unsigned char)(b))) << 8))
 
@@ -230,6 +230,7 @@ struct chip_version {
 	unsigned short maj_ver;
 };
 
+#define UART_DEV_NAME_LEN 32
 /**
  * struct kim_data_s - the KIM internal data, embedded as the
  *	platform's drv data. One for each ST device in the system.
@@ -271,6 +272,10 @@ struct kim_data_s {
 	enum proto_type rf_protos[ST_MAX_CHANNELS];
 	struct st_data_s *core_data;
 	struct chip_version version;
+	unsigned char ldisc_install;
+	unsigned char dev_name[UART_DEV_NAME_LEN];
+	unsigned char flow_cntrl;
+	unsigned long baud_rate;
 };
 
 /**
@@ -413,4 +418,14 @@ struct gps_event_hdr {
 	u16 plen;
 } __attribute__ ((packed));
 
+/* platform data */
+struct ti_st_plat_data {
+	long gpios[ST_MAX_CHANNELS]; /* BT, FM and GPS */
+	unsigned char dev_name[UART_DEV_NAME_LEN]; /* uart name */
+	unsigned char flow_cntrl; /* flow control flag */
+	unsigned long baud_rate;
+	int (*suspend)(struct platform_device *, pm_message_t);
+	int (*resume)(struct platform_device *);
+};
+
 #endif /* TI_WILINK_ST_H */
-- 
cgit v1.2.3


From ef04d121f030329aae0c2d3ec22beea0c5cbcfd3 Mon Sep 17 00:00:00 2001
From: Pavan Savoy <pavan_savoy@ti.com>
Date: Fri, 4 Feb 2011 02:23:13 -0600
Subject: drivers:misc: ti-st: firmware download optimization

To fasten the process of firmware download, the chip allows
disabling of the command complete event generation from host.
In these cases, only few very essential commands would have
the command complete events and hence the wait associated with
them.

So now the driver would wait for a command complete event, only
when it comes across a wait event during firmware parsing.
This would also mean we need to skip not just the change baud
rate command but also the wait for it.

Signed-off-by: Pavan Savoy <pavan_savoy@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/misc/ti-st/st_core.c | 18 ++++++++++
 drivers/misc/ti-st/st_kim.c  | 80 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/ti_wilink_st.h |  6 ++++
 3 files changed, 97 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index f7bb96f3a424..dd2c879faff6 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -52,6 +52,24 @@ static void remove_channel_from_table(struct st_data_s *st_gdata,
 	st_gdata->list[proto->chnl_id] = NULL;
 }
 
+/*
+ * called from KIM during firmware download.
+ *
+ * This is a wrapper function to tty->ops->write_room.
+ * It returns number of free space available in
+ * uart tx buffer.
+ */
+int st_get_uart_wr_room(struct st_data_s *st_gdata)
+{
+	struct tty_struct *tty;
+	if (unlikely(st_gdata == NULL || st_gdata->tty == NULL)) {
+		pr_err("tty unavailable to perform write");
+		return -1;
+	}
+	tty = st_gdata->tty;
+	return tty->ops->write_room(tty);
+}
+
 /* can be called in from
  * -- KIM (during fw download)
  * -- ST Core (during st_write)
diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c
index ccc46a7b0abb..2c096ccd53b0 100644
--- a/drivers/misc/ti-st/st_kim.c
+++ b/drivers/misc/ti-st/st_kim.c
@@ -232,6 +232,26 @@ static long read_local_version(struct kim_data_s *kim_gdata, char *bts_scr_name)
 	return 0;
 }
 
+void skip_change_remote_baud(unsigned char **ptr, long *len)
+{
+	unsigned char *nxt_action, *cur_action;
+	cur_action = *ptr;
+
+	nxt_action = cur_action + sizeof(struct bts_action) +
+		((struct bts_action *) cur_action)->size;
+
+	if (((struct bts_action *) nxt_action)->type != ACTION_WAIT_EVENT) {
+		pr_err("invalid action after change remote baud command");
+	} else {
+		*ptr = *ptr + sizeof(struct bts_action) +
+			((struct bts_action *)nxt_action)->size;
+		*len = *len - (sizeof(struct bts_action) +
+				((struct bts_action *)nxt_action)->size);
+		/* warn user on not commenting these in firmware */
+		pr_warn("skipping the wait event of change remote baud");
+	}
+}
+
 /**
  * download_firmware -
  *	internal function which parses through the .bts firmware
@@ -244,6 +264,9 @@ static long download_firmware(struct kim_data_s *kim_gdata)
 	unsigned char *ptr = NULL;
 	unsigned char *action_ptr = NULL;
 	unsigned char bts_scr_name[30] = { 0 };	/* 30 char long bts scr name? */
+	int wr_room_space;
+	int cmd_size;
+	unsigned long timeout;
 
 	err = read_local_version(kim_gdata, bts_scr_name);
 	if (err != 0) {
@@ -280,13 +303,43 @@ static long download_firmware(struct kim_data_s *kim_gdata)
 			     0xFF36)) {
 				/* ignore remote change
 				 * baud rate HCI VS command */
-				pr_err
-				    (" change remote baud"
+				pr_warn("change remote baud"
 				    " rate command in firmware");
+				skip_change_remote_baud(&ptr, &len);
 				break;
 			}
+			/*
+			 * Make sure we have enough free space in uart
+			 * tx buffer to write current firmware command
+			 */
+			cmd_size = ((struct bts_action *)ptr)->size;
+			timeout = jiffies + msecs_to_jiffies(CMD_WR_TIME);
+			do {
+				wr_room_space =
+					st_get_uart_wr_room(kim_gdata->core_data);
+				if (wr_room_space < 0) {
+					pr_err("Unable to get free "
+							"space info from uart tx buffer");
+					release_firmware(kim_gdata->fw_entry);
+					return wr_room_space;
+				}
+				mdelay(1); /* wait 1ms before checking room */
+			} while ((wr_room_space < cmd_size) &&
+					time_before(jiffies, timeout));
+
+			/* Timeout happened ? */
+			if (time_after_eq(jiffies, timeout)) {
+				pr_err("Timeout while waiting for free "
+						"free space in uart tx buffer");
+				release_firmware(kim_gdata->fw_entry);
+				return -ETIMEDOUT;
+			}
 
-			INIT_COMPLETION(kim_gdata->kim_rcvd);
+			/*
+			 * Free space found in uart buffer, call st_int_write
+			 * to send current firmware command to the uart tx
+			 * buffer.
+			 */
 			err = st_int_write(kim_gdata->core_data,
 			((struct bts_action_send *)action_ptr)->data,
 					   ((struct bts_action *)ptr)->size);
@@ -294,15 +347,28 @@ static long download_firmware(struct kim_data_s *kim_gdata)
 				release_firmware(kim_gdata->fw_entry);
 				return err;
 			}
+			/*
+			 * Check number of bytes written to the uart tx buffer
+			 * and requested command write size
+			 */
+			if (err != cmd_size) {
+				pr_err("Number of bytes written to uart "
+						"tx buffer are not matching with "
+						"requested cmd write size");
+				release_firmware(kim_gdata->fw_entry);
+				return -EIO;
+			}
+			break;
+		case ACTION_WAIT_EVENT:  /* wait */
 			if (!wait_for_completion_timeout
-			    (&kim_gdata->kim_rcvd,
-			     msecs_to_jiffies(CMD_RESP_TIME))) {
-				pr_err
-				    (" response timeout during fw download ");
+					(&kim_gdata->kim_rcvd,
+					 msecs_to_jiffies(CMD_RESP_TIME))) {
+				pr_err("response timeout during fw download ");
 				/* timed out */
 				release_firmware(kim_gdata->fw_entry);
 				return -ETIMEDOUT;
 			}
+			INIT_COMPLETION(kim_gdata->kim_rcvd);
 			break;
 		case ACTION_DELAY:	/* sleep */
 			pr_info("sleep command in scr");
diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 010cda7287a0..7885a779c588 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -166,6 +166,11 @@ struct st_data_s {
 	void *kim_data;
 };
 
+/*
+ * wrapper around tty->ops->write_room to check
+ * availability during firmware download
+ */
+int st_get_uart_wr_room(struct st_data_s *st_gdata);
 /**
  * st_int_write -
  * point this to tty->driver->write or tty->ops->write
@@ -208,6 +213,7 @@ void gps_chrdrv_stub_init(void);
  */
 #define LDISC_TIME	1000
 #define CMD_RESP_TIME	800
+#define CMD_WR_TIME	5000
 #define MAKEWORD(a, b)  ((unsigned short)(((unsigned char)(a)) \
 	| ((unsigned short)((unsigned char)(b))) << 8))
 
-- 
cgit v1.2.3


From 781a7395d239dbdb59738ca7fe08e71641bf583c Mon Sep 17 00:00:00 2001
From: Pavan Savoy <pavan_savoy@ti.com>
Date: Fri, 4 Feb 2011 02:23:15 -0600
Subject: drivers:misc: ti-st: remove multiple gpio handling

TI shared transport driver previously intended to expose rfkill
entries for each of the protocol gpio that the chip would have.
However now in case such gpios exist, which requires to be enabled
for a specific protocol, the responsibility lay on protocol driver.
This patch removes the request/free of multiple gpios, rfkill struct
references and also removes the chip_toggle function.

Signed-off-by: Pavan Savoy <pavan_savoy@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/misc/ti-st/st_core.c |  11 ----
 drivers/misc/ti-st/st_kim.c  | 117 +++++++++----------------------------------
 include/linux/ti_wilink_st.h |  19 +------
 3 files changed, 26 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index f0d24d852078..1847c477c0c0 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -515,7 +515,6 @@ long st_register(struct st_proto_s *new_proto)
 	if (test_bit(ST_REG_IN_PROGRESS, &st_gdata->st_state)) {
 		pr_info(" ST_REG_IN_PROGRESS:%d ", new_proto->chnl_id);
 		/* fw download in progress */
-		st_kim_chip_toggle(new_proto->chnl_id, KIM_GPIO_ACTIVE);
 
 		add_channel_to_table(st_gdata, new_proto);
 		st_gdata->protos_registered++;
@@ -548,10 +547,6 @@ long st_register(struct st_proto_s *new_proto)
 			return -EINVAL;
 		}
 
-		/* the chnl_id might require other gpios to be toggled
-		 */
-		st_kim_chip_toggle(new_proto->chnl_id, KIM_GPIO_ACTIVE);
-
 		clear_bit(ST_REG_IN_PROGRESS, &st_gdata->st_state);
 		st_recv = st_int_recv;
 
@@ -622,12 +617,6 @@ long st_unregister(struct st_proto_s *proto)
 
 	st_gdata->protos_registered--;
 	remove_channel_from_table(st_gdata, proto);
-
-	/* kim ignores BT in the below function
-	 * and handles the rest, BT is toggled
-	 * only in kim_start and kim_stop
-	 */
-	st_kim_chip_toggle(proto->chnl_id, KIM_GPIO_INACTIVE);
 	spin_unlock_irqrestore(&st_gdata->lock, flags);
 
 	if ((st_gdata->protos_registered == ST_EMPTY) &&
diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c
index 2c096ccd53b0..9ee4c788aa69 100644
--- a/drivers/misc/ti-st/st_kim.c
+++ b/drivers/misc/ti-st/st_kim.c
@@ -390,49 +390,6 @@ static long download_firmware(struct kim_data_s *kim_gdata)
 
 /**********************************************************************/
 /* functions called from ST core */
-/* function to toggle the GPIO
- * needs to know whether the GPIO is active high or active low
- */
-void st_kim_chip_toggle(enum proto_type type, enum kim_gpio_state state)
-{
-	struct platform_device	*kim_pdev;
-	struct kim_data_s	*kim_gdata;
-	pr_info(" %s ", __func__);
-
-	kim_pdev = st_get_plat_device(0);
-	kim_gdata = dev_get_drvdata(&kim_pdev->dev);
-
-	if (kim_gdata->gpios[type] == -1) {
-		pr_info("gpio not requested for protocol %d", type);
-		return;
-	}
-	switch (type) {
-	case ST_BT:
-		/*Do Nothing */
-		break;
-
-	case ST_FM:
-		if (state == KIM_GPIO_ACTIVE)
-			gpio_set_value(kim_gdata->gpios[ST_FM], GPIO_LOW);
-		else
-			gpio_set_value(kim_gdata->gpios[ST_FM], GPIO_HIGH);
-		break;
-
-	case ST_GPS:
-		if (state == KIM_GPIO_ACTIVE)
-			gpio_set_value(kim_gdata->gpios[ST_GPS], GPIO_HIGH);
-		else
-			gpio_set_value(kim_gdata->gpios[ST_GPS], GPIO_LOW);
-		break;
-
-	case ST_MAX_CHANNELS:
-	default:
-		break;
-	}
-
-	return;
-}
-
 /* called from ST Core, when REG_IN_PROGRESS (registration in progress)
  * can be because of
  * 1. response to read local version
@@ -482,9 +439,9 @@ long st_kim_start(void *kim_data)
 
 	do {
 		/* Configure BT nShutdown to HIGH state */
-		gpio_set_value(kim_gdata->gpios[ST_BT], GPIO_LOW);
+		gpio_set_value(kim_gdata->nshutdown, GPIO_LOW);
 		mdelay(5);	/* FIXME: a proper toggle */
-		gpio_set_value(kim_gdata->gpios[ST_BT], GPIO_HIGH);
+		gpio_set_value(kim_gdata->nshutdown, GPIO_HIGH);
 		mdelay(100);
 		/* re-initialize the completion */
 		INIT_COMPLETION(kim_gdata->ldisc_installed);
@@ -552,11 +509,11 @@ long st_kim_stop(void *kim_data)
 	}
 
 	/* By default configure BT nShutdown to LOW state */
-	gpio_set_value(kim_gdata->gpios[ST_BT], GPIO_LOW);
+	gpio_set_value(kim_gdata->nshutdown, GPIO_LOW);
 	mdelay(1);
-	gpio_set_value(kim_gdata->gpios[ST_BT], GPIO_HIGH);
+	gpio_set_value(kim_gdata->nshutdown, GPIO_HIGH);
 	mdelay(1);
-	gpio_set_value(kim_gdata->gpios[ST_BT], GPIO_LOW);
+	gpio_set_value(kim_gdata->nshutdown, GPIO_LOW);
 	return err;
 }
 
@@ -685,10 +642,8 @@ struct dentry *kim_debugfs_dir;
 static int kim_probe(struct platform_device *pdev)
 {
 	long status;
-	long proto;
 	struct kim_data_s	*kim_gdata;
 	struct ti_st_plat_data	*pdata = pdev->dev.platform_data;
-	long *gpios = pdata->gpios;
 
 	if ((pdev->id != -1) && (pdev->id < MAX_ST_DEVICES)) {
 		/* multiple devices could exist */
@@ -713,40 +668,19 @@ static int kim_probe(struct platform_device *pdev)
 	/* refer to itself */
 	kim_gdata->core_data->kim_data = kim_gdata;
 
-	for (proto = 0; proto < ST_MAX_CHANNELS; proto++) {
-		kim_gdata->gpios[proto] = gpios[proto];
-		pr_info(" %ld gpio to be requested", gpios[proto]);
+	/* Claim the chip enable nShutdown gpio from the system */
+	kim_gdata->nshutdown = pdata->nshutdown_gpio;
+	status = gpio_request(kim_gdata->nshutdown, "kim");
+	if (unlikely(status)) {
+		pr_err(" gpio %ld request failed ", kim_gdata->nshutdown);
+		return status;
 	}
 
-	for (proto = 0; (proto < ST_MAX_CHANNELS)
-			&& (gpios[proto] != -1); proto++) {
-		/* Claim the Bluetooth/FM/GPIO
-		 * nShutdown gpio from the system
-		 */
-		status = gpio_request(gpios[proto], "kim");
-		if (unlikely(status)) {
-			pr_err(" gpio %ld request failed ", gpios[proto]);
-			proto -= 1;
-			while (proto >= 0) {
-				if (gpios[proto] != -1)
-					gpio_free(gpios[proto]);
-			}
-			return status;
-		}
-
-		/* Configure nShutdown GPIO as output=0 */
-		status =
-		    gpio_direction_output(gpios[proto], 0);
-		if (unlikely(status)) {
-			pr_err(" unable to configure gpio %ld",
-				   gpios[proto]);
-			proto -= 1;
-			while (proto >= 0) {
-				if (gpios[proto] != -1)
-					gpio_free(gpios[proto]);
-			}
-			return status;
-		}
+	/* Configure nShutdown GPIO as output=0 */
+	status = gpio_direction_output(kim_gdata->nshutdown, 0);
+	if (unlikely(status)) {
+		pr_err(" unable to configure gpio %ld", kim_gdata->nshutdown);
+		return status;
 	}
 	/* get reference of pdev for request_firmware
 	 */
@@ -785,23 +719,20 @@ static int kim_remove(struct platform_device *pdev)
 {
 	/* free the GPIOs requested */
 	struct ti_st_plat_data	*pdata = pdev->dev.platform_data;
-	long *gpios = pdata->gpios;
-	long proto;
 	struct kim_data_s	*kim_gdata;
 
 	kim_gdata = dev_get_drvdata(&pdev->dev);
 
-	for (proto = 0; (proto < ST_MAX_CHANNELS)
-		&& (gpios[proto] != -1); proto++) {
-		/* Claim the Bluetooth/FM/GPIO
-		 * nShutdown gpio from the system
-		 */
-		gpio_free(gpios[proto]);
-	}
-	pr_info("kim: GPIO Freed");
-	debugfs_remove_recursive(kim_debugfs_dir);
+	/* Free the Bluetooth/FM/GPIO
+	 * nShutdown gpio from the system
+	 */
+	gpio_free(pdata->nshutdown_gpio);
+	pr_info("nshutdown GPIO Freed");
 
+	debugfs_remove_recursive(kim_debugfs_dir);
 	sysfs_remove_group(&pdev->dev.kobj, &uim_attr_grp);
+	pr_info("sysfs entries removed");
+
 	kim_gdata->kim_pdev = NULL;
 	st_core_exit(kim_gdata->core_data);
 
diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 7885a779c588..7071ec5d0118 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -25,15 +25,6 @@
 #ifndef TI_WILINK_ST_H
 #define TI_WILINK_ST_H
 
-/**
- * enum kim_gpio_state - Few protocols such as FM have ACTIVE LOW
- *	gpio states for their chip/core enable gpios
- */
-enum kim_gpio_state {
-	KIM_GPIO_INACTIVE,
-	KIM_GPIO_ACTIVE,
-};
-
 /**
  * enum proto-type - The protocol on WiLink chips which share a
  *	common physical interface like UART.
@@ -252,14 +243,11 @@ struct chip_version {
  *	the ldisc was properly installed.
  * @resp_buffer: data buffer for the .bts fw file name.
  * @fw_entry: firmware class struct to request/release the fw.
- * @gpios: the list of core/chip enable gpios for BT, FM and GPS cores.
  * @rx_state: the rx state for kim's receive func during fw download.
  * @rx_count: the rx count for the kim's receive func during fw download.
  * @rx_skb: all of fw data might not come at once, and hence data storage for
  *	whole of the fw response, only HCI_EVENTs and hence diff from ST's
  *	response.
- * @rfkill: rfkill data for each of the cores to be registered with rfkill.
- * @rf_protos: proto types of the data registered with rfkill sub-system.
  * @core_data: ST core's data, which mainly is the tty's disc_data
  * @version: chip version available via a sysfs entry.
  *
@@ -270,12 +258,10 @@ struct kim_data_s {
 	struct completion kim_rcvd, ldisc_installed;
 	char resp_buffer[30];
 	const struct firmware *fw_entry;
-	long gpios[ST_MAX_CHANNELS];
+	long nshutdown;
 	unsigned long rx_state;
 	unsigned long rx_count;
 	struct sk_buff *rx_skb;
-	struct rfkill *rfkill[ST_MAX_CHANNELS];
-	enum proto_type rf_protos[ST_MAX_CHANNELS];
 	struct st_data_s *core_data;
 	struct chip_version version;
 	unsigned char ldisc_install;
@@ -293,7 +279,6 @@ long st_kim_start(void *);
 long st_kim_stop(void *);
 
 void st_kim_recv(void *, const unsigned char *, long count);
-void st_kim_chip_toggle(enum proto_type, enum kim_gpio_state);
 void st_kim_complete(void *);
 void kim_st_list_protocols(struct st_data_s *, void *);
 
@@ -426,7 +411,7 @@ struct gps_event_hdr {
 
 /* platform data */
 struct ti_st_plat_data {
-	long gpios[ST_MAX_CHANNELS]; /* BT, FM and GPS */
+	long nshutdown_gpio;
 	unsigned char dev_name[UART_DEV_NAME_LEN]; /* uart name */
 	unsigned char flow_cntrl; /* flow control flag */
 	unsigned long baud_rate;
-- 
cgit v1.2.3


From 92d8682926342d2b6aa5b2ecc02221e00e1573a0 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 4 Feb 2011 15:55:25 -0800
Subject: inetpeer: Move ICMP rate limiting state into inet_peer entries.

Like metrics, the ICMP rate limiting bits are cached state about
a destination.  So move it into the inet_peer entries.

If an inet_peer cannot be bound (the reason is memory allocation
failure or similar), the policy is to allow.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h      |  2 --
 include/net/icmp.h     |  3 ---
 include/net/inetpeer.h |  3 +++
 net/ipv4/icmp.c        | 49 ++++++++-----------------------------------
 net/ipv4/inetpeer.c    | 43 ++++++++++++++++++++++++++++++++++++++
 net/ipv4/route.c       | 56 ++++++++++++++++++++++++++++++++++----------------
 net/ipv6/icmp.c        | 16 ++++++++-------
 net/ipv6/ip6_output.c  |  5 ++++-
 net/ipv6/ndisc.c       |  4 +++-
 9 files changed, 108 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 484f80b69ada..e550195d4f86 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -78,8 +78,6 @@ struct dst_entry {
 	atomic_t		__refcnt;	/* client references	*/
 	int			__use;
 	unsigned long		lastuse;
-	unsigned long		rate_last;	/* rate limiting for ICMP */
-	unsigned int		rate_tokens;
 	int			flags;
 #define DST_HOST		0x0001
 #define DST_NOXFRM		0x0002
diff --git a/include/net/icmp.h b/include/net/icmp.h
index 6e991e0d0d6f..f0698b955b73 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -45,7 +45,4 @@ extern int	icmp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 extern int	icmp_init(void);
 extern void	icmp_out_count(struct net *net, unsigned char type);
 
-/* Move into dst.h ? */
-extern int 	xrlim_allow(struct dst_entry *dst, int timeout);
-
 #endif	/* _ICMP_H */
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 61f2c66edb2a..ead2cb2de18c 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -44,6 +44,8 @@ struct inet_peer {
 			__u32		tcp_ts;
 			__u32		tcp_ts_stamp;
 			u32		metrics[RTAX_MAX];
+			u32		rate_tokens;	/* rate limiting for ICMP */
+			unsigned long	rate_last;
 		};
 		struct rcu_head         rcu;
 	};
@@ -81,6 +83,7 @@ static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int cr
 
 /* can be called from BH context or outside */
 extern void inet_putpeer(struct inet_peer *p);
+extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 
 /*
  * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 4aa1b7f01ea0..ad2bcf1b69ae 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -233,48 +233,11 @@ static inline void icmp_xmit_unlock(struct sock *sk)
  *	Send an ICMP frame.
  */
 
-/*
- *	Check transmit rate limitation for given message.
- *	The rate information is held in the destination cache now.
- *	This function is generic and could be used for other purposes
- *	too. It uses a Token bucket filter as suggested by Alexey Kuznetsov.
- *
- *	Note that the same dst_entry fields are modified by functions in
- *	route.c too, but these work for packet destinations while xrlim_allow
- *	works for icmp destinations. This means the rate limiting information
- *	for one "ip object" is shared - and these ICMPs are twice limited:
- *	by source and by destination.
- *
- *	RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate
- *			  SHOULD allow setting of rate limits
- *
- * 	Shared between ICMPv4 and ICMPv6.
- */
-#define XRLIM_BURST_FACTOR 6
-int xrlim_allow(struct dst_entry *dst, int timeout)
-{
-	unsigned long now, token = dst->rate_tokens;
-	int rc = 0;
-
-	now = jiffies;
-	token += now - dst->rate_last;
-	dst->rate_last = now;
-	if (token > XRLIM_BURST_FACTOR * timeout)
-		token = XRLIM_BURST_FACTOR * timeout;
-	if (token >= timeout) {
-		token -= timeout;
-		rc = 1;
-	}
-	dst->rate_tokens = token;
-	return rc;
-}
-EXPORT_SYMBOL(xrlim_allow);
-
-static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
+static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 		int type, int code)
 {
 	struct dst_entry *dst = &rt->dst;
-	int rc = 1;
+	bool rc = true;
 
 	if (type > NR_ICMP_TYPES)
 		goto out;
@@ -288,8 +251,12 @@ static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 		goto out;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if ((1 << type) & net->ipv4.sysctl_icmp_ratemask)
-		rc = xrlim_allow(dst, net->ipv4.sysctl_icmp_ratelimit);
+	if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) {
+		if (!rt->peer)
+			rt_bind_peer(rt, 1);
+		rc = inet_peer_xrlim_allow(rt->peer,
+					   net->ipv4.sysctl_icmp_ratelimit);
+	}
 out:
 	return rc;
 }
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b6513b13d729..709fbb4132d7 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -513,6 +513,8 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 		atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4));
 		p->tcp_ts_stamp = 0;
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
+		p->rate_tokens = 0;
+		p->rate_last = 0;
 		INIT_LIST_HEAD(&p->unused);
 
 
@@ -580,3 +582,44 @@ void inet_putpeer(struct inet_peer *p)
 	local_bh_enable();
 }
 EXPORT_SYMBOL_GPL(inet_putpeer);
+
+/*
+ *	Check transmit rate limitation for given message.
+ *	The rate information is held in the inet_peer entries now.
+ *	This function is generic and could be used for other purposes
+ *	too. It uses a Token bucket filter as suggested by Alexey Kuznetsov.
+ *
+ *	Note that the same inet_peer fields are modified by functions in
+ *	route.c too, but these work for packet destinations while xrlim_allow
+ *	works for icmp destinations. This means the rate limiting information
+ *	for one "ip object" is shared - and these ICMPs are twice limited:
+ *	by source and by destination.
+ *
+ *	RFC 1812: 4.3.2.8 SHOULD be able to limit error message rate
+ *			  SHOULD allow setting of rate limits
+ *
+ * 	Shared between ICMPv4 and ICMPv6.
+ */
+#define XRLIM_BURST_FACTOR 6
+bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
+{
+	unsigned long now, token;
+	bool rc = false;
+
+	if (!peer)
+		return true;
+
+	token = peer->rate_tokens;
+	now = jiffies;
+	token += now - peer->rate_last;
+	peer->rate_last = now;
+	if (token > XRLIM_BURST_FACTOR * timeout)
+		token = XRLIM_BURST_FACTOR * timeout;
+	if (token >= timeout) {
+		token -= timeout;
+		rc = true;
+	}
+	peer->rate_tokens = token;
+	return rc;
+}
+EXPORT_SYMBOL(inet_peer_xrlim_allow);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0ba6a382b2b4..2e225dafc4f8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1563,6 +1563,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 {
 	struct rtable *rt = skb_rtable(skb);
 	struct in_device *in_dev;
+	struct inet_peer *peer;
 	int log_martians;
 
 	rcu_read_lock();
@@ -1574,33 +1575,41 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	log_martians = IN_DEV_LOG_MARTIANS(in_dev);
 	rcu_read_unlock();
 
+	if (!rt->peer)
+		rt_bind_peer(rt, 1);
+	peer = rt->peer;
+	if (!peer) {
+		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+		return;
+	}
+
 	/* No redirected packets during ip_rt_redirect_silence;
 	 * reset the algorithm.
 	 */
-	if (time_after(jiffies, rt->dst.rate_last + ip_rt_redirect_silence))
-		rt->dst.rate_tokens = 0;
+	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+		peer->rate_tokens = 0;
 
 	/* Too many ignored redirects; do not send anything
 	 * set dst.rate_last to the last seen redirected packet.
 	 */
-	if (rt->dst.rate_tokens >= ip_rt_redirect_number) {
-		rt->dst.rate_last = jiffies;
+	if (peer->rate_tokens >= ip_rt_redirect_number) {
+		peer->rate_last = jiffies;
 		return;
 	}
 
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (rt->dst.rate_tokens == 0 ||
+	if (peer->rate_tokens == 0 ||
 	    time_after(jiffies,
-		       (rt->dst.rate_last +
-			(ip_rt_redirect_load << rt->dst.rate_tokens)))) {
+		       (peer->rate_last +
+			(ip_rt_redirect_load << peer->rate_tokens)))) {
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
-		rt->dst.rate_last = jiffies;
-		++rt->dst.rate_tokens;
+		peer->rate_last = jiffies;
+		++peer->rate_tokens;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
-		    rt->dst.rate_tokens == ip_rt_redirect_number &&
+		    peer->rate_tokens == ip_rt_redirect_number &&
 		    net_ratelimit())
 			printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
 				&rt->rt_src, rt->rt_iif,
@@ -1612,7 +1621,9 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 static int ip_error(struct sk_buff *skb)
 {
 	struct rtable *rt = skb_rtable(skb);
+	struct inet_peer *peer;
 	unsigned long now;
+	bool send;
 	int code;
 
 	switch (rt->dst.error) {
@@ -1632,15 +1643,24 @@ static int ip_error(struct sk_buff *skb)
 			break;
 	}
 
-	now = jiffies;
-	rt->dst.rate_tokens += now - rt->dst.rate_last;
-	if (rt->dst.rate_tokens > ip_rt_error_burst)
-		rt->dst.rate_tokens = ip_rt_error_burst;
-	rt->dst.rate_last = now;
-	if (rt->dst.rate_tokens >= ip_rt_error_cost) {
-		rt->dst.rate_tokens -= ip_rt_error_cost;
-		icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
+	if (!rt->peer)
+		rt_bind_peer(rt, 1);
+	peer = rt->peer;
+
+	send = true;
+	if (peer) {
+		now = jiffies;
+		peer->rate_tokens += now - peer->rate_last;
+		if (peer->rate_tokens > ip_rt_error_burst)
+			peer->rate_tokens = ip_rt_error_burst;
+		peer->rate_last = now;
+		if (peer->rate_tokens >= ip_rt_error_cost)
+			peer->rate_tokens -= ip_rt_error_cost;
+		else
+			send = false;
 	}
+	if (send)
+		icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
 
 out:	kfree_skb(skb);
 	return 0;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 03e62f94ff8e..a31d91b04c87 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -157,20 +157,20 @@ static int is_ineligible(struct sk_buff *skb)
 /*
  * Check the ICMP output rate limit
  */
-static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type,
-				     struct flowi *fl)
+static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+				      struct flowi *fl)
 {
 	struct dst_entry *dst;
 	struct net *net = sock_net(sk);
-	int res = 0;
+	bool res = false;
 
 	/* Informational messages are not limited. */
 	if (type & ICMPV6_INFOMSG_MASK)
-		return 1;
+		return true;
 
 	/* Do not limit pmtu discovery, it would break it. */
 	if (type == ICMPV6_PKT_TOOBIG)
-		return 1;
+		return true;
 
 	/*
 	 * Look up the output route.
@@ -182,7 +182,7 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type,
 		IP6_INC_STATS(net, ip6_dst_idev(dst),
 			      IPSTATS_MIB_OUTNOROUTES);
 	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
-		res = 1;
+		res = true;
 	} else {
 		struct rt6_info *rt = (struct rt6_info *)dst;
 		int tmo = net->ipv6.sysctl.icmpv6_time;
@@ -191,7 +191,9 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type,
 		if (rt->rt6i_dst.plen < 128)
 			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
 
-		res = xrlim_allow(dst, tmo);
+		if (!rt->rt6i_peer)
+			rt6_bind_peer(rt, 1);
+		res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo);
 	}
 	dst_release(dst);
 	return res;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5f8d242be3f3..2600e2288724 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -479,10 +479,13 @@ int ip6_forward(struct sk_buff *skb)
 		else
 			target = &hdr->daddr;
 
+		if (!rt->rt6i_peer)
+			rt6_bind_peer(rt, 1);
+
 		/* Limit redirects both by destination (here)
 		   and by source (inside ndisc_send_redirect)
 		 */
-		if (xrlim_allow(dst, 1*HZ))
+		if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
 			ndisc_send_redirect(skb, n, target);
 	} else {
 		int addrtype = ipv6_addr_type(&hdr->saddr);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 2342545a5ee9..7254ce364006 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1553,7 +1553,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 			   "ICMPv6 Redirect: destination is not a neighbour.\n");
 		goto release;
 	}
-	if (!xrlim_allow(dst, 1*HZ))
+	if (!rt->rt6i_peer)
+		rt6_bind_peer(rt, 1);
+	if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
 		goto release;
 
 	if (dev->addr_len) {
-- 
cgit v1.2.3


From 7eb38527c4e485923fa3f87d11ce11b4e6ebf807 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 5 Feb 2011 18:13:45 -0800
Subject: tcp: Add reference to initial CWND ietf draft.

Suggested by Alexander Zimmermann

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7118668ad534..adfe6dbe9053 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -196,7 +196,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* TCP thin-stream limits */
 #define TCP_THIN_LINEAR_RETRIES 6       /* After 6 linear retries, do exp. backoff */
 
-/* TCP initial congestion window */
+/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */
 #define TCP_INIT_CWND		10
 
 extern struct inet_timewait_death_row tcp_death_row;
-- 
cgit v1.2.3


From 4a3d27e98a7f2682e96d6f863752e0424b00d691 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 27 Jan 2011 23:19:49 -0500
Subject: tracing/filter: Move MAX_FILTER_PRED to local tracing directory

The MAX_FILTER_PRED is only needed by the kernel/trace/*.c files.
Move it to kernel/trace/trace.h.

Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h | 1 -
 kernel/trace/trace.h         | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 47e3997f7b5c..1a99e7939c2b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -208,7 +208,6 @@ struct ftrace_event_call {
 
 #define PERF_MAX_TRACE_SIZE	2048
 
-#define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
 extern void destroy_preds(struct ftrace_event_call *call);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d754330934bb..fbff872f8db1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -680,6 +680,8 @@ struct event_subsystem {
 #define FILTER_PRED_IS_RIGHT	(1 << 15)
 #define FILTER_PRED_FOLD	(1 << 15)
 
+#define MAX_FILTER_PRED		32
+
 struct filter_pred;
 struct regex;
 
-- 
cgit v1.2.3


From ba976970c79fd2fbfe1a4b3b6766a318f4eb9d4c Mon Sep 17 00:00:00 2001
From: Ian Munsie <imunsie@au1.ibm.com>
Date: Thu, 3 Feb 2011 14:27:20 +1100
Subject: tracing/syscalls: Don't add events for unmapped syscalls

FTRACE_SYSCALLS would create events for each and every system call, even
if it had failed to map the system call's name with it's number. This
resulted in a number of events being created that would not behave as
expected.

This could happen, for example, on architectures who's symbol names are
unusual and will not match the system call name. It could also happen
with system calls which were mapped to sys_ni_syscall.

This patch changes the default system call number in the metadata to -1.
If the system call name from the metadata is not successfully mapped to
a system call number during boot, than the event initialisation routine
will now return an error, preventing the event from being created.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
LKML-Reference: <1296703645-18718-2-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/syscalls.h      | 2 ++
 kernel/trace/trace_syscalls.c | 8 ++++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 98664db1be47..8e8968e74544 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -158,6 +158,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	static struct syscall_metadata __used			\
 	  __syscall_meta_##sname = {				\
 		.name 		= "sys"#sname,			\
+		.syscall_nr	= -1,	/* Filled in at boot */	\
 		.nb_args 	= nb,				\
 		.types		= types_##sname,		\
 		.args		= args_##sname,			\
@@ -175,6 +176,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	static struct syscall_metadata __used			\
 	  __syscall_meta__##sname = {				\
 		.name 		= "sys_"#sname,			\
+		.syscall_nr	= -1,	/* Filled in at boot */	\
 		.nb_args 	= 0,				\
 		.enter_event	= &event_enter__##sname,	\
 		.exit_event	= &event_exit__##sname,		\
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5c9fe08d2093..a9ceabd52247 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -424,6 +424,14 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
 int init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (num < 0 || num >= NR_syscalls) {
+		pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
+				((struct syscall_metadata *)call->data)->name);
+		return -ENOSYS;
+	}
 
 	if (set_syscall_print_fmt(call) < 0)
 		return -ENOMEM;
-- 
cgit v1.2.3


From e702112ff68a554bcac16bb03ddc2b8e5425bcbf Mon Sep 17 00:00:00 2001
From: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
Date: Mon, 3 Jan 2011 11:14:36 +0200
Subject: Bluetooth: Use non-flushable by default L2CAP data packets

Modification of Nick Pelly <npelly@google.com> patch.

With Bluetooth 2.1 ACL packets can be flushable or non-flushable. This commit
makes ACL data packets non-flushable by default on compatible chipsets, and
adds the BT_FLUSHABLE socket option to explicitly request flushable ACL
data packets for a given L2CAP socket. This is useful for A2DP data which can
be safely discarded if it can not be delivered within a short time (while
other ACL data should not be discarded).

Note that making ACL data flushable has no effect unless the automatic flush
timeout for that ACL link is changed from its default of 0 (infinite).

Default packet types (for compatible chipsets):
Frame 34: 13 bytes on wire (104 bits), 13 bytes captured (104 bits)
Bluetooth HCI H4
Bluetooth HCI ACL Packet
    .... 0000 0000 0010 = Connection Handle: 0x0002
    ..00 .... .... .... = PB Flag: First Non-automatically Flushable Packet (0)
    00.. .... .... .... = BC Flag: Point-To-Point (0)
    Data Total Length: 8
Bluetooth L2CAP Packet

After setting BT_FLUSHABLE
(sock.setsockopt(274 /*SOL_BLUETOOTH*/, 8 /* BT_FLUSHABLE */, 1 /* flush */))
Frame 34: 13 bytes on wire (104 bits), 13 bytes captured (104 bits)
Bluetooth HCI H4
Bluetooth HCI ACL Packet
    .... 0000 0000 0010 = Connection Handle: 0x0002
    ..10 .... .... .... = PB Flag: First Automatically Flushable Packet (2)
    00.. .... .... .... = BC Flag: Point-To-Point (0)
    Data Total Length: 8
Bluetooth L2CAP Packet

Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/bluetooth.h |  5 ++++
 include/net/bluetooth/hci.h       |  2 ++
 include/net/bluetooth/hci_core.h  |  1 +
 include/net/bluetooth/l2cap.h     |  1 +
 net/bluetooth/hci_core.c          |  7 +++--
 net/bluetooth/l2cap.c             | 59 ++++++++++++++++++++++++++++++++++++---
 6 files changed, 69 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 0c5e72503b77..ed7d775337e0 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -64,6 +64,11 @@ struct bt_security {
 
 #define BT_DEFER_SETUP	7
 
+#define BT_FLUSHABLE	8
+
+#define BT_FLUSHABLE_OFF	0
+#define BT_FLUSHABLE_ON		1
+
 #define BT_INFO(fmt, arg...) printk(KERN_INFO "Bluetooth: " fmt "\n" , ## arg)
 #define BT_ERR(fmt, arg...)  printk(KERN_ERR "%s: " fmt "\n" , __func__ , ## arg)
 #define BT_DBG(fmt, arg...)  pr_debug("%s: " fmt "\n" , __func__ , ## arg)
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 29a7a8ca0438..5d033dc9d43b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -150,6 +150,7 @@ enum {
 #define EDR_ESCO_MASK  (ESCO_2EV3 | ESCO_3EV3 | ESCO_2EV5 | ESCO_3EV5)
 
 /* ACL flags */
+#define ACL_START_NO_FLUSH	0x00
 #define ACL_CONT		0x01
 #define ACL_START		0x02
 #define ACL_ACTIVE_BCAST	0x04
@@ -194,6 +195,7 @@ enum {
 #define LMP_EDR_3S_ESCO	0x80
 
 #define LMP_SIMPLE_PAIR	0x08
+#define LMP_NO_FLUSH	0x40
 
 /* Connection modes */
 #define HCI_CM_ACTIVE	0x0000
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d2cf88407690..4e14610baece 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -458,6 +458,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_sniffsubr_capable(dev) ((dev)->features[5] & LMP_SNIFF_SUBR)
 #define lmp_esco_capable(dev)      ((dev)->features[3] & LMP_ESCO)
 #define lmp_ssp_capable(dev)       ((dev)->features[6] & LMP_SIMPLE_PAIR)
+#define lmp_no_flush_capable(dev)  ((dev)->features[6] & LMP_NO_FLUSH)
 
 /* ----- HCI protocols ----- */
 struct hci_proto {
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 7ad25ca60ec0..7f88a87d7a46 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -327,6 +327,7 @@ struct l2cap_pinfo {
 	__u8		sec_level;
 	__u8		role_switch;
 	__u8		force_reliable;
+	__u8		flushable;
 
 	__u8		conf_req[64];
 	__u8		conf_len;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 9c4541bc488a..9ba92adaa9ad 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1395,7 +1395,7 @@ void hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags)
 
 	skb->dev = (void *) hdev;
 	bt_cb(skb)->pkt_type = HCI_ACLDATA_PKT;
-	hci_add_acl_hdr(skb, conn->handle, flags | ACL_START);
+	hci_add_acl_hdr(skb, conn->handle, flags);
 
 	list = skb_shinfo(skb)->frag_list;
 	if (!list) {
@@ -1413,12 +1413,15 @@ void hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags)
 		spin_lock_bh(&conn->data_q.lock);
 
 		__skb_queue_tail(&conn->data_q, skb);
+
+		flags &= ~ACL_START;
+		flags |= ACL_CONT;
 		do {
 			skb = list; list = list->next;
 
 			skb->dev = (void *) hdev;
 			bt_cb(skb)->pkt_type = HCI_ACLDATA_PKT;
-			hci_add_acl_hdr(skb, conn->handle, flags | ACL_CONT);
+			hci_add_acl_hdr(skb, conn->handle, flags);
 
 			BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len);
 
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 675614e38e14..4bf98dfd24bc 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -373,13 +373,19 @@ static inline u8 l2cap_get_ident(struct l2cap_conn *conn)
 static inline void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data)
 {
 	struct sk_buff *skb = l2cap_build_cmd(conn, code, ident, len, data);
+	u8 flags;
 
 	BT_DBG("code 0x%2.2x", code);
 
 	if (!skb)
 		return;
 
-	hci_send_acl(conn->hcon, skb, 0);
+	if (lmp_no_flush_capable(conn->hcon->hdev))
+		flags = ACL_START_NO_FLUSH;
+	else
+		flags = ACL_START;
+
+	hci_send_acl(conn->hcon, skb, flags);
 }
 
 static inline void l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control)
@@ -389,6 +395,7 @@ static inline void l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control)
 	struct l2cap_conn *conn = pi->conn;
 	struct sock *sk = (struct sock *)pi;
 	int count, hlen = L2CAP_HDR_SIZE + 2;
+	u8 flags;
 
 	if (sk->sk_state != BT_CONNECTED)
 		return;
@@ -425,7 +432,12 @@ static inline void l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control)
 		put_unaligned_le16(fcs, skb_put(skb, 2));
 	}
 
-	hci_send_acl(pi->conn->hcon, skb, 0);
+	if (lmp_no_flush_capable(conn->hcon->hdev))
+		flags = ACL_START_NO_FLUSH;
+	else
+		flags = ACL_START;
+
+	hci_send_acl(pi->conn->hcon, skb, flags);
 }
 
 static inline void l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control)
@@ -912,6 +924,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 		pi->sec_level = l2cap_pi(parent)->sec_level;
 		pi->role_switch = l2cap_pi(parent)->role_switch;
 		pi->force_reliable = l2cap_pi(parent)->force_reliable;
+		pi->flushable = l2cap_pi(parent)->flushable;
 	} else {
 		pi->imtu = L2CAP_DEFAULT_MTU;
 		pi->omtu = 0;
@@ -927,6 +940,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 		pi->sec_level = BT_SECURITY_LOW;
 		pi->role_switch = 0;
 		pi->force_reliable = 0;
+		pi->flushable = BT_FLUSHABLE_OFF;
 	}
 
 	/* Default config options */
@@ -1431,10 +1445,17 @@ static void l2cap_drop_acked_frames(struct sock *sk)
 static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
+	struct hci_conn *hcon = pi->conn->hcon;
+	u16 flags;
 
 	BT_DBG("sk %p, skb %p len %d", sk, skb, skb->len);
 
-	hci_send_acl(pi->conn->hcon, skb, 0);
+	if (!pi->flushable && lmp_no_flush_capable(hcon->hdev))
+		flags = ACL_START_NO_FLUSH;
+	else
+		flags = ACL_START;
+
+	hci_send_acl(hcon, skb, flags);
 }
 
 static void l2cap_streaming_send(struct sock *sk)
@@ -2079,6 +2100,30 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch
 		bt_sk(sk)->defer_setup = opt;
 		break;
 
+	case BT_FLUSHABLE:
+		if (get_user(opt, (u32 __user *) optval)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (opt > BT_FLUSHABLE_ON) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (opt == BT_FLUSHABLE_OFF) {
+			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+			/* proceed futher only when we have l2cap_conn and
+			   No Flush support in the LM */
+			if (!conn || !lmp_no_flush_capable(conn->hcon->hdev)) {
+				err = -EINVAL;
+				break;
+			}
+		}
+
+		l2cap_pi(sk)->flushable = opt;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -2218,6 +2263,12 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch
 
 		break;
 
+	case BT_FLUSHABLE:
+		if (put_user(l2cap_pi(sk)->flushable, (u32 __user *) optval))
+			err = -EFAULT;
+
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -4678,7 +4729,7 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl
 
 	BT_DBG("conn %p len %d flags 0x%x", conn, skb->len, flags);
 
-	if (flags & ACL_START) {
+	if (!(flags & ACL_CONT)) {
 		struct l2cap_hdr *hdr;
 		struct sock *sk;
 		u16 cid;
-- 
cgit v1.2.3


From ab81cbf99c881ca2b9a83682a8722fc84b2483d2 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Wed, 15 Dec 2010 13:53:18 +0200
Subject: Bluetooth: Implement automatic setup procedure for local adapters

This patch implements automatic initialization of basic information
about newly registered Bluetooth adapters. E.g. the address and features
are always needed so it makes sense for the kernel to automatically
power on adapters and read this information. A new HCI_SETUP flag is
added to track this state.

In order to not consume unnecessary amounts of power if there isn't a
user space available that could switch the adapter back off, a timer is
added to do this automatically as long as no Bluetooth user space seems
to be present. A new HCI_AUTO_OFF flag is added that user space needs to
clear to avoid the automatic power off.

Additionally, the management interface index_added event is moved to the
end of the HCI_SETUP stage so a user space supporting the managment
inteface has all the necessary information available for fetching when
it gets notified of a new adapter. The HCI_DEV_REG event is kept in the
same place as before since existing HCI raw socket based user space
versions depend on seeing the kernels initialization sequence
(hci_init_req) to determine when the adapter is ready for use.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |  3 ++
 include/net/bluetooth/hci_core.h |  6 ++++
 net/bluetooth/hci_core.c         | 64 ++++++++++++++++++++++++++++++++++++++--
 net/bluetooth/mgmt.c             |  8 +++++
 4 files changed, 79 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 5d033dc9d43b..51c9df16e764 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -76,6 +76,9 @@ enum {
 	HCI_INQUIRY,
 
 	HCI_RAW,
+
+	HCI_SETUP,
+	HCI_AUTO_OFF,
 };
 
 /* HCI ioctl defines */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4e14610baece..75c4f201c1c6 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -114,6 +114,10 @@ struct hci_dev {
 
 	struct workqueue_struct	*workqueue;
 
+	struct work_struct	power_on;
+	struct work_struct	power_off;
+	struct timer_list	off_timer;
+
 	struct tasklet_struct	cmd_task;
 	struct tasklet_struct	rx_task;
 	struct tasklet_struct	tx_task;
@@ -437,6 +441,8 @@ int hci_inquiry(void __user *arg);
 struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr);
 int hci_blacklist_clear(struct hci_dev *hdev);
 
+void hci_del_off_timer(struct hci_dev *hdev);
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
 
 int hci_recv_frame(struct sk_buff *skb);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 9ba92adaa9ad..b22ce9f8bf91 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -50,6 +50,8 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
+#define AUTO_OFF_TIMEOUT 2000
+
 static void hci_cmd_task(unsigned long arg);
 static void hci_rx_task(unsigned long arg);
 static void hci_tx_task(unsigned long arg);
@@ -794,6 +796,7 @@ int hci_get_dev_list(void __user *arg)
 	list_for_each(p, &hci_dev_list) {
 		struct hci_dev *hdev;
 		hdev = list_entry(p, struct hci_dev, list);
+		hci_del_off_timer(hdev);
 		(dr + n)->dev_id  = hdev->id;
 		(dr + n)->dev_opt = hdev->flags;
 		if (++n >= dev_num)
@@ -823,6 +826,8 @@ int hci_get_dev_info(void __user *arg)
 	if (!hdev)
 		return -ENODEV;
 
+	hci_del_off_timer(hdev);
+
 	strcpy(di.name, hdev->name);
 	di.bdaddr   = hdev->bdaddr;
 	di.type     = (hdev->bus & 0x0f) | (hdev->dev_type << 4);
@@ -891,6 +896,51 @@ void hci_free_dev(struct hci_dev *hdev)
 }
 EXPORT_SYMBOL(hci_free_dev);
 
+static void hci_power_on(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev, power_on);
+
+	BT_DBG("%s", hdev->name);
+
+	if (hci_dev_open(hdev->id) < 0)
+		return;
+
+	if (test_bit(HCI_AUTO_OFF, &hdev->flags))
+		mod_timer(&hdev->off_timer,
+				jiffies + msecs_to_jiffies(AUTO_OFF_TIMEOUT));
+
+	if (test_and_clear_bit(HCI_SETUP, &hdev->flags))
+		mgmt_index_added(hdev->id);
+}
+
+static void hci_power_off(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev, power_off);
+
+	BT_DBG("%s", hdev->name);
+
+	hci_dev_close(hdev->id);
+}
+
+static void hci_auto_off(unsigned long data)
+{
+	struct hci_dev *hdev = (struct hci_dev *) data;
+
+	BT_DBG("%s", hdev->name);
+
+	clear_bit(HCI_AUTO_OFF, &hdev->flags);
+
+	queue_work(hdev->workqueue, &hdev->power_off);
+}
+
+void hci_del_off_timer(struct hci_dev *hdev)
+{
+	BT_DBG("%s", hdev->name);
+
+	clear_bit(HCI_AUTO_OFF, &hdev->flags);
+	del_timer(&hdev->off_timer);
+}
+
 /* Register HCI device */
 int hci_register_dev(struct hci_dev *hdev)
 {
@@ -948,6 +998,10 @@ int hci_register_dev(struct hci_dev *hdev)
 
 	INIT_LIST_HEAD(&hdev->blacklist);
 
+	INIT_WORK(&hdev->power_on, hci_power_on);
+	INIT_WORK(&hdev->power_off, hci_power_off);
+	setup_timer(&hdev->off_timer, hci_auto_off, (unsigned long) hdev);
+
 	memset(&hdev->stat, 0, sizeof(struct hci_dev_stats));
 
 	atomic_set(&hdev->promisc, 0);
@@ -969,7 +1023,10 @@ int hci_register_dev(struct hci_dev *hdev)
 		}
 	}
 
-	mgmt_index_added(hdev->id);
+	set_bit(HCI_AUTO_OFF, &hdev->flags);
+	set_bit(HCI_SETUP, &hdev->flags);
+	queue_work(hdev->workqueue, &hdev->power_on);
+
 	hci_notify(hdev, HCI_DEV_REG);
 
 	return id;
@@ -999,7 +1056,10 @@ int hci_unregister_dev(struct hci_dev *hdev)
 	for (i = 0; i < NUM_REASSEMBLY; i++)
 		kfree_skb(hdev->reassembly[i]);
 
-	mgmt_index_removed(hdev->id);
+	if (!test_bit(HCI_INIT, &hdev->flags) &&
+					!test_bit(HCI_SETUP, &hdev->flags))
+		mgmt_index_removed(hdev->id);
+
 	hci_notify(hdev, HCI_DEV_UNREG);
 
 	if (hdev->rfkill) {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ace872615c06..d479e241a9de 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -129,6 +129,12 @@ static int read_index_list(struct sock *sk)
 	i = 0;
 	list_for_each(p, &hci_dev_list) {
 		struct hci_dev *d = list_entry(p, struct hci_dev, list);
+
+		hci_del_off_timer(d);
+
+		if (test_bit(HCI_SETUP, &d->flags))
+			continue;
+
 		put_unaligned_le16(d->id, &rp->index[i++]);
 		BT_DBG("Added hci%u", d->id);
 	}
@@ -180,6 +186,8 @@ static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
 		return cmd_status(sk, MGMT_OP_READ_INFO, ENODEV);
 	}
 
+	hci_del_off_timer(hdev);
+
 	hci_dev_lock_bh(hdev);
 
 	put_unaligned_le16(hdev->id, &rp->index);
-- 
cgit v1.2.3


From 5add6af8fcbce269cac2457584c0ebfda055474a Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 16 Dec 2010 10:00:37 +0200
Subject: Bluetooth: Add support for management powered event

This patch adds support for the powered event that's used to indicate to
userspace when the powered state of a local adapter changes.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  1 +
 include/net/bluetooth/mgmt.h     |  6 ++++++
 net/bluetooth/hci_core.c         |  4 ++++
 net/bluetooth/mgmt.c             | 10 ++++++++++
 4 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 75c4f201c1c6..32e11b37ef28 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -673,6 +673,7 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb);
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
 int mgmt_index_added(u16 index);
 int mgmt_index_removed(u16 index);
+int mgmt_powered(u16 index, u8 powered);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index ca29c1367ffd..0ac1520573ed 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -85,3 +85,9 @@ struct mgmt_ev_index_added {
 struct mgmt_ev_index_removed {
 	__le16 index;
 } __packed;
+
+#define MGMT_EV_POWERED			0x0006
+struct mgmt_ev_powered {
+	__le16 index;
+	__u8 powered;
+} __packed;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b22ce9f8bf91..c5a78e797bc2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -535,6 +535,8 @@ int hci_dev_open(__u16 dev)
 		hci_dev_hold(hdev);
 		set_bit(HCI_UP, &hdev->flags);
 		hci_notify(hdev, HCI_DEV_UP);
+		if (!test_bit(HCI_SETUP, &hdev->flags))
+			mgmt_powered(hdev->id, 1);
 	} else {
 		/* Init failed, cleanup */
 		tasklet_kill(&hdev->rx_task);
@@ -616,6 +618,8 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 	 * and no tasks are scheduled. */
 	hdev->close(hdev);
 
+	mgmt_powered(hdev->id, 0);
+
 	/* Clear flags */
 	hdev->flags = 0;
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d479e241a9de..f746e19ebec0 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -316,3 +316,13 @@ int mgmt_index_removed(u16 index)
 
 	return mgmt_event(MGMT_EV_INDEX_REMOVED, &ev, sizeof(ev));
 }
+
+int mgmt_powered(u16 index, u8 powered)
+{
+	struct mgmt_ev_powered ev;
+
+	put_unaligned_le16(index, &ev.index);
+	ev.powered = powered;
+
+	return mgmt_event(MGMT_EV_POWERED, &ev, sizeof(ev));
+}
-- 
cgit v1.2.3


From eec8d2bcc841ae44edcde9660ff21144a2016053 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 16 Dec 2010 10:17:38 +0200
Subject: Bluetooth: Add support for set_powered management command

This patch adds a set_powered command to the management interface
through which the powered state of local adapters can be controlled.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |   3 +-
 include/net/bluetooth/mgmt.h     |  10 ++
 net/bluetooth/hci_core.c         |   4 +-
 net/bluetooth/hci_event.c        |   2 +-
 net/bluetooth/hci_sock.c         |   6 +-
 net/bluetooth/mgmt.c             | 200 ++++++++++++++++++++++++++++++++++++++-
 6 files changed, 215 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 32e11b37ef28..2d046e07a586 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -667,7 +667,8 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode);
 void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data);
 
 /* ----- HCI Sockets ----- */
-void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb);
+void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb,
+							struct sock *skip_sk);
 
 /* Management interface */
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 0ac1520573ed..81ef78918b66 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -58,6 +58,16 @@ struct mgmt_rp_read_info {
 	__u16 hci_rev;
 } __packed;
 
+#define MGMT_OP_SET_POWERED		0x0005
+struct mgmt_cp_set_powered {
+	__le16 index;
+	__u8 powered;
+} __packed;
+struct mgmt_rp_set_powered {
+	__le16 index;
+	__u8 powered;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c5a78e797bc2..dfc4ef90deca 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1377,7 +1377,7 @@ static int hci_send_frame(struct sk_buff *skb)
 		/* Time stamp */
 		__net_timestamp(skb);
 
-		hci_send_to_sock(hdev, skb);
+		hci_send_to_sock(hdev, skb, NULL);
 	}
 
 	/* Get rid of skb owner, prior to sending to the driver. */
@@ -1767,7 +1767,7 @@ static void hci_rx_task(unsigned long arg)
 	while ((skb = skb_dequeue(&hdev->rx_q))) {
 		if (atomic_read(&hdev->promisc)) {
 			/* Send copy to the sockets */
-			hci_send_to_sock(hdev, skb);
+			hci_send_to_sock(hdev, skb, NULL);
 		}
 
 		if (test_bit(HCI_RAW, &hdev->flags)) {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a290854fdaa6..d42fb35309b5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2083,6 +2083,6 @@ void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data)
 
 	bt_cb(skb)->pkt_type = HCI_EVENT_PKT;
 	skb->dev = (void *) hdev;
-	hci_send_to_sock(hdev, skb);
+	hci_send_to_sock(hdev, skb, NULL);
 	kfree_skb(skb);
 }
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 29827c77f6ce..d50e96136608 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -85,7 +85,8 @@ static struct bt_sock_list hci_sk_list = {
 };
 
 /* Send frame to RAW socket */
-void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
+void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb,
+							struct sock *skip_sk)
 {
 	struct sock *sk;
 	struct hlist_node *node;
@@ -97,6 +98,9 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 		struct hci_filter *flt;
 		struct sk_buff *nskb;
 
+		if (sk == skip_sk)
+			continue;
+
 		if (sk->sk_state != BT_BOUND || hci_pi(sk)->hdev != hdev)
 			continue;
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f746e19ebec0..b65b6ca08463 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -32,6 +32,16 @@
 #define MGMT_VERSION	0
 #define MGMT_REVISION	1
 
+struct pending_cmd {
+	struct list_head list;
+	__u16 opcode;
+	int index;
+	void *cmd;
+	struct sock *sk;
+};
+
+LIST_HEAD(cmd_list);
+
 static int cmd_status(struct sock *sk, u16 cmd, u8 status)
 {
 	struct sk_buff *skb;
@@ -220,6 +230,129 @@ static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
 	return 0;
 }
 
+static void mgmt_pending_free(struct pending_cmd *cmd)
+{
+	sock_put(cmd->sk);
+	kfree(cmd->cmd);
+	kfree(cmd);
+}
+
+static int mgmt_pending_add(struct sock *sk, u16 opcode, int index,
+							void *data, u16 len)
+{
+	struct pending_cmd *cmd;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->opcode = opcode;
+	cmd->index = index;
+
+	cmd->cmd = kmalloc(len, GFP_ATOMIC);
+	if (!cmd->cmd) {
+		kfree(cmd);
+		return -ENOMEM;
+	}
+
+	memcpy(cmd->cmd, data, len);
+
+	cmd->sk = sk;
+	sock_hold(sk);
+
+	list_add(&cmd->list, &cmd_list);
+
+	return 0;
+}
+
+static void mgmt_pending_foreach(u16 opcode, int index,
+				void (*cb)(struct pending_cmd *cmd, void *data),
+				void *data)
+{
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &cmd_list) {
+		struct pending_cmd *cmd;
+
+		cmd = list_entry(p, struct pending_cmd, list);
+
+		if (cmd->opcode != opcode)
+			continue;
+
+		if (index >= 0 && cmd->index != index)
+			continue;
+
+		cb(cmd, data);
+	}
+}
+
+static struct pending_cmd *mgmt_pending_find(u16 opcode, int index)
+{
+	struct list_head *p;
+
+	list_for_each(p, &cmd_list) {
+		struct pending_cmd *cmd;
+
+		cmd = list_entry(p, struct pending_cmd, list);
+
+		if (cmd->opcode != opcode)
+			continue;
+
+		if (index >= 0 && cmd->index != index)
+			continue;
+
+		return cmd;
+	}
+
+	return NULL;
+}
+
+static int set_powered(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct mgmt_cp_set_powered *cp;
+	struct hci_dev *hdev;
+	u16 dev_id;
+	int ret, up;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_POWERED, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	up = test_bit(HCI_UP, &hdev->flags);
+	if ((cp->powered && up) || (!cp->powered && !up)) {
+		ret = cmd_status(sk, MGMT_OP_SET_POWERED, EALREADY);
+		goto failed;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_SET_POWERED, dev_id)) {
+		ret = cmd_status(sk, MGMT_OP_SET_POWERED, EBUSY);
+		goto failed;
+	}
+
+	ret = mgmt_pending_add(sk, MGMT_OP_SET_POWERED, dev_id, data, len);
+	if (ret < 0)
+		goto failed;
+
+	if (cp->powered)
+		queue_work(hdev->workqueue, &hdev->power_on);
+	else
+		queue_work(hdev->workqueue, &hdev->power_off);
+
+	ret = 0;
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+	return ret;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -260,6 +393,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_READ_INFO:
 		err = read_controller_info(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_SET_POWERED:
+		err = set_powered(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -276,7 +412,7 @@ done:
 	return err;
 }
 
-static int mgmt_event(u16 event, void *data, u16 data_len)
+static int mgmt_event(u16 event, void *data, u16 data_len, struct sock *skip_sk)
 {
 	struct sk_buff *skb;
 	struct mgmt_hdr *hdr;
@@ -293,7 +429,7 @@ static int mgmt_event(u16 event, void *data, u16 data_len)
 
 	memcpy(skb_put(skb, data_len), data, data_len);
 
-	hci_send_to_sock(NULL, skb);
+	hci_send_to_sock(NULL, skb, skip_sk);
 	kfree_skb(skb);
 
 	return 0;
@@ -305,7 +441,7 @@ int mgmt_index_added(u16 index)
 
 	put_unaligned_le16(index, &ev.index);
 
-	return mgmt_event(MGMT_EV_INDEX_ADDED, &ev, sizeof(ev));
+	return mgmt_event(MGMT_EV_INDEX_ADDED, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_index_removed(u16 index)
@@ -314,15 +450,69 @@ int mgmt_index_removed(u16 index)
 
 	put_unaligned_le16(index, &ev.index);
 
-	return mgmt_event(MGMT_EV_INDEX_REMOVED, &ev, sizeof(ev));
+	return mgmt_event(MGMT_EV_INDEX_REMOVED, &ev, sizeof(ev), NULL);
+}
+
+struct powered_lookup {
+	u8 powered;
+	struct sock *sk;
+};
+
+static void power_rsp(struct pending_cmd *cmd, void *data)
+{
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_complete *ev;
+	struct mgmt_rp_set_powered *rp;
+	struct mgmt_cp_set_powered *cp = cmd->cmd;
+	struct sk_buff *skb;
+	struct powered_lookup *match = data;
+
+	if (cp->powered != match->powered)
+		return;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(*rp));
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	put_unaligned_le16(cmd->opcode, &ev->opcode);
+
+	rp = (void *) skb_put(skb, sizeof(*rp));
+	put_unaligned_le16(cmd->index, &rp->index);
+	rp->powered = cp->powered;
+
+	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
+		kfree_skb(skb);
+
+	list_del(&cmd->list);
+
+	if (match->sk == NULL) {
+		match->sk = cmd->sk;
+		sock_hold(match->sk);
+	}
+
+	mgmt_pending_free(cmd);
 }
 
 int mgmt_powered(u16 index, u8 powered)
 {
 	struct mgmt_ev_powered ev;
+	struct powered_lookup match = { powered, NULL };
+	int ret;
 
 	put_unaligned_le16(index, &ev.index);
 	ev.powered = powered;
 
-	return mgmt_event(MGMT_EV_POWERED, &ev, sizeof(ev));
+	mgmt_pending_foreach(MGMT_OP_SET_POWERED, index, power_rsp, &match);
+
+	ret = mgmt_event(MGMT_EV_POWERED, &ev, sizeof(ev), match.sk);
+
+	if (match.sk)
+		sock_put(match.sk);
+
+	return ret;
 }
-- 
cgit v1.2.3


From 73f22f62388795c0f6b4f3f97bda7a64f9681aac Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Wed, 29 Dec 2010 16:00:25 +0200
Subject: Bluetooth: Add support for set_discoverable management command

This patch adds a set_discoverable command to the management interface
as well as the corresponding event. The command is used to control the
discoverable state of adapters.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |   1 +
 include/net/bluetooth/mgmt.h     |  16 +++++
 net/bluetooth/hci_event.c        |   5 +-
 net/bluetooth/mgmt.c             | 142 +++++++++++++++++++++++++++++++++++++--
 4 files changed, 158 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2d046e07a586..ee5ec4f17a15 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -675,6 +675,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
 int mgmt_index_added(u16 index);
 int mgmt_index_removed(u16 index);
 int mgmt_powered(u16 index, u8 powered);
+int mgmt_discoverable(u16 index, u8 discoverable);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 81ef78918b66..434dbcf28b6e 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -68,6 +68,16 @@ struct mgmt_rp_set_powered {
 	__u8 powered;
 } __packed;
 
+#define MGMT_OP_SET_DISCOVERABLE	0x0006
+struct mgmt_cp_set_discoverable {
+	__le16 index;
+	__u8 discoverable;
+} __packed;
+struct mgmt_rp_set_discoverable {
+	__le16 index;
+	__u8 discoverable;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
@@ -101,3 +111,9 @@ struct mgmt_ev_powered {
 	__le16 index;
 	__u8 powered;
 } __packed;
+
+#define MGMT_EV_DISCOVERABLE		0x0007
+struct mgmt_ev_discoverable {
+	__le16 index;
+	__u8 discoverable;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d42fb35309b5..f55004af0558 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -278,8 +278,11 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb)
 		clear_bit(HCI_PSCAN, &hdev->flags);
 		clear_bit(HCI_ISCAN, &hdev->flags);
 
-		if (param & SCAN_INQUIRY)
+		if (param & SCAN_INQUIRY) {
 			set_bit(HCI_ISCAN, &hdev->flags);
+			mgmt_discoverable(hdev->id, 1);
+		} else
+			mgmt_discoverable(hdev->id, 0);
 
 		if (param & SCAN_PAGE)
 			set_bit(HCI_PSCAN, &hdev->flags);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index b65b6ca08463..5fa3034fe79f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -307,6 +307,18 @@ static struct pending_cmd *mgmt_pending_find(u16 opcode, int index)
 	return NULL;
 }
 
+static void mgmt_pending_remove(u16 opcode, int index)
+{
+	struct pending_cmd *cmd;
+
+	cmd = mgmt_pending_find(opcode, index);
+	if (cmd == NULL)
+		return;
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+}
+
 static int set_powered(struct sock *sk, unsigned char *data, u16 len)
 {
 	struct mgmt_cp_set_powered *cp;
@@ -353,6 +365,63 @@ failed:
 	return ret;
 }
 
+static int set_discoverable(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct mgmt_cp_set_discoverable *cp;
+	struct hci_dev *hdev;
+	u16 dev_id;
+	u8 scan;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, ENETDOWN);
+		goto failed;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, dev_id) ||
+			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, dev_id) ||
+			hci_sent_cmd_data(hdev, HCI_OP_WRITE_SCAN_ENABLE)) {
+		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, EBUSY);
+		goto failed;
+	}
+
+	if (cp->discoverable == test_bit(HCI_ISCAN, &hdev->flags) &&
+					test_bit(HCI_PSCAN, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, EALREADY);
+		goto failed;
+	}
+
+	err = mgmt_pending_add(sk, MGMT_OP_SET_DISCOVERABLE, dev_id, data, len);
+	if (err < 0)
+		goto failed;
+
+	scan = SCAN_PAGE;
+
+	if (cp->discoverable)
+		scan |= SCAN_INQUIRY;
+
+	err = hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+	if (err < 0)
+		mgmt_pending_remove(MGMT_OP_SET_DISCOVERABLE, dev_id);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -396,6 +465,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_SET_POWERED:
 		err = set_powered(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_SET_DISCOVERABLE:
+		err = set_discoverable(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -453,8 +525,8 @@ int mgmt_index_removed(u16 index)
 	return mgmt_event(MGMT_EV_INDEX_REMOVED, &ev, sizeof(ev), NULL);
 }
 
-struct powered_lookup {
-	u8 powered;
+struct cmd_lookup {
+	u8 value;
 	struct sock *sk;
 };
 
@@ -465,9 +537,9 @@ static void power_rsp(struct pending_cmd *cmd, void *data)
 	struct mgmt_rp_set_powered *rp;
 	struct mgmt_cp_set_powered *cp = cmd->cmd;
 	struct sk_buff *skb;
-	struct powered_lookup *match = data;
+	struct cmd_lookup *match = data;
 
-	if (cp->powered != match->powered)
+	if (cp->powered != match->value)
 		return;
 
 	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
@@ -501,7 +573,7 @@ static void power_rsp(struct pending_cmd *cmd, void *data)
 int mgmt_powered(u16 index, u8 powered)
 {
 	struct mgmt_ev_powered ev;
-	struct powered_lookup match = { powered, NULL };
+	struct cmd_lookup match = { powered, NULL };
 	int ret;
 
 	put_unaligned_le16(index, &ev.index);
@@ -516,3 +588,63 @@ int mgmt_powered(u16 index, u8 powered)
 
 	return ret;
 }
+
+static void discoverable_rsp(struct pending_cmd *cmd, void *data)
+{
+	struct mgmt_cp_set_discoverable *cp = cmd->cmd;
+	struct cmd_lookup *match = data;
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_complete *ev;
+	struct mgmt_rp_set_discoverable *rp;
+
+	if (cp->discoverable != match->value)
+		return;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(*rp));
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	put_unaligned_le16(MGMT_OP_SET_DISCOVERABLE, &ev->opcode);
+
+	rp = (void *) skb_put(skb, sizeof(*rp));
+	put_unaligned_le16(cmd->index, &rp->index);
+	rp->discoverable = cp->discoverable;
+
+	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
+		kfree_skb(skb);
+
+	list_del(&cmd->list);
+
+	if (match->sk == NULL) {
+		match->sk = cmd->sk;
+		sock_hold(match->sk);
+	}
+
+	mgmt_pending_free(cmd);
+}
+
+int mgmt_discoverable(u16 index, u8 discoverable)
+{
+	struct mgmt_ev_discoverable ev;
+	struct cmd_lookup match = { discoverable, NULL };
+	int ret;
+
+	put_unaligned_le16(index, &ev.index);
+	ev.discoverable = discoverable;
+
+	mgmt_pending_foreach(MGMT_OP_SET_DISCOVERABLE, index,
+						discoverable_rsp, &match);
+
+	ret = mgmt_event(MGMT_EV_DISCOVERABLE, &ev, sizeof(ev), match.sk);
+
+	if (match.sk)
+		sock_put(match.sk);
+
+	return ret;
+}
-- 
cgit v1.2.3


From 9fbcbb455dd01abfad4f314b618ac51d566114cb Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 30 Dec 2010 00:18:33 +0200
Subject: Bluetooth: Add set_connectable management command

This patch adds a set_connectable command as well as a corresponding
event to the management interface. It's mainly useful for setting an
adapter as connectable from a non-initialized state as well as setting
an already initialized adapter as non-connectable (mostly useful for
qualification purposes).

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |   1 +
 include/net/bluetooth/mgmt.h     |  17 ++++++
 net/bluetooth/hci_event.c        |  16 +++--
 net/bluetooth/mgmt.c             | 122 ++++++++++++++++++++++++++++++++++++++-
 4 files changed, 149 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ee5ec4f17a15..ba3dbe3188ed 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -676,6 +676,7 @@ int mgmt_index_added(u16 index);
 int mgmt_index_removed(u16 index);
 int mgmt_powered(u16 index, u8 powered);
 int mgmt_discoverable(u16 index, u8 discoverable);
+int mgmt_connectable(u16 index, u8 connectable);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 434dbcf28b6e..008acf54147a 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -47,6 +47,7 @@ struct mgmt_rp_read_info {
 	__le16 index;
 	__u8 type;
 	__u8 powered;
+	__u8 connectable;
 	__u8 discoverable;
 	__u8 pairable;
 	__u8 sec_mode;
@@ -78,6 +79,16 @@ struct mgmt_rp_set_discoverable {
 	__u8 discoverable;
 } __packed;
 
+#define MGMT_OP_SET_CONNECTABLE		0x0007
+struct mgmt_cp_set_connectable {
+	__le16 index;
+	__u8 connectable;
+} __packed;
+struct mgmt_rp_set_connectable {
+	__le16 index;
+	__u8 connectable;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
@@ -117,3 +128,9 @@ struct mgmt_ev_discoverable {
 	__le16 index;
 	__u8 discoverable;
 } __packed;
+
+#define MGMT_EV_CONNECTABLE		0x0008
+struct mgmt_ev_connectable {
+	__le16 index;
+	__u8 connectable;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index f55004af0558..a8a38f17ef78 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -274,18 +274,24 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb)
 
 	if (!status) {
 		__u8 param = *((__u8 *) sent);
+		int old_pscan, old_iscan;
 
-		clear_bit(HCI_PSCAN, &hdev->flags);
-		clear_bit(HCI_ISCAN, &hdev->flags);
+		old_pscan = test_and_clear_bit(HCI_PSCAN, &hdev->flags);
+		old_iscan = test_and_clear_bit(HCI_ISCAN, &hdev->flags);
 
 		if (param & SCAN_INQUIRY) {
 			set_bit(HCI_ISCAN, &hdev->flags);
-			mgmt_discoverable(hdev->id, 1);
-		} else
+			if (!old_iscan)
+				mgmt_discoverable(hdev->id, 1);
+		} else if (old_iscan)
 			mgmt_discoverable(hdev->id, 0);
 
-		if (param & SCAN_PAGE)
+		if (param & SCAN_PAGE) {
 			set_bit(HCI_PSCAN, &hdev->flags);
+			if (!old_pscan)
+				mgmt_connectable(hdev->id, 1);
+		} else if (old_pscan)
+			mgmt_connectable(hdev->id, 0);
 	}
 
 	hci_req_complete(hdev, HCI_OP_WRITE_SCAN_ENABLE, status);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 5fa3034fe79f..fc41cfc3f162 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -204,6 +204,7 @@ static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
 	rp->type = hdev->dev_type;
 
 	rp->powered = test_bit(HCI_UP, &hdev->flags);
+	rp->connectable = test_bit(HCI_PSCAN, &hdev->flags);
 	rp->discoverable = test_bit(HCI_ISCAN, &hdev->flags);
 	rp->pairable = test_bit(HCI_PSCAN, &hdev->flags);
 
@@ -390,8 +391,7 @@ static int set_discoverable(struct sock *sk, unsigned char *data, u16 len)
 	}
 
 	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, dev_id) ||
-			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, dev_id) ||
-			hci_sent_cmd_data(hdev, HCI_OP_WRITE_SCAN_ENABLE)) {
+			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, dev_id)) {
 		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, EBUSY);
 		goto failed;
 	}
@@ -422,6 +422,61 @@ failed:
 	return err;
 }
 
+static int set_connectable(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct mgmt_cp_set_connectable *cp;
+	struct hci_dev *hdev;
+	u16 dev_id;
+	u8 scan;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_CONNECTABLE, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, ENETDOWN);
+		goto failed;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, dev_id) ||
+			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, dev_id)) {
+		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, EBUSY);
+		goto failed;
+	}
+
+	if (cp->connectable == test_bit(HCI_PSCAN, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, EALREADY);
+		goto failed;
+	}
+
+	err = mgmt_pending_add(sk, MGMT_OP_SET_CONNECTABLE, dev_id, data, len);
+	if (err < 0)
+		goto failed;
+
+	if (cp->connectable)
+		scan = SCAN_PAGE;
+	else
+		scan = 0;
+
+	err = hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+	if (err < 0)
+		mgmt_pending_remove(MGMT_OP_SET_CONNECTABLE, dev_id);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -468,6 +523,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_SET_DISCOVERABLE:
 		err = set_discoverable(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_SET_CONNECTABLE:
+		err = set_connectable(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -648,3 +706,63 @@ int mgmt_discoverable(u16 index, u8 discoverable)
 
 	return ret;
 }
+
+static void connectable_rsp(struct pending_cmd *cmd, void *data)
+{
+	struct mgmt_cp_set_connectable *cp = cmd->cmd;
+	struct cmd_lookup *match = data;
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_complete *ev;
+	struct mgmt_rp_set_connectable *rp;
+
+	if (cp->connectable != match->value)
+		return;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(*rp));
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	put_unaligned_le16(MGMT_OP_SET_CONNECTABLE, &ev->opcode);
+
+	rp = (void *) skb_put(skb, sizeof(*rp));
+	put_unaligned_le16(cmd->index, &rp->index);
+	rp->connectable = cp->connectable;
+
+	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
+		kfree_skb(skb);
+
+	list_del(&cmd->list);
+
+	if (match->sk == NULL) {
+		match->sk = cmd->sk;
+		sock_hold(match->sk);
+	}
+
+	mgmt_pending_free(cmd);
+}
+
+int mgmt_connectable(u16 index, u8 connectable)
+{
+	struct mgmt_ev_connectable ev;
+	struct cmd_lookup match = { connectable, NULL };
+	int ret;
+
+	put_unaligned_le16(index, &ev.index);
+	ev.connectable = connectable;
+
+	mgmt_pending_foreach(MGMT_OP_SET_CONNECTABLE, index,
+						connectable_rsp, &match);
+
+	ret = mgmt_event(MGMT_EV_CONNECTABLE, &ev, sizeof(ev), match.sk);
+
+	if (match.sk)
+		sock_put(match.sk);
+
+	return ret;
+}
-- 
cgit v1.2.3


From 72a734ec1aca8cd2ef3fc85428c11bde662e149e Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 30 Dec 2010 00:38:22 +0200
Subject: Bluetooth: Unify mode related management messages to a single struct

The powered, connectable and discoverable messages all have the same
format. By using a single struct for all of them a lot of code can be
simplified and reused.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/mgmt.h |  39 ++----------
 net/bluetooth/mgmt.c         | 137 +++++++++----------------------------------
 2 files changed, 32 insertions(+), 144 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 008acf54147a..f61fd6779ee5 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -59,35 +59,16 @@ struct mgmt_rp_read_info {
 	__u16 hci_rev;
 } __packed;
 
-#define MGMT_OP_SET_POWERED		0x0005
-struct mgmt_cp_set_powered {
+struct mgmt_mode {
 	__le16 index;
-	__u8 powered;
-} __packed;
-struct mgmt_rp_set_powered {
-	__le16 index;
-	__u8 powered;
+	__u8 val;
 } __packed;
 
+#define MGMT_OP_SET_POWERED		0x0005
+
 #define MGMT_OP_SET_DISCOVERABLE	0x0006
-struct mgmt_cp_set_discoverable {
-	__le16 index;
-	__u8 discoverable;
-} __packed;
-struct mgmt_rp_set_discoverable {
-	__le16 index;
-	__u8 discoverable;
-} __packed;
 
 #define MGMT_OP_SET_CONNECTABLE		0x0007
-struct mgmt_cp_set_connectable {
-	__le16 index;
-	__u8 connectable;
-} __packed;
-struct mgmt_rp_set_connectable {
-	__le16 index;
-	__u8 connectable;
-} __packed;
 
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
@@ -118,19 +99,7 @@ struct mgmt_ev_index_removed {
 } __packed;
 
 #define MGMT_EV_POWERED			0x0006
-struct mgmt_ev_powered {
-	__le16 index;
-	__u8 powered;
-} __packed;
 
 #define MGMT_EV_DISCOVERABLE		0x0007
-struct mgmt_ev_discoverable {
-	__le16 index;
-	__u8 discoverable;
-} __packed;
 
 #define MGMT_EV_CONNECTABLE		0x0008
-struct mgmt_ev_connectable {
-	__le16 index;
-	__u8 connectable;
-} __packed;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index fc41cfc3f162..dbb1e5776644 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -322,7 +322,7 @@ static void mgmt_pending_remove(u16 opcode, int index)
 
 static int set_powered(struct sock *sk, unsigned char *data, u16 len)
 {
-	struct mgmt_cp_set_powered *cp;
+	struct mgmt_mode *cp;
 	struct hci_dev *hdev;
 	u16 dev_id;
 	int ret, up;
@@ -339,7 +339,7 @@ static int set_powered(struct sock *sk, unsigned char *data, u16 len)
 	hci_dev_lock_bh(hdev);
 
 	up = test_bit(HCI_UP, &hdev->flags);
-	if ((cp->powered && up) || (!cp->powered && !up)) {
+	if ((cp->val && up) || (!cp->val && !up)) {
 		ret = cmd_status(sk, MGMT_OP_SET_POWERED, EALREADY);
 		goto failed;
 	}
@@ -353,7 +353,7 @@ static int set_powered(struct sock *sk, unsigned char *data, u16 len)
 	if (ret < 0)
 		goto failed;
 
-	if (cp->powered)
+	if (cp->val)
 		queue_work(hdev->workqueue, &hdev->power_on);
 	else
 		queue_work(hdev->workqueue, &hdev->power_off);
@@ -368,7 +368,7 @@ failed:
 
 static int set_discoverable(struct sock *sk, unsigned char *data, u16 len)
 {
-	struct mgmt_cp_set_discoverable *cp;
+	struct mgmt_mode *cp;
 	struct hci_dev *hdev;
 	u16 dev_id;
 	u8 scan;
@@ -396,7 +396,7 @@ static int set_discoverable(struct sock *sk, unsigned char *data, u16 len)
 		goto failed;
 	}
 
-	if (cp->discoverable == test_bit(HCI_ISCAN, &hdev->flags) &&
+	if (cp->val == test_bit(HCI_ISCAN, &hdev->flags) &&
 					test_bit(HCI_PSCAN, &hdev->flags)) {
 		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, EALREADY);
 		goto failed;
@@ -408,7 +408,7 @@ static int set_discoverable(struct sock *sk, unsigned char *data, u16 len)
 
 	scan = SCAN_PAGE;
 
-	if (cp->discoverable)
+	if (cp->val)
 		scan |= SCAN_INQUIRY;
 
 	err = hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
@@ -424,7 +424,7 @@ failed:
 
 static int set_connectable(struct sock *sk, unsigned char *data, u16 len)
 {
-	struct mgmt_cp_set_connectable *cp;
+	struct mgmt_mode *cp;
 	struct hci_dev *hdev;
 	u16 dev_id;
 	u8 scan;
@@ -452,7 +452,7 @@ static int set_connectable(struct sock *sk, unsigned char *data, u16 len)
 		goto failed;
 	}
 
-	if (cp->connectable == test_bit(HCI_PSCAN, &hdev->flags)) {
+	if (cp->val == test_bit(HCI_PSCAN, &hdev->flags)) {
 		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, EALREADY);
 		goto failed;
 	}
@@ -461,7 +461,7 @@ static int set_connectable(struct sock *sk, unsigned char *data, u16 len)
 	if (err < 0)
 		goto failed;
 
-	if (cp->connectable)
+	if (cp->val)
 		scan = SCAN_PAGE;
 	else
 		scan = 0;
@@ -584,20 +584,20 @@ int mgmt_index_removed(u16 index)
 }
 
 struct cmd_lookup {
-	u8 value;
+	u8 val;
 	struct sock *sk;
 };
 
-static void power_rsp(struct pending_cmd *cmd, void *data)
+static void mode_rsp(struct pending_cmd *cmd, void *data)
 {
 	struct mgmt_hdr *hdr;
 	struct mgmt_ev_cmd_complete *ev;
-	struct mgmt_rp_set_powered *rp;
-	struct mgmt_cp_set_powered *cp = cmd->cmd;
+	struct mgmt_mode *rp;
+	struct mgmt_mode *cp = cmd->cmd;
 	struct sk_buff *skb;
 	struct cmd_lookup *match = data;
 
-	if (cp->powered != match->value)
+	if (cp->val != match->val)
 		return;
 
 	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
@@ -613,7 +613,7 @@ static void power_rsp(struct pending_cmd *cmd, void *data)
 
 	rp = (void *) skb_put(skb, sizeof(*rp));
 	put_unaligned_le16(cmd->index, &rp->index);
-	rp->powered = cp->powered;
+	rp->val = cp->val;
 
 	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
 		kfree_skb(skb);
@@ -630,14 +630,14 @@ static void power_rsp(struct pending_cmd *cmd, void *data)
 
 int mgmt_powered(u16 index, u8 powered)
 {
-	struct mgmt_ev_powered ev;
+	struct mgmt_mode ev;
 	struct cmd_lookup match = { powered, NULL };
 	int ret;
 
-	put_unaligned_le16(index, &ev.index);
-	ev.powered = powered;
+	mgmt_pending_foreach(MGMT_OP_SET_POWERED, index, mode_rsp, &match);
 
-	mgmt_pending_foreach(MGMT_OP_SET_POWERED, index, power_rsp, &match);
+	put_unaligned_le16(index, &ev.index);
+	ev.val = powered;
 
 	ret = mgmt_event(MGMT_EV_POWERED, &ev, sizeof(ev), match.sk);
 
@@ -647,57 +647,17 @@ int mgmt_powered(u16 index, u8 powered)
 	return ret;
 }
 
-static void discoverable_rsp(struct pending_cmd *cmd, void *data)
-{
-	struct mgmt_cp_set_discoverable *cp = cmd->cmd;
-	struct cmd_lookup *match = data;
-	struct sk_buff *skb;
-	struct mgmt_hdr *hdr;
-	struct mgmt_ev_cmd_complete *ev;
-	struct mgmt_rp_set_discoverable *rp;
-
-	if (cp->discoverable != match->value)
-		return;
-
-	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
-	if (!skb)
-		return;
-
-	hdr = (void *) skb_put(skb, sizeof(*hdr));
-	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
-	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(*rp));
-
-	ev = (void *) skb_put(skb, sizeof(*ev));
-	put_unaligned_le16(MGMT_OP_SET_DISCOVERABLE, &ev->opcode);
-
-	rp = (void *) skb_put(skb, sizeof(*rp));
-	put_unaligned_le16(cmd->index, &rp->index);
-	rp->discoverable = cp->discoverable;
-
-	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
-		kfree_skb(skb);
-
-	list_del(&cmd->list);
-
-	if (match->sk == NULL) {
-		match->sk = cmd->sk;
-		sock_hold(match->sk);
-	}
-
-	mgmt_pending_free(cmd);
-}
-
 int mgmt_discoverable(u16 index, u8 discoverable)
 {
-	struct mgmt_ev_discoverable ev;
+	struct mgmt_mode ev;
 	struct cmd_lookup match = { discoverable, NULL };
 	int ret;
 
-	put_unaligned_le16(index, &ev.index);
-	ev.discoverable = discoverable;
-
 	mgmt_pending_foreach(MGMT_OP_SET_DISCOVERABLE, index,
-						discoverable_rsp, &match);
+							mode_rsp, &match);
+
+	put_unaligned_le16(index, &ev.index);
+	ev.val = discoverable;
 
 	ret = mgmt_event(MGMT_EV_DISCOVERABLE, &ev, sizeof(ev), match.sk);
 
@@ -707,57 +667,16 @@ int mgmt_discoverable(u16 index, u8 discoverable)
 	return ret;
 }
 
-static void connectable_rsp(struct pending_cmd *cmd, void *data)
-{
-	struct mgmt_cp_set_connectable *cp = cmd->cmd;
-	struct cmd_lookup *match = data;
-	struct sk_buff *skb;
-	struct mgmt_hdr *hdr;
-	struct mgmt_ev_cmd_complete *ev;
-	struct mgmt_rp_set_connectable *rp;
-
-	if (cp->connectable != match->value)
-		return;
-
-	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
-	if (!skb)
-		return;
-
-	hdr = (void *) skb_put(skb, sizeof(*hdr));
-	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
-	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(*rp));
-
-	ev = (void *) skb_put(skb, sizeof(*ev));
-	put_unaligned_le16(MGMT_OP_SET_CONNECTABLE, &ev->opcode);
-
-	rp = (void *) skb_put(skb, sizeof(*rp));
-	put_unaligned_le16(cmd->index, &rp->index);
-	rp->connectable = cp->connectable;
-
-	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
-		kfree_skb(skb);
-
-	list_del(&cmd->list);
-
-	if (match->sk == NULL) {
-		match->sk = cmd->sk;
-		sock_hold(match->sk);
-	}
-
-	mgmt_pending_free(cmd);
-}
-
 int mgmt_connectable(u16 index, u8 connectable)
 {
-	struct mgmt_ev_connectable ev;
+	struct mgmt_mode ev;
 	struct cmd_lookup match = { connectable, NULL };
 	int ret;
 
-	put_unaligned_le16(index, &ev.index);
-	ev.connectable = connectable;
+	mgmt_pending_foreach(MGMT_OP_SET_CONNECTABLE, index, mode_rsp, &match);
 
-	mgmt_pending_foreach(MGMT_OP_SET_CONNECTABLE, index,
-						connectable_rsp, &match);
+	put_unaligned_le16(index, &ev.index);
+	ev.val = connectable;
 
 	ret = mgmt_event(MGMT_EV_CONNECTABLE, &ev, sizeof(ev), match.sk);
 
-- 
cgit v1.2.3


From ebc99feba7378349e2bfae7018af062767382f6c Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Tue, 4 Jan 2011 11:54:26 +0200
Subject: Bluetooth: Add flag to track managment controlled adapters

This patch adds a HCI_MGMT flag to track adapters which are under the
control of the management interface. This is needed to make sure that
new kernels will work with old user space versions. I.e. behaviour which
could break old user space versions (but is needed by the management
interface) should not be exhibited when the HCI_MGMT flag is not set.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h | 1 +
 net/bluetooth/mgmt.c        | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 51c9df16e764..469f8fdb2f5d 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -79,6 +79,7 @@ enum {
 
 	HCI_SETUP,
 	HCI_AUTO_OFF,
+	HCI_MGMT,
 };
 
 /* HCI ioctl defines */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index dbb1e5776644..5f871b385a27 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -142,6 +142,8 @@ static int read_index_list(struct sock *sk)
 
 		hci_del_off_timer(d);
 
+		set_bit(HCI_MGMT, &d->flags);
+
 		if (test_bit(HCI_SETUP, &d->flags))
 			continue;
 
@@ -200,6 +202,8 @@ static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
 
 	hci_dev_lock_bh(hdev);
 
+	set_bit(HCI_MGMT, &hdev->flags);
+
 	put_unaligned_le16(hdev->id, &rp->index);
 	rp->type = hdev->dev_type;
 
-- 
cgit v1.2.3


From c542a06c29acbf4ea0024884a198065a10613147 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Wed, 26 Jan 2011 13:11:03 +0200
Subject: Bluetooth: Implement set_pairable managment command

This patch implements a new set_pairable management command to control
the pairable state of local adapters. The state is represented using a
new HCI_PAIRABLE flag in the hci_dev struct.

For backwards compatibility with older user space versions the
HCI_PAIRABLE flag gets automatically set when the existence of an
adapter is reported to user space through legacy methods and the
HCI_MGMT flag is not set.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h  |  1 +
 include/net/bluetooth/mgmt.h |  4 ++
 net/bluetooth/hci_core.c     | 10 +++++
 net/bluetooth/mgmt.c         | 88 ++++++++++++++++++++++++++++++++------------
 4 files changed, 80 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 469f8fdb2f5d..f0c25b5ba4b2 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -80,6 +80,7 @@ enum {
 	HCI_SETUP,
 	HCI_AUTO_OFF,
 	HCI_MGMT,
+	HCI_PAIRABLE,
 };
 
 /* HCI ioctl defines */
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index f61fd6779ee5..a554802291ed 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -70,6 +70,8 @@ struct mgmt_mode {
 
 #define MGMT_OP_SET_CONNECTABLE		0x0007
 
+#define MGMT_OP_SET_PAIRABLE		0x0008
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
@@ -103,3 +105,5 @@ struct mgmt_ev_index_removed {
 #define MGMT_EV_DISCOVERABLE		0x0007
 
 #define MGMT_EV_CONNECTABLE		0x0008
+
+#define MGMT_EV_PAIRABLE		0x0009
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index dfc4ef90deca..13eb5a8beb84 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -799,10 +799,17 @@ int hci_get_dev_list(void __user *arg)
 	read_lock_bh(&hci_dev_list_lock);
 	list_for_each(p, &hci_dev_list) {
 		struct hci_dev *hdev;
+
 		hdev = list_entry(p, struct hci_dev, list);
+
 		hci_del_off_timer(hdev);
+
+		if (!test_bit(HCI_MGMT, &hdev->flags))
+			set_bit(HCI_PAIRABLE, &hdev->flags);
+
 		(dr + n)->dev_id  = hdev->id;
 		(dr + n)->dev_opt = hdev->flags;
+
 		if (++n >= dev_num)
 			break;
 	}
@@ -832,6 +839,9 @@ int hci_get_dev_info(void __user *arg)
 
 	hci_del_off_timer(hdev);
 
+	if (!test_bit(HCI_MGMT, &hdev->flags))
+		set_bit(HCI_PAIRABLE, &hdev->flags);
+
 	strcpy(di.name, hdev->name);
 	di.bdaddr   = hdev->bdaddr;
 	di.type     = (hdev->bus & 0x0f) | (hdev->dev_type << 4);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 13872ae219c9..d10735076a25 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -481,6 +481,29 @@ failed:
 	return err;
 }
 
+static int mgmt_event(u16 event, void *data, u16 data_len, struct sock *skip_sk)
+{
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+
+	skb = alloc_skb(sizeof(*hdr) + data_len, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	bt_cb(skb)->channel = HCI_CHANNEL_CONTROL;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(event);
+	hdr->len = cpu_to_le16(data_len);
+
+	memcpy(skb_put(skb, data_len), data, data_len);
+
+	hci_send_to_sock(NULL, skb, skip_sk);
+	kfree_skb(skb);
+
+	return 0;
+}
+
 static int send_mode_rsp(struct sock *sk, u16 opcode, u16 index, u8 val)
 {
 	struct mgmt_hdr *hdr;
@@ -509,6 +532,45 @@ static int send_mode_rsp(struct sock *sk, u16 opcode, u16 index, u8 val)
 	return 0;
 }
 
+static int set_pairable(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct mgmt_mode *cp, ev;
+	struct hci_dev *hdev;
+	u16 dev_id;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_PAIRABLE, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (cp->val)
+		set_bit(HCI_PAIRABLE, &hdev->flags);
+	else
+		clear_bit(HCI_PAIRABLE, &hdev->flags);
+
+	err = send_mode_rsp(sk, MGMT_OP_SET_PAIRABLE, dev_id, cp->val);
+	if (err < 0)
+		goto failed;
+
+	put_unaligned_le16(dev_id, &ev.index);
+	ev.val = cp->val;
+
+	err = mgmt_event(MGMT_EV_PAIRABLE, &ev, sizeof(ev), sk);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -558,6 +620,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_SET_CONNECTABLE:
 		err = set_connectable(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_SET_PAIRABLE:
+		err = set_pairable(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -574,29 +639,6 @@ done:
 	return err;
 }
 
-static int mgmt_event(u16 event, void *data, u16 data_len, struct sock *skip_sk)
-{
-	struct sk_buff *skb;
-	struct mgmt_hdr *hdr;
-
-	skb = alloc_skb(sizeof(*hdr) + data_len, GFP_ATOMIC);
-	if (!skb)
-		return -ENOMEM;
-
-	bt_cb(skb)->channel = HCI_CHANNEL_CONTROL;
-
-	hdr = (void *) skb_put(skb, sizeof(*hdr));
-	hdr->opcode = cpu_to_le16(event);
-	hdr->len = cpu_to_le16(data_len);
-
-	memcpy(skb_put(skb, data_len), data, data_len);
-
-	hci_send_to_sock(NULL, skb, skip_sk);
-	kfree_skb(skb);
-
-	return 0;
-}
-
 int mgmt_index_added(u16 index)
 {
 	struct mgmt_ev_index_added ev;
-- 
cgit v1.2.3


From 2aeb9a1ae0e34fb46cb78b82f827a6a54ab65111 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Tue, 4 Jan 2011 12:08:51 +0200
Subject: Bluetooth: Implement UUID handling through the management interface

This patch adds methods to the management interface for userspace to
notify the kernel of which services have been registered for specific
adapters. This information is needed for setting the appropriate Class
of Device value as well as the Extended Inquiry Response value. This
patch doesn't actually implement setting of these values but just
provides the storage of the UUIDs so the needed functionality can be
built on top of it.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  10 ++++
 include/net/bluetooth/mgmt.h     |  12 ++++
 net/bluetooth/hci_core.c         |  19 +++++++
 net/bluetooth/mgmt.c             | 120 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 161 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ba3dbe3188ed..8ee0b8bac77c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -66,6 +66,12 @@ struct bdaddr_list {
 	struct list_head list;
 	bdaddr_t bdaddr;
 };
+
+struct bt_uuid {
+	struct list_head list;
+	u8 uuid[16];
+};
+
 #define NUM_REASSEMBLY 4
 struct hci_dev {
 	struct list_head list;
@@ -139,6 +145,8 @@ struct hci_dev {
 	struct hci_conn_hash	conn_hash;
 	struct list_head	blacklist;
 
+	struct list_head	uuids;
+
 	struct hci_dev_stats	stat;
 
 	struct sk_buff_head	driver_init;
@@ -441,6 +449,8 @@ int hci_inquiry(void __user *arg);
 struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr);
 int hci_blacklist_clear(struct hci_dev *hdev);
 
+int hci_uuids_clear(struct hci_dev *hdev);
+
 void hci_del_off_timer(struct hci_dev *hdev);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index a554802291ed..c118ad3af332 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -72,6 +72,18 @@ struct mgmt_mode {
 
 #define MGMT_OP_SET_PAIRABLE		0x0008
 
+#define MGMT_OP_ADD_UUID		0x0009
+struct mgmt_cp_add_uuid {
+	__le16 index;
+	__u8 uuid[16];
+} __packed;
+
+#define MGMT_OP_REMOVE_UUID		0x000A
+struct mgmt_cp_remove_uuid {
+	__le16 index;
+	__u8 uuid[16];
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 13eb5a8beb84..b99248d4a5b2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -955,6 +955,22 @@ void hci_del_off_timer(struct hci_dev *hdev)
 	del_timer(&hdev->off_timer);
 }
 
+int hci_uuids_clear(struct hci_dev *hdev)
+{
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &hdev->uuids) {
+		struct bt_uuid *uuid;
+
+		uuid = list_entry(p, struct bt_uuid, list);
+
+		list_del(p);
+		kfree(uuid);
+	}
+
+	return 0;
+}
+
 /* Register HCI device */
 int hci_register_dev(struct hci_dev *hdev)
 {
@@ -1012,6 +1028,8 @@ int hci_register_dev(struct hci_dev *hdev)
 
 	INIT_LIST_HEAD(&hdev->blacklist);
 
+	INIT_LIST_HEAD(&hdev->uuids);
+
 	INIT_WORK(&hdev->power_on, hci_power_on);
 	INIT_WORK(&hdev->power_off, hci_power_off);
 	setup_timer(&hdev->off_timer, hci_auto_off, (unsigned long) hdev);
@@ -1087,6 +1105,7 @@ int hci_unregister_dev(struct hci_dev *hdev)
 
 	hci_dev_lock_bh(hdev);
 	hci_blacklist_clear(hdev);
+	hci_uuids_clear(hdev);
 	hci_dev_unlock_bh(hdev);
 
 	__hci_dev_put(hdev);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d10735076a25..0854c2f1073c 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -571,6 +571,120 @@ failed:
 	return err;
 }
 
+static int uuid_rsp(struct sock *sk, u16 opcode, u16 index)
+{
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_complete *ev;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(index), GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(index));
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	put_unaligned_le16(opcode, &ev->opcode);
+
+	put_unaligned_le16(index, skb_put(skb, sizeof(index)));
+
+	if (sock_queue_rcv_skb(sk, skb) < 0)
+		kfree_skb(skb);
+
+	return 0;
+}
+
+static int add_uuid(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct mgmt_cp_add_uuid *cp;
+	struct hci_dev *hdev;
+	struct bt_uuid *uuid;
+	u16 dev_id;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_ADD_UUID, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	uuid = kmalloc(sizeof(*uuid), GFP_ATOMIC);
+	if (!uuid) {
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	memcpy(uuid->uuid, cp->uuid, 16);
+
+	list_add(&uuid->list, &hdev->uuids);
+
+	err = uuid_rsp(sk, MGMT_OP_ADD_UUID, dev_id);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
+static int remove_uuid(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct list_head *p, *n;
+	struct mgmt_cp_add_uuid *cp;
+	struct hci_dev *hdev;
+	u8 bt_uuid_any[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+	u16 dev_id;
+	int err, found;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_REMOVE_UUID, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (memcmp(cp->uuid, bt_uuid_any, 16) == 0) {
+		err = hci_uuids_clear(hdev);
+		goto unlock;
+	}
+
+	found = 0;
+
+	list_for_each_safe(p, n, &hdev->uuids) {
+		struct bt_uuid *match = list_entry(p, struct bt_uuid, list);
+
+		if (memcmp(match->uuid, cp->uuid, 16) != 0)
+			continue;
+
+		list_del(&match->list);
+		found++;
+	}
+
+	if (found == 0) {
+		err = cmd_status(sk, MGMT_OP_REMOVE_UUID, ENOENT);
+		goto unlock;
+	}
+
+	err = uuid_rsp(sk, MGMT_OP_REMOVE_UUID, dev_id);
+
+unlock:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -623,6 +737,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_SET_PAIRABLE:
 		err = set_pairable(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_ADD_UUID:
+		err = add_uuid(sk, buf + sizeof(*hdr), len);
+		break;
+	case MGMT_OP_REMOVE_UUID:
+		err = remove_uuid(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
-- 
cgit v1.2.3


From 03b555e119de8288a16e086e1fbd223d9b429d3d Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Tue, 4 Jan 2011 15:40:05 +0200
Subject: Bluetooth: Reject pairing requests when in non-pairable mode

This patch adds the necessary logic to act accordingly when the
HCI_PAIRABLE flag is not set. In that case PIN code replies as well as
Secure Simple Pairing requests without a NoBonding requirement need to
be rejected.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      | 14 ++++++++++
 include/net/bluetooth/hci_core.h |  4 +++
 net/bluetooth/hci_event.c        | 55 ++++++++++++++++++++++++++++++++++++++--
 3 files changed, 71 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index f0c25b5ba4b2..65cab137e19f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -384,6 +384,12 @@ struct hci_cp_reject_sync_conn_req {
 	__u8     reason;
 } __packed;
 
+#define HCI_OP_IO_CAPABILITY_NEG_REPLY	0x0434
+struct hci_cp_io_capability_neg_reply {
+	bdaddr_t bdaddr;
+	__u8     reason;
+} __packed;
+
 #define HCI_OP_SNIFF_MODE		0x0803
 struct hci_cp_sniff_mode {
 	__le16   handle;
@@ -840,6 +846,14 @@ struct hci_ev_io_capa_request {
 	bdaddr_t bdaddr;
 } __packed;
 
+#define HCI_EV_IO_CAPA_REPLY		0x32
+struct hci_ev_io_capa_reply {
+	bdaddr_t bdaddr;
+	__u8     capability;
+	__u8     oob_data;
+	__u8     authentication;
+} __packed;
+
 #define HCI_EV_SIMPLE_PAIR_COMPLETE	0x36
 struct hci_ev_simple_pair_complete {
 	__u8     status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 8ee0b8bac77c..dc8084a139ed 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -201,6 +201,10 @@ struct hci_conn {
 	__u16            disc_timeout;
 	unsigned long	 pend;
 
+	__u8		remote_cap;
+	__u8		remote_oob;
+	__u8		remote_auth;
+
 	unsigned int	 sent;
 
 	struct sk_buff_head data_q;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a8a38f17ef78..cf3014ae00e4 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1595,6 +1595,10 @@ static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff
 		hci_conn_put(conn);
 	}
 
+	if (!test_bit(HCI_PAIRABLE, &hdev->flags))
+		hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY,
+					sizeof(ev->bdaddr), &ev->bdaddr);
+
 	hci_dev_unlock(hdev);
 }
 
@@ -1885,9 +1889,52 @@ static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
-	if (conn)
-		hci_conn_hold(conn);
+	if (!conn)
+		goto unlock;
+
+	hci_conn_hold(conn);
+
+	if (!test_bit(HCI_MGMT, &hdev->flags))
+		goto unlock;
+
+	if (test_bit(HCI_PAIRABLE, &hdev->flags) ||
+			(conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) {
+		/* FIXME: Do IO capa response based on information
+		 * provided through the management interface */
+	} else {
+		struct hci_cp_io_capability_neg_reply cp;
+
+		bacpy(&cp.bdaddr, &ev->bdaddr);
+		cp.reason = 0x16; /* Pairing not allowed */
 
+		hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_NEG_REPLY,
+							sizeof(cp), &cp);
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static inline void hci_io_capa_reply_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_io_capa_reply *ev = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s", hdev->name);
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
+	if (!conn)
+		goto unlock;
+
+	hci_conn_hold(conn);
+
+	conn->remote_cap = ev->capability;
+	conn->remote_oob = ev->oob_data;
+	conn->remote_auth = ev->authentication;
+
+unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -2051,6 +2098,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_io_capa_request_evt(hdev, skb);
 		break;
 
+	case HCI_EV_IO_CAPA_REPLY:
+		hci_io_capa_reply_evt(hdev, skb);
+		break;
+
 	case HCI_EV_SIMPLE_PAIR_COMPLETE:
 		hci_simple_pair_complete_evt(hdev, skb);
 		break;
-- 
cgit v1.2.3


From a5040efa2017f3e4f1b4d5f40fd989567f3994c1 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Mon, 10 Jan 2011 13:28:59 +0200
Subject: Bluetooth: Add special handling with __hci_request and HCI_INIT

To support a more dynamic HCI initialization sequence the __hci_request
behavior requires some more changes. Particularly, the init sequence
should be able to have conditionals in it (sending some HCI commands
depending on the outcome of a previous command) instead of being a fixed
list as it is right now.

The reasons for these additional requirements are the moving all
previously user space driven initialization commands to the kernel side
as well as the support the Low Energy controllers.

To fulfull these requirements the init sequence is made the only special
case for multi-command requests and req_last_cmd is renamed to
init_last_cmd. The hci_send_cmd function is changed to update
init_last_cmd as long as the HCI_INIT flag is set.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  3 ++-
 net/bluetooth/hci_core.c         | 17 +++++++++--------
 2 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index dc8084a139ed..0dbdcc5f44e4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -139,7 +139,8 @@ struct hci_dev {
 	wait_queue_head_t	req_wait_q;
 	__u32			req_status;
 	__u32			req_result;
-	__u16			req_last_cmd;
+
+	__u16			init_last_cmd;
 
 	struct inquiry_cache	inq_cache;
 	struct hci_conn_hash	conn_hash;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b99248d4a5b2..183ce81f7a5c 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -97,11 +97,10 @@ void hci_req_complete(struct hci_dev *hdev, __u16 cmd, int result)
 {
 	BT_DBG("%s command 0x%04x result 0x%2.2x", hdev->name, cmd, result);
 
-	/* If the request has set req_last_cmd (typical for multi-HCI
-	 * command requests) check if the completed command matches
-	 * this, and if not just return. Single HCI command requests
-	 * typically leave req_last_cmd as 0 */
-	if (hdev->req_last_cmd && cmd != hdev->req_last_cmd)
+	/* If this is the init phase check if the completed command matches
+	 * the last init command, and if not just return.
+	 */
+	if (test_bit(HCI_INIT, &hdev->flags) && hdev->init_last_cmd != cmd)
 		return;
 
 	if (hdev->req_status == HCI_REQ_PEND) {
@@ -158,7 +157,7 @@ static int __hci_request(struct hci_dev *hdev, void (*req)(struct hci_dev *hdev,
 		break;
 	}
 
-	hdev->req_last_cmd = hdev->req_status = hdev->req_result = 0;
+	hdev->req_status = hdev->req_result = 0;
 
 	BT_DBG("%s end: err %d", hdev->name, err);
 
@@ -261,8 +260,6 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt)
 	/* Connection accept timeout ~20 secs */
 	param = cpu_to_le16(0x7d00);
 	hci_send_cmd(hdev, HCI_OP_WRITE_CA_TIMEOUT, 2, &param);
-
-	hdev->req_last_cmd = HCI_OP_WRITE_CA_TIMEOUT;
 }
 
 static void hci_scan_req(struct hci_dev *hdev, unsigned long opt)
@@ -523,6 +520,7 @@ int hci_dev_open(__u16 dev)
 	if (!test_bit(HCI_RAW, &hdev->flags)) {
 		atomic_set(&hdev->cmd_cnt, 1);
 		set_bit(HCI_INIT, &hdev->flags);
+		hdev->init_last_cmd = 0;
 
 		//__hci_request(hdev, hci_reset_req, 0, HZ);
 		ret = __hci_request(hdev, hci_init_req, 0,
@@ -1442,6 +1440,9 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param)
 	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
 	skb->dev = (void *) hdev;
 
+	if (test_bit(HCI_INIT, &hdev->flags))
+		hdev->init_last_cmd = opcode;
+
 	skb_queue_tail(&hdev->cmd_q, skb);
 	tasklet_schedule(&hdev->cmd_task);
 
-- 
cgit v1.2.3


From b0916ea0d9e6ea3ed46bb7a61c13a2b357b0248b Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Mon, 10 Jan 2011 13:44:55 +0200
Subject: Bluetooth: Add controller side link key clearing to hci_init_req

The controller may have link keys in its own memory and these keys could
be used for secure connections. However, since the interface to access
these keys doesn't provide information about the key types (which would
be needed to infer the level of security each key provides) using these
keys is rather useless. Therefore, simply clear the controller side list
in the initialization procedure.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h |  6 ++++++
 net/bluetooth/hci_core.c    |  5 +++++
 net/bluetooth/hci_event.c   | 14 ++++++++++++++
 3 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 65cab137e19f..4e2f008d32e1 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -487,6 +487,12 @@ struct hci_cp_set_event_flt {
 #define HCI_CONN_SETUP_AUTO_OFF	0x01
 #define HCI_CONN_SETUP_AUTO_ON	0x02
 
+#define HCI_OP_DELETE_STORED_LINK_KEY	0x0c12
+struct hci_cp_delete_stored_link_key {
+	bdaddr_t bdaddr;
+	__u8     delete_all;
+} __packed;
+
 #define HCI_OP_WRITE_LOCAL_NAME		0x0c13
 struct hci_cp_write_local_name {
 	__u8     name[248];
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 183ce81f7a5c..cedb8a966df6 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -190,6 +190,7 @@ static void hci_reset_req(struct hci_dev *hdev, unsigned long opt)
 
 static void hci_init_req(struct hci_dev *hdev, unsigned long opt)
 {
+	struct hci_cp_delete_stored_link_key cp;
 	struct sk_buff *skb;
 	__le16 param;
 	__u8 flt_type;
@@ -260,6 +261,10 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt)
 	/* Connection accept timeout ~20 secs */
 	param = cpu_to_le16(0x7d00);
 	hci_send_cmd(hdev, HCI_OP_WRITE_CA_TIMEOUT, 2, &param);
+
+	bacpy(&cp.bdaddr, BDADDR_ANY);
+	cp.delete_all = 1;
+	hci_send_cmd(hdev, HCI_OP_DELETE_STORED_LINK_KEY, sizeof(cp), &cp);
 }
 
 static void hci_scan_req(struct hci_dev *hdev, unsigned long opt)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index cf3014ae00e4..49b387cdcc38 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -557,6 +557,16 @@ static void hci_cc_write_ca_timeout(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_req_complete(hdev, HCI_OP_WRITE_CA_TIMEOUT, status);
 }
 
+static void hci_cc_delete_stored_link_key(struct hci_dev *hdev,
+							struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%x", hdev->name, status);
+
+	hci_req_complete(hdev, HCI_OP_DELETE_STORED_LINK_KEY, status);
+}
+
 static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%x", hdev->name, status);
@@ -1402,6 +1412,10 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk
 		hci_cc_write_ca_timeout(hdev, skb);
 		break;
 
+	case HCI_OP_DELETE_STORED_LINK_KEY:
+		hci_cc_delete_stored_link_key(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
-- 
cgit v1.2.3


From d5859e22cd40b73164b3e5d8d5d796f96edcc6af Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Tue, 25 Jan 2011 01:19:58 +0200
Subject: Bluetooth: Implement a more complete adapter initialization sequence

Using the managment interface means that user space doesn't need to do
any HCI command sending at all. This patch moves the remaining
initialization commands from user space to the kernel side. The patch
makes use of the new feature of __hci_request which allows the request
to be dynamically modified while it is ongoing (something that is needed
to react appropriately to the local features and the version of the
adapter).

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |  11 +++
 include/net/bluetooth/hci_core.h |   2 +
 net/bluetooth/hci_event.c        | 194 ++++++++++++++++++++++++++++++++++++++-
 3 files changed, 206 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4e2f008d32e1..99ac3516fe9d 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -189,19 +189,26 @@ enum {
 #define LMP_PSCHEME	0x02
 #define LMP_PCONTROL	0x04
 
+#define LMP_RSSI_INQ	0x40
 #define LMP_ESCO	0x80
 
 #define LMP_EV4		0x01
 #define LMP_EV5		0x02
+#define LMP_LE		0x40
 
 #define LMP_SNIFF_SUBR	0x02
+#define LMP_PAUSE_ENC	0x04
 #define LMP_EDR_ESCO_2M	0x20
 #define LMP_EDR_ESCO_3M	0x40
 #define LMP_EDR_3S_ESCO	0x80
 
+#define LMP_EXT_INQ	0x01
 #define LMP_SIMPLE_PAIR	0x08
 #define LMP_NO_FLUSH	0x40
 
+#define LMP_LSTO	0x01
+#define LMP_INQ_TX_PWR	0x02
+
 /* Connection modes */
 #define HCI_CM_ACTIVE	0x0000
 #define HCI_CM_HOLD	0x0001
@@ -556,6 +563,8 @@ struct hci_cp_host_buffer_size {
 	__le16   sco_max_pkt;
 } __packed;
 
+#define HCI_OP_WRITE_INQUIRY_MODE	0x0c45
+
 #define HCI_OP_READ_SSP_MODE		0x0c55
 struct hci_rp_read_ssp_mode {
 	__u8     status;
@@ -567,6 +576,8 @@ struct hci_cp_write_ssp_mode {
 	__u8     mode;
 } __packed;
 
+#define HCI_OP_READ_INQ_RSP_TX_POWER	0x0c58
+
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
 struct hci_rp_read_local_version {
 	__u8     status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 0dbdcc5f44e4..71a3fbf1e785 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -91,7 +91,9 @@ struct hci_dev {
 	__u8		ssp_mode;
 	__u8		hci_ver;
 	__u16		hci_rev;
+	__u8		lmp_ver;
 	__u16		manufacturer;
+	__le16		lmp_subver;
 	__u16		voice_setting;
 
 	__u16		pkt_type;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 49b387cdcc38..c69ee44d5bd7 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -424,6 +424,115 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb)
 	hdev->ssp_mode = *((__u8 *) sent);
 }
 
+static u8 hci_get_inquiry_mode(struct hci_dev *hdev)
+{
+	if (hdev->features[6] & LMP_EXT_INQ)
+		return 2;
+
+	if (hdev->features[3] & LMP_RSSI_INQ)
+		return 1;
+
+	if (hdev->manufacturer == 11 && hdev->hci_rev == 0x00 &&
+						hdev->lmp_subver == 0x0757)
+		return 1;
+
+	if (hdev->manufacturer == 15) {
+		if (hdev->hci_rev == 0x03 && hdev->lmp_subver == 0x6963)
+			return 1;
+		if (hdev->hci_rev == 0x09 && hdev->lmp_subver == 0x6963)
+			return 1;
+		if (hdev->hci_rev == 0x00 && hdev->lmp_subver == 0x6965)
+			return 1;
+	}
+
+	if (hdev->manufacturer == 31 && hdev->hci_rev == 0x2005 &&
+						hdev->lmp_subver == 0x1805)
+		return 1;
+
+	return 0;
+}
+
+static void hci_setup_inquiry_mode(struct hci_dev *hdev)
+{
+	u8 mode;
+
+	mode = hci_get_inquiry_mode(hdev);
+
+	hci_send_cmd(hdev, HCI_OP_WRITE_INQUIRY_MODE, 1, &mode);
+}
+
+static void hci_setup_event_mask(struct hci_dev *hdev)
+{
+	/* The second byte is 0xff instead of 0x9f (two reserved bits
+	 * disabled) since a Broadcom 1.2 dongle doesn't respond to the
+	 * command otherwise */
+	u8 events[8] = { 0xff, 0xff, 0xfb, 0xff, 0x00, 0x00, 0x00, 0x00 };
+
+	/* Events for 1.2 and newer controllers */
+	if (hdev->lmp_ver > 1) {
+		events[4] |= 0x01; /* Flow Specification Complete */
+		events[4] |= 0x02; /* Inquiry Result with RSSI */
+		events[4] |= 0x04; /* Read Remote Extended Features Complete */
+		events[5] |= 0x08; /* Synchronous Connection Complete */
+		events[5] |= 0x10; /* Synchronous Connection Changed */
+	}
+
+	if (hdev->features[3] & LMP_RSSI_INQ)
+		events[4] |= 0x04; /* Inquiry Result with RSSI */
+
+	if (hdev->features[5] & LMP_SNIFF_SUBR)
+		events[5] |= 0x20; /* Sniff Subrating */
+
+	if (hdev->features[5] & LMP_PAUSE_ENC)
+		events[5] |= 0x80; /* Encryption Key Refresh Complete */
+
+	if (hdev->features[6] & LMP_EXT_INQ)
+		events[5] |= 0x40; /* Extended Inquiry Result */
+
+	if (hdev->features[6] & LMP_NO_FLUSH)
+		events[7] |= 0x01; /* Enhanced Flush Complete */
+
+	if (hdev->features[7] & LMP_LSTO)
+		events[6] |= 0x80; /* Link Supervision Timeout Changed */
+
+	if (hdev->features[6] & LMP_SIMPLE_PAIR) {
+		events[6] |= 0x01;	/* IO Capability Request */
+		events[6] |= 0x02;	/* IO Capability Response */
+		events[6] |= 0x04;	/* User Confirmation Request */
+		events[6] |= 0x08;	/* User Passkey Request */
+		events[6] |= 0x10;	/* Remote OOB Data Request */
+		events[6] |= 0x20;	/* Simple Pairing Complete */
+		events[7] |= 0x04;	/* User Passkey Notification */
+		events[7] |= 0x08;	/* Keypress Notification */
+		events[7] |= 0x10;	/* Remote Host Supported
+					 * Features Notification */
+	}
+
+	if (hdev->features[4] & LMP_LE)
+		events[7] |= 0x20;	/* LE Meta-Event */
+
+	hci_send_cmd(hdev, HCI_OP_SET_EVENT_MASK, sizeof(events), events);
+}
+
+static void hci_setup(struct hci_dev *hdev)
+{
+	hci_setup_event_mask(hdev);
+
+	if (hdev->lmp_ver > 1)
+		hci_send_cmd(hdev, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL);
+
+	if (hdev->features[6] & LMP_SIMPLE_PAIR) {
+		u8 mode = 0x01;
+		hci_send_cmd(hdev, HCI_OP_WRITE_SSP_MODE, sizeof(mode), &mode);
+	}
+
+	if (hdev->features[3] & LMP_RSSI_INQ)
+		hci_setup_inquiry_mode(hdev);
+
+	if (hdev->features[7] & LMP_INQ_TX_PWR)
+		hci_send_cmd(hdev, HCI_OP_READ_INQ_RSP_TX_POWER, 0, NULL);
+}
+
 static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_rp_read_local_version *rp = (void *) skb->data;
@@ -435,11 +544,34 @@ static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hdev->hci_ver = rp->hci_ver;
 	hdev->hci_rev = __le16_to_cpu(rp->hci_rev);
+	hdev->lmp_ver = rp->lmp_ver;
 	hdev->manufacturer = __le16_to_cpu(rp->manufacturer);
+	hdev->lmp_subver = __le16_to_cpu(rp->lmp_subver);
 
 	BT_DBG("%s manufacturer %d hci ver %d:%d", hdev->name,
 					hdev->manufacturer,
 					hdev->hci_ver, hdev->hci_rev);
+
+	if (test_bit(HCI_INIT, &hdev->flags))
+		hci_setup(hdev);
+}
+
+static void hci_setup_link_policy(struct hci_dev *hdev)
+{
+	u16 link_policy = 0;
+
+	if (hdev->features[0] & LMP_RSWITCH)
+		link_policy |= HCI_LP_RSWITCH;
+	if (hdev->features[0] & LMP_HOLD)
+		link_policy |= HCI_LP_HOLD;
+	if (hdev->features[0] & LMP_SNIFF)
+		link_policy |= HCI_LP_SNIFF;
+	if (hdev->features[1] & LMP_PARK)
+		link_policy |= HCI_LP_PARK;
+
+	link_policy = cpu_to_le16(link_policy);
+	hci_send_cmd(hdev, HCI_OP_WRITE_DEF_LINK_POLICY,
+					sizeof(link_policy), &link_policy);
 }
 
 static void hci_cc_read_local_commands(struct hci_dev *hdev, struct sk_buff *skb)
@@ -449,9 +581,15 @@ static void hci_cc_read_local_commands(struct hci_dev *hdev, struct sk_buff *skb
 	BT_DBG("%s status 0x%x", hdev->name, rp->status);
 
 	if (rp->status)
-		return;
+		goto done;
 
 	memcpy(hdev->commands, rp->commands, sizeof(hdev->commands));
+
+	if (test_bit(HCI_INIT, &hdev->flags) && (hdev->commands[5] & 0x10))
+		hci_setup_link_policy(hdev);
+
+done:
+	hci_req_complete(hdev, HCI_OP_READ_LOCAL_COMMANDS, rp->status);
 }
 
 static void hci_cc_read_local_features(struct hci_dev *hdev, struct sk_buff *skb)
@@ -567,6 +705,44 @@ static void hci_cc_delete_stored_link_key(struct hci_dev *hdev,
 	hci_req_complete(hdev, HCI_OP_DELETE_STORED_LINK_KEY, status);
 }
 
+static void hci_cc_set_event_mask(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%x", hdev->name, status);
+
+	hci_req_complete(hdev, HCI_OP_SET_EVENT_MASK, status);
+}
+
+static void hci_cc_write_inquiry_mode(struct hci_dev *hdev,
+							struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%x", hdev->name, status);
+
+	hci_req_complete(hdev, HCI_OP_WRITE_INQUIRY_MODE, status);
+}
+
+static void hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev,
+							struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%x", hdev->name, status);
+
+	hci_req_complete(hdev, HCI_OP_READ_INQ_RSP_TX_POWER, status);
+}
+
+static void hci_cc_set_event_flt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%x", hdev->name, status);
+
+	hci_req_complete(hdev, HCI_OP_SET_EVENT_FLT, status);
+}
+
 static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%x", hdev->name, status);
@@ -1416,6 +1592,22 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk
 		hci_cc_delete_stored_link_key(hdev, skb);
 		break;
 
+	case HCI_OP_SET_EVENT_MASK:
+		hci_cc_set_event_mask(hdev, skb);
+		break;
+
+	case HCI_OP_WRITE_INQUIRY_MODE:
+		hci_cc_write_inquiry_mode(hdev, skb);
+		break;
+
+	case HCI_OP_READ_INQ_RSP_TX_POWER:
+		hci_cc_read_inq_rsp_tx_power(hdev, skb);
+		break;
+
+	case HCI_OP_SET_EVENT_FLT:
+		hci_cc_set_event_flt(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
-- 
cgit v1.2.3


From 1aff6f09491f454d4cd9f405c783fa5e9d3168a0 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 13 Jan 2011 21:56:52 +0200
Subject: Bluetooth: Add class of device control to the management interface

This patch adds the possibility for user space to fully control the
Class of Device value of local adapters. To control the service class
bits each UUID that's added comes with a service class "hint" which acts
as a mask of bits that the UUID needs to have enabled. The
set_service_cache management command is used to make sure we queue up
all UUID changes as user space initializes its drivers and then send a
single HCI_Write_Class_of_Device command when initialization is
complete.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |   1 +
 include/net/bluetooth/hci_core.h |   3 +
 include/net/bluetooth/mgmt.h     |  14 +++++
 net/bluetooth/mgmt.c             | 121 ++++++++++++++++++++++++++++++++++++++-
 4 files changed, 136 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 99ac3516fe9d..9ce46cd00ba2 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -81,6 +81,7 @@ enum {
 	HCI_AUTO_OFF,
 	HCI_MGMT,
 	HCI_PAIRABLE,
+	HCI_SERVICE_CACHE,
 };
 
 /* HCI ioctl defines */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 71a3fbf1e785..e62da084e01d 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -70,6 +70,7 @@ struct bdaddr_list {
 struct bt_uuid {
 	struct list_head list;
 	u8 uuid[16];
+	u8 svc_hint;
 };
 
 #define NUM_REASSEMBLY 4
@@ -86,6 +87,8 @@ struct hci_dev {
 	bdaddr_t	bdaddr;
 	__u8		dev_name[248];
 	__u8		dev_class[3];
+	__u8		major_class;
+	__u8		minor_class;
 	__u8		features[8];
 	__u8		commands[64];
 	__u8		ssp_mode;
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index c118ad3af332..b092c4c014eb 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -76,6 +76,7 @@ struct mgmt_mode {
 struct mgmt_cp_add_uuid {
 	__le16 index;
 	__u8 uuid[16];
+	__u8 svc_hint;
 } __packed;
 
 #define MGMT_OP_REMOVE_UUID		0x000A
@@ -84,6 +85,19 @@ struct mgmt_cp_remove_uuid {
 	__u8 uuid[16];
 } __packed;
 
+#define MGMT_OP_SET_DEV_CLASS		0x000B
+struct mgmt_cp_set_dev_class {
+	__le16 index;
+	__u8 major;
+	__u8 minor;
+} __packed;
+
+#define MGMT_OP_SET_SERVICE_CACHE	0x000C
+struct mgmt_cp_set_service_cache {
+	__le16 index;
+	__u8 enable;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 0854c2f1073c..a08f4ce03182 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -571,7 +571,7 @@ failed:
 	return err;
 }
 
-static int uuid_rsp(struct sock *sk, u16 opcode, u16 index)
+static int index_rsp(struct sock *sk, u16 opcode, u16 index)
 {
 	struct mgmt_hdr *hdr;
 	struct mgmt_ev_cmd_complete *ev;
@@ -596,6 +596,39 @@ static int uuid_rsp(struct sock *sk, u16 opcode, u16 index)
 	return 0;
 }
 
+static u8 get_service_classes(struct hci_dev *hdev)
+{
+	struct list_head *p;
+	u8 val = 0;
+
+	list_for_each(p, &hdev->uuids) {
+		struct bt_uuid *uuid = list_entry(p, struct bt_uuid, list);
+
+		val |= uuid->svc_hint;
+	}
+
+	return val;
+}
+
+static int update_class(struct hci_dev *hdev)
+{
+	u8 cod[3];
+
+	BT_DBG("%s", hdev->name);
+
+	if (test_bit(HCI_SERVICE_CACHE, &hdev->flags))
+		return 0;
+
+	cod[0] = hdev->minor_class;
+	cod[1] = hdev->major_class;
+	cod[2] = get_service_classes(hdev);
+
+	if (memcmp(cod, hdev->dev_class, 3) == 0)
+		return 0;
+
+	return hci_send_cmd(hdev, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod);
+}
+
 static int add_uuid(struct sock *sk, unsigned char *data, u16 len)
 {
 	struct mgmt_cp_add_uuid *cp;
@@ -622,10 +655,15 @@ static int add_uuid(struct sock *sk, unsigned char *data, u16 len)
 	}
 
 	memcpy(uuid->uuid, cp->uuid, 16);
+	uuid->svc_hint = cp->svc_hint;
 
 	list_add(&uuid->list, &hdev->uuids);
 
-	err = uuid_rsp(sk, MGMT_OP_ADD_UUID, dev_id);
+	err = update_class(hdev);
+	if (err < 0)
+		goto failed;
+
+	err = index_rsp(sk, MGMT_OP_ADD_UUID, dev_id);
 
 failed:
 	hci_dev_unlock_bh(hdev);
@@ -676,7 +714,11 @@ static int remove_uuid(struct sock *sk, unsigned char *data, u16 len)
 		goto unlock;
 	}
 
-	err = uuid_rsp(sk, MGMT_OP_REMOVE_UUID, dev_id);
+	err = update_class(hdev);
+	if (err < 0)
+		goto unlock;
+
+	err = index_rsp(sk, MGMT_OP_REMOVE_UUID, dev_id);
 
 unlock:
 	hci_dev_unlock_bh(hdev);
@@ -685,6 +727,73 @@ unlock:
 	return err;
 }
 
+static int set_dev_class(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_set_dev_class *cp;
+	u16 dev_id;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	BT_DBG("request for hci%u", dev_id);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_DEV_CLASS, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	hdev->major_class = cp->major;
+	hdev->minor_class = cp->minor;
+
+	err = update_class(hdev);
+
+	if (err == 0)
+		err = index_rsp(sk, MGMT_OP_SET_DEV_CLASS, dev_id);
+
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
+static int set_service_cache(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_set_service_cache *cp;
+	u16 dev_id;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_SERVICE_CACHE, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	BT_DBG("hci%u enable %d", dev_id, cp->enable);
+
+	if (cp->enable) {
+		set_bit(HCI_SERVICE_CACHE, &hdev->flags);
+		err = 0;
+	} else {
+		clear_bit(HCI_SERVICE_CACHE, &hdev->flags);
+		err = update_class(hdev);
+	}
+
+	if (err == 0)
+		err = index_rsp(sk, MGMT_OP_SET_SERVICE_CACHE, dev_id);
+
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -743,6 +852,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_REMOVE_UUID:
 		err = remove_uuid(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_SET_DEV_CLASS:
+		err = set_dev_class(sk, buf + sizeof(*hdr), len);
+		break;
+	case MGMT_OP_SET_SERVICE_CACHE:
+		err = set_service_cache(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
-- 
cgit v1.2.3


From 55ed8ca10f3530de8edbbf138acb50992bf5005b Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Mon, 17 Jan 2011 14:41:05 +0200
Subject: Bluetooth: Implement link key handling for the management interface

This patch adds a management commands to feed the kernel with all stored
link keys as well as remove specific ones or all of them. Once the
load_keys command has been called the kernel takes over link key
replies. A new_key event is also added to inform userspace of newly
created link keys that should be stored permanently.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |   2 +
 include/net/bluetooth/hci_core.h |  17 ++++++
 include/net/bluetooth/mgmt.h     |  29 ++++++++++
 net/bluetooth/hci_core.c         |  85 ++++++++++++++++++++++++++++
 net/bluetooth/hci_event.c        |  51 +++++++++++++++++
 net/bluetooth/mgmt.c             | 116 +++++++++++++++++++++++++++++++++++++++
 6 files changed, 300 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 9ce46cd00ba2..08fbf1253b83 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -82,6 +82,8 @@ enum {
 	HCI_MGMT,
 	HCI_PAIRABLE,
 	HCI_SERVICE_CACHE,
+	HCI_LINK_KEYS,
+	HCI_DEBUG_KEYS,
 };
 
 /* HCI ioctl defines */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index e62da084e01d..009fa63a9048 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -73,6 +73,14 @@ struct bt_uuid {
 	u8 svc_hint;
 };
 
+struct link_key {
+	struct list_head list;
+	bdaddr_t bdaddr;
+	u8 type;
+	u8 val[16];
+	u8 pin_len;
+};
+
 #define NUM_REASSEMBLY 4
 struct hci_dev {
 	struct list_head list;
@@ -153,6 +161,8 @@ struct hci_dev {
 
 	struct list_head	uuids;
 
+	struct list_head	link_keys;
+
 	struct hci_dev_stats	stat;
 
 	struct sk_buff_head	driver_init;
@@ -461,6 +471,12 @@ int hci_blacklist_clear(struct hci_dev *hdev);
 
 int hci_uuids_clear(struct hci_dev *hdev);
 
+int hci_link_keys_clear(struct hci_dev *hdev);
+struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr);
+int hci_add_link_key(struct hci_dev *hdev, int new_key, bdaddr_t *bdaddr,
+						u8 *key, u8 type, u8 pin_len);
+int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr);
+
 void hci_del_off_timer(struct hci_dev *hdev);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
@@ -697,6 +713,7 @@ int mgmt_index_removed(u16 index);
 int mgmt_powered(u16 index, u8 powered);
 int mgmt_discoverable(u16 index, u8 discoverable);
 int mgmt_connectable(u16 index, u8 connectable);
+int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index b092c4c014eb..56b500a2f68c 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -98,6 +98,28 @@ struct mgmt_cp_set_service_cache {
 	__u8 enable;
 } __packed;
 
+struct mgmt_key_info {
+	bdaddr_t bdaddr;
+	u8 type;
+	u8 val[16];
+	u8 pin_len;
+} __packed;
+
+#define MGMT_OP_LOAD_KEYS		0x000D
+struct mgmt_cp_load_keys {
+	__le16 index;
+	__u8 debug_keys;
+	__le16 key_count;
+	struct mgmt_key_info keys[0];
+} __packed;
+
+#define MGMT_OP_REMOVE_KEY		0x000E
+struct mgmt_cp_remove_key {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 disconnect;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
@@ -133,3 +155,10 @@ struct mgmt_ev_index_removed {
 #define MGMT_EV_CONNECTABLE		0x0008
 
 #define MGMT_EV_PAIRABLE		0x0009
+
+#define MGMT_EV_NEW_KEY			0x000A
+struct mgmt_ev_new_key {
+	__le16 index;
+	struct mgmt_key_info key;
+	__u8 old_key_type;
+} __packed;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 748f5a65caf4..8ca8cf147058 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -970,6 +970,88 @@ int hci_uuids_clear(struct hci_dev *hdev)
 	return 0;
 }
 
+int hci_link_keys_clear(struct hci_dev *hdev)
+{
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &hdev->link_keys) {
+		struct link_key *key;
+
+		key = list_entry(p, struct link_key, list);
+
+		list_del(p);
+		kfree(key);
+	}
+
+	return 0;
+}
+
+struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
+{
+	struct list_head *p;
+
+	list_for_each(p, &hdev->link_keys) {
+		struct link_key *k;
+
+		k = list_entry(p, struct link_key, list);
+
+		if (bacmp(bdaddr, &k->bdaddr) == 0)
+			return k;
+	}
+
+	return NULL;
+}
+
+int hci_add_link_key(struct hci_dev *hdev, int new_key, bdaddr_t *bdaddr,
+						u8 *val, u8 type, u8 pin_len)
+{
+	struct link_key *key, *old_key;
+	u8 old_key_type;
+
+	old_key = hci_find_link_key(hdev, bdaddr);
+	if (old_key) {
+		old_key_type = old_key->type;
+		key = old_key;
+	} else {
+		old_key_type = 0xff;
+		key = kzalloc(sizeof(*key), GFP_ATOMIC);
+		if (!key)
+			return -ENOMEM;
+		list_add(&key->list, &hdev->link_keys);
+	}
+
+	BT_DBG("%s key for %s type %u", hdev->name, batostr(bdaddr), type);
+
+	bacpy(&key->bdaddr, bdaddr);
+	memcpy(key->val, val, 16);
+	key->type = type;
+	key->pin_len = pin_len;
+
+	if (new_key)
+		mgmt_new_key(hdev->id, key, old_key_type);
+
+	if (type == 0x06)
+		key->type = old_key_type;
+
+	return 0;
+}
+
+int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
+{
+	struct link_key *key;
+
+	key = hci_find_link_key(hdev, bdaddr);
+	if (!key)
+		return -ENOENT;
+
+	BT_DBG("%s removing %s", hdev->name, batostr(bdaddr));
+
+	list_del(&key->list);
+	kfree(key);
+
+	return 0;
+}
+
 /* Register HCI device */
 int hci_register_dev(struct hci_dev *hdev)
 {
@@ -1029,6 +1111,8 @@ int hci_register_dev(struct hci_dev *hdev)
 
 	INIT_LIST_HEAD(&hdev->uuids);
 
+	INIT_LIST_HEAD(&hdev->link_keys);
+
 	INIT_WORK(&hdev->power_on, hci_power_on);
 	INIT_WORK(&hdev->power_off, hci_power_off);
 	setup_timer(&hdev->off_timer, hci_auto_off, (unsigned long) hdev);
@@ -1105,6 +1189,7 @@ int hci_unregister_dev(struct hci_dev *hdev)
 	hci_dev_lock_bh(hdev);
 	hci_blacklist_clear(hdev);
 	hci_uuids_clear(hdev);
+	hci_link_keys_clear(hdev);
 	hci_dev_unlock_bh(hdev);
 
 	__hci_dev_put(hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index c69ee44d5bd7..80ffd3a901fc 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1810,13 +1810,60 @@ static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff
 
 static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
+	struct hci_ev_link_key_req *ev = (void *) skb->data;
+	struct hci_cp_link_key_reply cp;
+	struct hci_conn *conn;
+	struct link_key *key;
+
 	BT_DBG("%s", hdev->name);
+
+	if (!test_bit(HCI_LINK_KEYS, &hdev->flags))
+		return;
+
+	hci_dev_lock(hdev);
+
+	key = hci_find_link_key(hdev, &ev->bdaddr);
+	if (!key) {
+		BT_DBG("%s link key not found for %s", hdev->name,
+							batostr(&ev->bdaddr));
+		goto not_found;
+	}
+
+	BT_DBG("%s found key type %u for %s", hdev->name, key->type,
+							batostr(&ev->bdaddr));
+
+	if (!test_bit(HCI_DEBUG_KEYS, &hdev->flags) && key->type == 0x03) {
+		BT_DBG("%s ignoring debug key", hdev->name);
+		goto not_found;
+	}
+
+	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
+
+	if (key->type == 0x04 && conn && conn->auth_type != 0xff &&
+						(conn->auth_type & 0x01)) {
+		BT_DBG("%s ignoring unauthenticated key", hdev->name);
+		goto not_found;
+	}
+
+	bacpy(&cp.bdaddr, &ev->bdaddr);
+	memcpy(cp.link_key, key->val, 16);
+
+	hci_send_cmd(hdev, HCI_OP_LINK_KEY_REPLY, sizeof(cp), &cp);
+
+	hci_dev_unlock(hdev);
+
+	return;
+
+not_found:
+	hci_send_cmd(hdev, HCI_OP_LINK_KEY_NEG_REPLY, 6, &ev->bdaddr);
+	hci_dev_unlock(hdev);
 }
 
 static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_link_key_notify *ev = (void *) skb->data;
 	struct hci_conn *conn;
+	u8 pin_len = 0;
 
 	BT_DBG("%s", hdev->name);
 
@@ -1829,6 +1876,10 @@ static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff
 		hci_conn_put(conn);
 	}
 
+	if (test_bit(HCI_LINK_KEYS, &hdev->flags))
+		hci_add_link_key(hdev, 1, &ev->bdaddr, ev->link_key,
+							ev->key_type, pin_len);
+
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index a08f4ce03182..bdb0e85f182e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -794,6 +794,99 @@ static int set_service_cache(struct sock *sk, unsigned char *data, u16 len)
 	return err;
 }
 
+static int load_keys(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_load_keys *cp;
+	u16 dev_id, key_count, expected_len;
+	int i;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+	key_count = get_unaligned_le16(&cp->key_count);
+
+	expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_key_info);
+	if (expected_len != len) {
+		BT_ERR("load_keys: expected %u bytes, got %u bytes",
+							len, expected_len);
+		return -EINVAL;
+	}
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_LOAD_KEYS, ENODEV);
+
+	BT_DBG("hci%u debug_keys %u key_count %u", dev_id, cp->debug_keys,
+								key_count);
+
+	hci_dev_lock_bh(hdev);
+
+	hci_link_keys_clear(hdev);
+
+	set_bit(HCI_LINK_KEYS, &hdev->flags);
+
+	if (cp->debug_keys)
+		set_bit(HCI_DEBUG_KEYS, &hdev->flags);
+	else
+		clear_bit(HCI_DEBUG_KEYS, &hdev->flags);
+
+	for (i = 0; i < key_count; i++) {
+		struct mgmt_key_info *key = &cp->keys[i];
+
+		hci_add_link_key(hdev, 0, &key->bdaddr, key->val, key->type,
+								key->pin_len);
+	}
+
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return 0;
+}
+
+static int remove_key(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_remove_key *cp;
+	struct hci_conn *conn;
+	u16 dev_id;
+	int err;
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_REMOVE_KEY, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	err = hci_remove_link_key(hdev, &cp->bdaddr);
+	if (err < 0) {
+		err = cmd_status(sk, MGMT_OP_REMOVE_KEY, -err);
+		goto unlock;
+	}
+
+	err = 0;
+
+	if (!test_bit(HCI_UP, &hdev->flags) || !cp->disconnect)
+		goto unlock;
+
+	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr);
+	if (conn) {
+		struct hci_cp_disconnect dc;
+
+		put_unaligned_le16(conn->handle, &dc.handle);
+		dc.reason = 0x13; /* Remote User Terminated Connection */
+		err = hci_send_cmd(hdev, HCI_OP_DISCONNECT, 0, NULL);
+	}
+
+unlock:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -858,6 +951,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_SET_SERVICE_CACHE:
 		err = set_service_cache(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_LOAD_KEYS:
+		err = load_keys(sk, buf + sizeof(*hdr), len);
+		break;
+	case MGMT_OP_REMOVE_KEY:
+		err = remove_key(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -974,3 +1073,20 @@ int mgmt_connectable(u16 index, u8 connectable)
 
 	return ret;
 }
+
+int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type)
+{
+	struct mgmt_ev_new_key ev;
+
+	memset(&ev, 0, sizeof(ev));
+
+	put_unaligned_le16(index, &ev.index);
+
+	bacpy(&ev.key.bdaddr, &key->bdaddr);
+	ev.key.type = key->type;
+	memcpy(ev.key.val, key->val, 16);
+	ev.key.pin_len = key->pin_len;
+	ev.old_key_type = old_key_type;
+
+	return mgmt_event(MGMT_EV_NEW_KEY, &ev, sizeof(ev), NULL);
+}
-- 
cgit v1.2.3


From f7520543ab40341edbc2aeee7fef68218be19a0a Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 20 Jan 2011 12:34:39 +0200
Subject: Bluetooth: Add connected/disconnected management events

This patch adds connected and disconnected managment events to track the
connection status to remote devices. The events map directly to
successful connection complete and disconnection complete HCI events for
ACL links.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  2 ++
 include/net/bluetooth/mgmt.h     | 12 ++++++++++++
 net/bluetooth/hci_event.c        | 16 +++++++++++-----
 net/bluetooth/mgmt.c             | 20 ++++++++++++++++++++
 4 files changed, 45 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 009fa63a9048..746f8dc8aad1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -714,6 +714,8 @@ int mgmt_powered(u16 index, u8 powered);
 int mgmt_discoverable(u16 index, u8 discoverable);
 int mgmt_connectable(u16 index, u8 connectable);
 int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type);
+int mgmt_connected(u16 index, bdaddr_t *bdaddr);
+int mgmt_disconnected(u16 index, bdaddr_t *bdaddr);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 56b500a2f68c..6719e9a36613 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -162,3 +162,15 @@ struct mgmt_ev_new_key {
 	struct mgmt_key_info key;
 	__u8 old_key_type;
 } __packed;
+
+#define MGMT_EV_CONNECTED		0x000B
+struct mgmt_ev_connected {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
+
+#define MGMT_EV_DISCONNECTED		0x000C
+struct mgmt_ev_disconnected {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 80ffd3a901fc..46ddb029912b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1137,6 +1137,7 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s
 			conn->state = BT_CONFIG;
 			hci_conn_hold(conn);
 			conn->disc_timeout = HCI_DISCONN_TIMEOUT;
+			mgmt_connected(hdev->id, &ev->bdaddr);
 		} else
 			conn->state = BT_CONNECTED;
 
@@ -1269,13 +1270,18 @@ static inline void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle));
-	if (conn) {
-		conn->state = BT_CLOSED;
+	if (!conn)
+		goto unlock;
 
-		hci_proto_disconn_cfm(conn, ev->reason);
-		hci_conn_del(conn);
-	}
+	conn->state = BT_CLOSED;
+
+	if (conn->type == ACL_LINK)
+		mgmt_disconnected(hdev->id, &conn->dst);
 
+	hci_proto_disconn_cfm(conn, ev->reason);
+	hci_conn_del(conn);
+
+unlock:
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index bdb0e85f182e..7cf1968157d8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1090,3 +1090,23 @@ int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type)
 
 	return mgmt_event(MGMT_EV_NEW_KEY, &ev, sizeof(ev), NULL);
 }
+
+int mgmt_connected(u16 index, bdaddr_t *bdaddr)
+{
+	struct mgmt_ev_connected ev;
+
+	put_unaligned_le16(index, &ev.index);
+	bacpy(&ev.bdaddr, bdaddr);
+
+	return mgmt_event(MGMT_EV_CONNECTED, &ev, sizeof(ev), NULL);
+}
+
+int mgmt_disconnected(u16 index, bdaddr_t *bdaddr)
+{
+	struct mgmt_ev_disconnected ev;
+
+	put_unaligned_le16(index, &ev.index);
+	bacpy(&ev.bdaddr, bdaddr);
+
+	return mgmt_event(MGMT_EV_DISCONNECTED, &ev, sizeof(ev), NULL);
+}
-- 
cgit v1.2.3


From 8962ee74be48df16027100f657b2b12e8ef3d34d Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Thu, 20 Jan 2011 12:40:27 +0200
Subject: Bluetooth: Add disconnect managment command

This patch adds a disconnect command to the managment interface. Using
this command user space is able to force the disconnection of connected
devices. The command maps directly to the Disconnect HCI command.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |   1 +
 include/net/bluetooth/mgmt.h     |  10 ++++
 net/bluetooth/hci_event.c        |   9 ++-
 net/bluetooth/mgmt.c             | 119 ++++++++++++++++++++++++++++++++++++++-
 4 files changed, 137 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 746f8dc8aad1..2197a099a2b7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -716,6 +716,7 @@ int mgmt_connectable(u16 index, u8 connectable);
 int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type);
 int mgmt_connected(u16 index, bdaddr_t *bdaddr);
 int mgmt_disconnected(u16 index, bdaddr_t *bdaddr);
+int mgmt_disconnect_failed(u16 index);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 6719e9a36613..2c47601b6e63 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -120,6 +120,16 @@ struct mgmt_cp_remove_key {
 	__u8 disconnect;
 } __packed;
 
+#define MGMT_OP_DISCONNECT		0x000F
+struct mgmt_cp_disconnect {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
+struct mgmt_rp_disconnect {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 46ddb029912b..335c60bad96c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1264,8 +1264,10 @@ static inline void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff
 
 	BT_DBG("%s status %d", hdev->name, ev->status);
 
-	if (ev->status)
+	if (ev->status) {
+		mgmt_disconnect_failed(hdev->id);
 		return;
+	}
 
 	hci_dev_lock(hdev);
 
@@ -1680,6 +1682,11 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_exit_sniff_mode(hdev, ev->status);
 		break;
 
+	case HCI_OP_DISCONNECT:
+		if (ev->status != 0)
+			mgmt_disconnect_failed(hdev->id);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7cf1968157d8..48f266a64caf 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -887,6 +887,60 @@ unlock:
 	return err;
 }
 
+static int disconnect(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_disconnect *cp;
+	struct hci_cp_disconnect dc;
+	struct hci_conn *conn;
+	u16 dev_id;
+	int err;
+
+	BT_DBG("");
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_DISCONNECT, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_DISCONNECT, ENETDOWN);
+		goto failed;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_DISCONNECT, dev_id)) {
+		err = cmd_status(sk, MGMT_OP_DISCONNECT, EBUSY);
+		goto failed;
+	}
+
+	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr);
+	if (!conn) {
+		err = cmd_status(sk, MGMT_OP_DISCONNECT, ENOTCONN);
+		goto failed;
+	}
+
+	err = mgmt_pending_add(sk, MGMT_OP_DISCONNECT, dev_id, data, len);
+	if (err < 0)
+		goto failed;
+
+	put_unaligned_le16(conn->handle, &dc.handle);
+	dc.reason = 0x13; /* Remote User Terminated Connection */
+
+	err = hci_send_cmd(hdev, HCI_OP_DISCONNECT, sizeof(dc), &dc);
+	if (err < 0)
+		mgmt_pending_remove(MGMT_OP_DISCONNECT, dev_id);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -957,6 +1011,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_REMOVE_KEY:
 		err = remove_key(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_DISCONNECT:
+		err = disconnect(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -1101,12 +1158,72 @@ int mgmt_connected(u16 index, bdaddr_t *bdaddr)
 	return mgmt_event(MGMT_EV_CONNECTED, &ev, sizeof(ev), NULL);
 }
 
+static void disconnect_rsp(struct pending_cmd *cmd, void *data)
+{
+	struct mgmt_cp_disconnect *cp = cmd->cmd;
+	struct sock **sk = data;
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+	struct mgmt_ev_cmd_complete *ev;
+	struct mgmt_rp_disconnect *rp;
+
+	skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + sizeof(*rp), GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->len = cpu_to_le16(sizeof(*ev) + sizeof(*rp));
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	put_unaligned_le16(MGMT_OP_DISCONNECT, &ev->opcode);
+
+	rp = (void *) skb_put(skb, sizeof(*rp));
+	put_unaligned_le16(cmd->index, &rp->index);
+	bacpy(&rp->bdaddr, &cp->bdaddr);
+
+	if (sock_queue_rcv_skb(cmd->sk, skb) < 0)
+		kfree_skb(skb);
+
+	*sk = cmd->sk;
+	sock_hold(*sk);
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+}
+
 int mgmt_disconnected(u16 index, bdaddr_t *bdaddr)
 {
 	struct mgmt_ev_disconnected ev;
+	struct sock *sk = NULL;
+	int err;
+
+	mgmt_pending_foreach(MGMT_OP_DISCONNECT, index, disconnect_rsp, &sk);
 
 	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 
-	return mgmt_event(MGMT_EV_DISCONNECTED, &ev, sizeof(ev), NULL);
+	err = mgmt_event(MGMT_EV_DISCONNECTED, &ev, sizeof(ev), sk);
+
+	if (sk)
+		sock_put(sk);
+
+	return err;
+}
+
+int mgmt_disconnect_failed(u16 index)
+{
+	struct pending_cmd *cmd;
+	int err;
+
+	cmd = mgmt_pending_find(MGMT_OP_DISCONNECT, index);
+	if (!cmd)
+		return -ENOENT;
+
+	err = cmd_status(cmd->sk, MGMT_OP_DISCONNECT, EIO);
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+
+	return err;
 }
-- 
cgit v1.2.3


From 17d5c04cb597418a177c3ca18dfde679636dd51c Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Sat, 22 Jan 2011 06:09:08 +0200
Subject: Bluetooth: Add support for connect failed management event

This patch add a new connect failed management event to track failures
in connecting to remote devices. It is particularly useful for security
mode 3 scenarios when we don't have a connected state while pairing but
still need to detect when the connect attempt failed.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  1 +
 include/net/bluetooth/mgmt.h     |  7 +++++++
 net/bluetooth/hci_event.c        |  5 ++++-
 net/bluetooth/mgmt.c             | 11 +++++++++++
 4 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2197a099a2b7..45caae62cb8e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -717,6 +717,7 @@ int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type);
 int mgmt_connected(u16 index, bdaddr_t *bdaddr);
 int mgmt_disconnected(u16 index, bdaddr_t *bdaddr);
 int mgmt_disconnect_failed(u16 index);
+int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 2c47601b6e63..1d822f2c0f1a 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -184,3 +184,10 @@ struct mgmt_ev_disconnected {
 	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
+
+#define MGMT_EV_CONNECT_FAILED		0x000D
+struct mgmt_ev_connect_failed {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 status;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 335c60bad96c..995ae6c17f11 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1166,8 +1166,11 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s
 			hci_send_cmd(hdev, HCI_OP_CHANGE_CONN_PTYPE,
 							sizeof(cp), &cp);
 		}
-	} else
+	} else {
 		conn->state = BT_CLOSED;
+		if (conn->type == ACL_LINK)
+			mgmt_connect_failed(hdev->id, &ev->bdaddr, ev->status);
+	}
 
 	if (conn->type == ACL_LINK)
 		hci_sco_setup(conn, ev->status);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 48f266a64caf..9fb989f4216e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1227,3 +1227,14 @@ int mgmt_disconnect_failed(u16 index)
 
 	return err;
 }
+
+int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status)
+{
+	struct mgmt_ev_connect_failed ev;
+
+	put_unaligned_le16(index, &ev.index);
+	bacpy(&ev.bdaddr, bdaddr);
+	ev.status = status;
+
+	return mgmt_event(MGMT_EV_CONNECT_FAILED, &ev, sizeof(ev), NULL);
+}
-- 
cgit v1.2.3


From 2784eb41b1fbb3ff80f4921fe9dbb4c4acb6dc24 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Fri, 21 Jan 2011 13:56:35 +0200
Subject: Bluetooth: Add get_connections managment interface command

This patch adds a get_connections command to the management interface.
With this command userspace can get the current list of connected
devices. Typically this command would only be used once when enumerating
existing adapters. After that the connected and disconnected events are
used to track connections.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/mgmt.h | 10 ++++++
 net/bluetooth/mgmt.c         | 72 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 1d822f2c0f1a..3d8d589fa559 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -130,6 +130,16 @@ struct mgmt_rp_disconnect {
 	bdaddr_t bdaddr;
 } __packed;
 
+#define MGMT_OP_GET_CONNECTIONS		0x0010
+struct mgmt_cp_get_connections {
+	__le16 index;
+} __packed;
+struct mgmt_rp_get_connections {
+	__le16 index;
+	__le16 conn_count;
+	bdaddr_t conn[0];
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9fb989f4216e..8f4f47e9d5c9 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -941,6 +941,75 @@ failed:
 	return err;
 }
 
+static int get_connections(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct sk_buff *skb;
+	struct mgmt_hdr *hdr;
+	struct mgmt_cp_get_connections *cp;
+	struct mgmt_ev_cmd_complete *ev;
+	struct mgmt_rp_get_connections *rp;
+	struct hci_dev *hdev;
+	struct list_head *p;
+	size_t body_len;
+	u16 dev_id, count;
+	int i, err;
+
+	BT_DBG("");
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_GET_CONNECTIONS, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	count = 0;
+	list_for_each(p, &hdev->conn_hash.list) {
+		count++;
+	}
+
+	body_len = sizeof(*ev) + sizeof(*rp) + (count * sizeof(bdaddr_t));
+	skb = alloc_skb(sizeof(*hdr) + body_len, GFP_ATOMIC);
+	if (!skb) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	hdr = (void *) skb_put(skb, sizeof(*hdr));
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->len = cpu_to_le16(body_len);
+
+	ev = (void *) skb_put(skb, sizeof(*ev));
+	put_unaligned_le16(MGMT_OP_GET_CONNECTIONS, &ev->opcode);
+
+	rp = (void *) skb_put(skb, sizeof(*rp) + (count * sizeof(bdaddr_t)));
+	put_unaligned_le16(dev_id, &rp->index);
+	put_unaligned_le16(count, &rp->conn_count);
+
+	read_lock(&hci_dev_list_lock);
+
+	i = 0;
+	list_for_each(p, &hdev->conn_hash.list) {
+		struct hci_conn *c = list_entry(p, struct hci_conn, list);
+
+		bacpy(&rp->conn[i++], &c->dst);
+	}
+
+	read_unlock(&hci_dev_list_lock);
+
+	if (sock_queue_rcv_skb(sk, skb) < 0)
+		kfree_skb(skb);
+
+	err = 0;
+
+unlock:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -1014,6 +1083,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_DISCONNECT:
 		err = disconnect(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_GET_CONNECTIONS:
+		err = get_connections(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
-- 
cgit v1.2.3


From 980e1a537fed7dfa53e9a4b6e586b43341f8c2d5 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Sat, 22 Jan 2011 06:10:07 +0200
Subject: Bluetooth: Add support for PIN code handling in the management
 interface

This patch adds the necessary commands and events needed to communicate
PIN code related actions between the kernel and userspace. This includes
a pin_code_request event as well as pin_code_reply and
pin_code_negative_reply commands.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |   8 +++
 include/net/bluetooth/hci_core.h |   4 ++
 include/net/bluetooth/mgmt.h     |  20 ++++++
 net/bluetooth/hci_event.c        |  46 +++++++++++++
 net/bluetooth/mgmt.c             | 141 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 219 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 08fbf1253b83..e8e52da2b26b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -309,11 +309,19 @@ struct hci_cp_pin_code_reply {
 	__u8     pin_len;
 	__u8     pin_code[16];
 } __packed;
+struct hci_rp_pin_code_reply {
+	__u8     status;
+	bdaddr_t bdaddr;
+} __packed;
 
 #define HCI_OP_PIN_CODE_NEG_REPLY	0x040e
 struct hci_cp_pin_code_neg_reply {
 	bdaddr_t bdaddr;
 } __packed;
+struct hci_rp_pin_code_neg_reply {
+	__u8     status;
+	bdaddr_t bdaddr;
+} __packed;
 
 #define HCI_OP_CHANGE_CONN_PTYPE	0x040f
 struct hci_cp_change_conn_ptype {
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 45caae62cb8e..9ac3da6e4a9a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -213,6 +213,7 @@ struct hci_conn {
 	__u8             auth_type;
 	__u8             sec_level;
 	__u8		 pending_sec_level;
+	__u8		 pin_length;
 	__u8             power_save;
 	__u16            disc_timeout;
 	unsigned long	 pend;
@@ -718,6 +719,9 @@ int mgmt_connected(u16 index, bdaddr_t *bdaddr);
 int mgmt_disconnected(u16 index, bdaddr_t *bdaddr);
 int mgmt_disconnect_failed(u16 index);
 int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status);
+int mgmt_pin_code_request(u16 index, bdaddr_t *bdaddr);
+int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status);
+int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 3d8d589fa559..46fb56d21b59 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -140,6 +140,20 @@ struct mgmt_rp_get_connections {
 	bdaddr_t conn[0];
 } __packed;
 
+#define MGMT_OP_PIN_CODE_REPLY		0x0011
+struct mgmt_cp_pin_code_reply {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 pin_len;
+	__u8 pin_code[16];
+} __packed;
+
+#define MGMT_OP_PIN_CODE_NEG_REPLY	0x0012
+struct mgmt_cp_pin_code_neg_reply {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
@@ -201,3 +215,9 @@ struct mgmt_ev_connect_failed {
 	bdaddr_t bdaddr;
 	__u8 status;
 } __packed;
+
+#define MGMT_EV_PIN_CODE_REQUEST	0x000E
+struct mgmt_ev_pin_code_request {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 995ae6c17f11..98bcf78f2021 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -743,6 +743,40 @@ static void hci_cc_set_event_flt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_req_complete(hdev, HCI_OP_SET_EVENT_FLT, status);
 }
 
+static void hci_cc_pin_code_reply(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_rp_pin_code_reply *rp = (void *) skb->data;
+	struct hci_cp_pin_code_reply *cp;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%x", hdev->name, rp->status);
+
+	if (test_bit(HCI_MGMT, &hdev->flags))
+		mgmt_pin_code_reply_complete(hdev->id, &rp->bdaddr, rp->status);
+
+	if (rp->status != 0)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_PIN_CODE_REPLY);
+	if (!cp)
+		return;
+
+	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr);
+	if (conn)
+		conn->pin_length = cp->pin_len;
+}
+
+static void hci_cc_pin_code_neg_reply(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_rp_pin_code_neg_reply *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%x", hdev->name, rp->status);
+
+	if (test_bit(HCI_MGMT, &hdev->flags))
+		mgmt_pin_code_neg_reply_complete(hdev->id, &rp->bdaddr,
+								rp->status);
+}
+
 static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%x", hdev->name, status);
@@ -1619,6 +1653,14 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk
 		hci_cc_set_event_flt(hdev, skb);
 		break;
 
+	case HCI_OP_PIN_CODE_REPLY:
+		hci_cc_pin_code_reply(hdev, skb);
+		break;
+
+	case HCI_OP_PIN_CODE_NEG_REPLY:
+		hci_cc_pin_code_neg_reply(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
@@ -1821,6 +1863,9 @@ static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff
 		hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY,
 					sizeof(ev->bdaddr), &ev->bdaddr);
 
+	if (test_bit(HCI_MGMT, &hdev->flags))
+		mgmt_pin_code_request(hdev->id, &ev->bdaddr);
+
 	hci_dev_unlock(hdev);
 }
 
@@ -1889,6 +1934,7 @@ static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff
 	if (conn) {
 		hci_conn_hold(conn);
 		conn->disc_timeout = HCI_DISCONN_TIMEOUT;
+		pin_len = conn->pin_length;
 		hci_conn_put(conn);
 	}
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 005288b2a58e..3800aaf5792d 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -933,6 +933,89 @@ unlock:
 	return err;
 }
 
+static int pin_code_reply(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_pin_code_reply *cp;
+	struct hci_cp_pin_code_reply reply;
+	u16 dev_id;
+	int err;
+
+	BT_DBG("");
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_DISCONNECT, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_PIN_CODE_REPLY, ENETDOWN);
+		goto failed;
+	}
+
+	err = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_REPLY, dev_id, data, len);
+	if (err < 0)
+		goto failed;
+
+	bacpy(&reply.bdaddr, &cp->bdaddr);
+	reply.pin_len = cp->pin_len;
+	memcpy(reply.pin_code, cp->pin_code, 16);
+
+	err = hci_send_cmd(hdev, HCI_OP_PIN_CODE_REPLY, sizeof(reply), &reply);
+	if (err < 0)
+		mgmt_pending_remove(MGMT_OP_PIN_CODE_REPLY, dev_id);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
+static int pin_code_neg_reply(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_pin_code_neg_reply *cp;
+	u16 dev_id;
+	int err;
+
+	BT_DBG("");
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_PIN_CODE_NEG_REPLY, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = cmd_status(sk, MGMT_OP_PIN_CODE_NEG_REPLY, ENETDOWN);
+		goto failed;
+	}
+
+	err = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, dev_id,
+								data, len);
+	if (err < 0)
+		goto failed;
+
+	err = hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY, sizeof(bdaddr_t),
+								&cp->bdaddr);
+	if (err < 0)
+		mgmt_pending_remove(MGMT_OP_PIN_CODE_NEG_REPLY, dev_id);
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -1009,6 +1092,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_GET_CONNECTIONS:
 		err = get_connections(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_PIN_CODE_REPLY:
+		err = pin_code_reply(sk, buf + sizeof(*hdr), len);
+		break;
+	case MGMT_OP_PIN_CODE_NEG_REPLY:
+		err = pin_code_neg_reply(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -1217,3 +1306,55 @@ int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status)
 
 	return mgmt_event(MGMT_EV_CONNECT_FAILED, &ev, sizeof(ev), NULL);
 }
+
+int mgmt_pin_code_request(u16 index, bdaddr_t *bdaddr)
+{
+	struct mgmt_ev_pin_code_request ev;
+
+	put_unaligned_le16(index, &ev.index);
+	bacpy(&ev.bdaddr, bdaddr);
+
+	return mgmt_event(MGMT_EV_PIN_CODE_REQUEST, &ev, sizeof(ev), NULL);
+}
+
+int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
+{
+	struct pending_cmd *cmd;
+	int err;
+
+	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_REPLY, index);
+	if (!cmd)
+		return -ENOENT;
+
+	if (status != 0)
+		err = cmd_status(cmd->sk, MGMT_OP_PIN_CODE_REPLY, status);
+	else
+		err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_REPLY,
+						bdaddr, sizeof(*bdaddr));
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+
+	return err;
+}
+
+int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
+{
+	struct pending_cmd *cmd;
+	int err;
+
+	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, index);
+	if (!cmd)
+		return -ENOENT;
+
+	if (status != 0)
+		err = cmd_status(cmd->sk, MGMT_OP_PIN_CODE_NEG_REPLY, status);
+	else
+		err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_NEG_REPLY,
+						bdaddr, sizeof(*bdaddr));
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+
+	return err;
+}
-- 
cgit v1.2.3


From 17fa4b9dff72fb3a1a68cc80caf98fc941d2b8b3 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Tue, 25 Jan 2011 13:28:33 +0200
Subject: Bluetooth: Add set_io_capability management command

This patch adds a new set_io_capability management command which is used
to set the IO capability for Secure Simple Pairing (SSP) as well as the
Security Manager Protocol (SMP). The value is per hci_dev and each
hci_conn object inherits it upon creation.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |  8 ++++++++
 include/net/bluetooth/hci_core.h |  2 ++
 include/net/bluetooth/mgmt.h     |  6 ++++++
 net/bluetooth/hci_conn.c         |  1 +
 net/bluetooth/hci_core.c         |  1 +
 net/bluetooth/hci_event.c        | 30 ++++++++++++++++++++++++++++--
 net/bluetooth/mgmt.c             | 32 ++++++++++++++++++++++++++++++++
 7 files changed, 78 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e8e52da2b26b..4bee030e4b52 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -402,6 +402,14 @@ struct hci_cp_reject_sync_conn_req {
 	__u8     reason;
 } __packed;
 
+#define HCI_OP_IO_CAPABILITY_REPLY	0x042b
+struct hci_cp_io_capability_reply {
+	bdaddr_t bdaddr;
+	__u8     capability;
+	__u8     oob_data;
+	__u8     authentication;
+} __packed;
+
 #define HCI_OP_IO_CAPABILITY_NEG_REPLY	0x0434
 struct hci_cp_io_capability_neg_reply {
 	bdaddr_t bdaddr;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9ac3da6e4a9a..6163bff6fa91 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -106,6 +106,7 @@ struct hci_dev {
 	__u16		manufacturer;
 	__le16		lmp_subver;
 	__u16		voice_setting;
+	__u8		io_capability;
 
 	__u16		pkt_type;
 	__u16		esco_type;
@@ -214,6 +215,7 @@ struct hci_conn {
 	__u8             sec_level;
 	__u8		 pending_sec_level;
 	__u8		 pin_length;
+	__u8		 io_capability;
 	__u8             power_save;
 	__u16            disc_timeout;
 	unsigned long	 pend;
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 46fb56d21b59..44ac55c85079 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -154,6 +154,12 @@ struct mgmt_cp_pin_code_neg_reply {
 	bdaddr_t bdaddr;
 } __packed;
 
+#define MGMT_OP_SET_IO_CAPABILITY	0x0013
+struct mgmt_cp_set_io_capability {
+	__le16 index;
+	__u8 io_capability;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 99cd8d9d891b..42dc39f25b72 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -234,6 +234,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	conn->mode  = HCI_CM_ACTIVE;
 	conn->state = BT_OPEN;
 	conn->auth_type = HCI_AT_GENERAL_BONDING;
+	conn->io_capability = hdev->io_capability;
 
 	conn->power_save = 1;
 	conn->disc_timeout = HCI_DISCONN_TIMEOUT;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 8ca8cf147058..bf6729a53378 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1084,6 +1084,7 @@ int hci_register_dev(struct hci_dev *hdev)
 	hdev->pkt_type  = (HCI_DM1 | HCI_DH1 | HCI_HV1);
 	hdev->esco_type = (ESCO_HV1);
 	hdev->link_mode = (HCI_LM_ACCEPT);
+	hdev->io_capability = 0x03; /* No Input No Output */
 
 	hdev->idle_timeout = 0;
 	hdev->sniff_max_interval = 800;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 98bcf78f2021..617f58363dbc 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2198,6 +2198,25 @@ static inline void hci_extended_inquiry_result_evt(struct hci_dev *hdev, struct
 	hci_dev_unlock(hdev);
 }
 
+static inline u8 hci_get_auth_req(struct hci_conn *conn)
+{
+	/* If remote requests dedicated bonding follow that lead */
+	if (conn->remote_auth == 0x02 || conn->remote_auth == 0x03) {
+		/* If both remote and local IO capabilities allow MITM
+		 * protection then require it, otherwise don't */
+		if (conn->remote_cap == 0x03 || conn->io_capability == 0x03)
+			return 0x02;
+		else
+			return 0x03;
+	}
+
+	/* If remote requests no-bonding follow that lead */
+	if (conn->remote_auth == 0x00 || conn->remote_auth == 0x01)
+		return 0x00;
+
+	return conn->auth_type;
+}
+
 static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_io_capa_request *ev = (void *) skb->data;
@@ -2218,8 +2237,15 @@ static inline void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff
 
 	if (test_bit(HCI_PAIRABLE, &hdev->flags) ||
 			(conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) {
-		/* FIXME: Do IO capa response based on information
-		 * provided through the management interface */
+		struct hci_cp_io_capability_reply cp;
+
+		bacpy(&cp.bdaddr, &ev->bdaddr);
+		cp.capability = conn->io_capability;
+		cp.oob_data = 0;
+		cp.authentication = hci_get_auth_req(conn);
+
+		hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_REPLY,
+							sizeof(cp), &cp);
 	} else {
 		struct hci_cp_io_capability_neg_reply cp;
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3800aaf5792d..b2bda83050a4 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1016,6 +1016,35 @@ failed:
 	return err;
 }
 
+static int set_io_capability(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_set_io_capability *cp;
+	u16 dev_id;
+
+	BT_DBG("");
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_SET_IO_CAPABILITY, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	hdev->io_capability = cp->io_capability;
+
+	BT_DBG("%s IO capability set to 0x%02x", hdev->name,
+						hdev->io_capability);
+
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return cmd_complete(sk, MGMT_OP_SET_IO_CAPABILITY,
+						&dev_id, sizeof(dev_id));
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -1098,6 +1127,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_PIN_CODE_NEG_REPLY:
 		err = pin_code_neg_reply(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_SET_IO_CAPABILITY:
+		err = set_io_capability(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
-- 
cgit v1.2.3


From bb58f747e519aba07a6f05a78d58cf8a0788e2d5 Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Thu, 3 Feb 2011 20:50:35 -0200
Subject: Bluetooth: Initial work for L2CAP split.

This patch tries to do the minimal to move l2cap_sock_create() and its
dependencies to l2cap_sock.c. It create a API to initialize and cleanup
the L2CAP sockets from l2cap_core.c through l2cap_init_sockets() and
l2cap_cleanup_sockets().

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  15 +++
 net/bluetooth/Makefile        |   2 +-
 net/bluetooth/l2cap_core.c    | 187 +++---------------------------------
 net/bluetooth/l2cap_sock.c    | 213 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 240 insertions(+), 177 deletions(-)
 create mode 100644 net/bluetooth/l2cap_sock.c

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 7f88a87d7a46..fce5274a4f7b 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -424,6 +424,21 @@ static inline int l2cap_tx_window_full(struct sock *sk)
 #define __is_sframe(ctrl)	((ctrl) & L2CAP_CTRL_FRAME_TYPE)
 #define __is_sar_start(ctrl)	(((ctrl) & L2CAP_CTRL_SAR) == L2CAP_SDU_START)
 
+extern int disable_ertm;
+extern const struct proto_ops l2cap_sock_ops;
+extern struct bt_sock_list l2cap_sk_list;
+
+int l2cap_init_sockets(void);
+void l2cap_cleanup_sockets(void);
+
+void l2cap_sock_set_timer(struct sock *sk, long timeout);
+void __l2cap_sock_close(struct sock *sk, int reason);
+void l2cap_sock_kill(struct sock *sk);
+void l2cap_sock_init(struct sock *sk, struct sock *parent);
+struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
+							int proto, gfp_t prio);
+
+
 void l2cap_load(void);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index bf2945e1d9ef..339b42932b33 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -11,4 +11,4 @@ obj-$(CONFIG_BT_CMTP)	+= cmtp/
 obj-$(CONFIG_BT_HIDP)	+= hidp/
 
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o hci_sock.o hci_sysfs.o lib.o
-l2cap-y := l2cap_core.o
+l2cap-y := l2cap_core.o l2cap_sock.o
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 28d2954f94a4..af678efec15f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -24,7 +24,7 @@
    SOFTWARE IS DISCLAIMED.
 */
 
-/* Bluetooth L2CAP core and sockets. */
+/* Bluetooth L2CAP core. */
 
 #include <linux/module.h>
 
@@ -57,24 +57,20 @@
 
 #define VERSION "2.15"
 
-static int disable_ertm;
+int disable_ertm;
 
 static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN;
 static u8 l2cap_fixed_chan[8] = { 0x02, };
 
-static const struct proto_ops l2cap_sock_ops;
-
 static struct workqueue_struct *_busy_wq;
 
-static struct bt_sock_list l2cap_sk_list = {
+struct bt_sock_list l2cap_sk_list = {
 	.lock = __RW_LOCK_UNLOCKED(l2cap_sk_list.lock)
 };
 
 static void l2cap_busy_work(struct work_struct *work);
 
-static void __l2cap_sock_close(struct sock *sk, int reason);
 static void l2cap_sock_close(struct sock *sk);
-static void l2cap_sock_kill(struct sock *sk);
 
 static int l2cap_build_conf_req(struct sock *sk, void *data);
 static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
@@ -83,7 +79,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 static int l2cap_ertm_data_rcv(struct sock *sk, struct sk_buff *skb);
 
 /* ---- L2CAP timers ---- */
-static void l2cap_sock_set_timer(struct sock *sk, long timeout)
+void l2cap_sock_set_timer(struct sock *sk, long timeout)
 {
 	BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout);
 	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
@@ -95,39 +91,6 @@ static void l2cap_sock_clear_timer(struct sock *sk)
 	sk_stop_timer(sk, &sk->sk_timer);
 }
 
-static void l2cap_sock_timeout(unsigned long arg)
-{
-	struct sock *sk = (struct sock *) arg;
-	int reason;
-
-	BT_DBG("sock %p state %d", sk, sk->sk_state);
-
-	bh_lock_sock(sk);
-
-	if (sock_owned_by_user(sk)) {
-		/* sk is owned by user. Try again later */
-		l2cap_sock_set_timer(sk, HZ / 5);
-		bh_unlock_sock(sk);
-		sock_put(sk);
-		return;
-	}
-
-	if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG)
-		reason = ECONNREFUSED;
-	else if (sk->sk_state == BT_CONNECT &&
-				l2cap_pi(sk)->sec_level != BT_SECURITY_SDP)
-		reason = ECONNREFUSED;
-	else
-		reason = ETIMEDOUT;
-
-	__l2cap_sock_close(sk, reason);
-
-	bh_unlock_sock(sk);
-
-	l2cap_sock_kill(sk);
-	sock_put(sk);
-}
-
 /* ---- L2CAP channels ---- */
 static struct sock *__l2cap_get_chan_by_dcid(struct l2cap_chan_list *l, u16 cid)
 {
@@ -801,14 +764,6 @@ static struct sock *l2cap_get_sock_by_psm(int state, __le16 psm, bdaddr_t *src)
 	return node ? sk : sk1;
 }
 
-static void l2cap_sock_destruct(struct sock *sk)
-{
-	BT_DBG("sk %p", sk);
-
-	skb_queue_purge(&sk->sk_receive_queue);
-	skb_queue_purge(&sk->sk_write_queue);
-}
-
 static void l2cap_sock_cleanup_listen(struct sock *parent)
 {
 	struct sock *sk;
@@ -826,7 +781,7 @@ static void l2cap_sock_cleanup_listen(struct sock *parent)
 /* Kill socket (only if zapped and orphan)
  * Must be called on unlocked socket.
  */
-static void l2cap_sock_kill(struct sock *sk)
+void l2cap_sock_kill(struct sock *sk)
 {
 	if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket)
 		return;
@@ -839,7 +794,7 @@ static void l2cap_sock_kill(struct sock *sk)
 	sock_put(sk);
 }
 
-static void __l2cap_sock_close(struct sock *sk, int reason)
+void __l2cap_sock_close(struct sock *sk, int reason)
 {
 	BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket);
 
@@ -904,111 +859,6 @@ static void l2cap_sock_close(struct sock *sk)
 	l2cap_sock_kill(sk);
 }
 
-static void l2cap_sock_init(struct sock *sk, struct sock *parent)
-{
-	struct l2cap_pinfo *pi = l2cap_pi(sk);
-
-	BT_DBG("sk %p", sk);
-
-	if (parent) {
-		sk->sk_type = parent->sk_type;
-		bt_sk(sk)->defer_setup = bt_sk(parent)->defer_setup;
-
-		pi->imtu = l2cap_pi(parent)->imtu;
-		pi->omtu = l2cap_pi(parent)->omtu;
-		pi->conf_state = l2cap_pi(parent)->conf_state;
-		pi->mode = l2cap_pi(parent)->mode;
-		pi->fcs  = l2cap_pi(parent)->fcs;
-		pi->max_tx = l2cap_pi(parent)->max_tx;
-		pi->tx_win = l2cap_pi(parent)->tx_win;
-		pi->sec_level = l2cap_pi(parent)->sec_level;
-		pi->role_switch = l2cap_pi(parent)->role_switch;
-		pi->force_reliable = l2cap_pi(parent)->force_reliable;
-		pi->flushable = l2cap_pi(parent)->flushable;
-	} else {
-		pi->imtu = L2CAP_DEFAULT_MTU;
-		pi->omtu = 0;
-		if (!disable_ertm && sk->sk_type == SOCK_STREAM) {
-			pi->mode = L2CAP_MODE_ERTM;
-			pi->conf_state |= L2CAP_CONF_STATE2_DEVICE;
-		} else {
-			pi->mode = L2CAP_MODE_BASIC;
-		}
-		pi->max_tx = L2CAP_DEFAULT_MAX_TX;
-		pi->fcs  = L2CAP_FCS_CRC16;
-		pi->tx_win = L2CAP_DEFAULT_TX_WINDOW;
-		pi->sec_level = BT_SECURITY_LOW;
-		pi->role_switch = 0;
-		pi->force_reliable = 0;
-		pi->flushable = BT_FLUSHABLE_OFF;
-	}
-
-	/* Default config options */
-	pi->conf_len = 0;
-	pi->flush_to = L2CAP_DEFAULT_FLUSH_TO;
-	skb_queue_head_init(TX_QUEUE(sk));
-	skb_queue_head_init(SREJ_QUEUE(sk));
-	skb_queue_head_init(BUSY_QUEUE(sk));
-	INIT_LIST_HEAD(SREJ_LIST(sk));
-}
-
-static struct proto l2cap_proto = {
-	.name		= "L2CAP",
-	.owner		= THIS_MODULE,
-	.obj_size	= sizeof(struct l2cap_pinfo)
-};
-
-static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio)
-{
-	struct sock *sk;
-
-	sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto);
-	if (!sk)
-		return NULL;
-
-	sock_init_data(sock, sk);
-	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
-
-	sk->sk_destruct = l2cap_sock_destruct;
-	sk->sk_sndtimeo = msecs_to_jiffies(L2CAP_CONN_TIMEOUT);
-
-	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	sk->sk_protocol = proto;
-	sk->sk_state = BT_OPEN;
-
-	setup_timer(&sk->sk_timer, l2cap_sock_timeout, (unsigned long) sk);
-
-	bt_sock_link(&l2cap_sk_list, sk);
-	return sk;
-}
-
-static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol,
-			     int kern)
-{
-	struct sock *sk;
-
-	BT_DBG("sock %p", sock);
-
-	sock->state = SS_UNCONNECTED;
-
-	if (sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM &&
-			sock->type != SOCK_DGRAM && sock->type != SOCK_RAW)
-		return -ESOCKTNOSUPPORT;
-
-	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
-		return -EPERM;
-
-	sock->ops = &l2cap_sock_ops;
-
-	sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC);
-	if (!sk)
-		return -ENOMEM;
-
-	l2cap_sock_init(sk, NULL);
-	return 0;
-}
-
 static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 {
 	struct sock *sk = sock->sk;
@@ -4865,7 +4715,7 @@ static const struct file_operations l2cap_debugfs_fops = {
 
 static struct dentry *l2cap_debugfs;
 
-static const struct proto_ops l2cap_sock_ops = {
+const struct proto_ops l2cap_sock_ops = {
 	.family		= PF_BLUETOOTH,
 	.owner		= THIS_MODULE,
 	.release	= l2cap_sock_release,
@@ -4885,12 +4735,6 @@ static const struct proto_ops l2cap_sock_ops = {
 	.getsockopt	= l2cap_sock_getsockopt
 };
 
-static const struct net_proto_family l2cap_sock_family_ops = {
-	.family	= PF_BLUETOOTH,
-	.owner	= THIS_MODULE,
-	.create	= l2cap_sock_create,
-};
-
 static struct hci_proto l2cap_hci_proto = {
 	.name		= "L2CAP",
 	.id		= HCI_PROTO_L2CAP,
@@ -4906,19 +4750,13 @@ static int __init l2cap_init(void)
 {
 	int err;
 
-	err = proto_register(&l2cap_proto, 0);
+	err = l2cap_init_sockets();
 	if (err < 0)
 		return err;
 
 	_busy_wq = create_singlethread_workqueue("l2cap");
 	if (!_busy_wq) {
-		proto_unregister(&l2cap_proto);
-		return -ENOMEM;
-	}
-
-	err = bt_sock_register(BTPROTO_L2CAP, &l2cap_sock_family_ops);
-	if (err < 0) {
-		BT_ERR("L2CAP socket registration failed");
+		err = -ENOMEM;
 		goto error;
 	}
 
@@ -4943,7 +4781,7 @@ static int __init l2cap_init(void)
 
 error:
 	destroy_workqueue(_busy_wq);
-	proto_unregister(&l2cap_proto);
+	l2cap_cleanup_sockets();
 	return err;
 }
 
@@ -4954,13 +4792,10 @@ static void __exit l2cap_exit(void)
 	flush_workqueue(_busy_wq);
 	destroy_workqueue(_busy_wq);
 
-	if (bt_sock_unregister(BTPROTO_L2CAP) < 0)
-		BT_ERR("L2CAP socket unregistration failed");
-
 	if (hci_unregister_proto(&l2cap_hci_proto) < 0)
 		BT_ERR("L2CAP protocol unregistration failed");
 
-	proto_unregister(&l2cap_proto);
+	l2cap_cleanup_sockets();
 }
 
 void l2cap_load(void)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
new file mode 100644
index 000000000000..6ea1894cecb7
--- /dev/null
+++ b/net/bluetooth/l2cap_sock.c
@@ -0,0 +1,213 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   Copyright (C) 2000-2001 Qualcomm Incorporated
+   Copyright (C) 2009-2010 Gustavo F. Padovan <gustavo@padovan.org>
+   Copyright (C) 2010 Google Inc.
+
+   Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com>
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 as
+   published by the Free Software Foundation;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+/* Bluetooth L2CAP sockets. */
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/l2cap.h>
+
+static void l2cap_sock_timeout(unsigned long arg)
+{
+	struct sock *sk = (struct sock *) arg;
+	int reason;
+
+	BT_DBG("sock %p state %d", sk, sk->sk_state);
+
+	bh_lock_sock(sk);
+
+	if (sock_owned_by_user(sk)) {
+		/* sk is owned by user. Try again later */
+		l2cap_sock_set_timer(sk, HZ / 5);
+		bh_unlock_sock(sk);
+		sock_put(sk);
+		return;
+	}
+
+	if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG)
+		reason = ECONNREFUSED;
+	else if (sk->sk_state == BT_CONNECT &&
+				l2cap_pi(sk)->sec_level != BT_SECURITY_SDP)
+		reason = ECONNREFUSED;
+	else
+		reason = ETIMEDOUT;
+
+	__l2cap_sock_close(sk, reason);
+
+	bh_unlock_sock(sk);
+
+	l2cap_sock_kill(sk);
+	sock_put(sk);
+}
+
+
+static void l2cap_sock_destruct(struct sock *sk)
+{
+	BT_DBG("sk %p", sk);
+
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge(&sk->sk_write_queue);
+}
+
+void l2cap_sock_init(struct sock *sk, struct sock *parent)
+{
+	struct l2cap_pinfo *pi = l2cap_pi(sk);
+
+	BT_DBG("sk %p", sk);
+
+	if (parent) {
+		sk->sk_type = parent->sk_type;
+		bt_sk(sk)->defer_setup = bt_sk(parent)->defer_setup;
+
+		pi->imtu = l2cap_pi(parent)->imtu;
+		pi->omtu = l2cap_pi(parent)->omtu;
+		pi->conf_state = l2cap_pi(parent)->conf_state;
+		pi->mode = l2cap_pi(parent)->mode;
+		pi->fcs  = l2cap_pi(parent)->fcs;
+		pi->max_tx = l2cap_pi(parent)->max_tx;
+		pi->tx_win = l2cap_pi(parent)->tx_win;
+		pi->sec_level = l2cap_pi(parent)->sec_level;
+		pi->role_switch = l2cap_pi(parent)->role_switch;
+		pi->force_reliable = l2cap_pi(parent)->force_reliable;
+		pi->flushable = l2cap_pi(parent)->flushable;
+	} else {
+		pi->imtu = L2CAP_DEFAULT_MTU;
+		pi->omtu = 0;
+		if (!disable_ertm && sk->sk_type == SOCK_STREAM) {
+			pi->mode = L2CAP_MODE_ERTM;
+			pi->conf_state |= L2CAP_CONF_STATE2_DEVICE;
+		} else {
+			pi->mode = L2CAP_MODE_BASIC;
+		}
+		pi->max_tx = L2CAP_DEFAULT_MAX_TX;
+		pi->fcs  = L2CAP_FCS_CRC16;
+		pi->tx_win = L2CAP_DEFAULT_TX_WINDOW;
+		pi->sec_level = BT_SECURITY_LOW;
+		pi->role_switch = 0;
+		pi->force_reliable = 0;
+		pi->flushable = BT_FLUSHABLE_OFF;
+	}
+
+	/* Default config options */
+	pi->conf_len = 0;
+	pi->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+	skb_queue_head_init(TX_QUEUE(sk));
+	skb_queue_head_init(SREJ_QUEUE(sk));
+	skb_queue_head_init(BUSY_QUEUE(sk));
+	INIT_LIST_HEAD(SREJ_LIST(sk));
+}
+
+static struct proto l2cap_proto = {
+	.name		= "L2CAP",
+	.owner		= THIS_MODULE,
+	.obj_size	= sizeof(struct l2cap_pinfo)
+};
+
+struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio)
+{
+	struct sock *sk;
+
+	sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto);
+	if (!sk)
+		return NULL;
+
+	sock_init_data(sock, sk);
+	INIT_LIST_HEAD(&bt_sk(sk)->accept_q);
+
+	sk->sk_destruct = l2cap_sock_destruct;
+	sk->sk_sndtimeo = msecs_to_jiffies(L2CAP_CONN_TIMEOUT);
+
+	sock_reset_flag(sk, SOCK_ZAPPED);
+
+	sk->sk_protocol = proto;
+	sk->sk_state = BT_OPEN;
+
+	setup_timer(&sk->sk_timer, l2cap_sock_timeout, (unsigned long) sk);
+
+	bt_sock_link(&l2cap_sk_list, sk);
+	return sk;
+}
+
+static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol,
+			     int kern)
+{
+	struct sock *sk;
+
+	BT_DBG("sock %p", sock);
+
+	sock->state = SS_UNCONNECTED;
+
+	if (sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM &&
+			sock->type != SOCK_DGRAM && sock->type != SOCK_RAW)
+		return -ESOCKTNOSUPPORT;
+
+	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
+		return -EPERM;
+
+	sock->ops = &l2cap_sock_ops;
+
+	sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC);
+	if (!sk)
+		return -ENOMEM;
+
+	l2cap_sock_init(sk, NULL);
+	return 0;
+}
+
+static const struct net_proto_family l2cap_sock_family_ops = {
+	.family	= PF_BLUETOOTH,
+	.owner	= THIS_MODULE,
+	.create	= l2cap_sock_create,
+};
+
+int __init l2cap_init_sockets(void)
+{
+       int err;
+
+       err = proto_register(&l2cap_proto, 0);
+       if (err < 0)
+               return err;
+
+       err = bt_sock_register(BTPROTO_L2CAP, &l2cap_sock_family_ops);
+       if (err < 0)
+               goto error;
+
+       BT_INFO("L2CAP socket layer initialized");
+
+       return 0;
+
+error:
+       BT_ERR("L2CAP socket registration failed");
+       proto_unregister(&l2cap_proto);
+       return err;
+}
+
+void l2cap_cleanup_sockets(void)
+{
+       if (bt_sock_unregister(BTPROTO_L2CAP) < 0)
+               BT_ERR("L2CAP socket unregistration failed");
+
+       proto_unregister(&l2cap_proto);
+}
-- 
cgit v1.2.3


From 65390587c7bcf8bb60b48387db766d8d7dfea982 Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:33:56 -0200
Subject: Bluetooth: move l2cap_sock_ops to l2cap_sock.c

First step to move all l2cap_sock_ops function to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h | 12 ++++++++++++
 net/bluetooth/l2cap_core.c    | 42 +++++++++++-------------------------------
 net/bluetooth/l2cap_sock.c    | 21 ++++++++++++++++++++-
 3 files changed, 43 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index fce5274a4f7b..533bef5f6341 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -438,6 +438,18 @@ void l2cap_sock_init(struct sock *sk, struct sock *parent);
 struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
 
+int l2cap_sock_release(struct socket *sock);
+int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen);
+int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags);
+int l2cap_sock_listen(struct socket *sock, int backlog);
+int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags);
+int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer);
+int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
+int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
+int l2cap_sock_shutdown(struct socket *sock, int how);
+int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen);
+int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen);
+
 
 void l2cap_load(void);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index af678efec15f..74a3ea3625d6 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -859,7 +859,7 @@ static void l2cap_sock_close(struct sock *sk)
 	l2cap_sock_kill(sk);
 }
 
-static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
+int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_l2 la;
@@ -983,7 +983,7 @@ done:
 	return err;
 }
 
-static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags)
+int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_l2 la;
@@ -1068,7 +1068,7 @@ done:
 	return err;
 }
 
-static int l2cap_sock_listen(struct socket *sock, int backlog)
+int l2cap_sock_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
 	int err = 0;
@@ -1127,7 +1127,7 @@ done:
 	return err;
 }
 
-static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *nsk;
@@ -1183,7 +1183,7 @@ done:
 	return err;
 }
 
-static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer)
+int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer)
 {
 	struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
 	struct sock *sk = sock->sk;
@@ -1665,7 +1665,7 @@ static inline int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, siz
 	return size;
 }
 
-static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len)
+int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
@@ -1767,7 +1767,7 @@ done:
 	return err;
 }
 
-static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
+int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
 
@@ -1894,7 +1894,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us
 	return err;
 }
 
-static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
+int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 	struct bt_security sec;
@@ -2067,7 +2067,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us
 	return err;
 }
 
-static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
 {
 	struct sock *sk = sock->sk;
 	struct bt_security sec;
@@ -2128,7 +2128,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch
 	return err;
 }
 
-static int l2cap_sock_shutdown(struct socket *sock, int how)
+int l2cap_sock_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
 	int err = 0;
@@ -2159,7 +2159,7 @@ static int l2cap_sock_shutdown(struct socket *sock, int how)
 	return err;
 }
 
-static int l2cap_sock_release(struct socket *sock)
+int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	int err;
@@ -4715,26 +4715,6 @@ static const struct file_operations l2cap_debugfs_fops = {
 
 static struct dentry *l2cap_debugfs;
 
-const struct proto_ops l2cap_sock_ops = {
-	.family		= PF_BLUETOOTH,
-	.owner		= THIS_MODULE,
-	.release	= l2cap_sock_release,
-	.bind		= l2cap_sock_bind,
-	.connect	= l2cap_sock_connect,
-	.listen		= l2cap_sock_listen,
-	.accept		= l2cap_sock_accept,
-	.getname	= l2cap_sock_getname,
-	.sendmsg	= l2cap_sock_sendmsg,
-	.recvmsg	= l2cap_sock_recvmsg,
-	.poll		= bt_sock_poll,
-	.ioctl		= bt_sock_ioctl,
-	.mmap		= sock_no_mmap,
-	.socketpair	= sock_no_socketpair,
-	.shutdown	= l2cap_sock_shutdown,
-	.setsockopt	= l2cap_sock_setsockopt,
-	.getsockopt	= l2cap_sock_getsockopt
-};
-
 static struct hci_proto l2cap_hci_proto = {
 	.name		= "L2CAP",
 	.id		= HCI_PROTO_L2CAP,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 6ea1894cecb7..c1455f72bf03 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -62,7 +62,6 @@ static void l2cap_sock_timeout(unsigned long arg)
 	sock_put(sk);
 }
 
-
 static void l2cap_sock_destruct(struct sock *sk)
 {
 	BT_DBG("sk %p", sk);
@@ -176,6 +175,26 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol,
 	return 0;
 }
 
+const struct proto_ops l2cap_sock_ops = {
+	.family		= PF_BLUETOOTH,
+	.owner		= THIS_MODULE,
+	.release	= l2cap_sock_release,
+	.bind		= l2cap_sock_bind,
+	.connect	= l2cap_sock_connect,
+	.listen		= l2cap_sock_listen,
+	.accept		= l2cap_sock_accept,
+	.getname	= l2cap_sock_getname,
+	.sendmsg	= l2cap_sock_sendmsg,
+	.recvmsg	= l2cap_sock_recvmsg,
+	.poll		= bt_sock_poll,
+	.ioctl		= bt_sock_ioctl,
+	.mmap		= sock_no_mmap,
+	.socketpair	= sock_no_socketpair,
+	.shutdown	= l2cap_sock_shutdown,
+	.setsockopt	= l2cap_sock_setsockopt,
+	.getsockopt	= l2cap_sock_getsockopt
+};
+
 static const struct net_proto_family l2cap_sock_family_ops = {
 	.family	= PF_BLUETOOTH,
 	.owner	= THIS_MODULE,
-- 
cgit v1.2.3


From 554f05bb8a0707dcc0ba4ea1dba1fb9970846ab5 Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:36:42 -0200
Subject: Bluetooth: move l2cap_sock_release() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  1 -
 net/bluetooth/l2cap_core.c    | 17 -----------------
 net/bluetooth/l2cap_sock.c    | 17 +++++++++++++++++
 3 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 533bef5f6341..d0baf4163261 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -438,7 +438,6 @@ void l2cap_sock_init(struct sock *sk, struct sock *parent);
 struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
 
-int l2cap_sock_release(struct socket *sock);
 int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen);
 int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags);
 int l2cap_sock_listen(struct socket *sock, int backlog);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 74a3ea3625d6..5765a82cf380 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2159,23 +2159,6 @@ int l2cap_sock_shutdown(struct socket *sock, int how)
 	return err;
 }
 
-int l2cap_sock_release(struct socket *sock)
-{
-	struct sock *sk = sock->sk;
-	int err;
-
-	BT_DBG("sock %p, sk %p", sock, sk);
-
-	if (!sk)
-		return 0;
-
-	err = l2cap_sock_shutdown(sock, 2);
-
-	sock_orphan(sk);
-	l2cap_sock_kill(sk);
-	return err;
-}
-
 static void l2cap_chan_ready(struct sock *sk)
 {
 	struct sock *parent = bt_sk(sk)->parent;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index c1455f72bf03..20efd240a786 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -62,6 +62,23 @@ static void l2cap_sock_timeout(unsigned long arg)
 	sock_put(sk);
 }
 
+static int l2cap_sock_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	int err;
+
+	BT_DBG("sock %p, sk %p", sock, sk);
+
+	if (!sk)
+		return 0;
+
+	err = l2cap_sock_shutdown(sock, 2);
+
+	sock_orphan(sk);
+	l2cap_sock_kill(sk);
+	return err;
+}
+
 static void l2cap_sock_destruct(struct sock *sk)
 {
 	BT_DBG("sk %p", sk);
-- 
cgit v1.2.3


From af6bcd8205ac06fa1de98b2b28303157fb9c3dfc Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:40:28 -0200
Subject: Bluetooth: move l2cap_sock_bind()/listen() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |   2 -
 net/bluetooth/l2cap_core.c    | 134 -----------------------------------------
 net/bluetooth/l2cap_sock.c    | 135 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 135 insertions(+), 136 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index d0baf4163261..3ca4fe30d75e 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -438,9 +438,7 @@ void l2cap_sock_init(struct sock *sk, struct sock *parent);
 struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
 
-int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen);
 int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags);
-int l2cap_sock_listen(struct socket *sock, int backlog);
 int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags);
 int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer);
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 5765a82cf380..6af38722d5cb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -722,17 +722,6 @@ static inline void l2cap_chan_add(struct l2cap_conn *conn, struct sock *sk, stru
 }
 
 /* ---- Socket interface ---- */
-static struct sock *__l2cap_get_sock_by_addr(__le16 psm, bdaddr_t *src)
-{
-	struct sock *sk;
-	struct hlist_node *node;
-	sk_for_each(sk, node, &l2cap_sk_list.head)
-		if (l2cap_pi(sk)->sport == psm && !bacmp(&bt_sk(sk)->src, src))
-			goto found;
-	sk = NULL;
-found:
-	return sk;
-}
 
 /* Find socket with psm and source bdaddr.
  * Returns closest match.
@@ -859,70 +848,6 @@ static void l2cap_sock_close(struct sock *sk)
 	l2cap_sock_kill(sk);
 }
 
-int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
-{
-	struct sock *sk = sock->sk;
-	struct sockaddr_l2 la;
-	int len, err = 0;
-
-	BT_DBG("sk %p", sk);
-
-	if (!addr || addr->sa_family != AF_BLUETOOTH)
-		return -EINVAL;
-
-	memset(&la, 0, sizeof(la));
-	len = min_t(unsigned int, sizeof(la), alen);
-	memcpy(&la, addr, len);
-
-	if (la.l2_cid)
-		return -EINVAL;
-
-	lock_sock(sk);
-
-	if (sk->sk_state != BT_OPEN) {
-		err = -EBADFD;
-		goto done;
-	}
-
-	if (la.l2_psm) {
-		__u16 psm = __le16_to_cpu(la.l2_psm);
-
-		/* PSM must be odd and lsb of upper byte must be 0 */
-		if ((psm & 0x0101) != 0x0001) {
-			err = -EINVAL;
-			goto done;
-		}
-
-		/* Restrict usage of well-known PSMs */
-		if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) {
-			err = -EACCES;
-			goto done;
-		}
-	}
-
-	write_lock_bh(&l2cap_sk_list.lock);
-
-	if (la.l2_psm && __l2cap_get_sock_by_addr(la.l2_psm, &la.l2_bdaddr)) {
-		err = -EADDRINUSE;
-	} else {
-		/* Save source address */
-		bacpy(&bt_sk(sk)->src, &la.l2_bdaddr);
-		l2cap_pi(sk)->psm   = la.l2_psm;
-		l2cap_pi(sk)->sport = la.l2_psm;
-		sk->sk_state = BT_BOUND;
-
-		if (__le16_to_cpu(la.l2_psm) == 0x0001 ||
-					__le16_to_cpu(la.l2_psm) == 0x0003)
-			l2cap_pi(sk)->sec_level = BT_SECURITY_SDP;
-	}
-
-	write_unlock_bh(&l2cap_sk_list.lock);
-
-done:
-	release_sock(sk);
-	return err;
-}
-
 static int l2cap_do_connect(struct sock *sk)
 {
 	bdaddr_t *src = &bt_sk(sk)->src;
@@ -1068,65 +993,6 @@ done:
 	return err;
 }
 
-int l2cap_sock_listen(struct socket *sock, int backlog)
-{
-	struct sock *sk = sock->sk;
-	int err = 0;
-
-	BT_DBG("sk %p backlog %d", sk, backlog);
-
-	lock_sock(sk);
-
-	if ((sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM)
-			|| sk->sk_state != BT_BOUND) {
-		err = -EBADFD;
-		goto done;
-	}
-
-	switch (l2cap_pi(sk)->mode) {
-	case L2CAP_MODE_BASIC:
-		break;
-	case L2CAP_MODE_ERTM:
-	case L2CAP_MODE_STREAMING:
-		if (!disable_ertm)
-			break;
-		/* fall through */
-	default:
-		err = -ENOTSUPP;
-		goto done;
-	}
-
-	if (!l2cap_pi(sk)->psm) {
-		bdaddr_t *src = &bt_sk(sk)->src;
-		u16 psm;
-
-		err = -EINVAL;
-
-		write_lock_bh(&l2cap_sk_list.lock);
-
-		for (psm = 0x1001; psm < 0x1100; psm += 2)
-			if (!__l2cap_get_sock_by_addr(cpu_to_le16(psm), src)) {
-				l2cap_pi(sk)->psm   = cpu_to_le16(psm);
-				l2cap_pi(sk)->sport = cpu_to_le16(psm);
-				err = 0;
-				break;
-			}
-
-		write_unlock_bh(&l2cap_sk_list.lock);
-
-		if (err < 0)
-			goto done;
-	}
-
-	sk->sk_max_ack_backlog = backlog;
-	sk->sk_ack_backlog = 0;
-	sk->sk_state = BT_LISTEN;
-
-done:
-	release_sock(sk);
-	return err;
-}
-
 int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags)
 {
 	DECLARE_WAITQUEUE(wait, current);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 20efd240a786..ef9a60fda495 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -62,6 +62,141 @@ static void l2cap_sock_timeout(unsigned long arg)
 	sock_put(sk);
 }
 
+static struct sock *__l2cap_get_sock_by_addr(__le16 psm, bdaddr_t *src)
+{
+	struct sock *sk;
+	struct hlist_node *node;
+	sk_for_each(sk, node, &l2cap_sk_list.head)
+		if (l2cap_pi(sk)->sport == psm && !bacmp(&bt_sk(sk)->src, src))
+			goto found;
+	sk = NULL;
+found:
+	return sk;
+}
+
+static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_l2 la;
+	int len, err = 0;
+
+	BT_DBG("sk %p", sk);
+
+	if (!addr || addr->sa_family != AF_BLUETOOTH)
+		return -EINVAL;
+
+	memset(&la, 0, sizeof(la));
+	len = min_t(unsigned int, sizeof(la), alen);
+	memcpy(&la, addr, len);
+
+	if (la.l2_cid)
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	if (sk->sk_state != BT_OPEN) {
+		err = -EBADFD;
+		goto done;
+	}
+
+	if (la.l2_psm) {
+		__u16 psm = __le16_to_cpu(la.l2_psm);
+
+		/* PSM must be odd and lsb of upper byte must be 0 */
+		if ((psm & 0x0101) != 0x0001) {
+			err = -EINVAL;
+			goto done;
+		}
+
+		/* Restrict usage of well-known PSMs */
+		if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) {
+			err = -EACCES;
+			goto done;
+		}
+	}
+
+	write_lock_bh(&l2cap_sk_list.lock);
+
+	if (la.l2_psm && __l2cap_get_sock_by_addr(la.l2_psm, &la.l2_bdaddr)) {
+		err = -EADDRINUSE;
+	} else {
+		/* Save source address */
+		bacpy(&bt_sk(sk)->src, &la.l2_bdaddr);
+		l2cap_pi(sk)->psm   = la.l2_psm;
+		l2cap_pi(sk)->sport = la.l2_psm;
+		sk->sk_state = BT_BOUND;
+
+		if (__le16_to_cpu(la.l2_psm) == 0x0001 ||
+					__le16_to_cpu(la.l2_psm) == 0x0003)
+			l2cap_pi(sk)->sec_level = BT_SECURITY_SDP;
+	}
+
+	write_unlock_bh(&l2cap_sk_list.lock);
+
+done:
+	release_sock(sk);
+	return err;
+}
+
+static int l2cap_sock_listen(struct socket *sock, int backlog)
+{
+	struct sock *sk = sock->sk;
+	int err = 0;
+
+	BT_DBG("sk %p backlog %d", sk, backlog);
+
+	lock_sock(sk);
+
+	if ((sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM)
+			|| sk->sk_state != BT_BOUND) {
+		err = -EBADFD;
+		goto done;
+	}
+
+	switch (l2cap_pi(sk)->mode) {
+	case L2CAP_MODE_BASIC:
+		break;
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		if (!disable_ertm)
+			break;
+		/* fall through */
+	default:
+		err = -ENOTSUPP;
+		goto done;
+	}
+
+	if (!l2cap_pi(sk)->psm) {
+		bdaddr_t *src = &bt_sk(sk)->src;
+		u16 psm;
+
+		err = -EINVAL;
+
+		write_lock_bh(&l2cap_sk_list.lock);
+
+		for (psm = 0x1001; psm < 0x1100; psm += 2)
+			if (!__l2cap_get_sock_by_addr(cpu_to_le16(psm), src)) {
+				l2cap_pi(sk)->psm   = cpu_to_le16(psm);
+				l2cap_pi(sk)->sport = cpu_to_le16(psm);
+				err = 0;
+				break;
+			}
+
+		write_unlock_bh(&l2cap_sk_list.lock);
+
+		if (err < 0)
+			goto done;
+	}
+
+	sk->sk_max_ack_backlog = backlog;
+	sk->sk_ack_backlog = 0;
+	sk->sk_state = BT_LISTEN;
+
+done:
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From c47b7c724bc7106acf602b2ce99922a2d14ea62b Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:42:23 -0200
Subject: Bluetooth: move l2cap_sock_accept() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  1 -
 net/bluetooth/l2cap_core.c    | 56 -------------------------------------------
 net/bluetooth/l2cap_sock.c    | 56 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 3ca4fe30d75e..7921b6b980cb 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -439,7 +439,6 @@ struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
 
 int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags);
-int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags);
 int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer);
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
 int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 6af38722d5cb..ff6a54ffed89 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -993,62 +993,6 @@ done:
 	return err;
 }
 
-int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags)
-{
-	DECLARE_WAITQUEUE(wait, current);
-	struct sock *sk = sock->sk, *nsk;
-	long timeo;
-	int err = 0;
-
-	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
-
-	if (sk->sk_state != BT_LISTEN) {
-		err = -EBADFD;
-		goto done;
-	}
-
-	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
-
-	BT_DBG("sk %p timeo %ld", sk, timeo);
-
-	/* Wait for an incoming connection. (wake-one). */
-	add_wait_queue_exclusive(sk_sleep(sk), &wait);
-	while (!(nsk = bt_accept_dequeue(sk, newsock))) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (!timeo) {
-			err = -EAGAIN;
-			break;
-		}
-
-		release_sock(sk);
-		timeo = schedule_timeout(timeo);
-		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
-
-		if (sk->sk_state != BT_LISTEN) {
-			err = -EBADFD;
-			break;
-		}
-
-		if (signal_pending(current)) {
-			err = sock_intr_errno(timeo);
-			break;
-		}
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(sk_sleep(sk), &wait);
-
-	if (err)
-		goto done;
-
-	newsock->state = SS_CONNECTED;
-
-	BT_DBG("new socket %p", nsk);
-
-done:
-	release_sock(sk);
-	return err;
-}
-
 int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer)
 {
 	struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index ef9a60fda495..b19a386332fc 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -197,6 +197,62 @@ done:
 	return err;
 }
 
+static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	struct sock *sk = sock->sk, *nsk;
+	long timeo;
+	int err = 0;
+
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+
+	if (sk->sk_state != BT_LISTEN) {
+		err = -EBADFD;
+		goto done;
+	}
+
+	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
+
+	BT_DBG("sk %p timeo %ld", sk, timeo);
+
+	/* Wait for an incoming connection. (wake-one). */
+	add_wait_queue_exclusive(sk_sleep(sk), &wait);
+	while (!(nsk = bt_accept_dequeue(sk, newsock))) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!timeo) {
+			err = -EAGAIN;
+			break;
+		}
+
+		release_sock(sk);
+		timeo = schedule_timeout(timeo);
+		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+
+		if (sk->sk_state != BT_LISTEN) {
+			err = -EBADFD;
+			break;
+		}
+
+		if (signal_pending(current)) {
+			err = sock_intr_errno(timeo);
+			break;
+		}
+	}
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	if (err)
+		goto done;
+
+	newsock->state = SS_CONNECTED;
+
+	BT_DBG("new socket %p", nsk);
+
+done:
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From d7175d55255cb0a576844bc6e986000e0d7f8e9d Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:43:46 -0200
Subject: Bluetooth: move l2cap_sock_getname() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  1 -
 net/bluetooth/l2cap_core.c    | 23 -----------------------
 net/bluetooth/l2cap_sock.c    | 23 +++++++++++++++++++++++
 3 files changed, 23 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 7921b6b980cb..0d0c18014a54 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -439,7 +439,6 @@ struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
 
 int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags);
-int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer);
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
 int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
 int l2cap_sock_shutdown(struct socket *sock, int how);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ff6a54ffed89..bd46cacc165a 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -993,29 +993,6 @@ done:
 	return err;
 }
 
-int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer)
-{
-	struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
-	struct sock *sk = sock->sk;
-
-	BT_DBG("sock %p, sk %p", sock, sk);
-
-	addr->sa_family = AF_BLUETOOTH;
-	*len = sizeof(struct sockaddr_l2);
-
-	if (peer) {
-		la->l2_psm = l2cap_pi(sk)->psm;
-		bacpy(&la->l2_bdaddr, &bt_sk(sk)->dst);
-		la->l2_cid = cpu_to_le16(l2cap_pi(sk)->dcid);
-	} else {
-		la->l2_psm = l2cap_pi(sk)->sport;
-		bacpy(&la->l2_bdaddr, &bt_sk(sk)->src);
-		la->l2_cid = cpu_to_le16(l2cap_pi(sk)->scid);
-	}
-
-	return 0;
-}
-
 static int __l2cap_wait_ack(struct sock *sk)
 {
 	DECLARE_WAITQUEUE(wait, current);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index b19a386332fc..4c13f8bc1b18 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -253,6 +253,29 @@ done:
 	return err;
 }
 
+static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer)
+{
+	struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr;
+	struct sock *sk = sock->sk;
+
+	BT_DBG("sock %p, sk %p", sock, sk);
+
+	addr->sa_family = AF_BLUETOOTH;
+	*len = sizeof(struct sockaddr_l2);
+
+	if (peer) {
+		la->l2_psm = l2cap_pi(sk)->psm;
+		bacpy(&la->l2_bdaddr, &bt_sk(sk)->dst);
+		la->l2_cid = cpu_to_le16(l2cap_pi(sk)->dcid);
+	} else {
+		la->l2_psm = l2cap_pi(sk)->sport;
+		bacpy(&la->l2_bdaddr, &bt_sk(sk)->src);
+		la->l2_cid = cpu_to_le16(l2cap_pi(sk)->scid);
+	}
+
+	return 0;
+}
+
 static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From 33575df7be6748292f88453f29319af6d639c5c8 Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:48:48 -0200
Subject: Bluetooth: move l2cap_sock_setsockopt() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |   1 -
 net/bluetooth/l2cap_core.c    | 174 -----------------------------------------
 net/bluetooth/l2cap_sock.c    | 175 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 175 insertions(+), 175 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 0d0c18014a54..901ecbe573a3 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -442,7 +442,6 @@ int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
 int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
 int l2cap_sock_shutdown(struct socket *sock, int how);
-int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen);
 int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen);
 
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index bd46cacc165a..9d35cafe18aa 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1596,180 +1596,6 @@ int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m
 	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
 }
 
-static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen)
-{
-	struct sock *sk = sock->sk;
-	struct l2cap_options opts;
-	int len, err = 0;
-	u32 opt;
-
-	BT_DBG("sk %p", sk);
-
-	lock_sock(sk);
-
-	switch (optname) {
-	case L2CAP_OPTIONS:
-		if (sk->sk_state == BT_CONNECTED) {
-			err = -EINVAL;
-			break;
-		}
-
-		opts.imtu     = l2cap_pi(sk)->imtu;
-		opts.omtu     = l2cap_pi(sk)->omtu;
-		opts.flush_to = l2cap_pi(sk)->flush_to;
-		opts.mode     = l2cap_pi(sk)->mode;
-		opts.fcs      = l2cap_pi(sk)->fcs;
-		opts.max_tx   = l2cap_pi(sk)->max_tx;
-		opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win;
-
-		len = min_t(unsigned int, sizeof(opts), optlen);
-		if (copy_from_user((char *) &opts, optval, len)) {
-			err = -EFAULT;
-			break;
-		}
-
-		if (opts.txwin_size > L2CAP_DEFAULT_TX_WINDOW) {
-			err = -EINVAL;
-			break;
-		}
-
-		l2cap_pi(sk)->mode = opts.mode;
-		switch (l2cap_pi(sk)->mode) {
-		case L2CAP_MODE_BASIC:
-			l2cap_pi(sk)->conf_state &= ~L2CAP_CONF_STATE2_DEVICE;
-			break;
-		case L2CAP_MODE_ERTM:
-		case L2CAP_MODE_STREAMING:
-			if (!disable_ertm)
-				break;
-			/* fall through */
-		default:
-			err = -EINVAL;
-			break;
-		}
-
-		l2cap_pi(sk)->imtu = opts.imtu;
-		l2cap_pi(sk)->omtu = opts.omtu;
-		l2cap_pi(sk)->fcs  = opts.fcs;
-		l2cap_pi(sk)->max_tx = opts.max_tx;
-		l2cap_pi(sk)->tx_win = (__u8)opts.txwin_size;
-		break;
-
-	case L2CAP_LM:
-		if (get_user(opt, (u32 __user *) optval)) {
-			err = -EFAULT;
-			break;
-		}
-
-		if (opt & L2CAP_LM_AUTH)
-			l2cap_pi(sk)->sec_level = BT_SECURITY_LOW;
-		if (opt & L2CAP_LM_ENCRYPT)
-			l2cap_pi(sk)->sec_level = BT_SECURITY_MEDIUM;
-		if (opt & L2CAP_LM_SECURE)
-			l2cap_pi(sk)->sec_level = BT_SECURITY_HIGH;
-
-		l2cap_pi(sk)->role_switch    = (opt & L2CAP_LM_MASTER);
-		l2cap_pi(sk)->force_reliable = (opt & L2CAP_LM_RELIABLE);
-		break;
-
-	default:
-		err = -ENOPROTOOPT;
-		break;
-	}
-
-	release_sock(sk);
-	return err;
-}
-
-int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
-{
-	struct sock *sk = sock->sk;
-	struct bt_security sec;
-	int len, err = 0;
-	u32 opt;
-
-	BT_DBG("sk %p", sk);
-
-	if (level == SOL_L2CAP)
-		return l2cap_sock_setsockopt_old(sock, optname, optval, optlen);
-
-	if (level != SOL_BLUETOOTH)
-		return -ENOPROTOOPT;
-
-	lock_sock(sk);
-
-	switch (optname) {
-	case BT_SECURITY:
-		if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
-				&& sk->sk_type != SOCK_RAW) {
-			err = -EINVAL;
-			break;
-		}
-
-		sec.level = BT_SECURITY_LOW;
-
-		len = min_t(unsigned int, sizeof(sec), optlen);
-		if (copy_from_user((char *) &sec, optval, len)) {
-			err = -EFAULT;
-			break;
-		}
-
-		if (sec.level < BT_SECURITY_LOW ||
-					sec.level > BT_SECURITY_HIGH) {
-			err = -EINVAL;
-			break;
-		}
-
-		l2cap_pi(sk)->sec_level = sec.level;
-		break;
-
-	case BT_DEFER_SETUP:
-		if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
-			err = -EINVAL;
-			break;
-		}
-
-		if (get_user(opt, (u32 __user *) optval)) {
-			err = -EFAULT;
-			break;
-		}
-
-		bt_sk(sk)->defer_setup = opt;
-		break;
-
-	case BT_FLUSHABLE:
-		if (get_user(opt, (u32 __user *) optval)) {
-			err = -EFAULT;
-			break;
-		}
-
-		if (opt > BT_FLUSHABLE_ON) {
-			err = -EINVAL;
-			break;
-		}
-
-		if (opt == BT_FLUSHABLE_OFF) {
-			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
-			/* proceed futher only when we have l2cap_conn and
-			   No Flush support in the LM */
-			if (!conn || !lmp_no_flush_capable(conn->hcon->hdev)) {
-				err = -EINVAL;
-				break;
-			}
-		}
-
-		l2cap_pi(sk)->flushable = opt;
-		break;
-
-	default:
-		err = -ENOPROTOOPT;
-		break;
-	}
-
-	release_sock(sk);
-	return err;
-}
-
 static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
 {
 	struct sock *sk = sock->sk;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 4c13f8bc1b18..1bbe8a06189b 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -27,6 +27,7 @@
 /* Bluetooth L2CAP sockets. */
 
 #include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 
 static void l2cap_sock_timeout(unsigned long arg)
@@ -276,6 +277,180 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l
 	return 0;
 }
 
+static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct l2cap_options opts;
+	int len, err = 0;
+	u32 opt;
+
+	BT_DBG("sk %p", sk);
+
+	lock_sock(sk);
+
+	switch (optname) {
+	case L2CAP_OPTIONS:
+		if (sk->sk_state == BT_CONNECTED) {
+			err = -EINVAL;
+			break;
+		}
+
+		opts.imtu     = l2cap_pi(sk)->imtu;
+		opts.omtu     = l2cap_pi(sk)->omtu;
+		opts.flush_to = l2cap_pi(sk)->flush_to;
+		opts.mode     = l2cap_pi(sk)->mode;
+		opts.fcs      = l2cap_pi(sk)->fcs;
+		opts.max_tx   = l2cap_pi(sk)->max_tx;
+		opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win;
+
+		len = min_t(unsigned int, sizeof(opts), optlen);
+		if (copy_from_user((char *) &opts, optval, len)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (opts.txwin_size > L2CAP_DEFAULT_TX_WINDOW) {
+			err = -EINVAL;
+			break;
+		}
+
+		l2cap_pi(sk)->mode = opts.mode;
+		switch (l2cap_pi(sk)->mode) {
+		case L2CAP_MODE_BASIC:
+			l2cap_pi(sk)->conf_state &= ~L2CAP_CONF_STATE2_DEVICE;
+			break;
+		case L2CAP_MODE_ERTM:
+		case L2CAP_MODE_STREAMING:
+			if (!disable_ertm)
+				break;
+			/* fall through */
+		default:
+			err = -EINVAL;
+			break;
+		}
+
+		l2cap_pi(sk)->imtu = opts.imtu;
+		l2cap_pi(sk)->omtu = opts.omtu;
+		l2cap_pi(sk)->fcs  = opts.fcs;
+		l2cap_pi(sk)->max_tx = opts.max_tx;
+		l2cap_pi(sk)->tx_win = (__u8)opts.txwin_size;
+		break;
+
+	case L2CAP_LM:
+		if (get_user(opt, (u32 __user *) optval)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (opt & L2CAP_LM_AUTH)
+			l2cap_pi(sk)->sec_level = BT_SECURITY_LOW;
+		if (opt & L2CAP_LM_ENCRYPT)
+			l2cap_pi(sk)->sec_level = BT_SECURITY_MEDIUM;
+		if (opt & L2CAP_LM_SECURE)
+			l2cap_pi(sk)->sec_level = BT_SECURITY_HIGH;
+
+		l2cap_pi(sk)->role_switch    = (opt & L2CAP_LM_MASTER);
+		l2cap_pi(sk)->force_reliable = (opt & L2CAP_LM_RELIABLE);
+		break;
+
+	default:
+		err = -ENOPROTOOPT;
+		break;
+	}
+
+	release_sock(sk);
+	return err;
+}
+
+static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct bt_security sec;
+	int len, err = 0;
+	u32 opt;
+
+	BT_DBG("sk %p", sk);
+
+	if (level == SOL_L2CAP)
+		return l2cap_sock_setsockopt_old(sock, optname, optval, optlen);
+
+	if (level != SOL_BLUETOOTH)
+		return -ENOPROTOOPT;
+
+	lock_sock(sk);
+
+	switch (optname) {
+	case BT_SECURITY:
+		if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
+				&& sk->sk_type != SOCK_RAW) {
+			err = -EINVAL;
+			break;
+		}
+
+		sec.level = BT_SECURITY_LOW;
+
+		len = min_t(unsigned int, sizeof(sec), optlen);
+		if (copy_from_user((char *) &sec, optval, len)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (sec.level < BT_SECURITY_LOW ||
+					sec.level > BT_SECURITY_HIGH) {
+			err = -EINVAL;
+			break;
+		}
+
+		l2cap_pi(sk)->sec_level = sec.level;
+		break;
+
+	case BT_DEFER_SETUP:
+		if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (get_user(opt, (u32 __user *) optval)) {
+			err = -EFAULT;
+			break;
+		}
+
+		bt_sk(sk)->defer_setup = opt;
+		break;
+
+	case BT_FLUSHABLE:
+		if (get_user(opt, (u32 __user *) optval)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (opt > BT_FLUSHABLE_ON) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (opt == BT_FLUSHABLE_OFF) {
+			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+			/* proceed futher only when we have l2cap_conn and
+			   No Flush support in the LM */
+			if (!conn || !lmp_no_flush_capable(conn->hcon->hdev)) {
+				err = -EINVAL;
+				break;
+			}
+		}
+
+		l2cap_pi(sk)->flushable = opt;
+		break;
+
+	default:
+		err = -ENOPROTOOPT;
+		break;
+	}
+
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From 99f4808db0c052f3c92a689ec2841618bf2ce14a Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:52:55 -0200
Subject: Bluetooth: move l2cap_sock_getsockopt() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |   1 -
 net/bluetooth/l2cap_core.c    | 145 ------------------------------------------
 net/bluetooth/l2cap_sock.c    | 145 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 145 insertions(+), 146 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 901ecbe573a3..1905aad4ba0a 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -442,7 +442,6 @@ int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
 int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
 int l2cap_sock_shutdown(struct socket *sock, int how);
-int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen);
 
 
 void l2cap_load(void);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 9d35cafe18aa..8e015d971267 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1596,151 +1596,6 @@ int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m
 	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
 }
 
-static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
-{
-	struct sock *sk = sock->sk;
-	struct l2cap_options opts;
-	struct l2cap_conninfo cinfo;
-	int len, err = 0;
-	u32 opt;
-
-	BT_DBG("sk %p", sk);
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	lock_sock(sk);
-
-	switch (optname) {
-	case L2CAP_OPTIONS:
-		opts.imtu     = l2cap_pi(sk)->imtu;
-		opts.omtu     = l2cap_pi(sk)->omtu;
-		opts.flush_to = l2cap_pi(sk)->flush_to;
-		opts.mode     = l2cap_pi(sk)->mode;
-		opts.fcs      = l2cap_pi(sk)->fcs;
-		opts.max_tx   = l2cap_pi(sk)->max_tx;
-		opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win;
-
-		len = min_t(unsigned int, len, sizeof(opts));
-		if (copy_to_user(optval, (char *) &opts, len))
-			err = -EFAULT;
-
-		break;
-
-	case L2CAP_LM:
-		switch (l2cap_pi(sk)->sec_level) {
-		case BT_SECURITY_LOW:
-			opt = L2CAP_LM_AUTH;
-			break;
-		case BT_SECURITY_MEDIUM:
-			opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT;
-			break;
-		case BT_SECURITY_HIGH:
-			opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT |
-							L2CAP_LM_SECURE;
-			break;
-		default:
-			opt = 0;
-			break;
-		}
-
-		if (l2cap_pi(sk)->role_switch)
-			opt |= L2CAP_LM_MASTER;
-
-		if (l2cap_pi(sk)->force_reliable)
-			opt |= L2CAP_LM_RELIABLE;
-
-		if (put_user(opt, (u32 __user *) optval))
-			err = -EFAULT;
-		break;
-
-	case L2CAP_CONNINFO:
-		if (sk->sk_state != BT_CONNECTED &&
-					!(sk->sk_state == BT_CONNECT2 &&
-						bt_sk(sk)->defer_setup)) {
-			err = -ENOTCONN;
-			break;
-		}
-
-		cinfo.hci_handle = l2cap_pi(sk)->conn->hcon->handle;
-		memcpy(cinfo.dev_class, l2cap_pi(sk)->conn->hcon->dev_class, 3);
-
-		len = min_t(unsigned int, len, sizeof(cinfo));
-		if (copy_to_user(optval, (char *) &cinfo, len))
-			err = -EFAULT;
-
-		break;
-
-	default:
-		err = -ENOPROTOOPT;
-		break;
-	}
-
-	release_sock(sk);
-	return err;
-}
-
-int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
-{
-	struct sock *sk = sock->sk;
-	struct bt_security sec;
-	int len, err = 0;
-
-	BT_DBG("sk %p", sk);
-
-	if (level == SOL_L2CAP)
-		return l2cap_sock_getsockopt_old(sock, optname, optval, optlen);
-
-	if (level != SOL_BLUETOOTH)
-		return -ENOPROTOOPT;
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	lock_sock(sk);
-
-	switch (optname) {
-	case BT_SECURITY:
-		if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
-				&& sk->sk_type != SOCK_RAW) {
-			err = -EINVAL;
-			break;
-		}
-
-		sec.level = l2cap_pi(sk)->sec_level;
-
-		len = min_t(unsigned int, len, sizeof(sec));
-		if (copy_to_user(optval, (char *) &sec, len))
-			err = -EFAULT;
-
-		break;
-
-	case BT_DEFER_SETUP:
-		if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
-			err = -EINVAL;
-			break;
-		}
-
-		if (put_user(bt_sk(sk)->defer_setup, (u32 __user *) optval))
-			err = -EFAULT;
-
-		break;
-
-	case BT_FLUSHABLE:
-		if (put_user(l2cap_pi(sk)->flushable, (u32 __user *) optval))
-			err = -EFAULT;
-
-		break;
-
-	default:
-		err = -ENOPROTOOPT;
-		break;
-	}
-
-	release_sock(sk);
-	return err;
-}
-
 int l2cap_sock_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1bbe8a06189b..b7d5ae9c6bdf 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -277,6 +277,151 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l
 	return 0;
 }
 
+static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
+{
+	struct sock *sk = sock->sk;
+	struct l2cap_options opts;
+	struct l2cap_conninfo cinfo;
+	int len, err = 0;
+	u32 opt;
+
+	BT_DBG("sk %p", sk);
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	lock_sock(sk);
+
+	switch (optname) {
+	case L2CAP_OPTIONS:
+		opts.imtu     = l2cap_pi(sk)->imtu;
+		opts.omtu     = l2cap_pi(sk)->omtu;
+		opts.flush_to = l2cap_pi(sk)->flush_to;
+		opts.mode     = l2cap_pi(sk)->mode;
+		opts.fcs      = l2cap_pi(sk)->fcs;
+		opts.max_tx   = l2cap_pi(sk)->max_tx;
+		opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win;
+
+		len = min_t(unsigned int, len, sizeof(opts));
+		if (copy_to_user(optval, (char *) &opts, len))
+			err = -EFAULT;
+
+		break;
+
+	case L2CAP_LM:
+		switch (l2cap_pi(sk)->sec_level) {
+		case BT_SECURITY_LOW:
+			opt = L2CAP_LM_AUTH;
+			break;
+		case BT_SECURITY_MEDIUM:
+			opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT;
+			break;
+		case BT_SECURITY_HIGH:
+			opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT |
+							L2CAP_LM_SECURE;
+			break;
+		default:
+			opt = 0;
+			break;
+		}
+
+		if (l2cap_pi(sk)->role_switch)
+			opt |= L2CAP_LM_MASTER;
+
+		if (l2cap_pi(sk)->force_reliable)
+			opt |= L2CAP_LM_RELIABLE;
+
+		if (put_user(opt, (u32 __user *) optval))
+			err = -EFAULT;
+		break;
+
+	case L2CAP_CONNINFO:
+		if (sk->sk_state != BT_CONNECTED &&
+					!(sk->sk_state == BT_CONNECT2 &&
+						bt_sk(sk)->defer_setup)) {
+			err = -ENOTCONN;
+			break;
+		}
+
+		cinfo.hci_handle = l2cap_pi(sk)->conn->hcon->handle;
+		memcpy(cinfo.dev_class, l2cap_pi(sk)->conn->hcon->dev_class, 3);
+
+		len = min_t(unsigned int, len, sizeof(cinfo));
+		if (copy_to_user(optval, (char *) &cinfo, len))
+			err = -EFAULT;
+
+		break;
+
+	default:
+		err = -ENOPROTOOPT;
+		break;
+	}
+
+	release_sock(sk);
+	return err;
+}
+
+static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen)
+{
+	struct sock *sk = sock->sk;
+	struct bt_security sec;
+	int len, err = 0;
+
+	BT_DBG("sk %p", sk);
+
+	if (level == SOL_L2CAP)
+		return l2cap_sock_getsockopt_old(sock, optname, optval, optlen);
+
+	if (level != SOL_BLUETOOTH)
+		return -ENOPROTOOPT;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	lock_sock(sk);
+
+	switch (optname) {
+	case BT_SECURITY:
+		if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM
+				&& sk->sk_type != SOCK_RAW) {
+			err = -EINVAL;
+			break;
+		}
+
+		sec.level = l2cap_pi(sk)->sec_level;
+
+		len = min_t(unsigned int, len, sizeof(sec));
+		if (copy_to_user(optval, (char *) &sec, len))
+			err = -EFAULT;
+
+		break;
+
+	case BT_DEFER_SETUP:
+		if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (put_user(bt_sk(sk)->defer_setup, (u32 __user *) optval))
+			err = -EFAULT;
+
+		break;
+
+	case BT_FLUSHABLE:
+		if (put_user(l2cap_pi(sk)->flushable, (u32 __user *) optval))
+			err = -EFAULT;
+
+		break;
+
+	default:
+		err = -ENOPROTOOPT;
+		break;
+	}
+
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From 4e34c50bfe5ba87da1622cc7c6ed10712da255ad Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 02:56:13 -0200
Subject: Bluetooth: move l2cap_sock_connect() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  2 +-
 net/bluetooth/l2cap_core.c    | 87 +------------------------------------------
 net/bluetooth/l2cap_sock.c    | 85 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 87 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1905aad4ba0a..b5ebf878ca22 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -437,8 +437,8 @@ void l2cap_sock_kill(struct sock *sk);
 void l2cap_sock_init(struct sock *sk, struct sock *parent);
 struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
+int l2cap_do_connect(struct sock *sk);
 
-int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags);
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
 int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
 int l2cap_sock_shutdown(struct socket *sock, int how);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 8e015d971267..97327457b52d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -848,7 +848,7 @@ static void l2cap_sock_close(struct sock *sk)
 	l2cap_sock_kill(sk);
 }
 
-static int l2cap_do_connect(struct sock *sk)
+int l2cap_do_connect(struct sock *sk)
 {
 	bdaddr_t *src = &bt_sk(sk)->src;
 	bdaddr_t *dst = &bt_sk(sk)->dst;
@@ -908,91 +908,6 @@ done:
 	return err;
 }
 
-int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags)
-{
-	struct sock *sk = sock->sk;
-	struct sockaddr_l2 la;
-	int len, err = 0;
-
-	BT_DBG("sk %p", sk);
-
-	if (!addr || alen < sizeof(addr->sa_family) ||
-	    addr->sa_family != AF_BLUETOOTH)
-		return -EINVAL;
-
-	memset(&la, 0, sizeof(la));
-	len = min_t(unsigned int, sizeof(la), alen);
-	memcpy(&la, addr, len);
-
-	if (la.l2_cid)
-		return -EINVAL;
-
-	lock_sock(sk);
-
-	if ((sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM)
-			&& !la.l2_psm) {
-		err = -EINVAL;
-		goto done;
-	}
-
-	switch (l2cap_pi(sk)->mode) {
-	case L2CAP_MODE_BASIC:
-		break;
-	case L2CAP_MODE_ERTM:
-	case L2CAP_MODE_STREAMING:
-		if (!disable_ertm)
-			break;
-		/* fall through */
-	default:
-		err = -ENOTSUPP;
-		goto done;
-	}
-
-	switch (sk->sk_state) {
-	case BT_CONNECT:
-	case BT_CONNECT2:
-	case BT_CONFIG:
-		/* Already connecting */
-		goto wait;
-
-	case BT_CONNECTED:
-		/* Already connected */
-		err = -EISCONN;
-		goto done;
-
-	case BT_OPEN:
-	case BT_BOUND:
-		/* Can connect */
-		break;
-
-	default:
-		err = -EBADFD;
-		goto done;
-	}
-
-	/* PSM must be odd and lsb of upper byte must be 0 */
-	if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 &&
-		sk->sk_type != SOCK_RAW) {
-		err = -EINVAL;
-		goto done;
-	}
-
-	/* Set destination address and psm */
-	bacpy(&bt_sk(sk)->dst, &la.l2_bdaddr);
-	l2cap_pi(sk)->psm = la.l2_psm;
-
-	err = l2cap_do_connect(sk);
-	if (err)
-		goto done;
-
-wait:
-	err = bt_sock_wait_state(sk, BT_CONNECTED,
-			sock_sndtimeo(sk, flags & O_NONBLOCK));
-done:
-	release_sock(sk);
-	return err;
-}
-
 static int __l2cap_wait_ack(struct sock *sk)
 {
 	DECLARE_WAITQUEUE(wait, current);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index b7d5ae9c6bdf..e2f14f1783f6 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -139,6 +139,91 @@ done:
 	return err;
 }
 
+static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_l2 la;
+	int len, err = 0;
+
+	BT_DBG("sk %p", sk);
+
+	if (!addr || alen < sizeof(addr->sa_family) ||
+	    addr->sa_family != AF_BLUETOOTH)
+		return -EINVAL;
+
+	memset(&la, 0, sizeof(la));
+	len = min_t(unsigned int, sizeof(la), alen);
+	memcpy(&la, addr, len);
+
+	if (la.l2_cid)
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	if ((sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM)
+			&& !la.l2_psm) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	switch (l2cap_pi(sk)->mode) {
+	case L2CAP_MODE_BASIC:
+		break;
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		if (!disable_ertm)
+			break;
+		/* fall through */
+	default:
+		err = -ENOTSUPP;
+		goto done;
+	}
+
+	switch (sk->sk_state) {
+	case BT_CONNECT:
+	case BT_CONNECT2:
+	case BT_CONFIG:
+		/* Already connecting */
+		goto wait;
+
+	case BT_CONNECTED:
+		/* Already connected */
+		err = -EISCONN;
+		goto done;
+
+	case BT_OPEN:
+	case BT_BOUND:
+		/* Can connect */
+		break;
+
+	default:
+		err = -EBADFD;
+		goto done;
+	}
+
+	/* PSM must be odd and lsb of upper byte must be 0 */
+	if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 &&
+		sk->sk_type != SOCK_RAW) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	/* Set destination address and psm */
+	bacpy(&bt_sk(sk)->dst, &la.l2_bdaddr);
+	l2cap_pi(sk)->psm = la.l2_psm;
+
+	err = l2cap_do_connect(sk);
+	if (err)
+		goto done;
+
+wait:
+	err = bt_sock_wait_state(sk, BT_CONNECTED,
+			sock_sndtimeo(sk, flags & O_NONBLOCK));
+done:
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From 6898325923f9571fbede3372dc490faa43b3258a Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 03:02:31 -0200
Subject: Bluetooth: move l2cap_sock_recvmsg() to l2cap_sock.c

It causes the move of the declaration of 3 functions to l2cap.h:
l2cap_get_ident(), l2cap_send_cmd(), l2cap_build_conf_req()

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  5 ++++-
 net/bluetooth/l2cap_core.c    | 49 +++----------------------------------------
 net/bluetooth/l2cap_sock.c    | 42 +++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index b5ebf878ca22..336b2af758b3 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -431,6 +431,10 @@ extern struct bt_sock_list l2cap_sk_list;
 int l2cap_init_sockets(void);
 void l2cap_cleanup_sockets(void);
 
+u8 l2cap_get_ident(struct l2cap_conn *conn);
+void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data);
+int l2cap_build_conf_req(struct sock *sk, void *data);
+
 void l2cap_sock_set_timer(struct sock *sk, long timeout);
 void __l2cap_sock_close(struct sock *sk, int reason);
 void l2cap_sock_kill(struct sock *sk);
@@ -440,7 +444,6 @@ struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 int l2cap_do_connect(struct sock *sk);
 
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
-int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags);
 int l2cap_sock_shutdown(struct socket *sock, int how);
 
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 97327457b52d..3a0e42be89ea 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -72,7 +72,6 @@ static void l2cap_busy_work(struct work_struct *work);
 
 static void l2cap_sock_close(struct sock *sk);
 
-static int l2cap_build_conf_req(struct sock *sk, void *data);
 static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 				u8 code, u8 ident, u16 dlen, void *data);
 
@@ -311,7 +310,7 @@ static inline int l2cap_check_security(struct sock *sk)
 								auth_type);
 }
 
-static inline u8 l2cap_get_ident(struct l2cap_conn *conn)
+u8 l2cap_get_ident(struct l2cap_conn *conn)
 {
 	u8 id;
 
@@ -333,7 +332,7 @@ static inline u8 l2cap_get_ident(struct l2cap_conn *conn)
 	return id;
 }
 
-static inline void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data)
+void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data)
 {
 	struct sk_buff *skb = l2cap_build_cmd(conn, code, ident, len, data);
 	u8 flags;
@@ -1469,48 +1468,6 @@ done:
 	return err;
 }
 
-int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
-{
-	struct sock *sk = sock->sk;
-
-	lock_sock(sk);
-
-	if (sk->sk_state == BT_CONNECT2 && bt_sk(sk)->defer_setup) {
-		struct l2cap_conn_rsp rsp;
-		struct l2cap_conn *conn = l2cap_pi(sk)->conn;
-		u8 buf[128];
-
-		sk->sk_state = BT_CONFIG;
-
-		rsp.scid   = cpu_to_le16(l2cap_pi(sk)->dcid);
-		rsp.dcid   = cpu_to_le16(l2cap_pi(sk)->scid);
-		rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
-		rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
-		l2cap_send_cmd(l2cap_pi(sk)->conn, l2cap_pi(sk)->ident,
-					L2CAP_CONN_RSP, sizeof(rsp), &rsp);
-
-		if (l2cap_pi(sk)->conf_state & L2CAP_CONF_REQ_SENT) {
-			release_sock(sk);
-			return 0;
-		}
-
-		l2cap_pi(sk)->conf_state |= L2CAP_CONF_REQ_SENT;
-		l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
-				l2cap_build_conf_req(sk, buf), buf);
-		l2cap_pi(sk)->num_conf_req++;
-
-		release_sock(sk);
-		return 0;
-	}
-
-	release_sock(sk);
-
-	if (sock->type == SOCK_STREAM)
-		return bt_sock_stream_recvmsg(iocb, sock, msg, len, flags);
-
-	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
-}
-
 int l2cap_sock_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
@@ -1760,7 +1717,7 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask)
 	}
 }
 
-static int l2cap_build_conf_req(struct sock *sk, void *data)
+int l2cap_build_conf_req(struct sock *sk, void *data)
 {
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
 	struct l2cap_conf_req *req = data;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index e2f14f1783f6..fa2bc5d85560 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -681,6 +681,48 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch
 	return err;
 }
 
+static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
+{
+	struct sock *sk = sock->sk;
+
+	lock_sock(sk);
+
+	if (sk->sk_state == BT_CONNECT2 && bt_sk(sk)->defer_setup) {
+		struct l2cap_conn_rsp rsp;
+		struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+		u8 buf[128];
+
+		sk->sk_state = BT_CONFIG;
+
+		rsp.scid   = cpu_to_le16(l2cap_pi(sk)->dcid);
+		rsp.dcid   = cpu_to_le16(l2cap_pi(sk)->scid);
+		rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
+		rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+		l2cap_send_cmd(l2cap_pi(sk)->conn, l2cap_pi(sk)->ident,
+					L2CAP_CONN_RSP, sizeof(rsp), &rsp);
+
+		if (l2cap_pi(sk)->conf_state & L2CAP_CONF_REQ_SENT) {
+			release_sock(sk);
+			return 0;
+		}
+
+		l2cap_pi(sk)->conf_state |= L2CAP_CONF_REQ_SENT;
+		l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
+				l2cap_build_conf_req(sk, buf), buf);
+		l2cap_pi(sk)->num_conf_req++;
+
+		release_sock(sk);
+		return 0;
+	}
+
+	release_sock(sk);
+
+	if (sock->type == SOCK_STREAM)
+		return bt_sock_stream_recvmsg(iocb, sock, msg, len, flags);
+
+	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
+}
+
 static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From dcba0dba54b566a08376f93cab35cdabd6abda20 Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 03:08:36 -0200
Subject: Bluetooth: move l2cap_sock_shutdown() to l2cap_sock.c

Declare __l2cap_wait_ack() and  l2cap_sock_clear_timer() in l2cap.h

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  3 ++-
 net/bluetooth/l2cap_core.c    | 35 ++---------------------------------
 net/bluetooth/l2cap_sock.c    | 31 +++++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 336b2af758b3..c9df0ef5b6f5 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -434,8 +434,10 @@ void l2cap_cleanup_sockets(void);
 u8 l2cap_get_ident(struct l2cap_conn *conn);
 void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data);
 int l2cap_build_conf_req(struct sock *sk, void *data);
+int __l2cap_wait_ack(struct sock *sk);
 
 void l2cap_sock_set_timer(struct sock *sk, long timeout);
+void l2cap_sock_clear_timer(struct sock *sk);
 void __l2cap_sock_close(struct sock *sk, int reason);
 void l2cap_sock_kill(struct sock *sk);
 void l2cap_sock_init(struct sock *sk, struct sock *parent);
@@ -444,7 +446,6 @@ struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 int l2cap_do_connect(struct sock *sk);
 
 int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
-int l2cap_sock_shutdown(struct socket *sock, int how);
 
 
 void l2cap_load(void);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 3a0e42be89ea..6e48e580555e 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -84,7 +84,7 @@ void l2cap_sock_set_timer(struct sock *sk, long timeout)
 	sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout);
 }
 
-static void l2cap_sock_clear_timer(struct sock *sk)
+void l2cap_sock_clear_timer(struct sock *sk)
 {
 	BT_DBG("sock %p state %d", sk, sk->sk_state);
 	sk_stop_timer(sk, &sk->sk_timer);
@@ -907,7 +907,7 @@ done:
 	return err;
 }
 
-static int __l2cap_wait_ack(struct sock *sk)
+int __l2cap_wait_ack(struct sock *sk)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	int err = 0;
@@ -1468,37 +1468,6 @@ done:
 	return err;
 }
 
-int l2cap_sock_shutdown(struct socket *sock, int how)
-{
-	struct sock *sk = sock->sk;
-	int err = 0;
-
-	BT_DBG("sock %p, sk %p", sock, sk);
-
-	if (!sk)
-		return 0;
-
-	lock_sock(sk);
-	if (!sk->sk_shutdown) {
-		if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM)
-			err = __l2cap_wait_ack(sk);
-
-		sk->sk_shutdown = SHUTDOWN_MASK;
-		l2cap_sock_clear_timer(sk);
-		__l2cap_sock_close(sk, 0);
-
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
-			err = bt_sock_wait_state(sk, BT_CLOSED,
-							sk->sk_lingertime);
-	}
-
-	if (!err && sk->sk_err)
-		err = -sk->sk_err;
-
-	release_sock(sk);
-	return err;
-}
-
 static void l2cap_chan_ready(struct sock *sk)
 {
 	struct sock *parent = bt_sk(sk)->parent;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index fa2bc5d85560..93af233bb167 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -723,6 +723,37 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms
 	return bt_sock_recvmsg(iocb, sock, msg, len, flags);
 }
 
+static int l2cap_sock_shutdown(struct socket *sock, int how)
+{
+	struct sock *sk = sock->sk;
+	int err = 0;
+
+	BT_DBG("sock %p, sk %p", sock, sk);
+
+	if (!sk)
+		return 0;
+
+	lock_sock(sk);
+	if (!sk->sk_shutdown) {
+		if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM)
+			err = __l2cap_wait_ack(sk);
+
+		sk->sk_shutdown = SHUTDOWN_MASK;
+		l2cap_sock_clear_timer(sk);
+		__l2cap_sock_close(sk, 0);
+
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+			err = bt_sock_wait_state(sk, BT_CLOSED,
+							sk->sk_lingertime);
+	}
+
+	if (!err && sk->sk_err)
+		err = -sk->sk_err;
+
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From fd83ccdb393e3190633e0240dd73faac8998164b Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 03:20:52 -0200
Subject: Bluetooth: move l2cap_sock_sendmsg() to l2cap_sock.c

Also moves some L2CAP sending functions declaration to l2cap.h

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  11 ++--
 net/bluetooth/l2cap_core.c    | 116 +++---------------------------------------
 net/bluetooth/l2cap_sock.c    | 102 +++++++++++++++++++++++++++++++++++++
 3 files changed, 117 insertions(+), 112 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index c9df0ef5b6f5..d4c93eded727 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -436,6 +436,14 @@ void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *d
 int l2cap_build_conf_req(struct sock *sk, void *data);
 int __l2cap_wait_ack(struct sock *sk);
 
+struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr *msg, size_t len);
+struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *msg, size_t len);
+struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *msg, size_t len, u16 control, u16 sdulen);
+int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, size_t len);
+void l2cap_do_send(struct sock *sk, struct sk_buff *skb);
+void l2cap_streaming_send(struct sock *sk);
+int l2cap_ertm_send(struct sock *sk);
+
 void l2cap_sock_set_timer(struct sock *sk, long timeout);
 void l2cap_sock_clear_timer(struct sock *sk);
 void __l2cap_sock_close(struct sock *sk, int reason);
@@ -445,9 +453,6 @@ struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
 int l2cap_do_connect(struct sock *sk);
 
-int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len);
-
-
 void l2cap_load(void);
 
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 6e48e580555e..da9b3a44b0f0 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -993,7 +993,7 @@ static void l2cap_drop_acked_frames(struct sock *sk)
 		del_timer(&l2cap_pi(sk)->retrans_timer);
 }
 
-static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb)
+void l2cap_do_send(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
 	struct hci_conn *hcon = pi->conn->hcon;
@@ -1009,7 +1009,7 @@ static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb)
 	hci_send_acl(hcon, skb, flags);
 }
 
-static void l2cap_streaming_send(struct sock *sk)
+void l2cap_streaming_send(struct sock *sk)
 {
 	struct sk_buff *skb;
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
@@ -1078,7 +1078,7 @@ static void l2cap_retransmit_one_frame(struct sock *sk, u8 tx_seq)
 	l2cap_do_send(sk, tx_skb);
 }
 
-static int l2cap_ertm_send(struct sock *sk)
+int l2cap_ertm_send(struct sock *sk)
 {
 	struct sk_buff *skb, *tx_skb;
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
@@ -1218,7 +1218,7 @@ static inline int l2cap_skbuff_fromiovec(struct sock *sk, struct msghdr *msg, in
 	return sent;
 }
 
-static struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr *msg, size_t len)
+struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct l2cap_conn *conn = l2cap_pi(sk)->conn;
 	struct sk_buff *skb;
@@ -1247,7 +1247,7 @@ static struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr
 	return skb;
 }
 
-static struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *msg, size_t len)
+struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct l2cap_conn *conn = l2cap_pi(sk)->conn;
 	struct sk_buff *skb;
@@ -1275,7 +1275,7 @@ static struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *ms
 	return skb;
 }
 
-static struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *msg, size_t len, u16 control, u16 sdulen)
+struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *msg, size_t len, u16 control, u16 sdulen)
 {
 	struct l2cap_conn *conn = l2cap_pi(sk)->conn;
 	struct sk_buff *skb;
@@ -1320,7 +1320,7 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *m
 	return skb;
 }
 
-static inline int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, size_t len)
+int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
 	struct sk_buff *skb;
@@ -1366,108 +1366,6 @@ static inline int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, siz
 	return size;
 }
 
-int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len)
-{
-	struct sock *sk = sock->sk;
-	struct l2cap_pinfo *pi = l2cap_pi(sk);
-	struct sk_buff *skb;
-	u16 control;
-	int err;
-
-	BT_DBG("sock %p, sk %p", sock, sk);
-
-	err = sock_error(sk);
-	if (err)
-		return err;
-
-	if (msg->msg_flags & MSG_OOB)
-		return -EOPNOTSUPP;
-
-	lock_sock(sk);
-
-	if (sk->sk_state != BT_CONNECTED) {
-		err = -ENOTCONN;
-		goto done;
-	}
-
-	/* Connectionless channel */
-	if (sk->sk_type == SOCK_DGRAM) {
-		skb = l2cap_create_connless_pdu(sk, msg, len);
-		if (IS_ERR(skb)) {
-			err = PTR_ERR(skb);
-		} else {
-			l2cap_do_send(sk, skb);
-			err = len;
-		}
-		goto done;
-	}
-
-	switch (pi->mode) {
-	case L2CAP_MODE_BASIC:
-		/* Check outgoing MTU */
-		if (len > pi->omtu) {
-			err = -EMSGSIZE;
-			goto done;
-		}
-
-		/* Create a basic PDU */
-		skb = l2cap_create_basic_pdu(sk, msg, len);
-		if (IS_ERR(skb)) {
-			err = PTR_ERR(skb);
-			goto done;
-		}
-
-		l2cap_do_send(sk, skb);
-		err = len;
-		break;
-
-	case L2CAP_MODE_ERTM:
-	case L2CAP_MODE_STREAMING:
-		/* Entire SDU fits into one PDU */
-		if (len <= pi->remote_mps) {
-			control = L2CAP_SDU_UNSEGMENTED;
-			skb = l2cap_create_iframe_pdu(sk, msg, len, control, 0);
-			if (IS_ERR(skb)) {
-				err = PTR_ERR(skb);
-				goto done;
-			}
-			__skb_queue_tail(TX_QUEUE(sk), skb);
-
-			if (sk->sk_send_head == NULL)
-				sk->sk_send_head = skb;
-
-		} else {
-		/* Segment SDU into multiples PDUs */
-			err = l2cap_sar_segment_sdu(sk, msg, len);
-			if (err < 0)
-				goto done;
-		}
-
-		if (pi->mode == L2CAP_MODE_STREAMING) {
-			l2cap_streaming_send(sk);
-		} else {
-			if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) &&
-					(pi->conn_state & L2CAP_CONN_WAIT_F)) {
-				err = len;
-				break;
-			}
-			err = l2cap_ertm_send(sk);
-		}
-
-		if (err >= 0)
-			err = len;
-		break;
-
-	default:
-		BT_DBG("bad state %1.1x", pi->mode);
-		err = -EBADFD;
-	}
-
-done:
-	release_sock(sk);
-	return err;
-}
-
 static void l2cap_chan_ready(struct sock *sk)
 {
 	struct sock *parent = bt_sk(sk)->parent;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 93af233bb167..fe4f834f03dd 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -681,6 +681,108 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch
 	return err;
 }
 
+static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len)
+{
+	struct sock *sk = sock->sk;
+	struct l2cap_pinfo *pi = l2cap_pi(sk);
+	struct sk_buff *skb;
+	u16 control;
+	int err;
+
+	BT_DBG("sock %p, sk %p", sock, sk);
+
+	err = sock_error(sk);
+	if (err)
+		return err;
+
+	if (msg->msg_flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
+	lock_sock(sk);
+
+	if (sk->sk_state != BT_CONNECTED) {
+		err = -ENOTCONN;
+		goto done;
+	}
+
+	/* Connectionless channel */
+	if (sk->sk_type == SOCK_DGRAM) {
+		skb = l2cap_create_connless_pdu(sk, msg, len);
+		if (IS_ERR(skb)) {
+			err = PTR_ERR(skb);
+		} else {
+			l2cap_do_send(sk, skb);
+			err = len;
+		}
+		goto done;
+	}
+
+	switch (pi->mode) {
+	case L2CAP_MODE_BASIC:
+		/* Check outgoing MTU */
+		if (len > pi->omtu) {
+			err = -EMSGSIZE;
+			goto done;
+		}
+
+		/* Create a basic PDU */
+		skb = l2cap_create_basic_pdu(sk, msg, len);
+		if (IS_ERR(skb)) {
+			err = PTR_ERR(skb);
+			goto done;
+		}
+
+		l2cap_do_send(sk, skb);
+		err = len;
+		break;
+
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		/* Entire SDU fits into one PDU */
+		if (len <= pi->remote_mps) {
+			control = L2CAP_SDU_UNSEGMENTED;
+			skb = l2cap_create_iframe_pdu(sk, msg, len, control, 0);
+			if (IS_ERR(skb)) {
+				err = PTR_ERR(skb);
+				goto done;
+			}
+			__skb_queue_tail(TX_QUEUE(sk), skb);
+
+			if (sk->sk_send_head == NULL)
+				sk->sk_send_head = skb;
+
+		} else {
+		/* Segment SDU into multiples PDUs */
+			err = l2cap_sar_segment_sdu(sk, msg, len);
+			if (err < 0)
+				goto done;
+		}
+
+		if (pi->mode == L2CAP_MODE_STREAMING) {
+			l2cap_streaming_send(sk);
+		} else {
+			if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) &&
+					(pi->conn_state & L2CAP_CONN_WAIT_F)) {
+				err = len;
+				break;
+			}
+			err = l2cap_ertm_send(sk);
+		}
+
+		if (err >= 0)
+			err = len;
+		break;
+
+	default:
+		BT_DBG("bad state %1.1x", pi->mode);
+		err = -EBADFD;
+	}
+
+done:
+	release_sock(sk);
+	return err;
+}
+
 static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From 6de0702b5b93da0ef097aa092b4597fbc024ebba Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Fri, 4 Feb 2011 03:35:20 -0200
Subject: Bluetooth: move __l2cap_sock_close() to l2cap_sock.c

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  2 +
 net/bluetooth/l2cap_core.c    | 85 +------------------------------------------
 net/bluetooth/l2cap_sock.c    | 78 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 82 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index d4c93eded727..75ef0b2948f9 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -451,6 +451,8 @@ void l2cap_sock_kill(struct sock *sk);
 void l2cap_sock_init(struct sock *sk, struct sock *parent);
 struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 							int proto, gfp_t prio);
+void l2cap_send_disconn_req(struct l2cap_conn *conn, struct sock *sk, int err);
+void l2cap_chan_del(struct sock *sk, int err);
 int l2cap_do_connect(struct sock *sk);
 
 void l2cap_load(void);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 9d51af300d9c..ba7f9da68998 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -70,8 +70,6 @@ struct bt_sock_list l2cap_sk_list = {
 
 static void l2cap_busy_work(struct work_struct *work);
 
-static void l2cap_sock_close(struct sock *sk);
-
 static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 				u8 code, u8 ident, u16 dlen, void *data);
 
@@ -207,7 +205,7 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct sock *sk, struct so
 
 /* Delete channel.
  * Must be called on the locked socket. */
-static void l2cap_chan_del(struct sock *sk, int err)
+void l2cap_chan_del(struct sock *sk, int err)
 {
 	struct l2cap_conn *conn = l2cap_pi(sk)->conn;
 	struct sock *parent = bt_sk(sk)->parent;
@@ -457,7 +455,7 @@ static inline int l2cap_mode_supported(__u8 mode, __u32 feat_mask)
 	}
 }
 
-static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct sock *sk, int err)
+void l2cap_send_disconn_req(struct l2cap_conn *conn, struct sock *sk, int err)
 {
 	struct l2cap_disconn_req req;
 
@@ -739,85 +737,6 @@ static struct sock *l2cap_get_sock_by_psm(int state, __le16 psm, bdaddr_t *src)
 	return node ? sk : sk1;
 }
 
-static void l2cap_sock_cleanup_listen(struct sock *parent)
-{
-	struct sock *sk;
-
-	BT_DBG("parent %p", parent);
-
-	/* Close not yet accepted channels */
-	while ((sk = bt_accept_dequeue(parent, NULL)))
-		l2cap_sock_close(sk);
-
-	parent->sk_state = BT_CLOSED;
-	sock_set_flag(parent, SOCK_ZAPPED);
-}
-
-void __l2cap_sock_close(struct sock *sk, int reason)
-{
-	BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket);
-
-	switch (sk->sk_state) {
-	case BT_LISTEN:
-		l2cap_sock_cleanup_listen(sk);
-		break;
-
-	case BT_CONNECTED:
-	case BT_CONFIG:
-		if (sk->sk_type == SOCK_SEQPACKET ||
-				sk->sk_type == SOCK_STREAM) {
-			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
-
-			l2cap_sock_set_timer(sk, sk->sk_sndtimeo);
-			l2cap_send_disconn_req(conn, sk, reason);
-		} else
-			l2cap_chan_del(sk, reason);
-		break;
-
-	case BT_CONNECT2:
-		if (sk->sk_type == SOCK_SEQPACKET ||
-				sk->sk_type == SOCK_STREAM) {
-			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
-			struct l2cap_conn_rsp rsp;
-			__u16 result;
-
-			if (bt_sk(sk)->defer_setup)
-				result = L2CAP_CR_SEC_BLOCK;
-			else
-				result = L2CAP_CR_BAD_PSM;
-			sk->sk_state = BT_DISCONN;
-
-			rsp.scid   = cpu_to_le16(l2cap_pi(sk)->dcid);
-			rsp.dcid   = cpu_to_le16(l2cap_pi(sk)->scid);
-			rsp.result = cpu_to_le16(result);
-			rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
-			l2cap_send_cmd(conn, l2cap_pi(sk)->ident,
-					L2CAP_CONN_RSP, sizeof(rsp), &rsp);
-		} else
-			l2cap_chan_del(sk, reason);
-		break;
-
-	case BT_CONNECT:
-	case BT_DISCONN:
-		l2cap_chan_del(sk, reason);
-		break;
-
-	default:
-		sock_set_flag(sk, SOCK_ZAPPED);
-		break;
-	}
-}
-
-/* Must be called on unlocked socket. */
-static void l2cap_sock_close(struct sock *sk)
-{
-	l2cap_sock_clear_timer(sk);
-	lock_sock(sk);
-	__l2cap_sock_close(sk, ECONNRESET);
-	release_sock(sk);
-	l2cap_sock_kill(sk);
-}
-
 int l2cap_do_connect(struct sock *sk)
 {
 	bdaddr_t *src = &bt_sk(sk)->src;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 4b4e0201ebbe..adf41692daf3 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -854,6 +854,84 @@ void l2cap_sock_kill(struct sock *sk)
 	sock_put(sk);
 }
 
+/* Must be called on unlocked socket. */
+static void l2cap_sock_close(struct sock *sk)
+{
+	l2cap_sock_clear_timer(sk);
+	lock_sock(sk);
+	__l2cap_sock_close(sk, ECONNRESET);
+	release_sock(sk);
+	l2cap_sock_kill(sk);
+}
+
+static void l2cap_sock_cleanup_listen(struct sock *parent)
+{
+	struct sock *sk;
+
+	BT_DBG("parent %p", parent);
+
+	/* Close not yet accepted channels */
+	while ((sk = bt_accept_dequeue(parent, NULL)))
+		l2cap_sock_close(sk);
+
+	parent->sk_state = BT_CLOSED;
+	sock_set_flag(parent, SOCK_ZAPPED);
+}
+
+void __l2cap_sock_close(struct sock *sk, int reason)
+{
+	BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket);
+
+	switch (sk->sk_state) {
+	case BT_LISTEN:
+		l2cap_sock_cleanup_listen(sk);
+		break;
+
+	case BT_CONNECTED:
+	case BT_CONFIG:
+		if (sk->sk_type == SOCK_SEQPACKET ||
+				sk->sk_type == SOCK_STREAM) {
+			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+
+			l2cap_sock_set_timer(sk, sk->sk_sndtimeo);
+			l2cap_send_disconn_req(conn, sk, reason);
+		} else
+			l2cap_chan_del(sk, reason);
+		break;
+
+	case BT_CONNECT2:
+		if (sk->sk_type == SOCK_SEQPACKET ||
+				sk->sk_type == SOCK_STREAM) {
+			struct l2cap_conn *conn = l2cap_pi(sk)->conn;
+			struct l2cap_conn_rsp rsp;
+			__u16 result;
+
+			if (bt_sk(sk)->defer_setup)
+				result = L2CAP_CR_SEC_BLOCK;
+			else
+				result = L2CAP_CR_BAD_PSM;
+
+			rsp.scid   = cpu_to_le16(l2cap_pi(sk)->dcid);
+			rsp.dcid   = cpu_to_le16(l2cap_pi(sk)->scid);
+			rsp.result = cpu_to_le16(result);
+			rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+			l2cap_send_cmd(conn, l2cap_pi(sk)->ident,
+					L2CAP_CONN_RSP, sizeof(rsp), &rsp);
+		} else
+			l2cap_chan_del(sk, reason);
+		break;
+
+	case BT_CONNECT:
+	case BT_DISCONN:
+		l2cap_chan_del(sk, reason);
+		break;
+
+	default:
+		sock_set_flag(sk, SOCK_ZAPPED);
+		break;
+	}
+}
+
 static int l2cap_sock_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
-- 
cgit v1.2.3


From dc5f219e88294b93009eef946251251ffffb6d60 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 4 Feb 2011 13:19:20 +0100
Subject: genirq: Add IRQF_FORCE_RESUME

Xen needs to reenable interrupts which are marked IRQF_NO_SUSPEND in the
resume path. Add a flag to force the reenabling in the resume code.

Tested-and-acked-by: Ian Campbell <Ian.Campbell@eu.citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/interrupt.h |  3 ++-
 kernel/irq/manage.c       | 11 ++++++++++-
 kernel/irq/pm.c           |  3 ---
 3 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 55e0d4253e49..d746da19c6a2 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -55,7 +55,7 @@
  *                Used by threaded interrupts which need to keep the
  *                irq line disabled until the threaded handler has been run.
  * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
- *
+ * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
  */
 #define IRQF_DISABLED		0x00000020
 #define IRQF_SAMPLE_RANDOM	0x00000040
@@ -67,6 +67,7 @@
 #define IRQF_IRQPOLL		0x00001000
 #define IRQF_ONESHOT		0x00002000
 #define IRQF_NO_SUSPEND		0x00004000
+#define IRQF_FORCE_RESUME	0x00008000
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND)
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0caa59f747dd..b4198ee8cfdf 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -282,8 +282,17 @@ EXPORT_SYMBOL(disable_irq);
 
 void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
-	if (resume)
+	if (resume) {
+		if (!(desc->status & IRQ_SUSPENDED)) {
+			if (!desc->action)
+				return;
+			if (!(desc->action->flags & IRQF_FORCE_RESUME))
+				return;
+			/* Pretend that it got disabled ! */
+			desc->depth++;
+		}
 		desc->status &= ~IRQ_SUSPENDED;
+	}
 
 	switch (desc->depth) {
 	case 0:
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 0d4005d85b03..d6bfb89cce91 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -53,9 +53,6 @@ void resume_device_irqs(void)
 	for_each_irq_desc(irq, desc) {
 		unsigned long flags;
 
-		if (!(desc->status & IRQ_SUSPENDED))
-			continue;
-
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		__enable_irq(desc, irq, true);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
-- 
cgit v1.2.3


From fa9921e46fd52b78070dc67ce0d27ec301a90410 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 2 Feb 2011 06:29:02 +0000
Subject: ipsec: allow to align IPv4 AH on 32 bits

The Linux IPv4 AH stack aligns the AH header on a 64 bit boundary
(like in IPv6). This is not RFC compliant (see RFC4302, Section
3.3.3.2.1), it should be aligned on 32 bits.

For most of the authentication algorithms, the ICV size is 96 bits.
The AH header alignment on 32 or 64 bits gives the same results.

However for SHA-256-128 for instance, the wrong 64 bit alignment results
in adding useless padding in IPv4 AH, which is forbidden by the RFC.

To avoid breaking backward compatibility, we use a new flag
(XFRM_STATE_ALIGN4) do change original behavior.

Initial patch from Dang Hongwu <hongwu.dang@6wind.com> and
Christophe Gouault <christophe.gouault@6wind.com>.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/xfrm.h |  1 +
 include/net/xfrm.h   |  1 +
 net/ipv4/ah4.c       | 25 +++++++++++++++++++------
 3 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
index 930fdd2de79c..b93d6f598085 100644
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -350,6 +350,7 @@ struct xfrm_usersa_info {
 #define XFRM_STATE_WILDRECV	8
 #define XFRM_STATE_ICMP		16
 #define XFRM_STATE_AF_UNSPEC	32
+#define XFRM_STATE_ALIGN4	64
 };
 
 struct xfrm_usersa_id {
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b9f385da758e..1f6e8a0eb544 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -36,6 +36,7 @@
 #define XFRM_PROTO_ROUTING	IPPROTO_ROUTING
 #define XFRM_PROTO_DSTOPTS	IPPROTO_DSTOPTS
 
+#define XFRM_ALIGN4(len)	(((len) + 3) & ~3)
 #define XFRM_ALIGN8(len)	(((len) + 7) & ~7)
 #define MODULE_ALIAS_XFRM_MODE(family, encap) \
 	MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap))
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 86961bec70ab..325053df6e70 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -201,7 +201,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
 	top_iph->ttl = 0;
 	top_iph->check = 0;
 
-	ah->hdrlen  = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
+	if (x->props.flags & XFRM_STATE_ALIGN4)
+		ah->hdrlen  = (XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
+	else
+		ah->hdrlen  = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
 
 	ah->reserved = 0;
 	ah->spi = x->id.spi;
@@ -299,9 +302,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 	nexthdr = ah->nexthdr;
 	ah_hlen = (ah->hdrlen + 2) << 2;
 
-	if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
-	    ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
-		goto out;
+	if (x->props.flags & XFRM_STATE_ALIGN4) {
+		if (ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_full_len) &&
+		    ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len))
+			goto out;
+	} else {
+		if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
+		    ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
+			goto out;
+	}
 
 	if (!pskb_may_pull(skb, ah_hlen))
 		goto out;
@@ -450,8 +459,12 @@ static int ah_init_state(struct xfrm_state *x)
 
 	BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
 
-	x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
-					  ahp->icv_trunc_len);
+	if (x->props.flags & XFRM_STATE_ALIGN4)
+		x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) +
+						  ahp->icv_trunc_len);
+	else
+		x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
+						  ahp->icv_trunc_len);
 	if (x->props.mode == XFRM_MODE_TUNNEL)
 		x->props.header_len += sizeof(struct iphdr);
 	x->data = ahp;
-- 
cgit v1.2.3


From f4d5c029bd6731baac0937324cef0f746e7d5ea7 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Wed, 26 Jan 2011 16:49:00 +0800
Subject: tracing: Compile time initialization for event flags value

Compile time initialization is better than runtime initialization.

Remove many early_initcall()s and many trace_init_flags_##name()s.

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4D3FDFFC.6030304@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/syscalls.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8e8968e74544..a17fcea2ca58 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -132,11 +132,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
+		.flags			= TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
-	 *__event_enter_##sname = &event_enter_##sname;			\
-	__TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
+	 *__event_enter_##sname = &event_enter_##sname;
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
 	static struct syscall_metadata __syscall_meta_##sname;		\
@@ -146,11 +146,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
+		.flags			= TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
-	*__event_exit_##sname = &event_exit_##sname;			\
-	__TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
+	*__event_exit_##sname = &event_exit_##sname;
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\
-- 
cgit v1.2.3


From e7b66bdc02592f5573ade667e4d68ac6e7b0f9e1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 8 Feb 2011 15:33:22 -0800
Subject: net: Remove bogus barrier() in dst_allfrag().

I simply missed this one when modifying the other dst
metric interfaces earlier.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index e550195d4f86..e01855de21e8 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -220,8 +220,6 @@ static inline u32
 dst_allfrag(const struct dst_entry *dst)
 {
 	int ret = dst_feature(dst,  RTAX_FEATURE_ALLFRAG);
-	/* Yes, _exactly_. This is paranoia. */
-	barrier();
 	return ret;
 }
 
-- 
cgit v1.2.3


From 8d13a2a9fb3e5e3f68e9d3ec0de3c8fcfa56a224 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 8 Feb 2011 16:17:55 -0800
Subject: net: Kill NETEVENT_PMTU_UPDATE.

Nobody actually does anything in response to the event,
so just kill it off.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/cxgb3/cxgb3_offload.c | 2 --
 drivers/net/cxgb4/cxgb4_main.c    | 1 -
 include/net/netevent.h            | 1 -
 net/ipv4/route.c                  | 1 -
 net/ipv6/route.c                  | 1 -
 5 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c
index ef02aa68c926..7ea94b5205f8 100644
--- a/drivers/net/cxgb3/cxgb3_offload.c
+++ b/drivers/net/cxgb3/cxgb3_offload.c
@@ -967,8 +967,6 @@ static int nb_callback(struct notifier_block *self, unsigned long event,
 		cxgb_neigh_update((struct neighbour *)ctx);
 		break;
 	}
-	case (NETEVENT_PMTU_UPDATE):
-		break;
 	case (NETEVENT_REDIRECT):{
 		struct netevent_redirect *nr = ctx;
 		cxgb_redirect(nr->old, nr->new);
diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index ec35d458102c..5352c8a23f4d 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -2471,7 +2471,6 @@ static int netevent_cb(struct notifier_block *nb, unsigned long event,
 	case NETEVENT_NEIGH_UPDATE:
 		check_neigh_update(data);
 		break;
-	case NETEVENT_PMTU_UPDATE:
 	case NETEVENT_REDIRECT:
 	default:
 		break;
diff --git a/include/net/netevent.h b/include/net/netevent.h
index e82b7bab3ff3..22b239c17eaa 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -21,7 +21,6 @@ struct netevent_redirect {
 
 enum netevent_notif_type {
 	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
-	NETEVENT_PMTU_UPDATE,	   /* arg is struct dst_entry ptr */
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 };
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2e225dafc4f8..0455af851751 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1762,7 +1762,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 		}
 		dst_metric_set(dst, RTAX_MTU, mtu);
 		dst_set_expires(dst, ip_rt_mtu_expires);
-		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
 	}
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0a63d44e6f48..12ec83d48806 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -965,7 +965,6 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 			dst_metric_set(dst, RTAX_FEATURES, features);
 		}
 		dst_metric_set(dst, RTAX_MTU, mtu);
-		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
 	}
 }
 
-- 
cgit v1.2.3


From 4149efb22da66e326fc48baf80d628834509f7f0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 8 Feb 2011 10:39:03 +0100
Subject: workqueue: add system_freezeable_wq

Add system wide freezeable workqueue.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
---
 include/linux/workqueue.h | 4 ++++
 kernel/workqueue.c        | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 1ac11586a2f5..de6a755befac 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -286,11 +286,15 @@ enum {
  * any specific CPU, not concurrency managed, and all queued works are
  * executed immediately as long as max_active limit is not reached and
  * resources are available.
+ *
+ * system_freezeable_wq is equivalent to system_wq except that it's
+ * freezeable.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_nrt_wq;
 extern struct workqueue_struct *system_unbound_wq;
+extern struct workqueue_struct *system_freezeable_wq;
 
 extern struct workqueue_struct *
 __alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 11869faa6819..28f8bd08f0e7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -249,10 +249,12 @@ struct workqueue_struct *system_wq __read_mostly;
 struct workqueue_struct *system_long_wq __read_mostly;
 struct workqueue_struct *system_nrt_wq __read_mostly;
 struct workqueue_struct *system_unbound_wq __read_mostly;
+struct workqueue_struct *system_freezeable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_wq);
 EXPORT_SYMBOL_GPL(system_long_wq);
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
+EXPORT_SYMBOL_GPL(system_freezeable_wq);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
@@ -3764,8 +3766,10 @@ static int __init init_workqueues(void)
 	system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0);
 	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
 					    WQ_UNBOUND_MAX_ACTIVE);
+	system_freezeable_wq = alloc_workqueue("events_freezeable",
+					       WQ_FREEZEABLE, 0);
 	BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq ||
-	       !system_unbound_wq);
+	       !system_unbound_wq || !system_freezeable_wq);
 	return 0;
 }
 early_initcall(init_workqueues);
-- 
cgit v1.2.3


From 6d1d4ea4a82f8c17a3ff7c2f677bc3d41ea7484b Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Tue, 8 Feb 2011 23:32:17 +0100
Subject: ssb: extract boardflags2 for SPROMs rev 4 and 5
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/pci.c            | 4 ++++
 include/linux/ssb/ssb_regs.h | 4 ++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 158449e55044..5b33b3b06f7f 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -468,10 +468,14 @@ static void sprom_extract_r45(struct ssb_sprom *out, const u16 *in)
 		SPEX(country_code, SSB_SPROM4_CCODE, 0xFFFF, 0);
 		SPEX(boardflags_lo, SSB_SPROM4_BFLLO, 0xFFFF, 0);
 		SPEX(boardflags_hi, SSB_SPROM4_BFLHI, 0xFFFF, 0);
+		SPEX(boardflags2_lo, SSB_SPROM4_BFL2LO, 0xFFFF, 0);
+		SPEX(boardflags2_hi, SSB_SPROM4_BFL2HI, 0xFFFF, 0);
 	} else {
 		SPEX(country_code, SSB_SPROM5_CCODE, 0xFFFF, 0);
 		SPEX(boardflags_lo, SSB_SPROM5_BFLLO, 0xFFFF, 0);
 		SPEX(boardflags_hi, SSB_SPROM5_BFLHI, 0xFFFF, 0);
+		SPEX(boardflags2_lo, SSB_SPROM5_BFL2LO, 0xFFFF, 0);
+		SPEX(boardflags2_hi, SSB_SPROM5_BFL2HI, 0xFFFF, 0);
 	}
 	SPEX(ant_available_a, SSB_SPROM4_ANTAVAIL, SSB_SPROM4_ANTAVAIL_A,
 	     SSB_SPROM4_ANTAVAIL_A_SHIFT);
diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h
index 489f7b6d61c5..df9211a84634 100644
--- a/include/linux/ssb/ssb_regs.h
+++ b/include/linux/ssb/ssb_regs.h
@@ -268,6 +268,8 @@
 /* SPROM Revision 4 */
 #define SSB_SPROM4_BFLLO		0x0044	/* Boardflags (low 16 bits) */
 #define SSB_SPROM4_BFLHI		0x0046  /* Board Flags Hi */
+#define SSB_SPROM4_BFL2LO		0x0048	/* Board flags 2 (low 16 bits) */
+#define SSB_SPROM4_BFL2HI		0x004A	/* Board flags 2 Hi */
 #define SSB_SPROM4_IL0MAC		0x004C	/* 6 byte MAC address for a/b/g/n */
 #define SSB_SPROM4_CCODE		0x0052	/* Country Code (2 bytes) */
 #define SSB_SPROM4_GPIOA		0x0056	/* Gen. Purpose IO # 0 and 1 */
@@ -358,6 +360,8 @@
 #define SSB_SPROM5_CCODE		0x0044	/* Country Code (2 bytes) */
 #define SSB_SPROM5_BFLLO		0x004A	/* Boardflags (low 16 bits) */
 #define SSB_SPROM5_BFLHI		0x004C  /* Board Flags Hi */
+#define SSB_SPROM5_BFL2LO		0x004E	/* Board flags 2 (low 16 bits) */
+#define SSB_SPROM5_BFL2HI		0x0050	/* Board flags 2 Hi */
 #define SSB_SPROM5_IL0MAC		0x0052	/* 6 byte MAC address for a/b/g/n */
 #define SSB_SPROM5_GPIOA		0x0076	/* Gen. Purpose IO # 0 and 1 */
 #define  SSB_SPROM5_GPIOA_P0		0x00FF	/* Pin 0 */
-- 
cgit v1.2.3


From a68a27b6f2354273bacc39c3dd06456edb202230 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Tue, 2 Nov 2010 10:10:56 -0400
Subject: IMA: convert i_readcount to atomic

Convert the inode's i_readcount from an unsigned int to atomic.

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Acked-by: Eric Paris <eparis@redhat.com>
---
 include/linux/fs.h                |  3 +--
 security/integrity/ima/ima_iint.c |  7 ++++---
 security/integrity/ima/ima_main.c | 11 ++++++-----
 3 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index baf3e556ff0e..ef85322863b9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -794,8 +794,7 @@ struct inode {
 #endif
 
 #ifdef CONFIG_IMA
-	/* protected by i_lock */
-	unsigned int		i_readcount; /* struct files open RO */
+	atomic_t		i_readcount; /* struct files open RO */
 #endif
 	atomic_t		i_writecount;
 #ifdef CONFIG_SECURITY
diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c
index c442e47b6785..f0053552fd58 100644
--- a/security/integrity/ima/ima_iint.c
+++ b/security/integrity/ima/ima_iint.c
@@ -137,10 +137,11 @@ void ima_inode_free(struct inode *inode)
 {
 	struct ima_iint_cache *iint;
 
-	if (inode->i_readcount)
-		printk(KERN_INFO "%s: readcount: %u\n", __func__, inode->i_readcount);
+	if (atomic_read(&inode->i_readcount))
+		printk(KERN_INFO "%s: readcount: %u\n", __func__,
+		       atomic_read(&inode->i_readcount));
 
-	inode->i_readcount = 0;
+	atomic_set(&inode->i_readcount, 0);
 
 	if (!IS_IMA(inode))
 		return;
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 203de979d305..6e8cb931b8f1 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -113,7 +113,7 @@ void ima_counts_get(struct file *file)
 		goto out;
 
 	if (mode & FMODE_WRITE) {
-		if (inode->i_readcount && IS_IMA(inode))
+		if (atomic_read(&inode->i_readcount) && IS_IMA(inode))
 			send_tomtou = true;
 		goto out;
 	}
@@ -127,7 +127,7 @@ void ima_counts_get(struct file *file)
 out:
 	/* remember the vfs deals with i_writecount */
 	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
-		inode->i_readcount++;
+		atomic_inc(&inode->i_readcount);
 
 	spin_unlock(&inode->i_lock);
 
@@ -149,15 +149,16 @@ static void ima_dec_counts(struct inode *inode, struct file *file)
 	assert_spin_locked(&inode->i_lock);
 
 	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) {
-		if (unlikely(inode->i_readcount == 0)) {
+		if (unlikely(atomic_read(&inode->i_readcount) == 0)) {
 			if (!ima_limit_imbalance(file)) {
 				printk(KERN_INFO "%s: open/free imbalance (r:%u)\n",
-				       __func__, inode->i_readcount);
+				       __func__,
+				       atomic_read(&inode->i_readcount));
 				dump_stack();
 			}
 			return;
 		}
-		inode->i_readcount--;
+		atomic_dec(&inode->i_readcount);
 	}
 }
 
-- 
cgit v1.2.3


From a5c96ebf1d71df0c5fb77ab58c9aeb307cf02372 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Tue, 2 Nov 2010 10:11:37 -0400
Subject: IMA: define readcount functions

Define i_readcount_inc/dec() functions to be called from the VFS layer.

Changelog:
- renamed iget/iput_readcount to i_readcount_inc/dec (Dave Chinner's suggestion)
- removed i_lock in iput_readcount() (based on comments:Dave Chinner,Eric Paris)

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Acked-by: Eric Paris <eparis@redhat.com>
---
 include/linux/fs.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index ef85322863b9..a3e8f02b727d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2186,6 +2186,26 @@ static inline void allow_write_access(struct file *file)
 	if (file)
 		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 }
+#ifdef CONFIG_IMA
+static inline void i_readcount_dec(struct inode *inode)
+{
+	BUG_ON(!atomic_read(&inode->i_readcount));
+	atomic_dec(&inode->i_readcount);
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+	atomic_inc(&inode->i_readcount);
+}
+#else
+static inline void i_readcount_dec(struct inode *inode)
+{
+	return;
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+	return;
+}
+#endif
 extern int do_pipe_flags(int *, int);
 extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
-- 
cgit v1.2.3


From 890275b5eb79e9933d12290473eab9ac38da0051 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Tue, 2 Nov 2010 10:13:07 -0400
Subject: IMA: maintain i_readcount in the VFS layer

ima_counts_get() updated the readcount and invalidated the PCR,
as necessary. Only update the i_readcount in the VFS layer.
Move the PCR invalidation checks to ima_file_check(), where it
belongs.

Maintaining the i_readcount in the VFS layer, will allow other
subsystems to use i_readcount.

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Acked-by: Eric Paris <eparis@redhat.com>
---
 fs/file_table.c                   |  5 ++++-
 fs/open.c                         |  3 ++-
 include/linux/ima.h               |  6 ------
 security/integrity/ima/ima_iint.c |  2 --
 security/integrity/ima/ima_main.c | 25 ++++++++-----------------
 5 files changed, 14 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/file_table.c b/fs/file_table.c
index c3dee381f1b4..0c724deb46f9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -190,7 +190,8 @@ struct file *alloc_file(struct path *path, fmode_t mode,
 		file_take_write(file);
 		WARN_ON(mnt_clone_write(path->mnt));
 	}
-	ima_counts_get(file);
+	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
 EXPORT_SYMBOL(alloc_file);
@@ -251,6 +252,8 @@ static void __fput(struct file *file)
 	fops_put(file->f_op);
 	put_pid(file->f_owner.pid);
 	file_sb_list_del(file);
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_dec(inode);
 	if (file->f_mode & FMODE_WRITE)
 		drop_file_write_access(file);
 	file->f_path.dentry = NULL;
diff --git a/fs/open.c b/fs/open.c
index 4197b9ed023d..0d485c50bb95 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -688,7 +688,8 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 		if (error)
 			goto cleanup_all;
 	}
-	ima_counts_get(f);
+	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_inc(inode);
 
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 975837e7d6c0..09e6e62f9953 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -20,7 +20,6 @@ extern void ima_inode_free(struct inode *inode);
 extern int ima_file_check(struct file *file, int mask);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
-extern void ima_counts_get(struct file *file);
 
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
@@ -53,10 +52,5 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot)
 	return 0;
 }
 
-static inline void ima_counts_get(struct file *file)
-{
-	return;
-}
-
 #endif /* CONFIG_IMA_H */
 #endif /* _LINUX_IMA_H */
diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c
index f0053552fd58..68efe3b8d993 100644
--- a/security/integrity/ima/ima_iint.c
+++ b/security/integrity/ima/ima_iint.c
@@ -141,8 +141,6 @@ void ima_inode_free(struct inode *inode)
 		printk(KERN_INFO "%s: readcount: %u\n", __func__,
 		       atomic_read(&inode->i_readcount));
 
-	atomic_set(&inode->i_readcount, 0);
-
 	if (!IS_IMA(inode))
 		return;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 6e8cb931b8f1..69b4856af4da 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -86,17 +86,16 @@ out:
 }
 
 /*
- * ima_counts_get - increment file counts
+ * ima_rdwr_violation_check
  *
- * Maintain read/write counters for all files, but only
- * invalidate the PCR for measured files:
+ * Only invalidate the PCR for measured files:
  * 	- Opening a file for write when already open for read,
  *	  results in a time of measure, time of use (ToMToU) error.
  *	- Opening a file for read when already open for write,
  * 	  could result in a file measurement error.
  *
  */
-void ima_counts_get(struct file *file)
+static void ima_rdwr_violation_check(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -104,13 +103,10 @@ void ima_counts_get(struct file *file)
 	int rc;
 	bool send_tomtou = false, send_writers = false;
 
-	if (!S_ISREG(inode->i_mode))
+	if (!S_ISREG(inode->i_mode) || !ima_initialized)
 		return;
 
-	spin_lock(&inode->i_lock);
-
-	if (!ima_initialized)
-		goto out;
+	mutex_lock(&inode->i_mutex);	/* file metadata: permissions, xattr */
 
 	if (mode & FMODE_WRITE) {
 		if (atomic_read(&inode->i_readcount) && IS_IMA(inode))
@@ -125,11 +121,7 @@ void ima_counts_get(struct file *file)
 	if (atomic_read(&inode->i_writecount) > 0)
 		send_writers = true;
 out:
-	/* remember the vfs deals with i_writecount */
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
-		atomic_inc(&inode->i_readcount);
-
-	spin_unlock(&inode->i_lock);
+	mutex_unlock(&inode->i_mutex);
 
 	if (send_tomtou)
 		ima_add_violation(inode, dentry->d_name.name, "invalid_pcr",
@@ -158,7 +150,6 @@ static void ima_dec_counts(struct inode *inode, struct file *file)
 			}
 			return;
 		}
-		atomic_dec(&inode->i_readcount);
 	}
 }
 
@@ -203,8 +194,7 @@ static void ima_file_free_noiint(struct inode *inode, struct file *file)
  * ima_file_free - called on __fput()
  * @file: pointer to file structure being freed
  *
- * Flag files that changed, based on i_version;
- * and decrement the i_readcount.
+ * Flag files that changed, based on i_version
  */
 void ima_file_free(struct file *file)
 {
@@ -318,6 +308,7 @@ int ima_file_check(struct file *file, int mask)
 {
 	int rc;
 
+	ima_rdwr_violation_check(file);
 	rc = process_measurement(file, file->f_dentry->d_name.name,
 				 mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
 				 FILE_CHECK);
-- 
cgit v1.2.3


From 7a71ed899e77cc822abb863e24a422dcf7e9fa33 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 9 Feb 2011 14:30:26 -0800
Subject: inetpeer: Abstract address representation further.

Future changes will add caching information, and some of
these new elements will be addresses.

Since the family is implicit via the ->daddr.family member,
replicating the family in ever address we store is entirely
redundant.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 16 ++++++++++------
 net/ipv4/inetpeer.c    |  6 +++---
 net/ipv4/tcp_ipv4.c    |  2 +-
 net/ipv6/tcp_ipv6.c    |  2 +-
 4 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index ead2cb2de18c..60e2cd8d1319 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -15,12 +15,16 @@
 #include <net/ipv6.h>
 #include <asm/atomic.h>
 
-struct inetpeer_addr {
+struct inetpeer_addr_base {
 	union {
-		__be32		a4;
-		__be32		a6[4];
+		__be32			a4;
+		__be32			a6[4];
 	};
-	__u16	family;
+};
+
+struct inetpeer_addr {
+	struct inetpeer_addr_base	addr;
+	__u16				family;
 };
 
 struct inet_peer {
@@ -67,7 +71,7 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create)
 {
 	struct inetpeer_addr daddr;
 
-	daddr.a4 = v4daddr;
+	daddr.addr.a4 = v4daddr;
 	daddr.family = AF_INET;
 	return inet_getpeer(&daddr, create);
 }
@@ -76,7 +80,7 @@ static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int cr
 {
 	struct inetpeer_addr daddr;
 
-	ipv6_addr_copy((struct in6_addr *)daddr.a6, v6daddr);
+	ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr);
 	daddr.family = AF_INET6;
 	return inet_getpeer(&daddr, create);
 }
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 709fbb4132d7..4346c38763ae 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -167,9 +167,9 @@ static int addr_compare(const struct inetpeer_addr *a,
 	int i, n = (a->family == AF_INET ? 1 : 4);
 
 	for (i = 0; i < n; i++) {
-		if (a->a6[i] == b->a6[i])
+		if (a->addr.a6[i] == b->addr.a6[i])
 			continue;
-		if (a->a6[i] < b->a6[i])
+		if (a->addr.a6[i] < b->addr.a6[i])
 			return -1;
 		return 1;
 	}
@@ -510,7 +510,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 		p->daddr = *daddr;
 		atomic_set(&p->refcnt, 1);
 		atomic_set(&p->rid, 0);
-		atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4));
+		atomic_set(&p->ip_id_count, secure_ip_id(daddr->addr.a4));
 		p->tcp_ts_stamp = 0;
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 02f583b3744a..e2b9be27f226 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1341,7 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		    tcp_death_row.sysctl_tw_recycle &&
 		    (dst = inet_csk_route_req(sk, req)) != NULL &&
 		    (peer = rt_get_peer((struct rtable *)dst)) != NULL &&
-		    peer->daddr.a4 == saddr) {
+		    peer->daddr.addr.a4 == saddr) {
 			inet_peer_refcheck(peer);
 			if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
 			    (s32)(peer->tcp_ts - req->ts_recent) >
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 20aa95e37359..d6954e318324 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1323,7 +1323,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		    tcp_death_row.sysctl_tw_recycle &&
 		    (dst = inet6_csk_route_req(sk, req)) != NULL &&
 		    (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL &&
-		    ipv6_addr_equal((struct in6_addr *)peer->daddr.a6,
+		    ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6,
 				    &treq->rmt_addr)) {
 			inet_peer_refcheck(peer);
 			if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
-- 
cgit v1.2.3


From ddd4aa424b866a08ceba7ddf38e61542c91b93a0 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 9 Feb 2011 15:36:47 -0800
Subject: inetpeer: Add redirect and PMTU discovery cached info.

Validity of the cached PMTU information is indicated by it's
expiration value being non-zero, just as per dst->expires.

The scheme we will use is that we will remember the pre-ICMP value
held in the metrics or route entry, and then at expiration time
we will restore that value.

In this way PMTU expiration does not kill off the cached route as is
done currently.

Redirect information is permanent, or at least until another redirect
is received.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 18 +++++++++++-------
 net/ipv4/inetpeer.c    |  2 ++
 2 files changed, 13 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 60e2cd8d1319..e6dd8da6b2ad 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -43,13 +43,17 @@ struct inet_peer {
 	 */
 	union {
 		struct {
-			atomic_t	rid;		/* Frag reception counter */
-			atomic_t	ip_id_count;	/* IP ID for the next packet */
-			__u32		tcp_ts;
-			__u32		tcp_ts_stamp;
-			u32		metrics[RTAX_MAX];
-			u32		rate_tokens;	/* rate limiting for ICMP */
-			unsigned long	rate_last;
+			atomic_t			rid;		/* Frag reception counter */
+			atomic_t			ip_id_count;	/* IP ID for the next packet */
+			__u32				tcp_ts;
+			__u32				tcp_ts_stamp;
+			u32				metrics[RTAX_MAX];
+			u32				rate_tokens;	/* rate limiting for ICMP */
+			unsigned long			rate_last;
+			unsigned long			pmtu_expires;
+			u32				pmtu_orig;
+			u32				pmtu_learned;
+			struct inetpeer_addr_base	redirect_learned;
 		};
 		struct rcu_head         rcu;
 	};
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 4346c38763ae..48f8d4592ccd 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -515,6 +515,8 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		p->rate_last = 0;
+		p->pmtu_expires = 0;
+		memset(&p->redirect_learned, 0, sizeof(p->redirect_learned));
 		INIT_LIST_HEAD(&p->unused);
 
 
-- 
cgit v1.2.3


From 6431cbc25fa21635ee04eb0516ba6c51389fbfac Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 7 Feb 2011 20:38:06 -0800
Subject: inet: Create a mechanism for upward inetpeer propagation into routes.

If we didn't have a routing cache, we would not be able to properly
propagate certain kinds of dynamic path attributes, for example
PMTU information and redirects.

The reason is that if we didn't have a routing cache, then there would
be no way to lookup all of the active cached routes hanging off of
sockets, tunnels, IPSEC bundles, etc.

Consider the case where we created a cached route, but no inetpeer
entry existed and also we were not asked to pre-COW the route metrics
and therefore did not force the creation a new inetpeer entry.

If we later get a PMTU message, or a redirect, and store this
information in a new inetpeer entry, there is no way to teach that
cached route about the newly existing inetpeer entry.

The facilities implemented here handle this problem.

First we create a generation ID.  When we create a cached route of any
kind, we remember the generation ID at the time of attachment.  Any
time we force-create an inetpeer entry in response to new path
information, we bump that generation ID.

The dst_ops->check() callback is where the knowledge of this event
is propagated.  If the global generation ID does not equal the one
stored in the cached route, and the cached route has not attached
to an inetpeer yet, we look it up and attach if one is found.  Now
that we've updated the cached route's information, we update the
route's generation ID too.

This clears the way for implementing PMTU and redirects directly in
the inetpeer cache.  There is absolutely no need to consult cached
route information in order to maintain this information.

At this point nothing bumps the inetpeer genids, that comes in the
later changes which handle PMTUs and redirects using inetpeers.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  1 +
 include/net/route.h   |  1 +
 net/ipv4/route.c      | 19 ++++++++++++++++++-
 net/ipv6/route.c      | 18 ++++++++++++++++--
 4 files changed, 36 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 708ff7cb8806..46a6e8ae232c 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -108,6 +108,7 @@ struct rt6_info {
 	u32				rt6i_flags;
 	struct rt6key			rt6i_src;
 	u32				rt6i_metric;
+	u32				rt6i_peer_genid;
 
 	struct inet6_dev		*rt6i_idev;
 	struct inet_peer		*rt6i_peer;
diff --git a/include/net/route.h b/include/net/route.h
index e5864658dc76..bf790c1c6ac8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -69,6 +69,7 @@ struct rtable {
 
 	/* Miscellaneous cached information */
 	__be32			rt_spec_dst; /* RFC1122 specific destination */
+	u32			rt_peer_genid;
 	struct inet_peer	*peer; /* long-living peer info */
 	struct fib_info		*fi; /* for client ref to shared metrics */
 };
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0455af851751..0979e039104a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1308,6 +1308,13 @@ skip_hashing:
 	return 0;
 }
 
+static atomic_t __rt_peer_genid = ATOMIC_INIT(0);
+
+static u32 rt_peer_genid(void)
+{
+	return atomic_read(&__rt_peer_genid);
+}
+
 void rt_bind_peer(struct rtable *rt, int create)
 {
 	struct inet_peer *peer;
@@ -1316,6 +1323,8 @@ void rt_bind_peer(struct rtable *rt, int create)
 
 	if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
 		inet_putpeer(peer);
+	else
+		rt->rt_peer_genid = rt_peer_genid();
 }
 
 /*
@@ -1767,8 +1776,16 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 {
-	if (rt_is_expired((struct rtable *)dst))
+	struct rtable *rt = (struct rtable *) dst;
+
+	if (rt_is_expired(rt))
 		return NULL;
+	if (rt->rt_peer_genid != rt_peer_genid()) {
+		if (!rt->peer)
+			rt_bind_peer(rt, 0);
+
+		rt->rt_peer_genid = rt_peer_genid();
+	}
 	return dst;
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 12ec83d48806..ad8556e6fd41 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -240,6 +240,13 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	}
 }
 
+static atomic_t __rt6_peer_genid = ATOMIC_INIT(0);
+
+static u32 rt6_peer_genid(void)
+{
+	return atomic_read(&__rt6_peer_genid);
+}
+
 void rt6_bind_peer(struct rt6_info *rt, int create)
 {
 	struct inet_peer *peer;
@@ -247,6 +254,8 @@ void rt6_bind_peer(struct rt6_info *rt, int create)
 	peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
 	if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
 		inet_putpeer(peer);
+	else
+		rt->rt6i_peer_genid = rt6_peer_genid();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -912,9 +921,14 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt = (struct rt6_info *) dst;
 
-	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
+	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
+		if (rt->rt6i_peer_genid != rt6_peer_genid()) {
+			if (!rt->rt6i_peer)
+				rt6_bind_peer(rt, 0);
+			rt->rt6i_peer_genid = rt6_peer_genid();
+		}
 		return dst;
-
+	}
 	return NULL;
 }
 
-- 
cgit v1.2.3


From cfaea56741360311d0dabcb6603fa78c2e3de155 Mon Sep 17 00:00:00 2001
From: Trilok Soni <tsoni@codeaurora.org>
Date: Fri, 11 Feb 2011 00:44:41 -0800
Subject: Input: matrix_keypad - increase the limit of rows and columns

Some keyboard controllers support more than 16 columns and rows.
Increase the limit to 32.

Signed-off-by: Trilok Soni <tsoni@codeaurora.org>
Acked-by: Eric Miao <eric.y.miao@gmail.com>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
---
 include/linux/input/matrix_keypad.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h
index 80352ad6581a..b67feb8513a6 100644
--- a/include/linux/input/matrix_keypad.h
+++ b/include/linux/input/matrix_keypad.h
@@ -4,8 +4,8 @@
 #include <linux/types.h>
 #include <linux/input.h>
 
-#define MATRIX_MAX_ROWS		16
-#define MATRIX_MAX_COLS		16
+#define MATRIX_MAX_ROWS		32
+#define MATRIX_MAX_COLS		32
 
 #define KEY(row, col, val)	((((row) & (MATRIX_MAX_ROWS - 1)) << 24) |\
 				 (((col) & (MATRIX_MAX_COLS - 1)) << 16) |\
-- 
cgit v1.2.3


From d033d526a465c4bb8a499a0b5df65b3e7cf4da6f Mon Sep 17 00:00:00 2001
From: John Fastabend <john.r.fastabend@intel.com>
Date: Thu, 10 Feb 2011 14:40:01 +0000
Subject: ixgbe: DCB, implement 802.1Qaz routines

Implements 802.1Qaz support for ixgbe driver. Additionally,
this adds IEEE_8021QAZ_TSA_{} defines to dcbnl.h this is to
avoid having to use cryptic numeric codes for the TSA type.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe.h           |   4 ++
 drivers/net/ixgbe/ixgbe_dcb.c       | 103 ++++++++++++++++++++++++++++++++++++
 drivers/net/ixgbe/ixgbe_dcb.h       |   4 ++
 drivers/net/ixgbe/ixgbe_dcb_82598.c |   2 +-
 drivers/net/ixgbe/ixgbe_dcb_nl.c    |  91 +++++++++++++++++++++++++++++++
 drivers/net/ixgbe/ixgbe_main.c      |   4 ++
 include/linux/dcbnl.h               |   5 ++
 7 files changed, 212 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 3b8c92463617..d04afdeee035 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -334,6 +334,10 @@ struct ixgbe_adapter {
 	u16 bd_number;
 	struct work_struct reset_task;
 	struct ixgbe_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
+
+	/* DCB parameters */
+	struct ieee_pfc *ixgbe_ieee_pfc;
+	struct ieee_ets *ixgbe_ieee_ets;
 	struct ixgbe_dcb_config dcb_cfg;
 	struct ixgbe_dcb_config temp_dcb_cfg;
 	u8 dcb_set_bitmap;
diff --git a/drivers/net/ixgbe/ixgbe_dcb.c b/drivers/net/ixgbe/ixgbe_dcb.c
index d9bb670ae258..13c962efbfc9 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.c
+++ b/drivers/net/ixgbe/ixgbe_dcb.c
@@ -33,6 +33,42 @@
 #include "ixgbe_dcb_82598.h"
 #include "ixgbe_dcb_82599.h"
 
+/**
+ * ixgbe_ieee_credits - This calculates the ieee traffic class
+ * credits from the configured bandwidth percentages. Credits
+ * are the smallest unit programable into the underlying
+ * hardware. The IEEE 802.1Qaz specification do not use bandwidth
+ * groups so this is much simplified from the CEE case.
+ */
+s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame)
+{
+	int min_percent = 100;
+	int min_credit, multiplier;
+	int i;
+
+	min_credit = ((max_frame / 2) + DCB_CREDIT_QUANTUM - 1) /
+			DCB_CREDIT_QUANTUM;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		if (bw[i] < min_percent && bw[i])
+			min_percent = bw[i];
+	}
+
+	multiplier = (min_credit / min_percent) + 1;
+
+	/* Find out the hw credits for each TC */
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		int val = min(bw[i] * multiplier, MAX_CREDIT_REFILL);
+
+		if (val < min_credit)
+			val = min_credit;
+		refill[i] = val;
+
+		max[i] = (bw[i] * MAX_CREDIT)/100;
+	}
+	return 0;
+}
+
 /**
  * ixgbe_dcb_calculate_tc_credits - Calculates traffic class credits
  * @ixgbe_dcb_config: Struct containing DCB settings.
@@ -236,3 +272,70 @@ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw,
 	return ret;
 }
 
+/* Helper routines to abstract HW specifics from DCB netlink ops */
+s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en)
+{
+	int ret = -EINVAL;
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_82598EB:
+		ret = ixgbe_dcb_config_pfc_82598(hw, pfc_en);
+		break;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+		ret = ixgbe_dcb_config_pfc_82599(hw, pfc_en);
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw,
+			    u16 *refill, u16 *max, u8 *bwg_id, u8 *tsa)
+{
+	int i;
+	u8 prio_type[IEEE_8021QAZ_MAX_TCS];
+
+	/* Map TSA onto CEE prio type */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		switch (tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			prio_type[i] = 2;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			prio_type[i] = 0;
+			break;
+		default:
+			/* Hardware only supports priority strict or
+			 * ETS transmission selection algorithms if
+			 * we receive some other value from dcbnl
+			 * throw an error
+			 */
+			return -EINVAL;
+		}
+	}
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_82598EB:
+		ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max,
+							prio_type);
+		ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max,
+							     bwg_id, prio_type);
+		ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max,
+							     bwg_id, prio_type);
+		break;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+		ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max,
+						  bwg_id, prio_type);
+		ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max,
+						       bwg_id, prio_type);
+		ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max,
+						       bwg_id, prio_type);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h
index aa6cb5f9ebf4..4e4a641f3d53 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.h
+++ b/drivers/net/ixgbe/ixgbe_dcb.h
@@ -150,10 +150,14 @@ struct ixgbe_dcb_config {
 void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en);
 
 /* DCB credits calculation */
+s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame);
 s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *,
 				   struct ixgbe_dcb_config *, int, u8);
 
 /* DCB hw initialization */
+s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw,
+			    u16 *refill, u16 *max, u8 *bwg_id, u8 *prio_type);
+s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en);
 s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *);
 
 /* DCB definitions for credit calculation */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ixgbe/ixgbe_dcb_82598.c
index d1288060cbd0..2965edcdac7b 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82598.c
@@ -291,7 +291,7 @@ out:
  * Configure queue statistics registers, all queues belonging to same traffic
  * class uses a single set of queue statistics counters.
  */
-static s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw)
+s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw)
 {
 	u32 reg = 0;
 	u8  i   = 0;
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 6ab1f1abaa01..e75a3c91198d 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -606,7 +606,98 @@ static u8 ixgbe_dcbnl_setapp(struct net_device *netdev,
 	return rval;
 }
 
+static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
+				   struct ieee_ets *ets)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets;
+
+	/* No IEEE PFC settings available */
+	if (!my_ets)
+		return -EINVAL;
+
+	ets->ets_cap = MAX_TRAFFIC_CLASS;
+	ets->cbs = my_ets->cbs;
+	memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw));
+	memcpy(ets->tc_rx_bw, my_ets->tc_rx_bw, sizeof(ets->tc_rx_bw));
+	memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa));
+	memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc));
+	return 0;
+}
+
+static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
+				   struct ieee_ets *ets)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	__u16 refill[IEEE_8021QAZ_MAX_TCS], max[IEEE_8021QAZ_MAX_TCS];
+	int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
+	int err;
+	/* naively give each TC a bwg to map onto CEE hardware */
+	__u8 bwg_id[IEEE_8021QAZ_MAX_TCS] = {0, 1, 2, 3, 4, 5, 6, 7};
+
+	if (!adapter->ixgbe_ieee_ets) {
+		adapter->ixgbe_ieee_ets = kmalloc(sizeof(struct ieee_ets),
+						  GFP_KERNEL);
+		if (!adapter->ixgbe_ieee_ets)
+			return -ENOMEM;
+	}
+
+
+	memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets));
+
+	ixgbe_ieee_credits(ets->tc_tx_bw, refill, max, max_frame);
+	err = ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max,
+				      bwg_id, ets->tc_tsa);
+	return err;
+}
+
+static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
+				   struct ieee_pfc *pfc)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc;
+	int i;
+
+	/* No IEEE PFC settings available */
+	if (!my_pfc)
+		return -EINVAL;
+
+	pfc->pfc_cap = MAX_TRAFFIC_CLASS;
+	pfc->pfc_en = my_pfc->pfc_en;
+	pfc->mbc = my_pfc->mbc;
+	pfc->delay = my_pfc->delay;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		pfc->requests[i] = adapter->stats.pxoffrxc[i];
+		pfc->indications[i] = adapter->stats.pxofftxc[i];
+	}
+
+	return 0;
+}
+
+static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
+				   struct ieee_pfc *pfc)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	int err;
+
+	if (!adapter->ixgbe_ieee_pfc) {
+		adapter->ixgbe_ieee_pfc = kmalloc(sizeof(struct ieee_pfc),
+						  GFP_KERNEL);
+		if (!adapter->ixgbe_ieee_pfc)
+			return -ENOMEM;
+	}
+
+	memcpy(adapter->ixgbe_ieee_pfc, pfc, sizeof(*adapter->ixgbe_ieee_pfc));
+	err = ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en);
+	return err;
+}
+
 const struct dcbnl_rtnl_ops dcbnl_ops = {
+	.ieee_getets	= ixgbe_dcbnl_ieee_getets,
+	.ieee_setets	= ixgbe_dcbnl_ieee_setets,
+	.ieee_getpfc	= ixgbe_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= ixgbe_dcbnl_ieee_setpfc,
 	.getstate	= ixgbe_dcbnl_get_state,
 	.setstate	= ixgbe_dcbnl_set_state,
 	.getpermhwaddr	= ixgbe_dcbnl_get_perm_hw_addr,
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 1e4814875945..c2e09b9cff46 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -5609,6 +5609,10 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	}
 
 	ixgbe_clear_interrupt_scheme(adapter);
+#ifdef CONFIG_DCB
+	kfree(adapter->ixgbe_ieee_pfc);
+	kfree(adapter->ixgbe_ieee_ets);
+#endif
 
 #ifdef CONFIG_PM
 	retval = pci_save_state(pdev);
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 68cd248f6d3e..cd8d518efa3b 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -25,6 +25,11 @@
 /* IEEE 802.1Qaz std supported values */
 #define IEEE_8021QAZ_MAX_TCS	8
 
+#define IEEE_8021QAZ_TSA_STRICT		0
+#define IEEE_8021QAZ_TSA_CB_SHABER	1
+#define IEEE_8021QAZ_TSA_ETS		2
+#define IEEE_8021QAZ_TSA_VENDOR		255
+
 /* This structure contains the IEEE 802.1Qaz ETS managed object
  *
  * @willing: willing bit in ETS configuratin TLV
-- 
cgit v1.2.3


From 868baf07b1a259f5f3803c1dc2777b6c358f83cf Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 10 Feb 2011 21:26:13 -0500
Subject: ftrace: Fix memory leak with function graph and cpu hotplug

When the fuction graph tracer starts, it needs to make a special
stack for each task to save the real return values of the tasks.
All running tasks have this stack created, as well as any new
tasks.

On CPU hot plug, the new idle task will allocate a stack as well
when init_idle() is called. The problem is that cpu hotplug does
not create a new idle_task. Instead it uses the idle task that
existed when the cpu went down.

ftrace_graph_init_task() will add a new ret_stack to the task
that is given to it. Because a clone will make the task
have a stack of its parent it does not check if the task's
ret_stack is already NULL or not. When the CPU hotplug code
starts a CPU up again, it will allocate a new stack even
though one already existed for it.

The solution is to treat the idle_task specially. In fact, the
function_graph code already does, just not at init_idle().
Instead of using the ftrace_graph_init_task() for the idle task,
which that function expects the task to be a clone, have a
separate ftrace_graph_init_idle_task(). Also, we will create a
per_cpu ret_stack that is used by the idle task. When we call
ftrace_graph_init_idle_task() it will check if the idle task's
ret_stack is NULL, if it is, then it will assign it the per_cpu
ret_stack.

Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stable Tree <stable@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  2 ++
 kernel/sched.c         |  2 +-
 kernel/trace/ftrace.c  | 52 +++++++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 48 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index dcd6a7c3a435..ca29e03c1fac 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -428,6 +428,7 @@ extern void unregister_ftrace_graph(void);
 
 extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
+extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 
 static inline int task_curr_ret_stack(struct task_struct *t)
 {
@@ -451,6 +452,7 @@ static inline void unpause_graph_tracing(void)
 
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
+static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
 
 static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			  trace_func_graph_ent_t entryfunc)
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..fbe86cb04b61 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5571,7 +5571,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
-	ftrace_graph_init_task(idle);
+	ftrace_graph_init_idle_task(idle, cpu);
 }
 
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f3dadae83883..888b611897d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3328,7 +3328,7 @@ static int start_graph_tracing(void)
 	/* The cpu_boot init_task->ret_stack will never be freed */
 	for_each_online_cpu(cpu) {
 		if (!idle_task(cpu)->ret_stack)
-			ftrace_graph_init_task(idle_task(cpu));
+			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
 	}
 
 	do {
@@ -3418,6 +3418,49 @@ void unregister_ftrace_graph(void)
 	mutex_unlock(&ftrace_lock);
 }
 
+static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack);
+
+static void
+graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
+{
+	atomic_set(&t->tracing_graph_pause, 0);
+	atomic_set(&t->trace_overrun, 0);
+	t->ftrace_timestamp = 0;
+	/* make curr_ret_stack visable before we add the ret_stack */
+	smp_wmb();
+	t->ret_stack = ret_stack;
+}
+
+/*
+ * Allocate a return stack for the idle task. May be the first
+ * time through, or it may be done by CPU hotplug online.
+ */
+void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
+{
+	t->curr_ret_stack = -1;
+	/*
+	 * The idle task has no parent, it either has its own
+	 * stack or no stack at all.
+	 */
+	if (t->ret_stack)
+		WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu));
+
+	if (ftrace_graph_active) {
+		struct ftrace_ret_stack *ret_stack;
+
+		ret_stack = per_cpu(idle_ret_stack, cpu);
+		if (!ret_stack) {
+			ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+					    * sizeof(struct ftrace_ret_stack),
+					    GFP_KERNEL);
+			if (!ret_stack)
+				return;
+			per_cpu(idle_ret_stack, cpu) = ret_stack;
+		}
+		graph_init_task(t, ret_stack);
+	}
+}
+
 /* Allocate a return stack for newly created task */
 void ftrace_graph_init_task(struct task_struct *t)
 {
@@ -3433,12 +3476,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 				GFP_KERNEL);
 		if (!ret_stack)
 			return;
-		atomic_set(&t->tracing_graph_pause, 0);
-		atomic_set(&t->trace_overrun, 0);
-		t->ftrace_timestamp = 0;
-		/* make curr_ret_stack visable before we add the ret_stack */
-		smp_wmb();
-		t->ret_stack = ret_stack;
+		graph_init_task(t, ret_stack);
 	}
 }
 
-- 
cgit v1.2.3


From e89d15eeadb172bd53ca6362bf9ab6b22077224c Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed, 9 Feb 2011 15:35:03 -0800
Subject: [SCSI] target: Remove procfs based target_core_mib.c code

This patch removes the legacy procfs based target_core_mib.c code,
and moves the necessary scsi_index_tables functions and defines into
target_core_transport.c and target_core_base.h code to allow existing
fabric independent statistics to function.

This includes the removal of a handful of 'atomic_t mib_ref_count'
counters used in struct se_node_acl, se_session and se_hba to prevent
removal while using seq_list procfs walking logic.

[jejb: fix up compile failures]
Signed-off-by: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
---
 drivers/target/Makefile                |    3 +-
 drivers/target/target_core_configfs.c  |   15 -
 drivers/target/target_core_device.c    |    3 -
 drivers/target/target_core_mib.c       | 1078 --------------------------------
 drivers/target/target_core_mib.h       |   28 -
 drivers/target/target_core_tpg.c       |   29 +-
 drivers/target/target_core_transport.c |   42 +-
 include/target/target_core_base.h      |   27 +-
 include/target/target_core_transport.h |    2 +
 9 files changed, 79 insertions(+), 1148 deletions(-)
 delete mode 100644 drivers/target/target_core_mib.c
 delete mode 100644 drivers/target/target_core_mib.h

(limited to 'include')

diff --git a/drivers/target/Makefile b/drivers/target/Makefile
index 5cfd70819f08..973bb190ef57 100644
--- a/drivers/target/Makefile
+++ b/drivers/target/Makefile
@@ -13,8 +13,7 @@ target_core_mod-y		:= target_core_configfs.o \
 				   target_core_transport.o \
 				   target_core_cdb.o \
 				   target_core_ua.o \
-				   target_core_rd.o \
-				   target_core_mib.o
+				   target_core_rd.o
 
 obj-$(CONFIG_TARGET_CORE)	+= target_core_mod.o
 
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 1cb74d57ed5f..e77001b16063 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -37,7 +37,6 @@
 #include <linux/parser.h>
 #include <linux/syscalls.h>
 #include <linux/configfs.h>
-#include <linux/proc_fs.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_device.h>
@@ -3022,7 +3021,6 @@ static int target_core_init_configfs(void)
 	struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL;
 	struct config_group *lu_gp_cg = NULL;
 	struct configfs_subsystem *subsys;
-	struct proc_dir_entry *scsi_target_proc = NULL;
 	struct t10_alua_lu_gp *lu_gp;
 	int ret;
 
@@ -3128,21 +3126,10 @@ static int target_core_init_configfs(void)
 	if (core_dev_setup_virtual_lun0() < 0)
 		goto out;
 
-	scsi_target_proc = proc_mkdir("scsi_target", 0);
-	if (!(scsi_target_proc)) {
-		printk(KERN_ERR "proc_mkdir(scsi_target, 0) failed\n");
-		goto out;
-	}
-	ret = init_scsi_target_mib();
-	if (ret < 0)
-		goto out;
-
 	return 0;
 
 out:
 	configfs_unregister_subsystem(subsys);
-	if (scsi_target_proc)
-		remove_proc_entry("scsi_target", 0);
 	core_dev_release_virtual_lun0();
 	rd_module_exit();
 out_global:
@@ -3210,8 +3197,6 @@ static void target_core_exit_configfs(void)
 	printk(KERN_INFO "TARGET_CORE[0]: Released ConfigFS Fabric"
 			" Infrastructure\n");
 
-	remove_scsi_target_mib();
-	remove_proc_entry("scsi_target", 0);
 	core_dev_release_virtual_lun0();
 	rd_module_exit();
 	release_se_global();
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 9551ab541f03..5da051a07fa3 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -867,9 +867,6 @@ static void se_dev_stop(struct se_device *dev)
 		}
 	}
 	spin_unlock(&hba->device_lock);
-
-	while (atomic_read(&hba->dev_mib_access_count))
-		cpu_relax();
 }
 
 int se_dev_check_online(struct se_device *dev)
diff --git a/drivers/target/target_core_mib.c b/drivers/target/target_core_mib.c
deleted file mode 100644
index d5a48aa0d2d1..000000000000
--- a/drivers/target/target_core_mib.c
+++ /dev/null
@@ -1,1078 +0,0 @@
-/*******************************************************************************
- * Filename:  target_core_mib.c
- *
- * Copyright (c) 2006-2007 SBE, Inc.  All Rights Reserved.
- * Copyright (c) 2007-2010 Rising Tide Systems
- * Copyright (c) 2008-2010 Linux-iSCSI.org
- *
- * Nicholas A. Bellinger <nab@linux-iscsi.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- ******************************************************************************/
-
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/timer.h>
-#include <linux/string.h>
-#include <linux/version.h>
-#include <generated/utsrelease.h>
-#include <linux/utsname.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/blkdev.h>
-#include <scsi/scsi.h>
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_host.h>
-
-#include <target/target_core_base.h>
-#include <target/target_core_transport.h>
-#include <target/target_core_fabric_ops.h>
-#include <target/target_core_configfs.h>
-
-#include "target_core_hba.h"
-#include "target_core_mib.h"
-
-/* SCSI mib table index */
-static struct scsi_index_table scsi_index_table;
-
-#ifndef INITIAL_JIFFIES
-#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ))
-#endif
-
-/* SCSI Instance Table */
-#define SCSI_INST_SW_INDEX		1
-#define SCSI_TRANSPORT_INDEX		1
-
-#define NONE		"None"
-#define ISPRINT(a)   ((a >= ' ') && (a <= '~'))
-
-static inline int list_is_first(const struct list_head *list,
-				const struct list_head *head)
-{
-	return list->prev == head;
-}
-
-static void *locate_hba_start(
-	struct seq_file *seq,
-	loff_t *pos)
-{
-	spin_lock(&se_global->g_device_lock);
-	return seq_list_start(&se_global->g_se_dev_list, *pos);
-}
-
-static void *locate_hba_next(
-	struct seq_file *seq,
-	void *v,
-	loff_t *pos)
-{
-	return seq_list_next(v, &se_global->g_se_dev_list, pos);
-}
-
-static void locate_hba_stop(struct seq_file *seq, void *v)
-{
-	spin_unlock(&se_global->g_device_lock);
-}
-
-/****************************************************************************
- * SCSI MIB Tables
- ****************************************************************************/
-
-/*
- * SCSI Instance Table
- */
-static void *scsi_inst_seq_start(
-	struct seq_file *seq,
-	loff_t *pos)
-{
-	spin_lock(&se_global->hba_lock);
-	return seq_list_start(&se_global->g_hba_list, *pos);
-}
-
-static void *scsi_inst_seq_next(
-	struct seq_file *seq,
-	void *v,
-	loff_t *pos)
-{
-	return seq_list_next(v, &se_global->g_hba_list, pos);
-}
-
-static void scsi_inst_seq_stop(struct seq_file *seq, void *v)
-{
-	spin_unlock(&se_global->hba_lock);
-}
-
-static int scsi_inst_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba = list_entry(v, struct se_hba, hba_list);
-
-	if (list_is_first(&hba->hba_list, &se_global->g_hba_list))
-		seq_puts(seq, "inst sw_indx\n");
-
-	seq_printf(seq, "%u %u\n", hba->hba_index, SCSI_INST_SW_INDEX);
-	seq_printf(seq, "plugin: %s version: %s\n",
-			hba->transport->name, TARGET_CORE_VERSION);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_inst_seq_ops = {
-	.start	= scsi_inst_seq_start,
-	.next	= scsi_inst_seq_next,
-	.stop	= scsi_inst_seq_stop,
-	.show	= scsi_inst_seq_show
-};
-
-static int scsi_inst_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_inst_seq_ops);
-}
-
-static const struct file_operations scsi_inst_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_inst_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Device Table
- */
-static void *scsi_dev_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	return locate_hba_start(seq, pos);
-}
-
-static void *scsi_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_dev_seq_stop(struct seq_file *seq, void *v)
-{
-	locate_hba_stop(seq, v);
-}
-
-static int scsi_dev_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba;
-	struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
-						g_se_dev_list);
-	struct se_device *dev = se_dev->se_dev_ptr;
-	char str[28];
-	int k;
-
-	if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
-		seq_puts(seq, "inst indx role ports\n");
-
-	if (!(dev))
-		return 0;
-
-	hba = dev->se_hba;
-	if (!(hba)) {
-		/* Log error ? */
-		return 0;
-	}
-
-	seq_printf(seq, "%u %u %s %u\n", hba->hba_index,
-		   dev->dev_index, "Target", dev->dev_port_count);
-
-	memcpy(&str[0], (void *)DEV_T10_WWN(dev), 28);
-
-	/* vendor */
-	for (k = 0; k < 8; k++)
-		str[k] = ISPRINT(DEV_T10_WWN(dev)->vendor[k]) ?
-				DEV_T10_WWN(dev)->vendor[k] : 0x20;
-	str[k] = 0x20;
-
-	/* model */
-	for (k = 0; k < 16; k++)
-		str[k+9] = ISPRINT(DEV_T10_WWN(dev)->model[k]) ?
-				DEV_T10_WWN(dev)->model[k] : 0x20;
-	str[k + 9] = 0;
-
-	seq_printf(seq, "dev_alias: %s\n", str);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_dev_seq_ops = {
-	.start  = scsi_dev_seq_start,
-	.next   = scsi_dev_seq_next,
-	.stop   = scsi_dev_seq_stop,
-	.show   = scsi_dev_seq_show
-};
-
-static int scsi_dev_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_dev_seq_ops);
-}
-
-static const struct file_operations scsi_dev_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_dev_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Port Table
- */
-static void *scsi_port_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	return locate_hba_start(seq, pos);
-}
-
-static void *scsi_port_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_port_seq_stop(struct seq_file *seq, void *v)
-{
-	locate_hba_stop(seq, v);
-}
-
-static int scsi_port_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba;
-	struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
-						g_se_dev_list);
-	struct se_device *dev = se_dev->se_dev_ptr;
-	struct se_port *sep, *sep_tmp;
-
-	if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
-		seq_puts(seq, "inst device indx role busy_count\n");
-
-	if (!(dev))
-		return 0;
-
-	hba = dev->se_hba;
-	if (!(hba)) {
-		/* Log error ? */
-		return 0;
-	}
-
-	/* FIXME: scsiPortBusyStatuses count */
-	spin_lock(&dev->se_port_lock);
-	list_for_each_entry_safe(sep, sep_tmp, &dev->dev_sep_list, sep_list) {
-		seq_printf(seq, "%u %u %u %s%u %u\n", hba->hba_index,
-			dev->dev_index, sep->sep_index, "Device",
-			dev->dev_index, 0);
-	}
-	spin_unlock(&dev->se_port_lock);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_port_seq_ops = {
-	.start  = scsi_port_seq_start,
-	.next   = scsi_port_seq_next,
-	.stop   = scsi_port_seq_stop,
-	.show   = scsi_port_seq_show
-};
-
-static int scsi_port_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_port_seq_ops);
-}
-
-static const struct file_operations scsi_port_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_port_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Transport Table
- */
-static void *scsi_transport_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	return locate_hba_start(seq, pos);
-}
-
-static void *scsi_transport_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_transport_seq_stop(struct seq_file *seq, void *v)
-{
-	locate_hba_stop(seq, v);
-}
-
-static int scsi_transport_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba;
-	struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
-						g_se_dev_list);
-	struct se_device *dev = se_dev->se_dev_ptr;
-	struct se_port *se, *se_tmp;
-	struct se_portal_group *tpg;
-	struct t10_wwn *wwn;
-	char buf[64];
-
-	if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
-		seq_puts(seq, "inst device indx dev_name\n");
-
-	if (!(dev))
-		return 0;
-
-	hba = dev->se_hba;
-	if (!(hba)) {
-		/* Log error ? */
-		return 0;
-	}
-
-	wwn = DEV_T10_WWN(dev);
-
-	spin_lock(&dev->se_port_lock);
-	list_for_each_entry_safe(se, se_tmp, &dev->dev_sep_list, sep_list) {
-		tpg = se->sep_tpg;
-		sprintf(buf, "scsiTransport%s",
-				TPG_TFO(tpg)->get_fabric_name());
-
-		seq_printf(seq, "%u %s %u %s+%s\n",
-			hba->hba_index, /* scsiTransportIndex */
-			buf,  /* scsiTransportType */
-			(TPG_TFO(tpg)->tpg_get_inst_index != NULL) ?
-			TPG_TFO(tpg)->tpg_get_inst_index(tpg) :
-			0,
-			TPG_TFO(tpg)->tpg_get_wwn(tpg),
-			(strlen(wwn->unit_serial)) ?
-			/* scsiTransportDevName */
-			wwn->unit_serial : wwn->vendor);
-	}
-	spin_unlock(&dev->se_port_lock);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_transport_seq_ops = {
-	.start  = scsi_transport_seq_start,
-	.next   = scsi_transport_seq_next,
-	.stop   = scsi_transport_seq_stop,
-	.show   = scsi_transport_seq_show
-};
-
-static int scsi_transport_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_transport_seq_ops);
-}
-
-static const struct file_operations scsi_transport_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_transport_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Target Device Table
- */
-static void *scsi_tgt_dev_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	return locate_hba_start(seq, pos);
-}
-
-static void *scsi_tgt_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_tgt_dev_seq_stop(struct seq_file *seq, void *v)
-{
-	locate_hba_stop(seq, v);
-}
-
-
-#define LU_COUNT	1  /* for now */
-static int scsi_tgt_dev_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba;
-	struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
-						g_se_dev_list);
-	struct se_device *dev = se_dev->se_dev_ptr;
-	int non_accessible_lus = 0;
-	char status[16];
-
-	if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
-		seq_puts(seq, "inst indx num_LUs status non_access_LUs"
-			" resets\n");
-
-	if (!(dev))
-		return 0;
-
-	hba = dev->se_hba;
-	if (!(hba)) {
-		/* Log error ? */
-		return 0;
-	}
-
-	switch (dev->dev_status) {
-	case TRANSPORT_DEVICE_ACTIVATED:
-		strcpy(status, "activated");
-		break;
-	case TRANSPORT_DEVICE_DEACTIVATED:
-		strcpy(status, "deactivated");
-		non_accessible_lus = 1;
-		break;
-	case TRANSPORT_DEVICE_SHUTDOWN:
-		strcpy(status, "shutdown");
-		non_accessible_lus = 1;
-		break;
-	case TRANSPORT_DEVICE_OFFLINE_ACTIVATED:
-	case TRANSPORT_DEVICE_OFFLINE_DEACTIVATED:
-		strcpy(status, "offline");
-		non_accessible_lus = 1;
-		break;
-	default:
-		sprintf(status, "unknown(%d)", dev->dev_status);
-		non_accessible_lus = 1;
-	}
-
-	seq_printf(seq, "%u %u %u %s %u %u\n",
-		   hba->hba_index, dev->dev_index, LU_COUNT,
-		   status, non_accessible_lus, dev->num_resets);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_tgt_dev_seq_ops = {
-	.start  = scsi_tgt_dev_seq_start,
-	.next   = scsi_tgt_dev_seq_next,
-	.stop   = scsi_tgt_dev_seq_stop,
-	.show   = scsi_tgt_dev_seq_show
-};
-
-static int scsi_tgt_dev_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_tgt_dev_seq_ops);
-}
-
-static const struct file_operations scsi_tgt_dev_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_tgt_dev_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Target Port Table
- */
-static void *scsi_tgt_port_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	return locate_hba_start(seq, pos);
-}
-
-static void *scsi_tgt_port_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_tgt_port_seq_stop(struct seq_file *seq, void *v)
-{
-	locate_hba_stop(seq, v);
-}
-
-static int scsi_tgt_port_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba;
-	struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
-						g_se_dev_list);
-	struct se_device *dev = se_dev->se_dev_ptr;
-	struct se_port *sep, *sep_tmp;
-	struct se_portal_group *tpg;
-	u32 rx_mbytes, tx_mbytes;
-	unsigned long long num_cmds;
-	char buf[64];
-
-	if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
-		seq_puts(seq, "inst device indx name port_index in_cmds"
-			" write_mbytes read_mbytes hs_in_cmds\n");
-
-	if (!(dev))
-		return 0;
-
-	hba = dev->se_hba;
-	if (!(hba)) {
-		/* Log error ? */
-		return 0;
-	}
-
-	spin_lock(&dev->se_port_lock);
-	list_for_each_entry_safe(sep, sep_tmp, &dev->dev_sep_list, sep_list) {
-		tpg = sep->sep_tpg;
-		sprintf(buf, "%sPort#",
-			TPG_TFO(tpg)->get_fabric_name());
-
-		seq_printf(seq, "%u %u %u %s%d %s%s%d ",
-		     hba->hba_index,
-		     dev->dev_index,
-		     sep->sep_index,
-		     buf, sep->sep_index,
-		     TPG_TFO(tpg)->tpg_get_wwn(tpg), "+t+",
-		     TPG_TFO(tpg)->tpg_get_tag(tpg));
-
-		spin_lock(&sep->sep_lun->lun_sep_lock);
-		num_cmds = sep->sep_stats.cmd_pdus;
-		rx_mbytes = (sep->sep_stats.rx_data_octets >> 20);
-		tx_mbytes = (sep->sep_stats.tx_data_octets >> 20);
-		spin_unlock(&sep->sep_lun->lun_sep_lock);
-
-		seq_printf(seq, "%llu %u %u %u\n", num_cmds,
-			rx_mbytes, tx_mbytes, 0);
-	}
-	spin_unlock(&dev->se_port_lock);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_tgt_port_seq_ops = {
-	.start  = scsi_tgt_port_seq_start,
-	.next   = scsi_tgt_port_seq_next,
-	.stop   = scsi_tgt_port_seq_stop,
-	.show   = scsi_tgt_port_seq_show
-};
-
-static int scsi_tgt_port_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_tgt_port_seq_ops);
-}
-
-static const struct file_operations scsi_tgt_port_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_tgt_port_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Authorized Initiator Table:
- * It contains the SCSI Initiators authorized to be attached to one of the
- * local Target ports.
- * Iterates through all active TPGs and extracts the info from the ACLs
- */
-static void *scsi_auth_intr_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	spin_lock_bh(&se_global->se_tpg_lock);
-	return seq_list_start(&se_global->g_se_tpg_list, *pos);
-}
-
-static void *scsi_auth_intr_seq_next(struct seq_file *seq, void *v,
-					 loff_t *pos)
-{
-	return seq_list_next(v, &se_global->g_se_tpg_list, pos);
-}
-
-static void scsi_auth_intr_seq_stop(struct seq_file *seq, void *v)
-{
-	spin_unlock_bh(&se_global->se_tpg_lock);
-}
-
-static int scsi_auth_intr_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_portal_group *se_tpg = list_entry(v, struct se_portal_group,
-						se_tpg_list);
-	struct se_dev_entry *deve;
-	struct se_lun *lun;
-	struct se_node_acl *se_nacl;
-	int j;
-
-	if (list_is_first(&se_tpg->se_tpg_list,
-			  &se_global->g_se_tpg_list))
-		seq_puts(seq, "inst dev port indx dev_or_port intr_name "
-			 "map_indx att_count num_cmds read_mbytes "
-			 "write_mbytes hs_num_cmds creation_time row_status\n");
-
-	if (!(se_tpg))
-		return 0;
-
-	spin_lock(&se_tpg->acl_node_lock);
-	list_for_each_entry(se_nacl, &se_tpg->acl_node_list, acl_list) {
-
-		atomic_inc(&se_nacl->mib_ref_count);
-		smp_mb__after_atomic_inc();
-		spin_unlock(&se_tpg->acl_node_lock);
-
-		spin_lock_irq(&se_nacl->device_list_lock);
-		for (j = 0; j < TRANSPORT_MAX_LUNS_PER_TPG; j++) {
-			deve = &se_nacl->device_list[j];
-			if (!(deve->lun_flags &
-					TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) ||
-			    (!deve->se_lun))
-				continue;
-			lun = deve->se_lun;
-			if (!lun->lun_se_dev)
-				continue;
-
-			seq_printf(seq, "%u %u %u %u %u %s %u %u %u %u %u %u"
-					" %u %s\n",
-				/* scsiInstIndex */
-				(TPG_TFO(se_tpg)->tpg_get_inst_index != NULL) ?
-				TPG_TFO(se_tpg)->tpg_get_inst_index(se_tpg) :
-				0,
-				/* scsiDeviceIndex */
-				lun->lun_se_dev->dev_index,
-				/* scsiAuthIntrTgtPortIndex */
-				TPG_TFO(se_tpg)->tpg_get_tag(se_tpg),
-				/* scsiAuthIntrIndex */
-				se_nacl->acl_index,
-				/* scsiAuthIntrDevOrPort */
-				1,
-				/* scsiAuthIntrName */
-				se_nacl->initiatorname[0] ?
-					se_nacl->initiatorname : NONE,
-				/* FIXME: scsiAuthIntrLunMapIndex */
-				0,
-				/* scsiAuthIntrAttachedTimes */
-				deve->attach_count,
-				/* scsiAuthIntrOutCommands */
-				deve->total_cmds,
-				/* scsiAuthIntrReadMegaBytes */
-				(u32)(deve->read_bytes >> 20),
-				/* scsiAuthIntrWrittenMegaBytes */
-				(u32)(deve->write_bytes >> 20),
-				/* FIXME: scsiAuthIntrHSOutCommands */
-				0,
-				/* scsiAuthIntrLastCreation */
-				(u32)(((u32)deve->creation_time -
-					    INITIAL_JIFFIES) * 100 / HZ),
-				/* FIXME: scsiAuthIntrRowStatus */
-				"Ready");
-		}
-		spin_unlock_irq(&se_nacl->device_list_lock);
-
-		spin_lock(&se_tpg->acl_node_lock);
-		atomic_dec(&se_nacl->mib_ref_count);
-		smp_mb__after_atomic_dec();
-	}
-	spin_unlock(&se_tpg->acl_node_lock);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_auth_intr_seq_ops = {
-	.start	= scsi_auth_intr_seq_start,
-	.next	= scsi_auth_intr_seq_next,
-	.stop	= scsi_auth_intr_seq_stop,
-	.show	= scsi_auth_intr_seq_show
-};
-
-static int scsi_auth_intr_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_auth_intr_seq_ops);
-}
-
-static const struct file_operations scsi_auth_intr_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_auth_intr_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Attached Initiator Port Table:
- * It lists the SCSI Initiators attached to one of the local Target ports.
- * Iterates through all active TPGs and use active sessions from each TPG
- * to list the info fo this table.
- */
-static void *scsi_att_intr_port_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	spin_lock_bh(&se_global->se_tpg_lock);
-	return seq_list_start(&se_global->g_se_tpg_list, *pos);
-}
-
-static void *scsi_att_intr_port_seq_next(struct seq_file *seq, void *v,
-					 loff_t *pos)
-{
-	return seq_list_next(v, &se_global->g_se_tpg_list, pos);
-}
-
-static void scsi_att_intr_port_seq_stop(struct seq_file *seq, void *v)
-{
-	spin_unlock_bh(&se_global->se_tpg_lock);
-}
-
-static int scsi_att_intr_port_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_portal_group *se_tpg = list_entry(v, struct se_portal_group,
-						se_tpg_list);
-	struct se_dev_entry *deve;
-	struct se_lun *lun;
-	struct se_node_acl *se_nacl;
-	struct se_session *se_sess;
-	unsigned char buf[64];
-	int j;
-
-	if (list_is_first(&se_tpg->se_tpg_list,
-			  &se_global->g_se_tpg_list))
-		seq_puts(seq, "inst dev port indx port_auth_indx port_name"
-			" port_ident\n");
-
-	if (!(se_tpg))
-		return 0;
-
-	spin_lock(&se_tpg->session_lock);
-	list_for_each_entry(se_sess, &se_tpg->tpg_sess_list, sess_list) {
-		if ((TPG_TFO(se_tpg)->sess_logged_in(se_sess)) ||
-		    (!se_sess->se_node_acl) ||
-		    (!se_sess->se_node_acl->device_list))
-			continue;
-
-		atomic_inc(&se_sess->mib_ref_count);
-		smp_mb__after_atomic_inc();
-		se_nacl = se_sess->se_node_acl;
-		atomic_inc(&se_nacl->mib_ref_count);
-		smp_mb__after_atomic_inc();
-		spin_unlock(&se_tpg->session_lock);
-
-		spin_lock_irq(&se_nacl->device_list_lock);
-		for (j = 0; j < TRANSPORT_MAX_LUNS_PER_TPG; j++) {
-			deve = &se_nacl->device_list[j];
-			if (!(deve->lun_flags &
-					TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) ||
-			   (!deve->se_lun))
-				continue;
-
-			lun = deve->se_lun;
-			if (!lun->lun_se_dev)
-				continue;
-
-			memset(buf, 0, 64);
-			if (TPG_TFO(se_tpg)->sess_get_initiator_sid != NULL)
-				TPG_TFO(se_tpg)->sess_get_initiator_sid(
-					se_sess, (unsigned char *)&buf[0], 64);
-
-			seq_printf(seq, "%u %u %u %u %u %s+i+%s\n",
-				/* scsiInstIndex */
-				(TPG_TFO(se_tpg)->tpg_get_inst_index != NULL) ?
-				TPG_TFO(se_tpg)->tpg_get_inst_index(se_tpg) :
-				0,
-				/* scsiDeviceIndex */
-				lun->lun_se_dev->dev_index,
-				/* scsiPortIndex */
-				TPG_TFO(se_tpg)->tpg_get_tag(se_tpg),
-				/* scsiAttIntrPortIndex */
-				(TPG_TFO(se_tpg)->sess_get_index != NULL) ?
-				TPG_TFO(se_tpg)->sess_get_index(se_sess) :
-				0,
-				/* scsiAttIntrPortAuthIntrIdx */
-				se_nacl->acl_index,
-				/* scsiAttIntrPortName */
-				se_nacl->initiatorname[0] ?
-					se_nacl->initiatorname : NONE,
-				/* scsiAttIntrPortIdentifier */
-				buf);
-		}
-		spin_unlock_irq(&se_nacl->device_list_lock);
-
-		spin_lock(&se_tpg->session_lock);
-		atomic_dec(&se_nacl->mib_ref_count);
-		smp_mb__after_atomic_dec();
-		atomic_dec(&se_sess->mib_ref_count);
-		smp_mb__after_atomic_dec();
-	}
-	spin_unlock(&se_tpg->session_lock);
-
-	return 0;
-}
-
-static const struct seq_operations scsi_att_intr_port_seq_ops = {
-	.start	= scsi_att_intr_port_seq_start,
-	.next	= scsi_att_intr_port_seq_next,
-	.stop	= scsi_att_intr_port_seq_stop,
-	.show	= scsi_att_intr_port_seq_show
-};
-
-static int scsi_att_intr_port_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_att_intr_port_seq_ops);
-}
-
-static const struct file_operations scsi_att_intr_port_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_att_intr_port_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/*
- * SCSI Logical Unit Table
- */
-static void *scsi_lu_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	return locate_hba_start(seq, pos);
-}
-
-static void *scsi_lu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	return locate_hba_next(seq, v, pos);
-}
-
-static void scsi_lu_seq_stop(struct seq_file *seq, void *v)
-{
-	locate_hba_stop(seq, v);
-}
-
-#define SCSI_LU_INDEX		1
-static int scsi_lu_seq_show(struct seq_file *seq, void *v)
-{
-	struct se_hba *hba;
-	struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev,
-						g_se_dev_list);
-	struct se_device *dev = se_dev->se_dev_ptr;
-	int j;
-	char str[28];
-
-	if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list))
-		seq_puts(seq, "inst dev indx LUN lu_name vend prod rev"
-		" dev_type status state-bit num_cmds read_mbytes"
-		" write_mbytes resets full_stat hs_num_cmds creation_time\n");
-
-	if (!(dev))
-		return 0;
-
-	hba = dev->se_hba;
-	if (!(hba)) {
-		/* Log error ? */
-		return 0;
-	}
-
-	/* Fix LU state, if we can read it from the device */
-	seq_printf(seq, "%u %u %u %llu %s", hba->hba_index,
-			dev->dev_index, SCSI_LU_INDEX,
-			(unsigned long long)0, /* FIXME: scsiLuDefaultLun */
-			(strlen(DEV_T10_WWN(dev)->unit_serial)) ?
-			/* scsiLuWwnName */
-			(char *)&DEV_T10_WWN(dev)->unit_serial[0] :
-			"None");
-
-	memcpy(&str[0], (void *)DEV_T10_WWN(dev), 28);
-	/* scsiLuVendorId */
-	for (j = 0; j < 8; j++)
-		str[j] = ISPRINT(DEV_T10_WWN(dev)->vendor[j]) ?
-			DEV_T10_WWN(dev)->vendor[j] : 0x20;
-	str[8] = 0;
-	seq_printf(seq, " %s", str);
-
-	/* scsiLuProductId */
-	for (j = 0; j < 16; j++)
-		str[j] = ISPRINT(DEV_T10_WWN(dev)->model[j]) ?
-			DEV_T10_WWN(dev)->model[j] : 0x20;
-	str[16] = 0;
-	seq_printf(seq, " %s", str);
-
-	/* scsiLuRevisionId */
-	for (j = 0; j < 4; j++)
-		str[j] = ISPRINT(DEV_T10_WWN(dev)->revision[j]) ?
-			DEV_T10_WWN(dev)->revision[j] : 0x20;
-	str[4] = 0;
-	seq_printf(seq, " %s", str);
-
-	seq_printf(seq, " %u %s %s %llu %u %u %u %u %u %u\n",
-		/* scsiLuPeripheralType */
-		   TRANSPORT(dev)->get_device_type(dev),
-		   (dev->dev_status == TRANSPORT_DEVICE_ACTIVATED) ?
-		"available" : "notavailable", /* scsiLuStatus */
-		"exposed", 	/* scsiLuState */
-		(unsigned long long)dev->num_cmds,
-		/* scsiLuReadMegaBytes */
-		(u32)(dev->read_bytes >> 20),
-		/* scsiLuWrittenMegaBytes */
-		(u32)(dev->write_bytes >> 20),
-		dev->num_resets, /* scsiLuInResets */
-		0, /* scsiLuOutTaskSetFullStatus */
-		0, /* scsiLuHSInCommands */
-		(u32)(((u32)dev->creation_time - INITIAL_JIFFIES) *
-							100 / HZ));
-
-	return 0;
-}
-
-static const struct seq_operations scsi_lu_seq_ops = {
-	.start  = scsi_lu_seq_start,
-	.next   = scsi_lu_seq_next,
-	.stop   = scsi_lu_seq_stop,
-	.show   = scsi_lu_seq_show
-};
-
-static int scsi_lu_seq_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &scsi_lu_seq_ops);
-}
-
-static const struct file_operations scsi_lu_seq_fops = {
-	.owner	 = THIS_MODULE,
-	.open	 = scsi_lu_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
-};
-
-/****************************************************************************/
-
-/*
- * Remove proc fs entries
- */
-void remove_scsi_target_mib(void)
-{
-	remove_proc_entry("scsi_target/mib/scsi_inst", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_dev", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_port", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_transport", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_tgt_dev", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_tgt_port", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_auth_intr", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_att_intr_port", NULL);
-	remove_proc_entry("scsi_target/mib/scsi_lu", NULL);
-	remove_proc_entry("scsi_target/mib", NULL);
-}
-
-/*
- * Create proc fs entries for the mib tables
- */
-int init_scsi_target_mib(void)
-{
-	struct proc_dir_entry *dir_entry;
-	struct proc_dir_entry *scsi_inst_entry;
-	struct proc_dir_entry *scsi_dev_entry;
-	struct proc_dir_entry *scsi_port_entry;
-	struct proc_dir_entry *scsi_transport_entry;
-	struct proc_dir_entry *scsi_tgt_dev_entry;
-	struct proc_dir_entry *scsi_tgt_port_entry;
-	struct proc_dir_entry *scsi_auth_intr_entry;
-	struct proc_dir_entry *scsi_att_intr_port_entry;
-	struct proc_dir_entry *scsi_lu_entry;
-
-	dir_entry = proc_mkdir("scsi_target/mib", NULL);
-	if (!(dir_entry)) {
-		printk(KERN_ERR "proc_mkdir() failed.\n");
-		return -1;
-	}
-
-	scsi_inst_entry =
-		create_proc_entry("scsi_target/mib/scsi_inst", 0, NULL);
-	if (scsi_inst_entry)
-		scsi_inst_entry->proc_fops = &scsi_inst_seq_fops;
-	else
-		goto error;
-
-	scsi_dev_entry =
-		create_proc_entry("scsi_target/mib/scsi_dev", 0, NULL);
-	if (scsi_dev_entry)
-		scsi_dev_entry->proc_fops = &scsi_dev_seq_fops;
-	else
-		goto error;
-
-	scsi_port_entry =
-		create_proc_entry("scsi_target/mib/scsi_port", 0, NULL);
-	if (scsi_port_entry)
-		scsi_port_entry->proc_fops = &scsi_port_seq_fops;
-	else
-		goto error;
-
-	scsi_transport_entry =
-		create_proc_entry("scsi_target/mib/scsi_transport", 0, NULL);
-	if (scsi_transport_entry)
-		scsi_transport_entry->proc_fops = &scsi_transport_seq_fops;
-	else
-		goto error;
-
-	scsi_tgt_dev_entry =
-		create_proc_entry("scsi_target/mib/scsi_tgt_dev", 0, NULL);
-	if (scsi_tgt_dev_entry)
-		scsi_tgt_dev_entry->proc_fops = &scsi_tgt_dev_seq_fops;
-	else
-		goto error;
-
-	scsi_tgt_port_entry =
-		create_proc_entry("scsi_target/mib/scsi_tgt_port", 0, NULL);
-	if (scsi_tgt_port_entry)
-		scsi_tgt_port_entry->proc_fops = &scsi_tgt_port_seq_fops;
-	else
-		goto error;
-
-	scsi_auth_intr_entry =
-		create_proc_entry("scsi_target/mib/scsi_auth_intr", 0, NULL);
-	if (scsi_auth_intr_entry)
-		scsi_auth_intr_entry->proc_fops = &scsi_auth_intr_seq_fops;
-	else
-		goto error;
-
-	scsi_att_intr_port_entry =
-	      create_proc_entry("scsi_target/mib/scsi_att_intr_port", 0, NULL);
-	if (scsi_att_intr_port_entry)
-		scsi_att_intr_port_entry->proc_fops =
-				&scsi_att_intr_port_seq_fops;
-	else
-		goto error;
-
-	scsi_lu_entry = create_proc_entry("scsi_target/mib/scsi_lu", 0, NULL);
-	if (scsi_lu_entry)
-		scsi_lu_entry->proc_fops = &scsi_lu_seq_fops;
-	else
-		goto error;
-
-	return 0;
-
-error:
-	printk(KERN_ERR "create_proc_entry() failed.\n");
-	remove_scsi_target_mib();
-	return -1;
-}
-
-/*
- * Initialize the index table for allocating unique row indexes to various mib
- * tables
- */
-void init_scsi_index_table(void)
-{
-	memset(&scsi_index_table, 0, sizeof(struct scsi_index_table));
-	spin_lock_init(&scsi_index_table.lock);
-}
-
-/*
- * Allocate a new row index for the entry type specified
- */
-u32 scsi_get_new_index(scsi_index_t type)
-{
-	u32 new_index;
-
-	if ((type < 0) || (type >= SCSI_INDEX_TYPE_MAX)) {
-		printk(KERN_ERR "Invalid index type %d\n", type);
-		return -1;
-	}
-
-	spin_lock(&scsi_index_table.lock);
-	new_index = ++scsi_index_table.scsi_mib_index[type];
-	if (new_index == 0)
-		new_index = ++scsi_index_table.scsi_mib_index[type];
-	spin_unlock(&scsi_index_table.lock);
-
-	return new_index;
-}
-EXPORT_SYMBOL(scsi_get_new_index);
diff --git a/drivers/target/target_core_mib.h b/drivers/target/target_core_mib.h
deleted file mode 100644
index 277204633850..000000000000
--- a/drivers/target/target_core_mib.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef TARGET_CORE_MIB_H
-#define TARGET_CORE_MIB_H
-
-typedef enum {
-	SCSI_INST_INDEX,
-	SCSI_DEVICE_INDEX,
-	SCSI_AUTH_INTR_INDEX,
-	SCSI_INDEX_TYPE_MAX
-} scsi_index_t;
-
-struct scsi_index_table {
-	spinlock_t	lock;
-	u32 		scsi_mib_index[SCSI_INDEX_TYPE_MAX];
-} ____cacheline_aligned;
-
-/* SCSI Port stats */
-struct scsi_port_stats {
-	u64	cmd_pdus;
-	u64	tx_data_octets;
-	u64	rx_data_octets;
-} ____cacheline_aligned;
-
-extern int init_scsi_target_mib(void);
-extern void remove_scsi_target_mib(void);
-extern void init_scsi_index_table(void);
-extern u32 scsi_get_new_index(scsi_index_t);
-
-#endif   /*** TARGET_CORE_MIB_H ***/
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index abfa81a57115..c26f67467623 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -275,7 +275,6 @@ struct se_node_acl *core_tpg_check_initiator_node_acl(
 	spin_lock_init(&acl->device_list_lock);
 	spin_lock_init(&acl->nacl_sess_lock);
 	atomic_set(&acl->acl_pr_ref_count, 0);
-	atomic_set(&acl->mib_ref_count, 0);
 	acl->queue_depth = TPG_TFO(tpg)->tpg_get_default_depth(tpg);
 	snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
 	acl->se_tpg = tpg;
@@ -318,12 +317,6 @@ void core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *nacl)
 		cpu_relax();
 }
 
-void core_tpg_wait_for_mib_ref(struct se_node_acl *nacl)
-{
-	while (atomic_read(&nacl->mib_ref_count) != 0)
-		cpu_relax();
-}
-
 void core_tpg_clear_object_luns(struct se_portal_group *tpg)
 {
 	int i, ret;
@@ -480,7 +473,6 @@ int core_tpg_del_initiator_node_acl(
 	spin_unlock_bh(&tpg->session_lock);
 
 	core_tpg_wait_for_nacl_pr_ref(acl);
-	core_tpg_wait_for_mib_ref(acl);
 	core_clear_initiator_node_from_tpg(acl, tpg);
 	core_free_device_list_for_node(acl, tpg);
 
@@ -701,6 +693,8 @@ EXPORT_SYMBOL(core_tpg_register);
 
 int core_tpg_deregister(struct se_portal_group *se_tpg)
 {
+	struct se_node_acl *nacl, *nacl_tmp;
+
 	printk(KERN_INFO "TARGET_CORE[%s]: Deallocating %s struct se_portal_group"
 		" for endpoint: %s Portal Tag %u\n",
 		(se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) ?
@@ -714,6 +708,25 @@ int core_tpg_deregister(struct se_portal_group *se_tpg)
 
 	while (atomic_read(&se_tpg->tpg_pr_ref_count) != 0)
 		cpu_relax();
+	/*
+	 * Release any remaining demo-mode generated se_node_acl that have
+	 * not been released because of TFO->tpg_check_demo_mode_cache() == 1
+	 * in transport_deregister_session().
+	 */
+	spin_lock_bh(&se_tpg->acl_node_lock);
+	list_for_each_entry_safe(nacl, nacl_tmp, &se_tpg->acl_node_list,
+			acl_list) {
+		list_del(&nacl->acl_list);
+		se_tpg->num_node_acls--;
+		spin_unlock_bh(&se_tpg->acl_node_lock);
+
+		core_tpg_wait_for_nacl_pr_ref(nacl);
+		core_free_device_list_for_node(nacl, se_tpg);
+		TPG_TFO(se_tpg)->tpg_release_fabric_acl(se_tpg, nacl);
+
+		spin_lock_bh(&se_tpg->acl_node_lock);
+	}
+	spin_unlock_bh(&se_tpg->acl_node_lock);
 
 	if (se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL)
 		core_tpg_release_virtual_lun0(se_tpg);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 32dc5163b5a0..236e22d8cfae 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -379,6 +379,40 @@ void release_se_global(void)
 	se_global = NULL;
 }
 
+/* SCSI statistics table index */
+static struct scsi_index_table scsi_index_table;
+
+/*
+ * Initialize the index table for allocating unique row indexes to various mib
+ * tables.
+ */
+void init_scsi_index_table(void)
+{
+	memset(&scsi_index_table, 0, sizeof(struct scsi_index_table));
+	spin_lock_init(&scsi_index_table.lock);
+}
+
+/*
+ * Allocate a new row index for the entry type specified
+ */
+u32 scsi_get_new_index(scsi_index_t type)
+{
+	u32 new_index;
+
+	if ((type < 0) || (type >= SCSI_INDEX_TYPE_MAX)) {
+		printk(KERN_ERR "Invalid index type %d\n", type);
+		return -EINVAL;
+	}
+
+	spin_lock(&scsi_index_table.lock);
+	new_index = ++scsi_index_table.scsi_mib_index[type];
+	if (new_index == 0)
+		new_index = ++scsi_index_table.scsi_mib_index[type];
+	spin_unlock(&scsi_index_table.lock);
+
+	return new_index;
+}
+
 void transport_init_queue_obj(struct se_queue_obj *qobj)
 {
 	atomic_set(&qobj->queue_cnt, 0);
@@ -437,7 +471,6 @@ struct se_session *transport_init_session(void)
 	}
 	INIT_LIST_HEAD(&se_sess->sess_list);
 	INIT_LIST_HEAD(&se_sess->sess_acl_list);
-	atomic_set(&se_sess->mib_ref_count, 0);
 
 	return se_sess;
 }
@@ -546,12 +579,6 @@ void transport_deregister_session(struct se_session *se_sess)
 		transport_free_session(se_sess);
 		return;
 	}
-	/*
-	 * Wait for possible reference in drivers/target/target_core_mib.c:
-	 * scsi_att_intr_port_seq_show()
-	 */
-	while (atomic_read(&se_sess->mib_ref_count) != 0)
-		cpu_relax();
 
 	spin_lock_bh(&se_tpg->session_lock);
 	list_del(&se_sess->sess_list);
@@ -574,7 +601,6 @@ void transport_deregister_session(struct se_session *se_sess)
 				spin_unlock_bh(&se_tpg->acl_node_lock);
 
 				core_tpg_wait_for_nacl_pr_ref(se_nacl);
-				core_tpg_wait_for_mib_ref(se_nacl);
 				core_free_device_list_for_node(se_nacl, se_tpg);
 				TPG_TFO(se_tpg)->tpg_release_fabric_acl(se_tpg,
 						se_nacl);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 07fdfb6b9a9a..9f9265569185 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -8,7 +8,6 @@
 #include <scsi/scsi_cmnd.h>
 #include <net/sock.h>
 #include <net/tcp.h>
-#include "target_core_mib.h"
 
 #define TARGET_CORE_MOD_VERSION		"v4.0.0-rc6"
 #define SHUTDOWN_SIGS	(sigmask(SIGKILL)|sigmask(SIGINT)|sigmask(SIGABRT))
@@ -195,6 +194,21 @@ typedef enum {
 	SAM_TASK_ATTR_EMULATED
 } t10_task_attr_index_t;
 
+/*
+ * Used for target SCSI statistics
+ */
+typedef enum {
+	SCSI_INST_INDEX,
+	SCSI_DEVICE_INDEX,
+	SCSI_AUTH_INTR_INDEX,
+	SCSI_INDEX_TYPE_MAX
+} scsi_index_t;
+
+struct scsi_index_table {
+	spinlock_t	lock;
+	u32		scsi_mib_index[SCSI_INDEX_TYPE_MAX];
+} ____cacheline_aligned;
+
 struct se_cmd;
 
 struct t10_alua {
@@ -578,8 +592,6 @@ struct se_node_acl {
 	spinlock_t		stats_lock;
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
 	atomic_t		acl_pr_ref_count;
-	/* Used for MIB access */
-	atomic_t		mib_ref_count;
 	struct se_dev_entry	*device_list;
 	struct se_session	*nacl_sess;
 	struct se_portal_group *se_tpg;
@@ -595,8 +607,6 @@ struct se_node_acl {
 } ____cacheline_aligned;
 
 struct se_session {
-	/* Used for MIB access */
-	atomic_t		mib_ref_count;
 	u64			sess_bin_isid;
 	struct se_node_acl	*se_node_acl;
 	struct se_portal_group *se_tpg;
@@ -806,7 +816,6 @@ struct se_hba {
 	/* Virtual iSCSI devices attached. */
 	u32			dev_count;
 	u32			hba_index;
-	atomic_t		dev_mib_access_count;
 	atomic_t		load_balance_queue;
 	atomic_t		left_queue_depth;
 	/* Maximum queue depth the HBA can handle. */
@@ -845,6 +854,12 @@ struct se_lun {
 
 #define SE_LUN(c)		((struct se_lun *)(c)->se_lun)
 
+struct scsi_port_stats {
+       u64     cmd_pdus;
+       u64     tx_data_octets;
+       u64     rx_data_octets;
+} ____cacheline_aligned;
+
 struct se_port {
 	/* RELATIVE TARGET PORT IDENTIFER */
 	u16		sep_rtpi;
diff --git a/include/target/target_core_transport.h b/include/target/target_core_transport.h
index 66f44e56eb80..246940511579 100644
--- a/include/target/target_core_transport.h
+++ b/include/target/target_core_transport.h
@@ -111,6 +111,8 @@ struct se_subsystem_api;
 
 extern int init_se_global(void);
 extern void release_se_global(void);
+extern void init_scsi_index_table(void);
+extern u32 scsi_get_new_index(scsi_index_t);
 extern void transport_init_queue_obj(struct se_queue_obj *);
 extern int transport_subsystem_check_init(void);
 extern int transport_subsystem_register(struct se_subsystem_api *);
-- 
cgit v1.2.3


From 1f6fe7cba1c0a817a8712d7fdd0ec1b4ddd4ea2f Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed, 9 Feb 2011 15:34:54 -0800
Subject: [SCSI] target: fix use after free detected by SLUB poison

This patch moves a large number of memory release paths inside of the
configfs callback target_core_hba_item_ops->release() called from
within fs/configfs/item.c: config_item_cleanup() context.  This patch
resolves the SLUB 'Poison overwritten' warnings.

Signed-off-by: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
---
 drivers/target/target_core_configfs.c        | 120 +++++++++++++++++----------
 drivers/target/target_core_fabric_configfs.c |  92 ++++++++++++++------
 include/target/target_core_base.h            |   1 +
 3 files changed, 140 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index e77001b16063..caf8dc18ee0a 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -1970,13 +1970,35 @@ static void target_core_dev_release(struct config_item *item)
 {
 	struct se_subsystem_dev *se_dev = container_of(to_config_group(item),
 				struct se_subsystem_dev, se_dev_group);
-	struct config_group *dev_cg;
-
-	if (!(se_dev))
-		return;
+	struct se_hba *hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item);
+	struct se_subsystem_api *t = hba->transport;
+	struct config_group *dev_cg = &se_dev->se_dev_group;
 
-	dev_cg = &se_dev->se_dev_group;
 	kfree(dev_cg->default_groups);
+	/*
+	 * This pointer will set when the storage is enabled with:
+	 *`echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable`
+	 */
+	if (se_dev->se_dev_ptr) {
+		printk(KERN_INFO "Target_Core_ConfigFS: Calling se_free_"
+			"virtual_device() for se_dev_ptr: %p\n",
+			se_dev->se_dev_ptr);
+
+		se_free_virtual_device(se_dev->se_dev_ptr, hba);
+	} else {
+		/*
+		 * Release struct se_subsystem_dev->se_dev_su_ptr..
+		 */
+		printk(KERN_INFO "Target_Core_ConfigFS: Calling t->free_"
+			"device() for se_dev_su_ptr: %p\n",
+			se_dev->se_dev_su_ptr);
+
+		t->free_device(se_dev->se_dev_su_ptr);
+	}
+
+	printk(KERN_INFO "Target_Core_ConfigFS: Deallocating se_subsystem"
+			"_dev_t: %p\n", se_dev);
+	kfree(se_dev);
 }
 
 static ssize_t target_core_dev_show(struct config_item *item,
@@ -2139,7 +2161,16 @@ static struct configfs_attribute *target_core_alua_lu_gp_attrs[] = {
 	NULL,
 };
 
+static void target_core_alua_lu_gp_release(struct config_item *item)
+{
+	struct t10_alua_lu_gp *lu_gp = container_of(to_config_group(item),
+			struct t10_alua_lu_gp, lu_gp_group);
+
+	core_alua_free_lu_gp(lu_gp);
+}
+
 static struct configfs_item_operations target_core_alua_lu_gp_ops = {
+	.release		= target_core_alua_lu_gp_release,
 	.show_attribute		= target_core_alua_lu_gp_attr_show,
 	.store_attribute	= target_core_alua_lu_gp_attr_store,
 };
@@ -2190,9 +2221,11 @@ static void target_core_alua_drop_lu_gp(
 	printk(KERN_INFO "Target_Core_ConfigFS: Releasing ALUA Logical Unit"
 		" Group: core/alua/lu_gps/%s, ID: %hu\n",
 		config_item_name(item), lu_gp->lu_gp_id);
-
+	/*
+	 * core_alua_free_lu_gp() is called from target_core_alua_lu_gp_ops->release()
+	 * -> target_core_alua_lu_gp_release()
+	 */
 	config_item_put(item);
-	core_alua_free_lu_gp(lu_gp);
 }
 
 static struct configfs_group_operations target_core_alua_lu_gps_group_ops = {
@@ -2548,7 +2581,16 @@ static struct configfs_attribute *target_core_alua_tg_pt_gp_attrs[] = {
 	NULL,
 };
 
+static void target_core_alua_tg_pt_gp_release(struct config_item *item)
+{
+	struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(to_config_group(item),
+			struct t10_alua_tg_pt_gp, tg_pt_gp_group);
+
+	core_alua_free_tg_pt_gp(tg_pt_gp);
+}
+
 static struct configfs_item_operations target_core_alua_tg_pt_gp_ops = {
+	.release		= target_core_alua_tg_pt_gp_release,
 	.show_attribute		= target_core_alua_tg_pt_gp_attr_show,
 	.store_attribute	= target_core_alua_tg_pt_gp_attr_store,
 };
@@ -2601,9 +2643,11 @@ static void target_core_alua_drop_tg_pt_gp(
 	printk(KERN_INFO "Target_Core_ConfigFS: Releasing ALUA Target Port"
 		" Group: alua/tg_pt_gps/%s, ID: %hu\n",
 		config_item_name(item), tg_pt_gp->tg_pt_gp_id);
-
+	/*
+	 * core_alua_free_tg_pt_gp() is called from target_core_alua_tg_pt_gp_ops->release()
+	 * -> target_core_alua_tg_pt_gp_release().
+	 */
 	config_item_put(item);
-	core_alua_free_tg_pt_gp(tg_pt_gp);
 }
 
 static struct configfs_group_operations target_core_alua_tg_pt_gps_group_ops = {
@@ -2770,13 +2814,11 @@ static void target_core_drop_subdev(
 	struct se_subsystem_api *t;
 	struct config_item *df_item;
 	struct config_group *dev_cg, *tg_pt_gp_cg;
-	int i, ret;
+	int i;
 
 	hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item);
 
-	if (mutex_lock_interruptible(&hba->hba_access_mutex))
-		goto out;
-
+	mutex_lock(&hba->hba_access_mutex);
 	t = hba->transport;
 
 	spin_lock(&se_global->g_device_lock);
@@ -2790,7 +2832,10 @@ static void target_core_drop_subdev(
 		config_item_put(df_item);
 	}
 	kfree(tg_pt_gp_cg->default_groups);
-	core_alua_free_tg_pt_gp(T10_ALUA(se_dev)->default_tg_pt_gp);
+	/*
+	 * core_alua_free_tg_pt_gp() is called from ->default_tg_pt_gp
+	 * directly from target_core_alua_tg_pt_gp_release().
+	 */
 	T10_ALUA(se_dev)->default_tg_pt_gp = NULL;
 
 	dev_cg = &se_dev->se_dev_group;
@@ -2799,38 +2844,12 @@ static void target_core_drop_subdev(
 		dev_cg->default_groups[i] = NULL;
 		config_item_put(df_item);
 	}
-
-	config_item_put(item);
 	/*
-	 * This pointer will set when the storage is enabled with:
-	 * `echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable`
+	 * The releasing of se_dev and associated se_dev->se_dev_ptr is done
+	 * from target_core_dev_item_ops->release() ->target_core_dev_release().
 	 */
-	if (se_dev->se_dev_ptr) {
-		printk(KERN_INFO "Target_Core_ConfigFS: Calling se_free_"
-			"virtual_device() for se_dev_ptr: %p\n",
-				se_dev->se_dev_ptr);
-
-		ret = se_free_virtual_device(se_dev->se_dev_ptr, hba);
-		if (ret < 0)
-			goto hba_out;
-	} else {
-		/*
-		 * Release struct se_subsystem_dev->se_dev_su_ptr..
-		 */
-		printk(KERN_INFO "Target_Core_ConfigFS: Calling t->free_"
-			"device() for se_dev_su_ptr: %p\n",
-			se_dev->se_dev_su_ptr);
-
-		t->free_device(se_dev->se_dev_su_ptr);
-	}
-
-	printk(KERN_INFO "Target_Core_ConfigFS: Deallocating se_subsystem"
-		"_dev_t: %p\n", se_dev);
-
-hba_out:
+	config_item_put(item);
 	mutex_unlock(&hba->hba_access_mutex);
-out:
-	kfree(se_dev);
 }
 
 static struct configfs_group_operations target_core_hba_group_ops = {
@@ -2913,6 +2932,13 @@ SE_HBA_ATTR(hba_mode, S_IRUGO | S_IWUSR);
 
 CONFIGFS_EATTR_OPS(target_core_hba, se_hba, hba_group);
 
+static void target_core_hba_release(struct config_item *item)
+{
+	struct se_hba *hba = container_of(to_config_group(item),
+				struct se_hba, hba_group);
+	core_delete_hba(hba);
+}
+
 static struct configfs_attribute *target_core_hba_attrs[] = {
 	&target_core_hba_hba_info.attr,
 	&target_core_hba_hba_mode.attr,
@@ -2920,6 +2946,7 @@ static struct configfs_attribute *target_core_hba_attrs[] = {
 };
 
 static struct configfs_item_operations target_core_hba_item_ops = {
+	.release		= target_core_hba_release,
 	.show_attribute		= target_core_hba_attr_show,
 	.store_attribute	= target_core_hba_attr_store,
 };
@@ -2996,10 +3023,11 @@ static void target_core_call_delhbafromtarget(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct se_hba *hba = item_to_hba(item);
-
+	/*
+	 * core_delete_hba() is called from target_core_hba_item_ops->release()
+	 * -> target_core_hba_release()
+	 */
 	config_item_put(item);
-	core_delete_hba(hba);
 }
 
 static struct configfs_group_operations target_core_group_ops = {
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 32b148d7e261..b65d1c8e7740 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -214,12 +214,22 @@ TCM_MAPPEDLUN_ATTR(write_protect, S_IRUGO | S_IWUSR);
 
 CONFIGFS_EATTR_OPS(target_fabric_mappedlun, se_lun_acl, se_lun_group);
 
+static void target_fabric_mappedlun_release(struct config_item *item)
+{
+	struct se_lun_acl *lacl = container_of(to_config_group(item),
+				struct se_lun_acl, se_lun_group);
+	struct se_portal_group *se_tpg = lacl->se_lun_nacl->se_tpg;
+
+	core_dev_free_initiator_node_lun_acl(se_tpg, lacl);
+}
+
 static struct configfs_attribute *target_fabric_mappedlun_attrs[] = {
 	&target_fabric_mappedlun_write_protect.attr,
 	NULL,
 };
 
 static struct configfs_item_operations target_fabric_mappedlun_item_ops = {
+	.release		= target_fabric_mappedlun_release,
 	.show_attribute		= target_fabric_mappedlun_attr_show,
 	.store_attribute	= target_fabric_mappedlun_attr_store,
 	.allow_link		= target_fabric_mappedlun_link,
@@ -337,15 +347,21 @@ static void target_fabric_drop_mappedlun(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct se_lun_acl *lacl = container_of(to_config_group(item),
-			struct se_lun_acl, se_lun_group);
-	struct se_portal_group *se_tpg = lacl->se_lun_nacl->se_tpg;
-
 	config_item_put(item);
-	core_dev_free_initiator_node_lun_acl(se_tpg, lacl);
+}
+
+static void target_fabric_nacl_base_release(struct config_item *item)
+{
+	struct se_node_acl *se_nacl = container_of(to_config_group(item),
+			struct se_node_acl, acl_group);
+	struct se_portal_group *se_tpg = se_nacl->se_tpg;
+	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
+
+	tf->tf_ops.fabric_drop_nodeacl(se_nacl);
 }
 
 static struct configfs_item_operations target_fabric_nacl_base_item_ops = {
+	.release		= target_fabric_nacl_base_release,
 	.show_attribute		= target_fabric_nacl_base_attr_show,
 	.store_attribute	= target_fabric_nacl_base_attr_store,
 };
@@ -404,9 +420,6 @@ static void target_fabric_drop_nodeacl(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct se_portal_group *se_tpg = container_of(group,
-			struct se_portal_group, tpg_acl_group);
-	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
 	struct se_node_acl *se_nacl = container_of(to_config_group(item),
 			struct se_node_acl, acl_group);
 	struct config_item *df_item;
@@ -419,9 +432,10 @@ static void target_fabric_drop_nodeacl(
 		nacl_cg->default_groups[i] = NULL;
 		config_item_put(df_item);
 	}
-
+	/*
+	 * struct se_node_acl free is done in target_fabric_nacl_base_release()
+	 */
 	config_item_put(item);
-	tf->tf_ops.fabric_drop_nodeacl(se_nacl);
 }
 
 static struct configfs_group_operations target_fabric_nacl_group_ops = {
@@ -437,7 +451,18 @@ TF_CIT_SETUP(tpg_nacl, NULL, &target_fabric_nacl_group_ops, NULL);
 
 CONFIGFS_EATTR_OPS(target_fabric_np_base, se_tpg_np, tpg_np_group);
 
+static void target_fabric_np_base_release(struct config_item *item)
+{
+	struct se_tpg_np *se_tpg_np = container_of(to_config_group(item),
+				struct se_tpg_np, tpg_np_group);
+	struct se_portal_group *se_tpg = se_tpg_np->tpg_np_parent;
+	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
+
+	tf->tf_ops.fabric_drop_np(se_tpg_np);
+}
+
 static struct configfs_item_operations target_fabric_np_base_item_ops = {
+	.release		= target_fabric_np_base_release,
 	.show_attribute		= target_fabric_np_base_attr_show,
 	.store_attribute	= target_fabric_np_base_attr_store,
 };
@@ -466,6 +491,7 @@ static struct config_group *target_fabric_make_np(
 	if (!(se_tpg_np) || IS_ERR(se_tpg_np))
 		return ERR_PTR(-EINVAL);
 
+	se_tpg_np->tpg_np_parent = se_tpg;
 	config_group_init_type_name(&se_tpg_np->tpg_np_group, name,
 			&TF_CIT_TMPL(tf)->tfc_tpg_np_base_cit);
 
@@ -476,14 +502,10 @@ static void target_fabric_drop_np(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct se_portal_group *se_tpg = container_of(group,
-				struct se_portal_group, tpg_np_group);
-	struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf;
-	struct se_tpg_np *se_tpg_np = container_of(to_config_group(item),
-				struct se_tpg_np, tpg_np_group);
-
+	/*
+	 * struct se_tpg_np is released via target_fabric_np_base_release()
+	 */
 	config_item_put(item);
-	tf->tf_ops.fabric_drop_np(se_tpg_np);
 }
 
 static struct configfs_group_operations target_fabric_np_group_ops = {
@@ -814,7 +836,18 @@ TF_CIT_SETUP(tpg_param, &target_fabric_tpg_param_item_ops, NULL, NULL);
  */
 CONFIGFS_EATTR_OPS(target_fabric_tpg, se_portal_group, tpg_group);
 
+static void target_fabric_tpg_release(struct config_item *item)
+{
+	struct se_portal_group *se_tpg = container_of(to_config_group(item),
+			struct se_portal_group, tpg_group);
+	struct se_wwn *wwn = se_tpg->se_tpg_wwn;
+	struct target_fabric_configfs *tf = wwn->wwn_tf;
+
+	tf->tf_ops.fabric_drop_tpg(se_tpg);
+}
+
 static struct configfs_item_operations target_fabric_tpg_base_item_ops = {
+	.release		= target_fabric_tpg_release,
 	.show_attribute		= target_fabric_tpg_attr_show,
 	.store_attribute	= target_fabric_tpg_attr_store,
 };
@@ -872,8 +905,6 @@ static void target_fabric_drop_tpg(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct se_wwn *wwn = container_of(group, struct se_wwn, wwn_group);
-	struct target_fabric_configfs *tf = wwn->wwn_tf;
 	struct se_portal_group *se_tpg = container_of(to_config_group(item),
 				struct se_portal_group, tpg_group);
 	struct config_group *tpg_cg = &se_tpg->tpg_group;
@@ -890,15 +921,28 @@ static void target_fabric_drop_tpg(
 	}
 
 	config_item_put(item);
-	tf->tf_ops.fabric_drop_tpg(se_tpg);
 }
 
+static void target_fabric_release_wwn(struct config_item *item)
+{
+	struct se_wwn *wwn = container_of(to_config_group(item),
+				struct se_wwn, wwn_group);
+	struct target_fabric_configfs *tf = wwn->wwn_tf;
+
+	tf->tf_ops.fabric_drop_wwn(wwn);
+}
+
+static struct configfs_item_operations target_fabric_tpg_item_ops = {
+	.release	= target_fabric_release_wwn,
+};
+
 static struct configfs_group_operations target_fabric_tpg_group_ops = {
 	.make_group	= target_fabric_make_tpg,
 	.drop_item	= target_fabric_drop_tpg,
 };
 
-TF_CIT_SETUP(tpg, NULL, &target_fabric_tpg_group_ops, NULL);
+TF_CIT_SETUP(tpg, &target_fabric_tpg_item_ops, &target_fabric_tpg_group_ops,
+		NULL);
 
 /* End of tfc_tpg_cit */
 
@@ -932,13 +976,7 @@ static void target_fabric_drop_wwn(
 	struct config_group *group,
 	struct config_item *item)
 {
-	struct target_fabric_configfs *tf = container_of(group,
-				struct target_fabric_configfs, tf_group);
-	struct se_wwn *wwn = container_of(to_config_group(item),
-				struct se_wwn, wwn_group);
-
 	config_item_put(item);
-	tf->tf_ops.fabric_drop_wwn(wwn);
 }
 
 static struct configfs_group_operations target_fabric_wwn_group_ops = {
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 9f9265569185..0828b6c8610a 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -882,6 +882,7 @@ struct se_port {
 } ____cacheline_aligned;
 
 struct se_tpg_np {
+	struct se_portal_group *tpg_np_parent;
 	struct config_group	tpg_np_group;
 } ____cacheline_aligned;
 
-- 
cgit v1.2.3


From d59cfde2fb960b5970ccb5a38cea25d38b37a8e8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jpirko@redhat.com>
Date: Sat, 12 Feb 2011 00:46:06 +0000
Subject: net: remove the unnecessary dance around skb_bond_should_drop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

No need to check (master) twice and to drive in and out the header file.

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Reviewed-by: Nicolas de Pesloüan <nicolas.2p.debian@free.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 11 -----------
 net/core/dev.c            |  6 +++---
 2 files changed, 3 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c7d707452228..5a5baeaaa50f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2437,17 +2437,6 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 	dev->gso_max_size = size;
 }
 
-extern int __skb_bond_should_drop(struct sk_buff *skb,
-				  struct net_device *master);
-
-static inline int skb_bond_should_drop(struct sk_buff *skb,
-				       struct net_device *master)
-{
-	if (master)
-		return __skb_bond_should_drop(skb, master);
-	return 0;
-}
-
 extern struct pernet_operations __net_initdata loopback_net_ops;
 
 static inline int dev_ethtool_get_settings(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index 6392ea0a5910..d874fd1baf49 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3105,7 +3105,8 @@ static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
  * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
  * ARP on active-backup slaves with arp_validate enabled.
  */
-int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master)
+static int __skb_bond_should_drop(struct sk_buff *skb,
+				  struct net_device *master)
 {
 	struct net_device *dev = skb->dev;
 
@@ -3139,7 +3140,6 @@ int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master)
 	}
 	return 0;
 }
-EXPORT_SYMBOL(__skb_bond_should_drop);
 
 static int __netif_receive_skb(struct sk_buff *skb)
 {
@@ -3177,7 +3177,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	if (skb->deliver_no_wcard)
 		null_or_orig = orig_dev;
 	else if (master) {
-		if (skb_bond_should_drop(skb, master)) {
+		if (__skb_bond_should_drop(skb, master)) {
 			skb->deliver_no_wcard = 1;
 			null_or_orig = orig_dev; /* deliver only exact match */
 		} else
-- 
cgit v1.2.3


From 1765a575334f1a232c1478accdee5c7d19f4b3e3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jpirko@redhat.com>
Date: Sat, 12 Feb 2011 06:48:36 +0000
Subject: net: make dev->master general

dev->master is now tightly connected to bonding driver. This patch makes
this pointer more general and ready to be used by others.

 - netdev_set_master() - bond specifics moved to new function
   netdev_set_bond_master()
 - introduced netif_is_bond_slave() to check if device is a bonding slave

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/nes/nes.c    |  3 ++-
 drivers/infiniband/hw/nes/nes_cm.c |  2 +-
 drivers/net/bonding/bond_main.c    | 10 ++++----
 drivers/net/cxgb3/cxgb3_offload.c  |  3 ++-
 include/linux/netdevice.h          |  7 ++++++
 net/core/dev.c                     | 49 ++++++++++++++++++++++++++++----------
 6 files changed, 54 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index 3b4ec3238ceb..3d7f3664b67b 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -153,7 +153,8 @@ static int nes_inetaddr_event(struct notifier_block *notifier,
 				nesdev, nesdev->netdev[0]->name);
 		netdev = nesdev->netdev[0];
 		nesvnic = netdev_priv(netdev);
-		is_bonded = (netdev->master == event_netdev);
+		is_bonded = netif_is_bond_slave(netdev) &&
+			    (netdev->master == event_netdev);
 		if ((netdev == event_netdev) || is_bonded) {
 			if (nesvnic->rdma_enabled == 0) {
 				nes_debug(NES_DBG_NETDEV, "Returning without processing event for %s since"
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 009ec814d517..ec3aa11c36cb 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1118,7 +1118,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 		return rc;
 	}
 
-	if (nesvnic->netdev->master)
+	if (netif_is_bond_slave(netdev))
 		netdev = nesvnic->netdev->master;
 	else
 		netdev = nesvnic->netdev;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1df9f0ea9184..9f877878d636 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1594,9 +1594,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
-	res = netdev_set_master(slave_dev, bond_dev);
+	res = netdev_set_bond_master(slave_dev, bond_dev);
 	if (res) {
-		pr_debug("Error %d calling netdev_set_master\n", res);
+		pr_debug("Error %d calling netdev_set_bond_master\n", res);
 		goto err_restore_mac;
 	}
 	/* open the slave since the application closed it */
@@ -1812,7 +1812,7 @@ err_close:
 	dev_close(slave_dev);
 
 err_unset_master:
-	netdev_set_master(slave_dev, NULL);
+	netdev_set_bond_master(slave_dev, NULL);
 
 err_restore_mac:
 	if (!bond->params.fail_over_mac) {
@@ -1992,7 +1992,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
 		netif_addr_unlock_bh(bond_dev);
 	}
 
-	netdev_set_master(slave_dev, NULL);
+	netdev_set_bond_master(slave_dev, NULL);
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	read_lock_bh(&bond->lock);
@@ -2114,7 +2114,7 @@ static int bond_release_all(struct net_device *bond_dev)
 			netif_addr_unlock_bh(bond_dev);
 		}
 
-		netdev_set_master(slave_dev, NULL);
+		netdev_set_bond_master(slave_dev, NULL);
 
 		/* close slave before restoring its mac address */
 		dev_close(slave_dev);
diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c
index 7ea94b5205f8..862804f32b6e 100644
--- a/drivers/net/cxgb3/cxgb3_offload.c
+++ b/drivers/net/cxgb3/cxgb3_offload.c
@@ -186,9 +186,10 @@ static struct net_device *get_iff_from_mac(struct adapter *adapter,
 				dev = NULL;
 				if (grp)
 					dev = vlan_group_get_device(grp, vlan);
-			} else
+			} else if (netif_is_bond_slave(dev)) {
 				while (dev->master)
 					dev = dev->master;
+			}
 			return dev;
 		}
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5a5baeaaa50f..5a42b1003767 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2377,6 +2377,8 @@ extern int		netdev_max_backlog;
 extern int		netdev_tstamp_prequeue;
 extern int		weight_p;
 extern int		netdev_set_master(struct net_device *dev, struct net_device *master);
+extern int netdev_set_bond_master(struct net_device *dev,
+				  struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb);
 extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features);
 #ifdef CONFIG_BUG
@@ -2437,6 +2439,11 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 	dev->gso_max_size = size;
 }
 
+static inline int netif_is_bond_slave(struct net_device *dev)
+{
+	return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
+}
+
 extern struct pernet_operations __net_initdata loopback_net_ops;
 
 static inline int dev_ethtool_get_settings(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index d874fd1baf49..a4132766d363 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3146,7 +3146,6 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
 	struct net_device *orig_dev;
-	struct net_device *master;
 	struct net_device *null_or_orig;
 	struct net_device *orig_or_bond;
 	int ret = NET_RX_DROP;
@@ -3173,15 +3172,19 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	 */
 	null_or_orig = NULL;
 	orig_dev = skb->dev;
-	master = ACCESS_ONCE(orig_dev->master);
 	if (skb->deliver_no_wcard)
 		null_or_orig = orig_dev;
-	else if (master) {
-		if (__skb_bond_should_drop(skb, master)) {
-			skb->deliver_no_wcard = 1;
-			null_or_orig = orig_dev; /* deliver only exact match */
-		} else
-			skb->dev = master;
+	else if (netif_is_bond_slave(orig_dev)) {
+		struct net_device *bond_master = ACCESS_ONCE(orig_dev->master);
+
+		if (likely(bond_master)) {
+			if (__skb_bond_should_drop(skb, bond_master)) {
+				skb->deliver_no_wcard = 1;
+				/* deliver only exact match */
+				null_or_orig = orig_dev;
+			} else
+				skb->dev = bond_master;
+		}
 	}
 
 	__this_cpu_inc(softnet_data.processed);
@@ -4346,15 +4349,14 @@ static int __init dev_proc_init(void)
 
 
 /**
- *	netdev_set_master	-	set up master/slave pair
+ *	netdev_set_master	-	set up master pointer
  *	@slave: slave device
  *	@master: new master device
  *
  *	Changes the master device of the slave. Pass %NULL to break the
  *	bonding. The caller must hold the RTNL semaphore. On a failure
  *	a negative errno code is returned. On success the reference counts
- *	are adjusted, %RTM_NEWLINK is sent to the routing socket and the
- *	function returns zero.
+ *	are adjusted and the function returns zero.
  */
 int netdev_set_master(struct net_device *slave, struct net_device *master)
 {
@@ -4374,6 +4376,29 @@ int netdev_set_master(struct net_device *slave, struct net_device *master)
 		synchronize_net();
 		dev_put(old);
 	}
+	return 0;
+}
+EXPORT_SYMBOL(netdev_set_master);
+
+/**
+ *	netdev_set_bond_master	-	set up bonding master/slave pair
+ *	@slave: slave device
+ *	@master: new master device
+ *
+ *	Changes the master device of the slave. Pass %NULL to break the
+ *	bonding. The caller must hold the RTNL semaphore. On a failure
+ *	a negative errno code is returned. On success %RTM_NEWLINK is sent
+ *	to the routing socket and the function returns zero.
+ */
+int netdev_set_bond_master(struct net_device *slave, struct net_device *master)
+{
+	int err;
+
+	ASSERT_RTNL();
+
+	err = netdev_set_master(slave, master);
+	if (err)
+		return err;
 	if (master)
 		slave->flags |= IFF_SLAVE;
 	else
@@ -4382,7 +4407,7 @@ int netdev_set_master(struct net_device *slave, struct net_device *master)
 	rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
 	return 0;
 }
-EXPORT_SYMBOL(netdev_set_master);
+EXPORT_SYMBOL(netdev_set_bond_master);
 
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
-- 
cgit v1.2.3


From 28d639f7bd2559e3d6dc10c0316d19154b28a2a4 Mon Sep 17 00:00:00 2001
From: Stephen Warren <swarren@nvidia.com>
Date: Thu, 10 Feb 2011 15:37:13 -0700
Subject: ASoC: WM8903: Fix mic detection register definitions

* There is no hysteresis enable field in the current datasheet.
* Mic detection threshold field is only 2 bits wide.

Signed-off-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/wm8903.h | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/sound/wm8903.h b/include/sound/wm8903.h
index b4a0db2307ef..1eeebd534f7e 100644
--- a/include/sound/wm8903.h
+++ b/include/sound/wm8903.h
@@ -17,13 +17,9 @@
 /*
  * R6 (0x06) - Mic Bias Control 0
  */
-#define WM8903_MICDET_HYST_ENA                  0x0080  /* MICDET_HYST_ENA */
-#define WM8903_MICDET_HYST_ENA_MASK             0x0080  /* MICDET_HYST_ENA */
-#define WM8903_MICDET_HYST_ENA_SHIFT                 7  /* MICDET_HYST_ENA */
-#define WM8903_MICDET_HYST_ENA_WIDTH                 1  /* MICDET_HYST_ENA */
-#define WM8903_MICDET_THR_MASK                  0x0070  /* MICDET_THR - [6:4] */
-#define WM8903_MICDET_THR_SHIFT                      4  /* MICDET_THR - [6:4] */
-#define WM8903_MICDET_THR_WIDTH                      3  /* MICDET_THR - [6:4] */
+#define WM8903_MICDET_THR_MASK                  0x0030  /* MICDET_THR - [5:4] */
+#define WM8903_MICDET_THR_SHIFT                      4  /* MICDET_THR - [5:4] */
+#define WM8903_MICDET_THR_WIDTH                      2  /* MICDET_THR - [5:4] */
 #define WM8903_MICSHORT_THR_MASK                0x000C  /* MICSHORT_THR - [3:2] */
 #define WM8903_MICSHORT_THR_SHIFT                    2  /* MICSHORT_THR - [3:2] */
 #define WM8903_MICSHORT_THR_WIDTH                    2  /* MICSHORT_THR - [3:2] */
-- 
cgit v1.2.3


From fbaec0ea54f7d9131891ff98744e82c073ce03b1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jpirko@redhat.com>
Date: Sun, 13 Feb 2011 10:15:37 +0000
Subject: rtnetlink: implement setting of master device

This patch allows userspace to enslave/release slave devices via netlink
interface using IFLA_MASTER. This introduces generic way to add/remove
underling devices.

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 12 ++++++++++++
 net/core/rtnetlink.c      | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5a42b1003767..d08ef6538579 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -783,6 +783,14 @@ struct netdev_tc_txq {
  *	Set hardware filter for RFS.  rxq_index is the target queue index;
  *	flow_id is a flow ID to be passed to rps_may_expire_flow() later.
  *	Return the filter ID on success, or a negative error code.
+ *
+ *	Slave management functions (for bridge, bonding, etc). User should
+ *	call netdev_set_master() to set dev->master properly.
+ * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev);
+ *	Called to make another netdev an underling.
+ *
+ * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
+ *	Called to release previously enslaved netdev.
  */
 #define HAVE_NET_DEVICE_OPS
 struct net_device_ops {
@@ -862,6 +870,10 @@ struct net_device_ops {
 						     u16 rxq_index,
 						     u32 flow_id);
 #endif
+	int			(*ndo_add_slave)(struct net_device *dev,
+						 struct net_device *slave_dev);
+	int			(*ndo_del_slave)(struct net_device *dev,
+						 struct net_device *slave_dev);
 };
 
 /*
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index da0fe457c858..49f7ea5b4c75 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1036,6 +1036,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_MAP]		= { .len = sizeof(struct rtnl_link_ifmap) },
 	[IFLA_MTU]		= { .type = NLA_U32 },
 	[IFLA_LINK]		= { .type = NLA_U32 },
+	[IFLA_MASTER]		= { .type = NLA_U32 },
 	[IFLA_TXQLEN]		= { .type = NLA_U32 },
 	[IFLA_WEIGHT]		= { .type = NLA_U32 },
 	[IFLA_OPERSTATE]	= { .type = NLA_U8 },
@@ -1178,6 +1179,41 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 	return err;
 }
 
+static int do_set_master(struct net_device *dev, int ifindex)
+{
+	struct net_device *master_dev;
+	const struct net_device_ops *ops;
+	int err;
+
+	if (dev->master) {
+		if (dev->master->ifindex == ifindex)
+			return 0;
+		ops = dev->master->netdev_ops;
+		if (ops->ndo_del_slave) {
+			err = ops->ndo_del_slave(dev->master, dev);
+			if (err)
+				return err;
+		} else {
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (ifindex) {
+		master_dev = __dev_get_by_index(dev_net(dev), ifindex);
+		if (!master_dev)
+			return -EINVAL;
+		ops = master_dev->netdev_ops;
+		if (ops->ndo_add_slave) {
+			err = ops->ndo_add_slave(master_dev, dev);
+			if (err)
+				return err;
+		} else {
+			return -EOPNOTSUPP;
+		}
+	}
+	return 0;
+}
+
 static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
@@ -1301,6 +1337,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			goto errout;
 	}
 
+	if (tb[IFLA_MASTER]) {
+		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
+		if (err)
+			goto errout;
+		modified = 1;
+	}
+
 	if (tb[IFLA_TXQLEN])
 		dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
 
-- 
cgit v1.2.3


From 642745184f82688eb3ef0cdfaa4ba632055be9af Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Mon, 7 Feb 2011 20:08:52 -0200
Subject: Bluetooth: Merge L2CAP and SCO modules into bluetooth.ko

Actually doesn't make sense have these modules built separately.
The L2CAP layer is needed by almost all Bluetooth protocols and profiles.
There isn't any real use case without having L2CAP loaded.
SCO is only essential for Audio transfers, but it is so small that we can
have it loaded always in bluetooth.ko without problems.
If you really doesn't want it you can disable SCO in the kernel config.

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/bluetooth.h | 28 ++++++++++++++++++++++++++++
 net/bluetooth/Kconfig             | 10 ++--------
 net/bluetooth/Makefile            |  5 ++---
 net/bluetooth/af_bluetooth.c      | 32 ++++++++++++++++++++++++++++++--
 net/bluetooth/l2cap_core.c        | 16 ++--------------
 net/bluetooth/sco.c               | 16 ++--------------
 6 files changed, 66 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ed7d775337e0..43750439c521 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -205,4 +205,32 @@ extern void bt_sysfs_cleanup(void);
 
 extern struct dentry *bt_debugfs;
 
+#ifdef CONFIG_BT_L2CAP
+int l2cap_init(void);
+void l2cap_exit(void);
+#else
+static inline int l2cap_init(void)
+{
+	return 0;
+}
+
+static inline void l2cap_exit(void)
+{
+}
+#endif
+
+#ifdef CONFIG_BT_SCO
+int sco_init(void);
+void sco_exit(void);
+#else
+static inline int sco_init(void)
+{
+	return 0;
+}
+
+static inline void sco_exit(void)
+{
+}
+#endif
+
 #endif /* __BLUETOOTH_H */
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index e45eae66eaf3..c6f9c2fb4891 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -32,7 +32,7 @@ menuconfig BT
 	  more information, see <http://www.bluez.org/>.
 
 config BT_L2CAP
-	tristate "L2CAP protocol support"
+	bool "L2CAP protocol support"
 	depends on BT
 	select CRC16
 	help
@@ -40,19 +40,13 @@ config BT_L2CAP
 	  connection oriented and connection-less data transport.  L2CAP
 	  support is required for most Bluetooth applications.
 
-	  Say Y here to compile L2CAP support into the kernel or say M to
-	  compile it as module (l2cap).
-
 config BT_SCO
-	tristate "SCO links support"
+	bool "SCO links support"
 	depends on BT
 	help
 	  SCO link provides voice transport over Bluetooth.  SCO support is
 	  required for voice applications like Headset and Audio.
 
-	  Say Y here to compile SCO support into the kernel or say M to
-	  compile it as module (sco).
-
 source "net/bluetooth/rfcomm/Kconfig"
 
 source "net/bluetooth/bnep/Kconfig"
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index 339b42932b33..f04fe9a9d634 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -3,12 +3,11 @@
 #
 
 obj-$(CONFIG_BT)	+= bluetooth.o
-obj-$(CONFIG_BT_L2CAP)	+= l2cap.o
-obj-$(CONFIG_BT_SCO)	+= sco.o
 obj-$(CONFIG_BT_RFCOMM)	+= rfcomm/
 obj-$(CONFIG_BT_BNEP)	+= bnep/
 obj-$(CONFIG_BT_CMTP)	+= cmtp/
 obj-$(CONFIG_BT_HIDP)	+= hidp/
 
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o hci_sock.o hci_sysfs.o lib.o
-l2cap-y := l2cap_core.o l2cap_sock.o
+bluetooth-$(CONFIG_BT_L2CAP)	+= l2cap_core.o l2cap_sock.o
+bluetooth-$(CONFIG_BT_SCO)	+= sco.o
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 2abfe2f30453..c258027bc8fe 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -40,7 +40,7 @@
 
 #include <net/bluetooth/bluetooth.h>
 
-#define VERSION "2.15"
+#define VERSION "2.16"
 
 /* Bluetooth sockets */
 #define BT_MAX_PROTO	8
@@ -545,13 +545,41 @@ static int __init bt_init(void)
 
 	BT_INFO("HCI device and connection manager initialized");
 
-	hci_sock_init();
+	err = hci_sock_init();
+	if (err < 0)
+		goto error;
+
+	err = l2cap_init();
+	if (err < 0) {
+		hci_sock_cleanup();
+		goto sock_err;
+	}
+
+	err = sco_init();
+	if (err < 0) {
+		l2cap_exit();
+		goto sock_err;
+	}
 
 	return 0;
+
+sock_err:
+	hci_sock_cleanup();
+
+error:
+	sock_unregister(PF_BLUETOOTH);
+	bt_sysfs_cleanup();
+
+	return err;
 }
 
 static void __exit bt_exit(void)
 {
+
+	sco_exit();
+
+	l2cap_exit();
+
 	hci_sock_cleanup();
 
 	sock_unregister(PF_BLUETOOTH);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ba7f9da68998..6f054d906c6f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -55,8 +55,6 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 
-#define VERSION "2.15"
-
 int disable_ertm;
 
 static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN;
@@ -3806,7 +3804,7 @@ static struct hci_proto l2cap_hci_proto = {
 	.recv_acldata	= l2cap_recv_acldata
 };
 
-static int __init l2cap_init(void)
+int __init l2cap_init(void)
 {
 	int err;
 
@@ -3834,7 +3832,6 @@ static int __init l2cap_init(void)
 			BT_ERR("Failed to create L2CAP debug file");
 	}
 
-	BT_INFO("L2CAP ver %s", VERSION);
 	BT_INFO("L2CAP socket layer initialized");
 
 	return 0;
@@ -3845,7 +3842,7 @@ error:
 	return err;
 }
 
-static void __exit l2cap_exit(void)
+void l2cap_exit(void)
 {
 	debugfs_remove(l2cap_debugfs);
 
@@ -3866,14 +3863,5 @@ void l2cap_load(void)
 }
 EXPORT_SYMBOL(l2cap_load);
 
-module_init(l2cap_init);
-module_exit(l2cap_exit);
-
 module_param(disable_ertm, bool, 0644);
 MODULE_PARM_DESC(disable_ertm, "Disable enhanced retransmission mode");
-
-MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
-MODULE_DESCRIPTION("Bluetooth L2CAP ver " VERSION);
-MODULE_VERSION(VERSION);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("bt-proto-0");
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 926ed39912ea..c9348ddda877 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -50,8 +50,6 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/sco.h>
 
-#define VERSION "0.6"
-
 static int disable_esco;
 
 static const struct proto_ops sco_sock_ops;
@@ -1024,7 +1022,7 @@ static struct hci_proto sco_hci_proto = {
 	.recv_scodata	= sco_recv_scodata
 };
 
-static int __init sco_init(void)
+int __init sco_init(void)
 {
 	int err;
 
@@ -1052,7 +1050,6 @@ static int __init sco_init(void)
 			BT_ERR("Failed to create SCO debug file");
 	}
 
-	BT_INFO("SCO (Voice Link) ver %s", VERSION);
 	BT_INFO("SCO socket layer initialized");
 
 	return 0;
@@ -1062,7 +1059,7 @@ error:
 	return err;
 }
 
-static void __exit sco_exit(void)
+void __exit sco_exit(void)
 {
 	debugfs_remove(sco_debugfs);
 
@@ -1075,14 +1072,5 @@ static void __exit sco_exit(void)
 	proto_unregister(&sco_proto);
 }
 
-module_init(sco_init);
-module_exit(sco_exit);
-
 module_param(disable_esco, bool, 0644);
 MODULE_PARM_DESC(disable_esco, "Disable eSCO connection creation");
-
-MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
-MODULE_DESCRIPTION("Bluetooth SCO ver " VERSION);
-MODULE_VERSION(VERSION);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("bt-proto-2");
-- 
cgit v1.2.3


From d606ef3fe0c57504b8e534c58498f73a6abc049a Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Mon, 14 Feb 2011 02:05:33 +0000
Subject: phy/micrel: add ability to support 50MHz RMII clock on KZS8051RNL

Platform code can now set the MICREL_PHY_50MHZ_CLK bit of dev_flags in a fixup
routine (registered with phy_register_fixup_for_uid()), to make the KZS8051RNL
PHY work with 50MHz RMII reference clock.

Cc: David J. Choi <david.choi@micrel.com>
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 24 ++++++++++++++++--------
 include/linux/micrel_phy.h | 16 ++++++++++++++++
 2 files changed, 32 insertions(+), 8 deletions(-)
 create mode 100644 include/linux/micrel_phy.h

(limited to 'include')

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 0fd1678bc5a9..590f902deb6b 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -19,13 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/phy.h>
-
-#define	PHY_ID_KSZ9021			0x00221611
-#define	PHY_ID_KS8737			0x00221720
-#define	PHY_ID_KS8041			0x00221510
-#define	PHY_ID_KS8051			0x00221550
-/* both for ks8001 Rev. A/B, and for ks8721 Rev 3. */
-#define	PHY_ID_KS8001			0x0022161A
+#include <linux/micrel_phy.h>
 
 /* general Interrupt control/status reg in vendor specific block. */
 #define MII_KSZPHY_INTCS			0x1B
@@ -46,6 +40,7 @@
 #define KSZPHY_CTRL_INT_ACTIVE_HIGH		(1 << 9)
 #define KSZ9021_CTRL_INT_ACTIVE_HIGH		(1 << 14)
 #define KS8737_CTRL_INT_ACTIVE_HIGH		(1 << 14)
+#define KSZ8051_RMII_50MHZ_CLK			(1 << 7)
 
 static int kszphy_ack_interrupt(struct phy_device *phydev)
 {
@@ -106,6 +101,19 @@ static int kszphy_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+static int ks8051_config_init(struct phy_device *phydev)
+{
+	int regval;
+
+	if (phydev->dev_flags & MICREL_PHY_50MHZ_CLK) {
+		regval = phy_read(phydev, MII_KSZPHY_CTRL);
+		regval |= KSZ8051_RMII_50MHZ_CLK;
+		phy_write(phydev, MII_KSZPHY_CTRL, regval);
+	}
+
+	return 0;
+}
+
 static struct phy_driver ks8737_driver = {
 	.phy_id		= PHY_ID_KS8737,
 	.phy_id_mask	= 0x00fffff0,
@@ -142,7 +150,7 @@ static struct phy_driver ks8051_driver = {
 	.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause
 				| SUPPORTED_Asym_Pause),
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
-	.config_init	= kszphy_config_init,
+	.config_init	= ks8051_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
new file mode 100644
index 000000000000..dd8da342a991
--- /dev/null
+++ b/include/linux/micrel_phy.h
@@ -0,0 +1,16 @@
+#ifndef _MICREL_PHY_H
+#define _MICREL_PHY_H
+
+#define MICREL_PHY_ID_MASK	0x00fffff0
+
+#define PHY_ID_KSZ9021		0x00221611
+#define PHY_ID_KS8737		0x00221720
+#define PHY_ID_KS8041		0x00221510
+#define PHY_ID_KS8051		0x00221550
+/* both for ks8001 Rev. A/B, and for ks8721 Rev 3. */
+#define PHY_ID_KS8001		0x0022161A
+
+/* struct phy_device dev_flags definitions */
+#define MICREL_PHY_50MHZ_CLK	0x00000001
+
+#endif /* _MICREL_PHY_H */
-- 
cgit v1.2.3


From c531a12ae63b6438a7859994aca23859f5706010 Mon Sep 17 00:00:00 2001
From: "Gustavo F. Padovan" <padovan@profusion.mobi>
Date: Mon, 7 Feb 2011 20:19:30 -0200
Subject: Bluetooth: remove l2cap_load() hack

l2cap_load() was added to trigger l2cap.ko module loading from the RFCOMM
and BNEP modules. Now that L2CAP module is gone, we don't need it anymore.

Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h | 2 --
 net/bluetooth/bnep/core.c     | 2 --
 net/bluetooth/cmtp/core.c     | 2 --
 net/bluetooth/hidp/core.c     | 2 --
 net/bluetooth/l2cap_core.c    | 8 --------
 net/bluetooth/rfcomm/core.c   | 2 --
 6 files changed, 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 75ef0b2948f9..9fb87fe1aec3 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -455,6 +455,4 @@ void l2cap_send_disconn_req(struct l2cap_conn *conn, struct sock *sk, int err);
 void l2cap_chan_del(struct sock *sk, int err);
 int l2cap_do_connect(struct sock *sk);
 
-void l2cap_load(void);
-
 #endif /* __L2CAP_H */
diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c
index 5868597534e5..03d4d1245d58 100644
--- a/net/bluetooth/bnep/core.c
+++ b/net/bluetooth/bnep/core.c
@@ -708,8 +708,6 @@ static int __init bnep_init(void)
 {
 	char flt[50] = "";
 
-	l2cap_load();
-
 #ifdef CONFIG_BT_BNEP_PROTO_FILTER
 	strcat(flt, "protocol ");
 #endif
diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c
index 2cee71a714c4..964ea9126f9f 100644
--- a/net/bluetooth/cmtp/core.c
+++ b/net/bluetooth/cmtp/core.c
@@ -469,8 +469,6 @@ int cmtp_get_conninfo(struct cmtp_conninfo *ci)
 
 static int __init cmtp_init(void)
 {
-	l2cap_load();
-
 	BT_INFO("CMTP (CAPI Emulation) ver %s", VERSION);
 
 	cmtp_init_sockets();
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index e0de92952f32..2429ca2d7b06 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -1019,8 +1019,6 @@ static int __init hidp_init(void)
 {
 	int ret;
 
-	l2cap_load();
-
 	BT_INFO("HIDP (Human Interface Emulation) ver %s", VERSION);
 
 	ret = hid_register_driver(&hidp_driver);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 6f054d906c6f..bd88641b4ae7 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3855,13 +3855,5 @@ void l2cap_exit(void)
 	l2cap_cleanup_sockets();
 }
 
-void l2cap_load(void)
-{
-	/* Dummy function to trigger automatic L2CAP module loading by
-	 * other modules that use L2CAP sockets but don't use any other
-	 * symbols from it. */
-}
-EXPORT_SYMBOL(l2cap_load);
-
 module_param(disable_ertm, bool, 0644);
 MODULE_PARM_DESC(disable_ertm, "Disable enhanced retransmission mode");
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 6b83776534fb..c9973932456f 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -2154,8 +2154,6 @@ static int __init rfcomm_init(void)
 {
 	int err;
 
-	l2cap_load();
-
 	hci_register_cb(&rfcomm_cb);
 
 	rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd");
-- 
cgit v1.2.3


From a7d6e4ecdb7648478ddec76d30d87d03d6e22b31 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Tue, 15 Feb 2011 19:02:45 +0100
Subject: thp: prevent hugepages during args/env copying into the user stack

Transparent hugepages can only be created if rmap is fully
functional. So we must prevent hugepages to be created while
is_vma_temporary_stack() is true.

This also optmizes away some harmless but unnecessary setting of
khugepaged_scan.address and it switches some BUG_ON to VM_BUG_ON.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  3 ++-
 mm/huge_memory.c        | 35 ++++++++++++++++-------------------
 2 files changed, 18 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8e6c8c42bc3c..df29c8fde36b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -57,7 +57,8 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 	  (transparent_hugepage_flags &					\
 	   (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) &&			\
 	   ((__vma)->vm_flags & VM_HUGEPAGE))) &&			\
-	 !((__vma)->vm_flags & VM_NOHUGEPAGE))
+	 !((__vma)->vm_flags & VM_NOHUGEPAGE) &&			\
+	 !is_vma_temporary_stack(__vma))
 #define transparent_hugepage_defrag(__vma)				\
 	((transparent_hugepage_flags &					\
 	  (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) ||			\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e62ddb8f24b6..3e29781ee762 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1811,6 +1811,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 	/* VM_PFNMAP vmas may have vm_ops null but vm_file set */
 	if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
 		goto out;
+	if (is_vma_temporary_stack(vma))
+		goto out;
 	VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
 
 	pgd = pgd_offset(mm, address);
@@ -2032,32 +2034,27 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 		if ((!(vma->vm_flags & VM_HUGEPAGE) &&
 		     !khugepaged_always()) ||
 		    (vma->vm_flags & VM_NOHUGEPAGE)) {
+		skip:
 			progress++;
 			continue;
 		}
-
 		/* VM_PFNMAP vmas may have vm_ops null but vm_file set */
-		if (!vma->anon_vma || vma->vm_ops || vma->vm_file) {
-			khugepaged_scan.address = vma->vm_end;
-			progress++;
-			continue;
-		}
+		if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
+			goto skip;
+		if (is_vma_temporary_stack(vma))
+			goto skip;
+
 		VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
 
 		hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 		hend = vma->vm_end & HPAGE_PMD_MASK;
-		if (hstart >= hend) {
-			progress++;
-			continue;
-		}
+		if (hstart >= hend)
+			goto skip;
+		if (khugepaged_scan.address > hend)
+			goto skip;
 		if (khugepaged_scan.address < hstart)
 			khugepaged_scan.address = hstart;
-		if (khugepaged_scan.address > hend) {
-			khugepaged_scan.address = hend + HPAGE_PMD_SIZE;
-			progress++;
-			continue;
-		}
-		BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
+		VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
 
 		while (khugepaged_scan.address < hend) {
 			int ret;
@@ -2086,7 +2083,7 @@ breakouterloop:
 breakouterloop_mmap_sem:
 
 	spin_lock(&khugepaged_mm_lock);
-	BUG_ON(khugepaged_scan.mm_slot != mm_slot);
+	VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
 	/*
 	 * Release the current mm_slot if this mm is about to die, or
 	 * if we scanned all vmas of this mm.
@@ -2241,9 +2238,9 @@ static int khugepaged(void *none)
 
 	for (;;) {
 		mutex_unlock(&khugepaged_mutex);
-		BUG_ON(khugepaged_thread != current);
+		VM_BUG_ON(khugepaged_thread != current);
 		khugepaged_loop();
-		BUG_ON(khugepaged_thread != current);
+		VM_BUG_ON(khugepaged_thread != current);
 
 		mutex_lock(&khugepaged_mutex);
 		if (!khugepaged_enabled())
-- 
cgit v1.2.3


From 41ac51eeda58a85b8a06d748cce7035cc77deebd Mon Sep 17 00:00:00 2001
From: Patrick Schaaf <netdev@bof.de>
Date: Fri, 11 Feb 2011 14:01:12 +0100
Subject: ipvs: make "no destination available" message more informative

When IP_VS schedulers do not find a destination, they output a terse
"WLC: no destination available" message through kernel syslog, which I
can not only make sense of because syslog puts them in a logfile
together with keepalived checker results.

This patch makes the output a bit more informative, by telling you which
virtual service failed to find a destination.

Example output:

kernel: [1539214.552233] IPVS: wlc: TCP 192.168.8.30:22 - no destination available
kernel: [1539299.674418] IPVS: wlc: FWM 22 0x00000016 - no destination available

I have tested the code for IPv4 and FWM services, as you can see from
the example; I do not have an IPv6 setup to test the third code path
with.

To avoid code duplication, I put a new function ip_vs_scheduler_err()
into ip_vs_sched.c, and use that from the schedulers instead of calling
IP_VS_ERR_RL directly.

Signed-off-by: Patrick Schaaf <netdev@bof.de>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              |  2 ++
 net/netfilter/ipvs/ip_vs_lblc.c  |  2 +-
 net/netfilter/ipvs/ip_vs_lblcr.c |  2 +-
 net/netfilter/ipvs/ip_vs_lc.c    |  2 +-
 net/netfilter/ipvs/ip_vs_nq.c    |  2 +-
 net/netfilter/ipvs/ip_vs_rr.c    |  2 +-
 net/netfilter/ipvs/ip_vs_sched.c | 25 +++++++++++++++++++++++++
 net/netfilter/ipvs/ip_vs_sed.c   |  2 +-
 net/netfilter/ipvs/ip_vs_sh.c    |  2 +-
 net/netfilter/ipvs/ip_vs_wlc.c   |  2 +-
 net/netfilter/ipvs/ip_vs_wrr.c   | 14 ++++++++------
 11 files changed, 43 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 5d75feadf4f4..93995494dfd4 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1019,6 +1019,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 			struct ip_vs_proto_data *pd);
 
+extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
+
 
 /*
  *      IPVS control data and functions (from ip_vs_ctl.c)
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 00b5ffab3768..4a9c8cd19690 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -510,7 +510,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	/* No cache entry or it is invalid, time to schedule */
 	dest = __ip_vs_lblc_schedule(svc);
 	if (!dest) {
-		IP_VS_ERR_RL("LBLC: no destination available\n");
+		ip_vs_scheduler_err(svc, "no destination available");
 		return NULL;
 	}
 
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index bfa25f1ea9e4..bd329b1e9589 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -692,7 +692,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		/* The cache entry is invalid, time to schedule */
 		dest = __ip_vs_lblcr_schedule(svc);
 		if (!dest) {
-			IP_VS_ERR_RL("LBLCR: no destination available\n");
+			ip_vs_scheduler_err(svc, "no destination available");
 			read_unlock(&svc->sched_lock);
 			return NULL;
 		}
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 4f69db1fac56..60638007c6c7 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -70,7 +70,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	}
 
 	if (!least)
-		IP_VS_ERR_RL("LC: no destination available\n");
+		ip_vs_scheduler_err(svc, "no destination available");
 	else
 		IP_VS_DBG_BUF(6, "LC: server %s:%u activeconns %d "
 			      "inactconns %d\n",
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index c413e1830823..984d9c137d84 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -99,7 +99,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	}
 
 	if (!least) {
-		IP_VS_ERR_RL("NQ: no destination available\n");
+		ip_vs_scheduler_err(svc, "no destination available");
 		return NULL;
 	}
 
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index e210f37d8ea2..c49b388d1085 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -72,7 +72,7 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		q = q->next;
 	} while (q != p);
 	write_unlock(&svc->sched_lock);
-	IP_VS_ERR_RL("RR: no destination available\n");
+	ip_vs_scheduler_err(svc, "no destination available");
 	return NULL;
 
   out:
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 076ebe00435d..08dbdd5bc18f 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -29,6 +29,7 @@
 
 #include <net/ip_vs.h>
 
+EXPORT_SYMBOL(ip_vs_scheduler_err);
 /*
  *  IPVS scheduler list
  */
@@ -146,6 +147,30 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
 		module_put(scheduler->module);
 }
 
+/*
+ * Common error output helper for schedulers
+ */
+
+void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
+{
+	if (svc->fwmark) {
+		IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
+			     svc->scheduler->name, svc->fwmark,
+			     svc->fwmark, msg);
+#ifdef CONFIG_IP_VS_IPV6
+	} else if (svc->af == AF_INET6) {
+		IP_VS_ERR_RL("%s: %s [%pI6]:%d - %s\n",
+			     svc->scheduler->name,
+			     ip_vs_proto_name(svc->protocol),
+			     &svc->addr.in6, ntohs(svc->port), msg);
+#endif
+	} else {
+		IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
+			     svc->scheduler->name,
+			     ip_vs_proto_name(svc->protocol),
+			     &svc->addr.ip, ntohs(svc->port), msg);
+	}
+}
 
 /*
  *  Register a scheduler in the scheduler list
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index 1ab75a9dc400..89ead246ed3d 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -87,7 +87,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 			goto nextstage;
 		}
 	}
-	IP_VS_ERR_RL("SED: no destination available\n");
+	ip_vs_scheduler_err(svc, "no destination available");
 	return NULL;
 
 	/*
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index e6cc174fbc06..b5e2556c581a 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -223,7 +223,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	    || !(dest->flags & IP_VS_DEST_F_AVAILABLE)
 	    || atomic_read(&dest->weight) <= 0
 	    || is_overloaded(dest)) {
-		IP_VS_ERR_RL("SH: no destination available\n");
+		ip_vs_scheduler_err(svc, "no destination available");
 		return NULL;
 	}
 
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index bbddfdb10db2..fdf0f58962a4 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -75,7 +75,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 			goto nextstage;
 		}
 	}
-	IP_VS_ERR_RL("WLC: no destination available\n");
+	ip_vs_scheduler_err(svc, "no destination available");
 	return NULL;
 
 	/*
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 30db633f88f1..1ef41f50723c 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -147,8 +147,9 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 
 			if (mark->cl == mark->cl->next) {
 				/* no dest entry */
-				IP_VS_ERR_RL("WRR: no destination available: "
-					     "no destinations present\n");
+				ip_vs_scheduler_err(svc,
+					"no destination available: "
+					"no destinations present");
 				dest = NULL;
 				goto out;
 			}
@@ -162,8 +163,8 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 				 */
 				if (mark->cw == 0) {
 					mark->cl = &svc->destinations;
-					IP_VS_ERR_RL("WRR: no destination "
-						     "available\n");
+					ip_vs_scheduler_err(svc,
+						"no destination available");
 					dest = NULL;
 					goto out;
 				}
@@ -185,8 +186,9 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 			/* back to the start, and no dest is found.
 			   It is only possible when all dests are OVERLOADED */
 			dest = NULL;
-			IP_VS_ERR_RL("WRR: no destination available: "
-				     "all destinations are overloaded\n");
+			ip_vs_scheduler_err(svc,
+				"no destination available: "
+				"all destinations are overloaded");
 			goto out;
 		}
 	}
-- 
cgit v1.2.3


From d41d5a01631af821d3a3447e6613a316f5ee6c25 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Mon, 7 Feb 2011 17:02:20 +0100
Subject: cgroup: Fix cgroup_subsys::exit callback

Make the ::exit method act like ::attach, it is after all very nearly
the same thing.

The bug had no effect on correctness - fixing it is an optimization for
the scheduler. Also, later perf-cgroups patches rely on it.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Menage <menage@google.com>
LKML-Reference: <1297160655.13327.92.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/cgroup.h |  3 ++-
 kernel/cgroup.c        | 31 ++++++++++++++++++-------------
 kernel/sched.c         |  6 ++----
 3 files changed, 22 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ce104e33cd22..38117d937332 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -474,7 +474,8 @@ struct cgroup_subsys {
 			struct cgroup *old_cgrp, struct task_struct *tsk,
 			bool threadgroup);
 	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
-	void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+	void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+			struct cgroup *old_cgrp, struct task_struct *task);
 	int (*populate)(struct cgroup_subsys *ss,
 			struct cgroup *cgrp);
 	void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b24d7027b83c..f6495f33a355 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4230,20 +4230,8 @@ void cgroup_post_fork(struct task_struct *child)
  */
 void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 {
-	int i;
 	struct css_set *cg;
-
-	if (run_callbacks && need_forkexit_callback) {
-		/*
-		 * modular subsystems can't use callbacks, so no need to lock
-		 * the subsys array
-		 */
-		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-			if (ss->exit)
-				ss->exit(ss, tsk);
-		}
-	}
+	int i;
 
 	/*
 	 * Unlink from the css_set task list if necessary.
@@ -4261,7 +4249,24 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	task_lock(tsk);
 	cg = tsk->cgroups;
 	tsk->cgroups = &init_css_set;
+
+	if (run_callbacks && need_forkexit_callback) {
+		/*
+		 * modular subsystems can't use callbacks, so no need to lock
+		 * the subsys array
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss->exit) {
+				struct cgroup *old_cgrp =
+					rcu_dereference_raw(cg->subsys[i])->cgroup;
+				struct cgroup *cgrp = task_cgroup(tsk, i);
+				ss->exit(ss, cgrp, old_cgrp, tsk);
+			}
+		}
+	}
 	task_unlock(tsk);
+
 	if (cg)
 		put_css_set_taskexit(cg);
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index e142e92f38da..79e611cd83dd 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -606,9 +606,6 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
-	if (p->flags & PF_EXITING)
-		return &root_task_group;
-
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
@@ -8863,7 +8860,8 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 }
 
 static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
 {
 	/*
 	 * cgroup_exit() is called in the copy_process() failure path.
-- 
cgit v1.2.3


From e5d1367f17ba6a6fed5fd8b74e4d5720923e0c25 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Mon, 14 Feb 2011 11:20:01 +0200
Subject: perf: Add cgroup support

This kernel patch adds the ability to filter monitoring based on
container groups (cgroups). This is for use in per-cpu mode only.

The cgroup to monitor is passed as a file descriptor in the pid
argument to the syscall. The file descriptor must be opened to
the cgroup name in the cgroup filesystem. For instance, if the
cgroup name is foo and cgroupfs is mounted in /cgroup, then the
file descriptor is opened to /cgroup/foo. Cgroup mode is
activated by passing PERF_FLAG_PID_CGROUP in the flags argument
to the syscall.

For instance to measure in cgroup foo on CPU1 assuming
cgroupfs is mounted under /cgroup:

struct perf_event_attr attr;
int cgroup_fd, fd;

cgroup_fd = open("/cgroup/foo", O_RDONLY);
fd = perf_event_open(&attr, cgroup_fd, 1, -1, PERF_FLAG_PID_CGROUP);
close(cgroup_fd);

Signed-off-by: Stephane Eranian <eranian@google.com>
[ added perf_cgroup_{exit,attach} ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590250.114ddf0a.689e.4482@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/cgroup.h        |   1 +
 include/linux/cgroup_subsys.h |   4 +
 include/linux/perf_event.h    |  33 ++-
 init/Kconfig                  |  10 +
 kernel/cgroup.c               |  23 ++
 kernel/perf_event.c           | 638 +++++++++++++++++++++++++++++++++++++++---
 6 files changed, 671 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 38117d937332..e654fa239916 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -627,6 +627,7 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg,
 /* Get id and depth of css */
 unsigned short css_id(struct cgroup_subsys_state *css);
 unsigned short css_depth(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
 
 #else /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff02b6cb..cdbfcb8780ec 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -65,4 +65,8 @@ SUBSYS(net_cls)
 SUBSYS(blkio)
 #endif
 
+#ifdef CONFIG_CGROUP_PERF
+SUBSYS(perf)
+#endif
+
 /* */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index dda5b0a3ff60..38c8b2554842 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -464,6 +464,7 @@ enum perf_callchain_context {
 
 #define PERF_FLAG_FD_NO_GROUP	(1U << 0)
 #define PERF_FLAG_FD_OUTPUT	(1U << 1)
+#define PERF_FLAG_PID_CGROUP	(1U << 2) /* pid=cgroup id, per-cpu mode only */
 
 #ifdef __KERNEL__
 /*
@@ -471,6 +472,7 @@ enum perf_callchain_context {
  */
 
 #ifdef CONFIG_PERF_EVENTS
+# include <linux/cgroup.h>
 # include <asm/perf_event.h>
 # include <asm/local64.h>
 #endif
@@ -716,6 +718,22 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP	0x02
 #define PERF_ATTACH_TASK	0x04
 
+#ifdef CONFIG_CGROUP_PERF
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+	u64 time;
+	u64 timestamp;
+};
+
+struct perf_cgroup {
+	struct cgroup_subsys_state css;
+	struct perf_cgroup_info *info;	/* timing info, one per cpu */
+};
+#endif
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -832,6 +850,11 @@ struct perf_event {
 	struct event_filter		*filter;
 #endif
 
+#ifdef CONFIG_CGROUP_PERF
+	struct perf_cgroup		*cgrp; /* cgroup event is attach to */
+	int				cgrp_defer_enabled;
+#endif
+
 #endif /* CONFIG_PERF_EVENTS */
 };
 
@@ -886,6 +909,7 @@ struct perf_event_context {
 	u64				generation;
 	int				pin_count;
 	struct rcu_head			rcu_head;
+	int				nr_cgroups; /* cgroup events present */
 };
 
 /*
@@ -905,6 +929,9 @@ struct perf_cpu_context {
 	struct list_head		rotation_list;
 	int				jiffies_interval;
 	struct pmu			*active_pmu;
+#ifdef CONFIG_CGROUP_PERF
+	struct perf_cgroup		*cgrp;
+#endif
 };
 
 struct perf_output_handle {
@@ -1040,11 +1067,11 @@ have_event:
 	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
-extern atomic_t perf_task_events;
+extern atomic_t perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+	COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
 }
 
 static inline
@@ -1052,7 +1079,7 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex
 {
 	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
-	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+	COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
diff --git a/init/Kconfig b/init/Kconfig
index be788c0957d4..20d6bd919b8d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -683,6 +683,16 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
 	  select this option (if, for some reason, they need to disable it
 	  then noswapaccount does the trick).
 
+config CGROUP_PERF
+	bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
+	depends on PERF_EVENTS && CGROUPS
+	help
+	  This option extends the per-cpu mode to restrict monitoring to
+	  threads which belong to the cgroup specificied and run on the
+	  designated cpu.
+
+	  Say N if unsure.
+
 menuconfig CGROUP_SCHED
 	bool "Group CPU scheduler"
 	depends on EXPERIMENTAL
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f6495f33a355..95362d15128c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4818,6 +4818,29 @@ css_get_next(struct cgroup_subsys *ss, int id,
 	return ret;
 }
 
+/*
+ * get corresponding css from file open on cgroupfs directory
+ */
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
+{
+	struct cgroup *cgrp;
+	struct inode *inode;
+	struct cgroup_subsys_state *css;
+
+	inode = f->f_dentry->d_inode;
+	/* check in cgroup filesystem dir */
+	if (inode->i_op != &cgroup_dir_inode_operations)
+		return ERR_PTR(-EBADF);
+
+	if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
+		return ERR_PTR(-EINVAL);
+
+	/* get cgroup */
+	cgrp = __d_cgrp(f->f_dentry);
+	css = cgrp->subsys[id];
+	return css ? css : ERR_PTR(-ENOENT);
+}
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
 						   struct cgroup *cont)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 3d3f282fa50e..65dcdc76d709 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -111,13 +111,23 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 	return data.ret;
 }
 
+#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
+		       PERF_FLAG_FD_OUTPUT  |\
+		       PERF_FLAG_PID_CGROUP)
+
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
-atomic_t perf_task_events __read_mostly;
+/*
+ * perf_sched_events : >0 events exist
+ * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
+ */
+atomic_t perf_sched_events __read_mostly;
+static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
@@ -148,7 +158,11 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			      enum event_type_t event_type);
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type);
+			     enum event_type_t event_type,
+			     struct task_struct *task);
+
+static void update_context_time(struct perf_event_context *ctx);
+static u64 perf_event_time(struct perf_event *event);
 
 void __weak perf_event_print_debug(void)	{ }
 
@@ -162,6 +176,338 @@ static inline u64 perf_clock(void)
 	return local_clock();
 }
 
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+#ifdef CONFIG_CGROUP_PERF
+
+static inline struct perf_cgroup *
+perf_cgroup_from_task(struct task_struct *task)
+{
+	return container_of(task_subsys_state(task, perf_subsys_id),
+			struct perf_cgroup, css);
+}
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+
+	return !event->cgrp || event->cgrp == cpuctx->cgrp;
+}
+
+static inline void perf_get_cgroup(struct perf_event *event)
+{
+	css_get(&event->cgrp->css);
+}
+
+static inline void perf_put_cgroup(struct perf_event *event)
+{
+	css_put(&event->cgrp->css);
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{
+	perf_put_cgroup(event);
+	event->cgrp = NULL;
+}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+	return event->cgrp != NULL;
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+	struct perf_cgroup_info *t;
+
+	t = per_cpu_ptr(event->cgrp->info, event->cpu);
+	return t->time;
+}
+
+static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
+{
+	struct perf_cgroup_info *info;
+	u64 now;
+
+	now = perf_clock();
+
+	info = this_cpu_ptr(cgrp->info);
+
+	info->time += now - info->timestamp;
+	info->timestamp = now;
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
+	if (cgrp_out)
+		__update_cgrp_time(cgrp_out);
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+	struct perf_cgroup *cgrp = perf_cgroup_from_task(current);
+	/*
+	 * do not update time when cgroup is not active
+	 */
+	if (!event->cgrp || cgrp != event->cgrp)
+		return;
+
+	__update_cgrp_time(event->cgrp);
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task, u64 now)
+{
+	struct perf_cgroup *cgrp;
+	struct perf_cgroup_info *info;
+
+	if (!task)
+		return;
+
+	cgrp = perf_cgroup_from_task(task);
+	info = this_cpu_ptr(cgrp->info);
+	info->timestamp = now;
+}
+
+#define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
+#define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */
+
+/*
+ * reschedule events based on the cgroup constraint of task.
+ *
+ * mode SWOUT : schedule out everything
+ * mode SWIN : schedule in based on cgroup for next
+ */
+void perf_cgroup_switch(struct task_struct *task, int mode)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	/*
+	 * disable interrupts to avoid geting nr_cgroup
+	 * changes via __perf_event_disable(). Also
+	 * avoids preemption.
+	 */
+	local_irq_save(flags);
+
+	/*
+	 * we reschedule only in the presence of cgroup
+	 * constrained events.
+	 */
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+		perf_pmu_disable(cpuctx->ctx.pmu);
+
+		/*
+		 * perf_cgroup_events says at least one
+		 * context on this CPU has cgroup events.
+		 *
+		 * ctx->nr_cgroups reports the number of cgroup
+		 * events for a context.
+		 */
+		if (cpuctx->ctx.nr_cgroups > 0) {
+
+			if (mode & PERF_CGROUP_SWOUT) {
+				cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+				/*
+				 * must not be done before ctxswout due
+				 * to event_filter_match() in event_sched_out()
+				 */
+				cpuctx->cgrp = NULL;
+			}
+
+			if (mode & PERF_CGROUP_SWIN) {
+				/* set cgrp before ctxsw in to
+				 * allow event_filter_match() to not
+				 * have to pass task around
+				 */
+				cpuctx->cgrp = perf_cgroup_from_task(task);
+				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+			}
+		}
+
+		perf_pmu_enable(cpuctx->ctx.pmu);
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+	perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+	perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+}
+
+static inline int perf_cgroup_connect(int fd, struct perf_event *event,
+				      struct perf_event_attr *attr,
+				      struct perf_event *group_leader)
+{
+	struct perf_cgroup *cgrp;
+	struct cgroup_subsys_state *css;
+	struct file *file;
+	int ret = 0, fput_needed;
+
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+
+	css = cgroup_css_from_dir(file, perf_subsys_id);
+	if (IS_ERR(css))
+		return PTR_ERR(css);
+
+	cgrp = container_of(css, struct perf_cgroup, css);
+	event->cgrp = cgrp;
+
+	/*
+	 * all events in a group must monitor
+	 * the same cgroup because a task belongs
+	 * to only one perf cgroup at a time
+	 */
+	if (group_leader && group_leader->cgrp != cgrp) {
+		perf_detach_cgroup(event);
+		ret = -EINVAL;
+	} else {
+		/* must be done before we fput() the file */
+		perf_get_cgroup(event);
+	}
+	fput_light(file, fput_needed);
+	return ret;
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+	struct perf_cgroup_info *t;
+	t = per_cpu_ptr(event->cgrp->info, event->cpu);
+	event->shadow_ctx_time = now - t->timestamp;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+	/*
+	 * when the current task's perf cgroup does not match
+	 * the event's, we need to remember to call the
+	 * perf_mark_enable() function the first time a task with
+	 * a matching perf cgroup is scheduled in.
+	 */
+	if (is_cgroup_event(event) && !perf_cgroup_match(event))
+		event->cgrp_defer_enabled = 1;
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+			 struct perf_event_context *ctx)
+{
+	struct perf_event *sub;
+	u64 tstamp = perf_event_time(event);
+
+	if (!event->cgrp_defer_enabled)
+		return;
+
+	event->cgrp_defer_enabled = 0;
+
+	event->tstamp_enabled = tstamp - event->total_time_enabled;
+	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
+			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+			sub->cgrp_defer_enabled = 0;
+		}
+	}
+}
+#else /* !CONFIG_CGROUP_PERF */
+
+static inline bool
+perf_cgroup_match(struct perf_event *event)
+{
+	return true;
+}
+
+static inline void perf_detach_cgroup(struct perf_event *event)
+{}
+
+static inline int is_cgroup_event(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void update_cgrp_time_from_event(struct perf_event *event)
+{
+}
+
+static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
+{
+}
+
+static inline void perf_cgroup_sched_out(struct task_struct *task)
+{
+}
+
+static inline void perf_cgroup_sched_in(struct task_struct *task)
+{
+}
+
+static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
+				      struct perf_event_attr *attr,
+				      struct perf_event *group_leader)
+{
+	return -EINVAL;
+}
+
+static inline void
+perf_cgroup_set_timestamp(struct task_struct *task, u64 now)
+{
+}
+
+void
+perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+{
+}
+
+static inline void
+perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
+{
+}
+
+static inline u64 perf_cgroup_event_time(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void
+perf_cgroup_defer_enabled(struct perf_event *event)
+{
+}
+
+static inline void
+perf_cgroup_mark_enabled(struct perf_event *event,
+			 struct perf_event_context *ctx)
+{
+}
+#endif
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -343,6 +689,10 @@ static void update_context_time(struct perf_event_context *ctx)
 static u64 perf_event_time(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
+
+	if (is_cgroup_event(event))
+		return perf_cgroup_event_time(event);
+
 	return ctx ? ctx->time : 0;
 }
 
@@ -357,9 +707,20 @@ static void update_event_times(struct perf_event *event)
 	if (event->state < PERF_EVENT_STATE_INACTIVE ||
 	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
 		return;
-
-	if (ctx->is_active)
+	/*
+	 * in cgroup mode, time_enabled represents
+	 * the time the event was enabled AND active
+	 * tasks were in the monitored cgroup. This is
+	 * independent of the activity of the context as
+	 * there may be a mix of cgroup and non-cgroup events.
+	 *
+	 * That is why we treat cgroup events differently
+	 * here.
+	 */
+	if (is_cgroup_event(event))
 		run_end = perf_event_time(event);
+	else if (ctx->is_active)
+		run_end = ctx->time;
 	else
 		run_end = event->tstamp_stopped;
 
@@ -371,6 +732,7 @@ static void update_event_times(struct perf_event *event)
 		run_end = perf_event_time(event);
 
 	event->total_time_running = run_end - event->tstamp_running;
+
 }
 
 /*
@@ -419,6 +781,17 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		list_add_tail(&event->group_entry, list);
 	}
 
+	if (is_cgroup_event(event)) {
+		ctx->nr_cgroups++;
+		/*
+		 * one more event:
+		 * - that has cgroup constraint on event->cpu
+		 * - that may need work on context switch
+		 */
+		atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
+		jump_label_inc(&perf_sched_events);
+	}
+
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	if (!ctx->nr_events)
 		perf_pmu_rotate_start(ctx->pmu);
@@ -545,6 +918,12 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
+	if (is_cgroup_event(event)) {
+		ctx->nr_cgroups--;
+		atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
+		jump_label_dec(&perf_sched_events);
+	}
+
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -616,7 +995,8 @@ out:
 static inline int
 event_filter_match(struct perf_event *event)
 {
-	return event->cpu == -1 || event->cpu == smp_processor_id();
+	return (event->cpu == -1 || event->cpu == smp_processor_id())
+	    && perf_cgroup_match(event);
 }
 
 static void
@@ -634,7 +1014,7 @@ event_sched_out(struct perf_event *event,
 	 */
 	if (event->state == PERF_EVENT_STATE_INACTIVE
 	    && !event_filter_match(event)) {
-		delta = ctx->time - event->tstamp_stopped;
+		delta = tstamp - event->tstamp_stopped;
 		event->tstamp_running += delta;
 		event->tstamp_stopped = tstamp;
 	}
@@ -678,12 +1058,6 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
-	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
 /*
  * Cross CPU call to remove a performance event
  *
@@ -783,6 +1157,7 @@ static int __perf_event_disable(void *info)
 	 */
 	if (event->state >= PERF_EVENT_STATE_INACTIVE) {
 		update_context_time(ctx);
+		update_cgrp_time_from_event(event);
 		update_group_times(event);
 		if (event == event->group_leader)
 			group_sched_out(event, cpuctx, ctx);
@@ -851,6 +1226,41 @@ retry:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
+static void perf_set_shadow_time(struct perf_event *event,
+				 struct perf_event_context *ctx,
+				 u64 tstamp)
+{
+	/*
+	 * use the correct time source for the time snapshot
+	 *
+	 * We could get by without this by leveraging the
+	 * fact that to get to this function, the caller
+	 * has most likely already called update_context_time()
+	 * and update_cgrp_time_xx() and thus both timestamp
+	 * are identical (or very close). Given that tstamp is,
+	 * already adjusted for cgroup, we could say that:
+	 *    tstamp - ctx->timestamp
+	 * is equivalent to
+	 *    tstamp - cgrp->timestamp.
+	 *
+	 * Then, in perf_output_read(), the calculation would
+	 * work with no changes because:
+	 * - event is guaranteed scheduled in
+	 * - no scheduled out in between
+	 * - thus the timestamp would be the same
+	 *
+	 * But this is a bit hairy.
+	 *
+	 * So instead, we have an explicit cgroup call to remain
+	 * within the time time source all along. We believe it
+	 * is cleaner and simpler to understand.
+	 */
+	if (is_cgroup_event(event))
+		perf_cgroup_set_shadow_time(event, tstamp);
+	else
+		event->shadow_ctx_time = tstamp - ctx->timestamp;
+}
+
 #define MAX_INTERRUPTS (~0ULL)
 
 static void perf_log_throttle(struct perf_event *event, int enable);
@@ -891,7 +1301,7 @@ event_sched_in(struct perf_event *event,
 
 	event->tstamp_running += tstamp - event->tstamp_stopped;
 
-	event->shadow_ctx_time = tstamp - ctx->timestamp;
+	perf_set_shadow_time(event, ctx, tstamp);
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
@@ -1012,7 +1422,8 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
-static void perf_event_context_sched_in(struct perf_event_context *ctx);
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+					struct task_struct *tsk);
 
 /*
  * Cross CPU call to install and enable a performance event
@@ -1033,11 +1444,17 @@ static int  __perf_install_in_context(void *info)
 	 * which do context switches with IRQs enabled.
 	 */
 	if (ctx->task && !cpuctx->task_ctx)
-		perf_event_context_sched_in(ctx);
+		perf_event_context_sched_in(ctx, ctx->task);
 
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	update_context_time(ctx);
+	/*
+	 * update cgrp time only if current cgrp
+	 * matches event->cgrp. Must be done before
+	 * calling add_event_to_ctx()
+	 */
+	update_cgrp_time_from_event(event);
 
 	add_event_to_ctx(event, ctx);
 
@@ -1175,10 +1592,19 @@ static int __perf_event_enable(void *info)
 
 	if (event->state >= PERF_EVENT_STATE_INACTIVE)
 		goto unlock;
+
+	/*
+	 * set current task's cgroup time reference point
+	 */
+	perf_cgroup_set_timestamp(current, perf_clock());
+
 	__perf_event_mark_enabled(event, ctx);
 
-	if (!event_filter_match(event))
+	if (!event_filter_match(event)) {
+		if (is_cgroup_event(event))
+			perf_cgroup_defer_enabled(event);
 		goto unlock;
+	}
 
 	/*
 	 * If the event is in a group and isn't the group leader,
@@ -1307,6 +1733,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		goto out;
 	update_context_time(ctx);
+	update_cgrp_time_from_cpuctx(cpuctx);
 
 	if (!ctx->nr_active)
 		goto out;
@@ -1496,6 +1923,14 @@ void __perf_event_task_sched_out(struct task_struct *task,
 
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
+
+	/*
+	 * if cgroup events exist on this CPU, then we need
+	 * to check if we have to switch out PMU state.
+	 * cgroup event are system-wide mode only
+	 */
+	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+		perf_cgroup_sched_out(task);
 }
 
 static void task_ctx_sched_out(struct perf_event_context *ctx,
@@ -1534,6 +1969,10 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		/* may need to reset tstamp_enabled */
+		if (is_cgroup_event(event))
+			perf_cgroup_mark_enabled(event, ctx);
+
 		if (group_can_go_on(event, cpuctx, 1))
 			group_sched_in(event, cpuctx, ctx);
 
@@ -1566,6 +2005,10 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		/* may need to reset tstamp_enabled */
+		if (is_cgroup_event(event))
+			perf_cgroup_mark_enabled(event, ctx);
+
 		if (group_can_go_on(event, cpuctx, can_add_hw)) {
 			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
@@ -1576,15 +2019,19 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type)
+	     enum event_type_t event_type,
+	     struct task_struct *task)
 {
+	u64 now;
+
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	if (likely(!ctx->nr_events))
 		goto out;
 
-	ctx->timestamp = perf_clock();
-
+	now = perf_clock();
+	ctx->timestamp = now;
+	perf_cgroup_set_timestamp(task, now);
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
@@ -1601,11 +2048,12 @@ out:
 }
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type)
+			     enum event_type_t event_type,
+			     struct task_struct *task)
 {
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
-	ctx_sched_in(ctx, cpuctx, event_type);
+	ctx_sched_in(ctx, cpuctx, event_type, task);
 }
 
 static void task_ctx_sched_in(struct perf_event_context *ctx,
@@ -1617,11 +2065,12 @@ static void task_ctx_sched_in(struct perf_event_context *ctx,
 	if (cpuctx->task_ctx == ctx)
 		return;
 
-	ctx_sched_in(ctx, cpuctx, event_type);
+	ctx_sched_in(ctx, cpuctx, event_type, NULL);
 	cpuctx->task_ctx = ctx;
 }
 
-static void perf_event_context_sched_in(struct perf_event_context *ctx)
+static void perf_event_context_sched_in(struct perf_event_context *ctx,
+					struct task_struct *task)
 {
 	struct perf_cpu_context *cpuctx;
 
@@ -1637,9 +2086,9 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx)
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
-	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
+	ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 
 	cpuctx->task_ctx = ctx;
 
@@ -1672,8 +2121,15 @@ void __perf_event_task_sched_in(struct task_struct *task)
 		if (likely(!ctx))
 			continue;
 
-		perf_event_context_sched_in(ctx);
+		perf_event_context_sched_in(ctx, task);
 	}
+	/*
+	 * if cgroup events exist on this CPU, then we need
+	 * to check if we have to switch in PMU state.
+	 * cgroup event are system-wide mode only
+	 */
+	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+		perf_cgroup_sched_in(task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -1873,7 +2329,7 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 	if (ctx)
 		rotate_ctx(ctx);
 
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current);
 	if (ctx)
 		task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
 
@@ -1952,7 +2408,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
 	raw_spin_unlock(&ctx->lock);
 
-	perf_event_context_sched_in(ctx);
+	perf_event_context_sched_in(ctx, ctx->task);
 out:
 	local_irq_restore(flags);
 }
@@ -1977,8 +2433,10 @@ static void __perf_event_read(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	if (ctx->is_active)
+	if (ctx->is_active) {
 		update_context_time(ctx);
+		update_cgrp_time_from_event(event);
+	}
 	update_event_times(event);
 	if (event->state == PERF_EVENT_STATE_ACTIVE)
 		event->pmu->read(event);
@@ -2009,8 +2467,10 @@ static u64 perf_event_read(struct perf_event *event)
 		 * (e.g., thread is blocked), in that case
 		 * we cannot update context time
 		 */
-		if (ctx->is_active)
+		if (ctx->is_active) {
 			update_context_time(ctx);
+			update_cgrp_time_from_event(event);
+		}
 		update_event_times(event);
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
@@ -2395,7 +2855,7 @@ static void free_event(struct perf_event *event)
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_dec(&perf_task_events);
+			jump_label_dec(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_dec(&nr_mmap_events);
 		if (event->attr.comm)
@@ -2411,6 +2871,9 @@ static void free_event(struct perf_event *event)
 		event->buffer = NULL;
 	}
 
+	if (is_cgroup_event(event))
+		perf_detach_cgroup(event);
+
 	if (event->destroy)
 		event->destroy(event);
 
@@ -5300,6 +5763,7 @@ static void task_clock_event_read(struct perf_event *event)
 
 	if (!in_nmi()) {
 		update_context_time(event->ctx);
+		update_cgrp_time_from_event(event);
 		time = event->ctx->time;
 	} else {
 		u64 now = perf_clock();
@@ -5725,7 +6189,7 @@ done:
 
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
-			jump_label_inc(&perf_task_events);
+			jump_label_inc(&perf_sched_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_inc(&nr_mmap_events);
 		if (event->attr.comm)
@@ -5900,7 +6364,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int err;
 
 	/* for future expandability... */
-	if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT))
+	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
 	err = perf_copy_attr(attr_uptr, &attr);
@@ -5917,6 +6381,15 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}
 
+	/*
+	 * In cgroup mode, the pid argument is used to pass the fd
+	 * opened to the cgroup directory in cgroupfs. The cpu argument
+	 * designates the cpu on which to monitor threads from that
+	 * cgroup.
+	 */
+	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
+		return -EINVAL;
+
 	event_fd = get_unused_fd_flags(O_RDWR);
 	if (event_fd < 0)
 		return event_fd;
@@ -5934,7 +6407,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			group_leader = NULL;
 	}
 
-	if (pid != -1) {
+	if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
 		task = find_lively_task_by_vpid(pid);
 		if (IS_ERR(task)) {
 			err = PTR_ERR(task);
@@ -5948,6 +6421,12 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_task;
 	}
 
+	if (flags & PERF_FLAG_PID_CGROUP) {
+		err = perf_cgroup_connect(pid, event, &attr, group_leader);
+		if (err)
+			goto err_alloc;
+	}
+
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -6808,3 +7287,92 @@ unlock:
 	return ret;
 }
 device_initcall(perf_event_sysfs_init);
+
+#ifdef CONFIG_CGROUP_PERF
+static struct cgroup_subsys_state *perf_cgroup_create(
+	struct cgroup_subsys *ss, struct cgroup *cont)
+{
+	struct perf_cgroup *jc;
+	struct perf_cgroup_info *t;
+	int c;
+
+	jc = kmalloc(sizeof(*jc), GFP_KERNEL);
+	if (!jc)
+		return ERR_PTR(-ENOMEM);
+
+	memset(jc, 0, sizeof(*jc));
+
+	jc->info = alloc_percpu(struct perf_cgroup_info);
+	if (!jc->info) {
+		kfree(jc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for_each_possible_cpu(c) {
+		t = per_cpu_ptr(jc->info, c);
+		t->time = 0;
+		t->timestamp = 0;
+	}
+	return &jc->css;
+}
+
+static void perf_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+	struct perf_cgroup *jc;
+	jc = container_of(cgroup_subsys_state(cont, perf_subsys_id),
+			  struct perf_cgroup, css);
+	free_percpu(jc->info);
+	kfree(jc);
+}
+
+static int __perf_cgroup_move(void *info)
+{
+	struct task_struct *task = info;
+	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+	return 0;
+}
+
+static void perf_cgroup_move(struct task_struct *task)
+{
+	task_function_call(task, __perf_cgroup_move, task);
+}
+
+static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task,
+		bool threadgroup)
+{
+	perf_cgroup_move(task);
+	if (threadgroup) {
+		struct task_struct *c;
+		rcu_read_lock();
+		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+			perf_cgroup_move(c);
+		}
+		rcu_read_unlock();
+	}
+}
+
+static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
+{
+	/*
+	 * cgroup_exit() is called in the copy_process() failure path.
+	 * Ignore this case since the task hasn't ran yet, this avoids
+	 * trying to poke a half freed task state from generic code.
+	 */
+	if (!(task->flags & PF_EXITING))
+		return;
+
+	perf_cgroup_move(task);
+}
+
+struct cgroup_subsys perf_subsys = {
+	.name = "perf_event",
+	.subsys_id = perf_subsys_id,
+	.create = perf_cgroup_create,
+	.destroy = perf_cgroup_destroy,
+	.exit = perf_cgroup_exit,
+	.attach = perf_cgroup_attach,
+};
+#endif /* CONFIG_CGROUP_PERF */
-- 
cgit v1.2.3


From 163ec4354a5135c6c38c3f4a9b46a31900ebdf48 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 16 Feb 2011 11:22:34 +0100
Subject: perf: Optimize throttling code

By pre-computing the maximum number of samples per tick we can avoid a
multiplication and a conditional since MAX_INTERRUPTS >
max_samples_per_tick.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_event.h |  4 ++++
 kernel/perf_event.c        | 43 ++++++++++++++++++++++++-------------------
 kernel/sysctl.c            |  2 +-
 3 files changed, 29 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 38c8b2554842..8ceb5a6fd9c9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1110,6 +1110,10 @@ extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
 
+extern int perf_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
 	return sysctl_perf_event_paranoid > -1;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 65dcdc76d709..e03be08d0ddf 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -150,7 +150,24 @@ int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 /*
  * max perf event sample rate
  */
-int sysctl_perf_event_sample_rate __read_mostly = 100000;
+#define DEFAULT_MAX_SAMPLE_RATE 100000
+int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
+static int max_samples_per_tick __read_mostly =
+	DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+
+int perf_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (ret || !write)
+		return ret;
+
+	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+
+	return 0;
+}
 
 static atomic64_t perf_event_id;
 
@@ -4941,26 +4958,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	if (unlikely(!is_sampling_event(event)))
 		return 0;
 
-	if (!throttle) {
-		hwc->interrupts++;
-	} else {
-		if (hwc->interrupts != MAX_INTERRUPTS) {
-			hwc->interrupts++;
-			if (HZ * hwc->interrupts >
-					(u64)sysctl_perf_event_sample_rate) {
-				hwc->interrupts = MAX_INTERRUPTS;
-				perf_log_throttle(event, 0);
-				ret = 1;
-			}
-		} else {
-			/*
-			 * Keep re-disabling events even though on the previous
-			 * pass we disabled it - just in case we raced with a
-			 * sched-in and the event got enabled again:
-			 */
+	if (unlikely(hwc->interrupts >= max_samples_per_tick)) {
+		if (throttle) {
+			hwc->interrupts = MAX_INTERRUPTS;
+			perf_log_throttle(event, 0);
 			ret = 1;
 		}
-	}
+	} else
+		hwc->interrupts++;
 
 	if (event->attr.freq) {
 		u64 now = perf_clock();
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0f1bd83db985..daef911cbadb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -948,7 +948,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_perf_event_sample_rate,
 		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= perf_proc_update_handler,
 	},
 #endif
 #ifdef CONFIG_KMEMCHECK
-- 
cgit v1.2.3


From 58a69cb47ec6991bf006a3e5d202e8571b0327a4 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 16 Feb 2011 09:25:31 +0100
Subject: workqueue, freezer: unify spelling of 'freeze' + 'able' to
 'freezable'

There are two spellings in use for 'freeze' + 'able' - 'freezable' and
'freezeable'.  The former is the more prominent one.  The latter is
mostly used by workqueue and in a few other odd places.  Unify the
spelling to 'freezable'.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Acked-by: Dmitry Torokhov <dtor@mail.ru>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Alex Dubov <oakad@yahoo.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Steven Whitehouse <swhiteho@redhat.com>
---
 Documentation/workqueue.txt      |  4 ++--
 drivers/memstick/core/memstick.c |  2 +-
 drivers/misc/tifm_core.c         |  2 +-
 drivers/misc/vmw_balloon.c       |  2 +-
 drivers/mtd/nand/r852.c          |  2 +-
 drivers/mtd/sm_ftl.c             |  2 +-
 drivers/net/can/mcp251x.c        |  2 +-
 drivers/tty/serial/max3100.c     |  2 +-
 drivers/tty/serial/max3107.c     |  2 +-
 fs/gfs2/glock.c                  |  4 ++--
 fs/gfs2/main.c                   |  2 +-
 include/linux/freezer.h          |  2 +-
 include/linux/sched.h            |  2 +-
 include/linux/workqueue.h        |  8 ++++----
 kernel/power/main.c              |  2 +-
 kernel/power/process.c           |  6 +++---
 kernel/workqueue.c               | 24 ++++++++++++------------
 17 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt
index 996a27d9b8db..01c513fac40e 100644
--- a/Documentation/workqueue.txt
+++ b/Documentation/workqueue.txt
@@ -190,9 +190,9 @@ resources, scheduled and executed.
 	* Long running CPU intensive workloads which can be better
 	  managed by the system scheduler.
 
-  WQ_FREEZEABLE
+  WQ_FREEZABLE
 
-	A freezeable wq participates in the freeze phase of the system
+	A freezable wq participates in the freeze phase of the system
 	suspend operations.  Work items on the wq are drained and no
 	new work item starts execution until thawed.
 
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index e9a3eab7b0cf..8c1d85e27be4 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -621,7 +621,7 @@ static int __init memstick_init(void)
 {
 	int rc;
 
-	workqueue = create_freezeable_workqueue("kmemstick");
+	workqueue = create_freezable_workqueue("kmemstick");
 	if (!workqueue)
 		return -ENOMEM;
 
diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c
index 5f6852dff40b..44d4475a09dd 100644
--- a/drivers/misc/tifm_core.c
+++ b/drivers/misc/tifm_core.c
@@ -329,7 +329,7 @@ static int __init tifm_init(void)
 {
 	int rc;
 
-	workqueue = create_freezeable_workqueue("tifm");
+	workqueue = create_freezable_workqueue("tifm");
 	if (!workqueue)
 		return -ENOMEM;
 
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index 4d2ea8e80140..6df5a55da110 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -785,7 +785,7 @@ static int __init vmballoon_init(void)
 	if (x86_hyper != &x86_hyper_vmware)
 		return -ENODEV;
 
-	vmballoon_wq = create_freezeable_workqueue("vmmemctl");
+	vmballoon_wq = create_freezable_workqueue("vmmemctl");
 	if (!vmballoon_wq) {
 		pr_err("failed to create workqueue\n");
 		return -ENOMEM;
diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c
index d9d7efbc77cc..6322d1fb5d62 100644
--- a/drivers/mtd/nand/r852.c
+++ b/drivers/mtd/nand/r852.c
@@ -930,7 +930,7 @@ int  r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 
 	init_completion(&dev->dma_done);
 
-	dev->card_workqueue = create_freezeable_workqueue(DRV_NAME);
+	dev->card_workqueue = create_freezable_workqueue(DRV_NAME);
 
 	if (!dev->card_workqueue)
 		goto error9;
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index 67822cf6c025..ac0d6a8613b5 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -1258,7 +1258,7 @@ static struct mtd_blktrans_ops sm_ftl_ops = {
 static __init int sm_module_init(void)
 {
 	int error = 0;
-	cache_flush_workqueue = create_freezeable_workqueue("smflush");
+	cache_flush_workqueue = create_freezable_workqueue("smflush");
 
 	if (IS_ERR(cache_flush_workqueue))
 		return PTR_ERR(cache_flush_workqueue);
diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c
index 7ab534aee452..7513c4523ac4 100644
--- a/drivers/net/can/mcp251x.c
+++ b/drivers/net/can/mcp251x.c
@@ -940,7 +940,7 @@ static int mcp251x_open(struct net_device *net)
 		goto open_unlock;
 	}
 
-	priv->wq = create_freezeable_workqueue("mcp251x_wq");
+	priv->wq = create_freezable_workqueue("mcp251x_wq");
 	INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler);
 	INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler);
 
diff --git a/drivers/tty/serial/max3100.c b/drivers/tty/serial/max3100.c
index beb1afa27d8d..7b951adac54b 100644
--- a/drivers/tty/serial/max3100.c
+++ b/drivers/tty/serial/max3100.c
@@ -601,7 +601,7 @@ static int max3100_startup(struct uart_port *port)
 	s->rts = 0;
 
 	sprintf(b, "max3100-%d", s->minor);
-	s->workqueue = create_freezeable_workqueue(b);
+	s->workqueue = create_freezable_workqueue(b);
 	if (!s->workqueue) {
 		dev_warn(&s->spi->dev, "cannot create workqueue\n");
 		return -EBUSY;
diff --git a/drivers/tty/serial/max3107.c b/drivers/tty/serial/max3107.c
index 910870edf708..750b4f627315 100644
--- a/drivers/tty/serial/max3107.c
+++ b/drivers/tty/serial/max3107.c
@@ -833,7 +833,7 @@ static int max3107_startup(struct uart_port *port)
 	struct max3107_port *s = container_of(port, struct max3107_port, port);
 
 	/* Initialize work queue */
-	s->workqueue = create_freezeable_workqueue("max3107");
+	s->workqueue = create_freezable_workqueue("max3107");
 	if (!s->workqueue) {
 		dev_err(&s->spi->dev, "Workqueue creation failed\n");
 		return -EBUSY;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 08a8beb152e6..7cd9a5a68d59 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1779,11 +1779,11 @@ int __init gfs2_glock_init(void)
 #endif
 
 	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
-					  WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+					  WQ_HIGHPRI | WQ_FREEZABLE, 0);
 	if (IS_ERR(glock_workqueue))
 		return PTR_ERR(glock_workqueue);
 	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
-						WQ_MEM_RECLAIM | WQ_FREEZEABLE,
+						WQ_MEM_RECLAIM | WQ_FREEZABLE,
 						0);
 	if (IS_ERR(gfs2_delete_workqueue)) {
 		destroy_workqueue(glock_workqueue);
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index ebef7ab6e17e..85ba027d1c4d 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -144,7 +144,7 @@ static int __init init_gfs2_fs(void)
 
 	error = -ENOMEM;
 	gfs_recovery_wq = alloc_workqueue("gfs_recovery",
-					  WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0);
+					  WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
 	if (!gfs_recovery_wq)
 		goto fail_wq;
 
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index da7e52b099f3..1effc8b56b4e 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -109,7 +109,7 @@ static inline void freezer_count(void)
 }
 
 /*
- * Check if the task should be counted as freezeable by the freezer
+ * Check if the task should be counted as freezable by the freezer
  */
 static inline int freezer_should_skip(struct task_struct *p)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d747f948b34e..777d8a5ed06b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1744,7 +1744,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
-#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
+#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
 #define PF_FREEZER_NOSIG 0x80000000	/* Freezer won't send signals to it */
 
 /*
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 1ac11586a2f5..f7998a3bf020 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -250,7 +250,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
 enum {
 	WQ_NON_REENTRANT	= 1 << 0, /* guarantee non-reentrance */
 	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
-	WQ_FREEZEABLE		= 1 << 2, /* freeze during suspend */
+	WQ_FREEZABLE		= 1 << 2, /* freeze during suspend */
 	WQ_MEM_RECLAIM		= 1 << 3, /* may be used for memory reclaim */
 	WQ_HIGHPRI		= 1 << 4, /* high priority */
 	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu instensive workqueue */
@@ -318,7 +318,7 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
 /**
  * alloc_ordered_workqueue - allocate an ordered workqueue
  * @name: name of the workqueue
- * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful)
+ * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
  *
  * Allocate an ordered workqueue.  An ordered workqueue executes at
  * most one work item at any given time in the queued order.  They are
@@ -335,8 +335,8 @@ alloc_ordered_workqueue(const char *name, unsigned int flags)
 
 #define create_workqueue(name)					\
 	alloc_workqueue((name), WQ_MEM_RECLAIM, 1)
-#define create_freezeable_workqueue(name)			\
-	alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
+#define create_freezable_workqueue(name)			\
+	alloc_workqueue((name), WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
 #define create_singlethread_workqueue(name)			\
 	alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7b5db6a8561e..701853042c28 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(pm_wq);
 
 static int __init pm_start_workqueue(void)
 {
-	pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+	pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
 
 	return pm_wq ? 0 : -ENOMEM;
 }
diff --git a/kernel/power/process.c b/kernel/power/process.c
index d6d2a10320e0..0cf3a27a6c9d 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -22,7 +22,7 @@
  */
 #define TIMEOUT	(20 * HZ)
 
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
 {
 	if ((p == current) ||
 	    (p->flags & PF_NOFREEZE) ||
@@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only)
 		todo = 0;
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			if (frozen(p) || !freezeable(p))
+			if (frozen(p) || !freezable(p))
 				continue;
 
 			if (!freeze_task(p, sig_only))
@@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only)
 
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
-		if (!freezeable(p))
+		if (!freezable(p))
 			continue;
 
 		if (nosig_only && should_send_signal(p))
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 90a17ca2ad0b..88a3e34f51f6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2965,7 +2965,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
 	 */
 	spin_lock(&workqueue_lock);
 
-	if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+	if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
 		for_each_cwq_cpu(cpu, wq)
 			get_cwq(cpu, wq)->max_active = 0;
 
@@ -3077,7 +3077,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 
 		spin_lock_irq(&gcwq->lock);
 
-		if (!(wq->flags & WQ_FREEZEABLE) ||
+		if (!(wq->flags & WQ_FREEZABLE) ||
 		    !(gcwq->flags & GCWQ_FREEZING))
 			get_cwq(gcwq->cpu, wq)->max_active = max_active;
 
@@ -3327,7 +3327,7 @@ static int __cpuinit trustee_thread(void *__gcwq)
 	 * want to get it over with ASAP - spam rescuers, wake up as
 	 * many idlers as necessary and create new ones till the
 	 * worklist is empty.  Note that if the gcwq is frozen, there
-	 * may be frozen works in freezeable cwqs.  Don't declare
+	 * may be frozen works in freezable cwqs.  Don't declare
 	 * completion while frozen.
 	 */
 	while (gcwq->nr_workers != gcwq->nr_idle ||
@@ -3585,9 +3585,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 /**
  * freeze_workqueues_begin - begin freezing workqueues
  *
- * Start freezing workqueues.  After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues.  After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
  *
  * CONTEXT:
  * Grabs and releases workqueue_lock and gcwq->lock's.
@@ -3613,7 +3613,7 @@ void freeze_workqueues_begin(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (cwq && wq->flags & WQ_FREEZEABLE)
+			if (cwq && wq->flags & WQ_FREEZABLE)
 				cwq->max_active = 0;
 		}
 
@@ -3624,7 +3624,7 @@ void freeze_workqueues_begin(void)
 }
 
 /**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
  *
  * Check whether freezing is complete.  This function must be called
  * between freeze_workqueues_begin() and thaw_workqueues().
@@ -3633,8 +3633,8 @@ void freeze_workqueues_begin(void)
  * Grabs and releases workqueue_lock.
  *
  * RETURNS:
- * %true if some freezeable workqueues are still busy.  %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy.  %false if freezing
+ * is complete.
  */
 bool freeze_workqueues_busy(void)
 {
@@ -3654,7 +3654,7 @@ bool freeze_workqueues_busy(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+			if (!cwq || !(wq->flags & WQ_FREEZABLE))
 				continue;
 
 			BUG_ON(cwq->nr_active < 0);
@@ -3699,7 +3699,7 @@ void thaw_workqueues(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+			if (!cwq || !(wq->flags & WQ_FREEZABLE))
 				continue;
 
 			/* restore max_active and repopulate worklist */
-- 
cgit v1.2.3


From 63185f64ef06464706b32c9a301f71f68cd93e52 Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Thu, 10 Feb 2011 22:38:46 -0300
Subject: Bluetooth: Add low energy commands and events

Add needed HCI command and event structs to
create LE connections.

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h | 49 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4bee030e4b52..802d2505f138 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -642,6 +642,36 @@ struct hci_rp_read_bd_addr {
 	bdaddr_t bdaddr;
 } __packed;
 
+#define HCI_OP_LE_SET_EVENT_MASK	0x2001
+struct hci_cp_le_set_event_mask {
+	__u8     mask[8];
+} __packed;
+
+#define HCI_OP_LE_READ_BUFFER_SIZE	0x2002
+struct hci_rp_le_read_buffer_size {
+	__u8     status;
+	__le16   le_mtu;
+	__u8     le_max_pkt;
+} __packed;
+
+#define HCI_OP_LE_CREATE_CONN		0x200d
+struct hci_cp_le_create_conn {
+	__le16   scan_interval;
+	__le16   scan_window;
+	__u8     filter_policy;
+	__u8     peer_addr_type;
+	bdaddr_t peer_addr;
+	__u8     own_address_type;
+	__le16   conn_interval_min;
+	__le16   conn_interval_max;
+	__le16   conn_latency;
+	__le16   supervision_timeout;
+	__le16   min_ce_len;
+	__le16   max_ce_len;
+} __packed;
+
+#define HCI_OP_LE_CREATE_CONN_CANCEL	0x200e
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
@@ -902,6 +932,25 @@ struct hci_ev_remote_host_features {
 	__u8     features[8];
 } __packed;
 
+#define HCI_EV_LE_META			0x3e
+struct hci_ev_le_meta {
+	__u8     subevent;
+} __packed;
+
+/* Low energy meta events */
+#define HCI_EV_LE_CONN_COMPLETE		0x01
+struct hci_ev_le_conn_complete {
+	__u8     status;
+	__le16   handle;
+	__u8     role;
+	__u8     bdaddr_type;
+	bdaddr_t bdaddr;
+	__le16   interval;
+	__le16   latency;
+	__le16   supervision_timeout;
+	__u8     clk_accurancy;
+} __packed;
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
-- 
cgit v1.2.3


From fcd89c09a59a054fb986861e0862aa2fff7d7c40 Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Thu, 10 Feb 2011 22:38:47 -0300
Subject: Bluetooth: Add LE connect support

Bluetooth V4.0 adds support for Low Energy (LE) connections.
Specification introduces new set of hci commands to control LE
connection. This patch adds logic to create, cancel and disconnect
LE connections.

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |  2 +
 include/net/bluetooth/hci_core.h | 25 +++++++++--
 net/bluetooth/hci_conn.c         | 51 ++++++++++++++++++++--
 net/bluetooth/hci_event.c        | 93 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 164 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 802d2505f138..e756f82a29e5 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -168,6 +168,8 @@ enum {
 #define SCO_LINK	0x00
 #define ACL_LINK	0x01
 #define ESCO_LINK	0x02
+/* Low Energy links do not have defined link type. Use invented one */
+#define LE_LINK		0x80
 
 /* LMP features */
 #define LMP_3SLOT	0x01
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6163bff6fa91..f434e96ce020 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -60,6 +60,7 @@ struct hci_conn_hash {
 	spinlock_t       lock;
 	unsigned int     acl_num;
 	unsigned int     sco_num;
+	unsigned int     le_num;
 };
 
 struct bdaddr_list {
@@ -309,20 +310,36 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	list_add(&c->list, &h->list);
-	if (c->type == ACL_LINK)
+	switch (c->type) {
+	case ACL_LINK:
 		h->acl_num++;
-	else
+		break;
+	case LE_LINK:
+		h->le_num++;
+		break;
+	case SCO_LINK:
+	case ESCO_LINK:
 		h->sco_num++;
+		break;
+	}
 }
 
 static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	list_del(&c->list);
-	if (c->type == ACL_LINK)
+	switch (c->type) {
+	case ACL_LINK:
 		h->acl_num--;
-	else
+		break;
+	case LE_LINK:
+		h->le_num--;
+		break;
+	case SCO_LINK:
+	case ESCO_LINK:
 		h->sco_num--;
+		break;
+	}
 }
 
 static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev,
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 42dc39f25b72..d0c470c18f9d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -45,6 +45,32 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
+static void hci_le_connect(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+	struct hci_cp_le_create_conn cp;
+
+	conn->state = BT_CONNECT;
+	conn->out = 1;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.scan_interval = cpu_to_le16(0x0004);
+	cp.scan_window = cpu_to_le16(0x0004);
+	bacpy(&cp.peer_addr, &conn->dst);
+	cp.conn_interval_min = cpu_to_le16(0x0008);
+	cp.conn_interval_max = cpu_to_le16(0x0100);
+	cp.supervision_timeout = cpu_to_le16(0x0064);
+	cp.min_ce_len = cpu_to_le16(0x0001);
+	cp.max_ce_len = cpu_to_le16(0x0001);
+
+	hci_send_cmd(hdev, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp);
+}
+
+static void hci_le_connect_cancel(struct hci_conn *conn)
+{
+	hci_send_cmd(conn->hdev, HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL);
+}
+
 void hci_acl_connect(struct hci_conn *conn)
 {
 	struct hci_dev *hdev = conn->hdev;
@@ -193,8 +219,12 @@ static void hci_conn_timeout(unsigned long arg)
 	switch (conn->state) {
 	case BT_CONNECT:
 	case BT_CONNECT2:
-		if (conn->type == ACL_LINK && conn->out)
-			hci_acl_connect_cancel(conn);
+		if (conn->out) {
+			if (conn->type == ACL_LINK)
+				hci_acl_connect_cancel(conn);
+			else if (conn->type == LE_LINK)
+				hci_le_connect_cancel(conn);
+		}
 		break;
 	case BT_CONFIG:
 	case BT_CONNECTED:
@@ -361,15 +391,30 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src)
 }
 EXPORT_SYMBOL(hci_get_route);
 
-/* Create SCO or ACL connection.
+/* Create SCO, ACL or LE connection.
  * Device _must_ be locked */
 struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 sec_level, __u8 auth_type)
 {
 	struct hci_conn *acl;
 	struct hci_conn *sco;
+	struct hci_conn *le;
 
 	BT_DBG("%s dst %s", hdev->name, batostr(dst));
 
+	if (type == LE_LINK) {
+		le = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst);
+		if (!le)
+			le = hci_conn_add(hdev, LE_LINK, dst);
+		if (!le)
+			return NULL;
+		if (le->state == BT_OPEN)
+			hci_le_connect(le);
+
+		hci_conn_hold(le);
+
+		return le;
+	}
+
 	acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
 	if (!acl) {
 		acl = hci_conn_add(hdev, ACL_LINK, dst);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index cee46cbe7aeb..47c6e9316ce8 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1107,6 +1107,43 @@ static void hci_cs_exit_sniff_mode(struct hci_dev *hdev, __u8 status)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cs_le_create_conn(struct hci_dev *hdev, __u8 status)
+{
+	struct hci_cp_le_create_conn *cp;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%x", hdev->name, status);
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->peer_addr);
+
+	BT_DBG("%s bdaddr %s conn %p", hdev->name, batostr(&cp->peer_addr),
+		conn);
+
+	if (status) {
+		if (conn && conn->state == BT_CONNECT) {
+			conn->state = BT_CLOSED;
+			hci_proto_connect_cfm(conn, status);
+			hci_conn_del(conn);
+		}
+	} else {
+		if (!conn) {
+			conn = hci_conn_add(hdev, LE_LINK, &cp->peer_addr);
+			if (conn)
+				conn->out = 1;
+			else
+				BT_ERR("No memory for new connection");
+		}
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static inline void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -1738,6 +1775,10 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			mgmt_disconnect_failed(hdev->id);
 		break;
 
+	case HCI_OP_LE_CREATE_CONN:
+		hci_cs_le_create_conn(hdev, ev->status);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
@@ -2321,6 +2362,54 @@ static inline void hci_remote_host_features_evt(struct hci_dev *hdev, struct sk_
 	hci_dev_unlock(hdev);
 }
 
+static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_le_conn_complete *ev = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status %d", hdev->name, ev->status);
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &ev->bdaddr);
+	if (!conn)
+		goto unlock;
+
+	if (ev->status) {
+		hci_proto_connect_cfm(conn, ev->status);
+		conn->state = BT_CLOSED;
+		hci_conn_del(conn);
+		goto unlock;
+	}
+
+	conn->handle = __le16_to_cpu(ev->handle);
+	conn->state = BT_CONNECTED;
+
+	hci_conn_hold_device(conn);
+	hci_conn_add_sysfs(conn);
+
+	hci_proto_connect_cfm(conn, ev->status);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static inline void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_le_meta *le_ev = (void *) skb->data;
+
+	skb_pull(skb, sizeof(*le_ev));
+
+	switch (le_ev->subevent) {
+	case HCI_EV_LE_CONN_COMPLETE:
+		hci_le_conn_complete_evt(hdev, skb);
+		break;
+
+	default:
+		break;
+	}
+}
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_event_hdr *hdr = (void *) skb->data;
@@ -2461,6 +2550,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_remote_host_features_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LE_META:
+		hci_le_meta_evt(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s event 0x%x", hdev->name, event);
 		break;
-- 
cgit v1.2.3


From 6ed58ec520ad2b2fe3f955c8a5fd0eecafccebdf Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Thu, 10 Feb 2011 22:38:48 -0300
Subject: Bluetooth: Use LE buffers for LE traffic

Bluetooth chips may have separate buffers for LE traffic.
This patch add support to use LE buffers provided by the chip.

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  5 +++
 net/bluetooth/hci_conn.c         |  5 +++
 net/bluetooth/hci_core.c         | 74 +++++++++++++++++++++++++++++++++++++---
 net/bluetooth/hci_event.c        | 33 ++++++++++++++++++
 4 files changed, 113 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f434e96ce020..d30b93c82fd4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -123,15 +123,19 @@ struct hci_dev {
 	atomic_t	cmd_cnt;
 	unsigned int	acl_cnt;
 	unsigned int	sco_cnt;
+	unsigned int	le_cnt;
 
 	unsigned int	acl_mtu;
 	unsigned int	sco_mtu;
+	unsigned int	le_mtu;
 	unsigned int	acl_pkts;
 	unsigned int	sco_pkts;
+	unsigned int	le_pkts;
 
 	unsigned long	cmd_last_tx;
 	unsigned long	acl_last_tx;
 	unsigned long	sco_last_tx;
+	unsigned long	le_last_tx;
 
 	struct workqueue_struct	*workqueue;
 
@@ -521,6 +525,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_esco_capable(dev)      ((dev)->features[3] & LMP_ESCO)
 #define lmp_ssp_capable(dev)       ((dev)->features[6] & LMP_SIMPLE_PAIR)
 #define lmp_no_flush_capable(dev)  ((dev)->features[6] & LMP_NO_FLUSH)
+#define lmp_le_capable(dev)        ((dev)->features[4] & LMP_LE)
 
 /* ----- HCI protocols ----- */
 struct hci_proto {
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index d0c470c18f9d..aecd78e6cceb 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -326,6 +326,11 @@ int hci_conn_del(struct hci_conn *conn)
 
 		/* Unacked frames */
 		hdev->acl_cnt += conn->sent;
+	} else if (conn->type == LE_LINK) {
+		if (hdev->le_pkts)
+			hdev->le_cnt += conn->sent;
+		else
+			hdev->acl_cnt += conn->sent;
 	} else {
 		struct hci_conn *acl = conn->link;
 		if (acl) {
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 2f003224d2ea..92960532dea4 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -263,6 +263,14 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt)
 	hci_send_cmd(hdev, HCI_OP_DELETE_STORED_LINK_KEY, sizeof(cp), &cp);
 }
 
+static void hci_le_init_req(struct hci_dev *hdev, unsigned long opt)
+{
+	BT_DBG("%s", hdev->name);
+
+	/* Read LE buffer size */
+	hci_send_cmd(hdev, HCI_OP_LE_READ_BUFFER_SIZE, 0, NULL);
+}
+
 static void hci_scan_req(struct hci_dev *hdev, unsigned long opt)
 {
 	__u8 scan = opt;
@@ -529,6 +537,10 @@ int hci_dev_open(__u16 dev)
 		ret = __hci_request(hdev, hci_init_req, 0,
 					msecs_to_jiffies(HCI_INIT_TIMEOUT));
 
+		if (lmp_le_capable(hdev))
+			ret = __hci_request(hdev, hci_le_init_req, 0,
+					msecs_to_jiffies(HCI_INIT_TIMEOUT));
+
 		clear_bit(HCI_INIT, &hdev->flags);
 	}
 
@@ -671,7 +683,7 @@ int hci_dev_reset(__u16 dev)
 		hdev->flush(hdev);
 
 	atomic_set(&hdev->cmd_cnt, 1);
-	hdev->acl_cnt = 0; hdev->sco_cnt = 0;
+	hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0;
 
 	if (!test_bit(HCI_RAW, &hdev->flags))
 		ret = __hci_request(hdev, hci_reset_req, 0,
@@ -1672,8 +1684,25 @@ static inline struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int
 	}
 
 	if (conn) {
-		int cnt = (type == ACL_LINK ? hdev->acl_cnt : hdev->sco_cnt);
-		int q = cnt / num;
+		int cnt, q;
+
+		switch (conn->type) {
+		case ACL_LINK:
+			cnt = hdev->acl_cnt;
+			break;
+		case SCO_LINK:
+		case ESCO_LINK:
+			cnt = hdev->sco_cnt;
+			break;
+		case LE_LINK:
+			cnt = hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt;
+			break;
+		default:
+			cnt = 0;
+			BT_ERR("Unknown link type");
+		}
+
+		q = cnt / num;
 		*quote = q ? q : 1;
 	} else
 		*quote = 0;
@@ -1772,6 +1801,40 @@ static inline void hci_sched_esco(struct hci_dev *hdev)
 	}
 }
 
+static inline void hci_sched_le(struct hci_dev *hdev)
+{
+	struct hci_conn *conn;
+	struct sk_buff *skb;
+	int quote, cnt;
+
+	BT_DBG("%s", hdev->name);
+
+	if (!test_bit(HCI_RAW, &hdev->flags)) {
+		/* LE tx timeout must be longer than maximum
+		 * link supervision timeout (40.9 seconds) */
+		if (!hdev->le_cnt &&
+				time_after(jiffies, hdev->le_last_tx + HZ * 45))
+			hci_acl_tx_to(hdev);
+	}
+
+	cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt;
+	while (cnt && (conn = hci_low_sent(hdev, LE_LINK, &quote))) {
+		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
+			BT_DBG("skb %p len %d", skb, skb->len);
+
+			hci_send_frame(skb);
+			hdev->le_last_tx = jiffies;
+
+			cnt--;
+			conn->sent++;
+		}
+	}
+	if (hdev->le_pkts)
+		hdev->le_cnt = cnt;
+	else
+		hdev->acl_cnt = cnt;
+}
+
 static void hci_tx_task(unsigned long arg)
 {
 	struct hci_dev *hdev = (struct hci_dev *) arg;
@@ -1779,7 +1842,8 @@ static void hci_tx_task(unsigned long arg)
 
 	read_lock(&hci_task_lock);
 
-	BT_DBG("%s acl %d sco %d", hdev->name, hdev->acl_cnt, hdev->sco_cnt);
+	BT_DBG("%s acl %d sco %d le %d", hdev->name, hdev->acl_cnt,
+		hdev->sco_cnt, hdev->le_cnt);
 
 	/* Schedule queues and send stuff to HCI driver */
 
@@ -1789,6 +1853,8 @@ static void hci_tx_task(unsigned long arg)
 
 	hci_sched_esco(hdev);
 
+	hci_sched_le(hdev);
+
 	/* Send next queued raw (unknown type) packet */
 	while ((skb = skb_dequeue(&hdev->raw_q)))
 		hci_send_frame(skb);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 47c6e9316ce8..3155ad588076 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -776,6 +776,25 @@ static void hci_cc_pin_code_neg_reply(struct hci_dev *hdev, struct sk_buff *skb)
 		mgmt_pin_code_neg_reply_complete(hdev->id, &rp->bdaddr,
 								rp->status);
 }
+static void hci_cc_le_read_buffer_size(struct hci_dev *hdev,
+				       struct sk_buff *skb)
+{
+	struct hci_rp_le_read_buffer_size *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->le_mtu = __le16_to_cpu(rp->le_mtu);
+	hdev->le_pkts = rp->le_max_pkt;
+
+	hdev->le_cnt = hdev->le_pkts;
+
+	BT_DBG("%s le mtu %d:%d", hdev->name, hdev->le_mtu, hdev->le_pkts);
+
+	hci_req_complete(hdev, HCI_OP_LE_READ_BUFFER_SIZE, rp->status);
+}
 
 static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
@@ -1704,6 +1723,10 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk
 		hci_cc_pin_code_neg_reply(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_BUFFER_SIZE:
+		hci_cc_le_read_buffer_size(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
@@ -1849,6 +1872,16 @@ static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *s
 				hdev->acl_cnt += count;
 				if (hdev->acl_cnt > hdev->acl_pkts)
 					hdev->acl_cnt = hdev->acl_pkts;
+			} else if (conn->type == LE_LINK) {
+				if (hdev->le_pkts) {
+					hdev->le_cnt += count;
+					if (hdev->le_cnt > hdev->le_pkts)
+						hdev->le_cnt = hdev->le_pkts;
+				} else {
+					hdev->acl_cnt += count;
+					if (hdev->acl_cnt > hdev->acl_pkts)
+						hdev->acl_cnt = hdev->acl_pkts;
+				}
 			} else {
 				hdev->sco_cnt += count;
 				if (hdev->sco_cnt > hdev->sco_pkts)
-- 
cgit v1.2.3


From acd7d3708555b3da7522e23c183cc21efc785f72 Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Thu, 10 Feb 2011 22:38:49 -0300
Subject: Bluetooth: Add LE connection support to L2CAP

Add basic LE connection support to L2CAP. LE
connection can be created by specifying cid
in struct sockaddr_l2

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  3 +++
 net/bluetooth/l2cap_core.c    | 23 +++++++++++++++++++----
 net/bluetooth/l2cap_sock.c    |  7 ++++---
 3 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 9fb87fe1aec3..cd7a64250e3c 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -160,6 +160,9 @@ struct l2cap_conn_rsp {
 /* channel indentifier */
 #define L2CAP_CID_SIGNALING	0x0001
 #define L2CAP_CID_CONN_LESS	0x0002
+#define L2CAP_CID_LE_DATA	0x0004
+#define L2CAP_CID_LE_SIGNALING	0x0005
+#define L2CAP_CID_SMP		0x0006
 #define L2CAP_CID_DYN_START	0x0040
 #define L2CAP_CID_DYN_END	0xffff
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a72d6e4eab4f..123c1bfa0ce6 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -593,6 +593,12 @@ static void l2cap_conn_ready(struct l2cap_conn *conn)
 	for (sk = l->head; sk; sk = l2cap_pi(sk)->next_c) {
 		bh_lock_sock(sk);
 
+		if (conn->hcon->type == LE_LINK) {
+			l2cap_sock_clear_timer(sk);
+			sk->sk_state = BT_CONNECTED;
+			sk->sk_state_change(sk);
+		}
+
 		if (sk->sk_type != SOCK_SEQPACKET &&
 				sk->sk_type != SOCK_STREAM) {
 			l2cap_sock_clear_timer(sk);
@@ -651,7 +657,11 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status)
 
 	BT_DBG("hcon %p conn %p", hcon, conn);
 
-	conn->mtu = hcon->hdev->acl_mtu;
+	if (hcon->hdev->le_mtu && hcon->type == LE_LINK)
+		conn->mtu = hcon->hdev->le_mtu;
+	else
+		conn->mtu = hcon->hdev->acl_mtu;
+
 	conn->src = &hcon->hdev->bdaddr;
 	conn->dst = &hcon->dst;
 
@@ -758,8 +768,13 @@ int l2cap_do_connect(struct sock *sk)
 
 	auth_type = l2cap_get_auth_type(sk);
 
-	hcon = hci_connect(hdev, ACL_LINK, dst,
+	if (l2cap_pi(sk)->dcid == L2CAP_CID_LE_DATA)
+		hcon = hci_connect(hdev, LE_LINK, dst,
 					l2cap_pi(sk)->sec_level, auth_type);
+	else
+		hcon = hci_connect(hdev, ACL_LINK, dst,
+					l2cap_pi(sk)->sec_level, auth_type);
+
 	if (!hcon)
 		goto done;
 
@@ -3520,7 +3535,7 @@ static int l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 
 	BT_DBG("hcon %p bdaddr %s status %d", hcon, batostr(&hcon->dst), status);
 
-	if (hcon->type != ACL_LINK)
+	if (!(hcon->type == ACL_LINK || hcon->type == LE_LINK))
 		return -EINVAL;
 
 	if (!status) {
@@ -3549,7 +3564,7 @@ static int l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason)
 {
 	BT_DBG("hcon %p reason %d", hcon, reason);
 
-	if (hcon->type != ACL_LINK)
+	if (!(hcon->type == ACL_LINK || hcon->type == LE_LINK))
 		return -EINVAL;
 
 	l2cap_conn_del(hcon, bt_err(reason));
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 21f5385ca24d..f45d361e84d1 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -168,13 +168,13 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al
 	len = min_t(unsigned int, sizeof(la), alen);
 	memcpy(&la, addr, len);
 
-	if (la.l2_cid)
+	if (la.l2_cid && la.l2_psm)
 		return -EINVAL;
 
 	lock_sock(sk);
 
 	if ((sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM)
-			&& !la.l2_psm) {
+			&& !(la.l2_psm || la.l2_cid)) {
 		err = -EINVAL;
 		goto done;
 	}
@@ -216,7 +216,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al
 
 	/* PSM must be odd and lsb of upper byte must be 0 */
 	if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 &&
-		sk->sk_type != SOCK_RAW) {
+				sk->sk_type != SOCK_RAW && !la.l2_cid) {
 		err = -EINVAL;
 		goto done;
 	}
@@ -224,6 +224,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al
 	/* Set destination address and psm */
 	bacpy(&bt_sk(sk)->dst, &la.l2_bdaddr);
 	l2cap_pi(sk)->psm = la.l2_psm;
+	l2cap_pi(sk)->dcid = la.l2_cid;
 
 	err = l2cap_do_connect(sk);
 	if (err)
-- 
cgit v1.2.3


From b62f328b8f20abe97cdbaaf44c6e4f5e7a610f18 Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Thu, 10 Feb 2011 22:38:50 -0300
Subject: Bluetooth: Add server socket support for LE connection

Add support for LE server sockets.

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/hci_event.c     | 10 ++++-
 net/bluetooth/l2cap_core.c    | 94 +++++++++++++++++++++++++++++++++++++++++--
 net/bluetooth/l2cap_sock.c    |  7 +++-
 4 files changed, 105 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index cd7a64250e3c..41b3bc56f13f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -38,6 +38,7 @@
 #define L2CAP_DEFAULT_MAX_PDU_SIZE	1009    /* Sized for 3-DH5 packet */
 #define L2CAP_DEFAULT_ACK_TO		200
 #define L2CAP_LOCAL_BUSY_TRIES		12
+#define L2CAP_LE_DEFAULT_MTU		23
 
 #define L2CAP_CONN_TIMEOUT	(40000) /* 40 seconds */
 #define L2CAP_INFO_TIMEOUT	(4000)  /*  4 seconds */
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 3155ad588076..74f04a27734d 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2405,8 +2405,14 @@ static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &ev->bdaddr);
-	if (!conn)
-		goto unlock;
+	if (!conn) {
+		conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr);
+		if (!conn) {
+			BT_ERR("No memory for new connection");
+			hci_dev_unlock(hdev);
+			return;
+		}
+	}
 
 	if (ev->status) {
 		hci_proto_connect_cfm(conn, ev->status);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 123c1bfa0ce6..3079175065d4 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -181,8 +181,16 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct sock *sk, struct so
 	l2cap_pi(sk)->conn = conn;
 
 	if (sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM) {
-		/* Alloc CID for connection-oriented socket */
-		l2cap_pi(sk)->scid = l2cap_alloc_cid(l);
+		if (conn->hcon->type == LE_LINK) {
+			/* LE connection */
+			l2cap_pi(sk)->omtu = L2CAP_LE_DEFAULT_MTU;
+			l2cap_pi(sk)->scid = L2CAP_CID_LE_DATA;
+			l2cap_pi(sk)->dcid = L2CAP_CID_LE_DATA;
+		} else {
+			/* Alloc CID for connection-oriented socket */
+			l2cap_pi(sk)->scid = l2cap_alloc_cid(l);
+			l2cap_pi(sk)->omtu = L2CAP_DEFAULT_MTU;
+		}
 	} else if (sk->sk_type == SOCK_DGRAM) {
 		/* Connectionless socket */
 		l2cap_pi(sk)->scid = L2CAP_CID_CONN_LESS;
@@ -581,6 +589,82 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 	}
 }
 
+/* Find socket with cid and source bdaddr.
+ * Returns closest match, locked.
+ */
+static struct sock *l2cap_get_sock_by_scid(int state, __le16 cid, bdaddr_t *src)
+{
+	struct sock *s, *sk = NULL, *sk1 = NULL;
+	struct hlist_node *node;
+
+	read_lock(&l2cap_sk_list.lock);
+
+	sk_for_each(sk, node, &l2cap_sk_list.head) {
+		if (state && sk->sk_state != state)
+			continue;
+
+		if (l2cap_pi(sk)->scid == cid) {
+			/* Exact match. */
+			if (!bacmp(&bt_sk(sk)->src, src))
+				break;
+
+			/* Closest match */
+			if (!bacmp(&bt_sk(sk)->src, BDADDR_ANY))
+				sk1 = sk;
+		}
+	}
+	s = node ? sk : sk1;
+	if (s)
+		bh_lock_sock(s);
+	read_unlock(&l2cap_sk_list.lock);
+
+	return s;
+}
+
+static void l2cap_le_conn_ready(struct l2cap_conn *conn)
+{
+	struct l2cap_chan_list *list = &conn->chan_list;
+	struct sock *parent, *uninitialized_var(sk);
+
+	BT_DBG("");
+
+	/* Check if we have socket listening on cid */
+	parent = l2cap_get_sock_by_scid(BT_LISTEN, L2CAP_CID_LE_DATA,
+							conn->src);
+	if (!parent)
+		return;
+
+	/* Check for backlog size */
+	if (sk_acceptq_is_full(parent)) {
+		BT_DBG("backlog full %d", parent->sk_ack_backlog);
+		goto clean;
+	}
+
+	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC);
+	if (!sk)
+		goto clean;
+
+	write_lock_bh(&list->lock);
+
+	hci_conn_hold(conn->hcon);
+
+	l2cap_sock_init(sk, parent);
+	bacpy(&bt_sk(sk)->src, conn->src);
+	bacpy(&bt_sk(sk)->dst, conn->dst);
+
+	__l2cap_chan_add(conn, sk, parent);
+
+	l2cap_sock_set_timer(sk, sk->sk_sndtimeo);
+
+	sk->sk_state = BT_CONNECTED;
+	parent->sk_data_ready(parent, 0);
+
+	write_unlock_bh(&list->lock);
+
+clean:
+	bh_unlock_sock(parent);
+}
+
 static void l2cap_conn_ready(struct l2cap_conn *conn)
 {
 	struct l2cap_chan_list *l = &conn->chan_list;
@@ -588,6 +672,9 @@ static void l2cap_conn_ready(struct l2cap_conn *conn)
 
 	BT_DBG("conn %p", conn);
 
+	if (!conn->hcon->out && conn->hcon->type == LE_LINK)
+		l2cap_le_conn_ready(conn);
+
 	read_lock(&l->lock);
 
 	for (sk = l->head; sk; sk = l2cap_pi(sk)->next_c) {
@@ -670,7 +757,8 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status)
 	spin_lock_init(&conn->lock);
 	rwlock_init(&conn->chan_list.lock);
 
-	setup_timer(&conn->info_timer, l2cap_info_timeout,
+	if (hcon->type != LE_LINK)
+		setup_timer(&conn->info_timer, l2cap_info_timeout,
 						(unsigned long) conn);
 
 	conn->disc_reason = 0x13;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f45d361e84d1..a8d289373794 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -103,7 +103,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	len = min_t(unsigned int, sizeof(la), alen);
 	memcpy(&la, addr, len);
 
-	if (la.l2_cid)
+	if (la.l2_cid && la.l2_psm)
 		return -EINVAL;
 
 	lock_sock(sk);
@@ -145,6 +145,9 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 			l2cap_pi(sk)->sec_level = BT_SECURITY_SDP;
 	}
 
+	if (la.l2_cid)
+		l2cap_pi(sk)->scid = la.l2_cid;
+
 	write_unlock_bh(&l2cap_sk_list.lock);
 
 done:
@@ -266,7 +269,7 @@ static int l2cap_sock_listen(struct socket *sock, int backlog)
 		goto done;
 	}
 
-	if (!l2cap_pi(sk)->psm) {
+	if (!l2cap_pi(sk)->psm && !l2cap_pi(sk)->dcid) {
 		bdaddr_t *src = &bt_sk(sk)->src;
 		u16 psm;
 
-- 
cgit v1.2.3


From aff2cae3546df9f47f9fe24f3e85a7a84e825de8 Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Thu, 10 Feb 2011 22:38:54 -0300
Subject: Bluetooth: Add SMP command structures

Add command structures for security manager protocol.

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/smp.h | 76 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 include/net/bluetooth/smp.h

(limited to 'include')

diff --git a/include/net/bluetooth/smp.h b/include/net/bluetooth/smp.h
new file mode 100644
index 000000000000..8f2edbf979dc
--- /dev/null
+++ b/include/net/bluetooth/smp.h
@@ -0,0 +1,76 @@
+#ifndef __SMP_H
+#define __SMP_H
+
+struct smp_command_hdr {
+	__u8	code;
+} __packed;
+
+#define SMP_CMD_PAIRING_REQ	0x01
+#define SMP_CMD_PAIRING_RSP	0x02
+struct smp_cmd_pairing {
+	__u8	io_capability;
+	__u8	oob_flag;
+	__u8	auth_req;
+	__u8	max_key_size;
+	__u8	init_key_dist;
+	__u8	resp_key_dist;
+} __packed;
+
+#define SMP_CMD_PAIRING_CONFIRM	0x03
+struct smp_cmd_pairing_confirm {
+	__u8	confirm_val[16];
+} __packed;
+
+#define SMP_CMD_PAIRING_RANDOM	0x04
+struct smp_cmd_pairing_random {
+	__u8	rand_val[16];
+} __packed;
+
+#define SMP_CMD_PAIRING_FAIL	0x05
+struct smp_cmd_pairing_fail {
+	__u8	reason;
+} __packed;
+
+#define SMP_CMD_ENCRYPT_INFO	0x06
+struct smp_cmd_encrypt_info {
+	__u8	ltk[16];
+} __packed;
+
+#define SMP_CMD_MASTER_IDENT	0x07
+struct smp_cmd_master_ident {
+	__u16	ediv;
+	__u8	rand[8];
+} __packed;
+
+#define SMP_CMD_IDENT_INFO	0x08
+struct smp_cmd_ident_info {
+	__u8	irk[16];
+} __packed;
+
+#define SMP_CMD_IDENT_ADDR_INFO	0x09
+struct smp_cmd_ident_addr_info {
+	__u8	addr_type;
+	bdaddr_t bdaddr;
+} __packed;
+
+#define SMP_CMD_SIGN_INFO	0x0a
+struct smp_cmd_sign_info {
+	__u8	csrk[16];
+} __packed;
+
+#define SMP_CMD_SECURITY_REQ	0x0b
+struct smp_cmd_security_req {
+	__u8	auth_req;
+} __packed;
+
+#define SMP_PASSKEY_ENTRY_FAILED	0x01
+#define SMP_OOB_NOT_AVAIL		0x02
+#define SMP_AUTH_REQUIREMENTS		0x03
+#define SMP_CONFIRM_FAILED		0x04
+#define SMP_PAIRING_NOTSUPP		0x05
+#define SMP_ENC_KEY_SIZE		0x06
+#define SMP_CMD_NOTSUPP		0x07
+#define SMP_UNSPECIFIED		0x08
+#define SMP_REPEATED_ATTEMPTS		0x09
+
+#endif /* __SMP_H */
-- 
cgit v1.2.3


From 3300d9a930a79508032e3e03ac2bde3a22dd048d Mon Sep 17 00:00:00 2001
From: Claudio Takahasi <claudio.takahasi@openbossa.org>
Date: Fri, 11 Feb 2011 19:28:54 -0200
Subject: Bluetooth: Add LE signaling commands handling

This patch splits the L2CAP command handling function in order to
have a clear separation between the commands related to BR/EDR and
LE. Commands and responses in the LE signaling channel are not being
handled yet, command reject is sent to all received requests. Bluetooth
Core Specification, Volume 3, Part A, section 4 defines the signaling
packets formats and allowed commands/responses over the LE signaling
channel.

Signed-off-by: Claudio Takahasi <claudio.takahasi@openbossa.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h |   2 +
 net/bluetooth/l2cap_core.c    | 142 ++++++++++++++++++++++++++----------------
 2 files changed, 92 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 41b3bc56f13f..06f245dcf6b2 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -89,6 +89,8 @@ struct l2cap_conninfo {
 #define L2CAP_ECHO_RSP		0x09
 #define L2CAP_INFO_REQ		0x0a
 #define L2CAP_INFO_RSP		0x0b
+#define L2CAP_CONN_PARAM_UPDATE_REQ	0x12
+#define L2CAP_CONN_PARAM_UPDATE_RSP	0x13
 
 /* L2CAP feature mask */
 #define L2CAP_FEAT_FLOWCTL	0x00000001
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 3079175065d4..ce781a43f1d5 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1428,7 +1428,11 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 
 	lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE);
 	lh->len = cpu_to_le16(L2CAP_CMD_HDR_SIZE + dlen);
-	lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING);
+
+	if (conn->hcon->type == LE_LINK)
+		lh->cid = cpu_to_le16(L2CAP_CID_LE_SIGNALING);
+	else
+		lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING);
 
 	cmd = (struct l2cap_cmd_hdr *) skb_put(skb, L2CAP_CMD_HDR_SIZE);
 	cmd->code  = code;
@@ -2497,12 +2501,90 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm
 	return 0;
 }
 
-static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb)
+static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
+			struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data)
+{
+	int err = 0;
+
+	switch (cmd->code) {
+	case L2CAP_COMMAND_REJ:
+		l2cap_command_rej(conn, cmd, data);
+		break;
+
+	case L2CAP_CONN_REQ:
+		err = l2cap_connect_req(conn, cmd, data);
+		break;
+
+	case L2CAP_CONN_RSP:
+		err = l2cap_connect_rsp(conn, cmd, data);
+		break;
+
+	case L2CAP_CONF_REQ:
+		err = l2cap_config_req(conn, cmd, cmd_len, data);
+		break;
+
+	case L2CAP_CONF_RSP:
+		err = l2cap_config_rsp(conn, cmd, data);
+		break;
+
+	case L2CAP_DISCONN_REQ:
+		err = l2cap_disconnect_req(conn, cmd, data);
+		break;
+
+	case L2CAP_DISCONN_RSP:
+		err = l2cap_disconnect_rsp(conn, cmd, data);
+		break;
+
+	case L2CAP_ECHO_REQ:
+		l2cap_send_cmd(conn, cmd->ident, L2CAP_ECHO_RSP, cmd_len, data);
+		break;
+
+	case L2CAP_ECHO_RSP:
+		break;
+
+	case L2CAP_INFO_REQ:
+		err = l2cap_information_req(conn, cmd, data);
+		break;
+
+	case L2CAP_INFO_RSP:
+		err = l2cap_information_rsp(conn, cmd, data);
+		break;
+
+	default:
+		BT_ERR("Unknown BR/EDR signaling command 0x%2.2x", cmd->code);
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+}
+
+static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn,
+					struct l2cap_cmd_hdr *cmd, u8 *data)
+{
+	switch (cmd->code) {
+	case L2CAP_COMMAND_REJ:
+		return 0;
+
+	case L2CAP_CONN_PARAM_UPDATE_REQ:
+		return -EINVAL;
+
+	case L2CAP_CONN_PARAM_UPDATE_RSP:
+		return 0;
+
+	default:
+		BT_ERR("Unknown LE signaling command 0x%2.2x", cmd->code);
+		return -EINVAL;
+	}
+}
+
+static inline void l2cap_sig_channel(struct l2cap_conn *conn,
+							struct sk_buff *skb)
 {
 	u8 *data = skb->data;
 	int len = skb->len;
 	struct l2cap_cmd_hdr cmd;
-	int err = 0;
+	int err;
 
 	l2cap_raw_recv(conn, skb);
 
@@ -2521,55 +2603,10 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *sk
 			break;
 		}
 
-		switch (cmd.code) {
-		case L2CAP_COMMAND_REJ:
-			l2cap_command_rej(conn, &cmd, data);
-			break;
-
-		case L2CAP_CONN_REQ:
-			err = l2cap_connect_req(conn, &cmd, data);
-			break;
-
-		case L2CAP_CONN_RSP:
-			err = l2cap_connect_rsp(conn, &cmd, data);
-			break;
-
-		case L2CAP_CONF_REQ:
-			err = l2cap_config_req(conn, &cmd, cmd_len, data);
-			break;
-
-		case L2CAP_CONF_RSP:
-			err = l2cap_config_rsp(conn, &cmd, data);
-			break;
-
-		case L2CAP_DISCONN_REQ:
-			err = l2cap_disconnect_req(conn, &cmd, data);
-			break;
-
-		case L2CAP_DISCONN_RSP:
-			err = l2cap_disconnect_rsp(conn, &cmd, data);
-			break;
-
-		case L2CAP_ECHO_REQ:
-			l2cap_send_cmd(conn, cmd.ident, L2CAP_ECHO_RSP, cmd_len, data);
-			break;
-
-		case L2CAP_ECHO_RSP:
-			break;
-
-		case L2CAP_INFO_REQ:
-			err = l2cap_information_req(conn, &cmd, data);
-			break;
-
-		case L2CAP_INFO_RSP:
-			err = l2cap_information_rsp(conn, &cmd, data);
-			break;
-
-		default:
-			BT_ERR("Unknown signaling command 0x%2.2x", cmd.code);
-			err = -EINVAL;
-			break;
-		}
+		if (conn->hcon->type == LE_LINK)
+			err = l2cap_le_sig_cmd(conn, &cmd, data);
+		else
+			err = l2cap_bredr_sig_cmd(conn, &cmd, cmd_len, data);
 
 		if (err) {
 			struct l2cap_cmd_rej rej;
@@ -3566,6 +3603,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
 	BT_DBG("len %d, cid 0x%4.4x", len, cid);
 
 	switch (cid) {
+	case L2CAP_CID_LE_SIGNALING:
 	case L2CAP_CID_SIGNALING:
 		l2cap_sig_channel(conn, skb);
 		break;
-- 
cgit v1.2.3


From de73115a7d67e1b81dbde2285a7657f3e3867703 Mon Sep 17 00:00:00 2001
From: Claudio Takahasi <claudio.takahasi@openbossa.org>
Date: Fri, 11 Feb 2011 19:28:55 -0200
Subject: Bluetooth: Add connection parameter update response

Implements L2CAP Connection Parameter Update Response defined in
the Bluetooth Core Specification, Volume 3, Part A, section 4.21.
Address the LE Connection Parameter Procedure initiated by the slave.

Connection Interval Minimum and Maximum have the same range: 6 to
3200. Time = N * 1.25ms. Minimum shall be less or equal to Maximum.
The Slave Latency field shall have a value in the range of 0 to
((connSupervisionTimeout / connIntervalMax) - 1). Latency field shall
be less than 500. connSupervisionTimeout = Timeout Multiplier * 10 ms.
Multiplier field shall have a value in the range of 10 to 3200.

Signed-off-by: Claudio Takahasi <claudio.takahasi@openbossa.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/l2cap.h | 15 +++++++++++
 net/bluetooth/l2cap_core.c    | 59 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 73 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 06f245dcf6b2..4f4bff1eaed6 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -261,6 +261,21 @@ struct l2cap_info_rsp {
 #define L2CAP_IR_SUCCESS    0x0000
 #define L2CAP_IR_NOTSUPP    0x0001
 
+struct l2cap_conn_param_update_req {
+	__le16      min;
+	__le16      max;
+	__le16      latency;
+	__le16      to_multiplier;
+} __packed;
+
+struct l2cap_conn_param_update_rsp {
+	__le16      result;
+} __packed;
+
+/* Connection Parameters result */
+#define L2CAP_CONN_PARAM_ACCEPTED	0x0000
+#define L2CAP_CONN_PARAM_REJECTED	0x0001
+
 /* ----- L2CAP connections ----- */
 struct l2cap_chan_list {
 	struct sock	*head;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ce781a43f1d5..e0e7b82cff02 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2501,6 +2501,63 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm
 	return 0;
 }
 
+static int inline l2cap_check_conn_param(u16 min, u16 max, u16 latency,
+							u16 to_multiplier)
+{
+	u16 max_latency;
+
+	if (min > max || min < 6 || max > 3200)
+		return -EINVAL;
+
+	if (to_multiplier < 10 || to_multiplier > 3200)
+		return -EINVAL;
+
+	if (max >= to_multiplier * 8)
+		return -EINVAL;
+
+	max_latency = (to_multiplier * 8 / max) - 1;
+	if (latency > 499 || latency > max_latency)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
+					struct l2cap_cmd_hdr *cmd, u8 *data)
+{
+	struct hci_conn *hcon = conn->hcon;
+	struct l2cap_conn_param_update_req *req;
+	struct l2cap_conn_param_update_rsp rsp;
+	u16 min, max, latency, to_multiplier, cmd_len;
+
+	if (!(hcon->link_mode & HCI_LM_MASTER))
+		return -EINVAL;
+
+	cmd_len = __le16_to_cpu(cmd->len);
+	if (cmd_len != sizeof(struct l2cap_conn_param_update_req))
+		return -EPROTO;
+
+	req = (struct l2cap_conn_param_update_req *) data;
+	min 		= __le16_to_cpu(req->min);
+	max 		= __le16_to_cpu(req->max);
+	latency		= __le16_to_cpu(req->latency);
+	to_multiplier	= __le16_to_cpu(req->to_multiplier);
+
+	BT_DBG("min 0x%4.4x max 0x%4.4x latency: 0x%4.4x Timeout: 0x%4.4x",
+						min, max, latency, to_multiplier);
+
+	memset(&rsp, 0, sizeof(rsp));
+	if (l2cap_check_conn_param(min, max, latency, to_multiplier))
+		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
+	else
+		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED);
+
+	l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP,
+							sizeof(rsp), &rsp);
+
+	return 0;
+}
+
 static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
 			struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data)
 {
@@ -2567,7 +2624,7 @@ static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn,
 		return 0;
 
 	case L2CAP_CONN_PARAM_UPDATE_REQ:
-		return -EINVAL;
+		return l2cap_conn_param_update_req(conn, cmd, data);
 
 	case L2CAP_CONN_PARAM_UPDATE_RSP:
 		return 0;
-- 
cgit v1.2.3


From 6bd32326cdaa9b14794416150c88e4832fb7e592 Mon Sep 17 00:00:00 2001
From: Ville Tervo <ville.tervo@nokia.com>
Date: Wed, 16 Feb 2011 16:32:41 +0200
Subject: Bluetooth: Use proper timer for hci command timout

Use proper timer instead of hci command flow control to timeout
failed hci commands. Otherwise stack ends up sending commands
when flow control is used to block new commands.

2010-09-01 18:29:41.592132 < HCI Command: Remote Name Request (0x01|0x0019) plen 10
    bdaddr 00:16:CF:E1:C7:D7 mode 2 clkoffset 0x0000
2010-09-01 18:29:41.592681 > HCI Event: Command Status (0x0f) plen 4
    Remote Name Request (0x01|0x0019) status 0x00 ncmd 0
2010-09-01 18:29:51.022033 < HCI Command: Remote Name Request Cancel (0x01|0x001a) plen 6
    bdaddr 00:16:CF:E1:C7:D7

Signed-off-by: Ville Tervo <ville.tervo@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |  3 +++
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/hci_core.c         | 22 ++++++++++++++++------
 net/bluetooth/hci_event.c        |  6 ++++++
 4 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e756f82a29e5..6d4e11624fef 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -119,6 +119,7 @@ enum {
 #define HCI_PAIRING_TIMEOUT	(60000)	/* 60 seconds */
 #define HCI_IDLE_TIMEOUT	(6000)	/* 6 seconds */
 #define HCI_INIT_TIMEOUT	(10000)	/* 10 seconds */
+#define HCI_CMD_TIMEOUT		(1000)	/* 1 seconds */
 
 /* HCI data types */
 #define HCI_COMMAND_PKT		0x01
@@ -244,6 +245,8 @@ enum {
 #define HCI_AT_GENERAL_BONDING_MITM	0x05
 
 /* -----  HCI Commands ---- */
+#define HCI_OP_NOP			0x0000
+
 #define HCI_OP_INQUIRY			0x0401
 struct hci_cp_inquiry {
 	__u8     lap[3];
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d30b93c82fd4..ecd2acf24420 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -132,7 +132,6 @@ struct hci_dev {
 	unsigned int	sco_pkts;
 	unsigned int	le_pkts;
 
-	unsigned long	cmd_last_tx;
 	unsigned long	acl_last_tx;
 	unsigned long	sco_last_tx;
 	unsigned long	le_last_tx;
@@ -143,6 +142,7 @@ struct hci_dev {
 	struct work_struct	power_off;
 	struct timer_list	off_timer;
 
+	struct timer_list	cmd_timer;
 	struct tasklet_struct	cmd_task;
 	struct tasklet_struct	rx_task;
 	struct tasklet_struct	tx_task;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c01415bc8946..702d5651c656 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -41,6 +41,7 @@
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/rfkill.h>
+#include <linux/timer.h>
 #include <net/sock.h>
 
 #include <asm/system.h>
@@ -623,6 +624,7 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 
 	/* Drop last sent command */
 	if (hdev->sent_cmd) {
+		del_timer_sync(&hdev->cmd_timer);
 		kfree_skb(hdev->sent_cmd);
 		hdev->sent_cmd = NULL;
 	}
@@ -1066,6 +1068,16 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 	return 0;
 }
 
+/* HCI command timer function */
+static void hci_cmd_timer(unsigned long arg)
+{
+	struct hci_dev *hdev = (void *) arg;
+
+	BT_ERR("%s command tx timeout", hdev->name);
+	atomic_set(&hdev->cmd_cnt, 1);
+	tasklet_schedule(&hdev->cmd_task);
+}
+
 /* Register HCI device */
 int hci_register_dev(struct hci_dev *hdev)
 {
@@ -1112,6 +1124,8 @@ int hci_register_dev(struct hci_dev *hdev)
 	skb_queue_head_init(&hdev->cmd_q);
 	skb_queue_head_init(&hdev->raw_q);
 
+	setup_timer(&hdev->cmd_timer, hci_cmd_timer, (unsigned long) hdev);
+
 	for (i = 0; i < NUM_REASSEMBLY; i++)
 		hdev->reassembly[i] = NULL;
 
@@ -2004,11 +2018,6 @@ static void hci_cmd_task(unsigned long arg)
 
 	BT_DBG("%s cmd %d", hdev->name, atomic_read(&hdev->cmd_cnt));
 
-	if (!atomic_read(&hdev->cmd_cnt) && time_after(jiffies, hdev->cmd_last_tx + HZ)) {
-		BT_ERR("%s command tx timeout", hdev->name);
-		atomic_set(&hdev->cmd_cnt, 1);
-	}
-
 	/* Send queued commands */
 	if (atomic_read(&hdev->cmd_cnt)) {
 		skb = skb_dequeue(&hdev->cmd_q);
@@ -2021,7 +2030,8 @@ static void hci_cmd_task(unsigned long arg)
 		if (hdev->sent_cmd) {
 			atomic_dec(&hdev->cmd_cnt);
 			hci_send_frame(skb);
-			hdev->cmd_last_tx = jiffies;
+			mod_timer(&hdev->cmd_timer,
+				  jiffies + msecs_to_jiffies(HCI_CMD_TIMEOUT));
 		} else {
 			skb_queue_head(&hdev->cmd_q, skb);
 			tasklet_schedule(&hdev->cmd_task);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 74f04a27734d..09cb29e8713a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1732,6 +1732,9 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk
 		break;
 	}
 
+	if (ev->opcode != HCI_OP_NOP)
+		del_timer(&hdev->cmd_timer);
+
 	if (ev->ncmd) {
 		atomic_set(&hdev->cmd_cnt, 1);
 		if (!skb_queue_empty(&hdev->cmd_q))
@@ -1807,6 +1810,9 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 	}
 
+	if (ev->opcode != HCI_OP_NOP)
+		del_timer(&hdev->cmd_timer);
+
 	if (ev->ncmd) {
 		atomic_set(&hdev->cmd_cnt, 1);
 		if (!skb_queue_empty(&hdev->cmd_q))
-- 
cgit v1.2.3


From 2ce603ebe1f1420c7c5b013638ec29b4fc975180 Mon Sep 17 00:00:00 2001
From: Claudio Takahasi <claudio.takahasi@openbossa.org>
Date: Wed, 16 Feb 2011 20:44:53 -0200
Subject: Bluetooth: Send LE Connection Update Command

If the new connection update parameter are accepted, the LE master
host sends the LE Connection Update Command to its controller informing
the new requested parameters.

Signed-off-by: Claudio Takahasi <claudio.takahasi@openbossa.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      | 11 +++++++++++
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_conn.c         | 20 ++++++++++++++++++++
 net/bluetooth/l2cap_core.c       |  8 +++++++-
 4 files changed, 40 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6d4e11624fef..a5f8c4684a32 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -677,6 +677,17 @@ struct hci_cp_le_create_conn {
 
 #define HCI_OP_LE_CREATE_CONN_CANCEL	0x200e
 
+#define HCI_OP_LE_CONN_UPDATE		0x2013
+struct hci_cp_le_conn_update {
+	__le16   handle;
+	__le16   conn_interval_min;
+	__le16   conn_interval_max;
+	__le16   conn_latency;
+	__le16   supervision_timeout;
+	__le16   min_ce_len;
+	__le16   max_ce_len;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ecd2acf24420..7ee921d78a94 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -777,4 +777,6 @@ struct hci_sec_filter {
 
 void hci_req_complete(struct hci_dev *hdev, __u16 cmd, int result);
 
+void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max,
+					u16 latency, u16 to_multiplier);
 #endif /* __HCI_CORE_H */
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index efcd2b508f5d..a050a6984901 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -183,6 +183,26 @@ void hci_setup_sync(struct hci_conn *conn, __u16 handle)
 	hci_send_cmd(hdev, HCI_OP_SETUP_SYNC_CONN, sizeof(cp), &cp);
 }
 
+void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max,
+					u16 latency, u16 to_multiplier)
+{
+	struct hci_cp_le_conn_update cp;
+	struct hci_dev *hdev = conn->hdev;
+
+	memset(&cp, 0, sizeof(cp));
+
+	cp.handle		= cpu_to_le16(conn->handle);
+	cp.conn_interval_min	= cpu_to_le16(min);
+	cp.conn_interval_max	= cpu_to_le16(max);
+	cp.conn_latency		= cpu_to_le16(latency);
+	cp.supervision_timeout	= cpu_to_le16(to_multiplier);
+	cp.min_ce_len		= cpu_to_le16(0x0001);
+	cp.max_ce_len		= cpu_to_le16(0x0001);
+
+	hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp);
+}
+EXPORT_SYMBOL(hci_le_conn_update);
+
 /* Device _must_ be locked */
 void hci_sco_setup(struct hci_conn *conn, __u8 status)
 {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index e0e7b82cff02..bd3136710360 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2529,6 +2529,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 	struct l2cap_conn_param_update_req *req;
 	struct l2cap_conn_param_update_rsp rsp;
 	u16 min, max, latency, to_multiplier, cmd_len;
+	int err;
 
 	if (!(hcon->link_mode & HCI_LM_MASTER))
 		return -EINVAL;
@@ -2547,7 +2548,9 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 						min, max, latency, to_multiplier);
 
 	memset(&rsp, 0, sizeof(rsp));
-	if (l2cap_check_conn_param(min, max, latency, to_multiplier))
+
+	err = l2cap_check_conn_param(min, max, latency, to_multiplier);
+	if (err)
 		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
 	else
 		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED);
@@ -2555,6 +2558,9 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 	l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP,
 							sizeof(rsp), &rsp);
 
+	if (!err)
+		hci_le_conn_update(hcon, min, max, latency, to_multiplier);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From d503b30bd648b3cb4e5f50b65d27e389960cc6d9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fwestphal@astaro.com>
Date: Thu, 17 Feb 2011 11:32:38 +0100
Subject: netfilter: tproxy: do not assign timewait sockets to skb->sk

Assigning a socket in timewait state to skb->sk can trigger
kernel oops, e.g. in nfnetlink_log, which does:

if (skb->sk) {
        read_lock_bh(&skb->sk->sk_callback_lock);
        if (skb->sk->sk_socket && skb->sk->sk_socket->file) ...

in the timewait case, accessing sk->sk_callback_lock and sk->sk_socket
is invalid.

Either all of these spots will need to add a test for sk->sk_state != TCP_TIME_WAIT,
or xt_TPROXY must not assign a timewait socket to skb->sk.

This does the latter.

If a TW socket is found, assign the tproxy nfmark, but skip the skb->sk assignment,
thus mimicking behaviour of a '-m socket .. -j MARK/ACCEPT' re-routing rule.

The 'SYN to TW socket' case is left unchanged -- we try to redirect to the
listener socket.

Cc: Balazs Scheidler <bazsi@balabit.hu>
Cc: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_tproxy_core.h | 12 +-----------
 net/netfilter/nf_tproxy_core.c         | 27 ++++++++++++---------------
 net/netfilter/xt_TPROXY.c              | 22 ++++++++++++++++++++--
 net/netfilter/xt_socket.c              | 13 +++++++++++--
 4 files changed, 44 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h
index cd85b3bc8327..e505358d8999 100644
--- a/include/net/netfilter/nf_tproxy_core.h
+++ b/include/net/netfilter/nf_tproxy_core.h
@@ -201,18 +201,8 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
 }
 #endif
 
-static inline void
-nf_tproxy_put_sock(struct sock *sk)
-{
-	/* TIME_WAIT inet sockets have to be handled differently */
-	if ((sk->sk_protocol == IPPROTO_TCP) && (sk->sk_state == TCP_TIME_WAIT))
-		inet_twsk_put(inet_twsk(sk));
-	else
-		sock_put(sk);
-}
-
 /* assign a socket to the skb -- consumes sk */
-int
+void
 nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk);
 
 #endif
diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c
index 4d87befb04c0..474d621cbc2e 100644
--- a/net/netfilter/nf_tproxy_core.c
+++ b/net/netfilter/nf_tproxy_core.c
@@ -28,26 +28,23 @@ nf_tproxy_destructor(struct sk_buff *skb)
 	skb->destructor = NULL;
 
 	if (sk)
-		nf_tproxy_put_sock(sk);
+		sock_put(sk);
 }
 
 /* consumes sk */
-int
+void
 nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
 {
-	bool transparent = (sk->sk_state == TCP_TIME_WAIT) ?
-				inet_twsk(sk)->tw_transparent :
-				inet_sk(sk)->transparent;
-
-	if (transparent) {
-		skb_orphan(skb);
-		skb->sk = sk;
-		skb->destructor = nf_tproxy_destructor;
-		return 1;
-	} else
-		nf_tproxy_put_sock(sk);
-
-	return 0;
+	/* assigning tw sockets complicates things; most
+	 * skb->sk->X checks would have to test sk->sk_state first */
+	if (sk->sk_state == TCP_TIME_WAIT) {
+		inet_twsk_put(inet_twsk(sk));
+		return;
+	}
+
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = nf_tproxy_destructor;
 }
 EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock);
 
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 640678f47a2a..dcfd57eb9d02 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -33,6 +33,20 @@
 #include <net/netfilter/nf_tproxy_core.h>
 #include <linux/netfilter/xt_TPROXY.h>
 
+static bool tproxy_sk_is_transparent(struct sock *sk)
+{
+	if (sk->sk_state != TCP_TIME_WAIT) {
+		if (inet_sk(sk)->transparent)
+			return true;
+		sock_put(sk);
+	} else {
+		if (inet_twsk(sk)->tw_transparent)
+			return true;
+		inet_twsk_put(inet_twsk(sk));
+	}
+	return false;
+}
+
 static inline __be32
 tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 {
@@ -141,7 +155,7 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport,
 					   skb->dev, NFT_LOOKUP_LISTENER);
 
 	/* NOTE: assign_sock consumes our sk reference */
-	if (sk && nf_tproxy_assign_sock(skb, sk)) {
+	if (sk && tproxy_sk_is_transparent(sk)) {
 		/* This should be in a separate target, but we don't do multiple
 		   targets on the same rule yet */
 		skb->mark = (skb->mark & ~mark_mask) ^ mark_value;
@@ -149,6 +163,8 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport,
 		pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n",
 			 iph->protocol, &iph->daddr, ntohs(hp->dest),
 			 &laddr, ntohs(lport), skb->mark);
+
+		nf_tproxy_assign_sock(skb, sk);
 		return NF_ACCEPT;
 	}
 
@@ -306,7 +322,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 					   par->in, NFT_LOOKUP_LISTENER);
 
 	/* NOTE: assign_sock consumes our sk reference */
-	if (sk && nf_tproxy_assign_sock(skb, sk)) {
+	if (sk && tproxy_sk_is_transparent(sk)) {
 		/* This should be in a separate target, but we don't do multiple
 		   targets on the same rule yet */
 		skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value;
@@ -314,6 +330,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 		pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n",
 			 tproto, &iph->saddr, ntohs(hp->source),
 			 laddr, ntohs(lport), skb->mark);
+
+		nf_tproxy_assign_sock(skb, sk);
 		return NF_ACCEPT;
 	}
 
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 00d6ae838303..9cc46356b577 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -35,6 +35,15 @@
 #include <net/netfilter/nf_conntrack.h>
 #endif
 
+static void
+xt_socket_put_sk(struct sock *sk)
+{
+	if (sk->sk_state == TCP_TIME_WAIT)
+		inet_twsk_put(inet_twsk(sk));
+	else
+		sock_put(sk);
+}
+
 static int
 extract_icmp4_fields(const struct sk_buff *skb,
 		    u8 *protocol,
@@ -164,7 +173,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 				       (sk->sk_state == TCP_TIME_WAIT &&
 					inet_twsk(sk)->tw_transparent));
 
-		nf_tproxy_put_sock(sk);
+		xt_socket_put_sk(sk);
 
 		if (wildcard || !transparent)
 			sk = NULL;
@@ -298,7 +307,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par)
 				       (sk->sk_state == TCP_TIME_WAIT &&
 					inet_twsk(sk)->tw_transparent));
 
-		nf_tproxy_put_sock(sk);
+		xt_socket_put_sk(sk);
 
 		if (wildcard || !transparent)
 			sk = NULL;
-- 
cgit v1.2.3


From adc4266d87ba95e250e5ffa217c72b4b78c2b56a Mon Sep 17 00:00:00 2001
From: Szymon Janc <szymon.janc@tieto.com>
Date: Thu, 17 Feb 2011 16:42:00 +0100
Subject: Bluetooth: Fix some code style issues in hci_core.h

Signed-off-by: Szymon Janc <szymon.janc@tieto.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h | 58 ++++++++++++++++++++--------------------
 1 file changed, 29 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 7ee921d78a94..d5d8454236bf 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -199,37 +199,37 @@ struct hci_dev {
 struct hci_conn {
 	struct list_head list;
 
-	atomic_t	 refcnt;
-	spinlock_t	 lock;
-
-	bdaddr_t	 dst;
-	__u16		 handle;
-	__u16		 state;
-	__u8             mode;
-	__u8		 type;
-	__u8		 out;
-	__u8		 attempt;
-	__u8		 dev_class[3];
-	__u8             features[8];
-	__u8             ssp_mode;
-	__u16            interval;
-	__u16            pkt_type;
-	__u16            link_policy;
-	__u32		 link_mode;
-	__u8             auth_type;
-	__u8             sec_level;
-	__u8		 pending_sec_level;
-	__u8		 pin_length;
-	__u8		 io_capability;
-	__u8             power_save;
-	__u16            disc_timeout;
-	unsigned long	 pend;
+	atomic_t	refcnt;
+	spinlock_t	lock;
+
+	bdaddr_t	dst;
+	__u16		handle;
+	__u16		state;
+	__u8		mode;
+	__u8		type;
+	__u8		out;
+	__u8		attempt;
+	__u8		dev_class[3];
+	__u8		features[8];
+	__u8		ssp_mode;
+	__u16		interval;
+	__u16		pkt_type;
+	__u16		link_policy;
+	__u32		link_mode;
+	__u8		auth_type;
+	__u8		sec_level;
+	__u8		pending_sec_level;
+	__u8		pin_length;
+	__u8		io_capability;
+	__u8		power_save;
+	__u16		disc_timeout;
+	unsigned long	pend;
 
 	__u8		remote_cap;
 	__u8		remote_oob;
 	__u8		remote_auth;
 
-	unsigned int	 sent;
+	unsigned int	sent;
 
 	struct sk_buff_head data_q;
 
@@ -347,7 +347,7 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c)
 }
 
 static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev,
-					__u16 handle)
+								__u16 handle)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct list_head *p;
@@ -362,7 +362,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev,
 }
 
 static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev,
-					__u8 type, bdaddr_t *ba)
+							__u8 type, bdaddr_t *ba)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct list_head *p;
@@ -377,7 +377,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev,
 }
 
 static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev,
-					__u8 type, __u16 state)
+							__u8 type, __u16 state)
 {
 	struct hci_conn_hash *h = &hdev->conn_hash;
 	struct list_head *p;
-- 
cgit v1.2.3


From b9f2e9a122a4d51dc13e2e9571034cb2d29dfe44 Mon Sep 17 00:00:00 2001
From: Paul Bolle <pebolle@tiscali.nl>
Date: Mon, 14 Feb 2011 23:06:15 +0100
Subject: USB: usb.h: Make comment match the defines it describes

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/usb/ch11.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/ch11.h b/include/linux/usb/ch11.h
index 10ec0699bea4..38c42b013641 100644
--- a/include/linux/usb/ch11.h
+++ b/include/linux/usb/ch11.h
@@ -132,8 +132,8 @@ struct usb_port_status {
 
 /*
  * wPortChange bit field
- * See USB 2.0 spec Table 11-22
- * Bits 0 to 4 shown, bits 5 to 15 are reserved
+ * See USB 2.0 spec Table 11-22 and USB 2.0 LPM ECN Table-4.10
+ * Bits 0 to 5 shown, bits 6 to 15 are reserved
  */
 #define USB_PORT_STAT_C_CONNECTION	0x0001
 #define USB_PORT_STAT_C_ENABLE		0x0002
-- 
cgit v1.2.3


From d8692748408fbec28dfb065f4127307e24187476 Mon Sep 17 00:00:00 2001
From: Hema HK <hemahk@ti.com>
Date: Thu, 17 Feb 2011 12:06:06 +0530
Subject: usb: otg: OMAP4430: Add phy_suspend function pointer to
 twl4030_usb_data

Declare the .phy_suspend function pointer to twl4030_usb_data structure.
OMAP internal phy suspend function will be hooked though this function
pointer to use in the transceiver driver.

Signed-off-by: Hema HK <hemahk@ti.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Paul Walmsley <paul@pwsan.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/i2c/twl.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index 61b9609e55f2..a4bd05b7bd22 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -600,6 +600,8 @@ struct twl4030_usb_data {
 	int		(*phy_power)(struct device *dev, int iD, int on);
 	/* enable/disable  phy clocks */
 	int		(*phy_set_clock)(struct device *dev, int on);
+	/* suspend/resume of phy */
+	int		(*phy_suspend)(struct device *dev, int suspend);
 };
 
 struct twl4030_ins {
-- 
cgit v1.2.3


From 9fc3de9c83565fcaa23df74c2fc414bb6e7efb0a Mon Sep 17 00:00:00 2001
From: Arthur Taylor <art@ified.ca>
Date: Fri, 4 Feb 2011 13:55:50 -0800
Subject: vt: Add virtual console keyboard mode OFF

virtual console: add keyboard mode OFF

Add a new mode for the virtual console keyboard OFF in which all input
other than shift keys is ignored. Prevents vt input buffers from
overflowing when a program opens but doesn't read from a tty, like X11
using evdev for input.

Signed-off-by: Arthur Taylor <art@ified.ca>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/tty/vt/keyboard.c | 5 +++--
 drivers/tty/vt/vt_ioctl.c | 3 +++
 include/linux/kbd_kern.h  | 3 ++-
 include/linux/kd.h        | 1 +
 4 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index e95d7876ca6b..6dd3c68c13ad 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -654,7 +654,8 @@ static void k_spec(struct vc_data *vc, unsigned char value, char up_flag)
 	if (value >= ARRAY_SIZE(fn_handler))
 		return;
 	if ((kbd->kbdmode == VC_RAW ||
-	     kbd->kbdmode == VC_MEDIUMRAW) &&
+	     kbd->kbdmode == VC_MEDIUMRAW ||
+	     kbd->kbdmode == VC_OFF) &&
 	     value != KVAL(K_SAK))
 		return;		/* SAK is allowed even in raw mode */
 	fn_handler[value](vc);
@@ -1295,7 +1296,7 @@ static void kbd_keycode(unsigned int keycode, int down, int hw_raw)
 	if (rc == NOTIFY_STOP)
 		return;
 
-	if (raw_mode && type != KT_SPEC && type != KT_SHIFT)
+	if ((raw_mode || kbd->kbdmode == VC_OFF) && type != KT_SPEC && type != KT_SHIFT)
 		return;
 
 	(*k_handler[type])(vc, keysym & 0xff, !down);
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 1235ebda6e1c..6bcf05bf4978 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -688,6 +688,9 @@ int vt_ioctl(struct tty_struct *tty, struct file * file,
 			kbd->kbdmode = VC_UNICODE;
 			compute_shiftstate();
 			break;
+		  case K_OFF:
+			kbd->kbdmode = VC_OFF;
+			break;
 		  default:
 			ret = -EINVAL;
 			goto out;
diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h
index 506ad20c18f8..4b0761cc7dd9 100644
--- a/include/linux/kbd_kern.h
+++ b/include/linux/kbd_kern.h
@@ -50,11 +50,12 @@ struct kbd_struct {
 #define VC_CAPSLOCK	2	/* capslock mode */
 #define VC_KANALOCK	3	/* kanalock mode */
 
-	unsigned char kbdmode:2;	/* one 2-bit value */
+	unsigned char kbdmode:3;	/* one 3-bit value */
 #define VC_XLATE	0	/* translate keycodes using keymap */
 #define VC_MEDIUMRAW	1	/* medium raw (keycode) mode */
 #define VC_RAW		2	/* raw (scancode) mode */
 #define VC_UNICODE	3	/* Unicode mode */
+#define VC_OFF		4	/* disabled mode */
 
 	unsigned char modeflags:5;
 #define VC_APPLIC	0	/* application key mode */
diff --git a/include/linux/kd.h b/include/linux/kd.h
index 15f2853ea58f..c36d8476db55 100644
--- a/include/linux/kd.h
+++ b/include/linux/kd.h
@@ -81,6 +81,7 @@ struct unimapinit {
 #define		K_XLATE		0x01
 #define		K_MEDIUMRAW	0x02
 #define		K_UNICODE	0x03
+#define		K_OFF		0x04
 #define KDGKBMODE	0x4B44	/* gets current keyboard mode */
 #define KDSKBMODE	0x4B45	/* sets current keyboard mode */
 
-- 
cgit v1.2.3


From fcdba07ee390d9d9c15de8b2a17baef689284fcc Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Mon, 7 Feb 2011 19:31:25 +0100
Subject: tty,vcs removing con_buf/conf_buf_mtx

seems there's no longer need for using con_buf/conf_buf_mtx
as vcs_read/vcs_write buffer for user's data.

The do_con_write function, that was the other user of this,
is currently using its own kmalloc-ed buffer.

Not sure when this got changed, as I was able to find this code
in 2.6.9, but it's already gone as far as current git history
goes - 2.6.12-rc2.

AFAICS there's a behaviour change with the current change.
The lseek is not completely mutually exclusive with the
vcs_read/vcs_write - the file->f_pos might get updated
via lseek callback during the vcs_read/vcs_write processing.

I tried to find out if the prefered behaviour is to keep
this in sync within read/write/lseek functions, but I did
not find any pattern on different places.

I guess if user end up calling write/lseek from different
threads she should know what she's doing. If needed we
could use dedicated fd mutex/buffer.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/tty/vt/vc_screen.c | 98 ++++++++++++++++++++++++----------------------
 drivers/tty/vt/vt.c        | 12 ------
 include/linux/vt_kern.h    |  8 ----
 3 files changed, 52 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c
index 3c27c4bc6040..7b3bfbe2e6de 100644
--- a/drivers/tty/vt/vc_screen.c
+++ b/drivers/tty/vt/vc_screen.c
@@ -28,7 +28,6 @@
 #include <linux/interrupt.h>
 #include <linux/mm.h>
 #include <linux/init.h>
-#include <linux/mutex.h>
 #include <linux/vt_kern.h>
 #include <linux/selection.h>
 #include <linux/kbd_kern.h>
@@ -51,6 +50,8 @@
 #undef addr
 #define HEADER_SIZE	4
 
+#define CON_BUF_SIZE (CONFIG_BASE_SMALL ? 256 : PAGE_SIZE)
+
 struct vcs_poll_data {
 	struct notifier_block notifier;
 	unsigned int cons_num;
@@ -131,21 +132,45 @@ vcs_poll_data_get(struct file *file)
 	return poll;
 }
 
+/*
+ * Returns VC for inode.
+ * Must be called with console_lock.
+ */
+static struct vc_data*
+vcs_vc(struct inode *inode, int *viewed)
+{
+	unsigned int currcons = iminor(inode) & 127;
+
+	WARN_CONSOLE_UNLOCKED();
+
+	if (currcons == 0) {
+		currcons = fg_console;
+		if (viewed)
+			*viewed = 1;
+	} else {
+		currcons--;
+		if (viewed)
+			*viewed = 0;
+	}
+	return vc_cons[currcons].d;
+}
+
+/*
+ * Returns size for VC carried by inode.
+ * Must be called with console_lock.
+ */
 static int
 vcs_size(struct inode *inode)
 {
 	int size;
 	int minor = iminor(inode);
-	int currcons = minor & 127;
 	struct vc_data *vc;
 
-	if (currcons == 0)
-		currcons = fg_console;
-	else
-		currcons--;
-	if (!vc_cons_allocated(currcons))
+	WARN_CONSOLE_UNLOCKED();
+
+	vc = vcs_vc(inode, NULL);
+	if (!vc)
 		return -ENXIO;
-	vc = vc_cons[currcons].d;
 
 	size = vc->vc_rows * vc->vc_cols;
 
@@ -158,17 +183,13 @@ static loff_t vcs_lseek(struct file *file, loff_t offset, int orig)
 {
 	int size;
 
-	mutex_lock(&con_buf_mtx);
 	console_lock();
 	size = vcs_size(file->f_path.dentry->d_inode);
 	console_unlock();
-	if (size < 0) {
-		mutex_unlock(&con_buf_mtx);
+	if (size < 0)
 		return size;
-	}
 	switch (orig) {
 		default:
-			mutex_unlock(&con_buf_mtx);
 			return -EINVAL;
 		case 2:
 			offset += size;
@@ -179,11 +200,9 @@ static loff_t vcs_lseek(struct file *file, loff_t offset, int orig)
 			break;
 	}
 	if (offset < 0 || offset > size) {
-		mutex_unlock(&con_buf_mtx);
 		return -EINVAL;
 	}
 	file->f_pos = offset;
-	mutex_unlock(&con_buf_mtx);
 	return file->f_pos;
 }
 
@@ -196,12 +215,15 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	struct vc_data *vc;
 	struct vcs_poll_data *poll;
 	long pos;
-	long viewed, attr, read;
-	int col, maxcol;
+	long attr, read;
+	int col, maxcol, viewed;
 	unsigned short *org = NULL;
 	ssize_t ret;
+	char *con_buf;
 
-	mutex_lock(&con_buf_mtx);
+	con_buf = (char *) __get_free_page(GFP_KERNEL);
+	if (!con_buf)
+		return -ENOMEM;
 
 	pos = *ppos;
 
@@ -211,18 +233,10 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	console_lock();
 
 	attr = (currcons & 128);
-	currcons = (currcons & 127);
-	if (currcons == 0) {
-		currcons = fg_console;
-		viewed = 1;
-	} else {
-		currcons--;
-		viewed = 0;
-	}
 	ret = -ENXIO;
-	if (!vc_cons_allocated(currcons))
+	vc = vcs_vc(inode, &viewed);
+	if (!vc)
 		goto unlock_out;
-	vc = vc_cons[currcons].d;
 
 	ret = -EINVAL;
 	if (pos < 0)
@@ -367,7 +381,7 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		ret = read;
 unlock_out:
 	console_unlock();
-	mutex_unlock(&con_buf_mtx);
+	free_page((unsigned long) con_buf);
 	return ret;
 }
 
@@ -378,13 +392,16 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	unsigned int currcons = iminor(inode);
 	struct vc_data *vc;
 	long pos;
-	long viewed, attr, size, written;
+	long attr, size, written;
 	char *con_buf0;
-	int col, maxcol;
+	int col, maxcol, viewed;
 	u16 *org0 = NULL, *org = NULL;
 	size_t ret;
+	char *con_buf;
 
-	mutex_lock(&con_buf_mtx);
+	con_buf = (char *) __get_free_page(GFP_KERNEL);
+	if (!con_buf)
+		return -ENOMEM;
 
 	pos = *ppos;
 
@@ -394,19 +411,10 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 	console_lock();
 
 	attr = (currcons & 128);
-	currcons = (currcons & 127);
-
-	if (currcons == 0) {
-		currcons = fg_console;
-		viewed = 1;
-	} else {
-		currcons--;
-		viewed = 0;
-	}
 	ret = -ENXIO;
-	if (!vc_cons_allocated(currcons))
+	vc = vcs_vc(inode, &viewed);
+	if (!vc)
 		goto unlock_out;
-	vc = vc_cons[currcons].d;
 
 	size = vcs_size(inode);
 	ret = -EINVAL;
@@ -561,9 +569,7 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 
 unlock_out:
 	console_unlock();
-
-	mutex_unlock(&con_buf_mtx);
-
+	free_page((unsigned long) con_buf);
 	return ret;
 }
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index d5669ff72df4..798df6f89110 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -2068,18 +2068,6 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c)
 	}
 }
 
-/* This is a temporary buffer used to prepare a tty console write
- * so that we can easily avoid touching user space while holding the
- * console spinlock.  It is allocated in con_init and is shared by
- * this code and the vc_screen read/write tty calls.
- *
- * We have to allocate this statically in the kernel data section
- * since console_init (and thus con_init) are called before any
- * kernel memory allocation is available.
- */
-char con_buf[CON_BUF_SIZE];
-DEFINE_MUTEX(con_buf_mtx);
-
 /* is_double_width() is based on the wcwidth() implementation by
  * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
  * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h
index 6625cc1ab758..4d05e14ea60c 100644
--- a/include/linux/vt_kern.h
+++ b/include/linux/vt_kern.h
@@ -142,14 +142,6 @@ static inline bool vt_force_oops_output(struct vc_data *vc)
 	return false;
 }
 
-/*
- * vc_screen.c shares this temporary buffer with the console write code so that
- * we can easily avoid touching user space while holding the console spinlock.
- */
-
-#define CON_BUF_SIZE (CONFIG_BASE_SMALL ? 256 : PAGE_SIZE)
-extern char con_buf[CON_BUF_SIZE];
-extern struct mutex con_buf_mtx;
 extern char vt_dont_switch;
 extern int default_utf8;
 extern int global_cursor_default;
-- 
cgit v1.2.3


From 60b33c133ca0b7c0b6072c87234b63fee6e80558 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@linux.intel.com>
Date: Mon, 14 Feb 2011 16:26:14 +0000
Subject: tiocmget: kill off the passing of the struct file

We don't actually need this and it causes problems for internal use of
this functionality. Currently there is a single use of the FILE * pointer.
That is the serial core which uses it to check tty_hung_up_p. However if
that is true then IO_ERROR is also already set so the check may be removed.

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/char/amiserial.c                    | 2 +-
 drivers/char/cyclades.c                     | 2 +-
 drivers/char/epca.c                         | 4 ++--
 drivers/char/ip2/ip2main.c                  | 4 ++--
 drivers/char/isicom.c                       | 2 +-
 drivers/char/istallion.c                    | 2 +-
 drivers/char/moxa.c                         | 4 ++--
 drivers/char/mxser.c                        | 2 +-
 drivers/char/nozomi.c                       | 2 +-
 drivers/char/pcmcia/ipwireless/tty.c        | 2 +-
 drivers/char/pcmcia/synclink_cs.c           | 4 ++--
 drivers/char/riscom8.c                      | 2 +-
 drivers/char/rocket.c                       | 2 +-
 drivers/char/serial167.c                    | 2 +-
 drivers/char/specialix.c                    | 2 +-
 drivers/char/stallion.c                     | 2 +-
 drivers/char/sx.c                           | 2 +-
 drivers/char/synclink.c                     | 4 ++--
 drivers/char/synclink_gt.c                  | 4 ++--
 drivers/char/synclinkmp.c                   | 4 ++--
 drivers/isdn/gigaset/interface.c            | 4 ++--
 drivers/isdn/i4l/isdn_tty.c                 | 2 +-
 drivers/mmc/card/sdio_uart.c                | 2 +-
 drivers/net/usb/hso.c                       | 2 +-
 drivers/net/wan/pc300_tty.c                 | 4 ++--
 drivers/staging/quatech_usb2/quatech_usb2.c | 2 +-
 drivers/staging/serqt_usb2/serqt_usb2.c     | 6 +++---
 drivers/tty/hvc/hvsi.c                      | 2 +-
 drivers/tty/n_gsm.c                         | 2 +-
 drivers/tty/serial/68360serial.c            | 2 +-
 drivers/tty/serial/crisv10.c                | 2 +-
 drivers/tty/serial/ifx6x60.c                | 2 +-
 drivers/tty/serial/serial_core.c            | 6 ++----
 drivers/tty/tty_io.c                        | 6 +++---
 drivers/usb/class/cdc-acm.c                 | 2 +-
 drivers/usb/serial/ark3116.c                | 2 +-
 drivers/usb/serial/belkin_sa.c              | 4 ++--
 drivers/usb/serial/ch341.c                  | 2 +-
 drivers/usb/serial/cp210x.c                 | 4 ++--
 drivers/usb/serial/cypress_m8.c             | 4 ++--
 drivers/usb/serial/digi_acceleport.c        | 4 ++--
 drivers/usb/serial/ftdi_sio.c               | 4 ++--
 drivers/usb/serial/io_edgeport.c            | 4 ++--
 drivers/usb/serial/io_ti.c                  | 2 +-
 drivers/usb/serial/iuu_phoenix.c            | 2 +-
 drivers/usb/serial/keyspan.c                | 2 +-
 drivers/usb/serial/keyspan.h                | 3 +--
 drivers/usb/serial/keyspan_pda.c            | 2 +-
 drivers/usb/serial/kl5kusb105.c             | 4 ++--
 drivers/usb/serial/kobil_sct.c              | 4 ++--
 drivers/usb/serial/mct_u232.c               | 4 ++--
 drivers/usb/serial/mos7720.c                | 4 ++--
 drivers/usb/serial/mos7840.c                | 2 +-
 drivers/usb/serial/opticon.c                | 2 +-
 drivers/usb/serial/oti6858.c                | 4 ++--
 drivers/usb/serial/pl2303.c                 | 2 +-
 drivers/usb/serial/sierra.c                 | 2 +-
 drivers/usb/serial/spcp8x5.c                | 2 +-
 drivers/usb/serial/ssu100.c                 | 2 +-
 drivers/usb/serial/ti_usb_3410_5052.c       | 4 ++--
 drivers/usb/serial/usb-serial.c             | 4 ++--
 drivers/usb/serial/usb-wwan.h               | 2 +-
 drivers/usb/serial/usb_wwan.c               | 2 +-
 drivers/usb/serial/whiteheat.c              | 4 ++--
 include/linux/tty_driver.h                  | 2 +-
 include/linux/usb/serial.h                  | 2 +-
 include/net/irda/ircomm_tty.h               | 2 +-
 net/bluetooth/rfcomm/tty.c                  | 2 +-
 net/irda/ircomm/ircomm_tty_ioctl.c          | 4 ++--
 69 files changed, 98 insertions(+), 101 deletions(-)

(limited to 'include')

diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c
index 6ee3348bc3e4..bc67e6839059 100644
--- a/drivers/char/amiserial.c
+++ b/drivers/char/amiserial.c
@@ -1194,7 +1194,7 @@ static int get_lsr_info(struct async_struct * info, unsigned int __user *value)
 }
 
 
-static int rs_tiocmget(struct tty_struct *tty, struct file *file)
+static int rs_tiocmget(struct tty_struct *tty)
 {
 	struct async_struct * info = tty->driver_data;
 	unsigned char control, status;
diff --git a/drivers/char/cyclades.c b/drivers/char/cyclades.c
index 4f152c28f40e..e7945ddacd18 100644
--- a/drivers/char/cyclades.c
+++ b/drivers/char/cyclades.c
@@ -2429,7 +2429,7 @@ static int get_lsr_info(struct cyclades_port *info, unsigned int __user *value)
 	return put_user(result, (unsigned long __user *)value);
 }
 
-static int cy_tiocmget(struct tty_struct *tty, struct file *file)
+static int cy_tiocmget(struct tty_struct *tty)
 {
 	struct cyclades_port *info = tty->driver_data;
 	struct cyclades_card *card;
diff --git a/drivers/char/epca.c b/drivers/char/epca.c
index d9df46aa0fba..ecf6f0a889fc 100644
--- a/drivers/char/epca.c
+++ b/drivers/char/epca.c
@@ -1982,7 +1982,7 @@ static int info_ioctl(struct tty_struct *tty, struct file *file,
 	return 0;
 }
 
-static int pc_tiocmget(struct tty_struct *tty, struct file *file)
+static int pc_tiocmget(struct tty_struct *tty)
 {
 	struct channel *ch = tty->driver_data;
 	struct board_chan __iomem *bc;
@@ -2074,7 +2074,7 @@ static int pc_ioctl(struct tty_struct *tty, struct file *file,
 		return -EINVAL;
 	switch (cmd) {
 	case TIOCMODG:
-		mflag = pc_tiocmget(tty, file);
+		mflag = pc_tiocmget(tty);
 		if (put_user(mflag, (unsigned long __user *)argp))
 			return -EFAULT;
 		break;
diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c
index c3a025356b8b..476cd087118e 100644
--- a/drivers/char/ip2/ip2main.c
+++ b/drivers/char/ip2/ip2main.c
@@ -181,7 +181,7 @@ static void ip2_unthrottle(PTTY);
 static void ip2_stop(PTTY);
 static void ip2_start(PTTY);
 static void ip2_hangup(PTTY);
-static int  ip2_tiocmget(struct tty_struct *tty, struct file *file);
+static int  ip2_tiocmget(struct tty_struct *tty);
 static int  ip2_tiocmset(struct tty_struct *tty, struct file *file,
 			 unsigned int set, unsigned int clear);
 static int ip2_get_icount(struct tty_struct *tty,
@@ -2038,7 +2038,7 @@ ip2_stop ( PTTY tty )
 /* Device Ioctl Section                                                       */
 /******************************************************************************/
 
-static int ip2_tiocmget(struct tty_struct *tty, struct file *file)
+static int ip2_tiocmget(struct tty_struct *tty)
 {
 	i2ChanStrPtr pCh = DevTable[tty->index];
 #ifdef	ENABLE_DSSNOW
diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c
index c27e9d21fea9..836370bc04c2 100644
--- a/drivers/char/isicom.c
+++ b/drivers/char/isicom.c
@@ -1065,7 +1065,7 @@ static int isicom_send_break(struct tty_struct *tty, int length)
 	return 0;
 }
 
-static int isicom_tiocmget(struct tty_struct *tty, struct file *file)
+static int isicom_tiocmget(struct tty_struct *tty)
 {
 	struct isi_port *port = tty->driver_data;
 	/* just send the port status */
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index 7c6de4c92458..7843a847b76a 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -1501,7 +1501,7 @@ static int stli_setserial(struct tty_struct *tty, struct serial_struct __user *s
 
 /*****************************************************************************/
 
-static int stli_tiocmget(struct tty_struct *tty, struct file *file)
+static int stli_tiocmget(struct tty_struct *tty)
 {
 	struct stliport *portp = tty->driver_data;
 	struct stlibrd *brdp;
diff --git a/drivers/char/moxa.c b/drivers/char/moxa.c
index 107b0bd58d19..fdf069bb702f 100644
--- a/drivers/char/moxa.c
+++ b/drivers/char/moxa.c
@@ -199,7 +199,7 @@ static void moxa_set_termios(struct tty_struct *, struct ktermios *);
 static void moxa_stop(struct tty_struct *);
 static void moxa_start(struct tty_struct *);
 static void moxa_hangup(struct tty_struct *);
-static int moxa_tiocmget(struct tty_struct *tty, struct file *file);
+static int moxa_tiocmget(struct tty_struct *tty);
 static int moxa_tiocmset(struct tty_struct *tty, struct file *file,
 			 unsigned int set, unsigned int clear);
 static void moxa_poll(unsigned long);
@@ -1257,7 +1257,7 @@ static int moxa_chars_in_buffer(struct tty_struct *tty)
 	return chars;
 }
 
-static int moxa_tiocmget(struct tty_struct *tty, struct file *file)
+static int moxa_tiocmget(struct tty_struct *tty)
 {
 	struct moxa_port *ch = tty->driver_data;
 	int flag = 0, dtr, rts;
diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index dd9d75351cd6..4d2f03ec06cd 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -1320,7 +1320,7 @@ static int mxser_get_lsr_info(struct mxser_port *info,
 	return put_user(result, value);
 }
 
-static int mxser_tiocmget(struct tty_struct *tty, struct file *file)
+static int mxser_tiocmget(struct tty_struct *tty)
 {
 	struct mxser_port *info = tty->driver_data;
 	unsigned char control, status;
diff --git a/drivers/char/nozomi.c b/drivers/char/nozomi.c
index 294d03e8c61a..0e1dff2ffb1e 100644
--- a/drivers/char/nozomi.c
+++ b/drivers/char/nozomi.c
@@ -1750,7 +1750,7 @@ static int ntty_write_room(struct tty_struct *tty)
 }
 
 /* Gets io control parameters */
-static int ntty_tiocmget(struct tty_struct *tty, struct file *file)
+static int ntty_tiocmget(struct tty_struct *tty)
 {
 	const struct port *port = tty->driver_data;
 	const struct ctrl_dl *ctrl_dl = &port->ctrl_dl;
diff --git a/drivers/char/pcmcia/ipwireless/tty.c b/drivers/char/pcmcia/ipwireless/tty.c
index f5eb28b6cb0f..7d2ef4909a73 100644
--- a/drivers/char/pcmcia/ipwireless/tty.c
+++ b/drivers/char/pcmcia/ipwireless/tty.c
@@ -395,7 +395,7 @@ static int set_control_lines(struct ipw_tty *tty, unsigned int set,
 	return 0;
 }
 
-static int ipw_tiocmget(struct tty_struct *linux_tty, struct file *file)
+static int ipw_tiocmget(struct tty_struct *linux_tty)
 {
 	struct ipw_tty *tty = linux_tty->driver_data;
 	/* FIXME: Exactly how is the tty object locked here .. */
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index eaa41992fbe2..7b68ba6609fe 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -418,7 +418,7 @@ static void bh_status(MGSLPC_INFO *info);
 /*
  * ioctl handlers
  */
-static int tiocmget(struct tty_struct *tty, struct file *file);
+static int tiocmget(struct tty_struct *tty);
 static int tiocmset(struct tty_struct *tty, struct file *file,
 		    unsigned int set, unsigned int clear);
 static int get_stats(MGSLPC_INFO *info, struct mgsl_icount __user *user_icount);
@@ -2114,7 +2114,7 @@ static int modem_input_wait(MGSLPC_INFO *info,int arg)
 
 /* return the state of the serial control and status signals
  */
-static int tiocmget(struct tty_struct *tty, struct file *file)
+static int tiocmget(struct tty_struct *tty)
 {
 	MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data;
 	unsigned int result;
diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c
index af4de1fe8445..5d0c98456c93 100644
--- a/drivers/char/riscom8.c
+++ b/drivers/char/riscom8.c
@@ -1086,7 +1086,7 @@ static int rc_chars_in_buffer(struct tty_struct *tty)
 	return port->xmit_cnt;
 }
 
-static int rc_tiocmget(struct tty_struct *tty, struct file *file)
+static int rc_tiocmget(struct tty_struct *tty)
 {
 	struct riscom_port *port = tty->driver_data;
 	struct riscom_board *bp;
diff --git a/drivers/char/rocket.c b/drivers/char/rocket.c
index 3e4e73a0d7c1..75e98efbc8e9 100644
--- a/drivers/char/rocket.c
+++ b/drivers/char/rocket.c
@@ -1169,7 +1169,7 @@ static int sGetChanRI(CHANNEL_T * ChP)
  *  Returns the state of the serial modem control lines.  These next 2 functions 
  *  are the way kernel versions > 2.5 handle modem control lines rather than IOCTLs.
  */
-static int rp_tiocmget(struct tty_struct *tty, struct file *file)
+static int rp_tiocmget(struct tty_struct *tty)
 {
 	struct r_port *info = tty->driver_data;
 	unsigned int control, result, ChanStatus;
diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index 748c3b0ecd89..fda90643ead7 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -1308,7 +1308,7 @@ check_and_exit:
 	return startup(info);
 }				/* set_serial_info */
 
-static int cy_tiocmget(struct tty_struct *tty, struct file *file)
+static int cy_tiocmget(struct tty_struct *tty)
 {
 	struct cyclades_port *info = tty->driver_data;
 	int channel;
diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c
index c2bca3f25ef3..bfecfbef0895 100644
--- a/drivers/char/specialix.c
+++ b/drivers/char/specialix.c
@@ -1737,7 +1737,7 @@ static int sx_chars_in_buffer(struct tty_struct *tty)
 	return port->xmit_cnt;
 }
 
-static int sx_tiocmget(struct tty_struct *tty, struct file *file)
+static int sx_tiocmget(struct tty_struct *tty)
 {
 	struct specialix_port *port = tty->driver_data;
 	struct specialix_board *bp;
diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index 461a5a045517..8c2bf3fb5b89 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -1094,7 +1094,7 @@ static int stl_setserial(struct tty_struct *tty, struct serial_struct __user *sp
 
 /*****************************************************************************/
 
-static int stl_tiocmget(struct tty_struct *tty, struct file *file)
+static int stl_tiocmget(struct tty_struct *tty)
 {
 	struct stlport	*portp;
 
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index a786326cea2f..f46214e60d0c 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -1873,7 +1873,7 @@ static int sx_break(struct tty_struct *tty, int flag)
 	return 0;
 }
 
-static int sx_tiocmget(struct tty_struct *tty, struct file *file)
+static int sx_tiocmget(struct tty_struct *tty)
 {
 	struct sx_port *port = tty->driver_data;
 	return sx_getsignals(port);
diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c
index 3a6824f12be2..d359e092904a 100644
--- a/drivers/char/synclink.c
+++ b/drivers/char/synclink.c
@@ -823,7 +823,7 @@ static isr_dispatch_func UscIsrTable[7] =
 /*
  * ioctl call handlers
  */
-static int tiocmget(struct tty_struct *tty, struct file *file);
+static int tiocmget(struct tty_struct *tty);
 static int tiocmset(struct tty_struct *tty, struct file *file,
 		    unsigned int set, unsigned int clear);
 static int mgsl_get_stats(struct mgsl_struct * info, struct mgsl_icount
@@ -2846,7 +2846,7 @@ static int modem_input_wait(struct mgsl_struct *info,int arg)
 
 /* return the state of the serial control and status signals
  */
-static int tiocmget(struct tty_struct *tty, struct file *file)
+static int tiocmget(struct tty_struct *tty)
 {
 	struct mgsl_struct *info = tty->driver_data;
 	unsigned int result;
diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c
index d01fffeac951..f18ab8af0e1c 100644
--- a/drivers/char/synclink_gt.c
+++ b/drivers/char/synclink_gt.c
@@ -512,7 +512,7 @@ static int  tx_abort(struct slgt_info *info);
 static int  rx_enable(struct slgt_info *info, int enable);
 static int  modem_input_wait(struct slgt_info *info,int arg);
 static int  wait_mgsl_event(struct slgt_info *info, int __user *mask_ptr);
-static int  tiocmget(struct tty_struct *tty, struct file *file);
+static int  tiocmget(struct tty_struct *tty);
 static int  tiocmset(struct tty_struct *tty, struct file *file,
 		     unsigned int set, unsigned int clear);
 static int set_break(struct tty_struct *tty, int break_state);
@@ -3195,7 +3195,7 @@ static int modem_input_wait(struct slgt_info *info,int arg)
 /*
  *  return state of serial control and status signals
  */
-static int tiocmget(struct tty_struct *tty, struct file *file)
+static int tiocmget(struct tty_struct *tty)
 {
 	struct slgt_info *info = tty->driver_data;
 	unsigned int result;
diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c
index 2f9eb4b0dec1..5900213ae75b 100644
--- a/drivers/char/synclinkmp.c
+++ b/drivers/char/synclinkmp.c
@@ -546,7 +546,7 @@ static int  tx_abort(SLMP_INFO *info);
 static int  rx_enable(SLMP_INFO *info, int enable);
 static int  modem_input_wait(SLMP_INFO *info,int arg);
 static int  wait_mgsl_event(SLMP_INFO *info, int __user *mask_ptr);
-static int  tiocmget(struct tty_struct *tty, struct file *file);
+static int  tiocmget(struct tty_struct *tty);
 static int  tiocmset(struct tty_struct *tty, struct file *file,
 		     unsigned int set, unsigned int clear);
 static int  set_break(struct tty_struct *tty, int break_state);
@@ -3207,7 +3207,7 @@ static int modem_input_wait(SLMP_INFO *info,int arg)
 
 /* return the state of the serial control and status signals
  */
-static int tiocmget(struct tty_struct *tty, struct file *file)
+static int tiocmget(struct tty_struct *tty)
 {
 	SLMP_INFO *info = tty->driver_data;
 	unsigned int result;
diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c
index bb710d16a526..e1a7c14f5f1d 100644
--- a/drivers/isdn/gigaset/interface.c
+++ b/drivers/isdn/gigaset/interface.c
@@ -122,7 +122,7 @@ static int  if_chars_in_buffer(struct tty_struct *tty);
 static void if_throttle(struct tty_struct *tty);
 static void if_unthrottle(struct tty_struct *tty);
 static void if_set_termios(struct tty_struct *tty, struct ktermios *old);
-static int  if_tiocmget(struct tty_struct *tty, struct file *file);
+static int  if_tiocmget(struct tty_struct *tty);
 static int  if_tiocmset(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 static int  if_write(struct tty_struct *tty,
@@ -280,7 +280,7 @@ static int if_ioctl(struct tty_struct *tty, struct file *file,
 	return retval;
 }
 
-static int if_tiocmget(struct tty_struct *tty, struct file *file)
+static int if_tiocmget(struct tty_struct *tty)
 {
 	struct cardstate *cs;
 	int retval;
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index c463162843ba..ba6c2f124b58 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1345,7 +1345,7 @@ isdn_tty_get_lsr_info(modem_info * info, uint __user * value)
 
 
 static int
-isdn_tty_tiocmget(struct tty_struct *tty, struct file *file)
+isdn_tty_tiocmget(struct tty_struct *tty)
 {
 	modem_info *info = (modem_info *) tty->driver_data;
 	u_char control, status;
diff --git a/drivers/mmc/card/sdio_uart.c b/drivers/mmc/card/sdio_uart.c
index a0716967b7c8..86bb04d821b1 100644
--- a/drivers/mmc/card/sdio_uart.c
+++ b/drivers/mmc/card/sdio_uart.c
@@ -956,7 +956,7 @@ static int sdio_uart_break_ctl(struct tty_struct *tty, int break_state)
 	return 0;
 }
 
-static int sdio_uart_tiocmget(struct tty_struct *tty, struct file *file)
+static int sdio_uart_tiocmget(struct tty_struct *tty)
 {
 	struct sdio_uart_port *port = tty->driver_data;
 	int result;
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index bed8fcedff49..7c68c456c035 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1656,7 +1656,7 @@ static int hso_get_count(struct tty_struct *tty,
 }
 
 
-static int hso_serial_tiocmget(struct tty_struct *tty, struct file *file)
+static int hso_serial_tiocmget(struct tty_struct *tty)
 {
 	int retval;
 	struct hso_serial *serial = get_serial_by_tty(tty);
diff --git a/drivers/net/wan/pc300_tty.c b/drivers/net/wan/pc300_tty.c
index 515d9b8af01e..d999e54a7730 100644
--- a/drivers/net/wan/pc300_tty.c
+++ b/drivers/net/wan/pc300_tty.c
@@ -133,7 +133,7 @@ static void cpc_tty_signal_on(pc300dev_t *pc300dev, unsigned char);
 
 static int pc300_tiocmset(struct tty_struct *, struct file *,
 			  unsigned int, unsigned int);
-static int pc300_tiocmget(struct tty_struct *, struct file *);
+static int pc300_tiocmget(struct tty_struct *);
 
 /* functions called by PC300 driver */
 void cpc_tty_init(pc300dev_t *dev);
@@ -570,7 +570,7 @@ static int pc300_tiocmset(struct tty_struct *tty, struct file *file,
 	return 0;
 }
 
-static int pc300_tiocmget(struct tty_struct *tty, struct file *file)
+static int pc300_tiocmget(struct tty_struct *tty)
 {
 	unsigned int result;
 	unsigned char status;
diff --git a/drivers/staging/quatech_usb2/quatech_usb2.c b/drivers/staging/quatech_usb2/quatech_usb2.c
index ed58f482c963..1e50292aef74 100644
--- a/drivers/staging/quatech_usb2/quatech_usb2.c
+++ b/drivers/staging/quatech_usb2/quatech_usb2.c
@@ -1078,7 +1078,7 @@ static void qt2_set_termios(struct tty_struct *tty,
 	}
 }
 
-static int qt2_tiocmget(struct tty_struct *tty, struct file *file)
+static int qt2_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct usb_serial *serial = port->serial;
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index 27841ef6a568..56ded56db7b4 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -1383,7 +1383,7 @@ static void qt_break(struct tty_struct *tty, int break_state)
 
 static inline int qt_real_tiocmget(struct tty_struct *tty,
 				   struct usb_serial_port *port,
-				   struct file *file, struct usb_serial *serial)
+				   struct usb_serial *serial)
 {
 
 	u8 mcr;
@@ -1462,7 +1462,7 @@ static inline int qt_real_tiocmset(struct tty_struct *tty,
 		return 0;
 }
 
-static int qt_tiocmget(struct tty_struct *tty, struct file *file)
+static int qt_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct usb_serial *serial = get_usb_serial(port, __func__);
@@ -1480,7 +1480,7 @@ static int qt_tiocmget(struct tty_struct *tty, struct file *file)
 	dbg("%s - port %d\n", __func__, port->number);
 	dbg("%s - port->RxHolding = %d\n", __func__, qt_port->RxHolding);
 
-	retval = qt_real_tiocmget(tty, port, file, serial);
+	retval = qt_real_tiocmget(tty, port, serial);
 
 	spin_unlock_irqrestore(&qt_port->lock, flags);
 	return retval;
diff --git a/drivers/tty/hvc/hvsi.c b/drivers/tty/hvc/hvsi.c
index 67a75a502c01..55293105a56c 100644
--- a/drivers/tty/hvc/hvsi.c
+++ b/drivers/tty/hvc/hvsi.c
@@ -1095,7 +1095,7 @@ static void hvsi_unthrottle(struct tty_struct *tty)
 	h_vio_signal(hp->vtermno, VIO_IRQ_ENABLE);
 }
 
-static int hvsi_tiocmget(struct tty_struct *tty, struct file *file)
+static int hvsi_tiocmget(struct tty_struct *tty)
 {
 	struct hvsi_struct *hp = tty->driver_data;
 
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 44b8412a04e8..97e3d509ff82 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2648,7 +2648,7 @@ static void gsmtty_wait_until_sent(struct tty_struct *tty, int timeout)
 	   to do here */
 }
 
-static int gsmtty_tiocmget(struct tty_struct *tty, struct file *filp)
+static int gsmtty_tiocmget(struct tty_struct *tty)
 {
 	struct gsm_dlci *dlci = tty->driver_data;
 	return dlci->modem_rx;
diff --git a/drivers/tty/serial/68360serial.c b/drivers/tty/serial/68360serial.c
index 88b13356ec10..2a52cf14ce50 100644
--- a/drivers/tty/serial/68360serial.c
+++ b/drivers/tty/serial/68360serial.c
@@ -1240,7 +1240,7 @@ static int get_lsr_info(struct async_struct * info, unsigned int *value)
 }
 #endif
 
-static int rs_360_tiocmget(struct tty_struct *tty, struct file *file)
+static int rs_360_tiocmget(struct tty_struct *tty)
 {
 	ser_info_t *info = (ser_info_t *)tty->driver_data;
 	unsigned int result = 0;
diff --git a/drivers/tty/serial/crisv10.c b/drivers/tty/serial/crisv10.c
index bcc31f2140ac..8cc5c0224b25 100644
--- a/drivers/tty/serial/crisv10.c
+++ b/drivers/tty/serial/crisv10.c
@@ -3614,7 +3614,7 @@ rs_tiocmset(struct tty_struct *tty, struct file *file,
 }
 
 static int
-rs_tiocmget(struct tty_struct *tty, struct file *file)
+rs_tiocmget(struct tty_struct *tty)
 {
 	struct e100_serial *info = (struct e100_serial *)tty->driver_data;
 	unsigned int result;
diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c
index b68b96f53e6c..4d26d39ec344 100644
--- a/drivers/tty/serial/ifx6x60.c
+++ b/drivers/tty/serial/ifx6x60.c
@@ -245,7 +245,7 @@ static void ifx_spi_timeout(unsigned long arg)
  *	Map the signal state into Linux modem flags and report the value
  *	in Linux terms
  */
-static int ifx_spi_tiocmget(struct tty_struct *tty, struct file *filp)
+static int ifx_spi_tiocmget(struct tty_struct *tty)
 {
 	unsigned int value;
 	struct ifx_spi_device *ifx_dev = tty->driver_data;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 20563c509b21..53e490e47560 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -905,7 +905,7 @@ static int uart_get_lsr_info(struct tty_struct *tty,
 	return put_user(result, value);
 }
 
-static int uart_tiocmget(struct tty_struct *tty, struct file *file)
+static int uart_tiocmget(struct tty_struct *tty)
 {
 	struct uart_state *state = tty->driver_data;
 	struct tty_port *port = &state->port;
@@ -913,10 +913,8 @@ static int uart_tiocmget(struct tty_struct *tty, struct file *file)
 	int result = -EIO;
 
 	mutex_lock(&port->mutex);
-	if ((!file || !tty_hung_up_p(file)) &&
-	    !(tty->flags & (1 << TTY_IO_ERROR))) {
+	if (!(tty->flags & (1 << TTY_IO_ERROR))) {
 		result = uport->mctrl;
-
 		spin_lock_irq(&uport->lock);
 		result |= uport->ops->get_mctrl(uport);
 		spin_unlock_irq(&uport->lock);
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 0065da4b11c1..fde5a4dae3dd 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2465,12 +2465,12 @@ out:
  *	Locking: none (up to the driver)
  */
 
-static int tty_tiocmget(struct tty_struct *tty, struct file *file, int __user *p)
+static int tty_tiocmget(struct tty_struct *tty, int __user *p)
 {
 	int retval = -EINVAL;
 
 	if (tty->ops->tiocmget) {
-		retval = tty->ops->tiocmget(tty, file);
+		retval = tty->ops->tiocmget(tty);
 
 		if (retval >= 0)
 			retval = put_user(retval, p);
@@ -2655,7 +2655,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return send_break(tty, arg ? arg*100 : 250);
 
 	case TIOCMGET:
-		return tty_tiocmget(tty, file, p);
+		return tty_tiocmget(tty, p);
 	case TIOCMSET:
 	case TIOCMBIC:
 	case TIOCMBIS:
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index d6ede989ff22..2ae996b7ce7b 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -776,7 +776,7 @@ static int acm_tty_break_ctl(struct tty_struct *tty, int state)
 	return retval;
 }
 
-static int acm_tty_tiocmget(struct tty_struct *tty, struct file *file)
+static int acm_tty_tiocmget(struct tty_struct *tty)
 {
 	struct acm *acm = tty->driver_data;
 
diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c
index 8f1d4fb19d24..35b610aa3f92 100644
--- a/drivers/usb/serial/ark3116.c
+++ b/drivers/usb/serial/ark3116.c
@@ -485,7 +485,7 @@ static int ark3116_ioctl(struct tty_struct *tty, struct file *file,
 	return -ENOIOCTLCMD;
 }
 
-static int ark3116_tiocmget(struct tty_struct *tty, struct file *file)
+static int ark3116_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct ark3116_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/belkin_sa.c b/drivers/usb/serial/belkin_sa.c
index 36df35295db2..48fb3bad3cd6 100644
--- a/drivers/usb/serial/belkin_sa.c
+++ b/drivers/usb/serial/belkin_sa.c
@@ -100,7 +100,7 @@ static void belkin_sa_process_read_urb(struct urb *urb);
 static void belkin_sa_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios * old);
 static void belkin_sa_break_ctl(struct tty_struct *tty, int break_state);
-static int  belkin_sa_tiocmget(struct tty_struct *tty, struct file *file);
+static int  belkin_sa_tiocmget(struct tty_struct *tty);
 static int  belkin_sa_tiocmset(struct tty_struct *tty, struct file *file,
 					unsigned int set, unsigned int clear);
 
@@ -497,7 +497,7 @@ static void belkin_sa_break_ctl(struct tty_struct *tty, int break_state)
 		dev_err(&port->dev, "Set break_ctl %d\n", break_state);
 }
 
-static int belkin_sa_tiocmget(struct tty_struct *tty, struct file *file)
+static int belkin_sa_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct belkin_sa_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 7b8815ddf368..aa0962b72f4c 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -572,7 +572,7 @@ static int ch341_ioctl(struct tty_struct *tty, struct file *file,
 	return -ENOIOCTLCMD;
 }
 
-static int ch341_tiocmget(struct tty_struct *tty, struct file *file)
+static int ch341_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct ch341_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 735ea03157ab..b3873815035c 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -41,7 +41,7 @@ static void cp210x_get_termios_port(struct usb_serial_port *port,
 	unsigned int *cflagp, unsigned int *baudp);
 static void cp210x_set_termios(struct tty_struct *, struct usb_serial_port *,
 							struct ktermios*);
-static int cp210x_tiocmget(struct tty_struct *, struct file *);
+static int cp210x_tiocmget(struct tty_struct *);
 static int cp210x_tiocmset(struct tty_struct *, struct file *,
 		unsigned int, unsigned int);
 static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *,
@@ -742,7 +742,7 @@ static void cp210x_dtr_rts(struct usb_serial_port *p, int on)
 		cp210x_tiocmset_port(p, NULL,  0, TIOCM_DTR|TIOCM_RTS);
 }
 
-static int cp210x_tiocmget (struct tty_struct *tty, struct file *file)
+static int cp210x_tiocmget (struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	unsigned int control;
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index 2edf238b00b9..9c96cff691fd 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -173,7 +173,7 @@ static int  cypress_ioctl(struct tty_struct *tty, struct file *file,
 			unsigned int cmd, unsigned long arg);
 static void cypress_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
-static int  cypress_tiocmget(struct tty_struct *tty, struct file *file);
+static int  cypress_tiocmget(struct tty_struct *tty);
 static int  cypress_tiocmset(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 static int  cypress_chars_in_buffer(struct tty_struct *tty);
@@ -864,7 +864,7 @@ static int cypress_write_room(struct tty_struct *tty)
 }
 
 
-static int cypress_tiocmget(struct tty_struct *tty, struct file *file)
+static int cypress_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct cypress_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index 666e5a6edd82..08da46cb5825 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -445,7 +445,7 @@ static void digi_rx_unthrottle(struct tty_struct *tty);
 static void digi_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios);
 static void digi_break_ctl(struct tty_struct *tty, int break_state);
-static int digi_tiocmget(struct tty_struct *tty, struct file *file);
+static int digi_tiocmget(struct tty_struct *tty);
 static int digi_tiocmset(struct tty_struct *tty, struct file *file,
 	unsigned int set, unsigned int clear);
 static int digi_write(struct tty_struct *tty, struct usb_serial_port *port,
@@ -1118,7 +1118,7 @@ static void digi_break_ctl(struct tty_struct *tty, int break_state)
 }
 
 
-static int digi_tiocmget(struct tty_struct *tty, struct file *file)
+static int digi_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct digi_port *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 4787c0cd063f..281d18141051 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -856,7 +856,7 @@ static int ftdi_prepare_write_buffer(struct usb_serial_port *port,
 						void *dest, size_t size);
 static void ftdi_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
-static int  ftdi_tiocmget(struct tty_struct *tty, struct file *file);
+static int  ftdi_tiocmget(struct tty_struct *tty);
 static int  ftdi_tiocmset(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 static int  ftdi_ioctl(struct tty_struct *tty, struct file *file,
@@ -2149,7 +2149,7 @@ static void ftdi_set_termios(struct tty_struct *tty,
 	}
 }
 
-static int ftdi_tiocmget(struct tty_struct *tty, struct file *file)
+static int ftdi_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index cd769ef24f8a..e8fe4dcf72f0 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -219,7 +219,7 @@ static void edge_set_termios(struct tty_struct *tty,
 static int  edge_ioctl(struct tty_struct *tty, struct file *file,
 					unsigned int cmd, unsigned long arg);
 static void edge_break(struct tty_struct *tty, int break_state);
-static int  edge_tiocmget(struct tty_struct *tty, struct file *file);
+static int  edge_tiocmget(struct tty_struct *tty);
 static int  edge_tiocmset(struct tty_struct *tty, struct file *file,
 					unsigned int set, unsigned int clear);
 static int  edge_get_icount(struct tty_struct *tty,
@@ -1599,7 +1599,7 @@ static int edge_tiocmset(struct tty_struct *tty, struct file *file,
 	return 0;
 }
 
-static int edge_tiocmget(struct tty_struct *tty, struct file *file)
+static int edge_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct edgeport_port *edge_port = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 22506b095c4f..7cb9f5cb91f3 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -2477,7 +2477,7 @@ static int edge_tiocmset(struct tty_struct *tty, struct file *file,
 	return 0;
 }
 
-static int edge_tiocmget(struct tty_struct *tty, struct file *file)
+static int edge_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct edgeport_port *edge_port = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index 99b97c04896f..1d96142f135a 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -179,7 +179,7 @@ static int iuu_tiocmset(struct tty_struct *tty, struct file *file,
  * When no card , the reader respond with TIOCM_CD
  * This is known as CD autodetect mechanism
  */
-static int iuu_tiocmget(struct tty_struct *tty, struct file *file)
+static int iuu_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct iuu_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 0791778a66f3..1beebbb7a20a 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -301,7 +301,7 @@ static void keyspan_set_termios(struct tty_struct *tty,
 	keyspan_send_setup(port, 0);
 }
 
-static int keyspan_tiocmget(struct tty_struct *tty, struct file *file)
+static int keyspan_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct keyspan_port_private *p_priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/keyspan.h b/drivers/usb/serial/keyspan.h
index ce134dc28ddf..5e5fc71e68df 100644
--- a/drivers/usb/serial/keyspan.h
+++ b/drivers/usb/serial/keyspan.h
@@ -58,8 +58,7 @@ static void keyspan_set_termios		(struct tty_struct *tty,
 					 struct ktermios *old);
 static void keyspan_break_ctl		(struct tty_struct *tty,
 					 int break_state);
-static int  keyspan_tiocmget		(struct tty_struct *tty,
-					 struct file *file);
+static int  keyspan_tiocmget		(struct tty_struct *tty);
 static int  keyspan_tiocmset		(struct tty_struct *tty,
 					 struct file *file, unsigned int set,
 					 unsigned int clear);
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index 554a8693a463..49ad2baf77cd 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -457,7 +457,7 @@ static int keyspan_pda_set_modem_info(struct usb_serial *serial,
 	return rc;
 }
 
-static int keyspan_pda_tiocmget(struct tty_struct *tty, struct file *file)
+static int keyspan_pda_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct usb_serial *serial = port->serial;
diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c
index e8a65ce45a2f..a570f5201c73 100644
--- a/drivers/usb/serial/kl5kusb105.c
+++ b/drivers/usb/serial/kl5kusb105.c
@@ -68,7 +68,7 @@ static int  klsi_105_open(struct tty_struct *tty, struct usb_serial_port *port);
 static void klsi_105_close(struct usb_serial_port *port);
 static void klsi_105_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
-static int  klsi_105_tiocmget(struct tty_struct *tty, struct file *file);
+static int  klsi_105_tiocmget(struct tty_struct *tty);
 static int  klsi_105_tiocmset(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 static void klsi_105_process_read_urb(struct urb *urb);
@@ -637,7 +637,7 @@ static void mct_u232_break_ctl(struct tty_struct *tty, int break_state)
 }
 #endif
 
-static int klsi_105_tiocmget(struct tty_struct *tty, struct file *file)
+static int klsi_105_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct klsi_105_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index bd5bd8589e04..81d07fb299b8 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -77,7 +77,7 @@ static int  kobil_write(struct tty_struct *tty, struct usb_serial_port *port,
 static int  kobil_write_room(struct tty_struct *tty);
 static int  kobil_ioctl(struct tty_struct *tty, struct file *file,
 			unsigned int cmd, unsigned long arg);
-static int  kobil_tiocmget(struct tty_struct *tty, struct file *file);
+static int  kobil_tiocmget(struct tty_struct *tty);
 static int  kobil_tiocmset(struct tty_struct *tty, struct file *file,
 			   unsigned int set, unsigned int clear);
 static void kobil_read_int_callback(struct urb *urb);
@@ -504,7 +504,7 @@ static int kobil_write_room(struct tty_struct *tty)
 }
 
 
-static int kobil_tiocmget(struct tty_struct *tty, struct file *file)
+static int kobil_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct kobil_private *priv;
diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c
index 2849f8c32015..27447095feae 100644
--- a/drivers/usb/serial/mct_u232.c
+++ b/drivers/usb/serial/mct_u232.c
@@ -101,7 +101,7 @@ static void mct_u232_read_int_callback(struct urb *urb);
 static void mct_u232_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static void mct_u232_break_ctl(struct tty_struct *tty, int break_state);
-static int  mct_u232_tiocmget(struct tty_struct *tty, struct file *file);
+static int  mct_u232_tiocmget(struct tty_struct *tty);
 static int  mct_u232_tiocmset(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 static void mct_u232_throttle(struct tty_struct *tty);
@@ -762,7 +762,7 @@ static void mct_u232_break_ctl(struct tty_struct *tty, int break_state)
 } /* mct_u232_break_ctl */
 
 
-static int mct_u232_tiocmget(struct tty_struct *tty, struct file *file)
+static int mct_u232_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct mct_u232_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 7d3bc9a3e2b6..5d40d4151b5a 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -1833,7 +1833,7 @@ static int get_lsr_info(struct tty_struct *tty,
 	return 0;
 }
 
-static int mos7720_tiocmget(struct tty_struct *tty, struct file *file)
+static int mos7720_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct moschip_port *mos7720_port = usb_get_serial_port_data(port);
@@ -1865,7 +1865,7 @@ static int mos7720_tiocmset(struct tty_struct *tty, struct file *file,
 	struct moschip_port *mos7720_port = usb_get_serial_port_data(port);
 	unsigned int mcr ;
 	dbg("%s - port %d", __func__, port->number);
-	dbg("he was at tiocmget");
+	dbg("he was at tiocmset");
 
 	mcr = mos7720_port->shadowMCR;
 
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 5627993f9e41..ee0dc9a0890c 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -1644,7 +1644,7 @@ static void mos7840_unthrottle(struct tty_struct *tty)
 	}
 }
 
-static int mos7840_tiocmget(struct tty_struct *tty, struct file *file)
+static int mos7840_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct moschip_port *mos7840_port;
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index eda1f9266c4e..e305df807396 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -352,7 +352,7 @@ static void opticon_unthrottle(struct tty_struct *tty)
 	}
 }
 
-static int opticon_tiocmget(struct tty_struct *tty, struct file *file)
+static int opticon_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct opticon_private *priv = usb_get_serial_data(port->serial);
diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c
index 73613205be7a..4cd3b0ef4e61 100644
--- a/drivers/usb/serial/oti6858.c
+++ b/drivers/usb/serial/oti6858.c
@@ -144,7 +144,7 @@ static int oti6858_write(struct tty_struct *tty, struct usb_serial_port *port,
 			const unsigned char *buf, int count);
 static int oti6858_write_room(struct tty_struct *tty);
 static int oti6858_chars_in_buffer(struct tty_struct *tty);
-static int oti6858_tiocmget(struct tty_struct *tty, struct file *file);
+static int oti6858_tiocmget(struct tty_struct *tty);
 static int oti6858_tiocmset(struct tty_struct *tty, struct file *file,
 				unsigned int set, unsigned int clear);
 static int oti6858_startup(struct usb_serial *serial);
@@ -657,7 +657,7 @@ static int oti6858_tiocmset(struct tty_struct *tty, struct file *file,
 	return 0;
 }
 
-static int oti6858_tiocmget(struct tty_struct *tty, struct file *file)
+static int oti6858_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct oti6858_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 08c9181b8e48..6cb4f503a3f1 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -531,7 +531,7 @@ static int pl2303_tiocmset(struct tty_struct *tty, struct file *file,
 	return set_control_lines(port->serial->dev, control);
 }
 
-static int pl2303_tiocmget(struct tty_struct *tty, struct file *file)
+static int pl2303_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct pl2303_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 7481ff8a49e4..66437f1e9e5b 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -389,7 +389,7 @@ static void sierra_set_termios(struct tty_struct *tty,
 	sierra_send_setup(port);
 }
 
-static int sierra_tiocmget(struct tty_struct *tty, struct file *file)
+static int sierra_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	unsigned int value;
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index cbfb70bffdd0..cac13009fc5c 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -618,7 +618,7 @@ static int spcp8x5_tiocmset(struct tty_struct *tty, struct file *file,
 	return spcp8x5_set_ctrlLine(port->serial->dev, control , priv->type);
 }
 
-static int spcp8x5_tiocmget(struct tty_struct *tty, struct file *file)
+static int spcp8x5_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct spcp8x5_private *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index 8359ec798959..b21583fa825c 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -484,7 +484,7 @@ static int ssu100_attach(struct usb_serial *serial)
 	return ssu100_initdevice(serial->dev);
 }
 
-static int ssu100_tiocmget(struct tty_struct *tty, struct file *file)
+static int ssu100_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct usb_device *dev = port->serial->dev;
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index b2902f307b47..223e60e31735 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -112,7 +112,7 @@ static int ti_get_icount(struct tty_struct *tty,
 		struct serial_icounter_struct *icount);
 static void ti_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios);
-static int ti_tiocmget(struct tty_struct *tty, struct file *file);
+static int ti_tiocmget(struct tty_struct *tty);
 static int ti_tiocmset(struct tty_struct *tty, struct file *file,
 		unsigned int set, unsigned int clear);
 static void ti_break(struct tty_struct *tty, int break_state);
@@ -1000,7 +1000,7 @@ static void ti_set_termios(struct tty_struct *tty,
 }
 
 
-static int ti_tiocmget(struct tty_struct *tty, struct file *file)
+static int ti_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct ti_port *tport = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 546a52179bec..df105c6531a1 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -496,14 +496,14 @@ static const struct file_operations serial_proc_fops = {
 	.release	= single_release,
 };
 
-static int serial_tiocmget(struct tty_struct *tty, struct file *file)
+static int serial_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 
 	dbg("%s - port %d", __func__, port->number);
 
 	if (port->serial->type->tiocmget)
-		return port->serial->type->tiocmget(tty, file);
+		return port->serial->type->tiocmget(tty);
 	return -EINVAL;
 }
 
diff --git a/drivers/usb/serial/usb-wwan.h b/drivers/usb/serial/usb-wwan.h
index 3ab77c5d9819..8b68fc783d5f 100644
--- a/drivers/usb/serial/usb-wwan.h
+++ b/drivers/usb/serial/usb-wwan.h
@@ -15,7 +15,7 @@ extern int usb_wwan_write_room(struct tty_struct *tty);
 extern void usb_wwan_set_termios(struct tty_struct *tty,
 				 struct usb_serial_port *port,
 				 struct ktermios *old);
-extern int usb_wwan_tiocmget(struct tty_struct *tty, struct file *file);
+extern int usb_wwan_tiocmget(struct tty_struct *tty);
 extern int usb_wwan_tiocmset(struct tty_struct *tty, struct file *file,
 			     unsigned int set, unsigned int clear);
 extern int usb_wwan_ioctl(struct tty_struct *tty, struct file *file,
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index b004b2a485c3..60f942632cb4 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -79,7 +79,7 @@ void usb_wwan_set_termios(struct tty_struct *tty,
 }
 EXPORT_SYMBOL(usb_wwan_set_termios);
 
-int usb_wwan_tiocmget(struct tty_struct *tty, struct file *file)
+int usb_wwan_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	unsigned int value;
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 3f9ac88d588c..bf850139e0b8 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -156,7 +156,7 @@ static int  whiteheat_ioctl(struct tty_struct *tty, struct file *file,
 			unsigned int cmd, unsigned long arg);
 static void whiteheat_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
-static int  whiteheat_tiocmget(struct tty_struct *tty, struct file *file);
+static int  whiteheat_tiocmget(struct tty_struct *tty);
 static int  whiteheat_tiocmset(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 static void whiteheat_break_ctl(struct tty_struct *tty, int break_state);
@@ -833,7 +833,7 @@ static int whiteheat_write_room(struct tty_struct *tty)
 	return (room);
 }
 
-static int whiteheat_tiocmget(struct tty_struct *tty, struct file *file)
+static int whiteheat_tiocmget(struct tty_struct *tty)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct whiteheat_private *info = usb_get_serial_port_data(port);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index c3d43eb4150c..9539d74171db 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -271,7 +271,7 @@ struct tty_operations {
 	void (*set_ldisc)(struct tty_struct *tty);
 	void (*wait_until_sent)(struct tty_struct *tty, int timeout);
 	void (*send_xchar)(struct tty_struct *tty, char ch);
-	int (*tiocmget)(struct tty_struct *tty, struct file *file);
+	int (*tiocmget)(struct tty_struct *tty);
 	int (*tiocmset)(struct tty_struct *tty, struct file *file,
 			unsigned int set, unsigned int clear);
 	int (*resize)(struct tty_struct *tty, struct winsize *ws);
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index c9049139a7a5..30b945397d19 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -268,7 +268,7 @@ struct usb_serial_driver {
 	int  (*chars_in_buffer)(struct tty_struct *tty);
 	void (*throttle)(struct tty_struct *tty);
 	void (*unthrottle)(struct tty_struct *tty);
-	int  (*tiocmget)(struct tty_struct *tty, struct file *file);
+	int  (*tiocmget)(struct tty_struct *tty);
 	int  (*tiocmset)(struct tty_struct *tty, struct file *file,
 			 unsigned int set, unsigned int clear);
 	int  (*get_icount)(struct tty_struct *tty,
diff --git a/include/net/irda/ircomm_tty.h b/include/net/irda/ircomm_tty.h
index eea2e6152389..fa3793b5392d 100644
--- a/include/net/irda/ircomm_tty.h
+++ b/include/net/irda/ircomm_tty.h
@@ -120,7 +120,7 @@ struct ircomm_tty_cb {
 void ircomm_tty_start(struct tty_struct *tty);
 void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self);
 
-extern int ircomm_tty_tiocmget(struct tty_struct *tty, struct file *file);
+extern int ircomm_tty_tiocmget(struct tty_struct *tty);
 extern int ircomm_tty_tiocmset(struct tty_struct *tty, struct file *file,
 			       unsigned int set, unsigned int clear);
 extern int ircomm_tty_ioctl(struct tty_struct *tty, struct file *file, 
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 2575c2db6404..7f67fa4f2f5e 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -1089,7 +1089,7 @@ static void rfcomm_tty_hangup(struct tty_struct *tty)
 	}
 }
 
-static int rfcomm_tty_tiocmget(struct tty_struct *tty, struct file *filp)
+static int rfcomm_tty_tiocmget(struct tty_struct *tty)
 {
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
 
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index 24cb3aa2bbfb..bb47caeba7e6 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -189,12 +189,12 @@ void ircomm_tty_set_termios(struct tty_struct *tty,
 }
 
 /*
- * Function ircomm_tty_tiocmget (tty, file)
+ * Function ircomm_tty_tiocmget (tty)
  *
  *
  *
  */
-int ircomm_tty_tiocmget(struct tty_struct *tty, struct file *file)
+int ircomm_tty_tiocmget(struct tty_struct *tty)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
 	unsigned int result;
-- 
cgit v1.2.3


From 20b9d17715017ae4dd4ec87fabc36d33b9de708e Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@linux.intel.com>
Date: Mon, 14 Feb 2011 16:26:50 +0000
Subject: tiocmset: kill the file pointer argument

Doing tiocmget was such fun we should do tiocmset as well for the same
reasons

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/char/amiserial.c                    |  4 ++--
 drivers/char/cyclades.c                     |  2 +-
 drivers/char/epca.c                         |  4 ++--
 drivers/char/ip2/ip2main.c                  |  4 ++--
 drivers/char/isicom.c                       |  4 ++--
 drivers/char/istallion.c                    |  2 +-
 drivers/char/moxa.c                         |  4 ++--
 drivers/char/mxser.c                        |  2 +-
 drivers/char/nozomi.c                       |  4 ++--
 drivers/char/pcmcia/ipwireless/tty.c        |  2 +-
 drivers/char/pcmcia/synclink_cs.c           |  6 +++---
 drivers/char/riscom8.c                      |  4 ++--
 drivers/char/rocket.c                       |  4 ++--
 drivers/char/serial167.c                    |  3 +--
 drivers/char/specialix.c                    |  2 +-
 drivers/char/stallion.c                     |  2 +-
 drivers/char/sx.c                           |  4 ++--
 drivers/char/synclink.c                     |  6 +++---
 drivers/char/synclink_gt.c                  |  6 +++---
 drivers/char/synclinkmp.c                   |  8 ++++----
 drivers/isdn/gigaset/interface.c            |  4 ++--
 drivers/isdn/gigaset/ser-gigaset.c          |  2 +-
 drivers/isdn/i4l/isdn_tty.c                 |  2 +-
 drivers/mmc/card/sdio_uart.c                |  2 +-
 drivers/net/irda/irtty-sir.c                |  2 +-
 drivers/net/usb/hso.c                       |  6 +++---
 drivers/net/wan/pc300_tty.c                 |  5 ++---
 drivers/staging/quatech_usb2/quatech_usb2.c |  2 +-
 drivers/staging/serqt_usb2/serqt_usb2.c     |  5 ++---
 drivers/tty/hvc/hvsi.c                      |  4 ++--
 drivers/tty/n_gsm.c                         |  2 +-
 drivers/tty/serial/68360serial.c            |  2 +-
 drivers/tty/serial/crisv10.c                |  3 +--
 drivers/tty/serial/ifx6x60.c                |  3 +--
 drivers/tty/serial/serial_core.c            |  6 ++----
 drivers/tty/tty_io.c                        |  7 +++----
 drivers/usb/class/cdc-acm.c                 |  2 +-
 drivers/usb/serial/ark3116.c                |  2 +-
 drivers/usb/serial/belkin_sa.c              |  4 ++--
 drivers/usb/serial/ch341.c                  |  2 +-
 drivers/usb/serial/cp210x.c                 | 15 +++++++--------
 drivers/usb/serial/cypress_m8.c             |  4 ++--
 drivers/usb/serial/digi_acceleport.c        | 10 +++++-----
 drivers/usb/serial/ftdi_sio.c               |  4 ++--
 drivers/usb/serial/io_edgeport.c            |  4 ++--
 drivers/usb/serial/io_ti.c                  |  2 +-
 drivers/usb/serial/iuu_phoenix.c            |  2 +-
 drivers/usb/serial/keyspan.c                |  2 +-
 drivers/usb/serial/keyspan.h                |  2 +-
 drivers/usb/serial/keyspan_pda.c            |  2 +-
 drivers/usb/serial/kl5kusb105.c             |  4 ++--
 drivers/usb/serial/kobil_sct.c              |  4 ++--
 drivers/usb/serial/mct_u232.c               |  4 ++--
 drivers/usb/serial/mos7720.c                |  2 +-
 drivers/usb/serial/mos7840.c                |  2 +-
 drivers/usb/serial/oti6858.c                |  4 ++--
 drivers/usb/serial/pl2303.c                 |  2 +-
 drivers/usb/serial/sierra.c                 |  2 +-
 drivers/usb/serial/spcp8x5.c                |  2 +-
 drivers/usb/serial/ssu100.c                 |  2 +-
 drivers/usb/serial/ti_usb_3410_5052.c       |  6 +++---
 drivers/usb/serial/usb-serial.c             |  4 ++--
 drivers/usb/serial/usb-wwan.h               |  2 +-
 drivers/usb/serial/usb_wwan.c               |  2 +-
 drivers/usb/serial/whiteheat.c              |  4 ++--
 include/linux/tty_driver.h                  |  2 +-
 include/linux/usb/serial.h                  |  2 +-
 include/net/irda/ircomm_tty.h               |  2 +-
 net/bluetooth/rfcomm/tty.c                  |  2 +-
 net/irda/ircomm/ircomm_tty_ioctl.c          |  4 ++--
 70 files changed, 120 insertions(+), 129 deletions(-)

(limited to 'include')

diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c
index bc67e6839059..5c15fad71ad2 100644
--- a/drivers/char/amiserial.c
+++ b/drivers/char/amiserial.c
@@ -1216,8 +1216,8 @@ static int rs_tiocmget(struct tty_struct *tty)
 		| (!(status  & SER_CTS) ? TIOCM_CTS : 0);
 }
 
-static int rs_tiocmset(struct tty_struct *tty, struct file *file,
-		       unsigned int set, unsigned int clear)
+static int rs_tiocmset(struct tty_struct *tty, unsigned int set,
+						unsigned int clear)
 {
 	struct async_struct * info = tty->driver_data;
 	unsigned long flags;
diff --git a/drivers/char/cyclades.c b/drivers/char/cyclades.c
index e7945ddacd18..942b6f2b70a4 100644
--- a/drivers/char/cyclades.c
+++ b/drivers/char/cyclades.c
@@ -2483,7 +2483,7 @@ end:
 }				/* cy_tiomget */
 
 static int
-cy_tiocmset(struct tty_struct *tty, struct file *file,
+cy_tiocmset(struct tty_struct *tty,
 		unsigned int set, unsigned int clear)
 {
 	struct cyclades_port *info = tty->driver_data;
diff --git a/drivers/char/epca.c b/drivers/char/epca.c
index ecf6f0a889fc..e5872b59f9cd 100644
--- a/drivers/char/epca.c
+++ b/drivers/char/epca.c
@@ -2015,7 +2015,7 @@ static int pc_tiocmget(struct tty_struct *tty)
 	return mflag;
 }
 
-static int pc_tiocmset(struct tty_struct *tty, struct file *file,
+static int pc_tiocmset(struct tty_struct *tty,
 		       unsigned int set, unsigned int clear)
 {
 	struct channel *ch = tty->driver_data;
@@ -2081,7 +2081,7 @@ static int pc_ioctl(struct tty_struct *tty, struct file *file,
 	case TIOCMODS:
 		if (get_user(mstat, (unsigned __user *)argp))
 			return -EFAULT;
-		return pc_tiocmset(tty, file, mstat, ~mstat);
+		return pc_tiocmset(tty, mstat, ~mstat);
 	case TIOCSDTR:
 		spin_lock_irqsave(&epca_lock, flags);
 		ch->omodem |= ch->m_dtr;
diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c
index 476cd087118e..d5f866c7c672 100644
--- a/drivers/char/ip2/ip2main.c
+++ b/drivers/char/ip2/ip2main.c
@@ -182,7 +182,7 @@ static void ip2_stop(PTTY);
 static void ip2_start(PTTY);
 static void ip2_hangup(PTTY);
 static int  ip2_tiocmget(struct tty_struct *tty);
-static int  ip2_tiocmset(struct tty_struct *tty, struct file *file,
+static int  ip2_tiocmset(struct tty_struct *tty,
 			 unsigned int set, unsigned int clear);
 static int ip2_get_icount(struct tty_struct *tty,
 		struct serial_icounter_struct *icount);
@@ -2085,7 +2085,7 @@ static int ip2_tiocmget(struct tty_struct *tty)
 	      | ((pCh->dataSetIn  & I2_CTS) ? TIOCM_CTS : 0);
 }
 
-static int ip2_tiocmset(struct tty_struct *tty, struct file *file,
+static int ip2_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear)
 {
 	i2ChanStrPtr pCh = DevTable[tty->index];
diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c
index 836370bc04c2..60f4d8ae7a49 100644
--- a/drivers/char/isicom.c
+++ b/drivers/char/isicom.c
@@ -1082,8 +1082,8 @@ static int isicom_tiocmget(struct tty_struct *tty)
 		((status & ISI_RI ) ? TIOCM_RI  : 0);
 }
 
-static int isicom_tiocmset(struct tty_struct *tty, struct file *file,
-	unsigned int set, unsigned int clear)
+static int isicom_tiocmset(struct tty_struct *tty,
+					unsigned int set, unsigned int clear)
 {
 	struct isi_port *port = tty->driver_data;
 	unsigned long flags;
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index 7843a847b76a..763b58d58255 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -1524,7 +1524,7 @@ static int stli_tiocmget(struct tty_struct *tty)
 	return stli_mktiocm(portp->asig.sigvalue);
 }
 
-static int stli_tiocmset(struct tty_struct *tty, struct file *file,
+static int stli_tiocmset(struct tty_struct *tty,
 			 unsigned int set, unsigned int clear)
 {
 	struct stliport *portp = tty->driver_data;
diff --git a/drivers/char/moxa.c b/drivers/char/moxa.c
index fdf069bb702f..9f4cd8968a5a 100644
--- a/drivers/char/moxa.c
+++ b/drivers/char/moxa.c
@@ -200,7 +200,7 @@ static void moxa_stop(struct tty_struct *);
 static void moxa_start(struct tty_struct *);
 static void moxa_hangup(struct tty_struct *);
 static int moxa_tiocmget(struct tty_struct *tty);
-static int moxa_tiocmset(struct tty_struct *tty, struct file *file,
+static int moxa_tiocmset(struct tty_struct *tty,
 			 unsigned int set, unsigned int clear);
 static void moxa_poll(unsigned long);
 static void moxa_set_tty_param(struct tty_struct *, struct ktermios *);
@@ -1277,7 +1277,7 @@ static int moxa_tiocmget(struct tty_struct *tty)
 	return flag;
 }
 
-static int moxa_tiocmset(struct tty_struct *tty, struct file *file,
+static int moxa_tiocmset(struct tty_struct *tty,
 			 unsigned int set, unsigned int clear)
 {
 	struct moxa_port *ch;
diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index 4d2f03ec06cd..150a862c4989 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -1347,7 +1347,7 @@ static int mxser_tiocmget(struct tty_struct *tty)
 		    ((status & UART_MSR_CTS) ? TIOCM_CTS : 0);
 }
 
-static int mxser_tiocmset(struct tty_struct *tty, struct file *file,
+static int mxser_tiocmset(struct tty_struct *tty,
 		unsigned int set, unsigned int clear)
 {
 	struct mxser_port *info = tty->driver_data;
diff --git a/drivers/char/nozomi.c b/drivers/char/nozomi.c
index 0e1dff2ffb1e..1b74c48c4016 100644
--- a/drivers/char/nozomi.c
+++ b/drivers/char/nozomi.c
@@ -1767,8 +1767,8 @@ static int ntty_tiocmget(struct tty_struct *tty)
 }
 
 /* Sets io controls parameters */
-static int ntty_tiocmset(struct tty_struct *tty, struct file *file,
-	unsigned int set, unsigned int clear)
+static int ntty_tiocmset(struct tty_struct *tty,
+					unsigned int set, unsigned int clear)
 {
 	struct nozomi *dc = get_dc_by_tty(tty);
 	unsigned long flags;
diff --git a/drivers/char/pcmcia/ipwireless/tty.c b/drivers/char/pcmcia/ipwireless/tty.c
index 7d2ef4909a73..748190dfbab0 100644
--- a/drivers/char/pcmcia/ipwireless/tty.c
+++ b/drivers/char/pcmcia/ipwireless/tty.c
@@ -410,7 +410,7 @@ static int ipw_tiocmget(struct tty_struct *linux_tty)
 }
 
 static int
-ipw_tiocmset(struct tty_struct *linux_tty, struct file *file,
+ipw_tiocmset(struct tty_struct *linux_tty,
 	     unsigned int set, unsigned int clear)
 {
 	struct ipw_tty *tty = linux_tty->driver_data;
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index 7b68ba6609fe..02127cad0980 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -419,8 +419,8 @@ static void bh_status(MGSLPC_INFO *info);
  * ioctl handlers
  */
 static int tiocmget(struct tty_struct *tty);
-static int tiocmset(struct tty_struct *tty, struct file *file,
-		    unsigned int set, unsigned int clear);
+static int tiocmset(struct tty_struct *tty,
+					unsigned int set, unsigned int clear);
 static int get_stats(MGSLPC_INFO *info, struct mgsl_icount __user *user_icount);
 static int get_params(MGSLPC_INFO *info, MGSL_PARAMS __user *user_params);
 static int set_params(MGSLPC_INFO *info, MGSL_PARAMS __user *new_params, struct tty_struct *tty);
@@ -2139,7 +2139,7 @@ static int tiocmget(struct tty_struct *tty)
 
 /* set modem control signals (DTR/RTS)
  */
-static int tiocmset(struct tty_struct *tty, struct file *file,
+static int tiocmset(struct tty_struct *tty,
 		    unsigned int set, unsigned int clear)
 {
 	MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data;
diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c
index 5d0c98456c93..3666decc6438 100644
--- a/drivers/char/riscom8.c
+++ b/drivers/char/riscom8.c
@@ -1115,8 +1115,8 @@ static int rc_tiocmget(struct tty_struct *tty)
 	return result;
 }
 
-static int rc_tiocmset(struct tty_struct *tty, struct file *file,
-		       unsigned int set, unsigned int clear)
+static int rc_tiocmset(struct tty_struct *tty,
+				       unsigned int set, unsigned int clear)
 {
 	struct riscom_port *port = tty->driver_data;
 	unsigned long flags;
diff --git a/drivers/char/rocket.c b/drivers/char/rocket.c
index 75e98efbc8e9..36c108811a81 100644
--- a/drivers/char/rocket.c
+++ b/drivers/char/rocket.c
@@ -1189,8 +1189,8 @@ static int rp_tiocmget(struct tty_struct *tty)
 /* 
  *  Sets the modem control lines
  */
-static int rp_tiocmset(struct tty_struct *tty, struct file *file,
-		    unsigned int set, unsigned int clear)
+static int rp_tiocmset(struct tty_struct *tty,
+				unsigned int set, unsigned int clear)
 {
 	struct r_port *info = tty->driver_data;
 
diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index fda90643ead7..89ac542ffff2 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -1331,8 +1331,7 @@ static int cy_tiocmget(struct tty_struct *tty)
 }				/* cy_tiocmget */
 
 static int
-cy_tiocmset(struct tty_struct *tty, struct file *file,
-	    unsigned int set, unsigned int clear)
+cy_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 {
 	struct cyclades_port *info = tty->driver_data;
 	int channel;
diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c
index bfecfbef0895..a6b23847e4a7 100644
--- a/drivers/char/specialix.c
+++ b/drivers/char/specialix.c
@@ -1778,7 +1778,7 @@ static int sx_tiocmget(struct tty_struct *tty)
 }
 
 
-static int sx_tiocmset(struct tty_struct *tty, struct file *file,
+static int sx_tiocmset(struct tty_struct *tty,
 		       unsigned int set, unsigned int clear)
 {
 	struct specialix_port *port = tty->driver_data;
diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index 8c2bf3fb5b89..c42dbffbed16 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -1107,7 +1107,7 @@ static int stl_tiocmget(struct tty_struct *tty)
 	return stl_getsignals(portp);
 }
 
-static int stl_tiocmset(struct tty_struct *tty, struct file *file,
+static int stl_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear)
 {
 	struct stlport	*portp;
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index f46214e60d0c..342c6ae67da5 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -1879,8 +1879,8 @@ static int sx_tiocmget(struct tty_struct *tty)
 	return sx_getsignals(port);
 }
 
-static int sx_tiocmset(struct tty_struct *tty, struct file *file,
-		unsigned int set, unsigned int clear)
+static int sx_tiocmset(struct tty_struct *tty,
+					unsigned int set, unsigned int clear)
 {
 	struct sx_port *port = tty->driver_data;
 	int rts = -1, dtr = -1;
diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c
index d359e092904a..691e1094c20b 100644
--- a/drivers/char/synclink.c
+++ b/drivers/char/synclink.c
@@ -824,7 +824,7 @@ static isr_dispatch_func UscIsrTable[7] =
  * ioctl call handlers
  */
 static int tiocmget(struct tty_struct *tty);
-static int tiocmset(struct tty_struct *tty, struct file *file,
+static int tiocmset(struct tty_struct *tty,
 		    unsigned int set, unsigned int clear);
 static int mgsl_get_stats(struct mgsl_struct * info, struct mgsl_icount
 	__user *user_icount);
@@ -2871,8 +2871,8 @@ static int tiocmget(struct tty_struct *tty)
 
 /* set modem control signals (DTR/RTS)
  */
-static int tiocmset(struct tty_struct *tty, struct file *file,
-		    unsigned int set, unsigned int clear)
+static int tiocmset(struct tty_struct *tty,
+				    unsigned int set, unsigned int clear)
 {
 	struct mgsl_struct *info = tty->driver_data;
  	unsigned long flags;
diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c
index f18ab8af0e1c..04da6d61dc4f 100644
--- a/drivers/char/synclink_gt.c
+++ b/drivers/char/synclink_gt.c
@@ -513,8 +513,8 @@ static int  rx_enable(struct slgt_info *info, int enable);
 static int  modem_input_wait(struct slgt_info *info,int arg);
 static int  wait_mgsl_event(struct slgt_info *info, int __user *mask_ptr);
 static int  tiocmget(struct tty_struct *tty);
-static int  tiocmset(struct tty_struct *tty, struct file *file,
-		     unsigned int set, unsigned int clear);
+static int  tiocmset(struct tty_struct *tty,
+				unsigned int set, unsigned int clear);
 static int set_break(struct tty_struct *tty, int break_state);
 static int  get_interface(struct slgt_info *info, int __user *if_mode);
 static int  set_interface(struct slgt_info *info, int if_mode);
@@ -3223,7 +3223,7 @@ static int tiocmget(struct tty_struct *tty)
  *		TIOCMSET = set/clear signal values
  * 	value	bit mask for command
  */
-static int tiocmset(struct tty_struct *tty, struct file *file,
+static int tiocmset(struct tty_struct *tty,
 		    unsigned int set, unsigned int clear)
 {
 	struct slgt_info *info = tty->driver_data;
diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c
index 5900213ae75b..1f9de97e8cfc 100644
--- a/drivers/char/synclinkmp.c
+++ b/drivers/char/synclinkmp.c
@@ -547,8 +547,8 @@ static int  rx_enable(SLMP_INFO *info, int enable);
 static int  modem_input_wait(SLMP_INFO *info,int arg);
 static int  wait_mgsl_event(SLMP_INFO *info, int __user *mask_ptr);
 static int  tiocmget(struct tty_struct *tty);
-static int  tiocmset(struct tty_struct *tty, struct file *file,
-		     unsigned int set, unsigned int clear);
+static int  tiocmset(struct tty_struct *tty,
+			unsigned int set, unsigned int clear);
 static int  set_break(struct tty_struct *tty, int break_state);
 
 static void add_device(SLMP_INFO *info);
@@ -3232,8 +3232,8 @@ static int tiocmget(struct tty_struct *tty)
 
 /* set modem control signals (DTR/RTS)
  */
-static int tiocmset(struct tty_struct *tty, struct file *file,
-		    unsigned int set, unsigned int clear)
+static int tiocmset(struct tty_struct *tty,
+					unsigned int set, unsigned int clear)
 {
 	SLMP_INFO *info = tty->driver_data;
  	unsigned long flags;
diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c
index e1a7c14f5f1d..9b2bb491c614 100644
--- a/drivers/isdn/gigaset/interface.c
+++ b/drivers/isdn/gigaset/interface.c
@@ -123,7 +123,7 @@ static void if_throttle(struct tty_struct *tty);
 static void if_unthrottle(struct tty_struct *tty);
 static void if_set_termios(struct tty_struct *tty, struct ktermios *old);
 static int  if_tiocmget(struct tty_struct *tty);
-static int  if_tiocmset(struct tty_struct *tty, struct file *file,
+static int  if_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 static int  if_write(struct tty_struct *tty,
 		     const unsigned char *buf, int count);
@@ -303,7 +303,7 @@ static int if_tiocmget(struct tty_struct *tty)
 	return retval;
 }
 
-static int if_tiocmset(struct tty_struct *tty, struct file *file,
+static int if_tiocmset(struct tty_struct *tty,
 		       unsigned int set, unsigned int clear)
 {
 	struct cardstate *cs;
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 0ef09d0eb96b..86a5c4f7775e 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -440,7 +440,7 @@ static int gigaset_set_modem_ctrl(struct cardstate *cs, unsigned old_state,
 	if (!set && !clear)
 		return 0;
 	gig_dbg(DEBUG_IF, "tiocmset set %x clear %x", set, clear);
-	return tty->ops->tiocmset(tty, NULL, set, clear);
+	return tty->ops->tiocmset(tty, set, clear);
 }
 
 static int gigaset_baud_rate(struct cardstate *cs, unsigned cflag)
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index ba6c2f124b58..0341c69eb152 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1372,7 +1372,7 @@ isdn_tty_tiocmget(struct tty_struct *tty)
 }
 
 static int
-isdn_tty_tiocmset(struct tty_struct *tty, struct file *file,
+isdn_tty_tiocmset(struct tty_struct *tty,
 		unsigned int set, unsigned int clear)
 {
 	modem_info *info = (modem_info *) tty->driver_data;
diff --git a/drivers/mmc/card/sdio_uart.c b/drivers/mmc/card/sdio_uart.c
index 86bb04d821b1..c8c9edb3d7cb 100644
--- a/drivers/mmc/card/sdio_uart.c
+++ b/drivers/mmc/card/sdio_uart.c
@@ -970,7 +970,7 @@ static int sdio_uart_tiocmget(struct tty_struct *tty)
 	return result;
 }
 
-static int sdio_uart_tiocmset(struct tty_struct *tty, struct file *file,
+static int sdio_uart_tiocmset(struct tty_struct *tty,
 			      unsigned int set, unsigned int clear)
 {
 	struct sdio_uart_port *port = tty->driver_data;
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index ee1dde52e8fc..3352b2443e58 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -167,7 +167,7 @@ static int irtty_set_dtr_rts(struct sir_dev *dev, int dtr, int rts)
 	 * let's be careful... Jean II
 	 */
 	IRDA_ASSERT(priv->tty->ops->tiocmset != NULL, return -1;);
-	priv->tty->ops->tiocmset(priv->tty, NULL, set, clear);
+	priv->tty->ops->tiocmset(priv->tty, set, clear);
 
 	return 0;
 }
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 7c68c456c035..956e1d6e72a5 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -324,7 +324,7 @@ struct hso_device {
 /* Prototypes                                                                */
 /*****************************************************************************/
 /* Serial driver functions */
-static int hso_serial_tiocmset(struct tty_struct *tty, struct file *file,
+static int hso_serial_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear);
 static void ctrl_callback(struct urb *urb);
 static int put_rxbuf_data(struct urb *urb, struct hso_serial *serial);
@@ -1335,7 +1335,7 @@ static int hso_serial_open(struct tty_struct *tty, struct file *filp)
 
 	/* done */
 	if (result)
-		hso_serial_tiocmset(tty, NULL, TIOCM_RTS | TIOCM_DTR, 0);
+		hso_serial_tiocmset(tty, TIOCM_RTS | TIOCM_DTR, 0);
 err_out:
 	mutex_unlock(&serial->parent->mutex);
 	return result;
@@ -1687,7 +1687,7 @@ static int hso_serial_tiocmget(struct tty_struct *tty)
 	return retval;
 }
 
-static int hso_serial_tiocmset(struct tty_struct *tty, struct file *file,
+static int hso_serial_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear)
 {
 	int val = 0;
diff --git a/drivers/net/wan/pc300_tty.c b/drivers/net/wan/pc300_tty.c
index d999e54a7730..1c65d1c33873 100644
--- a/drivers/net/wan/pc300_tty.c
+++ b/drivers/net/wan/pc300_tty.c
@@ -131,8 +131,7 @@ static void cpc_tty_trace(pc300dev_t *dev, char* buf, int len, char rxtx);
 static void cpc_tty_signal_off(pc300dev_t *pc300dev, unsigned char);
 static void cpc_tty_signal_on(pc300dev_t *pc300dev, unsigned char);
 
-static int pc300_tiocmset(struct tty_struct *, struct file *,
-			  unsigned int, unsigned int);
+static int pc300_tiocmset(struct tty_struct *, unsigned int, unsigned int);
 static int pc300_tiocmget(struct tty_struct *);
 
 /* functions called by PC300 driver */
@@ -543,7 +542,7 @@ static int cpc_tty_chars_in_buffer(struct tty_struct *tty)
 	return 0;
 } 
 
-static int pc300_tiocmset(struct tty_struct *tty, struct file *file,
+static int pc300_tiocmset(struct tty_struct *tty,
 			  unsigned int set, unsigned int clear)
 {
 	st_cpc_tty_area    *cpc_tty; 
diff --git a/drivers/staging/quatech_usb2/quatech_usb2.c b/drivers/staging/quatech_usb2/quatech_usb2.c
index 1e50292aef74..3734448d1b82 100644
--- a/drivers/staging/quatech_usb2/quatech_usb2.c
+++ b/drivers/staging/quatech_usb2/quatech_usb2.c
@@ -1121,7 +1121,7 @@ static int qt2_tiocmget(struct tty_struct *tty)
 	}
 }
 
-static int qt2_tiocmset(struct tty_struct *tty, struct file *file,
+static int qt2_tiocmset(struct tty_struct *tty,
 		       unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index 56ded56db7b4..39776c1cf10f 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -1425,7 +1425,6 @@ static inline int qt_real_tiocmget(struct tty_struct *tty,
 
 static inline int qt_real_tiocmset(struct tty_struct *tty,
 				   struct usb_serial_port *port,
-				   struct file *file,
 				   struct usb_serial *serial,
 				   unsigned int value)
 {
@@ -1486,7 +1485,7 @@ static int qt_tiocmget(struct tty_struct *tty)
 	return retval;
 }
 
-static int qt_tiocmset(struct tty_struct *tty, struct file *file,
+static int qt_tiocmset(struct tty_struct *tty,
 		       unsigned int set, unsigned int clear)
 {
 
@@ -1506,7 +1505,7 @@ static int qt_tiocmset(struct tty_struct *tty, struct file *file,
 	dbg("%s - port %d\n", __func__, port->number);
 	dbg("%s - qt_port->RxHolding = %d\n", __func__, qt_port->RxHolding);
 
-	retval = qt_real_tiocmset(tty, port, file, serial, set);
+	retval = qt_real_tiocmset(tty, port, serial, set);
 
 	spin_unlock_irqrestore(&qt_port->lock, flags);
 	return retval;
diff --git a/drivers/tty/hvc/hvsi.c b/drivers/tty/hvc/hvsi.c
index 55293105a56c..8a8d6373f164 100644
--- a/drivers/tty/hvc/hvsi.c
+++ b/drivers/tty/hvc/hvsi.c
@@ -1103,8 +1103,8 @@ static int hvsi_tiocmget(struct tty_struct *tty)
 	return hp->mctrl;
 }
 
-static int hvsi_tiocmset(struct tty_struct *tty, struct file *file,
-		unsigned int set, unsigned int clear)
+static int hvsi_tiocmset(struct tty_struct *tty,
+				unsigned int set, unsigned int clear)
 {
 	struct hvsi_struct *hp = tty->driver_data;
 	unsigned long flags;
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 97e3d509ff82..88477d16b8b7 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2654,7 +2654,7 @@ static int gsmtty_tiocmget(struct tty_struct *tty)
 	return dlci->modem_rx;
 }
 
-static int gsmtty_tiocmset(struct tty_struct *tty, struct file *filp,
+static int gsmtty_tiocmset(struct tty_struct *tty,
 	unsigned int set, unsigned int clear)
 {
 	struct gsm_dlci *dlci = tty->driver_data;
diff --git a/drivers/tty/serial/68360serial.c b/drivers/tty/serial/68360serial.c
index 2a52cf14ce50..217fe1c299e0 100644
--- a/drivers/tty/serial/68360serial.c
+++ b/drivers/tty/serial/68360serial.c
@@ -1271,7 +1271,7 @@ static int rs_360_tiocmget(struct tty_struct *tty)
 	return result;
 }
 
-static int rs_360_tiocmset(struct tty_struct *tty, struct file *file,
+static int rs_360_tiocmset(struct tty_struct *tty,
 			   unsigned int set, unsigned int clear)
 {
 #ifdef modem_control
diff --git a/drivers/tty/serial/crisv10.c b/drivers/tty/serial/crisv10.c
index 8cc5c0224b25..b9fcd0bda60c 100644
--- a/drivers/tty/serial/crisv10.c
+++ b/drivers/tty/serial/crisv10.c
@@ -3581,8 +3581,7 @@ rs_break(struct tty_struct *tty, int break_state)
 }
 
 static int
-rs_tiocmset(struct tty_struct *tty, struct file *file,
-		unsigned int set, unsigned int clear)
+rs_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 {
 	struct e100_serial *info = (struct e100_serial *)tty->driver_data;
 	unsigned long flags;
diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c
index 4d26d39ec344..8ee5a41d340d 100644
--- a/drivers/tty/serial/ifx6x60.c
+++ b/drivers/tty/serial/ifx6x60.c
@@ -263,7 +263,6 @@ static int ifx_spi_tiocmget(struct tty_struct *tty)
 /**
  *	ifx_spi_tiocmset	-	set modem bits
  *	@tty: the tty structure
- *	@filp: file handle issuing the request
  *	@set: bits to set
  *	@clear: bits to clear
  *
@@ -272,7 +271,7 @@ static int ifx_spi_tiocmget(struct tty_struct *tty)
  *
  *	FIXME: do we need to kick the tranfers when we do this ?
  */
-static int ifx_spi_tiocmset(struct tty_struct *tty, struct file *filp,
+static int ifx_spi_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct ifx_spi_device *ifx_dev = tty->driver_data;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 53e490e47560..623d6bd911d7 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -925,8 +925,7 @@ static int uart_tiocmget(struct tty_struct *tty)
 }
 
 static int
-uart_tiocmset(struct tty_struct *tty, struct file *file,
-	      unsigned int set, unsigned int clear)
+uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 {
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *uport = state->uart_port;
@@ -934,8 +933,7 @@ uart_tiocmset(struct tty_struct *tty, struct file *file,
 	int ret = -EIO;
 
 	mutex_lock(&port->mutex);
-	if ((!file || !tty_hung_up_p(file)) &&
-	    !(tty->flags & (1 << TTY_IO_ERROR))) {
+	if (!(tty->flags & (1 << TTY_IO_ERROR))) {
 		uart_update_mctrl(uport, set, clear);
 		ret = 0;
 	}
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index fde5a4dae3dd..83af24ca1e5e 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2481,7 +2481,6 @@ static int tty_tiocmget(struct tty_struct *tty, int __user *p)
 /**
  *	tty_tiocmset		-	set modem status
  *	@tty: tty device
- *	@file: user file pointer
  *	@cmd: command - clear bits, set bits or set all
  *	@p: pointer to desired bits
  *
@@ -2491,7 +2490,7 @@ static int tty_tiocmget(struct tty_struct *tty, int __user *p)
  *	Locking: none (up to the driver)
  */
 
-static int tty_tiocmset(struct tty_struct *tty, struct file *file, unsigned int cmd,
+static int tty_tiocmset(struct tty_struct *tty, unsigned int cmd,
 	     unsigned __user *p)
 {
 	int retval;
@@ -2518,7 +2517,7 @@ static int tty_tiocmset(struct tty_struct *tty, struct file *file, unsigned int
 	}
 	set &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP;
 	clear &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP;
-	return tty->ops->tiocmset(tty, file, set, clear);
+	return tty->ops->tiocmset(tty, set, clear);
 }
 
 static int tty_tiocgicount(struct tty_struct *tty, void __user *arg)
@@ -2659,7 +2658,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case TIOCMSET:
 	case TIOCMBIC:
 	case TIOCMBIS:
-		return tty_tiocmset(tty, file, cmd, p);
+		return tty_tiocmset(tty, cmd, p);
 	case TIOCGICOUNT:
 		retval = tty_tiocgicount(tty, p);
 		/* For the moment allow fall through to the old method */
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 2ae996b7ce7b..e9a26fbd079c 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -791,7 +791,7 @@ static int acm_tty_tiocmget(struct tty_struct *tty)
 	       TIOCM_CTS;
 }
 
-static int acm_tty_tiocmset(struct tty_struct *tty, struct file *file,
+static int acm_tty_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct acm *acm = tty->driver_data;
diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c
index 35b610aa3f92..2f837e983339 100644
--- a/drivers/usb/serial/ark3116.c
+++ b/drivers/usb/serial/ark3116.c
@@ -511,7 +511,7 @@ static int ark3116_tiocmget(struct tty_struct *tty)
 		(ctrl   & UART_MCR_OUT2 ? TIOCM_OUT2 : 0);
 }
 
-static int ark3116_tiocmset(struct tty_struct *tty, struct file *file,
+static int ark3116_tiocmset(struct tty_struct *tty,
 			unsigned set, unsigned clr)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/belkin_sa.c b/drivers/usb/serial/belkin_sa.c
index 48fb3bad3cd6..d6921fa1403c 100644
--- a/drivers/usb/serial/belkin_sa.c
+++ b/drivers/usb/serial/belkin_sa.c
@@ -101,7 +101,7 @@ static void belkin_sa_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios * old);
 static void belkin_sa_break_ctl(struct tty_struct *tty, int break_state);
 static int  belkin_sa_tiocmget(struct tty_struct *tty);
-static int  belkin_sa_tiocmset(struct tty_struct *tty, struct file *file,
+static int  belkin_sa_tiocmset(struct tty_struct *tty,
 					unsigned int set, unsigned int clear);
 
 
@@ -513,7 +513,7 @@ static int belkin_sa_tiocmget(struct tty_struct *tty)
 	return control_state;
 }
 
-static int belkin_sa_tiocmset(struct tty_struct *tty, struct file *file,
+static int belkin_sa_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index aa0962b72f4c..5cbef313281e 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -431,7 +431,7 @@ out:
 	kfree(break_reg);
 }
 
-static int ch341_tiocmset(struct tty_struct *tty, struct file *file,
+static int ch341_tiocmset(struct tty_struct *tty,
 			  unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index b3873815035c..4df3e0cecbae 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -42,9 +42,8 @@ static void cp210x_get_termios_port(struct usb_serial_port *port,
 static void cp210x_set_termios(struct tty_struct *, struct usb_serial_port *,
 							struct ktermios*);
 static int cp210x_tiocmget(struct tty_struct *);
-static int cp210x_tiocmset(struct tty_struct *, struct file *,
-		unsigned int, unsigned int);
-static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *,
+static int cp210x_tiocmset(struct tty_struct *, unsigned int, unsigned int);
+static int cp210x_tiocmset_port(struct usb_serial_port *port,
 		unsigned int, unsigned int);
 static void cp210x_break_ctl(struct tty_struct *, int);
 static int cp210x_startup(struct usb_serial *);
@@ -698,14 +697,14 @@ static void cp210x_set_termios(struct tty_struct *tty,
 
 }
 
-static int cp210x_tiocmset (struct tty_struct *tty, struct file *file,
+static int cp210x_tiocmset (struct tty_struct *tty,
 		unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
-	return cp210x_tiocmset_port(port, file, set, clear);
+	return cp210x_tiocmset_port(port, set, clear);
 }
 
-static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *file,
+static int cp210x_tiocmset_port(struct usb_serial_port *port,
 		unsigned int set, unsigned int clear)
 {
 	unsigned int control = 0;
@@ -737,9 +736,9 @@ static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *file,
 static void cp210x_dtr_rts(struct usb_serial_port *p, int on)
 {
 	if (on)
-		cp210x_tiocmset_port(p, NULL,  TIOCM_DTR|TIOCM_RTS, 0);
+		cp210x_tiocmset_port(p, TIOCM_DTR|TIOCM_RTS, 0);
 	else
-		cp210x_tiocmset_port(p, NULL,  0, TIOCM_DTR|TIOCM_RTS);
+		cp210x_tiocmset_port(p, 0, TIOCM_DTR|TIOCM_RTS);
 }
 
 static int cp210x_tiocmget (struct tty_struct *tty)
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index 9c96cff691fd..2beb5a66180d 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -174,7 +174,7 @@ static int  cypress_ioctl(struct tty_struct *tty, struct file *file,
 static void cypress_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static int  cypress_tiocmget(struct tty_struct *tty);
-static int  cypress_tiocmset(struct tty_struct *tty, struct file *file,
+static int  cypress_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 static int  cypress_chars_in_buffer(struct tty_struct *tty);
 static void cypress_throttle(struct tty_struct *tty);
@@ -892,7 +892,7 @@ static int cypress_tiocmget(struct tty_struct *tty)
 }
 
 
-static int cypress_tiocmset(struct tty_struct *tty, struct file *file,
+static int cypress_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index 08da46cb5825..86fbba6336c9 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -446,10 +446,10 @@ static void digi_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios);
 static void digi_break_ctl(struct tty_struct *tty, int break_state);
 static int digi_tiocmget(struct tty_struct *tty);
-static int digi_tiocmset(struct tty_struct *tty, struct file *file,
-	unsigned int set, unsigned int clear);
+static int digi_tiocmset(struct tty_struct *tty, unsigned int set,
+		unsigned int clear);
 static int digi_write(struct tty_struct *tty, struct usb_serial_port *port,
-	const unsigned char *buf, int count);
+		const unsigned char *buf, int count);
 static void digi_write_bulk_callback(struct urb *urb);
 static int digi_write_room(struct tty_struct *tty);
 static int digi_chars_in_buffer(struct tty_struct *tty);
@@ -1134,8 +1134,8 @@ static int digi_tiocmget(struct tty_struct *tty)
 }
 
 
-static int digi_tiocmset(struct tty_struct *tty, struct file *file,
-	unsigned int set, unsigned int clear)
+static int digi_tiocmset(struct tty_struct *tty,
+					unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct digi_port *priv = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 281d18141051..f521ab1eb60f 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -857,7 +857,7 @@ static int ftdi_prepare_write_buffer(struct usb_serial_port *port,
 static void ftdi_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static int  ftdi_tiocmget(struct tty_struct *tty);
-static int  ftdi_tiocmset(struct tty_struct *tty, struct file *file,
+static int  ftdi_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 static int  ftdi_ioctl(struct tty_struct *tty, struct file *file,
 			unsigned int cmd, unsigned long arg);
@@ -2202,7 +2202,7 @@ out:
 	return ret;
 }
 
-static int ftdi_tiocmset(struct tty_struct *tty, struct file *file,
+static int ftdi_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index e8fe4dcf72f0..0b8846e27a79 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -220,7 +220,7 @@ static int  edge_ioctl(struct tty_struct *tty, struct file *file,
 					unsigned int cmd, unsigned long arg);
 static void edge_break(struct tty_struct *tty, int break_state);
 static int  edge_tiocmget(struct tty_struct *tty);
-static int  edge_tiocmset(struct tty_struct *tty, struct file *file,
+static int  edge_tiocmset(struct tty_struct *tty,
 					unsigned int set, unsigned int clear);
 static int  edge_get_icount(struct tty_struct *tty,
 				struct serial_icounter_struct *icount);
@@ -1568,7 +1568,7 @@ static int get_lsr_info(struct edgeport_port *edge_port,
 	return 0;
 }
 
-static int edge_tiocmset(struct tty_struct *tty, struct file *file,
+static int edge_tiocmset(struct tty_struct *tty,
 					unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 7cb9f5cb91f3..88120523710b 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -2444,7 +2444,7 @@ static void edge_set_termios(struct tty_struct *tty,
 	change_port_settings(tty, edge_port, old_termios);
 }
 
-static int edge_tiocmset(struct tty_struct *tty, struct file *file,
+static int edge_tiocmset(struct tty_struct *tty,
 					unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index 1d96142f135a..6aca631a407a 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -150,7 +150,7 @@ static void iuu_release(struct usb_serial *serial)
 	}
 }
 
-static int iuu_tiocmset(struct tty_struct *tty, struct file *file,
+static int iuu_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 1beebbb7a20a..c6e968f24e04 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -317,7 +317,7 @@ static int keyspan_tiocmget(struct tty_struct *tty)
 	return value;
 }
 
-static int keyspan_tiocmset(struct tty_struct *tty, struct file *file,
+static int keyspan_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/keyspan.h b/drivers/usb/serial/keyspan.h
index 5e5fc71e68df..13fa1d1cc900 100644
--- a/drivers/usb/serial/keyspan.h
+++ b/drivers/usb/serial/keyspan.h
@@ -60,7 +60,7 @@ static void keyspan_break_ctl		(struct tty_struct *tty,
 					 int break_state);
 static int  keyspan_tiocmget		(struct tty_struct *tty);
 static int  keyspan_tiocmset		(struct tty_struct *tty,
-					 struct file *file, unsigned int set,
+					 unsigned int set,
 					 unsigned int clear);
 static int  keyspan_fake_startup	(struct usb_serial *serial);
 
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index 49ad2baf77cd..207caabdc4ff 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -478,7 +478,7 @@ static int keyspan_pda_tiocmget(struct tty_struct *tty)
 	return value;
 }
 
-static int keyspan_pda_tiocmset(struct tty_struct *tty, struct file *file,
+static int keyspan_pda_tiocmset(struct tty_struct *tty,
 				unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c
index a570f5201c73..19373cb7c5bf 100644
--- a/drivers/usb/serial/kl5kusb105.c
+++ b/drivers/usb/serial/kl5kusb105.c
@@ -69,7 +69,7 @@ static void klsi_105_close(struct usb_serial_port *port);
 static void klsi_105_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static int  klsi_105_tiocmget(struct tty_struct *tty);
-static int  klsi_105_tiocmset(struct tty_struct *tty, struct file *file,
+static int  klsi_105_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 static void klsi_105_process_read_urb(struct urb *urb);
 static int klsi_105_prepare_write_buffer(struct usb_serial_port *port,
@@ -661,7 +661,7 @@ static int klsi_105_tiocmget(struct tty_struct *tty)
 	return (int)line_state;
 }
 
-static int klsi_105_tiocmset(struct tty_struct *tty, struct file *file,
+static int klsi_105_tiocmset(struct tty_struct *tty,
 			     unsigned int set, unsigned int clear)
 {
 	int retval = -EINVAL;
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index 81d07fb299b8..22cd0c08f46f 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -78,7 +78,7 @@ static int  kobil_write_room(struct tty_struct *tty);
 static int  kobil_ioctl(struct tty_struct *tty, struct file *file,
 			unsigned int cmd, unsigned long arg);
 static int  kobil_tiocmget(struct tty_struct *tty);
-static int  kobil_tiocmset(struct tty_struct *tty, struct file *file,
+static int  kobil_tiocmset(struct tty_struct *tty,
 			   unsigned int set, unsigned int clear);
 static void kobil_read_int_callback(struct urb *urb);
 static void kobil_write_callback(struct urb *purb);
@@ -544,7 +544,7 @@ static int kobil_tiocmget(struct tty_struct *tty)
 	return result;
 }
 
-static int kobil_tiocmset(struct tty_struct *tty, struct file *file,
+static int kobil_tiocmset(struct tty_struct *tty,
 			   unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c
index 27447095feae..ef49902c5a51 100644
--- a/drivers/usb/serial/mct_u232.c
+++ b/drivers/usb/serial/mct_u232.c
@@ -102,7 +102,7 @@ static void mct_u232_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static void mct_u232_break_ctl(struct tty_struct *tty, int break_state);
 static int  mct_u232_tiocmget(struct tty_struct *tty);
-static int  mct_u232_tiocmset(struct tty_struct *tty, struct file *file,
+static int  mct_u232_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 static void mct_u232_throttle(struct tty_struct *tty);
 static void mct_u232_unthrottle(struct tty_struct *tty);
@@ -778,7 +778,7 @@ static int mct_u232_tiocmget(struct tty_struct *tty)
 	return control_state;
 }
 
-static int mct_u232_tiocmset(struct tty_struct *tty, struct file *file,
+static int mct_u232_tiocmset(struct tty_struct *tty,
 			      unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 5d40d4151b5a..95b1c64cac03 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -1858,7 +1858,7 @@ static int mos7720_tiocmget(struct tty_struct *tty)
 	return result;
 }
 
-static int mos7720_tiocmset(struct tty_struct *tty, struct file *file,
+static int mos7720_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index ee0dc9a0890c..9424178c6689 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -1674,7 +1674,7 @@ static int mos7840_tiocmget(struct tty_struct *tty)
 	return result;
 }
 
-static int mos7840_tiocmset(struct tty_struct *tty, struct file *file,
+static int mos7840_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c
index 4cd3b0ef4e61..63734cb0fb0f 100644
--- a/drivers/usb/serial/oti6858.c
+++ b/drivers/usb/serial/oti6858.c
@@ -145,7 +145,7 @@ static int oti6858_write(struct tty_struct *tty, struct usb_serial_port *port,
 static int oti6858_write_room(struct tty_struct *tty);
 static int oti6858_chars_in_buffer(struct tty_struct *tty);
 static int oti6858_tiocmget(struct tty_struct *tty);
-static int oti6858_tiocmset(struct tty_struct *tty, struct file *file,
+static int oti6858_tiocmset(struct tty_struct *tty,
 				unsigned int set, unsigned int clear);
 static int oti6858_startup(struct usb_serial *serial);
 static void oti6858_release(struct usb_serial *serial);
@@ -624,7 +624,7 @@ static void oti6858_close(struct usb_serial_port *port)
 	usb_kill_urb(port->interrupt_in_urb);
 }
 
-static int oti6858_tiocmset(struct tty_struct *tty, struct file *file,
+static int oti6858_tiocmset(struct tty_struct *tty,
 				unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 6cb4f503a3f1..b797992fa54b 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -505,7 +505,7 @@ static int pl2303_open(struct tty_struct *tty, struct usb_serial_port *port)
 	return 0;
 }
 
-static int pl2303_tiocmset(struct tty_struct *tty, struct file *file,
+static int pl2303_tiocmset(struct tty_struct *tty,
 			   unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 66437f1e9e5b..79ee6c79ad54 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -408,7 +408,7 @@ static int sierra_tiocmget(struct tty_struct *tty)
 	return value;
 }
 
-static int sierra_tiocmset(struct tty_struct *tty, struct file *file,
+static int sierra_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index cac13009fc5c..dfbc543e0db8 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -595,7 +595,7 @@ static int spcp8x5_ioctl(struct tty_struct *tty, struct file *file,
 	return -ENOIOCTLCMD;
 }
 
-static int spcp8x5_tiocmset(struct tty_struct *tty, struct file *file,
+static int spcp8x5_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index b21583fa825c..abceee9d3af9 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -517,7 +517,7 @@ mget_out:
 	return r;
 }
 
-static int ssu100_tiocmset(struct tty_struct *tty, struct file *file,
+static int ssu100_tiocmset(struct tty_struct *tty,
 			   unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 223e60e31735..c7fea4a2a1be 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -113,7 +113,7 @@ static int ti_get_icount(struct tty_struct *tty,
 static void ti_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios);
 static int ti_tiocmget(struct tty_struct *tty);
-static int ti_tiocmset(struct tty_struct *tty, struct file *file,
+static int ti_tiocmset(struct tty_struct *tty,
 		unsigned int set, unsigned int clear);
 static void ti_break(struct tty_struct *tty, int break_state);
 static void ti_interrupt_callback(struct urb *urb);
@@ -1033,8 +1033,8 @@ static int ti_tiocmget(struct tty_struct *tty)
 }
 
 
-static int ti_tiocmset(struct tty_struct *tty, struct file *file,
-	unsigned int set, unsigned int clear)
+static int ti_tiocmset(struct tty_struct *tty,
+				unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	struct ti_port *tport = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index df105c6531a1..dab679e5b7ea 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -507,7 +507,7 @@ static int serial_tiocmget(struct tty_struct *tty)
 	return -EINVAL;
 }
 
-static int serial_tiocmset(struct tty_struct *tty, struct file *file,
+static int serial_tiocmset(struct tty_struct *tty,
 			    unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
@@ -515,7 +515,7 @@ static int serial_tiocmset(struct tty_struct *tty, struct file *file,
 	dbg("%s - port %d", __func__, port->number);
 
 	if (port->serial->type->tiocmset)
-		return port->serial->type->tiocmset(tty, file, set, clear);
+		return port->serial->type->tiocmset(tty, set, clear);
 	return -EINVAL;
 }
 
diff --git a/drivers/usb/serial/usb-wwan.h b/drivers/usb/serial/usb-wwan.h
index 8b68fc783d5f..4d65f1c8dd93 100644
--- a/drivers/usb/serial/usb-wwan.h
+++ b/drivers/usb/serial/usb-wwan.h
@@ -16,7 +16,7 @@ extern void usb_wwan_set_termios(struct tty_struct *tty,
 				 struct usb_serial_port *port,
 				 struct ktermios *old);
 extern int usb_wwan_tiocmget(struct tty_struct *tty);
-extern int usb_wwan_tiocmset(struct tty_struct *tty, struct file *file,
+extern int usb_wwan_tiocmset(struct tty_struct *tty,
 			     unsigned int set, unsigned int clear);
 extern int usb_wwan_ioctl(struct tty_struct *tty, struct file *file,
 			  unsigned int cmd, unsigned long arg);
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index 60f942632cb4..b72912027ae8 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -98,7 +98,7 @@ int usb_wwan_tiocmget(struct tty_struct *tty)
 }
 EXPORT_SYMBOL(usb_wwan_tiocmget);
 
-int usb_wwan_tiocmset(struct tty_struct *tty, struct file *file,
+int usb_wwan_tiocmset(struct tty_struct *tty,
 		      unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index bf850139e0b8..6e0c397e869f 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -157,7 +157,7 @@ static int  whiteheat_ioctl(struct tty_struct *tty, struct file *file,
 static void whiteheat_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static int  whiteheat_tiocmget(struct tty_struct *tty);
-static int  whiteheat_tiocmset(struct tty_struct *tty, struct file *file,
+static int  whiteheat_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 static void whiteheat_break_ctl(struct tty_struct *tty, int break_state);
 static int  whiteheat_chars_in_buffer(struct tty_struct *tty);
@@ -850,7 +850,7 @@ static int whiteheat_tiocmget(struct tty_struct *tty)
 	return modem_signals;
 }
 
-static int whiteheat_tiocmset(struct tty_struct *tty, struct file *file,
+static int whiteheat_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 9539d74171db..5dabaa2e6da3 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -272,7 +272,7 @@ struct tty_operations {
 	void (*wait_until_sent)(struct tty_struct *tty, int timeout);
 	void (*send_xchar)(struct tty_struct *tty, char ch);
 	int (*tiocmget)(struct tty_struct *tty);
-	int (*tiocmset)(struct tty_struct *tty, struct file *file,
+	int (*tiocmset)(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 	int (*resize)(struct tty_struct *tty, struct winsize *ws);
 	int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew);
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 30b945397d19..c1aa1b243ba3 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -269,7 +269,7 @@ struct usb_serial_driver {
 	void (*throttle)(struct tty_struct *tty);
 	void (*unthrottle)(struct tty_struct *tty);
 	int  (*tiocmget)(struct tty_struct *tty);
-	int  (*tiocmset)(struct tty_struct *tty, struct file *file,
+	int  (*tiocmset)(struct tty_struct *tty,
 			 unsigned int set, unsigned int clear);
 	int  (*get_icount)(struct tty_struct *tty,
 			struct serial_icounter_struct *icount);
diff --git a/include/net/irda/ircomm_tty.h b/include/net/irda/ircomm_tty.h
index fa3793b5392d..980ccb66e1b4 100644
--- a/include/net/irda/ircomm_tty.h
+++ b/include/net/irda/ircomm_tty.h
@@ -121,7 +121,7 @@ void ircomm_tty_start(struct tty_struct *tty);
 void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self);
 
 extern int ircomm_tty_tiocmget(struct tty_struct *tty);
-extern int ircomm_tty_tiocmset(struct tty_struct *tty, struct file *file,
+extern int ircomm_tty_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear);
 extern int ircomm_tty_ioctl(struct tty_struct *tty, struct file *file, 
 			    unsigned int cmd, unsigned long arg);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 7f67fa4f2f5e..8e78e7447726 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -1098,7 +1098,7 @@ static int rfcomm_tty_tiocmget(struct tty_struct *tty)
 	return dev->modem_status;
 }
 
-static int rfcomm_tty_tiocmset(struct tty_struct *tty, struct file *filp, unsigned int set, unsigned int clear)
+static int rfcomm_tty_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 {
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
 	struct rfcomm_dlc *dlc = dev->dlc;
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index bb47caeba7e6..5e0e718c930a 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -214,12 +214,12 @@ int ircomm_tty_tiocmget(struct tty_struct *tty)
 }
 
 /*
- * Function ircomm_tty_tiocmset (tty, file, set, clear)
+ * Function ircomm_tty_tiocmset (tty, set, clear)
  *
  *
  *
  */
-int ircomm_tty_tiocmset(struct tty_struct *tty, struct file *file,
+int ircomm_tty_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
-- 
cgit v1.2.3


From 00a0d0d65b61241a718d0aee96f46b9a2d93bf26 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@linux.intel.com>
Date: Mon, 14 Feb 2011 16:27:06 +0000
Subject: tty: remove filp from the USB tty ioctls

We don't use it so we can trim it from here as we try and stamp the file
object dependencies out of the serial code.

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/staging/quatech_usb2/quatech_usb2.c | 2 +-
 drivers/staging/serqt_usb2/serqt_usb2.c     | 2 +-
 drivers/usb/serial/ark3116.c                | 2 +-
 drivers/usb/serial/ch341.c                  | 3 +--
 drivers/usb/serial/cypress_m8.c             | 4 ++--
 drivers/usb/serial/ftdi_sio.c               | 4 ++--
 drivers/usb/serial/io_edgeport.c            | 4 ++--
 drivers/usb/serial/io_ti.c                  | 2 +-
 drivers/usb/serial/kobil_sct.c              | 4 ++--
 drivers/usb/serial/mos7720.c                | 2 +-
 drivers/usb/serial/mos7840.c                | 2 +-
 drivers/usb/serial/opticon.c                | 2 +-
 drivers/usb/serial/oti6858.c                | 4 ++--
 drivers/usb/serial/pl2303.c                 | 2 +-
 drivers/usb/serial/spcp8x5.c                | 2 +-
 drivers/usb/serial/ssu100.c                 | 2 +-
 drivers/usb/serial/ti_usb_3410_5052.c       | 4 ++--
 drivers/usb/serial/usb-serial.c             | 2 +-
 drivers/usb/serial/usb-wwan.h               | 2 +-
 drivers/usb/serial/usb_wwan.c               | 2 +-
 drivers/usb/serial/whiteheat.c              | 4 ++--
 include/linux/usb/serial.h                  | 2 +-
 22 files changed, 29 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/quatech_usb2/quatech_usb2.c b/drivers/staging/quatech_usb2/quatech_usb2.c
index 3734448d1b82..36b18e302718 100644
--- a/drivers/staging/quatech_usb2/quatech_usb2.c
+++ b/drivers/staging/quatech_usb2/quatech_usb2.c
@@ -852,7 +852,7 @@ static int qt2_chars_in_buffer(struct tty_struct *tty)
  * TIOCMGET and TIOCMSET are filtered off to their own methods before they get
  * here, so we don't have to handle them.
  */
-static int qt2_ioctl(struct tty_struct *tty, struct file *file,
+static int qt2_ioctl(struct tty_struct *tty,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index 39776c1cf10f..e0aae86a8809 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -1191,7 +1191,7 @@ static int qt_write_room(struct tty_struct *tty)
 
 }
 
-static int qt_ioctl(struct tty_struct *tty, struct file *file,
+static int qt_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c
index 2f837e983339..5cdb9d912275 100644
--- a/drivers/usb/serial/ark3116.c
+++ b/drivers/usb/serial/ark3116.c
@@ -431,7 +431,7 @@ static int ark3116_get_icount(struct tty_struct *tty,
 	return 0;
 }
 
-static int ark3116_ioctl(struct tty_struct *tty, struct file *file,
+static int ark3116_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 5cbef313281e..d0b9feac5dc3 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -552,8 +552,7 @@ static int wait_modem_info(struct usb_serial_port *port, unsigned int arg)
 	return 0;
 }
 
-/*static int ch341_ioctl(struct usb_serial_port *port, struct file *file,*/
-static int ch341_ioctl(struct tty_struct *tty, struct file *file,
+static int ch341_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index 2beb5a66180d..987e9bf7bd02 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -169,7 +169,7 @@ static int  cypress_write(struct tty_struct *tty, struct usb_serial_port *port,
 			const unsigned char *buf, int count);
 static void cypress_send(struct usb_serial_port *port);
 static int  cypress_write_room(struct tty_struct *tty);
-static int  cypress_ioctl(struct tty_struct *tty, struct file *file,
+static int  cypress_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg);
 static void cypress_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
@@ -917,7 +917,7 @@ static int cypress_tiocmset(struct tty_struct *tty,
 }
 
 
-static int cypress_ioctl(struct tty_struct *tty, struct file *file,
+static int cypress_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index f521ab1eb60f..e3e23a4e227d 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -859,7 +859,7 @@ static void ftdi_set_termios(struct tty_struct *tty,
 static int  ftdi_tiocmget(struct tty_struct *tty);
 static int  ftdi_tiocmset(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
-static int  ftdi_ioctl(struct tty_struct *tty, struct file *file,
+static int  ftdi_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg);
 static void ftdi_break_ctl(struct tty_struct *tty, int break_state);
 
@@ -2210,7 +2210,7 @@ static int ftdi_tiocmset(struct tty_struct *tty,
 	return update_mctrl(port, set, clear);
 }
 
-static int ftdi_ioctl(struct tty_struct *tty, struct file *file,
+static int ftdi_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index 0b8846e27a79..ae91bcdcb2bc 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -216,7 +216,7 @@ static void edge_unthrottle(struct tty_struct *tty);
 static void edge_set_termios(struct tty_struct *tty,
 					struct usb_serial_port *port,
 					struct ktermios *old_termios);
-static int  edge_ioctl(struct tty_struct *tty, struct file *file,
+static int  edge_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg);
 static void edge_break(struct tty_struct *tty, int break_state);
 static int  edge_tiocmget(struct tty_struct *tty);
@@ -1679,7 +1679,7 @@ static int get_serial_info(struct edgeport_port *edge_port,
  * SerialIoctl
  *	this function handles any ioctl calls to the driver
  *****************************************************************************/
-static int edge_ioctl(struct tty_struct *tty, struct file *file,
+static int edge_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 88120523710b..d8434910fa7b 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -2552,7 +2552,7 @@ static int get_serial_info(struct edgeport_port *edge_port,
 	return 0;
 }
 
-static int edge_ioctl(struct tty_struct *tty, struct file *file,
+static int edge_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index 22cd0c08f46f..667863ef0625 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -75,7 +75,7 @@ static void kobil_close(struct usb_serial_port *port);
 static int  kobil_write(struct tty_struct *tty, struct usb_serial_port *port,
 			 const unsigned char *buf, int count);
 static int  kobil_write_room(struct tty_struct *tty);
-static int  kobil_ioctl(struct tty_struct *tty, struct file *file,
+static int  kobil_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg);
 static int  kobil_tiocmget(struct tty_struct *tty);
 static int  kobil_tiocmset(struct tty_struct *tty,
@@ -668,7 +668,7 @@ static void kobil_set_termios(struct tty_struct *tty,
 		);
 }
 
-static int kobil_ioctl(struct tty_struct *tty, struct file *file,
+static int kobil_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 95b1c64cac03..d8b3e8fa14e9 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -1987,7 +1987,7 @@ static int get_serial_info(struct moschip_port *mos7720_port,
 	return 0;
 }
 
-static int mos7720_ioctl(struct tty_struct *tty, struct file *file,
+static int mos7720_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 9424178c6689..7b50aa122752 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -2235,7 +2235,7 @@ static int mos7840_get_icount(struct tty_struct *tty,
  *	this function handles any ioctl calls to the driver
  *****************************************************************************/
 
-static int mos7840_ioctl(struct tty_struct *tty, struct file *file,
+static int mos7840_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index e305df807396..8d603a1ca2eb 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -396,7 +396,7 @@ static int get_serial_info(struct opticon_private *priv,
 	return 0;
 }
 
-static int opticon_ioctl(struct tty_struct *tty, struct file *file,
+static int opticon_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c
index 63734cb0fb0f..4c29e6c2bda7 100644
--- a/drivers/usb/serial/oti6858.c
+++ b/drivers/usb/serial/oti6858.c
@@ -135,7 +135,7 @@ static void oti6858_close(struct usb_serial_port *port);
 static void oti6858_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static void oti6858_init_termios(struct tty_struct *tty);
-static int oti6858_ioctl(struct tty_struct *tty, struct file *file,
+static int oti6858_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg);
 static void oti6858_read_int_callback(struct urb *urb);
 static void oti6858_read_bulk_callback(struct urb *urb);
@@ -728,7 +728,7 @@ static int wait_modem_info(struct usb_serial_port *port, unsigned int arg)
 	return 0;
 }
 
-static int oti6858_ioctl(struct tty_struct *tty, struct file *file,
+static int oti6858_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index b797992fa54b..30461fcc2206 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -606,7 +606,7 @@ static int wait_modem_info(struct usb_serial_port *port, unsigned int arg)
 	return 0;
 }
 
-static int pl2303_ioctl(struct tty_struct *tty, struct file *file,
+static int pl2303_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg)
 {
 	struct serial_struct ser;
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index dfbc543e0db8..180ea6c7911c 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -576,7 +576,7 @@ static int spcp8x5_wait_modem_info(struct usb_serial_port *port,
 	return 0;
 }
 
-static int spcp8x5_ioctl(struct tty_struct *tty, struct file *file,
+static int spcp8x5_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index abceee9d3af9..87362e48796e 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -439,7 +439,7 @@ static int ssu100_get_icount(struct tty_struct *tty,
 
 
 
-static int ssu100_ioctl(struct tty_struct *tty, struct file *file,
+static int ssu100_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index c7fea4a2a1be..f4a57ad27db8 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -106,7 +106,7 @@ static int ti_write_room(struct tty_struct *tty);
 static int ti_chars_in_buffer(struct tty_struct *tty);
 static void ti_throttle(struct tty_struct *tty);
 static void ti_unthrottle(struct tty_struct *tty);
-static int ti_ioctl(struct tty_struct *tty, struct file *file,
+static int ti_ioctl(struct tty_struct *tty,
 		unsigned int cmd, unsigned long arg);
 static int ti_get_icount(struct tty_struct *tty,
 		struct serial_icounter_struct *icount);
@@ -818,7 +818,7 @@ static int ti_get_icount(struct tty_struct *tty,
 	return 0;
 }
 
-static int ti_ioctl(struct tty_struct *tty, struct file *file,
+static int ti_ioctl(struct tty_struct *tty,
 	unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index dab679e5b7ea..b1110e136c33 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -417,7 +417,7 @@ static int serial_ioctl(struct tty_struct *tty, struct file *file,
 	/* pass on to the driver specific version of this function
 	   if it is available */
 	if (port->serial->type->ioctl) {
-		retval = port->serial->type->ioctl(tty, file, cmd, arg);
+		retval = port->serial->type->ioctl(tty, cmd, arg);
 	} else
 		retval = -ENOIOCTLCMD;
 	return retval;
diff --git a/drivers/usb/serial/usb-wwan.h b/drivers/usb/serial/usb-wwan.h
index 4d65f1c8dd93..c47b6ec03063 100644
--- a/drivers/usb/serial/usb-wwan.h
+++ b/drivers/usb/serial/usb-wwan.h
@@ -18,7 +18,7 @@ extern void usb_wwan_set_termios(struct tty_struct *tty,
 extern int usb_wwan_tiocmget(struct tty_struct *tty);
 extern int usb_wwan_tiocmset(struct tty_struct *tty,
 			     unsigned int set, unsigned int clear);
-extern int usb_wwan_ioctl(struct tty_struct *tty, struct file *file,
+extern int usb_wwan_ioctl(struct tty_struct *tty,
 			  unsigned int cmd, unsigned long arg);
 extern int usb_wwan_send_setup(struct usb_serial_port *port);
 extern int usb_wwan_write(struct tty_struct *tty, struct usb_serial_port *port,
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index b72912027ae8..b38d77b389d4 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -178,7 +178,7 @@ static int set_serial_info(struct usb_serial_port *port,
 	return retval;
 }
 
-int usb_wwan_ioctl(struct tty_struct *tty, struct file *file,
+int usb_wwan_ioctl(struct tty_struct *tty,
 		   unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 6e0c397e869f..5b073bcc807b 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -152,7 +152,7 @@ static int  whiteheat_write(struct tty_struct *tty,
 			struct usb_serial_port *port,
 			const unsigned char *buf, int count);
 static int  whiteheat_write_room(struct tty_struct *tty);
-static int  whiteheat_ioctl(struct tty_struct *tty, struct file *file,
+static int  whiteheat_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg);
 static void whiteheat_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
@@ -874,7 +874,7 @@ static int whiteheat_tiocmset(struct tty_struct *tty,
 }
 
 
-static int whiteheat_ioctl(struct tty_struct *tty, struct file *file,
+static int whiteheat_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index c1aa1b243ba3..00e98ee5fba0 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -260,7 +260,7 @@ struct usb_serial_driver {
 			const unsigned char *buf, int count);
 	/* Called only by the tty layer */
 	int  (*write_room)(struct tty_struct *tty);
-	int  (*ioctl)(struct tty_struct *tty, struct file *file,
+	int  (*ioctl)(struct tty_struct *tty,
 		      unsigned int cmd, unsigned long arg);
 	void (*set_termios)(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
-- 
cgit v1.2.3


From 6caa76b7786891b42b66a0e61e2c2fff2c884620 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@linux.intel.com>
Date: Mon, 14 Feb 2011 16:27:22 +0000
Subject: tty: now phase out the ioctl file pointer for good

Only oddities here are a couple of drivers that bogusly called the ldisc
helpers instead of returning -ENOIOCTLCMD. Fix the bug and the rest goes
away.

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/char/amiserial.c             |  2 +-
 drivers/char/cyclades.c              |  2 +-
 drivers/char/epca.c                  |  8 ++++----
 drivers/char/ip2/ip2main.c           |  4 ++--
 drivers/char/isicom.c                |  2 +-
 drivers/char/istallion.c             |  4 ++--
 drivers/char/moxa.c                  |  2 +-
 drivers/char/mxser.c                 |  2 +-
 drivers/char/nozomi.c                |  2 +-
 drivers/char/pcmcia/ipwireless/tty.c |  4 ++--
 drivers/char/riscom8.c               |  2 +-
 drivers/char/rocket.c                |  2 +-
 drivers/char/ser_a2232.c             |  6 +++---
 drivers/char/serial167.c             |  2 +-
 drivers/char/specialix.c             |  2 +-
 drivers/char/stallion.c              |  5 ++---
 drivers/char/sx.c                    |  2 +-
 drivers/char/synclink.c              |  3 +--
 drivers/char/synclink_gt.c           |  9 ++++-----
 drivers/char/synclinkmp.c            |  5 ++---
 drivers/char/ttyprintk.c             |  2 +-
 drivers/char/vme_scc.c               |  4 ++--
 drivers/isdn/capi/capi.c             | 10 ++--------
 drivers/isdn/gigaset/interface.c     |  4 ++--
 drivers/isdn/i4l/isdn_tty.c          |  3 +--
 drivers/net/usb/hso.c                |  2 +-
 drivers/tty/n_gsm.c                  |  2 +-
 drivers/tty/pty.c                    |  4 ++--
 drivers/tty/serial/68328serial.c     |  2 +-
 drivers/tty/serial/68360serial.c     |  2 +-
 drivers/tty/serial/crisv10.c         |  2 +-
 drivers/tty/serial/serial_core.c     |  4 ++--
 drivers/tty/tty_io.c                 |  4 ++--
 drivers/tty/vt/vt_ioctl.c            |  6 +++---
 drivers/usb/class/cdc-acm.c          |  2 +-
 drivers/usb/serial/usb-serial.c      |  2 +-
 include/linux/tty.h                  |  2 +-
 include/linux/tty_driver.h           |  9 ++++-----
 include/net/irda/ircomm_tty.h        |  2 +-
 net/bluetooth/rfcomm/tty.c           |  2 +-
 net/irda/ircomm/ircomm_tty_ioctl.c   |  4 ++--
 41 files changed, 66 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c
index 5c15fad71ad2..f214e5022472 100644
--- a/drivers/char/amiserial.c
+++ b/drivers/char/amiserial.c
@@ -1293,7 +1293,7 @@ static int rs_get_icount(struct tty_struct *tty,
 	return 0;
 }
 
-static int rs_ioctl(struct tty_struct *tty, struct file * file,
+static int rs_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct async_struct * info = tty->driver_data;
diff --git a/drivers/char/cyclades.c b/drivers/char/cyclades.c
index 942b6f2b70a4..c99728f0cd9f 100644
--- a/drivers/char/cyclades.c
+++ b/drivers/char/cyclades.c
@@ -2680,7 +2680,7 @@ static int cy_cflags_changed(struct cyclades_port *info, unsigned long arg,
  * not recognized by the driver, it should return ENOIOCTLCMD.
  */
 static int
-cy_ioctl(struct tty_struct *tty, struct file *file,
+cy_ioctl(struct tty_struct *tty,
 	 unsigned int cmd, unsigned long arg)
 {
 	struct cyclades_port *info = tty->driver_data;
diff --git a/drivers/char/epca.c b/drivers/char/epca.c
index e5872b59f9cd..7ad3638967ae 100644
--- a/drivers/char/epca.c
+++ b/drivers/char/epca.c
@@ -175,9 +175,9 @@ static unsigned termios2digi_i(struct channel *ch, unsigned);
 static unsigned termios2digi_c(struct channel *ch, unsigned);
 static void epcaparam(struct tty_struct *, struct channel *);
 static void receive_data(struct channel *, struct tty_struct *tty);
-static int pc_ioctl(struct tty_struct *, struct file *,
+static int pc_ioctl(struct tty_struct *,
 			unsigned int, unsigned long);
-static int info_ioctl(struct tty_struct *, struct file *,
+static int info_ioctl(struct tty_struct *,
 			unsigned int, unsigned long);
 static void pc_set_termios(struct tty_struct *, struct ktermios *);
 static void do_softint(struct work_struct *work);
@@ -1919,7 +1919,7 @@ static void receive_data(struct channel *ch, struct tty_struct *tty)
 	tty_schedule_flip(tty);
 }
 
-static int info_ioctl(struct tty_struct *tty, struct file *file,
+static int info_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -2057,7 +2057,7 @@ static int pc_tiocmset(struct tty_struct *tty,
 	return 0;
 }
 
-static int pc_ioctl(struct tty_struct *tty, struct file *file,
+static int pc_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	digiflow_t dflow;
diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c
index d5f866c7c672..ea7a8fb08283 100644
--- a/drivers/char/ip2/ip2main.c
+++ b/drivers/char/ip2/ip2main.c
@@ -173,7 +173,7 @@ static void ip2_flush_chars(PTTY);
 static int  ip2_write_room(PTTY);
 static int  ip2_chars_in_buf(PTTY);
 static void ip2_flush_buffer(PTTY);
-static int  ip2_ioctl(PTTY, struct file *, UINT, ULONG);
+static int  ip2_ioctl(PTTY, UINT, ULONG);
 static void ip2_set_termios(PTTY, struct ktermios *);
 static void ip2_set_line_discipline(PTTY);
 static void ip2_throttle(PTTY);
@@ -2127,7 +2127,7 @@ static int ip2_tiocmset(struct tty_struct *tty,
 /*                                                                            */
 /******************************************************************************/
 static int
-ip2_ioctl ( PTTY tty, struct file *pFile, UINT cmd, ULONG arg )
+ip2_ioctl ( PTTY tty, UINT cmd, ULONG arg )
 {
 	wait_queue_t wait;
 	i2ChanStrPtr pCh = DevTable[tty->index];
diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c
index 60f4d8ae7a49..db1cf9c328d8 100644
--- a/drivers/char/isicom.c
+++ b/drivers/char/isicom.c
@@ -1167,7 +1167,7 @@ static int isicom_get_serial_info(struct isi_port *port,
 	return 0;
 }
 
-static int isicom_ioctl(struct tty_struct *tty, struct file *filp,
+static int isicom_ioctl(struct tty_struct *tty,
 	unsigned int cmd, unsigned long arg)
 {
 	struct isi_port *port = tty->driver_data;
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index 763b58d58255..0b266272cccd 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -603,7 +603,7 @@ static int	stli_putchar(struct tty_struct *tty, unsigned char ch);
 static void	stli_flushchars(struct tty_struct *tty);
 static int	stli_writeroom(struct tty_struct *tty);
 static int	stli_charsinbuffer(struct tty_struct *tty);
-static int	stli_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg);
+static int	stli_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg);
 static void	stli_settermios(struct tty_struct *tty, struct ktermios *old);
 static void	stli_throttle(struct tty_struct *tty);
 static void	stli_unthrottle(struct tty_struct *tty);
@@ -1556,7 +1556,7 @@ static int stli_tiocmset(struct tty_struct *tty,
 			    sizeof(asysigs_t), 0);
 }
 
-static int stli_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg)
+static int stli_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 {
 	struct stliport *portp;
 	struct stlibrd *brdp;
diff --git a/drivers/char/moxa.c b/drivers/char/moxa.c
index 9f4cd8968a5a..35b0c38590e6 100644
--- a/drivers/char/moxa.c
+++ b/drivers/char/moxa.c
@@ -287,7 +287,7 @@ static void moxa_low_water_check(void __iomem *ofsAddr)
  * TTY operations
  */
 
-static int moxa_ioctl(struct tty_struct *tty, struct file *file,
+static int moxa_ioctl(struct tty_struct *tty,
 		      unsigned int cmd, unsigned long arg)
 {
 	struct moxa_port *ch = tty->driver_data;
diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index 150a862c4989..d188f378684d 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -1655,7 +1655,7 @@ static int mxser_cflags_changed(struct mxser_port *info, unsigned long arg,
 	return ret;
 }
 
-static int mxser_ioctl(struct tty_struct *tty, struct file *file,
+static int mxser_ioctl(struct tty_struct *tty,
 		unsigned int cmd, unsigned long arg)
 {
 	struct mxser_port *info = tty->driver_data;
diff --git a/drivers/char/nozomi.c b/drivers/char/nozomi.c
index 1b74c48c4016..513ba12064ea 100644
--- a/drivers/char/nozomi.c
+++ b/drivers/char/nozomi.c
@@ -1824,7 +1824,7 @@ static int ntty_tiocgicount(struct tty_struct *tty,
 	return 0;
 }
 
-static int ntty_ioctl(struct tty_struct *tty, struct file *file,
+static int ntty_ioctl(struct tty_struct *tty,
 		      unsigned int cmd, unsigned long arg)
 {
 	struct port *port = tty->driver_data;
diff --git a/drivers/char/pcmcia/ipwireless/tty.c b/drivers/char/pcmcia/ipwireless/tty.c
index 748190dfbab0..ef92869502a7 100644
--- a/drivers/char/pcmcia/ipwireless/tty.c
+++ b/drivers/char/pcmcia/ipwireless/tty.c
@@ -425,7 +425,7 @@ ipw_tiocmset(struct tty_struct *linux_tty,
 	return set_control_lines(tty, set, clear);
 }
 
-static int ipw_ioctl(struct tty_struct *linux_tty, struct file *file,
+static int ipw_ioctl(struct tty_struct *linux_tty,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct ipw_tty *tty = linux_tty->driver_data;
@@ -484,7 +484,7 @@ static int ipw_ioctl(struct tty_struct *linux_tty, struct file *file,
 			return tty_perform_flush(linux_tty, arg);
 		}
 	}
-	return tty_mode_ioctl(linux_tty, file, cmd , arg);
+	return -ENOIOCTLCMD;
 }
 
 static int add_tty(int j,
diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c
index 3666decc6438..602643a40b4b 100644
--- a/drivers/char/riscom8.c
+++ b/drivers/char/riscom8.c
@@ -1236,7 +1236,7 @@ static int rc_get_serial_info(struct riscom_port *port,
 	return copy_to_user(retinfo, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
-static int rc_ioctl(struct tty_struct *tty, struct file *filp,
+static int rc_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct riscom_port *port = tty->driver_data;
diff --git a/drivers/char/rocket.c b/drivers/char/rocket.c
index 36c108811a81..3780da8ad12d 100644
--- a/drivers/char/rocket.c
+++ b/drivers/char/rocket.c
@@ -1326,7 +1326,7 @@ static int get_version(struct r_port *info, struct rocket_version __user *retver
 }
 
 /*  IOCTL call handler into the driver */
-static int rp_ioctl(struct tty_struct *tty, struct file *file,
+static int rp_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct r_port *info = tty->driver_data;
diff --git a/drivers/char/ser_a2232.c b/drivers/char/ser_a2232.c
index 9610861d1f5f..3f47c2ead8e5 100644
--- a/drivers/char/ser_a2232.c
+++ b/drivers/char/ser_a2232.c
@@ -133,8 +133,8 @@ static void a2232_hungup(void *ptr);
 /* END GENERIC_SERIAL PROTOTYPES */
 
 /* Functions that the TTY driver struct expects */
-static int  a2232_ioctl(struct tty_struct *tty, struct file *file,
-										unsigned int cmd, unsigned long arg);
+static int  a2232_ioctl(struct tty_struct *tty,
+				unsigned int cmd, unsigned long arg);
 static void a2232_throttle(struct tty_struct *tty);
 static void a2232_unthrottle(struct tty_struct *tty);
 static int  a2232_open(struct tty_struct * tty, struct file * filp);
@@ -447,7 +447,7 @@ static void a2232_hungup(void *ptr)
 /*** END   OF REAL_DRIVER FUNCTIONS ***/
 
 /*** BEGIN  FUNCTIONS EXPECTED BY TTY DRIVER STRUCTS ***/
-static int a2232_ioctl(	struct tty_struct *tty, struct file *file,
+static int a2232_ioctl(	struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg)
 {
 	return -ENOIOCTLCMD;
diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index 89ac542ffff2..674af6933978 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -1492,7 +1492,7 @@ get_default_timeout(struct cyclades_port *info, unsigned long __user * value)
 }
 
 static int
-cy_ioctl(struct tty_struct *tty, struct file *file,
+cy_ioctl(struct tty_struct *tty,
 	 unsigned int cmd, unsigned long arg)
 {
 	struct cyclades_port *info = tty->driver_data;
diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c
index a6b23847e4a7..47e5753f732a 100644
--- a/drivers/char/specialix.c
+++ b/drivers/char/specialix.c
@@ -1928,7 +1928,7 @@ static int sx_get_serial_info(struct specialix_port *port,
 }
 
 
-static int sx_ioctl(struct tty_struct *tty, struct file *filp,
+static int sx_ioctl(struct tty_struct *tty,
 				unsigned int cmd, unsigned long arg)
 {
 	struct specialix_port *port = tty->driver_data;
diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index c42dbffbed16..4fff5cd3b163 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -1132,14 +1132,13 @@ static int stl_tiocmset(struct tty_struct *tty,
 	return 0;
 }
 
-static int stl_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg)
+static int stl_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 {
 	struct stlport	*portp;
 	int		rc;
 	void __user *argp = (void __user *)arg;
 
-	pr_debug("stl_ioctl(tty=%p,file=%p,cmd=%x,arg=%lx)\n", tty, file, cmd,
-			arg);
+	pr_debug("stl_ioctl(tty=%p,cmd=%x,arg=%lx)\n", tty, cmd, arg);
 
 	portp = tty->driver_data;
 	if (portp == NULL)
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index 342c6ae67da5..1291462bcddb 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -1899,7 +1899,7 @@ static int sx_tiocmset(struct tty_struct *tty,
 	return 0;
 }
 
-static int sx_ioctl(struct tty_struct *tty, struct file *filp,
+static int sx_ioctl(struct tty_struct *tty,
 		unsigned int cmd, unsigned long arg)
 {
 	int rc;
diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c
index 691e1094c20b..18888d005a0a 100644
--- a/drivers/char/synclink.c
+++ b/drivers/char/synclink.c
@@ -2962,13 +2962,12 @@ static int msgl_get_icount(struct tty_struct *tty,
  * Arguments:
  * 
  * 	tty	pointer to tty instance data
- * 	file	pointer to associated file object for device
  * 	cmd	IOCTL command code
  * 	arg	command argument/context
  * 	
  * Return Value:	0 if success, otherwise error code
  */
-static int mgsl_ioctl(struct tty_struct *tty, struct file * file,
+static int mgsl_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct mgsl_struct * info = tty->driver_data;
diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c
index 04da6d61dc4f..a35dd549a008 100644
--- a/drivers/char/synclink_gt.c
+++ b/drivers/char/synclink_gt.c
@@ -154,7 +154,7 @@ static void flush_buffer(struct tty_struct *tty);
 static void tx_hold(struct tty_struct *tty);
 static void tx_release(struct tty_struct *tty);
 
-static int  ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg);
+static int  ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg);
 static int  chars_in_buffer(struct tty_struct *tty);
 static void throttle(struct tty_struct * tty);
 static void unthrottle(struct tty_struct * tty);
@@ -1030,13 +1030,12 @@ static void tx_release(struct tty_struct *tty)
  * Arguments
  *
  * 	tty	pointer to tty instance data
- * 	file	pointer to associated file object for device
  * 	cmd	IOCTL command code
  * 	arg	command argument/context
  *
  * Return 0 if success, otherwise error code
  */
-static int ioctl(struct tty_struct *tty, struct file *file,
+static int ioctl(struct tty_struct *tty,
 		 unsigned int cmd, unsigned long arg)
 {
 	struct slgt_info *info = tty->driver_data;
@@ -1200,7 +1199,7 @@ static long set_params32(struct slgt_info *info, struct MGSL_PARAMS32 __user *ne
 	return 0;
 }
 
-static long slgt_compat_ioctl(struct tty_struct *tty, struct file *file,
+static long slgt_compat_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	struct slgt_info *info = tty->driver_data;
@@ -1239,7 +1238,7 @@ static long slgt_compat_ioctl(struct tty_struct *tty, struct file *file,
 	case MGSL_IOCSIF:
 	case MGSL_IOCSXSYNC:
 	case MGSL_IOCSXCTRL:
-		rc = ioctl(tty, file, cmd, arg);
+		rc = ioctl(tty, cmd, arg);
 		break;
 	}
 
diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c
index 1f9de97e8cfc..327343694473 100644
--- a/drivers/char/synclinkmp.c
+++ b/drivers/char/synclinkmp.c
@@ -520,7 +520,7 @@ static void flush_buffer(struct tty_struct *tty);
 static void tx_hold(struct tty_struct *tty);
 static void tx_release(struct tty_struct *tty);
 
-static int  ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg);
+static int  ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg);
 static int  chars_in_buffer(struct tty_struct *tty);
 static void throttle(struct tty_struct * tty);
 static void unthrottle(struct tty_struct * tty);
@@ -1248,13 +1248,12 @@ static void tx_release(struct tty_struct *tty)
  * Arguments:
  *
  * 	tty	pointer to tty instance data
- * 	file	pointer to associated file object for device
  * 	cmd	IOCTL command code
  * 	arg	command argument/context
  *
  * Return Value:	0 if success, otherwise error code
  */
-static int ioctl(struct tty_struct *tty, struct file *file,
+static int ioctl(struct tty_struct *tty,
 		 unsigned int cmd, unsigned long arg)
 {
 	SLMP_INFO *info = tty->driver_data;
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index c40c1612c8a7..a1f68af4ccf4 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -144,7 +144,7 @@ static int tpk_write_room(struct tty_struct *tty)
 /*
  * TTY operations ioctl function.
  */
-static int tpk_ioctl(struct tty_struct *tty, struct file *file,
+static int tpk_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg)
 {
 	struct ttyprintk_port *tpkp = tty->driver_data;
diff --git a/drivers/char/vme_scc.c b/drivers/char/vme_scc.c
index 12de1202d22c..96838640f575 100644
--- a/drivers/char/vme_scc.c
+++ b/drivers/char/vme_scc.c
@@ -75,7 +75,7 @@ static void scc_hungup(void  *ptr);
 static void scc_close(void  *ptr);
 static int scc_chars_in_buffer(void * ptr);
 static int scc_open(struct tty_struct * tty, struct file * filp);
-static int scc_ioctl(struct tty_struct * tty, struct file * filp,
+static int scc_ioctl(struct tty_struct * tty,
                      unsigned int cmd, unsigned long arg);
 static void scc_throttle(struct tty_struct *tty);
 static void scc_unthrottle(struct tty_struct *tty);
@@ -1046,7 +1046,7 @@ static void scc_unthrottle (struct tty_struct * tty)
 }
 
 
-static int scc_ioctl(struct tty_struct *tty, struct file *file,
+static int scc_ioctl(struct tty_struct *tty,
 		     unsigned int cmd, unsigned long arg)
 {
 	return -ENOIOCTLCMD;
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index f80a7c48a35f..0d7088367038 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1219,16 +1219,10 @@ static int capinc_tty_chars_in_buffer(struct tty_struct *tty)
 	return mp->outbytes;
 }
 
-static int capinc_tty_ioctl(struct tty_struct *tty, struct file * file,
+static int capinc_tty_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
-	int error = 0;
-	switch (cmd) {
-	default:
-		error = n_tty_ioctl_helper(tty, file, cmd, arg);
-		break;
-	}
-	return error;
+	return -ENOIOCTLCMD;
 }
 
 static void capinc_tty_set_termios(struct tty_struct *tty, struct ktermios * old)
diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c
index 9b2bb491c614..59de638225fe 100644
--- a/drivers/isdn/gigaset/interface.c
+++ b/drivers/isdn/gigaset/interface.c
@@ -115,7 +115,7 @@ static int if_config(struct cardstate *cs, int *arg)
 
 static int  if_open(struct tty_struct *tty, struct file *filp);
 static void if_close(struct tty_struct *tty, struct file *filp);
-static int  if_ioctl(struct tty_struct *tty, struct file *file,
+static int  if_ioctl(struct tty_struct *tty,
 		     unsigned int cmd, unsigned long arg);
 static int  if_write_room(struct tty_struct *tty);
 static int  if_chars_in_buffer(struct tty_struct *tty);
@@ -205,7 +205,7 @@ static void if_close(struct tty_struct *tty, struct file *filp)
 	module_put(cs->driver->owner);
 }
 
-static int if_ioctl(struct tty_struct *tty, struct file *file,
+static int if_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	struct cardstate *cs;
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 0341c69eb152..3d88f15aa218 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1413,8 +1413,7 @@ isdn_tty_tiocmset(struct tty_struct *tty,
 }
 
 static int
-isdn_tty_ioctl(struct tty_struct *tty, struct file *file,
-	       uint cmd, ulong arg)
+isdn_tty_ioctl(struct tty_struct *tty, uint cmd, ulong arg)
 {
 	modem_info *info = (modem_info *) tty->driver_data;
 	int retval;
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 956e1d6e72a5..2ad58a0377b7 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1730,7 +1730,7 @@ static int hso_serial_tiocmset(struct tty_struct *tty,
 			       USB_CTRL_SET_TIMEOUT);
 }
 
-static int hso_serial_ioctl(struct tty_struct *tty, struct file *file,
+static int hso_serial_ioctl(struct tty_struct *tty,
 			    unsigned int cmd, unsigned long arg)
 {
 	struct hso_serial *serial =  get_serial_by_tty(tty);
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 88477d16b8b7..50f3ffd610b7 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2671,7 +2671,7 @@ static int gsmtty_tiocmset(struct tty_struct *tty,
 }
 
 
-static int gsmtty_ioctl(struct tty_struct *tty, struct file *filp,
+static int gsmtty_ioctl(struct tty_struct *tty,
 			unsigned int cmd, unsigned long arg)
 {
 	return -ENOIOCTLCMD;
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 923a48585501..c88029af84dd 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -334,7 +334,7 @@ free_mem_out:
 	return -ENOMEM;
 }
 
-static int pty_bsd_ioctl(struct tty_struct *tty, struct file *file,
+static int pty_bsd_ioctl(struct tty_struct *tty,
 			 unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -489,7 +489,7 @@ static struct ctl_table pty_root_table[] = {
 };
 
 
-static int pty_unix98_ioctl(struct tty_struct *tty, struct file *file,
+static int pty_unix98_ioctl(struct tty_struct *tty,
 			    unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
diff --git a/drivers/tty/serial/68328serial.c b/drivers/tty/serial/68328serial.c
index a9d99856c892..1de0e8d4bde1 100644
--- a/drivers/tty/serial/68328serial.c
+++ b/drivers/tty/serial/68328serial.c
@@ -945,7 +945,7 @@ static void send_break(struct m68k_serial * info, unsigned int duration)
         local_irq_restore(flags);
 }
 
-static int rs_ioctl(struct tty_struct *tty, struct file * file,
+static int rs_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	int error;
diff --git a/drivers/tty/serial/68360serial.c b/drivers/tty/serial/68360serial.c
index 217fe1c299e0..514a356d8d64 100644
--- a/drivers/tty/serial/68360serial.c
+++ b/drivers/tty/serial/68360serial.c
@@ -1405,7 +1405,7 @@ static int rs_360_get_icount(struct tty_struct *tty,
 	return 0;
 }
 
-static int rs_360_ioctl(struct tty_struct *tty, struct file * file,
+static int rs_360_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg)
 {
 	int error;
diff --git a/drivers/tty/serial/crisv10.c b/drivers/tty/serial/crisv10.c
index b9fcd0bda60c..225123b37f19 100644
--- a/drivers/tty/serial/crisv10.c
+++ b/drivers/tty/serial/crisv10.c
@@ -3647,7 +3647,7 @@ rs_tiocmget(struct tty_struct *tty)
 
 
 static int
-rs_ioctl(struct tty_struct *tty, struct file * file,
+rs_ioctl(struct tty_struct *tty,
 	 unsigned int cmd, unsigned long arg)
 {
 	struct e100_serial * info = (struct e100_serial *)tty->driver_data;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 623d6bd911d7..733fe8e73f0f 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1099,7 +1099,7 @@ static int uart_get_icount(struct tty_struct *tty,
  * Called via sys_ioctl.  We can use spin_lock_irq() here.
  */
 static int
-uart_ioctl(struct tty_struct *tty, struct file *filp, unsigned int cmd,
+uart_ioctl(struct tty_struct *tty, unsigned int cmd,
 	   unsigned long arg)
 {
 	struct uart_state *state = tty->driver_data;
@@ -1152,7 +1152,7 @@ uart_ioctl(struct tty_struct *tty, struct file *filp, unsigned int cmd,
 
 	mutex_lock(&port->mutex);
 
-	if (tty_hung_up_p(filp)) {
+	if (tty->flags & (1 << TTY_IO_ERROR)) {
 		ret = -EIO;
 		goto out_up;
 	}
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 83af24ca1e5e..20a862a2a0c2 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2676,7 +2676,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		break;
 	}
 	if (tty->ops->ioctl) {
-		retval = (tty->ops->ioctl)(tty, file, cmd, arg);
+		retval = (tty->ops->ioctl)(tty, cmd, arg);
 		if (retval != -ENOIOCTLCMD)
 			return retval;
 	}
@@ -2704,7 +2704,7 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd,
 		return -EINVAL;
 
 	if (tty->ops->compat_ioctl) {
-		retval = (tty->ops->compat_ioctl)(tty, file, cmd, arg);
+		retval = (tty->ops->compat_ioctl)(tty, cmd, arg);
 		if (retval != -ENOIOCTLCMD)
 			return retval;
 	}
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 9e9a901442a3..b64804965316 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -495,7 +495,7 @@ do_unimap_ioctl(int cmd, struct unimapdesc __user *user_ud, int perm, struct vc_
  * We handle the console-specific ioctl's here.  We allow the
  * capability to modify any console, not just the fg_console. 
  */
-int vt_ioctl(struct tty_struct *tty, struct file * file,
+int vt_ioctl(struct tty_struct *tty,
 	     unsigned int cmd, unsigned long arg)
 {
 	struct vc_data *vc = tty->driver_data;
@@ -1495,7 +1495,7 @@ compat_unimap_ioctl(unsigned int cmd, struct compat_unimapdesc __user *user_ud,
 	return 0;
 }
 
-long vt_compat_ioctl(struct tty_struct *tty, struct file * file,
+long vt_compat_ioctl(struct tty_struct *tty,
 	     unsigned int cmd, unsigned long arg)
 {
 	struct vc_data *vc = tty->driver_data;
@@ -1581,7 +1581,7 @@ out:
 
 fallback:
 	tty_unlock();
-	return vt_ioctl(tty, file, cmd, arg);
+	return vt_ioctl(tty, cmd, arg);
 }
 
 
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index e9a26fbd079c..8d994a8bdc90 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -813,7 +813,7 @@ static int acm_tty_tiocmset(struct tty_struct *tty,
 	return acm_set_control(acm, acm->ctrlout = newctrl);
 }
 
-static int acm_tty_ioctl(struct tty_struct *tty, struct file *file,
+static int acm_tty_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct acm *acm = tty->driver_data;
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index b1110e136c33..a72575349744 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -406,7 +406,7 @@ static void serial_unthrottle(struct tty_struct *tty)
 		port->serial->type->unthrottle(tty);
 }
 
-static int serial_ioctl(struct tty_struct *tty, struct file *file,
+static int serial_ioctl(struct tty_struct *tty,
 					unsigned int cmd, unsigned long arg)
 {
 	struct usb_serial_port *port = tty->driver_data;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 54e4eaaa0561..483df15146d2 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -584,7 +584,7 @@ extern int pcxe_open(struct tty_struct *tty, struct file *filp);
 
 /* vt.c */
 
-extern int vt_ioctl(struct tty_struct *tty, struct file *file,
+extern int vt_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg);
 
 extern long vt_compat_ioctl(struct tty_struct *tty, struct file * file,
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 5dabaa2e6da3..9deeac855240 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -98,8 +98,7 @@
  *
  *	Note: Do not call this function directly, call tty_write_room
  * 
- * int  (*ioctl)(struct tty_struct *tty, struct file * file,
- * 	    unsigned int cmd, unsigned long arg);
+ * int  (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg);
  *
  * 	This routine allows the tty driver to implement
  *	device-specific ioctls.  If the ioctl number passed in cmd
@@ -107,7 +106,7 @@
  *
  *	Optional
  *
- * long (*compat_ioctl)(struct tty_struct *tty, struct file * file,
+ * long (*compat_ioctl)(struct tty_struct *tty,,
  * 	                unsigned int cmd, unsigned long arg);
  *
  * 	implement ioctl processing for 32 bit process on 64 bit system
@@ -256,9 +255,9 @@ struct tty_operations {
 	void (*flush_chars)(struct tty_struct *tty);
 	int  (*write_room)(struct tty_struct *tty);
 	int  (*chars_in_buffer)(struct tty_struct *tty);
-	int  (*ioctl)(struct tty_struct *tty, struct file * file,
+	int  (*ioctl)(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg);
-	long (*compat_ioctl)(struct tty_struct *tty, struct file * file,
+	long (*compat_ioctl)(struct tty_struct *tty,
 			     unsigned int cmd, unsigned long arg);
 	void (*set_termios)(struct tty_struct *tty, struct ktermios * old);
 	void (*throttle)(struct tty_struct * tty);
diff --git a/include/net/irda/ircomm_tty.h b/include/net/irda/ircomm_tty.h
index 980ccb66e1b4..59ba38bc400f 100644
--- a/include/net/irda/ircomm_tty.h
+++ b/include/net/irda/ircomm_tty.h
@@ -123,7 +123,7 @@ void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self);
 extern int ircomm_tty_tiocmget(struct tty_struct *tty);
 extern int ircomm_tty_tiocmset(struct tty_struct *tty,
 			       unsigned int set, unsigned int clear);
-extern int ircomm_tty_ioctl(struct tty_struct *tty, struct file *file, 
+extern int ircomm_tty_ioctl(struct tty_struct *tty, 
 			    unsigned int cmd, unsigned long arg);
 extern void ircomm_tty_set_termios(struct tty_struct *tty, 
 				   struct ktermios *old_termios);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 8e78e7447726..b1805ff95415 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -830,7 +830,7 @@ static int rfcomm_tty_write_room(struct tty_struct *tty)
 	return room;
 }
 
-static int rfcomm_tty_ioctl(struct tty_struct *tty, struct file *filp, unsigned int cmd, unsigned long arg)
+static int rfcomm_tty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg)
 {
 	BT_DBG("tty %p cmd 0x%02x", tty, cmd);
 
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index 5e0e718c930a..77c5e6499f8f 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -365,12 +365,12 @@ static int ircomm_tty_set_serial_info(struct ircomm_tty_cb *self,
 }
 
 /*
- * Function ircomm_tty_ioctl (tty, file, cmd, arg)
+ * Function ircomm_tty_ioctl (tty, cmd, arg)
  *
  *
  *
  */
-int ircomm_tty_ioctl(struct tty_struct *tty, struct file *file,
+int ircomm_tty_ioctl(struct tty_struct *tty,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) tty->driver_data;
-- 
cgit v1.2.3


From 94c2273d6c1b65eaaf2a6446c7147bdf6e5ae924 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@suse.de>
Date: Thu, 17 Feb 2011 12:02:51 -0800
Subject: tty: fix build error in vt_ioctl.c if CONFIG_COMPAT is enabled

This was caused by the previous patch to remove the file pointer
from the tty ioctl handler.

Cc: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/tty.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 483df15146d2..ef1e0123573b 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -587,7 +587,7 @@ extern int pcxe_open(struct tty_struct *tty, struct file *filp);
 extern int vt_ioctl(struct tty_struct *tty,
 		    unsigned int cmd, unsigned long arg);
 
-extern long vt_compat_ioctl(struct tty_struct *tty, struct file * file,
+extern long vt_compat_ioctl(struct tty_struct *tty,
 		     unsigned int cmd, unsigned long arg);
 
 /* tty_mutex.c */
-- 
cgit v1.2.3


From 8d075b199b9a66ad90296f898f1f15c0ae1511b8 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@linux.intel.com>
Date: Mon, 14 Feb 2011 16:27:53 +0000
Subject: tty: add a helper for setting termios data from kernel side

This basically encapsulates the small bit of locking knowledge needed. While
we are at it make sure we blow up on any more abusers and unsafe misuses of
ioctl for this kind of stuff.

We change the function to return an argument as at some point it needs to
honour the POSIX 'I asked for changes but got none of them' error reporting
corner case.

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/tty/tty_ioctl.c | 14 +++++++++-----
 include/linux/tty.h     |  1 +
 2 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 0c1889971459..1a1135d580a2 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -486,7 +486,7 @@ int tty_termios_hw_change(struct ktermios *a, struct ktermios *b)
 EXPORT_SYMBOL(tty_termios_hw_change);
 
 /**
- *	change_termios		-	update termios values
+ *	tty_set_termios		-	update termios values
  *	@tty: tty to update
  *	@new_termios: desired new value
  *
@@ -497,7 +497,7 @@ EXPORT_SYMBOL(tty_termios_hw_change);
  *	Locking: termios_mutex
  */
 
-static void change_termios(struct tty_struct *tty, struct ktermios *new_termios)
+int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios)
 {
 	struct ktermios old_termios;
 	struct tty_ldisc *ld;
@@ -553,7 +553,9 @@ static void change_termios(struct tty_struct *tty, struct ktermios *new_termios)
 		tty_ldisc_deref(ld);
 	}
 	mutex_unlock(&tty->termios_mutex);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(tty_set_termios);
 
 /**
  *	set_termios		-	set termios values for a tty
@@ -562,7 +564,7 @@ static void change_termios(struct tty_struct *tty, struct ktermios *new_termios)
  *	@opt: option information
  *
  *	Helper function to prepare termios data and run necessary other
- *	functions before using change_termios to do the actual changes.
+ *	functions before using tty_set_termios to do the actual changes.
  *
  *	Locking:
  *		Called functions take ldisc and termios_mutex locks
@@ -620,7 +622,7 @@ static int set_termios(struct tty_struct *tty, void __user *arg, int opt)
 			return -EINTR;
 	}
 
-	change_termios(tty, &tmp_termios);
+	tty_set_termios(tty, &tmp_termios);
 
 	/* FIXME: Arguably if tmp_termios == tty->termios AND the
 	   actual requested termios was not tmp_termios then we may
@@ -797,7 +799,7 @@ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb)
 						termios.c_ospeed);
 #endif
 	mutex_unlock(&tty->termios_mutex);
-	change_termios(tty, &termios);
+	tty_set_termios(tty, &termios);
 	return 0;
 }
 #endif
@@ -951,6 +953,8 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 	int ret = 0;
 	struct ktermios kterm;
 
+	BUG_ON(file == NULL);
+
 	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
 	    tty->driver->subtype == PTY_TYPE_MASTER)
 		real_tty = tty->link;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index ef1e0123573b..4e53d4641b38 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -448,6 +448,7 @@ extern void tty_encode_baud_rate(struct tty_struct *tty,
 						speed_t ibaud, speed_t obaud);
 extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old);
 extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b);
+extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt);
 
 extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *);
 extern void tty_ldisc_deref(struct tty_ldisc *);
-- 
cgit v1.2.3


From 3c95c985fa91ecf6a0e29622bbdd13dcfc5ce9f1 Mon Sep 17 00:00:00 2001
From: Kay Sievers <kay.sievers@vrfy.org>
Date: Thu, 17 Feb 2011 18:39:28 +0100
Subject: tty: add TIOCVHANGUP to allow clean tty shutdown of all ttys

This is useful for system management software so that it can kick
off things like gettys and everything that's started from a tty,
before we reuse it from/for something else or shut it down.

Without this ioctl it would have to temporarily become the owner of
the tty, then call vhangup() and then give it up again.

Cc: Lennart Poettering <lennart@poettering.net>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/alpha/include/asm/ioctls.h   | 1 +
 arch/mips/include/asm/ioctls.h    | 1 +
 arch/parisc/include/asm/ioctls.h  | 1 +
 arch/powerpc/include/asm/ioctls.h | 1 +
 arch/sh/include/asm/ioctls.h      | 1 +
 arch/sparc/include/asm/ioctls.h   | 1 +
 arch/xtensa/include/asm/ioctls.h  | 1 +
 drivers/tty/tty_io.c              | 5 +++++
 include/asm-generic/ioctls.h      | 1 +
 9 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/arch/alpha/include/asm/ioctls.h b/arch/alpha/include/asm/ioctls.h
index 034b6cf5d9f3..80e1cee90f1f 100644
--- a/arch/alpha/include/asm/ioctls.h
+++ b/arch/alpha/include/asm/ioctls.h
@@ -94,6 +94,7 @@
 #define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
+#define TIOCVHANGUP	0x5437
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/mips/include/asm/ioctls.h b/arch/mips/include/asm/ioctls.h
index d967b8997626..92403c3d6007 100644
--- a/arch/mips/include/asm/ioctls.h
+++ b/arch/mips/include/asm/ioctls.h
@@ -85,6 +85,7 @@
 #define TIOCSPTLCK	_IOW('T', 0x31, int)  /* Lock/unlock Pty */
 #define TIOCGDEV	_IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T', 0x36, int)  /* Generate signal on Pty slave */
+#define TIOCVHANGUP	0x5437
 
 /* I hope the range from 0x5480 on is free ... */
 #define TIOCSCTTY	0x5480		/* become controlling tty */
diff --git a/arch/parisc/include/asm/ioctls.h b/arch/parisc/include/asm/ioctls.h
index 6ba80d03623a..054ec06f9e23 100644
--- a/arch/parisc/include/asm/ioctls.h
+++ b/arch/parisc/include/asm/ioctls.h
@@ -54,6 +54,7 @@
 #define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
 #define TIOCGDEV	_IOR('T',0x32, int)  /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
+#define TIOCVHANGUP	0x5437
 
 #define FIONCLEX	0x5450  /* these numbers need to be adjusted. */
 #define FIOCLEX		0x5451
diff --git a/arch/powerpc/include/asm/ioctls.h b/arch/powerpc/include/asm/ioctls.h
index c7dc17cf84f1..e9b78870aaab 100644
--- a/arch/powerpc/include/asm/ioctls.h
+++ b/arch/powerpc/include/asm/ioctls.h
@@ -96,6 +96,7 @@
 #define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
+#define TIOCVHANGUP	0x5437
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/sh/include/asm/ioctls.h b/arch/sh/include/asm/ioctls.h
index 84e85a792638..a6769f352bf6 100644
--- a/arch/sh/include/asm/ioctls.h
+++ b/arch/sh/include/asm/ioctls.h
@@ -87,6 +87,7 @@
 #define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
+#define TIOCVHANGUP	_IO('T', 0x37)
 
 #define TIOCSERCONFIG	_IO('T', 83) /* 0x5453 */
 #define TIOCSERGWILD	_IOR('T', 84,  int) /* 0x5454 */
diff --git a/arch/sparc/include/asm/ioctls.h b/arch/sparc/include/asm/ioctls.h
index ed3807b96bb5..28d0c8b02cc3 100644
--- a/arch/sparc/include/asm/ioctls.h
+++ b/arch/sparc/include/asm/ioctls.h
@@ -20,6 +20,7 @@
 #define TCSETSW2	_IOW('T', 14, struct termios2)
 #define TCSETSF2	_IOW('T', 15, struct termios2)
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
+#define TIOCVHANGUP	_IO('T', 0x37)
 
 /* Note that all the ioctls that are not available in Linux have a 
  * double underscore on the front to: a) avoid some programs to
diff --git a/arch/xtensa/include/asm/ioctls.h b/arch/xtensa/include/asm/ioctls.h
index ccf1800f0b0c..fd1d1369a407 100644
--- a/arch/xtensa/include/asm/ioctls.h
+++ b/arch/xtensa/include/asm/ioctls.h
@@ -100,6 +100,7 @@
 #define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
 #define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
+#define TIOCVHANGUP	_IO('T', 0x37)
 
 #define TIOCSERCONFIG	_IO('T', 83)
 #define TIOCSERGWILD	_IOR('T', 84,  int)
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 20a862a2a0c2..8ef2d69470ec 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2626,6 +2626,11 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return put_user(tty->ldisc->ops->num, (int __user *)p);
 	case TIOCSETD:
 		return tiocsetd(tty, p);
+	case TIOCVHANGUP:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		tty_vhangup(tty);
+		return 0;
 	case TIOCGDEV:
 	{
 		unsigned int ret = new_encode_dev(tty_devnum(real_tty));
diff --git a/include/asm-generic/ioctls.h b/include/asm-generic/ioctls.h
index 3f3f2d189fb8..199975fac395 100644
--- a/include/asm-generic/ioctls.h
+++ b/include/asm-generic/ioctls.h
@@ -73,6 +73,7 @@
 #define TCSETXF		0x5434
 #define TCSETXW		0x5435
 #define TIOCSIG		_IOW('T', 0x36, int)  /* pty: generate signal */
+#define TIOCVHANGUP	0x5437
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451
-- 
cgit v1.2.3


From 212b573f5552c60265da721ff9ce32e3462a2cdd Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 15 Feb 2011 16:59:16 +0000
Subject: ethtool: enable GSO and GRO by default
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +++
 net/core/dev.c            | 18 ++++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d08ef6538579..168e3ad14daf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -984,6 +984,9 @@ struct net_device {
 				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
 				 NETIF_F_FRAGLIST)
 
+	/* changeable features with no special hardware requirements */
+#define NETIF_F_SOFT_FEATURES	(NETIF_F_GSO | NETIF_F_GRO)
+
 	/* Interface index. Unique device identifier	*/
 	int			ifindex;
 	int			iflink;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4580460ebecd..8686f6ffe7f0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5274,6 +5274,12 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
 		features &= ~NETIF_F_TSO;
 	}
 
+	/* Software GSO depends on SG. */
+	if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) {
+		netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n");
+		features &= ~NETIF_F_GSO;
+	}
+
 	/* UFO needs SG and checksumming */
 	if (features & NETIF_F_UFO) {
 		/* maybe split UFO into V4 and V6? */
@@ -5430,11 +5436,15 @@ int register_netdevice(struct net_device *dev)
 	if (dev->iflink == -1)
 		dev->iflink = dev->ifindex;
 
-	dev->features = netdev_fix_features(dev, dev->features);
+	/* Enable software offloads by default - will be stripped in
+	 * netdev_fix_features() if not supported. */
+	dev->features |= NETIF_F_SOFT_FEATURES;
 
-	/* Enable software GSO if SG is supported. */
-	if (dev->features & NETIF_F_SG)
-		dev->features |= NETIF_F_GSO;
+	/* Avoid warning from netdev_fix_features() for GSO without SG */
+	if (!(dev->features & NETIF_F_SG))
+		dev->features &= ~NETIF_F_GSO;
+
+	dev->features = netdev_fix_features(dev, dev->features);
 
 	/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
 	 * vlan_dev_init() will do the dev->features check, so these features
-- 
cgit v1.2.3


From 0a417704777ed29d0e8c72b7274a328e61248e75 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 15 Feb 2011 16:59:17 +0000
Subject: ethtool: factorize get/set_one_feature
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows to enable GRO even if RX csum is disabled. GRO will not
be used for packets without hardware checksum anyway.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |   6 +
 net/core/ethtool.c        | 274 ++++++++++++++++++++++------------------------
 2 files changed, 138 insertions(+), 142 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 168e3ad14daf..dede3fdbb4be 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -976,6 +976,12 @@ struct net_device {
 #define NETIF_F_V6_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
 #define NETIF_F_ALL_CSUM	(NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
 
+#define NETIF_F_ALL_TSO 	(NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+
+#define NETIF_F_ALL_TX_OFFLOADS	(NETIF_F_ALL_CSUM | NETIF_F_SG | \
+				 NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+				 NETIF_F_SCTP_CSUM | NETIF_F_FCOE_CRC)
+
 	/*
 	 * If one device supports one of these features, then enable them
 	 * for all in netdev_increment_features.
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 85aaeab862a8..c3fb8f90de6d 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -191,6 +191,109 @@ static void __ethtool_get_strings(struct net_device *dev,
 	ops->get_strings(dev, stringset, data);
 }
 
+static u32 ethtool_get_feature_mask(u32 eth_cmd)
+{
+	/* feature masks of legacy discrete ethtool ops */
+
+	switch (eth_cmd) {
+	case ETHTOOL_GTXCSUM:
+	case ETHTOOL_STXCSUM:
+		return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM;
+	case ETHTOOL_GSG:
+	case ETHTOOL_SSG:
+		return NETIF_F_SG;
+	case ETHTOOL_GTSO:
+	case ETHTOOL_STSO:
+		return NETIF_F_ALL_TSO;
+	case ETHTOOL_GUFO:
+	case ETHTOOL_SUFO:
+		return NETIF_F_UFO;
+	case ETHTOOL_GGSO:
+	case ETHTOOL_SGSO:
+		return NETIF_F_GSO;
+	case ETHTOOL_GGRO:
+	case ETHTOOL_SGRO:
+		return NETIF_F_GRO;
+	default:
+		BUG();
+	}
+}
+
+static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+
+	if (!ops)
+		return NULL;
+
+	switch (ethcmd) {
+	case ETHTOOL_GTXCSUM:
+		return ops->get_tx_csum;
+	case ETHTOOL_SSG:
+		return ops->get_sg;
+	case ETHTOOL_STSO:
+		return ops->get_tso;
+	case ETHTOOL_SUFO:
+		return ops->get_ufo;
+	default:
+		return NULL;
+	}
+}
+
+static int ethtool_get_one_feature(struct net_device *dev,
+	char __user *useraddr, u32 ethcmd)
+{
+	struct ethtool_value edata = {
+		.cmd = ethcmd,
+		.data = !!(dev->features & ethtool_get_feature_mask(ethcmd)),
+	};
+	u32 (*actor)(struct net_device *);
+
+	actor = __ethtool_get_one_feature_actor(dev, ethcmd);
+	if (actor)
+		edata.data = actor(dev);
+
+	if (copy_to_user(useraddr, &edata, sizeof(edata)))
+		return -EFAULT;
+	return 0;
+}
+
+static int __ethtool_set_tx_csum(struct net_device *dev, u32 data);
+static int __ethtool_set_sg(struct net_device *dev, u32 data);
+static int __ethtool_set_tso(struct net_device *dev, u32 data);
+static int __ethtool_set_ufo(struct net_device *dev, u32 data);
+
+static int ethtool_set_one_feature(struct net_device *dev,
+	void __user *useraddr, u32 ethcmd)
+{
+	struct ethtool_value edata;
+	u32 mask;
+
+	if (copy_from_user(&edata, useraddr, sizeof(edata)))
+		return -EFAULT;
+
+	switch (ethcmd) {
+	case ETHTOOL_STXCSUM:
+		return __ethtool_set_tx_csum(dev, edata.data);
+	case ETHTOOL_SSG:
+		return __ethtool_set_sg(dev, edata.data);
+	case ETHTOOL_STSO:
+		return __ethtool_set_tso(dev, edata.data);
+	case ETHTOOL_SUFO:
+		return __ethtool_set_ufo(dev, edata.data);
+	case ETHTOOL_SGSO:
+	case ETHTOOL_SGRO:
+		mask = ethtool_get_feature_mask(ethcmd);
+		if (edata.data)
+			dev->features |= mask;
+		else
+			dev->features &= ~mask;
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
 {
 	struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET };
@@ -1107,6 +1210,9 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data)
 {
 	int err;
 
+	if (data && !(dev->features & NETIF_F_ALL_CSUM))
+		return -EINVAL;
+
 	if (!data && dev->ethtool_ops->set_tso) {
 		err = dev->ethtool_ops->set_tso(dev, 0);
 		if (err)
@@ -1121,24 +1227,20 @@ static int __ethtool_set_sg(struct net_device *dev, u32 data)
 	return dev->ethtool_ops->set_sg(dev, data);
 }
 
-static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_tx_csum(struct net_device *dev, u32 data)
 {
-	struct ethtool_value edata;
 	int err;
 
 	if (!dev->ethtool_ops->set_tx_csum)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-
-	if (!edata.data && dev->ethtool_ops->set_sg) {
+	if (!data && dev->ethtool_ops->set_sg) {
 		err = __ethtool_set_sg(dev, 0);
 		if (err)
 			return err;
 	}
 
-	return dev->ethtool_ops->set_tx_csum(dev, edata.data);
+	return dev->ethtool_ops->set_tx_csum(dev, data);
 }
 
 static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
@@ -1157,108 +1259,28 @@ static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
 	return dev->ethtool_ops->set_rx_csum(dev, edata.data);
 }
 
-static int ethtool_set_sg(struct net_device *dev, char __user *useraddr)
-{
-	struct ethtool_value edata;
-
-	if (!dev->ethtool_ops->set_sg)
-		return -EOPNOTSUPP;
-
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-
-	if (edata.data &&
-	    !(dev->features & NETIF_F_ALL_CSUM))
-		return -EINVAL;
-
-	return __ethtool_set_sg(dev, edata.data);
-}
-
-static int ethtool_set_tso(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_tso(struct net_device *dev, u32 data)
 {
-	struct ethtool_value edata;
-
 	if (!dev->ethtool_ops->set_tso)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-
-	if (edata.data && !(dev->features & NETIF_F_SG))
+	if (data && !(dev->features & NETIF_F_SG))
 		return -EINVAL;
 
-	return dev->ethtool_ops->set_tso(dev, edata.data);
+	return dev->ethtool_ops->set_tso(dev, data);
 }
 
-static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_ufo(struct net_device *dev, u32 data)
 {
-	struct ethtool_value edata;
-
 	if (!dev->ethtool_ops->set_ufo)
 		return -EOPNOTSUPP;
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-	if (edata.data && !(dev->features & NETIF_F_SG))
+	if (data && !(dev->features & NETIF_F_SG))
 		return -EINVAL;
-	if (edata.data && !((dev->features & NETIF_F_GEN_CSUM) ||
+	if (data && !((dev->features & NETIF_F_GEN_CSUM) ||
 		(dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
 			== (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)))
 		return -EINVAL;
-	return dev->ethtool_ops->set_ufo(dev, edata.data);
-}
-
-static int ethtool_get_gso(struct net_device *dev, char __user *useraddr)
-{
-	struct ethtool_value edata = { ETHTOOL_GGSO };
-
-	edata.data = dev->features & NETIF_F_GSO;
-	if (copy_to_user(useraddr, &edata, sizeof(edata)))
-		return -EFAULT;
-	return 0;
-}
-
-static int ethtool_set_gso(struct net_device *dev, char __user *useraddr)
-{
-	struct ethtool_value edata;
-
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-	if (edata.data)
-		dev->features |= NETIF_F_GSO;
-	else
-		dev->features &= ~NETIF_F_GSO;
-	return 0;
-}
-
-static int ethtool_get_gro(struct net_device *dev, char __user *useraddr)
-{
-	struct ethtool_value edata = { ETHTOOL_GGRO };
-
-	edata.data = dev->features & NETIF_F_GRO;
-	if (copy_to_user(useraddr, &edata, sizeof(edata)))
-		return -EFAULT;
-	return 0;
-}
-
-static int ethtool_set_gro(struct net_device *dev, char __user *useraddr)
-{
-	struct ethtool_value edata;
-
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-
-	if (edata.data) {
-		u32 rxcsum = dev->ethtool_ops->get_rx_csum ?
-				dev->ethtool_ops->get_rx_csum(dev) :
-				ethtool_op_get_rx_csum(dev);
-
-		if (!rxcsum)
-			return -EINVAL;
-		dev->features |= NETIF_F_GRO;
-	} else
-		dev->features &= ~NETIF_F_GRO;
-
-	return 0;
+	return dev->ethtool_ops->set_ufo(dev, data);
 }
 
 static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
@@ -1590,33 +1612,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXCSUM:
 		rc = ethtool_set_rx_csum(dev, useraddr);
 		break;
-	case ETHTOOL_GTXCSUM:
-		rc = ethtool_get_value(dev, useraddr, ethcmd,
-				       (dev->ethtool_ops->get_tx_csum ?
-					dev->ethtool_ops->get_tx_csum :
-					ethtool_op_get_tx_csum));
-		break;
-	case ETHTOOL_STXCSUM:
-		rc = ethtool_set_tx_csum(dev, useraddr);
-		break;
-	case ETHTOOL_GSG:
-		rc = ethtool_get_value(dev, useraddr, ethcmd,
-				       (dev->ethtool_ops->get_sg ?
-					dev->ethtool_ops->get_sg :
-					ethtool_op_get_sg));
-		break;
-	case ETHTOOL_SSG:
-		rc = ethtool_set_sg(dev, useraddr);
-		break;
-	case ETHTOOL_GTSO:
-		rc = ethtool_get_value(dev, useraddr, ethcmd,
-				       (dev->ethtool_ops->get_tso ?
-					dev->ethtool_ops->get_tso :
-					ethtool_op_get_tso));
-		break;
-	case ETHTOOL_STSO:
-		rc = ethtool_set_tso(dev, useraddr);
-		break;
 	case ETHTOOL_TEST:
 		rc = ethtool_self_test(dev, useraddr);
 		break;
@@ -1632,21 +1627,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GPERMADDR:
 		rc = ethtool_get_perm_addr(dev, useraddr);
 		break;
-	case ETHTOOL_GUFO:
-		rc = ethtool_get_value(dev, useraddr, ethcmd,
-				       (dev->ethtool_ops->get_ufo ?
-					dev->ethtool_ops->get_ufo :
-					ethtool_op_get_ufo));
-		break;
-	case ETHTOOL_SUFO:
-		rc = ethtool_set_ufo(dev, useraddr);
-		break;
-	case ETHTOOL_GGSO:
-		rc = ethtool_get_gso(dev, useraddr);
-		break;
-	case ETHTOOL_SGSO:
-		rc = ethtool_set_gso(dev, useraddr);
-		break;
 	case ETHTOOL_GFLAGS:
 		rc = ethtool_get_value(dev, useraddr, ethcmd,
 				       (dev->ethtool_ops->get_flags ?
@@ -1677,12 +1657,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXCLSRLINS:
 		rc = ethtool_set_rxnfc(dev, ethcmd, useraddr);
 		break;
-	case ETHTOOL_GGRO:
-		rc = ethtool_get_gro(dev, useraddr);
-		break;
-	case ETHTOOL_SGRO:
-		rc = ethtool_set_gro(dev, useraddr);
-		break;
 	case ETHTOOL_FLASHDEV:
 		rc = ethtool_flash_device(dev, useraddr);
 		break;
@@ -1704,6 +1678,22 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXFHINDIR:
 		rc = ethtool_set_rxfh_indir(dev, useraddr);
 		break;
+	case ETHTOOL_GTXCSUM:
+	case ETHTOOL_GSG:
+	case ETHTOOL_GTSO:
+	case ETHTOOL_GUFO:
+	case ETHTOOL_GGSO:
+	case ETHTOOL_GGRO:
+		rc = ethtool_get_one_feature(dev, useraddr, ethcmd);
+		break;
+	case ETHTOOL_STXCSUM:
+	case ETHTOOL_SSG:
+	case ETHTOOL_STSO:
+	case ETHTOOL_SUFO:
+	case ETHTOOL_SGSO:
+	case ETHTOOL_SGRO:
+		rc = ethtool_set_one_feature(dev, useraddr, ethcmd);
+		break;
 	default:
 		rc = -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 5455c6998d34dc983a8693500e4dffefc3682dc5 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 15 Feb 2011 16:59:17 +0000
Subject: net: Introduce new feature setting ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This introduces a new framework to handle device features setting.
It consists of:
  - new fields in struct net_device:
	+ hw_features - features that hw/driver supports toggling
	+ wanted_features - features that user wants enabled, when possible
  - new netdev_ops:
	+ feat = ndo_fix_features(dev, feat) - API checking constraints for
		enabling features or their combinations
	+ ndo_set_features(dev) - API updating hardware state to match
		changed dev->features
  - new ethtool commands:
	+ ETHTOOL_GFEATURES/ETHTOOL_SFEATURES: get/set dev->wanted_features
		and trigger device reconfiguration if resulting dev->features
		changed
	+ ETHTOOL_GSTRINGS(ETH_SS_FEATURES): get feature bits names (meaning)

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h   |  85 +++++++++++++++++++++++++++++++
 include/linux/netdevice.h |  37 +++++++++++++-
 net/core/dev.c            |  46 ++++++++++++++---
 net/core/ethtool.c        | 125 +++++++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 283 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 1908929204a9..806e716bb4fb 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -251,6 +251,7 @@ enum ethtool_stringset {
 	ETH_SS_STATS,
 	ETH_SS_PRIV_FLAGS,
 	ETH_SS_NTUPLE_FILTERS,
+	ETH_SS_FEATURES,
 };
 
 /* for passing string sets for data tagging */
@@ -523,6 +524,87 @@ struct ethtool_flash {
 	char	data[ETHTOOL_FLASH_MAX_FILENAME];
 };
 
+/* for returning and changing feature sets */
+
+/**
+ * struct ethtool_get_features_block - block with state of 32 features
+ * @available: mask of changeable features
+ * @requested: mask of features requested to be enabled if possible
+ * @active: mask of currently enabled features
+ * @never_changed: mask of features not changeable for any device
+ */
+struct ethtool_get_features_block {
+	__u32	available;
+	__u32	requested;
+	__u32	active;
+	__u32	never_changed;
+};
+
+/**
+ * struct ethtool_gfeatures - command to get state of device's features
+ * @cmd: command number = %ETHTOOL_GFEATURES
+ * @size: in: number of elements in the features[] array;
+ *       out: number of elements in features[] needed to hold all features
+ * @features: state of features
+ */
+struct ethtool_gfeatures {
+	__u32	cmd;
+	__u32	size;
+	struct ethtool_get_features_block features[0];
+};
+
+/**
+ * struct ethtool_set_features_block - block with request for 32 features
+ * @valid: mask of features to be changed
+ * @requested: values of features to be changed
+ */
+struct ethtool_set_features_block {
+	__u32	valid;
+	__u32	requested;
+};
+
+/**
+ * struct ethtool_sfeatures - command to request change in device's features
+ * @cmd: command number = %ETHTOOL_SFEATURES
+ * @size: array size of the features[] array
+ * @features: feature change masks
+ */
+struct ethtool_sfeatures {
+	__u32	cmd;
+	__u32	size;
+	struct ethtool_set_features_block features[0];
+};
+
+/*
+ * %ETHTOOL_SFEATURES changes features present in features[].valid to the
+ * values of corresponding bits in features[].requested. Bits in .requested
+ * not set in .valid or not changeable are ignored.
+ *
+ * Returns %EINVAL when .valid contains undefined or never-changable bits
+ * or size is not equal to required number of features words (32-bit blocks).
+ * Returns >= 0 if request was completed; bits set in the value mean:
+ *   %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not
+ *	changeable (not present in %ETHTOOL_GFEATURES' features[].available)
+ *	those bits were ignored.
+ *   %ETHTOOL_F_WISH - some or all changes requested were recorded but the
+ *      resulting state of bits masked by .valid is not equal to .requested.
+ *      Probably there are other device-specific constraints on some features
+ *      in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered
+ *      here as though ignored bits were cleared.
+ *
+ * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of
+ * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands
+ * for ETH_SS_FEATURES string set. First entry in the table corresponds to least
+ * significant bit in features[0] fields. Empty strings mark undefined features.
+ */
+enum ethtool_sfeatures_retval_bits {
+	ETHTOOL_F_UNSUPPORTED__BIT,
+	ETHTOOL_F_WISH__BIT,
+};
+
+#define ETHTOOL_F_UNSUPPORTED   (1 << ETHTOOL_F_UNSUPPORTED__BIT)
+#define ETHTOOL_F_WISH          (1 << ETHTOOL_F_WISH__BIT)
+
 #ifdef __KERNEL__
 
 #include <linux/rculist.h>
@@ -744,6 +826,9 @@ struct ethtool_ops {
 #define ETHTOOL_GRXFHINDIR	0x00000038 /* Get RX flow hash indir'n table */
 #define ETHTOOL_SRXFHINDIR	0x00000039 /* Set RX flow hash indir'n table */
 
+#define ETHTOOL_GFEATURES	0x0000003a /* Get device offload settings */
+#define ETHTOOL_SFEATURES	0x0000003b /* Change device offload settings */
+
 /* compatibility with older code */
 #define SPARC_ETH_GSET		ETHTOOL_GSET
 #define SPARC_ETH_SSET		ETHTOOL_SSET
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dede3fdbb4be..85f67e225f60 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -791,6 +791,18 @@ struct netdev_tc_txq {
  *
  * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
  *	Called to release previously enslaved netdev.
+ *
+ *      Feature/offload setting functions.
+ * u32 (*ndo_fix_features)(struct net_device *dev, u32 features);
+ *	Adjusts the requested feature flags according to device-specific
+ *	constraints, and returns the resulting flags. Must not modify
+ *	the device state.
+ *
+ * int (*ndo_set_features)(struct net_device *dev, u32 features);
+ *	Called to update device configuration to new features. Passed
+ *	feature set might be less than what was returned by ndo_fix_features()).
+ *	Must return >0 or -errno if it changed dev->features itself.
+ *
  */
 #define HAVE_NET_DEVICE_OPS
 struct net_device_ops {
@@ -874,6 +886,10 @@ struct net_device_ops {
 						 struct net_device *slave_dev);
 	int			(*ndo_del_slave)(struct net_device *dev,
 						 struct net_device *slave_dev);
+	u32			(*ndo_fix_features)(struct net_device *dev,
+						    u32 features);
+	int			(*ndo_set_features)(struct net_device *dev,
+						    u32 features);
 };
 
 /*
@@ -925,12 +941,18 @@ struct net_device {
 	struct list_head	napi_list;
 	struct list_head	unreg_list;
 
-	/* Net device features */
+	/* currently active device features */
 	u32			features;
-
+	/* user-changeable features */
+	u32			hw_features;
+	/* user-requested features */
+	u32			wanted_features;
 	/* VLAN feature mask */
 	u32			vlan_features;
 
+	/* Net device feature bits; if you change something,
+	 * also update netdev_features_strings[] in ethtool.c */
+
 #define NETIF_F_SG		1	/* Scatter/gather IO. */
 #define NETIF_F_IP_CSUM		2	/* Can checksum TCP/UDP over IPv4. */
 #define NETIF_F_NO_CSUM		4	/* Does not require checksum. F.e. loopack. */
@@ -966,6 +988,12 @@ struct net_device {
 #define NETIF_F_TSO6		(SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
 #define NETIF_F_FSO		(SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
 
+	/* Features valid for ethtool to change */
+	/* = all defined minus driver/device-class-related */
+#define NETIF_F_NEVER_CHANGE	(NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \
+				  NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+#define NETIF_F_ETHTOOL_BITS	(0x1f3fffff & ~NETIF_F_NEVER_CHANGE)
+
 	/* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | \
 				 NETIF_F_TSO6 | NETIF_F_UFO)
@@ -2428,8 +2456,13 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l
 
 extern void linkwatch_run_queue(void);
 
+static inline u32 netdev_get_wanted_features(struct net_device *dev)
+{
+	return (dev->features & ~dev->hw_features) | dev->wanted_features;
+}
 u32 netdev_increment_features(u32 all, u32 one, u32 mask);
 u32 netdev_fix_features(struct net_device *dev, u32 features);
+void netdev_update_features(struct net_device *dev);
 
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 8686f6ffe7f0..4f6943928fe8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5302,6 +5302,37 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
 }
 EXPORT_SYMBOL(netdev_fix_features);
 
+void netdev_update_features(struct net_device *dev)
+{
+	u32 features;
+	int err = 0;
+
+	features = netdev_get_wanted_features(dev);
+
+	if (dev->netdev_ops->ndo_fix_features)
+		features = dev->netdev_ops->ndo_fix_features(dev, features);
+
+	/* driver might be less strict about feature dependencies */
+	features = netdev_fix_features(dev, features);
+
+	if (dev->features == features)
+		return;
+
+	netdev_info(dev, "Features changed: 0x%08x -> 0x%08x\n",
+		dev->features, features);
+
+	if (dev->netdev_ops->ndo_set_features)
+		err = dev->netdev_ops->ndo_set_features(dev, features);
+
+	if (!err)
+		dev->features = features;
+	else if (err < 0)
+		netdev_err(dev,
+			"set_features() failed (%d); wanted 0x%08x, left 0x%08x\n",
+			err, features, dev->features);
+}
+EXPORT_SYMBOL(netdev_update_features);
+
 /**
  *	netif_stacked_transfer_operstate -	transfer operstate
  *	@rootdev: the root or lower level device to transfer state from
@@ -5436,15 +5467,18 @@ int register_netdevice(struct net_device *dev)
 	if (dev->iflink == -1)
 		dev->iflink = dev->ifindex;
 
-	/* Enable software offloads by default - will be stripped in
-	 * netdev_fix_features() if not supported. */
-	dev->features |= NETIF_F_SOFT_FEATURES;
+	/* Transfer changeable features to wanted_features and enable
+	 * software offloads (GSO and GRO).
+	 */
+	dev->hw_features |= NETIF_F_SOFT_FEATURES;
+	dev->wanted_features = (dev->features & dev->hw_features)
+		| NETIF_F_SOFT_FEATURES;
 
 	/* Avoid warning from netdev_fix_features() for GSO without SG */
-	if (!(dev->features & NETIF_F_SG))
-		dev->features &= ~NETIF_F_GSO;
+	if (!(dev->wanted_features & NETIF_F_SG))
+		dev->wanted_features &= ~NETIF_F_GSO;
 
-	dev->features = netdev_fix_features(dev, dev->features);
+	netdev_update_features(dev);
 
 	/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
 	 * vlan_dev_init() will do the dev->features check, so these features
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c3fb8f90de6d..95773960dc77 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -172,10 +172,120 @@ EXPORT_SYMBOL(ethtool_ntuple_flush);
 
 /* Handlers for each ethtool command */
 
+#define ETHTOOL_DEV_FEATURE_WORDS	1
+
+static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
+{
+	struct ethtool_gfeatures cmd = {
+		.cmd = ETHTOOL_GFEATURES,
+		.size = ETHTOOL_DEV_FEATURE_WORDS,
+	};
+	struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = {
+		{
+			.available = dev->hw_features,
+			.requested = dev->wanted_features,
+			.active = dev->features,
+			.never_changed = NETIF_F_NEVER_CHANGE,
+		},
+	};
+	u32 __user *sizeaddr;
+	u32 copy_size;
+
+	sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size);
+	if (get_user(copy_size, sizeaddr))
+		return -EFAULT;
+
+	if (copy_size > ETHTOOL_DEV_FEATURE_WORDS)
+		copy_size = ETHTOOL_DEV_FEATURE_WORDS;
+
+	if (copy_to_user(useraddr, &cmd, sizeof(cmd)))
+		return -EFAULT;
+	useraddr += sizeof(cmd);
+	if (copy_to_user(useraddr, features, copy_size * sizeof(*features)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
+{
+	struct ethtool_sfeatures cmd;
+	struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
+	int ret = 0;
+
+	if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
+		return -EFAULT;
+	useraddr += sizeof(cmd);
+
+	if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS)
+		return -EINVAL;
+
+	if (copy_from_user(features, useraddr, sizeof(features)))
+		return -EFAULT;
+
+	if (features[0].valid & ~NETIF_F_ETHTOOL_BITS)
+		return -EINVAL;
+
+	if (features[0].valid & ~dev->hw_features) {
+		features[0].valid &= dev->hw_features;
+		ret |= ETHTOOL_F_UNSUPPORTED;
+	}
+
+	dev->wanted_features &= ~features[0].valid;
+	dev->wanted_features |= features[0].valid & features[0].requested;
+	netdev_update_features(dev);
+
+	if ((dev->wanted_features ^ dev->features) & features[0].valid)
+		ret |= ETHTOOL_F_WISH;
+
+	return ret;
+}
+
+static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = {
+	/* NETIF_F_SG */              "tx-scatter-gather",
+	/* NETIF_F_IP_CSUM */         "tx-checksum-ipv4",
+	/* NETIF_F_NO_CSUM */         "tx-checksum-unneeded",
+	/* NETIF_F_HW_CSUM */         "tx-checksum-ip-generic",
+	/* NETIF_F_IPV6_CSUM */       "tx_checksum-ipv6",
+	/* NETIF_F_HIGHDMA */         "highdma",
+	/* NETIF_F_FRAGLIST */        "tx-scatter-gather-fraglist",
+	/* NETIF_F_HW_VLAN_TX */      "tx-vlan-hw-insert",
+
+	/* NETIF_F_HW_VLAN_RX */      "rx-vlan-hw-parse",
+	/* NETIF_F_HW_VLAN_FILTER */  "rx-vlan-filter",
+	/* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged",
+	/* NETIF_F_GSO */             "tx-generic-segmentation",
+	/* NETIF_F_LLTX */            "tx-lockless",
+	/* NETIF_F_NETNS_LOCAL */     "netns-local",
+	/* NETIF_F_GRO */             "rx-gro",
+	/* NETIF_F_LRO */             "rx-lro",
+
+	/* NETIF_F_TSO */             "tx-tcp-segmentation",
+	/* NETIF_F_UFO */             "tx-udp-fragmentation",
+	/* NETIF_F_GSO_ROBUST */      "tx-gso-robust",
+	/* NETIF_F_TSO_ECN */         "tx-tcp-ecn-segmentation",
+	/* NETIF_F_TSO6 */            "tx-tcp6-segmentation",
+	/* NETIF_F_FSO */             "tx-fcoe-segmentation",
+	"",
+	"",
+
+	/* NETIF_F_FCOE_CRC */        "tx-checksum-fcoe-crc",
+	/* NETIF_F_SCTP_CSUM */       "tx-checksum-sctp",
+	/* NETIF_F_FCOE_MTU */        "fcoe-mtu",
+	/* NETIF_F_NTUPLE */          "rx-ntuple-filter",
+	/* NETIF_F_RXHASH */          "rx-hashing",
+	"",
+	"",
+	"",
+};
+
 static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 
+	if (sset == ETH_SS_FEATURES)
+		return ARRAY_SIZE(netdev_features_strings);
+
 	if (ops && ops->get_sset_count && ops->get_strings)
 		return ops->get_sset_count(dev, sset);
 	else
@@ -187,8 +297,12 @@ static void __ethtool_get_strings(struct net_device *dev,
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 
-	/* ops->get_strings is valid because checked earlier */
-	ops->get_strings(dev, stringset, data);
+	if (stringset == ETH_SS_FEATURES)
+		memcpy(data, netdev_features_strings,
+			sizeof(netdev_features_strings));
+	else
+		/* ops->get_strings is valid because checked earlier */
+		ops->get_strings(dev, stringset, data);
 }
 
 static u32 ethtool_get_feature_mask(u32 eth_cmd)
@@ -1533,6 +1647,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GRXCLSRLCNT:
 	case ETHTOOL_GRXCLSRULE:
 	case ETHTOOL_GRXCLSRLALL:
+	case ETHTOOL_GFEATURES:
 		break;
 	default:
 		if (!capable(CAP_NET_ADMIN))
@@ -1678,6 +1793,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXFHINDIR:
 		rc = ethtool_set_rxfh_indir(dev, useraddr);
 		break;
+	case ETHTOOL_GFEATURES:
+		rc = ethtool_get_features(dev, useraddr);
+		break;
+	case ETHTOOL_SFEATURES:
+		rc = ethtool_set_features(dev, useraddr);
+		break;
 	case ETHTOOL_GTXCSUM:
 	case ETHTOOL_GSG:
 	case ETHTOOL_GTSO:
-- 
cgit v1.2.3


From e83d360d9a7e5d71d55c13e96b19109a2ea23bf0 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 15 Feb 2011 16:59:18 +0000
Subject: net: introduce NETIF_F_RXCSUM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce NETIF_F_RXCSUM to replace device-private flags for RX checksum
offload. Integrate it with ndo_fix_features.

ethtool_op_get_rx_csum() is removed altogether as nothing in-tree uses it.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h   |  1 -
 include/linux/netdevice.h |  5 ++++-
 net/core/ethtool.c        | 47 +++++++++++++++++++++++------------------------
 3 files changed, 27 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 806e716bb4fb..54d776c2c1b5 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -625,7 +625,6 @@ struct net_device;
 
 /* Some generic methods drivers may use in their ethtool_ops */
 u32 ethtool_op_get_link(struct net_device *dev);
-u32 ethtool_op_get_rx_csum(struct net_device *dev);
 u32 ethtool_op_get_tx_csum(struct net_device *dev);
 int ethtool_op_set_tx_csum(struct net_device *dev, u32 data);
 int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 85f67e225f60..ffe56c16df8a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -977,6 +977,7 @@ struct net_device {
 #define NETIF_F_FCOE_MTU	(1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
 #define NETIF_F_NTUPLE		(1 << 27) /* N-tuple filters supported */
 #define NETIF_F_RXHASH		(1 << 28) /* Receive hashing offload */
+#define NETIF_F_RXCSUM		(1 << 29) /* Receive checksumming offload */
 
 	/* Segmentation offload features */
 #define NETIF_F_GSO_SHIFT	16
@@ -992,7 +993,7 @@ struct net_device {
 	/* = all defined minus driver/device-class-related */
 #define NETIF_F_NEVER_CHANGE	(NETIF_F_HIGHDMA | NETIF_F_VLAN_CHALLENGED | \
 				  NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
-#define NETIF_F_ETHTOOL_BITS	(0x1f3fffff & ~NETIF_F_NEVER_CHANGE)
+#define NETIF_F_ETHTOOL_BITS	(0x3f3fffff & ~NETIF_F_NEVER_CHANGE)
 
 	/* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | \
@@ -2510,6 +2511,8 @@ static inline int dev_ethtool_get_settings(struct net_device *dev,
 
 static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev)
 {
+	if (dev->hw_features & NETIF_F_RXCSUM)
+		return !!(dev->features & NETIF_F_RXCSUM);
 	if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum)
 		return 0;
 	return dev->ethtool_ops->get_rx_csum(dev);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 65b3d50a6df2..66cdc76770ce 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -34,12 +34,6 @@ u32 ethtool_op_get_link(struct net_device *dev)
 }
 EXPORT_SYMBOL(ethtool_op_get_link);
 
-u32 ethtool_op_get_rx_csum(struct net_device *dev)
-{
-	return (dev->features & NETIF_F_ALL_CSUM) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_rx_csum);
-
 u32 ethtool_op_get_tx_csum(struct net_device *dev)
 {
 	return (dev->features & NETIF_F_ALL_CSUM) != 0;
@@ -274,7 +268,7 @@ static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GS
 	/* NETIF_F_FCOE_MTU */        "fcoe-mtu",
 	/* NETIF_F_NTUPLE */          "rx-ntuple-filter",
 	/* NETIF_F_RXHASH */          "rx-hashing",
-	"",
+	/* NETIF_F_RXCSUM */          "rx-checksum",
 	"",
 	"",
 };
@@ -313,6 +307,9 @@ static u32 ethtool_get_feature_mask(u32 eth_cmd)
 	case ETHTOOL_GTXCSUM:
 	case ETHTOOL_STXCSUM:
 		return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM;
+	case ETHTOOL_GRXCSUM:
+	case ETHTOOL_SRXCSUM:
+		return NETIF_F_RXCSUM;
 	case ETHTOOL_GSG:
 	case ETHTOOL_SSG:
 		return NETIF_F_SG;
@@ -343,6 +340,8 @@ static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
 	switch (ethcmd) {
 	case ETHTOOL_GTXCSUM:
 		return ops->get_tx_csum;
+	case ETHTOOL_GRXCSUM:
+		return ops->get_rx_csum;
 	case ETHTOOL_SSG:
 		return ops->get_sg;
 	case ETHTOOL_STSO:
@@ -354,6 +353,11 @@ static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
 	}
 }
 
+static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev)
+{
+	return !!(dev->features & NETIF_F_ALL_CSUM);
+}
+
 static int ethtool_get_one_feature(struct net_device *dev,
 	char __user *useraddr, u32 ethcmd)
 {
@@ -369,6 +373,10 @@ static int ethtool_get_one_feature(struct net_device *dev,
 
 		actor = __ethtool_get_one_feature_actor(dev, ethcmd);
 
+		/* bug compatibility with old get_rx_csum */
+		if (ethcmd == ETHTOOL_GRXCSUM && !actor)
+			actor = __ethtool_get_rx_csum_oldbug;
+
 		if (actor)
 			edata.data = actor(dev);
 	}
@@ -379,6 +387,7 @@ static int ethtool_get_one_feature(struct net_device *dev,
 }
 
 static int __ethtool_set_tx_csum(struct net_device *dev, u32 data);
+static int __ethtool_set_rx_csum(struct net_device *dev, u32 data);
 static int __ethtool_set_sg(struct net_device *dev, u32 data);
 static int __ethtool_set_tso(struct net_device *dev, u32 data);
 static int __ethtool_set_ufo(struct net_device *dev, u32 data);
@@ -416,6 +425,8 @@ static int ethtool_set_one_feature(struct net_device *dev,
 	switch (ethcmd) {
 	case ETHTOOL_STXCSUM:
 		return __ethtool_set_tx_csum(dev, edata.data);
+	case ETHTOOL_SRXCSUM:
+		return __ethtool_set_rx_csum(dev, edata.data);
 	case ETHTOOL_SSG:
 		return __ethtool_set_sg(dev, edata.data);
 	case ETHTOOL_STSO:
@@ -1404,20 +1415,15 @@ static int __ethtool_set_tx_csum(struct net_device *dev, u32 data)
 	return dev->ethtool_ops->set_tx_csum(dev, data);
 }
 
-static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr)
+static int __ethtool_set_rx_csum(struct net_device *dev, u32 data)
 {
-	struct ethtool_value edata;
-
 	if (!dev->ethtool_ops->set_rx_csum)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&edata, useraddr, sizeof(edata)))
-		return -EFAULT;
-
-	if (!edata.data && dev->ethtool_ops->set_sg)
+	if (!data)
 		dev->features &= ~NETIF_F_GRO;
 
-	return dev->ethtool_ops->set_rx_csum(dev, edata.data);
+	return dev->ethtool_ops->set_rx_csum(dev, data);
 }
 
 static int __ethtool_set_tso(struct net_device *dev, u32 data)
@@ -1765,15 +1771,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SPAUSEPARAM:
 		rc = ethtool_set_pauseparam(dev, useraddr);
 		break;
-	case ETHTOOL_GRXCSUM:
-		rc = ethtool_get_value(dev, useraddr, ethcmd,
-				       (dev->ethtool_ops->get_rx_csum ?
-					dev->ethtool_ops->get_rx_csum :
-					ethtool_op_get_rx_csum));
-		break;
-	case ETHTOOL_SRXCSUM:
-		rc = ethtool_set_rx_csum(dev, useraddr);
-		break;
 	case ETHTOOL_TEST:
 		rc = ethtool_self_test(dev, useraddr);
 		break;
@@ -1846,6 +1843,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 		rc = ethtool_set_features(dev, useraddr);
 		break;
 	case ETHTOOL_GTXCSUM:
+	case ETHTOOL_GRXCSUM:
 	case ETHTOOL_GSG:
 	case ETHTOOL_GTSO:
 	case ETHTOOL_GUFO:
@@ -1854,6 +1852,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 		rc = ethtool_get_one_feature(dev, useraddr, ethcmd);
 		break;
 	case ETHTOOL_STXCSUM:
+	case ETHTOOL_SRXCSUM:
 	case ETHTOOL_SSG:
 	case ETHTOOL_STSO:
 	case ETHTOOL_SUFO:
-- 
cgit v1.2.3


From 6e57b1d6a8d8ed1998229b71c102be1997e397c6 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Fri, 11 Feb 2011 17:45:40 -0800
Subject: RTC: Revert UIE emulation removal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Uwe pointed out that my alarm based UIE emulation is not sufficient
to replace the older timer/polling based UIE emulation on devices
where there is no alarm irq. This causes rtc devices without alarms
to return -EINVAL to UIE ioctls. The fix is to re-instate the old
timer/polling method for devices without alarm irqs.

This patch reverts the following commits:
042620a018afcfba1d678062b62e46 - Remove UIE emulation
1daeddd5962acad1bea55e524fc0fa - Cleanup removed UIE emulation declaration
b5cc8ca1c9c3a37eaddf709b2fd3e1 - Remove Kconfig symbol for UIE emulation

The emulation mode will still need to be wired-in with a following
patch before it will work.

CC: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
CC: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/Kconfig   |  12 ++++++
 drivers/rtc/rtc-dev.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/rtc.h   |  14 +++++++
 3 files changed, 130 insertions(+)

(limited to 'include')

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index cdd97192dc69..4941cade319f 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -97,6 +97,18 @@ config RTC_INTF_DEV
 
 	  If unsure, say Y.
 
+config RTC_INTF_DEV_UIE_EMUL
+	bool "RTC UIE emulation on dev interface"
+	depends on RTC_INTF_DEV
+	help
+	  Provides an emulation for RTC_UIE if the underlying rtc chip
+	  driver does not expose RTC_UIE ioctls. Those requests generate
+	  once-per-second update interrupts, used for synchronization.
+
+	  The emulation code will read the time from the hardware
+	  clock several times per second, please enable this option
+	  only if you know that you really need it.
+
 config RTC_DRV_TEST
 	tristate "Test driver/device"
 	help
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index 37c3cc1b3dd5..dfa72c9c2687 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -46,6 +46,105 @@ static int rtc_dev_open(struct inode *inode, struct file *file)
 	return err;
 }
 
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+/*
+ * Routine to poll RTC seconds field for change as often as possible,
+ * after first RTC_UIE use timer to reduce polling
+ */
+static void rtc_uie_task(struct work_struct *work)
+{
+	struct rtc_device *rtc =
+		container_of(work, struct rtc_device, uie_task);
+	struct rtc_time tm;
+	int num = 0;
+	int err;
+
+	err = rtc_read_time(rtc, &tm);
+
+	spin_lock_irq(&rtc->irq_lock);
+	if (rtc->stop_uie_polling || err) {
+		rtc->uie_task_active = 0;
+	} else if (rtc->oldsecs != tm.tm_sec) {
+		num = (tm.tm_sec + 60 - rtc->oldsecs) % 60;
+		rtc->oldsecs = tm.tm_sec;
+		rtc->uie_timer.expires = jiffies + HZ - (HZ/10);
+		rtc->uie_timer_active = 1;
+		rtc->uie_task_active = 0;
+		add_timer(&rtc->uie_timer);
+	} else if (schedule_work(&rtc->uie_task) == 0) {
+		rtc->uie_task_active = 0;
+	}
+	spin_unlock_irq(&rtc->irq_lock);
+	if (num)
+		rtc_update_irq(rtc, num, RTC_UF | RTC_IRQF);
+}
+static void rtc_uie_timer(unsigned long data)
+{
+	struct rtc_device *rtc = (struct rtc_device *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc->irq_lock, flags);
+	rtc->uie_timer_active = 0;
+	rtc->uie_task_active = 1;
+	if ((schedule_work(&rtc->uie_task) == 0))
+		rtc->uie_task_active = 0;
+	spin_unlock_irqrestore(&rtc->irq_lock, flags);
+}
+
+static int clear_uie(struct rtc_device *rtc)
+{
+	spin_lock_irq(&rtc->irq_lock);
+	if (rtc->uie_irq_active) {
+		rtc->stop_uie_polling = 1;
+		if (rtc->uie_timer_active) {
+			spin_unlock_irq(&rtc->irq_lock);
+			del_timer_sync(&rtc->uie_timer);
+			spin_lock_irq(&rtc->irq_lock);
+			rtc->uie_timer_active = 0;
+		}
+		if (rtc->uie_task_active) {
+			spin_unlock_irq(&rtc->irq_lock);
+			flush_scheduled_work();
+			spin_lock_irq(&rtc->irq_lock);
+		}
+		rtc->uie_irq_active = 0;
+	}
+	spin_unlock_irq(&rtc->irq_lock);
+	return 0;
+}
+
+static int set_uie(struct rtc_device *rtc)
+{
+	struct rtc_time tm;
+	int err;
+
+	err = rtc_read_time(rtc, &tm);
+	if (err)
+		return err;
+	spin_lock_irq(&rtc->irq_lock);
+	if (!rtc->uie_irq_active) {
+		rtc->uie_irq_active = 1;
+		rtc->stop_uie_polling = 0;
+		rtc->oldsecs = tm.tm_sec;
+		rtc->uie_task_active = 1;
+		if (schedule_work(&rtc->uie_task) == 0)
+			rtc->uie_task_active = 0;
+	}
+	rtc->irq_data = 0;
+	spin_unlock_irq(&rtc->irq_lock);
+	return 0;
+}
+
+int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, unsigned int enabled)
+{
+	if (enabled)
+		return set_uie(rtc);
+	else
+		return clear_uie(rtc);
+}
+EXPORT_SYMBOL(rtc_dev_update_irq_enable_emul);
+
+#endif /* CONFIG_RTC_INTF_DEV_UIE_EMUL */
 
 static ssize_t
 rtc_dev_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
@@ -387,6 +486,11 @@ void rtc_dev_prepare(struct rtc_device *rtc)
 
 	rtc->dev.devt = MKDEV(MAJOR(rtc_devt), rtc->id);
 
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+	INIT_WORK(&rtc->uie_task, rtc_uie_task);
+	setup_timer(&rtc->uie_timer, rtc_uie_timer, (unsigned long)rtc);
+#endif
+
 	cdev_init(&rtc->char_dev, &rtc_dev_fops);
 	rtc->char_dev.owner = rtc->owner;
 }
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index a0b639f8e805..80408e711bed 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -203,6 +203,18 @@ struct rtc_device
 	struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */
 	int pie_enabled;
 	struct work_struct irqwork;
+
+
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+	struct work_struct uie_task;
+	struct timer_list uie_timer;
+	/* Those fields are protected by rtc->irq_lock */
+	unsigned int oldsecs;
+	unsigned int uie_irq_active:1;
+	unsigned int stop_uie_polling:1;
+	unsigned int uie_task_active:1;
+	unsigned int uie_timer_active:1;
+#endif
 };
 #define to_rtc_device(d) container_of(d, struct rtc_device, dev)
 
@@ -235,6 +247,8 @@ extern int rtc_irq_set_freq(struct rtc_device *rtc,
 				struct rtc_task *task, int freq);
 extern int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled);
 extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled);
+extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc,
+						unsigned int enabled);
 
 void rtc_aie_update_irq(void *private);
 void rtc_uie_update_irq(void *private);
-- 
cgit v1.2.3


From 456d66ecd09e3bc326b93174745faafb6ac378d6 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Fri, 11 Feb 2011 18:15:23 -0800
Subject: RTC: Re-enable UIE timer/polling emulation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch re-enables UIE timer/polling emulation for rtc devices
that do not support alarm irqs.

CC: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
CC: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/interface.c | 18 +++++++++++++++++-
 drivers/rtc/rtc-dev.c   |  2 +-
 include/linux/rtc.h     |  1 +
 3 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 413ae0537915..cb2f0728fd70 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -228,6 +228,12 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled)
 	if (err)
 		return err;
 
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+	if (enabled == 0 && rtc->uie_irq_active) {
+		mutex_unlock(&rtc->ops_lock);
+		return rtc_dev_update_irq_enable_emul(rtc, 0);
+	}
+#endif
 	/* make sure we're changing state */
 	if (rtc->uie_rtctimer.enabled == enabled)
 		goto out;
@@ -247,6 +253,16 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled)
 
 out:
 	mutex_unlock(&rtc->ops_lock);
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+	/*
+	 * Enable emulation if the driver did not provide
+	 * the update_irq_enable function pointer or if returned
+	 * -EINVAL to signal that it has been configured without
+	 * interrupts or that are not available at the moment.
+	 */
+	if (err == -EINVAL)
+		err = rtc_dev_update_irq_enable_emul(rtc, enabled);
+#endif
 	return err;
 
 }
@@ -262,7 +278,7 @@ EXPORT_SYMBOL_GPL(rtc_update_irq_enable);
  *
  * Triggers the registered irq_task function callback.
  */
-static void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode)
+void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode)
 {
 	unsigned long flags;
 
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index dfa72c9c2687..d0e06edb14c5 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -76,7 +76,7 @@ static void rtc_uie_task(struct work_struct *work)
 	}
 	spin_unlock_irq(&rtc->irq_lock);
 	if (num)
-		rtc_update_irq(rtc, num, RTC_UF | RTC_IRQF);
+		rtc_handle_legacy_irq(rtc, num, RTC_UF);
 }
 static void rtc_uie_timer(unsigned long data)
 {
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 80408e711bed..89c3e5182991 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -250,6 +250,7 @@ extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled);
 extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc,
 						unsigned int enabled);
 
+void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode);
 void rtc_aie_update_irq(void *private);
 void rtc_uie_update_irq(void *private);
 enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer);
-- 
cgit v1.2.3


From 3c7bd1a14071b99d6535b710bc998ae5d3abbb66 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 16 Feb 2011 14:08:44 -0800
Subject: net: Add initial_ref arg to dst_alloc().

This allows avoiding multiple writes to the initial __refcnt.

The most simplest cases of wanting an initial reference of "1"
in ipv4 and ipv6 have been converted, the rest have been left
along and kept at the existing "0".

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h      | 2 +-
 net/core/dst.c         | 4 ++--
 net/decnet/dn_route.c  | 4 ++--
 net/ipv4/route.c       | 7 ++-----
 net/ipv6/route.c       | 5 ++---
 net/xfrm/xfrm_policy.c | 2 +-
 6 files changed, 10 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index e01855de21e8..23b564d3e110 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -352,7 +352,7 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 }
 
 extern int dst_discard(struct sk_buff *skb);
-extern void * dst_alloc(struct dst_ops * ops);
+extern void *dst_alloc(struct dst_ops * ops, int initial_ref);
 extern void __dst_free(struct dst_entry * dst);
 extern struct dst_entry *dst_destroy(struct dst_entry * dst);
 
diff --git a/net/core/dst.c b/net/core/dst.c
index c1674fde827d..91104d35de7d 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -166,7 +166,7 @@ EXPORT_SYMBOL(dst_discard);
 
 const u32 dst_default_metrics[RTAX_MAX];
 
-void *dst_alloc(struct dst_ops *ops)
+void *dst_alloc(struct dst_ops *ops, int initial_ref)
 {
 	struct dst_entry *dst;
 
@@ -177,7 +177,7 @@ void *dst_alloc(struct dst_ops *ops)
 	dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC);
 	if (!dst)
 		return NULL;
-	atomic_set(&dst->__refcnt, 0);
+	atomic_set(&dst->__refcnt, initial_ref);
 	dst->ops = ops;
 	dst->lastuse = jiffies;
 	dst->path = dst;
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 42c9c62d3417..06c054d5ccba 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1122,7 +1122,7 @@ make_route:
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
 
-	rt = dst_alloc(&dn_dst_ops);
+	rt = dst_alloc(&dn_dst_ops, 0);
 	if (rt == NULL)
 		goto e_nobufs;
 
@@ -1383,7 +1383,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
 	}
 
 make_route:
-	rt = dst_alloc(&dn_dst_ops);
+	rt = dst_alloc(&dn_dst_ops, 0);
 	if (rt == NULL)
 		goto e_nobufs;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 79a287181025..9841543c468d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1818,12 +1818,10 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 
 static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
 {
-	struct rtable *rt = dst_alloc(&ipv4_dst_ops);
+	struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1);
 	if (rt) {
 		rt->dst.obsolete = -1;
 
-		atomic_set(&rt->dst.__refcnt, 1);
-
 		rt->dst.flags = DST_HOST |
 			(nopolicy ? DST_NOPOLICY : 0) |
 			(noxfrm ? DST_NOXFRM : 0);
@@ -2679,12 +2677,11 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi
 {
 	struct rtable *ort = *rp;
 	struct rtable *rt = (struct rtable *)
-		dst_alloc(&ipv4_dst_blackhole_ops);
+		dst_alloc(&ipv4_dst_blackhole_ops, 1);
 
 	if (rt) {
 		struct dst_entry *new = &rt->dst;
 
-		atomic_set(&new->__refcnt, 1);
 		new->__use = 1;
 		new->input = dst_discard;
 		new->output = dst_discard;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ad8556e6fd41..7946b53692da 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -221,7 +221,7 @@ static struct rt6_info ip6_blk_hole_entry_template = {
 /* allocate dst with ip6_dst_ops */
 static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
 {
-	return (struct rt6_info *)dst_alloc(ops);
+	return (struct rt6_info *)dst_alloc(ops, 0);
 }
 
 static void ip6_dst_destroy(struct dst_entry *dst)
@@ -873,13 +873,12 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl
 {
 	struct rt6_info *ort = (struct rt6_info *) *dstp;
 	struct rt6_info *rt = (struct rt6_info *)
-		dst_alloc(&ip6_dst_blackhole_ops);
+		dst_alloc(&ip6_dst_blackhole_ops, 1);
 	struct dst_entry *new = NULL;
 
 	if (rt) {
 		new = &rt->dst;
 
-		atomic_set(&new->__refcnt, 1);
 		new->__use = 1;
 		new->input = dst_discard;
 		new->output = dst_discard;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8b3ef404c794..3f1257add4f3 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1340,7 +1340,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 	default:
 		BUG();
 	}
-	xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS);
+	xdst = dst_alloc(dst_ops, 0) ?: ERR_PTR(-ENOBUFS);
 	xfrm_policy_put_afinfo(afinfo);
 
 	xdst->flo.ops = &xfrm_bundle_fc_ops;
-- 
cgit v1.2.3


From b6bf3ca032c9cd517526178f579e7a4e395c6e45 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 16 Feb 2011 22:04:57 -0800
Subject: ipv4: Mark fib_combine_itag()'s 'res' arg as const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 08b46b8c3031..b3019d89e8be 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -232,7 +232,7 @@ extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res
 extern void fib_trie_init(void);
 extern struct fib_table *fib_trie_table(u32 id);
 
-static inline void fib_combine_itag(u32 *itag, struct fib_result *res)
+static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 {
 #ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
-- 
cgit v1.2.3


From 982721f3911b2619482e05910644e5699fbeb065 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 16 Feb 2011 21:44:24 -0800
Subject: ipv4: Use const'ify fib_result deep in the route call chains.

The only troublesome bit here is __mkroute_output which wants
to override res->fi and res->type, compute those in local
variables instead.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h |  2 +-
 net/ipv4/fib_rules.c |  2 +-
 net/ipv4/route.c     | 32 +++++++++++++++++---------------
 3 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b3019d89e8be..523a170b0ecb 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -202,7 +202,7 @@ extern int __net_init fib4_rules_init(struct net *net);
 extern void __net_exit fib4_rules_exit(struct net *net);
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
-extern u32 fib_rules_tclass(struct fib_result *res);
+extern u32 fib_rules_tclass(const struct fib_result *res);
 #endif
 
 extern int fib_lookup(struct net *n, struct flowi *flp, struct fib_result *res);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 9cefe72029cf..3018efbaea77 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -47,7 +47,7 @@ struct fib4_rule {
 };
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
-u32 fib_rules_tclass(struct fib_result *res)
+u32 fib_rules_tclass(const struct fib_result *res)
 {
 	return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9841543c468d..2facde0985f9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1787,10 +1787,10 @@ static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
 	}
 }
 
-static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
+static void rt_set_nexthop(struct rtable *rt, const struct fib_result *res,
+			   struct fib_info *fi, u16 type, u32 itag)
 {
 	struct dst_entry *dst = &rt->dst;
-	struct fib_info *fi = res->fi;
 
 	if (fi) {
 		if (FIB_RES_GW(*res) &&
@@ -1813,7 +1813,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 #endif
 	set_class_tag(rt, itag);
 #endif
-	rt->rt_type = res->type;
+	rt->rt_type = type;
 }
 
 static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
@@ -1939,7 +1939,7 @@ static void ip_handle_martian_source(struct net_device *dev,
 
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
-			   struct fib_result *res,
+			   const struct fib_result *res,
 			   struct in_device *in_dev,
 			   __be32 daddr, __be32 saddr, u32 tos,
 			   struct rtable **result)
@@ -2018,7 +2018,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->dst.output = ip_output;
 	rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
 
-	rt_set_nexthop(rth, res, itag);
+	rt_set_nexthop(rth, res, res->fi, res->type, itag);
 
 	rth->rt_flags = flags;
 
@@ -2319,23 +2319,25 @@ skip_cache:
 EXPORT_SYMBOL(ip_route_input_common);
 
 /* called with rcu_read_lock() */
-static struct rtable *__mkroute_output(struct fib_result *res,
+static struct rtable *__mkroute_output(const struct fib_result *res,
 				       const struct flowi *fl,
 				       const struct flowi *oldflp,
 				       struct net_device *dev_out,
 				       unsigned int flags)
 {
+	struct fib_info *fi = res->fi;
 	u32 tos = RT_FL_TOS(oldflp);
 	struct in_device *in_dev;
+	u16 type = res->type;
 	struct rtable *rth;
 
 	if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags & IFF_LOOPBACK))
 		return ERR_PTR(-EINVAL);
 
 	if (ipv4_is_lbcast(fl->fl4_dst))
-		res->type = RTN_BROADCAST;
+		type = RTN_BROADCAST;
 	else if (ipv4_is_multicast(fl->fl4_dst))
-		res->type = RTN_MULTICAST;
+		type = RTN_MULTICAST;
 	else if (ipv4_is_zeronet(fl->fl4_dst))
 		return ERR_PTR(-EINVAL);
 
@@ -2346,10 +2348,10 @@ static struct rtable *__mkroute_output(struct fib_result *res,
 	if (!in_dev)
 		return ERR_PTR(-EINVAL);
 
-	if (res->type == RTN_BROADCAST) {
+	if (type == RTN_BROADCAST) {
 		flags |= RTCF_BROADCAST | RTCF_LOCAL;
-		res->fi = NULL;
-	} else if (res->type == RTN_MULTICAST) {
+		fi = NULL;
+	} else if (type == RTN_MULTICAST) {
 		flags |= RTCF_MULTICAST | RTCF_LOCAL;
 		if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
 				 oldflp->proto))
@@ -2358,8 +2360,8 @@ static struct rtable *__mkroute_output(struct fib_result *res,
 		 * default one, but do not gateway in this case.
 		 * Yes, it is hack.
 		 */
-		if (res->fi && res->prefixlen < 4)
-			res->fi = NULL;
+		if (fi && res->prefixlen < 4)
+			fi = NULL;
 	}
 
 	rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
@@ -2399,7 +2401,7 @@ static struct rtable *__mkroute_output(struct fib_result *res,
 			RT_CACHE_STAT_INC(out_slow_mc);
 		}
 #ifdef CONFIG_IP_MROUTE
-		if (res->type == RTN_MULTICAST) {
+		if (type == RTN_MULTICAST) {
 			if (IN_DEV_MFORWARD(in_dev) &&
 			    !ipv4_is_local_multicast(oldflp->fl4_dst)) {
 				rth->dst.input = ip_mr_input;
@@ -2409,7 +2411,7 @@ static struct rtable *__mkroute_output(struct fib_result *res,
 #endif
 	}
 
-	rt_set_nexthop(rth, res, 0);
+	rt_set_nexthop(rth, res, fi, type, 0);
 
 	rth->rt_flags = flags;
 	return rth;
-- 
cgit v1.2.3


From 647b2d9c61fe9a842dd89eb01b5f01e9d437993c Mon Sep 17 00:00:00 2001
From: Hema HK <hemahk@ti.com>
Date: Thu, 17 Feb 2011 12:06:09 +0530
Subject: usb: otg: TWL6030 Save the last event in otg_transceiver

Save the last event in the otg_transceiver so that it can used in the
musb driver and gadget driver to configure the musb and enable the
vbus for host mode and OTG mode, if the device is connected during boot.

Signed-off-by: Hema HK <hemahk@ti.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Paul Walmsley <paul@pwsan.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/otg/twl6030-usb.c | 3 +++
 include/linux/usb/otg.h       | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/otg/twl6030-usb.c b/drivers/usb/otg/twl6030-usb.c
index b4eda02c97f7..05f17b77d54c 100644
--- a/drivers/usb/otg/twl6030-usb.c
+++ b/drivers/usb/otg/twl6030-usb.c
@@ -262,11 +262,13 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl)
 			twl->otg.default_a = false;
 			twl->otg.state = OTG_STATE_B_IDLE;
 			twl->linkstat = status;
+			twl->otg.last_event = status;
 			blocking_notifier_call_chain(&twl->otg.notifier,
 						status, twl->otg.gadget);
 		} else {
 			status = USB_EVENT_NONE;
 			twl->linkstat = status;
+			twl->otg.last_event = status;
 			blocking_notifier_call_chain(&twl->otg.notifier,
 						status, twl->otg.gadget);
 			if (twl->asleep) {
@@ -299,6 +301,7 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl)
 		twl->otg.default_a = true;
 		twl->otg.state = OTG_STATE_A_IDLE;
 		twl->linkstat = status;
+		twl->otg.last_event = status;
 		blocking_notifier_call_chain(&twl->otg.notifier, status,
 							twl->otg.gadget);
 	} else  {
diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h
index a1a1e7a73ec9..da511eec3cb8 100644
--- a/include/linux/usb/otg.h
+++ b/include/linux/usb/otg.h
@@ -66,6 +66,7 @@ struct otg_transceiver {
 
 	u8			default_a;
 	enum usb_otg_state	state;
+	enum usb_xceiv_events	last_event;
 
 	struct usb_bus		*host;
 	struct usb_gadget	*gadget;
-- 
cgit v1.2.3


From cccad6d4b103e53fb3d1fc1467f654ecb572d047 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <balbi@ti.com>
Date: Wed, 29 Sep 2010 10:55:49 +0300
Subject: usb: otg: notifier: switch to atomic notifier

most of our notifications, will be called from IRQ
context, so an atomic notifier suits the job better.

Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/otg/ab8500-usb.c    | 6 +++---
 drivers/usb/otg/nop-usb-xceiv.c | 2 +-
 drivers/usb/otg/twl4030-usb.c   | 6 +++---
 drivers/usb/otg/twl6030-usb.c   | 8 ++++----
 include/linux/usb/otg.h         | 6 +++---
 5 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/otg/ab8500-usb.c b/drivers/usb/otg/ab8500-usb.c
index d14736b3107b..07ccea9ada40 100644
--- a/drivers/usb/otg/ab8500-usb.c
+++ b/drivers/usb/otg/ab8500-usb.c
@@ -212,7 +212,7 @@ static int ab8500_usb_link_status_update(struct ab8500_usb *ab)
 		break;
 	}
 
-	blocking_notifier_call_chain(&ab->otg.notifier, event, v);
+	atomic_notifier_call_chain(&ab->otg.notifier, event, v);
 
 	return 0;
 }
@@ -281,7 +281,7 @@ static int ab8500_usb_set_power(struct otg_transceiver *otg, unsigned mA)
 	ab->vbus_draw = mA;
 
 	if (mA)
-		blocking_notifier_call_chain(&ab->otg.notifier,
+		atomic_notifier_call_chain(&ab->otg.notifier,
 				USB_EVENT_ENUMERATED, ab->otg.gadget);
 	return 0;
 }
@@ -500,7 +500,7 @@ static int __devinit ab8500_usb_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, ab);
 
-	BLOCKING_INIT_NOTIFIER_HEAD(&ab->otg.notifier);
+	ATOMIC_INIT_NOTIFIER_HEAD(&ab->otg.notifier);
 
 	/* v1: Wait for link status to become stable.
 	 * all: Updates form set_host and set_peripheral as they are atomic.
diff --git a/drivers/usb/otg/nop-usb-xceiv.c b/drivers/usb/otg/nop-usb-xceiv.c
index 8acf165fe13b..c1e360046435 100644
--- a/drivers/usb/otg/nop-usb-xceiv.c
+++ b/drivers/usb/otg/nop-usb-xceiv.c
@@ -132,7 +132,7 @@ static int __devinit nop_usb_xceiv_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, nop);
 
-	BLOCKING_INIT_NOTIFIER_HEAD(&nop->otg.notifier);
+	ATOMIC_INIT_NOTIFIER_HEAD(&nop->otg.notifier);
 
 	return 0;
 exit:
diff --git a/drivers/usb/otg/twl4030-usb.c b/drivers/usb/otg/twl4030-usb.c
index 6ca505f333e4..2362d8352bc8 100644
--- a/drivers/usb/otg/twl4030-usb.c
+++ b/drivers/usb/otg/twl4030-usb.c
@@ -512,7 +512,7 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
 		else
 			twl4030_phy_resume(twl);
 
-		blocking_notifier_call_chain(&twl->otg.notifier, status,
+		atomic_notifier_call_chain(&twl->otg.notifier, status,
 				twl->otg.gadget);
 	}
 	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
@@ -534,7 +534,7 @@ static void twl4030_usb_phy_init(struct twl4030_usb *twl)
 			twl->asleep = 0;
 		}
 
-		blocking_notifier_call_chain(&twl->otg.notifier, status,
+		atomic_notifier_call_chain(&twl->otg.notifier, status,
 				twl->otg.gadget);
 	}
 	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
@@ -623,7 +623,7 @@ static int __devinit twl4030_usb_probe(struct platform_device *pdev)
 	if (device_create_file(&pdev->dev, &dev_attr_vbus))
 		dev_warn(&pdev->dev, "could not create sysfs file\n");
 
-	BLOCKING_INIT_NOTIFIER_HEAD(&twl->otg.notifier);
+	ATOMIC_INIT_NOTIFIER_HEAD(&twl->otg.notifier);
 
 	/* Our job is to use irqs and status from the power module
 	 * to keep the transceiver disabled when nothing's connected.
diff --git a/drivers/usb/otg/twl6030-usb.c b/drivers/usb/otg/twl6030-usb.c
index 05f17b77d54c..8a91b4b832a1 100644
--- a/drivers/usb/otg/twl6030-usb.c
+++ b/drivers/usb/otg/twl6030-usb.c
@@ -263,13 +263,13 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl)
 			twl->otg.state = OTG_STATE_B_IDLE;
 			twl->linkstat = status;
 			twl->otg.last_event = status;
-			blocking_notifier_call_chain(&twl->otg.notifier,
+			atomic_notifier_call_chain(&twl->otg.notifier,
 						status, twl->otg.gadget);
 		} else {
 			status = USB_EVENT_NONE;
 			twl->linkstat = status;
 			twl->otg.last_event = status;
-			blocking_notifier_call_chain(&twl->otg.notifier,
+			atomic_notifier_call_chain(&twl->otg.notifier,
 						status, twl->otg.gadget);
 			if (twl->asleep) {
 				regulator_disable(twl->usb3v3);
@@ -302,7 +302,7 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl)
 		twl->otg.state = OTG_STATE_A_IDLE;
 		twl->linkstat = status;
 		twl->otg.last_event = status;
-		blocking_notifier_call_chain(&twl->otg.notifier, status,
+		atomic_notifier_call_chain(&twl->otg.notifier, status,
 							twl->otg.gadget);
 	} else  {
 		twl6030_writeb(twl, TWL_MODULE_USB, USB_ID_INT_EN_HI_CLR,
@@ -419,7 +419,7 @@ static int __devinit twl6030_usb_probe(struct platform_device *pdev)
 	if (device_create_file(&pdev->dev, &dev_attr_vbus))
 		dev_warn(&pdev->dev, "could not create sysfs file\n");
 
-	BLOCKING_INIT_NOTIFIER_HEAD(&twl->otg.notifier);
+	ATOMIC_INIT_NOTIFIER_HEAD(&twl->otg.notifier);
 
 	twl->irq_enabled = true;
 	status = request_threaded_irq(twl->irq1, NULL, twl6030_usbotg_irq,
diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h
index da511eec3cb8..6e40718f5abe 100644
--- a/include/linux/usb/otg.h
+++ b/include/linux/usb/otg.h
@@ -75,7 +75,7 @@ struct otg_transceiver {
 	void __iomem			*io_priv;
 
 	/* for notification of usb_xceiv_events */
-	struct blocking_notifier_head	notifier;
+	struct atomic_notifier_head	notifier;
 
 	/* to pass extra port status to the root hub */
 	u16			port_status;
@@ -235,13 +235,13 @@ otg_start_srp(struct otg_transceiver *otg)
 static inline int
 otg_register_notifier(struct otg_transceiver *otg, struct notifier_block *nb)
 {
-	return blocking_notifier_chain_register(&otg->notifier, nb);
+	return atomic_notifier_chain_register(&otg->notifier, nb);
 }
 
 static inline void
 otg_unregister_notifier(struct otg_transceiver *otg, struct notifier_block *nb)
 {
-	blocking_notifier_chain_unregister(&otg->notifier, nb);
+	atomic_notifier_chain_unregister(&otg->notifier, nb);
 }
 
 /* for OTG controller drivers (and maybe other stuff) */
-- 
cgit v1.2.3


From b38360a284f8acab4ae431b387c05a4e19ff4129 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <randy.dunlap@oracle.com>
Date: Sun, 6 Feb 2011 21:57:18 -0800
Subject: kobject.h: fix build when CONFIG_HOTPLUG is disabled

When CONFIG_HOTPLUG is not enabled, the inline function add_uevent_var()
needs to have its __attribute__ before the function name/parameters,
otherwise there are syntax errors.

linux-next-20110207/include/linux/kobject.h:232: error: expected ',' or ';' before '{' token

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/kobject.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 15e82c132f78..9229b64ee3aa 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -226,9 +226,8 @@ static inline int kobject_uevent_env(struct kobject *kobj,
 				      char *envp[])
 { return 0; }
 
-static inline int add_uevent_var(struct kobj_uevent_env *env,
-				 const char *format, ...)
-	__attribute__((format(printf, 2, 3)))
+static inline __attribute__((format(printf, 2, 3)))
+int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...)
 { return 0; }
 
 static inline int kobject_action_type(const char *buf, size_t count,
-- 
cgit v1.2.3


From 71d642908d4e8e7a2a4a6e0490432e719ff466d5 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Feb 2011 23:23:27 +0100
Subject: Driver core: convert platform_{get,set}_drvdata to static inline
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch converts the macros for platform_{get,set}_drvdata to
static inline functions to add typechecking.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/platform_device.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 2e700ec0601f..d96db9825708 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -130,8 +130,15 @@ extern void platform_driver_unregister(struct platform_driver *);
 extern int platform_driver_probe(struct platform_driver *driver,
 		int (*probe)(struct platform_device *));
 
-#define platform_get_drvdata(_dev)	dev_get_drvdata(&(_dev)->dev)
-#define platform_set_drvdata(_dev,data)	dev_set_drvdata(&(_dev)->dev, (data))
+static inline void *platform_get_drvdata(const struct platform_device *pdev)
+{
+	return dev_get_drvdata(&pdev->dev);
+}
+
+static inline void platform_set_drvdata(struct platform_device *pdev, void *data)
+{
+	dev_set_drvdata(&pdev->dev, data);
+}
 
 extern struct platform_device *platform_create_bundle(struct platform_driver *driver,
 					int (*probe)(struct platform_device *),
-- 
cgit v1.2.3


From 3c18d4de86e4a7f93815c081e50e0543fa27200f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 18 Feb 2011 11:32:28 -0800
Subject: Expand CONFIG_DEBUG_LIST to several other list operations

When list debugging is enabled, we aim to readably show list corruption
errors, and the basic list_add/list_del operations end up having extra
debugging code in them to do some basic validation of the list entries.

However, "list_del_init()" and "list_move[_tail]()" ended up avoiding
the debug code due to how they were written. This fixes that.

So the _next_ time we have list_move() problems with stale list entries,
we'll hopefully have an easier time finding them..

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 12 +++++++++---
 lib/list_debug.c     | 39 ++++++++++++++++++++++++++-------------
 2 files changed, 35 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index 9a5f8a71810c..3a54266a1e85 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -96,6 +96,11 @@ static inline void __list_del(struct list_head * prev, struct list_head * next)
  * in an undefined state.
  */
 #ifndef CONFIG_DEBUG_LIST
+static inline void __list_del_entry(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+}
+
 static inline void list_del(struct list_head *entry)
 {
 	__list_del(entry->prev, entry->next);
@@ -103,6 +108,7 @@ static inline void list_del(struct list_head *entry)
 	entry->prev = LIST_POISON2;
 }
 #else
+extern void __list_del_entry(struct list_head *entry);
 extern void list_del(struct list_head *entry);
 #endif
 
@@ -135,7 +141,7 @@ static inline void list_replace_init(struct list_head *old,
  */
 static inline void list_del_init(struct list_head *entry)
 {
-	__list_del(entry->prev, entry->next);
+	__list_del_entry(entry);
 	INIT_LIST_HEAD(entry);
 }
 
@@ -146,7 +152,7 @@ static inline void list_del_init(struct list_head *entry)
  */
 static inline void list_move(struct list_head *list, struct list_head *head)
 {
-	__list_del(list->prev, list->next);
+	__list_del_entry(list);
 	list_add(list, head);
 }
 
@@ -158,7 +164,7 @@ static inline void list_move(struct list_head *list, struct list_head *head)
 static inline void list_move_tail(struct list_head *list,
 				  struct list_head *head)
 {
-	__list_del(list->prev, list->next);
+	__list_del_entry(list);
 	list_add_tail(list, head);
 }
 
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 344c710d16ca..b8029a5583ff 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -35,6 +35,31 @@ void __list_add(struct list_head *new,
 }
 EXPORT_SYMBOL(__list_add);
 
+void __list_del_entry(struct list_head *entry)
+{
+	struct list_head *prev, *next;
+
+	prev = entry->prev;
+	next = entry->next;
+
+	if (WARN(next == LIST_POISON1,
+		"list_del corruption, %p->next is LIST_POISON1 (%p)\n",
+		entry, LIST_POISON1) ||
+	    WARN(prev == LIST_POISON2,
+		"list_del corruption, %p->prev is LIST_POISON2 (%p)\n",
+		entry, LIST_POISON2) ||
+	    WARN(prev->next != entry,
+		"list_del corruption. prev->next should be %p, "
+		"but was %p\n", entry, prev->next) ||
+	    WARN(next->prev != entry,
+		"list_del corruption. next->prev should be %p, "
+		"but was %p\n", entry, next->prev))
+		return;
+
+	__list_del(prev, next);
+}
+EXPORT_SYMBOL(__list_del_entry);
+
 /**
  * list_del - deletes entry from list.
  * @entry: the element to delete from the list.
@@ -43,19 +68,7 @@ EXPORT_SYMBOL(__list_add);
  */
 void list_del(struct list_head *entry)
 {
-	WARN(entry->next == LIST_POISON1,
-		"list_del corruption, next is LIST_POISON1 (%p)\n",
-		LIST_POISON1);
-	WARN(entry->next != LIST_POISON1 && entry->prev == LIST_POISON2,
-		"list_del corruption, prev is LIST_POISON2 (%p)\n",
-		LIST_POISON2);
-	WARN(entry->prev->next != entry,
-		"list_del corruption. prev->next should be %p, "
-		"but was %p\n", entry, entry->prev->next);
-	WARN(entry->next->prev != entry,
-		"list_del corruption. next->prev should be %p, "
-		"but was %p\n", entry, entry->next->prev);
-	__list_del(entry->prev, entry->next);
+	__list_del_entry(entry);
 	entry->next = LIST_POISON1;
 	entry->prev = LIST_POISON2;
 }
-- 
cgit v1.2.3


From fd23c3b31107e2fc483301ee923d8a1db14e53f4 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 18 Feb 2011 12:42:28 -0800
Subject: ipv4: Add hash table of interface addresses.

This will be used to optimize __ip_dev_find() and friends.

With help from Eric Dumazet.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inetdevice.h |  1 +
 net/ipv4/devinet.c         | 45 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ae8fdc54e0c0..5f8146695b7f 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -144,6 +144,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 #define IN_DEV_ARP_NOTIFY(in_dev)	IN_DEV_MAXCONF((in_dev), ARP_NOTIFY)
 
 struct in_ifaddr {
+	struct hlist_node	hash;
 	struct in_ifaddr	*ifa_next;
 	struct in_device	*ifa_dev;
 	struct rcu_head		rcu_head;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 748cb5b337bd..2fe50765a672 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -51,6 +51,7 @@
 #include <linux/inetdevice.h>
 #include <linux/igmp.h>
 #include <linux/slab.h>
+#include <linux/hash.h>
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 #endif
@@ -92,6 +93,38 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
 	[IFA_LABEL]     	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
 };
 
+/* inet_addr_hash's shifting is dependent upon this IN4_ADDR_HSIZE
+ * value.  So if you change this define, make appropriate changes to
+ * inet_addr_hash as well.
+ */
+#define IN4_ADDR_HSIZE	256
+static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
+static DEFINE_SPINLOCK(inet_addr_hash_lock);
+
+static inline unsigned int inet_addr_hash(struct net *net, __be32 addr)
+{
+	u32 val = (__force u32) addr ^ hash_ptr(net, 8);
+
+	return ((val ^ (val >> 8) ^ (val >> 16) ^ (val >> 24)) &
+		(IN4_ADDR_HSIZE - 1));
+}
+
+static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
+{
+	unsigned int hash = inet_addr_hash(net, ifa->ifa_address);
+
+	spin_lock(&inet_addr_hash_lock);
+	hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
+	spin_unlock(&inet_addr_hash_lock);
+}
+
+static void inet_hash_remove(struct in_ifaddr *ifa)
+{
+	spin_lock(&inet_addr_hash_lock);
+	hlist_del_init_rcu(&ifa->hash);
+	spin_unlock(&inet_addr_hash_lock);
+}
+
 static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
 
 static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
@@ -265,6 +298,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			}
 
 			if (!do_promote) {
+				inet_hash_remove(ifa);
 				*ifap1 = ifa->ifa_next;
 
 				rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid);
@@ -281,6 +315,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
+	inet_hash_remove(ifa1);
 
 	/* 3. Announce address deletion */
 
@@ -368,6 +403,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	ifa->ifa_next = *ifap;
 	*ifap = ifa;
 
+	inet_hash_insert(dev_net(in_dev->dev), ifa);
+
 	/* Send message first, then call notifier.
 	   Notifier will trigger FIB update, so that
 	   listeners of netlink will know about new ifaddr */
@@ -521,6 +558,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
 	if (tb[IFA_ADDRESS] == NULL)
 		tb[IFA_ADDRESS] = tb[IFA_LOCAL];
 
+	INIT_HLIST_NODE(&ifa->hash);
 	ifa->ifa_prefixlen = ifm->ifa_prefixlen;
 	ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
 	ifa->ifa_flags = ifm->ifa_flags;
@@ -728,6 +766,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 		if (!ifa) {
 			ret = -ENOBUFS;
 			ifa = inet_alloc_ifa();
+			INIT_HLIST_NODE(&ifa->hash);
 			if (!ifa)
 				break;
 			if (colon)
@@ -1069,6 +1108,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 			struct in_ifaddr *ifa = inet_alloc_ifa();
 
 			if (ifa) {
+				INIT_HLIST_NODE(&ifa->hash);
 				ifa->ifa_local =
 				  ifa->ifa_address = htonl(INADDR_LOOPBACK);
 				ifa->ifa_prefixlen = 8;
@@ -1710,6 +1750,11 @@ static struct rtnl_af_ops inet_af_ops = {
 
 void __init devinet_init(void)
 {
+	int i;
+
+	for (i = 0; i < IN4_ADDR_HSIZE; i++)
+		INIT_HLIST_HEAD(&inet_addr_lst[i]);
+
 	register_pernet_subsys(&devinet_ops);
 
 	register_gifconf(PF_INET, inet_gifconf);
-- 
cgit v1.2.3


From f2f1794835f1d8900d2b15d114c54e70c849809b Mon Sep 17 00:00:00 2001
From: Tony SIM <chinyeow.sim.xt@renesas.com>
Date: Tue, 15 Feb 2011 19:10:27 +0900
Subject: staging: iio: ak8975: add platform data.

As some of the platform not support irq_to_gpio, we pass gpio port
by platform data.

Signed-off-by: Tony SIM <chinyeow.sim.xt@renesas.com>
Signed-off-by: Andrew Chew <achew@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/staging/iio/magnetometer/ak8975.c |  8 +++++++-
 include/linux/input/ak8975.h              | 20 ++++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/input/ak8975.h

(limited to 'include')

diff --git a/drivers/staging/iio/magnetometer/ak8975.c b/drivers/staging/iio/magnetometer/ak8975.c
index 420f206cf517..80c0f4137076 100644
--- a/drivers/staging/iio/magnetometer/ak8975.c
+++ b/drivers/staging/iio/magnetometer/ak8975.c
@@ -29,6 +29,7 @@
 #include <linux/delay.h>
 
 #include <linux/gpio.h>
+#include <linux/input/ak8975.h>
 
 #include "../iio.h"
 #include "magnet.h"
@@ -435,6 +436,7 @@ static int ak8975_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct ak8975_data *data;
+	struct ak8975_platform_data *pdata;
 	int err;
 
 	/* Allocate our device context. */
@@ -452,7 +454,11 @@ static int ak8975_probe(struct i2c_client *client,
 
 	/* Grab and set up the supplied GPIO. */
 	data->eoc_irq = client->irq;
-	data->eoc_gpio = irq_to_gpio(client->irq);
+	pdata = client->dev.platform_data;
+	if (pdata)
+		data->eoc_gpio = pdata->gpio;
+	else
+		data->eoc_gpio = irq_to_gpio(client->irq);
 
 	if (!data->eoc_gpio) {
 		dev_err(&client->dev, "failed, no valid GPIO\n");
diff --git a/include/linux/input/ak8975.h b/include/linux/input/ak8975.h
new file mode 100644
index 000000000000..25d41eb10c3e
--- /dev/null
+++ b/include/linux/input/ak8975.h
@@ -0,0 +1,20 @@
+/*
+ * ak8975 platform support
+ *
+ * Copyright (C) 2010 Renesas Solutions Corp.
+ *
+ * Author: Tony SIM <chinyeow.sim.xt@renesas.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _AK8975_H
+#define _AK8975_H
+
+struct ak8975_platform_data {
+	int gpio;
+};
+
+#endif
-- 
cgit v1.2.3


From 8b2988c13da00ac9d03f1764fdb26180c188f9e0 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Wed, 16 Feb 2011 13:58:26 +0100
Subject: ssb: remove invalid define SSB_TMSLOW_PHYCLK
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It was incorrectly introduced in d2730b2a6a019d14455556019d744ab051e6554b. We
have already fixed function to use correct define, but forgot remove old one.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Cc: Gábor Stefanik <netrolller.3d@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/ssb/ssb_regs.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h
index df9211a84634..9b1125bea1fc 100644
--- a/include/linux/ssb/ssb_regs.h
+++ b/include/linux/ssb/ssb_regs.h
@@ -97,7 +97,6 @@
 #define  SSB_TMSLOW_RESET	0x00000001 /* Reset */
 #define  SSB_TMSLOW_REJECT_22	0x00000002 /* Reject (Backplane rev 2.2) */
 #define  SSB_TMSLOW_REJECT_23	0x00000004 /* Reject (Backplane rev 2.3) */
-#define  SSB_TMSLOW_PHYCLK	0x00000010 /* MAC PHY Clock Control Enable */
 #define  SSB_TMSLOW_CLOCK	0x00010000 /* Clock Enable */
 #define  SSB_TMSLOW_FGC		0x00020000 /* Force Gated Clocks On */
 #define  SSB_TMSLOW_PE		0x40000000 /* Power Management Enable */
-- 
cgit v1.2.3


From b1a1bcf714c4d79f7872a34138d100941ebb0a0b Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Thu, 17 Feb 2011 01:50:50 +0100
Subject: ssb: when needed, reject IM input while disabling device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/ssb/main.c           | 16 +++++++++++++++-
 include/linux/ssb/ssb_regs.h |  2 ++
 2 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 775c579817b4..06c0b6d5250d 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -1220,7 +1220,7 @@ static int ssb_wait_bits(struct ssb_device *dev, u16 reg, u32 bitmask,
 
 void ssb_device_disable(struct ssb_device *dev, u32 core_specific_flags)
 {
-	u32 reject;
+	u32 reject, val;
 
 	if (ssb_read32(dev, SSB_TMSLOW) & SSB_TMSLOW_RESET)
 		return;
@@ -1229,12 +1229,26 @@ void ssb_device_disable(struct ssb_device *dev, u32 core_specific_flags)
 	ssb_write32(dev, SSB_TMSLOW, reject | SSB_TMSLOW_CLOCK);
 	ssb_wait_bits(dev, SSB_TMSLOW, reject, 1000, 1);
 	ssb_wait_bits(dev, SSB_TMSHIGH, SSB_TMSHIGH_BUSY, 1000, 0);
+
+	if (ssb_read32(dev, SSB_IDLOW) & SSB_IDLOW_INITIATOR) {
+		val = ssb_read32(dev, SSB_IMSTATE);
+		val |= SSB_IMSTATE_REJECT;
+		ssb_write32(dev, SSB_IMSTATE, val);
+		ssb_wait_bits(dev, SSB_IMSTATE, SSB_IMSTATE_BUSY, 1000, 0);
+	}
+
 	ssb_write32(dev, SSB_TMSLOW,
 		    SSB_TMSLOW_FGC | SSB_TMSLOW_CLOCK |
 		    reject | SSB_TMSLOW_RESET |
 		    core_specific_flags);
 	ssb_flush_tmslow(dev);
 
+	if (ssb_read32(dev, SSB_IDLOW) & SSB_IDLOW_INITIATOR) {
+		val = ssb_read32(dev, SSB_IMSTATE);
+		val &= ~SSB_IMSTATE_REJECT;
+		ssb_write32(dev, SSB_IMSTATE, val);
+	}
+
 	ssb_write32(dev, SSB_TMSLOW,
 		    reject | SSB_TMSLOW_RESET |
 		    core_specific_flags);
diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h
index 9b1125bea1fc..402955ae48ce 100644
--- a/include/linux/ssb/ssb_regs.h
+++ b/include/linux/ssb/ssb_regs.h
@@ -85,6 +85,8 @@
 #define  SSB_IMSTATE_AP_RSV	0x00000030 /* Reserved */
 #define  SSB_IMSTATE_IBE	0x00020000 /* In Band Error */
 #define  SSB_IMSTATE_TO		0x00040000 /* Timeout */
+#define  SSB_IMSTATE_BUSY	0x01800000 /* Busy (Backplane rev >= 2.3 only) */
+#define  SSB_IMSTATE_REJECT	0x02000000 /* Reject (Backplane rev >= 2.3 only) */
 #define SSB_INTVEC		0x0F94     /* SB Interrupt Mask */
 #define  SSB_INTVEC_PCI		0x00000001 /* Enable interrupts for PCI */
 #define  SSB_INTVEC_ENET0	0x00000002 /* Enable interrupts for enet 0 */
-- 
cgit v1.2.3


From a0cd9ca2b907d7ee26575e7b63ac92dad768a75e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 11:36:33 +0100
Subject: genirq: Namespace cleanup

The irq namespace has become quite convoluted. My bad.  Clean it up
and deprecate the old functions. All new functions follow the scheme:

irq number based:
    irq_set/get/xxx/_xxx(unsigned int irq, ...)

irq_data based:
	 irq_data_set/get/xxx/_xxx(struct irq_data *d, ....)

irq_desc based:
	 irq_desc_get_xxx(struct irq_desc *desc)

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/interrupt.h | 14 +++++++--
 include/linux/irq.h       | 79 ++++++++++++++++++++++++++++++++++++++---------
 include/linux/irqdesc.h   | 44 +++++++++++++++++++++++---
 kernel/irq/chip.c         | 28 ++++++++---------
 kernel/irq/manage.c       |  6 ++--
 5 files changed, 133 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 56b7c97aaf0a..7834726dd95b 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -346,16 +346,24 @@ static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long
 }
 
 /* IRQ wakeup (PM) control: */
-extern int set_irq_wake(unsigned int irq, unsigned int on);
+extern int irq_set_irq_wake(unsigned int irq, unsigned int on);
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_wake(unsigned int irq, unsigned int on)
+{
+	return irq_set_irq_wake(irq, on);
+}
+#endif
 
 static inline int enable_irq_wake(unsigned int irq)
 {
-	return set_irq_wake(irq, 1);
+	return irq_set_irq_wake(irq, 1);
 }
 
 static inline int disable_irq_wake(unsigned int irq)
 {
-	return set_irq_wake(irq, 0);
+	return irq_set_irq_wake(irq, 0);
 }
 
 #else /* !CONFIG_GENERIC_HARDIRQS */
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 80fcb53057bc..e9f847d56c4d 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -292,8 +292,7 @@ set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
  *  IRQ_NOREQUEST and IRQ_NOPROBE)
  */
 static inline void
-set_irq_chained_handler(unsigned int irq,
-			irq_flow_handler_t handle)
+set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
 {
 	__set_irq_handler(irq, handle, 1, NULL);
 }
@@ -312,12 +311,12 @@ static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr)
 	irq_modify_status(irq, clr, 0);
 }
 
-static inline void set_irq_noprobe(unsigned int irq)
+static inline void irq_set_noprobe(unsigned int irq)
 {
 	irq_modify_status(irq, 0, IRQ_NOPROBE);
 }
 
-static inline void set_irq_probe(unsigned int irq)
+static inline void irq_set_probe(unsigned int irq)
 {
 	irq_modify_status(irq, IRQ_NOPROBE, 0);
 }
@@ -338,14 +337,14 @@ static inline void dynamic_irq_init(unsigned int irq)
 }
 
 /* Set/get chip/data for an IRQ: */
-extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
-extern int set_irq_data(unsigned int irq, void *data);
-extern int set_irq_chip_data(unsigned int irq, void *data);
-extern int set_irq_type(unsigned int irq, unsigned int type);
-extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern int irq_set_chip(unsigned int irq, struct irq_chip *chip);
+extern int irq_set_handler_data(unsigned int irq, void *data);
+extern int irq_set_chip_data(unsigned int irq, void *data);
+extern int irq_set_irq_type(unsigned int irq, unsigned int type);
+extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
 extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
-static inline struct irq_chip *get_irq_chip(unsigned int irq)
+static inline struct irq_chip *irq_get_chip(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->chip : NULL;
@@ -356,7 +355,7 @@ static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d)
 	return d->chip;
 }
 
-static inline void *get_irq_chip_data(unsigned int irq)
+static inline void *irq_get_chip_data(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->chip_data : NULL;
@@ -367,18 +366,18 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d)
 	return d->chip_data;
 }
 
-static inline void *get_irq_data(unsigned int irq)
+static inline void *irq_get_handler_data(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->handler_data : NULL;
 }
 
-static inline void *irq_data_get_irq_data(struct irq_data *d)
+static inline void *irq_data_get_irq_handler_data(struct irq_data *d)
 {
 	return d->handler_data;
 }
 
-static inline struct msi_desc *get_irq_msi(unsigned int irq)
+static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 	return d ? d->msi_desc : NULL;
@@ -389,6 +388,58 @@ static inline struct msi_desc *irq_data_get_msi(struct irq_data *d)
 	return d->msi_desc;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+{
+	return irq_set_chip(irq, chip);
+}
+static inline int set_irq_data(unsigned int irq, void *data)
+{
+	return irq_set_handler_data(irq, data);
+}
+static inline int set_irq_chip_data(unsigned int irq, void *data)
+{
+	return irq_set_chip_data(irq, data);
+}
+static inline int set_irq_type(unsigned int irq, unsigned int type)
+{
+	return irq_set_irq_type(irq, type);
+}
+static inline int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+{
+	return irq_set_msi_desc(irq, entry);
+}
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
+{
+	return irq_get_chip(irq);
+}
+static inline void *get_irq_chip_data(unsigned int irq)
+{
+	return irq_get_chip_data(irq);
+}
+static inline void *get_irq_data(unsigned int irq)
+{
+	return irq_get_handler_data(irq);
+}
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+	return irq_data_get_irq_handler_data(d);
+}
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
+{
+	return irq_get_msi_desc(irq);
+}
+static inline void set_irq_noprobe(unsigned int irq)
+{
+	irq_set_noprobe(irq);
+}
+static inline void set_irq_probe(unsigned int irq)
+{
+	irq_set_probe(irq);
+}
+#endif
+
 int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
 void irq_free_descs(unsigned int irq, unsigned int cnt);
 int irq_reserve_irqs(unsigned int from, unsigned int cnt);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index bfef56dadddb..64794dec93b6 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -98,10 +98,46 @@ static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#define get_irq_desc_chip(desc)		((desc)->irq_data.chip)
-#define get_irq_desc_chip_data(desc)	((desc)->irq_data.chip_data)
-#define get_irq_desc_data(desc)		((desc)->irq_data.handler_data)
-#define get_irq_desc_msi(desc)		((desc)->irq_data.msi_desc)
+static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc)
+{
+	return desc->irq_data.chip;
+}
+
+static inline void *irq_desc_get_chip_data(struct irq_desc *desc)
+{
+	return desc->irq_data.chip_data;
+}
+
+static inline void *irq_desc_get_handler_data(struct irq_desc *desc)
+{
+	return desc->irq_data.handler_data;
+}
+
+static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
+{
+	return desc->irq_data.msi_desc;
+}
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline struct irq_chip *get_irq_desc_chip(struct irq_desc *desc)
+{
+	return irq_desc_get_chip(desc);
+}
+static inline void *get_irq_desc_data(struct irq_desc *desc)
+{
+	return irq_desc_get_handler_data(desc);
+}
+
+static inline void *get_irq_desc_chip_data(struct irq_desc *desc)
+{
+	return irq_desc_get_chip_data(desc);
+}
+
+static inline struct msi_desc *get_irq_desc_msi(struct irq_desc *desc)
+{
+	return irq_desc_get_msi_desc(desc);
+}
+#endif
 
 /*
  * Architectures call this to let the generic IRQ layer
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 9639ab8bece0..622b55ac0e09 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -19,11 +19,11 @@
 #include "internals.h"
 
 /**
- *	set_irq_chip - set the irq chip for an irq
+ *	irq_set_chip - set the irq chip for an irq
  *	@irq:	irq number
  *	@chip:	pointer to irq chip description structure
  */
-int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -43,14 +43,14 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_chip);
+EXPORT_SYMBOL(irq_set_chip);
 
 /**
- *	set_irq_type - set the irq trigger type for an irq
+ *	irq_set_type - set the irq trigger type for an irq
  *	@irq:	irq number
  *	@type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
  */
-int set_irq_type(unsigned int irq, unsigned int type)
+int irq_set_irq_type(unsigned int irq, unsigned int type)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -72,16 +72,16 @@ int set_irq_type(unsigned int irq, unsigned int type)
 	chip_bus_sync_unlock(desc);
 	return ret;
 }
-EXPORT_SYMBOL(set_irq_type);
+EXPORT_SYMBOL(irq_set_irq_type);
 
 /**
- *	set_irq_data - set irq type data for an irq
+ *	irq_set_handler_data - set irq handler data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to interrupt specific data
  *
  *	Set the hardware irq controller data for an irq
  */
-int set_irq_data(unsigned int irq, void *data)
+int irq_set_handler_data(unsigned int irq, void *data)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -97,16 +97,16 @@ int set_irq_data(unsigned int irq, void *data)
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_data);
+EXPORT_SYMBOL(irq_set_handler_data);
 
 /**
- *	set_irq_msi - set MSI descriptor data for an irq
+ *	irq_set_msi_desc - set MSI descriptor data for an irq
  *	@irq:	Interrupt number
  *	@entry:	Pointer to MSI descriptor data
  *
  *	Set the MSI descriptor entry for an irq
  */
-int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -126,13 +126,13 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 }
 
 /**
- *	set_irq_chip_data - set irq chip data for an irq
+ *	irq_set_chip_data - set irq chip data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to chip specific data
  *
  *	Set the hardware irq chip data for an irq
  */
-int set_irq_chip_data(unsigned int irq, void *data)
+int irq_set_chip_data(unsigned int irq, void *data)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -154,7 +154,7 @@ int set_irq_chip_data(unsigned int irq, void *data)
 
 	return 0;
 }
-EXPORT_SYMBOL(set_irq_chip_data);
+EXPORT_SYMBOL(irq_set_chip_data);
 
 struct irq_data *irq_get_irq_data(unsigned int irq)
 {
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a400db220cf3..b1b4da9446e6 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -434,7 +434,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 }
 
 /**
- *	set_irq_wake - control irq power management wakeup
+ *	irq_set_irq_wake - control irq power management wakeup
  *	@irq:	interrupt to control
  *	@on:	enable/disable power management wakeup
  *
@@ -445,7 +445,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
  *	Wakeup mode lets this IRQ wake the system from sleep
  *	states like "suspend to RAM".
  */
-int set_irq_wake(unsigned int irq, unsigned int on)
+int irq_set_irq_wake(unsigned int irq, unsigned int on)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -480,7 +480,7 @@ int set_irq_wake(unsigned int irq, unsigned int on)
 	chip_bus_sync_unlock(desc);
 	return ret;
 }
-EXPORT_SYMBOL(set_irq_wake);
+EXPORT_SYMBOL(irq_set_irq_wake);
 
 /*
  * Internal function that tells the architecture code whether a
-- 
cgit v1.2.3


From 3b8249e759c701c4a82f99d957be651a7657bf6f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 16:02:20 +0100
Subject: genirq: Do not copy affinity before set

While rumaging through arch code I found that there are a few
workarounds which deal with the fact that the initial affinity setting
from request_irq() copies the mask into irq_data->affinity before the
chip code is called. In the normal path we unconditionally copy the
mask when the chip code returns 0.

Copy after the code is called and add a return code
IRQ_SET_MASK_OK_NOCOPY for the chip functions, which prevents the
copy. That way we see the real mask when the chip function decided to
truncate it further as some arches do. IRQ_SET_MASK_OK is 0, which is
the current behaviour.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 11 +++++++++++
 kernel/irq/internals.h |  2 +-
 kernel/irq/manage.c    | 47 ++++++++++++++++++++++++++++++++++-------------
 kernel/irq/proc.c      |  2 +-
 4 files changed, 47 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index e9f847d56c4d..f5e900309d21 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -85,6 +85,17 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 # define IRQ_NO_BALANCING_MASK	IRQ_NO_BALANCING
 #endif
 
+/*
+ * Return value for chip->irq_set_affinity()
+ *
+ * IRQ_SET_MASK_OK	- OK, core updates irq_data.affinity
+ * IRQ_SET_MASK_NOCPY	- OK, chip did update irq_data.affinity
+ */
+enum {
+	IRQ_SET_MASK_OK = 0,
+	IRQ_SET_MASK_OK_NOCOPY,
+};
+
 struct msi_desc;
 
 /**
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 99c3bc8a6fb4..b5bfa24aa6a6 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -43,7 +43,7 @@ static inline void unregister_handler_proc(unsigned int irq,
 					   struct irqaction *action) { }
 #endif
 
-extern int irq_select_affinity_usr(unsigned int irq);
+extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ade65bfb466d..dc95d53df510 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -148,9 +148,12 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	if (irq_can_move_pcntxt(desc)) {
 		ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
-		if (!ret) {
+		switch (ret) {
+		case IRQ_SET_MASK_OK:
 			cpumask_copy(desc->irq_data.affinity, mask);
+		case IRQ_SET_MASK_OK_NOCOPY:
 			irq_set_thread_affinity(desc);
+			ret = 0;
 		}
 	} else {
 		desc->status |= IRQ_MOVE_PENDING;
@@ -254,9 +257,12 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 /*
  * Generic version of the affinity autoselector.
  */
-static int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
+	struct irq_chip *chip = get_irq_desc_chip(desc);
 	struct cpumask *set = irq_default_affinity;
+	int ret;
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
@@ -273,13 +279,20 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
-	cpumask_and(desc->irq_data.affinity, cpu_online_mask, set);
-	desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
 
+	cpumask_and(mask, cpu_online_mask, set);
+	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		cpumask_copy(desc->irq_data.affinity, mask);
+	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_set_thread_affinity(desc);
+	}
 	return 0;
 }
 #else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask)
 {
 	return irq_select_affinity(irq);
 }
@@ -288,23 +301,23 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
 /*
  * Called when affinity is set via /proc/irq
  */
-int irq_select_affinity_usr(unsigned int irq)
+int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 	int ret;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = setup_affinity(irq, desc);
+	ret = setup_affinity(irq, desc, mask);
 	if (!ret)
 		irq_set_thread_affinity(desc);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
 	return ret;
 }
 
 #else
-static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
+static inline int
+setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
 	return 0;
 }
@@ -765,8 +778,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
 	unsigned long flags;
-	int nested, shared = 0;
-	int ret;
+	int ret, nested, shared = 0;
+	cpumask_var_t mask;
 
 	if (!desc)
 		return -EINVAL;
@@ -831,6 +844,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		new->thread = t;
 	}
 
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out_thread;
+	}
+
 	/*
 	 * The following block of code has to be executed atomically
 	 */
@@ -876,7 +894,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 					new->flags & IRQF_TRIGGER_MASK);
 
 			if (ret)
-				goto out_thread;
+				goto out_mask;
 		} else
 			compat_irq_chip_set_default_handler(desc);
 #if defined(CONFIG_IRQ_PER_CPU)
@@ -903,7 +921,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_NO_BALANCING;
 
 		/* Set default affinity mask once everything is setup */
-		setup_affinity(irq, desc);
+		setup_affinity(irq, desc, mask);
 
 	} else if ((new->flags & IRQF_TRIGGER_MASK)
 			&& (new->flags & IRQF_TRIGGER_MASK)
@@ -956,6 +974,9 @@ mismatch:
 #endif
 	ret = -EBUSY;
 
+out_mask:
+	free_cpumask_var(mask);
+
 out_thread:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	if (new->thread) {
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6c8a2a9f8a7b..a46bd762db47 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -89,7 +89,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	if (!cpumask_intersects(new_value, cpu_online_mask)) {
 		/* Special case for empty set - allow the architecture
 		   code to set default SMP affinity. */
-		err = irq_select_affinity_usr(irq) ? -EINVAL : count;
+		err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count;
 	} else {
 		irq_set_affinity(irq, new_value);
 		err = count;
-- 
cgit v1.2.3


From fe200ae48ef5c79bf7941fe8046ff9505c570ff6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 10:34:30 +0100
Subject: genirq: Mark polled irqs and defer the real handler

With the chip.end() function gone we might run into a situation where
a poll call runs and the real interrupt comes in, sees IRQ_INPROGRESS
and disables the line. That might be a perfect working one, which will
then be masked forever.

So mark them polled while the poll runs. When the real handler sees
IRQ_INPROGRESS it checks the poll flag and waits for the polling to
complete. Add the necessary amount of sanity checks to it to avoid
deadlocks.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  1 +
 kernel/irq/chip.c      | 26 +++++++++++++++++++------
 kernel/irq/internals.h | 11 +----------
 kernel/irq/spurious.c  | 51 ++++++++++++++++++++++++++++++++++++++------------
 4 files changed, 61 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index f5e900309d21..e32b64ccdc89 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -71,6 +71,7 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
 #define IRQ_ONESHOT		0x08000000	/* IRQ is not unmasked after hardirq */
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
+#define IRQ_POLL_INPROGRESS	0x20000000	/* IRQ poll is in progress */
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 622b55ac0e09..31258782742c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -448,6 +448,13 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_nested_irq);
 
+static bool irq_check_poll(struct irq_desc *desc)
+{
+	if (!(desc->status & IRQ_POLL_INPROGRESS))
+		return false;
+	return irq_wait_for_poll(desc);
+}
+
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
  *	@irq:	the interrupt number
@@ -469,7 +476,9 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out_unlock;
+		if (!irq_check_poll(desc))
+			goto out_unlock;
+
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
@@ -510,7 +519,9 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	mask_ack_irq(desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out_unlock;
+		if (!irq_check_poll(desc))
+			goto out_unlock;
+
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
@@ -558,7 +569,8 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
-		goto out;
+		if (!irq_check_poll(desc))
+			goto out;
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
@@ -620,9 +632,11 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	 */
 	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
 		    !desc->action)) {
-		desc->status |= (IRQ_PENDING | IRQ_MASKED);
-		mask_ack_irq(desc);
-		goto out_unlock;
+		if (!irq_check_poll(desc)) {
+			desc->status |= (IRQ_PENDING | IRQ_MASKED);
+			mask_ack_irq(desc);
+			goto out_unlock;
+		}
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b5bfa24aa6a6..0eff7e92b1a9 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -28,6 +28,7 @@ extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
 /* Resending of interrupts :*/
 void check_irq_resend(struct irq_desc *desc, unsigned int irq);
+bool irq_wait_for_poll(struct irq_desc *desc);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
@@ -47,16 +48,6 @@ extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
-#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
-static inline void irq_end(unsigned int irq, struct irq_desc *desc)
-{
-	if (desc->irq_data.chip && desc->irq_data.chip->end)
-		desc->irq_data.chip->end(irq);
-}
-#else
-static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
-#endif
-
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 56ff8fffb8b0..f749d29bfd81 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -24,13 +24,45 @@ static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
 static int irq_poll_cpu;
 static atomic_t irq_poll_active;
 
+/*
+ * We wait here for a poller to finish.
+ *
+ * If the poll runs on this CPU, then we yell loudly and return
+ * false. That will leave the interrupt line disabled in the worst
+ * case, but it should never happen.
+ *
+ * We wait until the poller is done and then recheck disabled and
+ * action (about to be disabled). Only if it's still active, we return
+ * true and let the handler run.
+ */
+bool irq_wait_for_poll(struct irq_desc *desc)
+{
+	if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
+		      "irq poll in progress on cpu %d for irq %d\n",
+		      smp_processor_id(), desc->irq_data.irq))
+		return false;
+
+#ifdef CONFIG_SMP
+	do {
+		raw_spin_unlock(&desc->lock);
+		while (desc->status & IRQ_INPROGRESS)
+			cpu_relax();
+		raw_spin_lock(&desc->lock);
+	} while (desc->status & IRQ_INPROGRESS);
+	/* Might have been disabled in meantime */
+	return !(desc->status & IRQ_DISABLED) && desc->action;
+#else
+	return false;
+#endif
+}
+
 /*
  * Recovery handler for misrouted interrupts.
  */
 static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 {
 	struct irqaction *action;
-	int ok = 0, work = 0;
+	int ok = 0;
 
 	raw_spin_lock(&desc->lock);
 
@@ -64,10 +96,9 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 		goto out;
 	}
 
-	/* Honour the normal IRQ locking */
-	desc->status |= IRQ_INPROGRESS;
+	/* Honour the normal IRQ locking and mark it poll in progress */
+	desc->status |= IRQ_INPROGRESS | IRQ_POLL_INPROGRESS;
 	do {
-		work++;
 		desc->status &= ~IRQ_PENDING;
 		raw_spin_unlock(&desc->lock);
 		if (handle_IRQ_event(irq, action) != IRQ_NONE)
@@ -76,14 +107,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 		action = desc->action;
 	}  while ((desc->status & IRQ_PENDING) && action);
 
-	desc->status &= ~IRQ_INPROGRESS;
-	/*
-	 * If we did actual work for the real IRQ line we must let the
-	 * IRQ controller clean up too
-	 */
-	if (work > 1)
-		irq_end(irq, desc);
-
+	desc->status &= ~(IRQ_INPROGRESS | IRQ_POLL_INPROGRESS);
 out:
 	raw_spin_unlock(&desc->lock);
 	return ok;
@@ -238,6 +262,9 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
+	if (desc->status & IRQ_POLL_INPROGRESS)
+		return;
+
 	if (unlikely(action_ret != IRQ_HANDLED)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
-- 
cgit v1.2.3


From 1535dfacbf21c4da1b73fcf07c39913da5bd5581 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 01:55:43 +0100
Subject: genirq: Move irq thread flags to core

Soleley used in core code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/interrupt.h | 14 --------------
 kernel/irq/internals.h    | 14 ++++++++++++++
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 7834726dd95b..de97b958f478 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -73,20 +73,6 @@
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND)
 
-/*
- * Bits used by threaded handlers:
- * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
- * IRQTF_DIED      - handler thread died
- * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
- * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
- */
-enum {
-	IRQTF_RUNTHREAD,
-	IRQTF_DIED,
-	IRQTF_WARNED,
-	IRQTF_AFFINITY,
-};
-
 /*
  * These values can be returned by request_any_context_irq() and
  * describe the context the interrupt will be run in.
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 0eff7e92b1a9..b17c98440400 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -11,6 +11,20 @@
 
 extern int noirqdebug;
 
+/*
+ * Bits used by threaded handlers:
+ * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
+ * IRQTF_DIED      - handler thread died
+ * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
+ * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
+ */
+enum {
+	IRQTF_RUNTHREAD,
+	IRQTF_DIED,
+	IRQTF_WARNED,
+	IRQTF_AFFINITY,
+};
+
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
 
 /* Set default functions for irq_chip structures: */
-- 
cgit v1.2.3


From c78b9b65faa291def628dbd8539649f58299f0f3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 16 Dec 2010 17:21:47 +0100
Subject: genirq: Implement generic irq_show_interrupts()

All archs implement show_interrupts() in more or less the same
way. That's tons of duplicated code with different bugs with no
value. Implement a generic version and deprecate show_interrupts()

Unfortunately we need some ifdeffery for !GENERIC_HARDIRQ archs.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/interrupt.h |  1 +
 kernel/irq/Kconfig        |  3 +++
 kernel/irq/proc.c         | 63 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 67 insertions(+)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index de97b958f478..8da6643e39a6 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -671,6 +671,7 @@ static inline void init_irq_proc(void)
 
 struct seq_file;
 int show_interrupts(struct seq_file *p, void *v);
+int arch_show_interrupts(struct seq_file *p, int prec);
 
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 8e42fec7686d..4cd5d7135e0f 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -20,6 +20,9 @@ config HAVE_SPARSE_IRQ
 config GENERIC_IRQ_PROBE
 	def_bool n
 
+config GENERIC_IRQ_SHOW
+       def_bool n
+
 config GENERIC_PENDING_IRQ
 	def_bool n
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index a46bd762db47..26449239bb46 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -11,6 +11,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
 
 #include "internals.h"
 
@@ -357,3 +358,65 @@ void init_irq_proc(void)
 	}
 }
 
+#ifdef CONFIG_GENERIC_IRQ_SHOW
+
+int __weak arch_show_interrupts(struct seq_file *p, int prec)
+{
+	return 0;
+}
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+	static int prec;
+
+	unsigned long flags, any_count = 0;
+	int i = *(loff_t *) v, j;
+	struct irqaction *action;
+	struct irq_desc *desc;
+
+	if (i > nr_irqs)
+		return 0;
+
+	if (i == nr_irqs)
+		return arch_show_interrupts(p, prec);
+
+	/* print header and calculate the width of the first column */
+	if (i == 0) {
+		for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+			j *= 10;
+
+		seq_printf(p, "%*s", prec + 8, "");
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%-8d", j);
+		seq_putc(p, '\n');
+	}
+
+	desc = irq_to_desc(i);
+	if (!desc)
+		return 0;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	for_each_online_cpu(j)
+		any_count |= kstat_irqs_cpu(i, j);
+	action = desc->action;
+	if (!action && !any_count)
+		goto out;
+
+	seq_printf(p, "%*d: ", prec, i);
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+	seq_printf(p, " %8s", desc->irq_data.chip->name);
+	seq_printf(p, "-%-8s", desc->name);
+
+	if (action) {
+		seq_printf(p, "  %s", action->name);
+		while ((action = action->next) != NULL)
+			seq_printf(p, ", %s", action->name);
+	}
+
+	seq_putc(p, '\n');
+out:
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	return 0;
+}
+#endif
-- 
cgit v1.2.3


From dbec07bac614a61e3392c1e7c08cc6a49ad43f7a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 20:19:55 +0100
Subject: genirq: Add internal state field to irq_desc

That field will contain internal state information which is not going
to be exposed to anything outside the core code - except via accessor
functions. I'm tired of everyone fiddling in irq_desc.status.

core_internal_state__do_not_mess_with_it is clear enough, annoying to
type and easy to grep for. Offenders will be tracked down and slapped
with stinking trouts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqdesc.h | 3 ++-
 kernel/irq/internals.h  | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 64794dec93b6..782bf9851a9f 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -19,6 +19,7 @@ struct timer_rand_state;
  * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
  * @action:		the irq action chain
  * @status:		status information
+ * @core_internal_state__do_not_mess_with_it: core internal status information
  * @depth:		disable-depth, for nested irq_disable() calls
  * @wake_depth:		enable depth, for multiple set_irq_wake() callers
  * @irq_count:		stats field to detect stalled irqs
@@ -63,7 +64,7 @@ struct irq_desc {
 	irq_flow_handler_t	handle_irq;
 	struct irqaction	*action;	/* IRQ action list */
 	unsigned int		status;		/* IRQ status */
-
+	unsigned int		core_internal_state__do_not_mess_with_it;
 	unsigned int		depth;		/* nested irq disables */
 	unsigned int		wake_depth;	/* nested wake enables */
 	unsigned int		irq_count;	/* For detecting broken IRQs */
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b61824cdadc6..ae96e688f4e1 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -1,5 +1,9 @@
 /*
  * IRQ subsystem internal functions and variables:
+ *
+ * Do not ever include this file from anything else than
+ * kernel/irq/. Do not even think about using any information outside
+ * of this file for your non core code.
  */
 #include <linux/irqdesc.h>
 
@@ -9,6 +13,8 @@
 # define IRQ_BITMAP_BITS	NR_IRQS
 #endif
 
+#define istate core_internal_state__do_not_mess_with_it
+
 extern int noirqdebug;
 
 /*
-- 
cgit v1.2.3


From bd062e7667ac173afef57fbfe9327f3b914a9d4c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 20:25:25 +0100
Subject: genirq: Move IRQ_AUTODETECT to internal state

No users outside of core

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  1 -
 kernel/irq/autoprobe.c | 29 ++++++++++++-----------------
 kernel/irq/internals.h | 15 +++++++++++++--
 kernel/irq/manage.c    |  3 ++-
 4 files changed, 27 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index e32b64ccdc89..d1f9c352cd1b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -54,7 +54,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_DISABLED		0x00000200	/* IRQ disabled - do not enter! */
 #define IRQ_PENDING		0x00000400	/* IRQ pending - replay on enable */
 #define IRQ_REPLAY		0x00000800	/* IRQ has been replayed but not acked yet */
-#define IRQ_AUTODETECT		0x00001000	/* IRQ is being autodetected */
 #define IRQ_WAITING		0x00002000	/* IRQ not yet seen - for autodetection */
 #define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
 #define IRQ_MASKED		0x00008000	/* IRQ masked - shouldn't be seen again */
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 08947cb61725..916e56e10a2e 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -32,7 +32,6 @@ unsigned long probe_irq_on(void)
 {
 	struct irq_desc *desc;
 	unsigned long mask = 0;
-	unsigned int status;
 	int i;
 
 	/*
@@ -76,7 +75,8 @@ unsigned long probe_irq_on(void)
 	for_each_irq_desc_reverse(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
-			desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
+			desc->istate |= IRQS_AUTODETECT;
+			desc->status |= IRQ_WAITING;
 			if (irq_startup(desc))
 				desc->status |= IRQ_PENDING;
 		}
@@ -93,12 +93,11 @@ unsigned long probe_irq_on(void)
 	 */
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
 
-		if (status & IRQ_AUTODETECT) {
+		if (desc->istate & IRQS_AUTODETECT) {
 			/* It triggered already - consider it spurious. */
-			if (!(status & IRQ_WAITING)) {
-				desc->status = status & ~IRQ_AUTODETECT;
+			if (!(desc->status & IRQ_WAITING)) {
+				desc->istate &= ~IRQS_AUTODETECT;
 				irq_shutdown(desc);
 			} else
 				if (i < 32)
@@ -125,19 +124,17 @@ EXPORT_SYMBOL(probe_irq_on);
  */
 unsigned int probe_irq_mask(unsigned long val)
 {
-	unsigned int status, mask = 0;
+	unsigned int mask = 0;
 	struct irq_desc *desc;
 	int i;
 
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
-
-		if (status & IRQ_AUTODETECT) {
-			if (i < 16 && !(status & IRQ_WAITING))
+		if (desc->istate & IRQS_AUTODETECT) {
+			if (i < 16 && !(desc->status & IRQ_WAITING))
 				mask |= 1 << i;
 
-			desc->status = status & ~IRQ_AUTODETECT;
+			desc->istate &= ~IRQS_AUTODETECT;
 			irq_shutdown(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
@@ -169,19 +166,17 @@ int probe_irq_off(unsigned long val)
 {
 	int i, irq_found = 0, nr_of_irqs = 0;
 	struct irq_desc *desc;
-	unsigned int status;
 
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
-		status = desc->status;
 
-		if (status & IRQ_AUTODETECT) {
-			if (!(status & IRQ_WAITING)) {
+		if (desc->istate & IRQS_AUTODETECT) {
+			if (!(desc->status & IRQ_WAITING)) {
 				if (!nr_of_irqs)
 					irq_found = i;
 				nr_of_irqs++;
 			}
-			desc->status = status & ~IRQ_AUTODETECT;
+			desc->istate &= ~IRQS_AUTODETECT;
 			irq_shutdown(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 8f200310a952..7ffd4f439b92 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -33,6 +33,15 @@ enum {
 	IRQTF_AFFINITY,
 };
 
+/*
+ * Bit masks for desc->state
+ *
+ * IRQS_AUTODETECT		- autodetection in progress
+ */
+enum {
+	IRQS_AUTODETECT		= 0x00000001,
+};
+
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
 
 /* Set default functions for irq_chip structures: */
@@ -98,6 +107,7 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 #include <linux/kallsyms.h>
 
 #define P(f) if (desc->status & f) printk("%14s set\n", #f)
+#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
 
 static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 {
@@ -117,7 +127,6 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	P(IRQ_DISABLED);
 	P(IRQ_PENDING);
 	P(IRQ_REPLAY);
-	P(IRQ_AUTODETECT);
 	P(IRQ_WAITING);
 	P(IRQ_LEVEL);
 	P(IRQ_MASKED);
@@ -127,7 +136,9 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	P(IRQ_NOPROBE);
 	P(IRQ_NOREQUEST);
 	P(IRQ_NOAUTOEN);
+
+	PS(IRQS_AUTODETECT);
 }
 
 #undef P
-
+#undef PS
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index dd4e5c21b9e7..abe852c9449d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -897,8 +897,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT |
+		desc->status &= ~(IRQ_WAITING | IRQ_ONESHOT |
 				  IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
+		desc->istate &= ~IRQS_AUTODETECT;
 
 		if (new->flags & IRQF_ONESHOT)
 			desc->status |= IRQ_ONESHOT;
-- 
cgit v1.2.3


From 7acdd53e5b2c55b6f7e3427e85e2f91fa814a4f9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 20:40:54 +0100
Subject: genirq: Move IRQ_SPURIOUS_DISABLED to core state

No users outside.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 1 -
 kernel/irq/internals.h | 3 +++
 kernel/irq/manage.c    | 9 ++++-----
 kernel/irq/spurious.c  | 8 ++++----
 4 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index d1f9c352cd1b..a900741b43ea 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -64,7 +64,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_WAKEUP		0x00100000	/* IRQ triggers system wakeup */
 #define IRQ_MOVE_PENDING	0x00200000	/* need to re-target IRQ destination */
 #define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
-#define IRQ_SPURIOUS_DISABLED	0x00800000	/* IRQ was disabled by the spurious trap */
 #define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
 #define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
 #define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 7ffd4f439b92..dc5e21b84f9e 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -37,9 +37,12 @@ enum {
  * Bit masks for desc->state
  *
  * IRQS_AUTODETECT		- autodetection in progress
+ * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
+ *				  detection
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
+	IRQS_SPURIOUS_DISABLED	= 0x00000002,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index abe852c9449d..5b918ffa46af 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -897,9 +897,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~(IRQ_WAITING | IRQ_ONESHOT |
-				  IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
-		desc->istate &= ~IRQS_AUTODETECT;
+		desc->status &= ~(IRQ_WAITING | IRQ_ONESHOT | IRQ_INPROGRESS);
+		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED);
 
 		if (new->flags & IRQF_ONESHOT)
 			desc->status |= IRQ_ONESHOT;
@@ -937,8 +936,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 * Check whether we disabled the irq via the spurious handler
 	 * before. Reenable it and give it another chance.
 	 */
-	if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
-		desc->status &= ~IRQ_SPURIOUS_DISABLED;
+	if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
+		desc->istate &= ~IRQS_SPURIOUS_DISABLED;
 		__enable_irq(desc, irq, false);
 	}
 
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index bc0620745d5f..2941d8a22df7 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -146,15 +146,15 @@ static void poll_spurious_irqs(unsigned long dummy)
 	irq_poll_cpu = smp_processor_id();
 
 	for_each_irq_desc(i, desc) {
-		unsigned int status;
+		unsigned int state;
 
 		if (!i)
 			 continue;
 
 		/* Racy but it doesn't matter */
-		status = desc->status;
+		state = desc->istate;
 		barrier();
-		if (!(status & IRQ_SPURIOUS_DISABLED))
+		if (!(state & IRQS_SPURIOUS_DISABLED))
 			continue;
 
 		local_irq_disable();
@@ -298,7 +298,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		 * Now kill the IRQ
 		 */
 		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
-		desc->status |= IRQ_SPURIOUS_DISABLED;
+		desc->istate |= IRQS_SPURIOUS_DISABLED;
 		desc->depth++;
 		irq_disable(desc);
 
-- 
cgit v1.2.3


From 6f91a52d9bb28396177662f1da0f2e2cef9cf5d0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 14 Feb 2011 13:33:16 +0100
Subject: genirq: Use modify_status for set_irq_nested_thread

No need for a separate function in the core code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 16 +++++++++++++---
 kernel/irq/chip.c   | 28 ----------------------------
 2 files changed, 13 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index a900741b43ea..67b77cfb2a34 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -74,7 +74,7 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
-	 IRQ_PER_CPU)
+	 IRQ_PER_CPU | IRQ_NESTED_THREAD)
 
 #ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
@@ -307,8 +307,6 @@ set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
 	__set_irq_handler(irq, handle, 1, NULL);
 }
 
-extern void set_irq_nested_thread(unsigned int irq, int nest);
-
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
 
 static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
@@ -331,6 +329,14 @@ static inline void irq_set_probe(unsigned int irq)
 	irq_modify_status(irq, IRQ_NOPROBE, 0);
 }
 
+static inline void irq_set_nested_thread(unsigned int irq, bool nest)
+{
+	if (nest)
+		irq_set_status_flags(irq, IRQ_NESTED_THREAD);
+	else
+		irq_clear_status_flags(irq, IRQ_NESTED_THREAD);
+}
+
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
@@ -448,6 +454,10 @@ static inline void set_irq_probe(unsigned int irq)
 {
 	irq_set_probe(irq);
 }
+static inline void set_irq_nested_thread(unsigned int irq, int nest)
+{
+	irq_set_nested_thread(irq, nest);
+}
 #endif
 
 int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 143eb2a9fa4e..bff21f233a02 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -164,34 +164,6 @@ struct irq_data *irq_get_irq_data(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(irq_get_irq_data);
 
-/**
- *	set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
- *
- *	@irq:	Interrupt number
- *	@nest:	0 to clear / 1 to set the IRQ_NESTED_THREAD flag
- *
- *	The IRQ_NESTED_THREAD flag indicates that on
- *	request_threaded_irq() no separate interrupt thread should be
- *	created for the irq as the handler are called nested in the
- *	context of a demultiplexing interrupt handler thread.
- */
-void set_irq_nested_thread(unsigned int irq, int nest)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc)
-		return;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (nest)
-		desc->status |= IRQ_NESTED_THREAD;
-	else
-		desc->status &= ~IRQ_NESTED_THREAD;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-EXPORT_SYMBOL_GPL(set_irq_nested_thread);
-
 int irq_startup(struct irq_desc *desc)
 {
 	desc->status &= ~IRQ_DISABLED;
-- 
cgit v1.2.3


From 6954b75b488dd740950573f244ddd66fd28620aa Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 20:55:35 +0100
Subject: genirq: Move IRQ_POLL_INPROGRESS to core

No users outside of core.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 1 -
 kernel/irq/chip.c      | 2 +-
 kernel/irq/internals.h | 2 ++
 kernel/irq/spurious.c  | 6 +++---
 4 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 67b77cfb2a34..047a695511df 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -69,7 +69,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
 #define IRQ_ONESHOT		0x08000000	/* IRQ is not unmasked after hardirq */
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
-#define IRQ_POLL_INPROGRESS	0x20000000	/* IRQ poll is in progress */
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index bff21f233a02..34245e7d1213 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -400,7 +400,7 @@ EXPORT_SYMBOL_GPL(handle_nested_irq);
 
 static bool irq_check_poll(struct irq_desc *desc)
 {
-	if (!(desc->status & IRQ_POLL_INPROGRESS))
+	if (!(desc->istate & IRQS_POLL_INPROGRESS))
 		return false;
 	return irq_wait_for_poll(desc);
 }
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index dc5e21b84f9e..f5d28e1e1eda 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -39,10 +39,12 @@ enum {
  * IRQS_AUTODETECT		- autodetection in progress
  * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
  *				  detection
+ * IRQS_POLL_INPROGRESS		- polling in progress
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
 	IRQS_SPURIOUS_DISABLED	= 0x00000002,
+	IRQS_POLL_INPROGRESS	= 0x00000008,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 2941d8a22df7..21c46178b1a6 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -98,13 +98,13 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	}
 
 	/* Mark it poll in progress */
-	desc->status |= IRQ_POLL_INPROGRESS;
+	desc->istate |= IRQS_POLL_INPROGRESS;
 	do {
 		if (handle_irq_event(desc) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
 		action = desc->action;
 	} while ((desc->status & IRQ_PENDING) && action);
-	desc->status &= ~IRQ_POLL_INPROGRESS;
+	desc->istate &= ~IRQS_POLL_INPROGRESS;
 out:
 	raw_spin_unlock(&desc->lock);
 	return ret == IRQ_HANDLED;
@@ -259,7 +259,7 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
-	if (desc->status & IRQ_POLL_INPROGRESS)
+	if (desc->istate & IRQS_POLL_INPROGRESS)
 		return;
 
 	if (unlikely(action_ret != IRQ_HANDLED)) {
-- 
cgit v1.2.3


From 009b4c3b8ad584b3462734127a5bec680d5d6af4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 21:48:49 +0100
Subject: genirq: Add IRQ_INPROGRESS to core

We need to maintain the flag for now in both fields status and istate.
Add a CONFIG_GENERIC_HARDIRQS_NO_COMPAT switch to allow testing w/o
the status one. Wrap the access to status IRQ_INPROGRESS in a inline
which can be turned of with CONFIG_GENERIC_HARDIRQS_NO_COMPAT along
with the define.

There is no reason that anything outside of core looks at this. That
needs some modifications, but we'll get there.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  6 +++++-
 kernel/irq/Kconfig     |  3 +++
 kernel/irq/chip.c      | 16 +++++++++-------
 kernel/irq/compat.h    | 17 +++++++++++++++++
 kernel/irq/handle.c    |  6 ++++--
 kernel/irq/internals.h |  5 ++++-
 kernel/irq/manage.c    | 17 +++++++++--------
 kernel/irq/settings.h  |  3 +++
 kernel/irq/spurious.c  |  6 +++---
 9 files changed, 57 insertions(+), 22 deletions(-)
 create mode 100644 kernel/irq/compat.h

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 047a695511df..274590fc55a3 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -50,7 +50,11 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_TYPE_PROBE		0x00000010	/* Probing in progress */
 
 /* Internal flags */
-#define IRQ_INPROGRESS		0x00000100	/* IRQ handler active - do not enter! */
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+#define IRQ_INPROGRESS		0x00000100	/* DEPRECATED */
+#endif
+
 #define IRQ_DISABLED		0x00000200	/* IRQ disabled - do not enter! */
 #define IRQ_PENDING		0x00000400	/* IRQ pending - replay on enable */
 #define IRQ_REPLAY		0x00000800	/* IRQ has been replayed but not acked yet */
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 4cd5d7135e0f..9e2256de1d1a 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -13,6 +13,9 @@ config GENERIC_HARDIRQS
 config GENERIC_HARDIRQS_NO_DEPRECATED
        def_bool n
 
+config GENERIC_HARDIRQS_NO_COMPAT
+       def_bool n
+
 # Options selectable by the architecture code
 config HAVE_SPARSE_IRQ
        def_bool n
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 34245e7d1213..075385549dcd 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -383,7 +383,8 @@ void handle_nested_irq(unsigned int irq)
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
 		goto out_unlock;
 
-	desc->status |= IRQ_INPROGRESS;
+	irq_compat_set_progress(desc);
+	desc->istate |= IRQS_INPROGRESS;
 	raw_spin_unlock_irq(&desc->lock);
 
 	action_ret = action->thread_fn(action->irq, action->dev_id);
@@ -391,7 +392,8 @@ void handle_nested_irq(unsigned int irq)
 		note_interrupt(irq, desc, action_ret);
 
 	raw_spin_lock_irq(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
+	desc->istate &= ~IRQS_INPROGRESS;
+	irq_compat_clr_progress(desc);
 
 out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
@@ -422,7 +424,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
 		if (!irq_check_poll(desc))
 			goto out_unlock;
 
@@ -454,7 +456,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 	mask_ack_irq(desc);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
 		if (!irq_check_poll(desc))
 			goto out_unlock;
 
@@ -492,7 +494,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(desc->status & IRQ_INPROGRESS))
+	if (unlikely(desc->istate & IRQS_INPROGRESS))
 		if (!irq_check_poll(desc))
 			goto out;
 
@@ -542,8 +544,8 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	 * we shouldn't process the IRQ. Mark it pending, handle
 	 * the necessary masking and go out
 	 */
-	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
-		    !desc->action)) {
+	if (unlikely((desc->istate & (IRQS_INPROGRESS) ||
+		      (desc->status & IRQ_DISABLED) || !desc->action))) {
 		if (!irq_check_poll(desc)) {
 			desc->status |= IRQ_PENDING;
 			mask_ack_irq(desc);
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
new file mode 100644
index 000000000000..aac6e400e608
--- /dev/null
+++ b/kernel/irq/compat.h
@@ -0,0 +1,17 @@
+/*
+ * Compat layer for transition period
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline void irq_compat_set_progress(struct irq_desc *desc)
+{
+	desc->status |= IRQ_INPROGRESS;
+}
+
+static inline void irq_compat_clr_progress(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_INPROGRESS;
+}
+#else
+static inline void irq_compat_set_progress(struct irq_desc *desc) { }
+static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
+#endif
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index ff40e0f5e2e2..d4ae0b1ccc00 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -123,13 +123,15 @@ irqreturn_t handle_irq_event(struct irq_desc *desc)
 	irqreturn_t ret;
 
 	desc->status &= ~IRQ_PENDING;
-	desc->status |= IRQ_INPROGRESS;
+	irq_compat_set_progress(desc);
+	desc->istate |= IRQS_INPROGRESS;
 	raw_spin_unlock(&desc->lock);
 
 	ret = handle_irq_event_percpu(desc, action);
 
 	raw_spin_lock(&desc->lock);
-	desc->status &= ~IRQ_INPROGRESS;
+	desc->istate &= ~IRQS_INPROGRESS;
+	irq_compat_clr_progress(desc);
 	return ret;
 }
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index f5d28e1e1eda..d1cb1f8df6fe 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -13,6 +13,7 @@
 # define IRQ_BITMAP_BITS	NR_IRQS
 #endif
 
+#include "compat.h"
 #include "settings.h"
 
 #define istate core_internal_state__do_not_mess_with_it
@@ -40,11 +41,13 @@ enum {
  * IRQS_SPURIOUS_DISABLED	- was disabled due to spurious interrupt
  *				  detection
  * IRQS_POLL_INPROGRESS		- polling in progress
+ * IRQS_INPROGRESS		- Interrupt in progress
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
 	IRQS_SPURIOUS_DISABLED	= 0x00000002,
 	IRQS_POLL_INPROGRESS	= 0x00000008,
+	IRQS_INPROGRESS		= 0x00000010,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
@@ -128,7 +131,6 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		print_symbol("%s\n", (unsigned long)desc->action->handler);
 	}
 
-	P(IRQ_INPROGRESS);
 	P(IRQ_DISABLED);
 	P(IRQ_PENDING);
 	P(IRQ_REPLAY);
@@ -143,6 +145,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	P(IRQ_NOAUTOEN);
 
 	PS(IRQS_AUTODETECT);
+	PS(IRQS_INPROGRESS);
 }
 
 #undef P
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5b918ffa46af..7e5a50825088 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -30,7 +30,7 @@
 void synchronize_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned int status;
+	unsigned int state;
 
 	if (!desc)
 		return;
@@ -42,16 +42,16 @@ void synchronize_irq(unsigned int irq)
 		 * Wait until we're out of the critical section.  This might
 		 * give the wrong answer due to the lack of memory barriers.
 		 */
-		while (desc->status & IRQ_INPROGRESS)
+		while (desc->istate & IRQS_INPROGRESS)
 			cpu_relax();
 
 		/* Ok, that indicated we're done: double-check carefully. */
 		raw_spin_lock_irqsave(&desc->lock, flags);
-		status = desc->status;
+		state = desc->istate;
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 		/* Oops, that failed? */
-	} while (status & IRQ_INPROGRESS);
+	} while (state & IRQS_INPROGRESS);
 
 	/*
 	 * We made sure that no hardirq handler is running. Now verify
@@ -637,9 +637,9 @@ again:
 	 * The thread is faster done than the hard interrupt handler
 	 * on the other CPU. If we unmask the irq line then the
 	 * interrupt can come in again and masks the line, leaves due
-	 * to IRQ_INPROGRESS and the irq line is masked forever.
+	 * to IRQS_INPROGRESS and the irq line is masked forever.
 	 */
-	if (unlikely(desc->status & IRQ_INPROGRESS)) {
+	if (unlikely(desc->istate & IRQS_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
 		chip_bus_sync_unlock(desc);
 		cpu_relax();
@@ -897,8 +897,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~(IRQ_WAITING | IRQ_ONESHOT | IRQ_INPROGRESS);
-		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED);
+		desc->status &= ~(IRQ_WAITING | IRQ_ONESHOT);
+		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
+				  IRQS_INPROGRESS);
 
 		if (new->flags & IRQF_ONESHOT)
 			desc->status |= IRQ_ONESHOT;
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 610f55597ce7..a96140eea409 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -5,3 +5,6 @@
 enum {
 	_IRQ_DEFAULT_INIT_FLAGS	= IRQ_DEFAULT_INIT_FLAGS,
 };
+
+#undef IRQ_INPROGRESS
+#define IRQ_INPROGRESS		GOT_YOU_MORON
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 21c46178b1a6..51504837d8cc 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -45,10 +45,10 @@ bool irq_wait_for_poll(struct irq_desc *desc)
 #ifdef CONFIG_SMP
 	do {
 		raw_spin_unlock(&desc->lock);
-		while (desc->status & IRQ_INPROGRESS)
+		while (desc->istate & IRQS_INPROGRESS)
 			cpu_relax();
 		raw_spin_lock(&desc->lock);
-	} while (desc->status & IRQ_INPROGRESS);
+	} while (desc->istate & IRQS_INPROGRESS);
 	/* Might have been disabled in meantime */
 	return !(desc->status & IRQ_DISABLED) && desc->action;
 #else
@@ -88,7 +88,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 		goto out;
 
 	/* Already running on another processor */
-	if (desc->status & IRQ_INPROGRESS) {
+	if (desc->istate & IRQS_INPROGRESS) {
 		/*
 		 * Already running: If it is shared get the other
 		 * CPU to go looking for our mystery interrupt too
-- 
cgit v1.2.3


From 3d67baec7f1b01fc289ac1a2f1a7e6d5e43391c6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 21:02:10 +0100
Subject: genirq: Move IRQ_ONESHOT to core

No users outside of core.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 1 -
 kernel/irq/chip.c      | 2 +-
 kernel/irq/internals.h | 2 ++
 kernel/irq/manage.c    | 8 ++++----
 4 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 274590fc55a3..1a4c723e74e1 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -71,7 +71,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
 #define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
 #define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
-#define IRQ_ONESHOT		0x08000000	/* IRQ is not unmasked after hardirq */
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
 
 #define IRQF_MODIFY_MASK	\
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 075385549dcd..420fa6bdb117 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -472,7 +472,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	handle_irq_event(desc);
 
-	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+	if (!(desc->status & IRQ_DISABLED) && !(desc->istate & IRQS_ONESHOT))
 		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index d1cb1f8df6fe..36563f731ff8 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -42,12 +42,14 @@ enum {
  *				  detection
  * IRQS_POLL_INPROGRESS		- polling in progress
  * IRQS_INPROGRESS		- Interrupt in progress
+ * IRQS_ONESHOT			- irq is not unmasked in primary handler
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
 	IRQS_SPURIOUS_DISABLED	= 0x00000002,
 	IRQS_POLL_INPROGRESS	= 0x00000008,
 	IRQS_INPROGRESS		= 0x00000010,
+	IRQS_ONESHOT		= 0x00000020,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7e5a50825088..aca4208a03ac 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -697,7 +697,7 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake, oneshot = desc->status & IRQ_ONESHOT;
+	int wake, oneshot = desc->istate & IRQS_ONESHOT;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -897,12 +897,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~(IRQ_WAITING | IRQ_ONESHOT);
+		desc->status &= ~IRQ_WAITING;
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
-				  IRQS_INPROGRESS);
+				  IRQS_INPROGRESS | IRQS_ONESHOT);
 
 		if (new->flags & IRQF_ONESHOT)
-			desc->status |= IRQ_ONESHOT;
+			desc->istate |= IRQS_ONESHOT;
 
 		if (!(desc->status & IRQ_NOAUTOEN))
 			irq_startup(desc);
-- 
cgit v1.2.3


From 163ef3091195f514a06f064b12914597d2644c55 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 11:39:15 +0100
Subject: genirq: Move IRQ_REPLAY and IRQ_WAITING to core

No users outside of core.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  9 +++++----
 kernel/irq/autoprobe.c | 11 +++++------
 kernel/irq/chip.c      |  9 ++++-----
 kernel/irq/internals.h |  8 ++++++--
 kernel/irq/manage.c    |  4 ++--
 kernel/irq/resend.c    |  7 +++++--
 kernel/irq/settings.h  |  4 ++++
 7 files changed, 31 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1a4c723e74e1..c38dbd506656 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -53,12 +53,13 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
 #define IRQ_INPROGRESS		0x00000100	/* DEPRECATED */
+#define IRQ_REPLAY		0x00000200	/* DEPRECATED */
+#define IRQ_WAITING		0x00000400	/* DEPRECATED */
 #endif
 
-#define IRQ_DISABLED		0x00000200	/* IRQ disabled - do not enter! */
-#define IRQ_PENDING		0x00000400	/* IRQ pending - replay on enable */
-#define IRQ_REPLAY		0x00000800	/* IRQ has been replayed but not acked yet */
-#define IRQ_WAITING		0x00002000	/* IRQ not yet seen - for autodetection */
+#define IRQ_DISABLED		0x00000800	/* IRQ disabled - do not enter! */
+#define IRQ_PENDING		0x00001000	/* IRQ pending - replay on enable */
+
 #define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
 #define IRQ_MASKED		0x00008000	/* IRQ masked - shouldn't be seen again */
 #define IRQ_PER_CPU		0x00010000	/* IRQ is per CPU */
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 916e56e10a2e..9ea8bb99f7c1 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -17,7 +17,7 @@
 /*
  * Autodetection depends on the fact that any interrupt that
  * comes in on to an unassigned handler will get stuck with
- * "IRQ_WAITING" cleared and the interrupt disabled.
+ * "IRQS_WAITING" cleared and the interrupt disabled.
  */
 static DEFINE_MUTEX(probing_active);
 
@@ -75,8 +75,7 @@ unsigned long probe_irq_on(void)
 	for_each_irq_desc_reverse(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
-			desc->istate |= IRQS_AUTODETECT;
-			desc->status |= IRQ_WAITING;
+			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
 			if (irq_startup(desc))
 				desc->status |= IRQ_PENDING;
 		}
@@ -96,7 +95,7 @@ unsigned long probe_irq_on(void)
 
 		if (desc->istate & IRQS_AUTODETECT) {
 			/* It triggered already - consider it spurious. */
-			if (!(desc->status & IRQ_WAITING)) {
+			if (!(desc->istate & IRQS_WAITING)) {
 				desc->istate &= ~IRQS_AUTODETECT;
 				irq_shutdown(desc);
 			} else
@@ -131,7 +130,7 @@ unsigned int probe_irq_mask(unsigned long val)
 	for_each_irq_desc(i, desc) {
 		raw_spin_lock_irq(&desc->lock);
 		if (desc->istate & IRQS_AUTODETECT) {
-			if (i < 16 && !(desc->status & IRQ_WAITING))
+			if (i < 16 && !(desc->istate & IRQS_WAITING))
 				mask |= 1 << i;
 
 			desc->istate &= ~IRQS_AUTODETECT;
@@ -171,7 +170,7 @@ int probe_irq_off(unsigned long val)
 		raw_spin_lock_irq(&desc->lock);
 
 		if (desc->istate & IRQS_AUTODETECT) {
-			if (!(desc->status & IRQ_WAITING)) {
+			if (!(desc->istate & IRQS_WAITING)) {
 				if (!nr_of_irqs)
 					irq_found = i;
 				nr_of_irqs++;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 420fa6bdb117..59ae14527ecd 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -428,7 +428,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 		if (!irq_check_poll(desc))
 			goto out_unlock;
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	if (unlikely(!desc->action || (desc->status & IRQ_DISABLED)))
@@ -460,7 +460,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 		if (!irq_check_poll(desc))
 			goto out_unlock;
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
@@ -498,7 +498,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		if (!irq_check_poll(desc))
 			goto out;
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
@@ -537,8 +537,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
-	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	/*
 	 * If we're currently running this IRQ, or its disabled,
 	 * we shouldn't process the IRQ. Mark it pending, handle
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 36563f731ff8..54037533af7a 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -43,6 +43,8 @@ enum {
  * IRQS_POLL_INPROGRESS		- polling in progress
  * IRQS_INPROGRESS		- Interrupt in progress
  * IRQS_ONESHOT			- irq is not unmasked in primary handler
+ * IRQS_REPLAY			- irq is replayed
+ * IRQS_WAITING			- irq is waiting
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -50,6 +52,8 @@ enum {
 	IRQS_POLL_INPROGRESS	= 0x00000008,
 	IRQS_INPROGRESS		= 0x00000010,
 	IRQS_ONESHOT		= 0x00000020,
+	IRQS_REPLAY		= 0x00000040,
+	IRQS_WAITING		= 0x00000080,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
@@ -135,8 +139,6 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 
 	P(IRQ_DISABLED);
 	P(IRQ_PENDING);
-	P(IRQ_REPLAY);
-	P(IRQ_WAITING);
 	P(IRQ_LEVEL);
 	P(IRQ_MASKED);
 #ifdef CONFIG_IRQ_PER_CPU
@@ -148,6 +150,8 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 
 	PS(IRQS_AUTODETECT);
 	PS(IRQS_INPROGRESS);
+	PS(IRQS_REPLAY);
+	PS(IRQS_WAITING);
 }
 
 #undef P
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index aca4208a03ac..7971df53d6a9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -897,9 +897,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->status |= IRQ_PER_CPU;
 #endif
 
-		desc->status &= ~IRQ_WAITING;
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
-				  IRQS_INPROGRESS | IRQS_ONESHOT);
+				  IRQS_INPROGRESS | IRQS_ONESHOT | \
+				  IRQS_WAITING);
 
 		if (new->flags & IRQF_ONESHOT)
 			desc->istate |= IRQS_ONESHOT;
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 60b20261041b..f83387cd11f3 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -62,8 +62,11 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	 */
 	if (desc->status & IRQ_LEVEL)
 		return;
-	if ((desc->status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
-		desc->status = (desc->status & ~IRQ_PENDING) | IRQ_REPLAY;
+	if (desc->istate & IRQS_REPLAY)
+		return;
+	if (desc->status & IRQ_PENDING) {
+		desc->status &= ~IRQ_PENDING;
+		desc->istate |= IRQS_REPLAY;
 
 		if (!desc->irq_data.chip->irq_retrigger ||
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index a96140eea409..2e7d08fff0ce 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -8,3 +8,7 @@ enum {
 
 #undef IRQ_INPROGRESS
 #define IRQ_INPROGRESS		GOT_YOU_MORON
+#undef IRQ_REPLAY
+#define IRQ_REPLAY		GOT_YOU_MORON
+#undef IRQ_WAITING
+#define IRQ_WAITING		GOT_YOU_MORON
-- 
cgit v1.2.3


From c1594b77e46124bb462f961e536120e471c67446 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 7 Feb 2011 22:11:30 +0100
Subject: genirq: Move IRQ_DISABLED to core

Keep status in sync until all abusers are fixed.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  4 ++--
 kernel/irq/chip.c      | 48 +++++++++++++++++++++++++++++++-----------------
 kernel/irq/compat.h    | 12 ++++++++++++
 kernel/irq/internals.h |  4 +++-
 kernel/irq/irqdesc.c   |  2 ++
 kernel/irq/manage.c    |  4 ++--
 kernel/irq/migration.c |  2 +-
 kernel/irq/settings.h  |  2 ++
 kernel/irq/spurious.c  |  4 ++--
 9 files changed, 57 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index c38dbd506656..32efca71ce88 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -55,9 +55,9 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_INPROGRESS		0x00000100	/* DEPRECATED */
 #define IRQ_REPLAY		0x00000200	/* DEPRECATED */
 #define IRQ_WAITING		0x00000400	/* DEPRECATED */
+#define IRQ_DISABLED		0x00000800	/* DEPRECATED */
 #endif
 
-#define IRQ_DISABLED		0x00000800	/* IRQ disabled - do not enter! */
 #define IRQ_PENDING		0x00001000	/* IRQ pending - replay on enable */
 
 #define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
@@ -231,7 +231,7 @@ struct irq_chip {
 # define ARCH_IRQ_INIT_FLAGS	0
 #endif
 
-#define IRQ_DEFAULT_INIT_FLAGS	(IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
+#define IRQ_DEFAULT_INIT_FLAGS	ARCH_IRQ_INIT_FLAGS
 
 struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 59ae14527ecd..527df7ab1b05 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -164,9 +164,21 @@ struct irq_data *irq_get_irq_data(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(irq_get_irq_data);
 
+static void irq_state_clr_disabled(struct irq_desc *desc)
+{
+	desc->istate &= ~IRQS_DISABLED;
+	irq_compat_clr_disabled(desc);
+}
+
+static void irq_state_set_disabled(struct irq_desc *desc)
+{
+	desc->istate |= IRQS_DISABLED;
+	irq_compat_set_disabled(desc);
+}
+
 int irq_startup(struct irq_desc *desc)
 {
-	desc->status &= ~IRQ_DISABLED;
+	irq_state_clr_disabled(desc);
 	desc->depth = 0;
 
 	if (desc->irq_data.chip->irq_startup) {
@@ -181,7 +193,7 @@ int irq_startup(struct irq_desc *desc)
 
 void irq_shutdown(struct irq_desc *desc)
 {
-	desc->status |= IRQ_DISABLED;
+	irq_state_set_disabled(desc);
 	desc->depth = 1;
 	if (desc->irq_data.chip->irq_shutdown)
 		desc->irq_data.chip->irq_shutdown(&desc->irq_data);
@@ -194,7 +206,7 @@ void irq_shutdown(struct irq_desc *desc)
 
 void irq_enable(struct irq_desc *desc)
 {
-	desc->status &= ~IRQ_DISABLED;
+	irq_state_clr_disabled(desc);
 	if (desc->irq_data.chip->irq_enable)
 		desc->irq_data.chip->irq_enable(&desc->irq_data);
 	else
@@ -204,7 +216,7 @@ void irq_enable(struct irq_desc *desc)
 
 void irq_disable(struct irq_desc *desc)
 {
-	desc->status |= IRQ_DISABLED;
+	irq_state_set_disabled(desc);
 	if (desc->irq_data.chip->irq_disable) {
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
 		desc->status |= IRQ_MASKED;
@@ -380,7 +392,7 @@ void handle_nested_irq(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
-	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
 	irq_compat_set_progress(desc);
@@ -431,7 +443,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (unlikely(!desc->action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
 	handle_irq_event(desc);
@@ -467,12 +479,12 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	 * If its disabled or no action available
 	 * keep it masked and get out of here
 	 */
-	if (unlikely(!desc->action || (desc->status & IRQ_DISABLED)))
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED)))
 		goto out_unlock;
 
 	handle_irq_event(desc);
 
-	if (!(desc->status & IRQ_DISABLED) && !(desc->istate & IRQS_ONESHOT))
+	if (!(desc->istate & (IRQS_DISABLED | IRQS_ONESHOT)))
 		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
@@ -505,7 +517,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	 * If its disabled or no action available
 	 * then mask it and get out of here:
 	 */
-	if (unlikely(!desc->action || (desc->status & IRQ_DISABLED))) {
+	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED))) {
 		desc->status |= IRQ_PENDING;
 		mask_irq(desc);
 		goto out;
@@ -543,8 +555,8 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	 * we shouldn't process the IRQ. Mark it pending, handle
 	 * the necessary masking and go out
 	 */
-	if (unlikely((desc->istate & (IRQS_INPROGRESS) ||
-		      (desc->status & IRQ_DISABLED) || !desc->action))) {
+	if (unlikely((desc->istate & (IRQS_DISABLED | IRQS_INPROGRESS) ||
+		      !desc->action))) {
 		if (!irq_check_poll(desc)) {
 			desc->status |= IRQ_PENDING;
 			mask_ack_irq(desc);
@@ -567,15 +579,16 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		 * one, we could have masked the irq.
 		 * Renable it, if it was not disabled in meantime.
 		 */
-		if (unlikely((desc->status &
-			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
-			      (IRQ_PENDING | IRQ_MASKED))) {
-			unmask_irq(desc);
+		if (unlikely(desc->status & IRQ_PENDING)) {
+			if (!(desc->istate & IRQS_DISABLED) &&
+			    (desc->status & IRQ_MASKED))
+				unmask_irq(desc);
 		}
 
 		handle_irq_event(desc);
 
-	} while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING);
+	} while ((desc->status & IRQ_PENDING) &&
+		 !(desc->istate & IRQS_DISABLED));
 
 out_unlock:
 	raw_spin_unlock(&desc->lock);
@@ -639,7 +652,8 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	if (handle == handle_bad_irq) {
 		if (desc->irq_data.chip != &no_irq_chip)
 			mask_ack_irq(desc);
-		desc->status |= IRQ_DISABLED;
+		irq_compat_set_disabled(desc);
+		desc->istate |= IRQS_DISABLED;
 		desc->depth = 1;
 	}
 	desc->handle_irq = handle;
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
index aac6e400e608..bc0c2a501e82 100644
--- a/kernel/irq/compat.h
+++ b/kernel/irq/compat.h
@@ -11,7 +11,19 @@ static inline void irq_compat_clr_progress(struct irq_desc *desc)
 {
 	desc->status &= ~IRQ_INPROGRESS;
 }
+static inline void irq_compat_set_disabled(struct irq_desc *desc)
+{
+	desc->status |= IRQ_DISABLED;
+}
+
+static inline void irq_compat_clr_disabled(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_DISABLED;
+}
 #else
 static inline void irq_compat_set_progress(struct irq_desc *desc) { }
 static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
+static inline void irq_compat_set_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_clr_disabled(struct irq_desc *desc) { }
 #endif
+
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 54037533af7a..919d2dd0bb33 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -45,6 +45,7 @@ enum {
  * IRQS_ONESHOT			- irq is not unmasked in primary handler
  * IRQS_REPLAY			- irq is replayed
  * IRQS_WAITING			- irq is waiting
+ * IRQS_DISABLED		- irq is disabled
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -54,6 +55,7 @@ enum {
 	IRQS_ONESHOT		= 0x00000020,
 	IRQS_REPLAY		= 0x00000040,
 	IRQS_WAITING		= 0x00000080,
+	IRQS_DISABLED		= 0x00000100,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
@@ -137,7 +139,6 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		print_symbol("%s\n", (unsigned long)desc->action->handler);
 	}
 
-	P(IRQ_DISABLED);
 	P(IRQ_PENDING);
 	P(IRQ_LEVEL);
 	P(IRQ_MASKED);
@@ -152,6 +153,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	PS(IRQS_INPROGRESS);
 	PS(IRQS_REPLAY);
 	PS(IRQS_WAITING);
+	PS(IRQS_DISABLED);
 }
 
 #undef P
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 8b87f2ce0203..78866d050bc9 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -80,6 +80,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
 	desc->irq_data.handler_data = NULL;
 	desc->irq_data.msi_desc = NULL;
 	desc->status = _IRQ_DEFAULT_INIT_FLAGS;
+	desc->istate = IRQS_DISABLED;
 	desc->handle_irq = handle_bad_irq;
 	desc->depth = 1;
 	desc->irq_count = 0;
@@ -247,6 +248,7 @@ int __init early_irq_init(void)
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status		= _IRQ_DEFAULT_INIT_FLAGS,
+		.istate		= IRQS_DISABLED,
 		.handle_irq	= handle_bad_irq,
 		.depth		= 1,
 		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7971df53d6a9..77ff275b54cf 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -646,7 +646,7 @@ again:
 		goto again;
 	}
 
-	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
+	if (!(desc->istate & IRQS_DISABLED) && (desc->status & IRQ_MASKED)) {
 		desc->status &= ~IRQ_MASKED;
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
@@ -709,7 +709,7 @@ static int irq_thread(void *data)
 		atomic_inc(&desc->threads_active);
 
 		raw_spin_lock_irq(&desc->lock);
-		if (unlikely(desc->status & IRQ_DISABLED)) {
+		if (unlikely(desc->istate & IRQS_DISABLED)) {
 			/*
 			 * CHECKME: We might need a dedicated
 			 * IRQ_THREAD_PENDING flag here, which
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 441fd629ff04..8c68cb8555a7 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -61,7 +61,7 @@ void move_native_irq(int irq)
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
 
-	if (unlikely(desc->status & IRQ_DISABLED))
+	if (unlikely(desc->istate & IRQS_DISABLED))
 		return;
 
 	/*
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 2e7d08fff0ce..5e3411c7c62b 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -12,3 +12,5 @@ enum {
 #define IRQ_REPLAY		GOT_YOU_MORON
 #undef IRQ_WAITING
 #define IRQ_WAITING		GOT_YOU_MORON
+#undef IRQ_DISABLED
+#define IRQ_DISABLED		GOT_YOU_MORON
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 51504837d8cc..367614f858ff 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -50,7 +50,7 @@ bool irq_wait_for_poll(struct irq_desc *desc)
 		raw_spin_lock(&desc->lock);
 	} while (desc->istate & IRQS_INPROGRESS);
 	/* Might have been disabled in meantime */
-	return !(desc->status & IRQ_DISABLED) && desc->action;
+	return !(desc->istate & IRQS_DISABLED) && desc->action;
 #else
 	return false;
 #endif
@@ -75,7 +75,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	 * Do not poll disabled interrupts unless the spurious
 	 * disabled poller asks explicitely.
 	 */
-	if ((desc->status & IRQ_DISABLED) && !force)
+	if ((desc->istate & IRQS_DISABLED) && !force)
 		goto out;
 
 	/*
-- 
cgit v1.2.3


From 2a0d6fb335d4428285dab2d254911748e6040807 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 12:17:57 +0100
Subject: genirq: Move IRQ_PENDING flag to core

Keep status in sync until all users are fixed.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  2 +-
 kernel/irq/autoprobe.c |  6 ++++--
 kernel/irq/chip.c      | 10 ++++++----
 kernel/irq/compat.h    | 12 +++++++++++-
 kernel/irq/handle.c    |  3 ++-
 kernel/irq/internals.h |  4 +++-
 kernel/irq/manage.c    |  5 +++--
 kernel/irq/pm.c        |  3 ++-
 kernel/irq/resend.c    |  5 +++--
 kernel/irq/settings.h  |  2 ++
 kernel/irq/spurious.c  |  5 +++--
 11 files changed, 40 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 32efca71ce88..7ca55c9deba4 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -56,9 +56,9 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_REPLAY		0x00000200	/* DEPRECATED */
 #define IRQ_WAITING		0x00000400	/* DEPRECATED */
 #define IRQ_DISABLED		0x00000800	/* DEPRECATED */
+#define IRQ_PENDING		0x00001000	/* DEPRECATED */
 #endif
 
-#define IRQ_PENDING		0x00001000	/* IRQ pending - replay on enable */
 
 #define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
 #define IRQ_MASKED		0x00008000	/* IRQ masked - shouldn't be seen again */
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 9ea8bb99f7c1..aab64c262726 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -76,8 +76,10 @@ unsigned long probe_irq_on(void)
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
 			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
-			if (irq_startup(desc))
-				desc->status |= IRQ_PENDING;
+			if (irq_startup(desc)) {
+				irq_compat_set_pending(desc);
+				desc->istate |= IRQS_PENDING;
+			}
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 527df7ab1b05..17c87865bfb1 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -518,7 +518,8 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	 * then mask it and get out of here:
 	 */
 	if (unlikely(!desc->action || (desc->istate & IRQS_DISABLED))) {
-		desc->status |= IRQ_PENDING;
+		irq_compat_set_pending(desc);
+		desc->istate |= IRQS_PENDING;
 		mask_irq(desc);
 		goto out;
 	}
@@ -558,7 +559,8 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely((desc->istate & (IRQS_DISABLED | IRQS_INPROGRESS) ||
 		      !desc->action))) {
 		if (!irq_check_poll(desc)) {
-			desc->status |= IRQ_PENDING;
+			irq_compat_set_pending(desc);
+			desc->istate |= IRQS_PENDING;
 			mask_ack_irq(desc);
 			goto out_unlock;
 		}
@@ -579,7 +581,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		 * one, we could have masked the irq.
 		 * Renable it, if it was not disabled in meantime.
 		 */
-		if (unlikely(desc->status & IRQ_PENDING)) {
+		if (unlikely(desc->istate & IRQS_PENDING)) {
 			if (!(desc->istate & IRQS_DISABLED) &&
 			    (desc->status & IRQ_MASKED))
 				unmask_irq(desc);
@@ -587,7 +589,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 
 		handle_irq_event(desc);
 
-	} while ((desc->status & IRQ_PENDING) &&
+	} while ((desc->istate & IRQS_PENDING) &&
 		 !(desc->istate & IRQS_DISABLED));
 
 out_unlock:
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
index bc0c2a501e82..0067a69781f4 100644
--- a/kernel/irq/compat.h
+++ b/kernel/irq/compat.h
@@ -15,15 +15,25 @@ static inline void irq_compat_set_disabled(struct irq_desc *desc)
 {
 	desc->status |= IRQ_DISABLED;
 }
-
 static inline void irq_compat_clr_disabled(struct irq_desc *desc)
 {
 	desc->status &= ~IRQ_DISABLED;
 }
+static inline void irq_compat_set_pending(struct irq_desc *desc)
+{
+	desc->status |= IRQ_PENDING;
+}
+
+static inline void irq_compat_clr_pending(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_PENDING;
+}
 #else
 static inline void irq_compat_set_progress(struct irq_desc *desc) { }
 static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
 static inline void irq_compat_set_disabled(struct irq_desc *desc) { }
 static inline void irq_compat_clr_disabled(struct irq_desc *desc) { }
+static inline void irq_compat_set_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_pending(struct irq_desc *desc) { }
 #endif
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d4ae0b1ccc00..6e34bdbeb26a 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -122,7 +122,8 @@ irqreturn_t handle_irq_event(struct irq_desc *desc)
 	struct irqaction *action = desc->action;
 	irqreturn_t ret;
 
-	desc->status &= ~IRQ_PENDING;
+	irq_compat_clr_pending(desc);
+	desc->istate &= ~IRQS_PENDING;
 	irq_compat_set_progress(desc);
 	desc->istate |= IRQS_INPROGRESS;
 	raw_spin_unlock(&desc->lock);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 919d2dd0bb33..fdf2524437eb 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -46,6 +46,7 @@ enum {
  * IRQS_REPLAY			- irq is replayed
  * IRQS_WAITING			- irq is waiting
  * IRQS_DISABLED		- irq is disabled
+ * IRQS_PENDING			- irq is pending and replayed later
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -56,6 +57,7 @@ enum {
 	IRQS_REPLAY		= 0x00000040,
 	IRQS_WAITING		= 0x00000080,
 	IRQS_DISABLED		= 0x00000100,
+	IRQS_PENDING		= 0x00000200,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
@@ -139,7 +141,6 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		print_symbol("%s\n", (unsigned long)desc->action->handler);
 	}
 
-	P(IRQ_PENDING);
 	P(IRQ_LEVEL);
 	P(IRQ_MASKED);
 #ifdef CONFIG_IRQ_PER_CPU
@@ -154,6 +155,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	PS(IRQS_REPLAY);
 	PS(IRQS_WAITING);
 	PS(IRQS_DISABLED);
+	PS(IRQS_PENDING);
 }
 
 #undef P
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 77ff275b54cf..ac060814a787 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -714,10 +714,11 @@ static int irq_thread(void *data)
 			 * CHECKME: We might need a dedicated
 			 * IRQ_THREAD_PENDING flag here, which
 			 * retriggers the thread in check_irq_resend()
-			 * but AFAICT IRQ_PENDING should be fine as it
+			 * but AFAICT IRQS_PENDING should be fine as it
 			 * retriggers the interrupt itself --- tglx
 			 */
-			desc->status |= IRQ_PENDING;
+			irq_compat_set_pending(desc);
+			desc->istate |= IRQS_PENDING;
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
 			raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index d6bfb89cce91..d7389418e91a 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -69,7 +69,8 @@ int check_wakeup_irqs(void)
 	int irq;
 
 	for_each_irq_desc(irq, desc)
-		if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING))
+		if ((desc->status & IRQ_WAKEUP) &&
+		    (desc->istate & IRQS_PENDING))
 			return -EBUSY;
 
 	return 0;
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index f83387cd11f3..ff1fea060014 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -64,8 +64,9 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 		return;
 	if (desc->istate & IRQS_REPLAY)
 		return;
-	if (desc->status & IRQ_PENDING) {
-		desc->status &= ~IRQ_PENDING;
+	if (desc->istate & IRQS_PENDING) {
+		irq_compat_clr_pending(desc);
+		desc->istate &= ~IRQS_PENDING;
 		desc->istate |= IRQS_REPLAY;
 
 		if (!desc->irq_data.chip->irq_retrigger ||
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 5e3411c7c62b..623fcf83e7de 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -14,3 +14,5 @@ enum {
 #define IRQ_WAITING		GOT_YOU_MORON
 #undef IRQ_DISABLED
 #define IRQ_DISABLED		GOT_YOU_MORON
+#undef IRQ_PENDING
+#define IRQ_PENDING		GOT_YOU_MORON
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 367614f858ff..692ce2bae302 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -93,7 +93,8 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 		 * Already running: If it is shared get the other
 		 * CPU to go looking for our mystery interrupt too
 		 */
-		desc->status |= IRQ_PENDING;
+		irq_compat_set_pending(desc);
+		desc->istate |= IRQS_PENDING;
 		goto out;
 	}
 
@@ -103,7 +104,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 		if (handle_irq_event(desc) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
 		action = desc->action;
-	} while ((desc->status & IRQ_PENDING) && action);
+	} while ((desc->istate & IRQS_PENDING) && action);
 	desc->istate &= ~IRQS_POLL_INPROGRESS;
 out:
 	raw_spin_unlock(&desc->lock);
-- 
cgit v1.2.3


From 6e40262ea43c4b0e3f435b3a083e4461ef921c17 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 12:36:06 +0100
Subject: genirq: Move IRQ_MASKED to core

Keep status in sync until all users are fixed.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  2 +-
 kernel/irq/chip.c      | 28 ++++++++++++++++++++--------
 kernel/irq/compat.h    | 11 +++++++++++
 kernel/irq/internals.h |  4 +++-
 kernel/irq/manage.c    |  5 +++--
 kernel/irq/migration.c |  2 +-
 kernel/irq/settings.h  |  2 ++
 7 files changed, 41 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 7ca55c9deba4..9800bac4c398 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -57,11 +57,11 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_WAITING		0x00000400	/* DEPRECATED */
 #define IRQ_DISABLED		0x00000800	/* DEPRECATED */
 #define IRQ_PENDING		0x00001000	/* DEPRECATED */
+#define IRQ_MASKED		0x00002000	/* DEPRECATED */
 #endif
 
 
 #define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
-#define IRQ_MASKED		0x00008000	/* IRQ masked - shouldn't be seen again */
 #define IRQ_PER_CPU		0x00010000	/* IRQ is per CPU */
 #define IRQ_NOPROBE		0x00020000	/* IRQ is not valid for probing */
 #define IRQ_NOREQUEST		0x00040000	/* IRQ cannot be requested */
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 17c87865bfb1..73b2e7e00934 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -176,6 +176,18 @@ static void irq_state_set_disabled(struct irq_desc *desc)
 	irq_compat_set_disabled(desc);
 }
 
+static void irq_state_clr_masked(struct irq_desc *desc)
+{
+	desc->istate &= ~IRQS_MASKED;
+	irq_compat_clr_masked(desc);
+}
+
+static void irq_state_set_masked(struct irq_desc *desc)
+{
+	desc->istate |= IRQS_MASKED;
+	irq_compat_set_masked(desc);
+}
+
 int irq_startup(struct irq_desc *desc)
 {
 	irq_state_clr_disabled(desc);
@@ -183,7 +195,7 @@ int irq_startup(struct irq_desc *desc)
 
 	if (desc->irq_data.chip->irq_startup) {
 		int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
-		desc->status &= ~IRQ_MASKED;
+		irq_state_clr_masked(desc);
 		return ret;
 	}
 
@@ -201,7 +213,7 @@ void irq_shutdown(struct irq_desc *desc)
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	else
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
-	desc->status |= IRQ_MASKED;
+	irq_state_set_masked(desc);
 }
 
 void irq_enable(struct irq_desc *desc)
@@ -211,7 +223,7 @@ void irq_enable(struct irq_desc *desc)
 		desc->irq_data.chip->irq_enable(&desc->irq_data);
 	else
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
-	desc->status &= ~IRQ_MASKED;
+	irq_state_clr_masked(desc);
 }
 
 void irq_disable(struct irq_desc *desc)
@@ -219,8 +231,8 @@ void irq_disable(struct irq_desc *desc)
 	irq_state_set_disabled(desc);
 	if (desc->irq_data.chip->irq_disable) {
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
-		desc->status |= IRQ_MASKED;
 	}
+	irq_state_set_masked(desc);
 }
 
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
@@ -352,14 +364,14 @@ static inline void mask_ack_irq(struct irq_desc *desc)
 		if (desc->irq_data.chip->irq_ack)
 			desc->irq_data.chip->irq_ack(&desc->irq_data);
 	}
-	desc->status |= IRQ_MASKED;
+	irq_state_set_masked(desc);
 }
 
 static inline void mask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_mask) {
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
-		desc->status |= IRQ_MASKED;
+		irq_state_set_masked(desc);
 	}
 }
 
@@ -367,7 +379,7 @@ static inline void unmask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_unmask) {
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
-		desc->status &= ~IRQ_MASKED;
+		irq_state_clr_masked(desc);
 	}
 }
 
@@ -583,7 +595,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		 */
 		if (unlikely(desc->istate & IRQS_PENDING)) {
 			if (!(desc->istate & IRQS_DISABLED) &&
-			    (desc->status & IRQ_MASKED))
+			    (desc->istate & IRQS_MASKED))
 				unmask_irq(desc);
 		}
 
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
index 0067a69781f4..593abecbcc44 100644
--- a/kernel/irq/compat.h
+++ b/kernel/irq/compat.h
@@ -28,6 +28,15 @@ static inline void irq_compat_clr_pending(struct irq_desc *desc)
 {
 	desc->status &= ~IRQ_PENDING;
 }
+static inline void irq_compat_set_masked(struct irq_desc *desc)
+{
+	desc->status |= IRQ_MASKED;
+}
+
+static inline void irq_compat_clr_masked(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_MASKED;
+}
 #else
 static inline void irq_compat_set_progress(struct irq_desc *desc) { }
 static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
@@ -35,5 +44,7 @@ static inline void irq_compat_set_disabled(struct irq_desc *desc) { }
 static inline void irq_compat_clr_disabled(struct irq_desc *desc) { }
 static inline void irq_compat_set_pending(struct irq_desc *desc) { }
 static inline void irq_compat_clr_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_masked(struct irq_desc *desc) { }
+static inline void irq_compat_clr_masked(struct irq_desc *desc) { }
 #endif
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index fdf2524437eb..3f2fcc194dcc 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -47,6 +47,7 @@ enum {
  * IRQS_WAITING			- irq is waiting
  * IRQS_DISABLED		- irq is disabled
  * IRQS_PENDING			- irq is pending and replayed later
+ * IRQS_MASKED			- irq is masked
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -58,6 +59,7 @@ enum {
 	IRQS_WAITING		= 0x00000080,
 	IRQS_DISABLED		= 0x00000100,
 	IRQS_PENDING		= 0x00000200,
+	IRQS_MASKED		= 0x00000400,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
@@ -142,7 +144,6 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	}
 
 	P(IRQ_LEVEL);
-	P(IRQ_MASKED);
 #ifdef CONFIG_IRQ_PER_CPU
 	P(IRQ_PER_CPU);
 #endif
@@ -156,6 +157,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	PS(IRQS_WAITING);
 	PS(IRQS_DISABLED);
 	PS(IRQS_PENDING);
+	PS(IRQS_MASKED);
 }
 
 #undef P
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ac060814a787..83fd20194e5b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -646,8 +646,9 @@ again:
 		goto again;
 	}
 
-	if (!(desc->istate & IRQS_DISABLED) && (desc->status & IRQ_MASKED)) {
-		desc->status &= ~IRQ_MASKED;
+	if (!(desc->istate & IRQS_DISABLED) && (desc->istate & IRQS_MASKED)) {
+		irq_compat_clr_masked(desc);
+		desc->istate &= ~IRQS_MASKED;
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
 	raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 8c68cb8555a7..6f2f98480354 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -69,7 +69,7 @@ void move_native_irq(int irq)
 	 * threaded interrupt with ONESHOT set, we can end up with an
 	 * interrupt storm.
 	 */
-	masked = desc->status & IRQ_MASKED;
+	masked = desc->istate & IRQS_MASKED;
 	if (!masked)
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
 	move_masked_irq(irq);
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 623fcf83e7de..2cd45fd5ec8a 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -16,3 +16,5 @@ enum {
 #define IRQ_DISABLED		GOT_YOU_MORON
 #undef IRQ_PENDING
 #define IRQ_PENDING		GOT_YOU_MORON
+#undef IRQ_MASKED
+#define IRQ_MASKED		GOT_YOU_MORON
-- 
cgit v1.2.3


From c531e8361f1968d664e6e97fbd3bfa4cf0e62e42 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 12:44:58 +0100
Subject: genirq: Move IRQ_SUSPENDED to core

No users outside of core.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 2 --
 kernel/irq/internals.h | 2 ++
 kernel/irq/manage.c    | 8 ++++----
 kernel/irq/pm.c        | 6 +++---
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 9800bac4c398..3ce45c257edb 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -60,7 +60,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_MASKED		0x00002000	/* DEPRECATED */
 #endif
 
-
 #define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
 #define IRQ_PER_CPU		0x00010000	/* IRQ is per CPU */
 #define IRQ_NOPROBE		0x00020000	/* IRQ is not valid for probing */
@@ -71,7 +70,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
 #define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
 #define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
-#define IRQ_SUSPENDED		0x04000000	/* IRQ has gone through suspend sequence */
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
 
 #define IRQF_MODIFY_MASK	\
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 3f2fcc194dcc..46889119e6a6 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -48,6 +48,7 @@ enum {
  * IRQS_DISABLED		- irq is disabled
  * IRQS_PENDING			- irq is pending and replayed later
  * IRQS_MASKED			- irq is masked
+ * IRQS_SUSPENDED		- irq is suspended
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -60,6 +61,7 @@ enum {
 	IRQS_DISABLED		= 0x00000100,
 	IRQS_PENDING		= 0x00000200,
 	IRQS_MASKED		= 0x00000400,
+	IRQS_SUSPENDED		= 0x00000800,
 };
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 83fd20194e5b..b912de4ff4de 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -326,7 +326,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 	if (suspend) {
 		if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
 			return;
-		desc->status |= IRQ_SUSPENDED;
+		desc->istate |= IRQS_SUSPENDED;
 	}
 
 	if (!desc->depth++)
@@ -388,7 +388,7 @@ EXPORT_SYMBOL(disable_irq);
 void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 {
 	if (resume) {
-		if (!(desc->status & IRQ_SUSPENDED)) {
+		if (!(desc->istate & IRQS_SUSPENDED)) {
 			if (!desc->action)
 				return;
 			if (!(desc->action->flags & IRQF_FORCE_RESUME))
@@ -396,7 +396,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 			/* Pretend that it got disabled ! */
 			desc->depth++;
 		}
-		desc->status &= ~IRQ_SUSPENDED;
+		desc->istate &= ~IRQS_SUSPENDED;
 	}
 
 	switch (desc->depth) {
@@ -405,7 +405,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
 		break;
 	case 1: {
-		if (desc->status & IRQ_SUSPENDED)
+		if (desc->istate & IRQS_SUSPENDED)
 			goto err_out;
 		/* Prevent probing on this irq: */
 		desc->status |= IRQ_NOPROBE;
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index d7389418e91a..d81337fc1cff 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -18,7 +18,7 @@
  * During system-wide suspend or hibernation device drivers need to be prevented
  * from receiving interrupts and this function is provided for this purpose.
  * It marks all interrupt lines in use, except for the timer ones, as disabled
- * and sets the IRQ_SUSPENDED flag for each of them.
+ * and sets the IRQS_SUSPENDED flag for each of them.
  */
 void suspend_device_irqs(void)
 {
@@ -34,7 +34,7 @@ void suspend_device_irqs(void)
 	}
 
 	for_each_irq_desc(irq, desc)
-		if (desc->status & IRQ_SUSPENDED)
+		if (desc->istate & IRQS_SUSPENDED)
 			synchronize_irq(irq);
 }
 EXPORT_SYMBOL_GPL(suspend_device_irqs);
@@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(suspend_device_irqs);
  * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
  *
  * Enable all interrupt lines previously disabled by suspend_device_irqs() that
- * have the IRQ_SUSPENDED flag set.
+ * have the IRQS_SUSPENDED flag set.
  */
 void resume_device_irqs(void)
 {
-- 
cgit v1.2.3


From 91c499178139d6597e68db19638e4135510a34b8 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 3 Feb 2011 20:48:29 +0100
Subject: genirq: Add state field to irq_data

Some chip implementations need to access certain status flags. With
sparse irqs that requires a lookup of the irq descriptor. Add a state
field which contains such flags.

Name it in a way which will make coders happy to access it with the
proper accessor functions. And it's easy to grep for.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h     | 3 +++
 include/linux/irqdesc.h | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3ce45c257edb..62bb08e4af13 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -102,6 +102,8 @@ struct msi_desc;
  * struct irq_data - per irq and irq chip data passed down to chip functions
  * @irq:		interrupt number
  * @node:		node index useful for balancing
+ * @state_use_accessor: status information for irq chip functions.
+ *			Use accessor functions to deal with it
  * @chip:		low level interrupt hardware access
  * @handler_data:	per-IRQ data for the irq_chip methods
  * @chip_data:		platform-specific per-chip private data for the chip
@@ -116,6 +118,7 @@ struct msi_desc;
 struct irq_data {
 	unsigned int		irq;
 	unsigned int		node;
+	unsigned int		state_use_accessors;
 	struct irq_chip		*chip;
 	void			*handler_data;
 	void			*chip_data;
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 782bf9851a9f..581d9665fd38 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -48,6 +48,7 @@ struct irq_desc {
 		struct {
 			unsigned int		irq;
 			unsigned int		node;
+			unsigned int		pad_do_not_even_think_about_it;
 			struct irq_chip		*chip;
 			void			*handler_data;
 			void			*chip_data;
-- 
cgit v1.2.3


From f230b6d5c48f8d12f4dfa1f8b5ab0b0320076d21 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 5 Feb 2011 15:20:04 +0100
Subject: genirq: Add IRQ_MOVE_PENDING to irq_data.state

chip implementations need to know about it. Keep status in sync until
all users are fixed.

Accessor function: irqd_is_setaffinity_pending(irqdata)

Coders who access them directly will be tracked down and slapped with
stinking trouts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 20 ++++++++++++++++++--
 kernel/irq/compat.h    | 11 +++++++++++
 kernel/irq/internals.h | 15 +++++++++++++++
 kernel/irq/manage.c    |  4 ++--
 kernel/irq/migration.c |  6 +++---
 kernel/irq/proc.c      |  2 +-
 kernel/irq/settings.h  |  2 ++
 7 files changed, 52 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62bb08e4af13..2899905bfac7 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -58,15 +58,16 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_DISABLED		0x00000800	/* DEPRECATED */
 #define IRQ_PENDING		0x00001000	/* DEPRECATED */
 #define IRQ_MASKED		0x00002000	/* DEPRECATED */
+/* DEPRECATED use irq_setaffinity_pending() instead*/
+#define IRQ_MOVE_PENDING	0x00004000
 #endif
 
-#define IRQ_LEVEL		0x00004000	/* IRQ level triggered */
+#define IRQ_LEVEL		0x00008000	/* IRQ level triggered */
 #define IRQ_PER_CPU		0x00010000	/* IRQ is per CPU */
 #define IRQ_NOPROBE		0x00020000	/* IRQ is not valid for probing */
 #define IRQ_NOREQUEST		0x00040000	/* IRQ cannot be requested */
 #define IRQ_NOAUTOEN		0x00080000	/* IRQ will not be enabled on request irq */
 #define IRQ_WAKEUP		0x00100000	/* IRQ triggers system wakeup */
-#define IRQ_MOVE_PENDING	0x00200000	/* need to re-target IRQ destination */
 #define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
 #define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
 #define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
@@ -128,6 +129,21 @@ struct irq_data {
 #endif
 };
 
+/*
+ * Bit masks for irq_data.state
+ *
+ * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
+ */
+enum {
+	/* Bit 0 - 7 reserved for TYPE will use later */
+	IRQD_SETAFFINITY_PENDING = (1 << 8),
+};
+
+static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_SETAFFINITY_PENDING;
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
index 593abecbcc44..5e33aadadacc 100644
--- a/kernel/irq/compat.h
+++ b/kernel/irq/compat.h
@@ -37,6 +37,15 @@ static inline void irq_compat_clr_masked(struct irq_desc *desc)
 {
 	desc->status &= ~IRQ_MASKED;
 }
+static inline void irq_compat_set_move_pending(struct irq_desc *desc)
+{
+	desc->status |= IRQ_MOVE_PENDING;
+}
+
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_MOVE_PENDING;
+}
 #else
 static inline void irq_compat_set_progress(struct irq_desc *desc) { }
 static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
@@ -46,5 +55,7 @@ static inline void irq_compat_set_pending(struct irq_desc *desc) { }
 static inline void irq_compat_clr_pending(struct irq_desc *desc) { }
 static inline void irq_compat_set_masked(struct irq_desc *desc) { }
 static inline void irq_compat_clr_masked(struct irq_desc *desc) { }
+static inline void irq_compat_set_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_clr_move_pending(struct irq_desc *desc) { }
 #endif
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index cef0849dcfa5..e93e6090cd47 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -124,6 +124,21 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
+/*
+ * Manipulation functions for irq_data.state
+ */
+static inline void irqd_set_move_pending(struct irq_data *d)
+{
+	d->state_use_accessors |= IRQD_SETAFFINITY_PENDING;
+	irq_compat_set_move_pending(irq_data_to_desc(d));
+}
+
+static inline void irqd_clr_move_pending(struct irq_data *d)
+{
+	d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
+	irq_compat_clr_move_pending(irq_data_to_desc(d));
+}
+
 /*
  * Debugging printout:
  */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ccc9389909ff..9a99c471d470 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -107,7 +107,7 @@ static inline bool irq_can_move_pcntxt(struct irq_desc *desc)
 }
 static inline bool irq_move_pending(struct irq_desc *desc)
 {
-	return desc->status & IRQ_MOVE_PENDING;
+	return irqd_is_setaffinity_pending(&desc->irq_data);
 }
 static inline void
 irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
@@ -156,7 +156,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 			ret = 0;
 		}
 	} else {
-		desc->status |= IRQ_MOVE_PENDING;
+		irqd_set_move_pending(&desc->irq_data);
 		irq_copy_pending(desc, mask);
 	}
 
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 6f2f98480354..9485ae081dcd 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -9,7 +9,7 @@ void move_masked_irq(int irq)
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_chip *chip = desc->irq_data.chip;
 
-	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
 		return;
 
 	/*
@@ -20,7 +20,7 @@ void move_masked_irq(int irq)
 		return;
 	}
 
-	desc->status &= ~IRQ_MOVE_PENDING;
+	irqd_clr_move_pending(&desc->irq_data);
 
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
@@ -58,7 +58,7 @@ void move_native_irq(int irq)
 	struct irq_desc *desc = irq_to_desc(irq);
 	bool masked;
 
-	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
+	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
 		return;
 
 	if (unlikely(desc->istate & IRQS_DISABLED))
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 26449239bb46..afe4e6803148 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -25,7 +25,7 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v)
 	const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PENDING)
+	if (irqd_is_setaffinity_pending(&desc->irq_data))
 		mask = desc->pending_mask;
 #endif
 	seq_cpumask(m, mask);
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index ef09824e4b32..bb104a2dce73 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -20,3 +20,5 @@ enum {
 #define IRQ_MASKED		GOT_YOU_MORON
 #undef IRQ_WAKEUP
 #define IRQ_WAKEUP		GOT_YOU_MORON
+#undef IRQ_MOVE_PENDING
+#define IRQ_MOVE_PENDING	GOT_YOU_MORON
-- 
cgit v1.2.3


From 6a58fb3bad099076f36f0f30f44507bc3275cdb6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 15:40:05 +0100
Subject: genirq: Remove CONFIG_IRQ_PER_CPU

The saving of this switch is minimal versus the ifdef mess it
creates. Simple enable PER_CPU unconditionally and remove the config
switch.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 5 -----
 kernel/irq/Kconfig     | 3 ---
 kernel/irq/internals.h | 2 --
 kernel/irq/manage.c    | 9 +++------
 4 files changed, 3 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 2899905bfac7..ab708f27a33b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -78,13 +78,8 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD)
 
-#ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
 # define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
-#else
-# define CHECK_IRQ_PER_CPU(var) 0
-# define IRQ_NO_BALANCING_MASK	IRQ_NO_BALANCING
-#endif
 
 /*
  * Return value for chip->irq_set_affinity()
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 9e2256de1d1a..48ad25f5fa59 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -32,9 +32,6 @@ config GENERIC_PENDING_IRQ
 config AUTO_IRQ_AFFINITY
        def_bool n
 
-config IRQ_PER_CPU
-       def_bool n
-
 config HARDIRQS_SW_RESEND
        def_bool n
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index e93e6090cd47..9e32b3d35d35 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -163,9 +163,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 	}
 
 	P(IRQ_LEVEL);
-#ifdef CONFIG_IRQ_PER_CPU
 	P(IRQ_PER_CPU);
-#endif
 	P(IRQ_NOPROBE);
 	P(IRQ_NOREQUEST);
 	P(IRQ_NOAUTOEN);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9a99c471d470..056aa49698b4 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -865,12 +865,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			goto mismatch;
 		}
 
-#if defined(CONFIG_IRQ_PER_CPU)
 		/* All handlers must agree on per-cpuness */
 		if ((old->flags & IRQF_PERCPU) !=
 		    (new->flags & IRQF_PERCPU))
 			goto mismatch;
-#endif
 
 		/* add new interrupt at end of irq queue */
 		do {
@@ -894,15 +892,14 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 				goto out_mask;
 		} else
 			compat_irq_chip_set_default_handler(desc);
-#if defined(CONFIG_IRQ_PER_CPU)
-		if (new->flags & IRQF_PERCPU)
-			desc->status |= IRQ_PER_CPU;
-#endif
 
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
 				  IRQS_INPROGRESS | IRQS_ONESHOT | \
 				  IRQS_WAITING);
 
+		if (new->flags & IRQF_PERCPU)
+			desc->status |= IRQ_PER_CPU;
+
 		if (new->flags & IRQF_ONESHOT)
 			desc->istate |= IRQS_ONESHOT;
 
-- 
cgit v1.2.3


From 8f53f92404bead2ab2154d45c8f508880bb5d95d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 16:50:00 +0100
Subject: genirq: Make CHECK_IRQ_PER_CPU an inline and deprecate it

Its' too ugly and needs to go. The only users are core code and
parisc. Core code does not need it and parisc gets a new check once
IRQ_PER_CPU is reflected in irq_data.state.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index ab708f27a33b..3f607ad94220 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -78,8 +78,12 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD)
 
-# define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
-# define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
+#define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
+
+static inline __deprecated bool CHECK_IRQ_PER_CPU(unsigned int status)
+{
+	return status & IRQ_PER_CPU;
+}
 
 /*
  * Return value for chip->irq_set_affinity()
-- 
cgit v1.2.3


From a005677b3dd05decdd8880cf3044ae709856f58f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 17:11:03 +0100
Subject: genirq: Mirror IRQ_PER_CPU and IRQ_NO_BALANCING in irq_data.state

That's the right data structure to look at for arch code.

Accessor functions are provided.

	 irqd_is_per_cpu(irqdata);
	 irqd_can_balance(irqdata);

Coders who access them directly will be tracked down and slapped with
stinking trouts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 16 +++++++++++++++-
 kernel/irq/chip.c      | 15 +++++++++------
 kernel/irq/internals.h | 11 +++++++++++
 kernel/irq/manage.c    | 16 ++++++++++------
 kernel/irq/migration.c |  2 +-
 kernel/irq/settings.h  | 36 ++++++++++++++++++++++++++++++++++++
 kernel/irq/spurious.c  |  3 ++-
 7 files changed, 84 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3f607ad94220..d5312e6fe1aa 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -132,10 +132,14 @@ struct irq_data {
  * Bit masks for irq_data.state
  *
  * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
+ * IRQD_NO_BALANCING		- Balancing disabled for this IRQ
+ * IRQD_PER_CPU			- Interrupt is per cpu
  */
 enum {
 	/* Bit 0 - 7 reserved for TYPE will use later */
-	IRQD_SETAFFINITY_PENDING = (1 << 8),
+	IRQD_SETAFFINITY_PENDING	= (1 <<  8),
+	IRQD_NO_BALANCING		= (1 << 10),
+	IRQD_PER_CPU			= (1 << 11),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -143,6 +147,16 @@ static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
 	return d->state_use_accessors & IRQD_SETAFFINITY_PENDING;
 }
 
+static inline bool irqd_is_per_cpu(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_PER_CPU;
+}
+
+static inline bool irqd_can_balance(struct irq_data *d)
+{
+	return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING));
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 73b2e7e00934..b8aa3dfe8301 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -706,12 +706,15 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 	if (!desc)
 		return;
 
-	/* Sanitize flags */
-	set &= IRQF_MODIFY_MASK;
-	clr &= IRQF_MODIFY_MASK;
-
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status &= ~clr;
-	desc->status |= set;
+
+	irq_settings_clr_and_set(desc, clr, set);
+
+	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU);
+	if (irq_settings_has_no_balance_set(desc))
+		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+	if (irq_settings_is_per_cpu(desc))
+		irqd_set(&desc->irq_data, IRQD_PER_CPU);
+
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b2ba59e73f21..a80b44d2735e 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -139,3 +139,14 @@ static inline void irqd_clr_move_pending(struct irq_data *d)
 	d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING;
 	irq_compat_clr_move_pending(irq_data_to_desc(d));
 }
+
+static inline void irqd_clear(struct irq_data *d, unsigned int mask)
+{
+	d->state_use_accessors &= ~mask;
+}
+
+static inline void irqd_set(struct irq_data *d, unsigned int mask)
+{
+	d->state_use_accessors |= mask;
+}
+
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f1cfa271ba70..84a0a9c22226 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -73,8 +73,8 @@ int irq_can_set_affinity(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if ((desc->status & (IRQ_PER_CPU | IRQ_NO_BALANCING)) ||
-	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
+	if (!irqd_can_balance(&desc->irq_data) || !desc->irq_data.chip ||
+	    !desc->irq_data.chip->irq_set_affinity)
 		return 0;
 
 	return 1;
@@ -897,8 +897,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 				  IRQS_INPROGRESS | IRQS_ONESHOT | \
 				  IRQS_WAITING);
 
-		if (new->flags & IRQF_PERCPU)
-			desc->status |= IRQ_PER_CPU;
+		if (new->flags & IRQF_PERCPU) {
+			irqd_set(&desc->irq_data, IRQD_PER_CPU);
+			irq_settings_set_per_cpu(desc);
+		}
 
 		if (new->flags & IRQF_ONESHOT)
 			desc->istate |= IRQS_ONESHOT;
@@ -910,8 +912,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->depth = 1;
 
 		/* Exclude IRQ from balancing if requested */
-		if (new->flags & IRQF_NOBALANCING)
-			desc->status |= IRQ_NO_BALANCING;
+		if (new->flags & IRQF_NOBALANCING) {
+			irq_settings_set_no_balancing(desc);
+			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+		}
 
 		/* Set default affinity mask once everything is setup */
 		setup_affinity(irq, desc, mask);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 24f53caddf47..7a93c6b88b25 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -15,7 +15,7 @@ void move_masked_irq(int irq)
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (desc->status & (IRQ_PER_CPU | IRQ_NO_BALANCING)) {
+	if (!irqd_can_balance(&desc->irq_data)) {
 		WARN_ON(1);
 		return;
 	}
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index bb104a2dce73..ba0fffe410ad 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -4,6 +4,9 @@
  */
 enum {
 	_IRQ_DEFAULT_INIT_FLAGS	= IRQ_DEFAULT_INIT_FLAGS,
+	_IRQ_PER_CPU		= IRQ_PER_CPU,
+	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
+	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
 #undef IRQ_INPROGRESS
@@ -22,3 +25,36 @@ enum {
 #define IRQ_WAKEUP		GOT_YOU_MORON
 #undef IRQ_MOVE_PENDING
 #define IRQ_MOVE_PENDING	GOT_YOU_MORON
+#undef IRQ_PER_CPU
+#define IRQ_PER_CPU		GOT_YOU_MORON
+#undef IRQ_NO_BALANCING
+#define IRQ_NO_BALANCING	GOT_YOU_MORON
+#undef IRQF_MODIFY_MASK
+#define IRQF_MODIFY_MASK	GOT_YOU_MORON
+
+static inline void
+irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
+{
+	desc->status &= ~(clr & _IRQF_MODIFY_MASK);
+	desc->status |= (set & _IRQF_MODIFY_MASK);
+}
+
+static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_PER_CPU;
+}
+
+static inline void irq_settings_set_no_balancing(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_NO_BALANCING;
+}
+
+static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_NO_BALANCING;
+}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 692ce2bae302..226ed7d26a84 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -68,7 +68,8 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	raw_spin_lock(&desc->lock);
 
 	/* PER_CPU and nested thread interrupts are never polled */
-	if (desc->status & (IRQ_PER_CPU | IRQ_NESTED_THREAD))
+	if (irq_settings_is_per_cpu(desc) ||
+	    (desc->status & IRQ_NESTED_THREAD))
 		goto out;
 
 	/*
-- 
cgit v1.2.3


From 2bdd10558c8d93009cb6c32ce9e30800fbb08add Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 17:22:00 +0100
Subject: genirq: Move IRQ_AFFINITY_SET to core

Keep status in sync until last abuser is gone.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  9 ++++++++-
 kernel/irq/compat.h    | 11 +++++++++++
 kernel/irq/internals.h |  4 ++++
 kernel/irq/manage.c    | 11 +++++++----
 kernel/irq/settings.h  |  2 ++
 5 files changed, 32 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index d5312e6fe1aa..8da1782ecfca 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -60,6 +60,7 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_MASKED		0x00002000	/* DEPRECATED */
 /* DEPRECATED use irq_setaffinity_pending() instead*/
 #define IRQ_MOVE_PENDING	0x00004000
+#define IRQ_AFFINITY_SET	0x02000000	/* DEPRECATED */
 #endif
 
 #define IRQ_LEVEL		0x00008000	/* IRQ level triggered */
@@ -70,7 +71,6 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_WAKEUP		0x00100000	/* IRQ triggers system wakeup */
 #define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
 #define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
-#define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
 
 #define IRQF_MODIFY_MASK	\
@@ -134,12 +134,14 @@ struct irq_data {
  * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
  * IRQD_NO_BALANCING		- Balancing disabled for this IRQ
  * IRQD_PER_CPU			- Interrupt is per cpu
+ * IRQD_AFFINITY_SET		- Interrupt affinity was set
  */
 enum {
 	/* Bit 0 - 7 reserved for TYPE will use later */
 	IRQD_SETAFFINITY_PENDING	= (1 <<  8),
 	IRQD_NO_BALANCING		= (1 << 10),
 	IRQD_PER_CPU			= (1 << 11),
+	IRQD_AFFINITY_SET		= (1 << 12),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -157,6 +159,11 @@ static inline bool irqd_can_balance(struct irq_data *d)
 	return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING));
 }
 
+static inline bool irqd_affinity_was_set(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_AFFINITY_SET;
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
diff --git a/kernel/irq/compat.h b/kernel/irq/compat.h
index 5e33aadadacc..6bbaf66aca85 100644
--- a/kernel/irq/compat.h
+++ b/kernel/irq/compat.h
@@ -46,6 +46,15 @@ static inline void irq_compat_clr_move_pending(struct irq_desc *desc)
 {
 	desc->status &= ~IRQ_MOVE_PENDING;
 }
+static inline void irq_compat_set_affinity(struct irq_desc *desc)
+{
+	desc->status |= IRQ_AFFINITY_SET;
+}
+
+static inline void irq_compat_clr_affinity(struct irq_desc *desc)
+{
+	desc->status &= ~IRQ_AFFINITY_SET;
+}
 #else
 static inline void irq_compat_set_progress(struct irq_desc *desc) { }
 static inline void irq_compat_clr_progress(struct irq_desc *desc) { }
@@ -57,5 +66,7 @@ static inline void irq_compat_set_masked(struct irq_desc *desc) { }
 static inline void irq_compat_clr_masked(struct irq_desc *desc) { }
 static inline void irq_compat_set_move_pending(struct irq_desc *desc) { }
 static inline void irq_compat_clr_move_pending(struct irq_desc *desc) { }
+static inline void irq_compat_set_affinity(struct irq_desc *desc) { }
+static inline void irq_compat_clr_affinity(struct irq_desc *desc) { }
 #endif
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index a80b44d2735e..6776453c454c 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -150,3 +150,7 @@ static inline void irqd_set(struct irq_data *d, unsigned int mask)
 	d->state_use_accessors |= mask;
 }
 
+static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
+{
+	return d->state_use_accessors & mask;
+}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 550ae97a0040..8246afc81956 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -164,7 +164,8 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 		kref_get(&desc->affinity_notify->kref);
 		schedule_work(&desc->affinity_notify->work);
 	}
-	desc->status |= IRQ_AFFINITY_SET;
+	irq_compat_set_affinity(desc);
+	irqd_set(&desc->irq_data, IRQD_AFFINITY_SET);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return ret;
 }
@@ -272,12 +273,14 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 	 * Preserve an userspace affinity setup, but make sure that
 	 * one of the targets is online.
 	 */
-	if (desc->status & (IRQ_AFFINITY_SET)) {
+	if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
 		if (cpumask_intersects(desc->irq_data.affinity,
 				       cpu_online_mask))
 			set = desc->irq_data.affinity;
-		else
-			desc->status &= ~IRQ_AFFINITY_SET;
+		else {
+			irq_compat_clr_affinity(desc);
+			irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
+		}
 	}
 
 	cpumask_and(mask, cpu_online_mask, set);
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index ba0fffe410ad..da5acb446b1c 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -29,6 +29,8 @@ enum {
 #define IRQ_PER_CPU		GOT_YOU_MORON
 #undef IRQ_NO_BALANCING
 #define IRQ_NO_BALANCING	GOT_YOU_MORON
+#undef IRQ_AFFINITY_SET
+#define IRQ_AFFINITY_SET	GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
-- 
cgit v1.2.3


From 876dbd4cc1b35c1a4cb96a2be1d43ea0eabce3b4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 17:28:12 +0100
Subject: genirq: Mirror irq trigger type bits in irq_data.state

That's the data structure chip functions get provided. Also allow them
to signal the core code that they updated the flags in irq_data.state
by returning IRQ_SET_MASK_OK_NOCOPY. The default is unchanged.

The type bits should be accessed via:

val = irqd_get_trigger_type(irqdata);
and
irqd_set_trigger_type(irqdata, val);

Coders who access them directly will be tracked down and slapped with
stinking trouts.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h   | 26 +++++++++++++++++++++++++-
 kernel/irq/chip.c     |  5 ++++-
 kernel/irq/manage.c   | 44 +++++++++++++++++++++++++++-----------------
 kernel/irq/resend.c   |  2 +-
 kernel/irq/settings.h | 30 ++++++++++++++++++++++++++++++
 5 files changed, 87 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8da1782ecfca..be73c0a3c19d 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -46,7 +46,9 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_TYPE_EDGE_BOTH (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)
 #define IRQ_TYPE_LEVEL_HIGH	0x00000004	/* Level high type */
 #define IRQ_TYPE_LEVEL_LOW	0x00000008	/* Level low type */
+#define IRQ_TYPE_LEVEL_MASK	(IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)
 #define IRQ_TYPE_SENSE_MASK	0x0000000f	/* Mask of the above */
+
 #define IRQ_TYPE_PROBE		0x00000010	/* Probing in progress */
 
 /* Internal flags */
@@ -131,17 +133,20 @@ struct irq_data {
 /*
  * Bit masks for irq_data.state
  *
+ * IRQD_TRIGGER_MASK		- Mask for the trigger type bits
  * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
  * IRQD_NO_BALANCING		- Balancing disabled for this IRQ
  * IRQD_PER_CPU			- Interrupt is per cpu
  * IRQD_AFFINITY_SET		- Interrupt affinity was set
+ * IRQD_LEVEL			- Interrupt is level triggered
  */
 enum {
-	/* Bit 0 - 7 reserved for TYPE will use later */
+	IRQD_TRIGGER_MASK		= 0xf,
 	IRQD_SETAFFINITY_PENDING	= (1 <<  8),
 	IRQD_NO_BALANCING		= (1 << 10),
 	IRQD_PER_CPU			= (1 << 11),
 	IRQD_AFFINITY_SET		= (1 << 12),
+	IRQD_LEVEL			= (1 << 13),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -164,6 +169,25 @@ static inline bool irqd_affinity_was_set(struct irq_data *d)
 	return d->state_use_accessors & IRQD_AFFINITY_SET;
 }
 
+static inline u32 irqd_get_trigger_type(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_TRIGGER_MASK;
+}
+
+/*
+ * Must only be called inside irq_chip.irq_set_type() functions.
+ */
+static inline void irqd_set_trigger_type(struct irq_data *d, u32 type)
+{
+	d->state_use_accessors &= ~IRQD_TRIGGER_MASK;
+	d->state_use_accessors |= type & IRQD_TRIGGER_MASK;
+}
+
+static inline bool irqd_is_level_type(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_LEVEL;
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b8aa3dfe8301..9c9b573a718e 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -710,11 +710,14 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 
 	irq_settings_clr_and_set(desc, clr, set);
 
-	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU);
+	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
+		   IRQD_TRIGGER_MASK | IRQD_LEVEL);
 	if (irq_settings_has_no_balance_set(desc))
 		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 	if (irq_settings_is_per_cpu(desc))
 		irqd_set(&desc->irq_data, IRQD_PER_CPU);
 
+	irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc));
+
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 8246afc81956..9ae758ed8e66 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -567,23 +567,32 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		return 0;
 	}
 
+	flags &= IRQ_TYPE_SENSE_MASK;
 	/* caller masked out all except trigger mode flags */
 	ret = chip->irq_set_type(&desc->irq_data, flags);
 
-	if (ret)
-		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
-		       flags, irq, chip->irq_set_type);
-	else {
-		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
-			flags |= IRQ_LEVEL;
-		/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
-		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
-		desc->status |= flags;
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
+		irqd_set(&desc->irq_data, flags);
+
+	case IRQ_SET_MASK_OK_NOCOPY:
+		flags = irqd_get_trigger_type(&desc->irq_data);
+		irq_settings_set_trigger_mask(desc, flags);
+		irqd_clear(&desc->irq_data, IRQD_LEVEL);
+		irq_settings_clr_level(desc);
+		if (flags & IRQ_TYPE_LEVEL_MASK) {
+			irq_settings_set_level(desc);
+			irqd_set(&desc->irq_data, IRQD_LEVEL);
+		}
 
 		if (chip != desc->irq_data.chip)
 			irq_chip_set_defaults(desc->irq_data.chip);
+		return 0;
+	default:
+		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		       flags, irq, chip->irq_set_type);
 	}
-
 	return ret;
 }
 
@@ -923,13 +932,14 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		/* Set default affinity mask once everything is setup */
 		setup_affinity(irq, desc, mask);
 
-	} else if ((new->flags & IRQF_TRIGGER_MASK)
-			&& (new->flags & IRQF_TRIGGER_MASK)
-				!= (desc->status & IRQ_TYPE_SENSE_MASK)) {
-		/* hope the handler works with the actual trigger mode... */
-		pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
-				irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
-				(int)(new->flags & IRQF_TRIGGER_MASK));
+	} else if (new->flags & IRQF_TRIGGER_MASK) {
+		unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
+		unsigned int omsk = irq_settings_get_trigger_mask(desc);
+
+		if (nmsk != omsk)
+			/* hope the handler works with current  trigger mode */
+			pr_warning("IRQ %d uses trigger mode %u; requested %u\n",
+				   irq, nmsk, omsk);
 	}
 
 	new->irq = irq;
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index ff1fea060014..ad683a99b1ec 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -60,7 +60,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	 * interrupts are resent by hardware when they are still
 	 * active.
 	 */
-	if (desc->status & IRQ_LEVEL)
+	if (irq_settings_is_level(desc))
 		return;
 	if (desc->istate & IRQS_REPLAY)
 		return;
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index da5acb446b1c..2201f2aaa9a0 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -5,6 +5,7 @@
 enum {
 	_IRQ_DEFAULT_INIT_FLAGS	= IRQ_DEFAULT_INIT_FLAGS,
 	_IRQ_PER_CPU		= IRQ_PER_CPU,
+	_IRQ_LEVEL		= IRQ_LEVEL,
 	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
@@ -31,6 +32,8 @@ enum {
 #define IRQ_NO_BALANCING	GOT_YOU_MORON
 #undef IRQ_AFFINITY_SET
 #define IRQ_AFFINITY_SET	GOT_YOU_MORON
+#undef IRQ_LEVEL
+#define IRQ_LEVEL		GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -60,3 +63,30 @@ static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc)
 {
 	return desc->status & _IRQ_NO_BALANCING;
 }
+
+static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc)
+{
+	return desc->status & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline void
+irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask)
+{
+	desc->status &= ~IRQ_TYPE_SENSE_MASK;
+	desc->status |= mask & IRQ_TYPE_SENSE_MASK;
+}
+
+static inline bool irq_settings_is_level(struct irq_desc *desc)
+{
+	return desc->status & _IRQ_LEVEL;
+}
+
+static inline void irq_settings_clr_level(struct irq_desc *desc)
+{
+	desc->status &= ~_IRQ_LEVEL;
+}
+
+static inline void irq_settings_set_level(struct irq_desc *desc)
+{
+	desc->status |= _IRQ_LEVEL;
+}
-- 
cgit v1.2.3


From 5d4d8fc9ac3e9a90bbdf90bae6864cb2c01f2208 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 8 Feb 2011 17:27:18 +0100
Subject: genirq: Cleanup irq.h

Put the constants into an enum and document them.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h   | 95 +++++++++++++++++++++++++++++++++------------------
 kernel/irq/settings.h | 16 ---------
 2 files changed, 62 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index be73c0a3c19d..2e3d1e5f0408 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -36,44 +36,73 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 /*
  * IRQ line status.
  *
- * Bits 0-7 are reserved for the IRQF_* bits in linux/interrupt.h
+ * Bits 0-7 are the same as the IRQF_* bits in linux/interrupt.h
+ *
+ * IRQ_TYPE_NONE		- default, unspecified type
+ * IRQ_TYPE_EDGE_RISING		- rising edge triggered
+ * IRQ_TYPE_EDGE_FALLING	- falling edge triggered
+ * IRQ_TYPE_EDGE_BOTH		- rising and falling edge triggered
+ * IRQ_TYPE_LEVEL_HIGH		- high level triggered
+ * IRQ_TYPE_LEVEL_LOW		- low level triggered
+ * IRQ_TYPE_LEVEL_MASK		- Mask to filter out the level bits
+ * IRQ_TYPE_SENSE_MASK		- Mask for all the above bits
+ * IRQ_TYPE_PROBE		- Special flag for probing in progress
+ *
+ * Bits which can be modified via irq_set/clear/modify_status_flags()
+ * IRQ_LEVEL			- Interrupt is level type. Will be also
+ *				  updated in the code when the above trigger
+ *				  bits are modified via set_irq_type()
+ * IRQ_PER_CPU			- Mark an interrupt PER_CPU. Will protect
+ *				  it from affinity setting
+ * IRQ_NOPROBE			- Interrupt cannot be probed by autoprobing
+ * IRQ_NOREQUEST		- Interrupt cannot be requested via
+ *				  request_irq()
+ * IRQ_NOAUTOEN			- Interrupt is not automatically enabled in
+ *				  request/setup_irq()
+ * IRQ_NO_BALANCING		- Interrupt cannot be balanced (affinity set)
+ * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
+ * IRQ_NESTED_TRHEAD		- Interrupt nests into another thread
+ *
+ * Deprecated bits. They are kept updated as long as
+ * CONFIG_GENERIC_HARDIRQS_NO_COMPAT is not set. Will go away soon. These bits
+ * are internal state of the core code and if you really need to acces
+ * them then talk to the genirq maintainer instead of hacking
+ * something weird.
  *
- * IRQ types
  */
-#define IRQ_TYPE_NONE		0x00000000	/* Default, unspecified type */
-#define IRQ_TYPE_EDGE_RISING	0x00000001	/* Edge rising type */
-#define IRQ_TYPE_EDGE_FALLING	0x00000002	/* Edge falling type */
-#define IRQ_TYPE_EDGE_BOTH (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)
-#define IRQ_TYPE_LEVEL_HIGH	0x00000004	/* Level high type */
-#define IRQ_TYPE_LEVEL_LOW	0x00000008	/* Level low type */
-#define IRQ_TYPE_LEVEL_MASK	(IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)
-#define IRQ_TYPE_SENSE_MASK	0x0000000f	/* Mask of the above */
-
-#define IRQ_TYPE_PROBE		0x00000010	/* Probing in progress */
-
-/* Internal flags */
+enum {
+	IRQ_TYPE_NONE		= 0x00000000,
+	IRQ_TYPE_EDGE_RISING	= 0x00000001,
+	IRQ_TYPE_EDGE_FALLING	= 0x00000002,
+	IRQ_TYPE_EDGE_BOTH	= (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING),
+	IRQ_TYPE_LEVEL_HIGH	= 0x00000004,
+	IRQ_TYPE_LEVEL_LOW	= 0x00000008,
+	IRQ_TYPE_LEVEL_MASK	= (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH),
+	IRQ_TYPE_SENSE_MASK	= 0x0000000f,
+
+	IRQ_TYPE_PROBE		= 0x00000010,
+
+	IRQ_LEVEL		= (1 <<  8),
+	IRQ_PER_CPU		= (1 <<  9),
+	IRQ_NOPROBE		= (1 << 10),
+	IRQ_NOREQUEST		= (1 << 11),
+	IRQ_NOAUTOEN		= (1 << 12),
+	IRQ_NO_BALANCING	= (1 << 13),
+	IRQ_MOVE_PCNTXT		= (1 << 14),
+	IRQ_NESTED_THREAD	= (1 << 15),
 
 #ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
-#define IRQ_INPROGRESS		0x00000100	/* DEPRECATED */
-#define IRQ_REPLAY		0x00000200	/* DEPRECATED */
-#define IRQ_WAITING		0x00000400	/* DEPRECATED */
-#define IRQ_DISABLED		0x00000800	/* DEPRECATED */
-#define IRQ_PENDING		0x00001000	/* DEPRECATED */
-#define IRQ_MASKED		0x00002000	/* DEPRECATED */
-/* DEPRECATED use irq_setaffinity_pending() instead*/
-#define IRQ_MOVE_PENDING	0x00004000
-#define IRQ_AFFINITY_SET	0x02000000	/* DEPRECATED */
+	IRQ_INPROGRESS		= (1 << 16),
+	IRQ_REPLAY		= (1 << 17),
+	IRQ_WAITING		= (1 << 18),
+	IRQ_DISABLED		= (1 << 19),
+	IRQ_PENDING		= (1 << 20),
+	IRQ_MASKED		= (1 << 21),
+	IRQ_MOVE_PENDING	= (1 << 22),
+	IRQ_AFFINITY_SET	= (1 << 23),
+	IRQ_WAKEUP		= (1 << 24),
 #endif
-
-#define IRQ_LEVEL		0x00008000	/* IRQ level triggered */
-#define IRQ_PER_CPU		0x00010000	/* IRQ is per CPU */
-#define IRQ_NOPROBE		0x00020000	/* IRQ is not valid for probing */
-#define IRQ_NOREQUEST		0x00040000	/* IRQ cannot be requested */
-#define IRQ_NOAUTOEN		0x00080000	/* IRQ will not be enabled on request irq */
-#define IRQ_WAKEUP		0x00100000	/* IRQ triggers system wakeup */
-#define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
-#define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
-#define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
+};
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 47bcd3b9f399..55ebe1e09da4 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -15,37 +15,21 @@ enum {
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
-#undef IRQ_INPROGRESS
 #define IRQ_INPROGRESS		GOT_YOU_MORON
-#undef IRQ_REPLAY
 #define IRQ_REPLAY		GOT_YOU_MORON
-#undef IRQ_WAITING
 #define IRQ_WAITING		GOT_YOU_MORON
-#undef IRQ_DISABLED
 #define IRQ_DISABLED		GOT_YOU_MORON
-#undef IRQ_PENDING
 #define IRQ_PENDING		GOT_YOU_MORON
-#undef IRQ_MASKED
 #define IRQ_MASKED		GOT_YOU_MORON
-#undef IRQ_WAKEUP
 #define IRQ_WAKEUP		GOT_YOU_MORON
-#undef IRQ_MOVE_PENDING
 #define IRQ_MOVE_PENDING	GOT_YOU_MORON
-#undef IRQ_PER_CPU
 #define IRQ_PER_CPU		GOT_YOU_MORON
-#undef IRQ_NO_BALANCING
 #define IRQ_NO_BALANCING	GOT_YOU_MORON
-#undef IRQ_AFFINITY_SET
 #define IRQ_AFFINITY_SET	GOT_YOU_MORON
-#undef IRQ_LEVEL
 #define IRQ_LEVEL		GOT_YOU_MORON
-#undef IRQ_NOPROBE
 #define IRQ_NOPROBE		GOT_YOU_MORON
-#undef IRQ_NOREQUEST
 #define IRQ_NOREQUEST		GOT_YOU_MORON
-#undef IRQ_NOAUTOEN
 #define IRQ_NOAUTOEN		GOT_YOU_MORON
-#undef IRQ_NESTED_THREAD
 #define IRQ_NESTED_THREAD	GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
-- 
cgit v1.2.3


From 2bff17ad2107c66fc8ca96501a7128dd7fa7a390 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 13:08:38 +0100
Subject: genirq: Add flags to irq_chip

Looking through irq_chip implementations I noticed that some of them
have special requirements, like setting the type masked and therefor
fiddle in irq_desc->status. Add a flag field, so the core code can
handle it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 2e3d1e5f0408..aefb30bbcf0e 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -253,6 +253,7 @@ static inline bool irqd_is_level_type(struct irq_data *d)
  * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
  * @irq_bus_lock:	function to lock access to slow bus (i2c) chips
  * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
+ * @flags:		chip specific flags
  *
  * @release:		release function solely used by UML
  */
@@ -299,6 +300,8 @@ struct irq_chip {
 	void		(*irq_bus_lock)(struct irq_data *data);
 	void		(*irq_bus_sync_unlock)(struct irq_data *data);
 
+	unsigned long	flags;
+
 	/* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
 	void		(*release)(unsigned int irq, void *dev_id);
-- 
cgit v1.2.3


From d4d5e08960844a062da8387ee5f16ca7a33200d0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 13:16:14 +0100
Subject: genirq: Add IRQCHIP_SET_TYPE_MASKED flag

irq_chips, which require to mask the chip before changing the trigger
type should set this flag. So the core takes care of it and the
requirement for looking into desc->status in the chip goes away.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Walleij <linus.walleij@stericsson.com>
Cc: Lars-Peter Clausen <lars@metafoo.de>
---
 include/linux/irq.h    |  9 +++++++++
 kernel/irq/chip.c      |  4 ++--
 kernel/irq/internals.h |  2 ++
 kernel/irq/manage.c    | 16 +++++++++++++---
 4 files changed, 26 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index aefb30bbcf0e..ef6b66dc9d03 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -308,6 +308,15 @@ struct irq_chip {
 #endif
 };
 
+/*
+ * irq_chip specific flags
+ *
+ * IRQCHIP_SET_TYPE_MASKED:		Mask before calling chip.irq_set_type()
+ */
+enum {
+	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
+};
+
 /* This include will go away once we isolated irq_desc usage to core code */
 #include <linux/irqdesc.h>
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 9e9220da4deb..4687457fe7f0 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -367,7 +367,7 @@ static inline void mask_ack_irq(struct irq_desc *desc)
 	irq_state_set_masked(desc);
 }
 
-static inline void mask_irq(struct irq_desc *desc)
+void mask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_mask) {
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
@@ -375,7 +375,7 @@ static inline void mask_irq(struct irq_desc *desc)
 	}
 }
 
-static inline void unmask_irq(struct irq_desc *desc)
+void unmask_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_unmask) {
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 6776453c454c..1d500fbde0d4 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -84,6 +84,8 @@ extern int irq_startup(struct irq_desc *desc);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
+extern void mask_irq(struct irq_desc *desc);
+extern void unmask_irq(struct irq_desc *desc);
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index b5de828e58d9..50809c79c7ad 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -554,8 +554,8 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		      unsigned long flags)
 {
-	int ret;
 	struct irq_chip *chip = desc->irq_data.chip;
+	int ret, unmask = 0;
 
 	if (!chip || !chip->irq_set_type) {
 		/*
@@ -568,6 +568,14 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	}
 
 	flags &= IRQ_TYPE_SENSE_MASK;
+
+	if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
+		if (!(desc->istate & IRQS_MASKED))
+			mask_irq(desc);
+		if (!(desc->istate & IRQS_DISABLED))
+			unmask = 1;
+	}
+
 	/* caller masked out all except trigger mode flags */
 	ret = chip->irq_set_type(&desc->irq_data, flags);
 
@@ -588,11 +596,13 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 
 		if (chip != desc->irq_data.chip)
 			irq_chip_set_defaults(desc->irq_data.chip);
-		return 0;
+		ret = 0;
 	default:
 		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
 		       flags, irq, chip->irq_set_type);
 	}
+	if (unmask)
+		unmask_irq(desc);
 	return ret;
 }
 
@@ -669,7 +679,7 @@ again:
 
 #ifdef CONFIG_SMP
 /*
- * Check whether we need to change the affinity of the interrupt thread.
+ * Check whether we need to chasnge the affinity of the interrupt thread.
  */
 static void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
-- 
cgit v1.2.3


From 7f94226f03299f1ca32f118f02f2a0295e0e5e93 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 19:46:26 +0100
Subject: genirq: Move wakeup state to irq_data

Some irq_chips need to know the state of wakeup mode for
setting the trigger type etc. Reflect it in irq_data state.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    | 8 ++++++++
 kernel/irq/internals.h | 2 --
 kernel/irq/manage.c    | 4 ++--
 kernel/irq/pm.c        | 2 +-
 4 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index ef6b66dc9d03..94c8f5bb548f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -168,6 +168,8 @@ struct irq_data {
  * IRQD_PER_CPU			- Interrupt is per cpu
  * IRQD_AFFINITY_SET		- Interrupt affinity was set
  * IRQD_LEVEL			- Interrupt is level triggered
+ * IRQD_WAKEUP_STATE		- Interrupt is configured for wakeup
+ *				  from suspend
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -176,6 +178,7 @@ enum {
 	IRQD_PER_CPU			= (1 << 11),
 	IRQD_AFFINITY_SET		= (1 << 12),
 	IRQD_LEVEL			= (1 << 13),
+	IRQD_WAKEUP_STATE		= (1 << 14),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -217,6 +220,11 @@ static inline bool irqd_is_level_type(struct irq_data *d)
 	return d->state_use_accessors & IRQD_LEVEL;
 }
 
+static inline bool irqd_is_wakeup_set(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_WAKEUP_STATE;
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 1d500fbde0d4..5e2366da9f38 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -46,7 +46,6 @@ enum {
  * IRQS_PENDING			- irq is pending and replayed later
  * IRQS_MASKED			- irq is masked
  * IRQS_SUSPENDED		- irq is suspended
- * IRQS_WAKEUP			- irq triggers system wakeup from suspend
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -60,7 +59,6 @@ enum {
 	IRQS_PENDING		= 0x00000200,
 	IRQS_MASKED		= 0x00000400,
 	IRQS_SUSPENDED		= 0x00000800,
-	IRQS_WAKEUP		= 0x00001000,
 };
 
 #include "compat.h"
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 50809c79c7ad..ea6add6036b1 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -492,7 +492,7 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
 			if (ret)
 				desc->wake_depth = 0;
 			else
-				desc->istate |= IRQS_WAKEUP;
+				irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
 		}
 	} else {
 		if (desc->wake_depth == 0) {
@@ -502,7 +502,7 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
 			if (ret)
 				desc->wake_depth = 1;
 			else
-				desc->istate &= ~IRQS_WAKEUP;
+				irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
 		}
 	}
 
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index f39383d8672d..1329f0eff49e 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -69,7 +69,7 @@ int check_wakeup_irqs(void)
 	int irq;
 
 	for_each_irq_desc(irq, desc)
-		if ((desc->istate & IRQS_WAKEUP) &&
+		if (irqd_is_wakeup_set(&desc->irq_data) &&
 		    (desc->istate & IRQS_PENDING))
 			return -EBUSY;
 
-- 
cgit v1.2.3


From e1ef824146131709d7466e37f889f2dab24ca98e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 22:25:31 +0100
Subject: genirq: Reflect IRQ_MOVE_PCNTXT in irq_data state

Required by x86.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 8 ++++++++
 kernel/irq/chip.c   | 4 +++-
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 94c8f5bb548f..c101ad4b821f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -170,6 +170,8 @@ struct irq_data {
  * IRQD_LEVEL			- Interrupt is level triggered
  * IRQD_WAKEUP_STATE		- Interrupt is configured for wakeup
  *				  from suspend
+ * IRDQ_MOVE_PCNTXT		- Interrupt can be moved in process
+ *				  context
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -179,6 +181,7 @@ enum {
 	IRQD_AFFINITY_SET		= (1 << 12),
 	IRQD_LEVEL			= (1 << 13),
 	IRQD_WAKEUP_STATE		= (1 << 14),
+	IRQD_MOVE_PCNTXT		= (1 << 15),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -225,6 +228,11 @@ static inline bool irqd_is_wakeup_set(struct irq_data *d)
 	return d->state_use_accessors & IRQD_WAKEUP_STATE;
 }
 
+static inline bool irqd_can_move_in_process_context(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_MOVE_PCNTXT;
+}
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 4687457fe7f0..2b0f9192a830 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -712,11 +712,13 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 	irq_settings_clr_and_set(desc, clr, set);
 
 	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
-		   IRQD_TRIGGER_MASK | IRQD_LEVEL);
+		   IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
 	if (irq_settings_has_no_balance_set(desc))
 		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 	if (irq_settings_is_per_cpu(desc))
 		irqd_set(&desc->irq_data, IRQD_PER_CPU);
+	if (irq_settings_can_move_pcntxt(desc))
+		irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
 
 	irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc));
 
-- 
cgit v1.2.3


From a6967caf00ebbb2d4acdebcb72a25f2e9ba43fd2 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 22:01:25 +0100
Subject: genirq: Remove desc->status when GENERIC_HARDIRQS_NO_COMPAT=y

If everything uses the right accessors, then enabling
GENERIC_HARDIRQS_NO_COMPAT should just work. If not it will tell you.

Don't be lazy and use the trick which I use in the core code!

git grep status_use_accessors

will unearth it in a split second. Offenders are tracked down and not
slapped with stinking trouts. This time we use frozen shark for a
better educational value.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqdesc.h | 6 ++++++
 kernel/irq/internals.h  | 4 ++++
 kernel/irq/settings.h   | 1 +
 3 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 581d9665fd38..36c95f08023d 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -64,7 +64,11 @@ struct irq_desc {
 	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
 	struct irqaction	*action;	/* IRQ action list */
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+	unsigned int		status_use_accessors;
+#else
 	unsigned int		status;		/* IRQ status */
+#endif
 	unsigned int		core_internal_state__do_not_mess_with_it;
 	unsigned int		depth;		/* nested irq disables */
 	unsigned int		wake_depth;	/* nested wake enables */
@@ -164,6 +168,7 @@ static inline int irq_has_action(unsigned int irq)
 	return desc->action != NULL;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
 static inline int irq_balancing_disabled(unsigned int irq)
 {
 	struct irq_desc *desc;
@@ -171,6 +176,7 @@ static inline int irq_balancing_disabled(unsigned int irq)
 	desc = irq_to_desc(irq);
 	return desc->status & IRQ_NO_BALANCING_MASK;
 }
+#endif
 
 /* caller has locked the irq_desc and both params are valid */
 static inline void __set_irq_handler_unlocked(int irq,
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 5e2366da9f38..fd5777ab2d34 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -15,6 +15,10 @@
 
 #define istate core_internal_state__do_not_mess_with_it
 
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+# define status status_use_accessors
+#endif
+
 extern int noirqdebug;
 
 /*
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 55ebe1e09da4..0227ad358272 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -134,4 +134,5 @@ static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
 }
 
 /* Nothing should touch desc->status from now on */
+#undef status
 #define status		USE_THE_PROPER_WRAPPERS_YOU_MORON
-- 
cgit v1.2.3


From 3836ca08aad4575c120ccf328652f3873eea9063 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 14 Feb 2011 20:09:19 +0100
Subject: genirq: Consolidate set_chip_handler functions

No need to have separate functions if we have one plus inline wrappers.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 51 +++++++++++++++++++++++++++++++++++++++------------
 kernel/irq/chip.c   | 16 ++++------------
 2 files changed, 43 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index c101ad4b821f..3e29e2f42e04 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -398,23 +398,23 @@ extern struct irq_chip no_irq_chip;
 extern struct irq_chip dummy_irq_chip;
 
 extern void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
-			 irq_flow_handler_t handle);
-extern void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 			      irq_flow_handler_t handle, const char *name);
 
+static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+					    irq_flow_handler_t handle)
+{
+	irq_set_chip_and_handler_name(irq, chip, handle, NULL);
+}
+
 extern void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name);
 
-/*
- * Set a highlevel flow handler for a given IRQ:
- */
 static inline void
-set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+irq_set_handler(unsigned int irq, irq_flow_handler_t handle)
 {
-	__set_irq_handler(irq, handle, 0, NULL);
+	__irq_set_handler(irq, handle, 0, NULL);
 }
 
 /*
@@ -423,9 +423,9 @@ set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
  *  IRQ_NOREQUEST and IRQ_NOPROBE)
  */
 static inline void
-set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
+irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle)
 {
-	__set_irq_handler(irq, handle, 1, NULL);
+	__irq_set_handler(irq, handle, 1, NULL);
 }
 
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
@@ -579,6 +579,33 @@ static inline void set_irq_nested_thread(unsigned int irq, int nest)
 {
 	irq_set_nested_thread(irq, nest);
 }
+static inline void
+set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+			      irq_flow_handler_t handle, const char *name)
+{
+	irq_set_chip_and_handler_name(irq, chip, handle, name);
+}
+static inline void
+set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+			 irq_flow_handler_t handle)
+{
+	irq_set_chip_and_handler(irq, chip, handle);
+}
+static inline void
+__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+		  const char *name)
+{
+	__irq_set_handler(irq, handle, is_chained, name);
+}
+static inline void set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+	irq_set_handler(irq, handle);
+}
+static inline void
+set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+	irq_set_chained_handler(irq, handle);
+}
 #endif
 
 int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3ea6aecd99c0..2a36038b8f59 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -600,7 +600,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 }
 
 void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name)
 {
 	unsigned long flags;
@@ -635,22 +635,14 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 out:
 	irq_put_desc_busunlock(desc, flags);
 }
-EXPORT_SYMBOL_GPL(__set_irq_handler);
+EXPORT_SYMBOL_GPL(__irq_set_handler);
 
 void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
-			 irq_flow_handler_t handle)
-{
-	irq_set_chip(irq, chip);
-	__set_irq_handler(irq, handle, 0, NULL);
-}
-
-void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 			      irq_flow_handler_t handle, const char *name)
 {
 	irq_set_chip(irq, chip);
-	__set_irq_handler(irq, handle, 0, name);
+	__irq_set_handler(irq, handle, 0, name);
 }
 
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
-- 
cgit v1.2.3


From 781295762defc709a609efc01d8bb065276cd9a2 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Feb 2011 15:14:20 +0100
Subject: genirq: Add preflow handler support

sparc64 needs to call a preflow handler on certain interrupts befor
calling the action chain. Integrate it into handle_fasteoi_irq. Must
be enabled via CONFIG_IRQ_FASTEOI_PREFLOW. No impact when disabled.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: David S. Miller <davem@davemloft.net>
---
 include/linux/irq.h     |  3 ++-
 include/linux/irqdesc.h | 14 ++++++++++++++
 kernel/irq/Kconfig      |  3 +++
 kernel/irq/chip.c       | 11 +++++++++++
 4 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3e29e2f42e04..36390970693c 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -29,9 +29,10 @@
 #include <asm/irq_regs.h>
 
 struct irq_desc;
+struct irq_data;
 typedef	void (*irq_flow_handler_t)(unsigned int irq,
 					    struct irq_desc *desc);
-
+typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
 
 /*
  * IRQ line status.
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 36c95f08023d..2f87d6441302 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -63,6 +63,9 @@ struct irq_desc {
 	struct timer_rand_state *timer_rand_state;
 	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+	irq_preflow_handler_t	preflow_handler;
+#endif
 	struct irqaction	*action;	/* IRQ action list */
 #ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
 	unsigned int		status_use_accessors;
@@ -187,6 +190,17 @@ static inline void __set_irq_handler_unlocked(int irq,
 	desc = irq_to_desc(irq);
 	desc->handle_irq = handler;
 }
+
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void
+__irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->preflow_handler = handler;
+}
+#endif
 #endif
 
 #endif
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 48ad25f5fa59..9149be729e45 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -35,6 +35,9 @@ config AUTO_IRQ_AFFINITY
 config HARDIRQS_SW_RESEND
        def_bool n
 
+config IRQ_PREFLOW_FASTEOI
+       def_bool n
+
 config SPARSE_IRQ
 	bool "Support sparse irq numbering"
 	depends on HAVE_SPARSE_IRQ
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 2a36038b8f59..08be5d182be3 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -471,6 +471,16 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_level_irq);
 
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void preflow_handler(struct irq_desc *desc)
+{
+	if (desc->preflow_handler)
+		desc->preflow_handler(&desc->irq_data);
+}
+#else
+static inline void preflow_handler(struct irq_desc *desc) { }
+#endif
+
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
  *	@irq:	the interrupt number
@@ -503,6 +513,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		mask_irq(desc);
 		goto out;
 	}
+	preflow_handler(desc);
 	handle_irq_event(desc);
 out:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
-- 
cgit v1.2.3


From 77694b408abb8f92195ad5ed6ce5492f1d794c77 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 15 Feb 2011 10:33:57 +0100
Subject: genirq; Add fasteoi irq_chip quirk

Some chips want irq_eoi() only called when an interrupt is actually
handled. So they have checks for INPROGRESS and DISABLED in their
irq_eoi callbacks. Add a chip flag, which allows to handle that in the
generic code. No impact on the fastpath.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 4 +++-
 kernel/irq/chip.c   | 9 ++++++++-
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 36390970693c..ea2970c294aa 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -328,10 +328,12 @@ struct irq_chip {
 /*
  * irq_chip specific flags
  *
- * IRQCHIP_SET_TYPE_MASKED:		Mask before calling chip.irq_set_type()
+ * IRQCHIP_SET_TYPE_MASKED:	Mask before calling chip.irq_set_type()
+ * IRQCHIP_EOI_IF_HANDLED:	Only issue irq_eoi() when irq was handled
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
+	IRQCHIP_EOI_IF_HANDLED		= (1 <<  1),
 };
 
 /* This include will go away once we isolated irq_desc usage to core code */
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 08be5d182be3..1d3e25e68b0c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -515,9 +515,16 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	}
 	preflow_handler(desc);
 	handle_irq_event(desc);
-out:
+
+out_eoi:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
+out_unlock:
 	raw_spin_unlock(&desc->lock);
+	return;
+out:
+	if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
+		goto out_eoi;
+	goto out_unlock;
 }
 
 /**
-- 
cgit v1.2.3


From a439520f8b18917b322f576be04c54aba84bb044 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 4 Feb 2011 18:46:16 +0100
Subject: genirq: Implement irq_data based move_*_irq() versions

No need to lookup the irq descriptor when calling from a chip callback
function which has irq_data already handy.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h    |  4 ++++
 kernel/irq/migration.c | 28 +++++++++++++++++++---------
 2 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index ea2970c294aa..ff62d0145b8f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -363,9 +363,13 @@ extern void remove_irq(unsigned int irq, struct irqaction *act);
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
+void irq_move_irq(struct irq_data *data);
+void irq_move_masked_irq(struct irq_data *data);
 #else
 static inline void move_native_irq(int irq) { }
 static inline void move_masked_irq(int irq) { }
+static inline void irq_move_irq(struct irq_data *data) { }
+static inline void irq_move_masked_irq(struct irq_data *data) { }
 #endif
 
 extern int no_irq_affinity;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 7a93c6b88b25..ec4806d4778b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -4,10 +4,10 @@
 
 #include "internals.h"
 
-void move_masked_irq(int irq)
+void irq_move_masked_irq(struct irq_data *idata)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_chip *chip = desc->irq_data.chip;
+	struct irq_desc *desc = irq_data_to_desc(idata);
+	struct irq_chip *chip = idata->chip;
 
 	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
 		return;
@@ -53,12 +53,17 @@ void move_masked_irq(int irq)
 	cpumask_clear(desc->pending_mask);
 }
 
-void move_native_irq(int irq)
+void move_masked_irq(int irq)
+{
+	irq_move_masked_irq(irq_get_irq_data(irq));
+}
+
+void irq_move_irq(struct irq_data *idata)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(idata);
 	bool masked;
 
-	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+	if (likely(!irqd_is_setaffinity_pending(idata)))
 		return;
 
 	if (unlikely(desc->istate & IRQS_DISABLED))
@@ -71,8 +76,13 @@ void move_native_irq(int irq)
 	 */
 	masked = desc->istate & IRQS_MASKED;
 	if (!masked)
-		desc->irq_data.chip->irq_mask(&desc->irq_data);
-	move_masked_irq(irq);
+		idata->chip->irq_mask(idata);
+	irq_move_masked_irq(idata);
 	if (!masked)
-		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+		idata->chip->irq_unmask(idata);
+}
+
+void move_native_irq(int irq)
+{
+	irq_move_irq(irq_get_irq_data(irq));
 }
-- 
cgit v1.2.3


From 226111d1fbe611bc7a5ffaa5275ccb41e73fd011 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.r.fastabend@intel.com>
Date: Fri, 18 Feb 2011 13:30:17 +0000
Subject: net: dcb: match dcb_app protocol field with 802.1Qaz spec

The dcb_app protocol field is a __u32 however the 802.1Qaz
specification defines it as a 16 bit field. This patch brings
the structure inline with the spec making it a __u16.

CC: Shmulik Ravid <shmulikr@broadcom.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dcbnl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 68cd248f6d3e..66900e3c6eb1 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -101,8 +101,8 @@ struct ieee_pfc {
  */
 struct dcb_app {
 	__u8	selector;
-	__u32	protocol;
 	__u8	priority;
+	__u16	protocol;
 };
 
 struct dcbmsg {
-- 
cgit v1.2.3


From 33619f0d3ff715a2a5499520967d526ad931d70d Mon Sep 17 00:00:00 2001
From: Dominik Brodowski <linux@dominikbrodowski.net>
Date: Sat, 19 Feb 2011 12:35:15 +0100
Subject: pcmcia: re-enable Zoomed Video support

Allow drivers to enable Zoomed Video support. Currently, this is only
used by out-of-tree drivers (L64020 DVB driver in particular).

CC: <stable@kernel.org> [for 2.6.37]
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/pcmcia_resource.c | 2 ++
 include/pcmcia/ds.h              | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c
index 0bdda5b3ed55..42fbf1a75576 100644
--- a/drivers/pcmcia/pcmcia_resource.c
+++ b/drivers/pcmcia/pcmcia_resource.c
@@ -518,6 +518,8 @@ int pcmcia_enable_device(struct pcmcia_device *p_dev)
 		flags |= CONF_ENABLE_IOCARD;
 	if (flags & CONF_ENABLE_IOCARD)
 		s->socket.flags |= SS_IOCARD;
+	if (flags & CONF_ENABLE_ZVCARD)
+		s->socket.flags |= SS_ZVCARD | SS_IOCARD;
 	if (flags & CONF_ENABLE_SPKR) {
 		s->socket.flags |= SS_SPKR_ENA;
 		status = CCSR_AUDIO_ENA;
diff --git a/include/pcmcia/ds.h b/include/pcmcia/ds.h
index 8479b66c067b..3fd5064dd43a 100644
--- a/include/pcmcia/ds.h
+++ b/include/pcmcia/ds.h
@@ -261,6 +261,7 @@ void pcmcia_disable_device(struct pcmcia_device *p_dev);
 #define CONF_ENABLE_ESR         0x0008
 #define CONF_ENABLE_IOCARD	0x0010 /* auto-enabled if IO resources or IRQ
 					* (CONF_ENABLE_IRQ) in use */
+#define CONF_ENABLE_ZVCARD	0x0020
 
 /* flags used by pcmcia_loop_config() autoconfiguration */
 #define CONF_AUTO_CHECK_VCC	0x0100 /* check for matching Vcc? */
-- 
cgit v1.2.3


From 089c34827e52346f0303d1e6a7b744c1f4da3095 Mon Sep 17 00:00:00 2001
From: Shan Wei <shanwei@cn.fujitsu.com>
Date: Sat, 19 Feb 2011 21:55:45 +0000
Subject: tcp: Remove debug macro of TCP_CHECK_TIMER

Now, TCP_CHECK_TIMER is not used for debuging, it does nothing.
And, it has been there for several years, maybe 6 years.

Remove it to keep code clearer.

Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    | 2 --
 net/ipv4/tcp.c       | 9 ---------
 net/ipv4/tcp_ipv4.c  | 5 -----
 net/ipv4/tcp_timer.c | 3 ---
 net/ipv6/tcp_ipv6.c  | 4 ----
 5 files changed, 23 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index adfe6dbe9053..cda30ea354a2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1068,8 +1068,6 @@ static inline int tcp_paws_reject(const struct tcp_options_received *rx_opt,
 	return 1;
 }
 
-#define TCP_CHECK_TIMER(sk) do { } while (0)
-
 static inline void tcp_mib_init(struct net *net)
 {
 	/* See RFC 2012 */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f9867d2dbef4..a17a5a72b98d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -873,9 +873,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 					flags);
 
 	lock_sock(sk);
-	TCP_CHECK_TIMER(sk);
 	res = do_tcp_sendpages(sk, &page, offset, size, flags);
-	TCP_CHECK_TIMER(sk);
 	release_sock(sk);
 	return res;
 }
@@ -916,7 +914,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	long timeo;
 
 	lock_sock(sk);
-	TCP_CHECK_TIMER(sk);
 
 	flags = msg->msg_flags;
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
@@ -1104,7 +1101,6 @@ wait_for_memory:
 out:
 	if (copied)
 		tcp_push(sk, flags, mss_now, tp->nonagle);
-	TCP_CHECK_TIMER(sk);
 	release_sock(sk);
 	return copied;
 
@@ -1123,7 +1119,6 @@ do_error:
 		goto out;
 out_err:
 	err = sk_stream_error(sk, flags, err);
-	TCP_CHECK_TIMER(sk);
 	release_sock(sk);
 	return err;
 }
@@ -1415,8 +1410,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	lock_sock(sk);
 
-	TCP_CHECK_TIMER(sk);
-
 	err = -ENOTCONN;
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
@@ -1767,12 +1760,10 @@ skip_copy:
 	/* Clean up data we have read: This will do ACK frames. */
 	tcp_cleanup_rbuf(sk, copied);
 
-	TCP_CHECK_TIMER(sk);
 	release_sock(sk);
 	return copied;
 
 out:
-	TCP_CHECK_TIMER(sk);
 	release_sock(sk);
 	return err;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e2b9be27f226..ef5a90beb9b0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1556,12 +1556,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
 		sock_rps_save_rxhash(sk, skb->rxhash);
-		TCP_CHECK_TIMER(sk);
 		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
 			rsk = sk;
 			goto reset;
 		}
-		TCP_CHECK_TIMER(sk);
 		return 0;
 	}
 
@@ -1583,13 +1581,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 	} else
 		sock_rps_save_rxhash(sk, skb->rxhash);
 
-
-	TCP_CHECK_TIMER(sk);
 	if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) {
 		rsk = sk;
 		goto reset;
 	}
-	TCP_CHECK_TIMER(sk);
 	return 0;
 
 reset:
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 74a6aa003657..ecd44b0c45f1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -259,7 +259,6 @@ static void tcp_delack_timer(unsigned long data)
 		tcp_send_ack(sk);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKS);
 	}
-	TCP_CHECK_TIMER(sk);
 
 out:
 	if (tcp_memory_pressure)
@@ -481,7 +480,6 @@ static void tcp_write_timer(unsigned long data)
 		tcp_probe_timer(sk);
 		break;
 	}
-	TCP_CHECK_TIMER(sk);
 
 out:
 	sk_mem_reclaim(sk);
@@ -589,7 +587,6 @@ static void tcp_keepalive_timer (unsigned long data)
 		elapsed = keepalive_time_when(tp) - elapsed;
 	}
 
-	TCP_CHECK_TIMER(sk);
 	sk_mem_reclaim(sk);
 
 resched:
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d6954e318324..1d0ab5570904 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1636,10 +1636,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		opt_skb = skb_clone(skb, GFP_ATOMIC);
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
-		TCP_CHECK_TIMER(sk);
 		if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
 			goto reset;
-		TCP_CHECK_TIMER(sk);
 		if (opt_skb)
 			goto ipv6_pktoptions;
 		return 0;
@@ -1667,10 +1665,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
-	TCP_CHECK_TIMER(sk);
 	if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len))
 		goto reset;
-	TCP_CHECK_TIMER(sk);
 	if (opt_skb)
 		goto ipv6_pktoptions;
 	return 0;
-- 
cgit v1.2.3


From 24d51add7438f9696a7205927bf9de3c5c787a58 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 21 Feb 2011 09:52:50 +0100
Subject: workqueue: fix build failure introduced by s/freezeable/freezable/

wq:fixes-2.6.38 does s/WQ_FREEZEABLE/WQ_FREEZABLE and wq:for-2.6.39
adds new usage of the flag.  The combination of the two creates a
build failure after merge.  Fix it by renaming all freezeables to
freezables.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
 include/linux/workqueue.h |  6 +++---
 kernel/workqueue.c        | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index d110cc4f9fed..f584aba78ca9 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -287,14 +287,14 @@ enum {
  * executed immediately as long as max_active limit is not reached and
  * resources are available.
  *
- * system_freezeable_wq is equivalent to system_wq except that it's
- * freezeable.
+ * system_freezable_wq is equivalent to system_wq except that it's
+ * freezable.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_nrt_wq;
 extern struct workqueue_struct *system_unbound_wq;
-extern struct workqueue_struct *system_freezeable_wq;
+extern struct workqueue_struct *system_freezable_wq;
 
 extern struct workqueue_struct *
 __alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 572f559f6cb9..1b64d225f067 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -251,12 +251,12 @@ struct workqueue_struct *system_wq __read_mostly;
 struct workqueue_struct *system_long_wq __read_mostly;
 struct workqueue_struct *system_nrt_wq __read_mostly;
 struct workqueue_struct *system_unbound_wq __read_mostly;
-struct workqueue_struct *system_freezeable_wq __read_mostly;
+struct workqueue_struct *system_freezable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_wq);
 EXPORT_SYMBOL_GPL(system_long_wq);
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
-EXPORT_SYMBOL_GPL(system_freezeable_wq);
+EXPORT_SYMBOL_GPL(system_freezable_wq);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
@@ -3777,10 +3777,10 @@ static int __init init_workqueues(void)
 	system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0);
 	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
 					    WQ_UNBOUND_MAX_ACTIVE);
-	system_freezeable_wq = alloc_workqueue("events_freezeable",
-					       WQ_FREEZEABLE, 0);
+	system_freezable_wq = alloc_workqueue("events_freezable",
+					      WQ_FREEZABLE, 0);
 	BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq ||
-	       !system_unbound_wq || !system_freezeable_wq);
+	       !system_unbound_wq || !system_freezable_wq);
 	return 0;
 }
 early_initcall(init_workqueues);
-- 
cgit v1.2.3


From e9a416b5ce0c0f93819f55d34cf6882196e9c3b2 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Sat, 19 Feb 2011 12:05:56 -0300
Subject: Bluetooth: Add mgmt_pair_device command

This patch adds a new mgmt_pair_device which can be used to initiate a
dedicated bonding procedure. Some extra callbacks are added to the
hci_conn struct so that the pairing code can get notified of the
completion of the procedure.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  16 +++++
 include/net/bluetooth/mgmt.h     |  12 ++++
 net/bluetooth/mgmt.c             | 133 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 161 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d5d8454236bf..506f25089207 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -248,6 +248,10 @@ struct hci_conn {
 	void		*priv;
 
 	struct hci_conn	*link;
+
+	void (*connect_cfm_cb)	(struct hci_conn *conn, u8 status);
+	void (*security_cfm_cb)	(struct hci_conn *conn, u8 status);
+	void (*disconn_cfm_cb)	(struct hci_conn *conn, u8 reason);
 };
 
 extern struct hci_proto *hci_proto[];
@@ -571,6 +575,9 @@ static inline void hci_proto_connect_cfm(struct hci_conn *conn, __u8 status)
 	hp = hci_proto[HCI_PROTO_SCO];
 	if (hp && hp->connect_cfm)
 		hp->connect_cfm(conn, status);
+
+	if (conn->connect_cfm_cb)
+		conn->connect_cfm_cb(conn, status);
 }
 
 static inline int hci_proto_disconn_ind(struct hci_conn *conn)
@@ -600,6 +607,9 @@ static inline void hci_proto_disconn_cfm(struct hci_conn *conn, __u8 reason)
 	hp = hci_proto[HCI_PROTO_SCO];
 	if (hp && hp->disconn_cfm)
 		hp->disconn_cfm(conn, reason);
+
+	if (conn->disconn_cfm_cb)
+		conn->disconn_cfm_cb(conn, reason);
 }
 
 static inline void hci_proto_auth_cfm(struct hci_conn *conn, __u8 status)
@@ -619,6 +629,9 @@ static inline void hci_proto_auth_cfm(struct hci_conn *conn, __u8 status)
 	hp = hci_proto[HCI_PROTO_SCO];
 	if (hp && hp->security_cfm)
 		hp->security_cfm(conn, status, encrypt);
+
+	if (conn->security_cfm_cb)
+		conn->security_cfm_cb(conn, status);
 }
 
 static inline void hci_proto_encrypt_cfm(struct hci_conn *conn, __u8 status, __u8 encrypt)
@@ -632,6 +645,9 @@ static inline void hci_proto_encrypt_cfm(struct hci_conn *conn, __u8 status, __u
 	hp = hci_proto[HCI_PROTO_SCO];
 	if (hp && hp->security_cfm)
 		hp->security_cfm(conn, status, encrypt);
+
+	if (conn->security_cfm_cb)
+		conn->security_cfm_cb(conn, status);
 }
 
 int hci_register_proto(struct hci_proto *hproto);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 44ac55c85079..1d25c59be2e3 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -160,6 +160,18 @@ struct mgmt_cp_set_io_capability {
 	__u8 io_capability;
 } __packed;
 
+#define MGMT_OP_PAIR_DEVICE		0x0014
+struct mgmt_cp_pair_device {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 io_cap;
+} __packed;
+struct mgmt_rp_pair_device {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 status;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 52e5f88b753a..d7fc54dcbc9e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -38,6 +38,7 @@ struct pending_cmd {
 	int index;
 	void *cmd;
 	struct sock *sk;
+	void *user_data;
 };
 
 LIST_HEAD(cmd_list);
@@ -1063,6 +1064,135 @@ static int set_io_capability(struct sock *sk, unsigned char *data, u16 len)
 						&dev_id, sizeof(dev_id));
 }
 
+static inline struct pending_cmd *find_pairing(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+	struct list_head *p;
+
+	list_for_each(p, &cmd_list) {
+		struct pending_cmd *cmd;
+
+		cmd = list_entry(p, struct pending_cmd, list);
+
+		if (cmd->opcode != MGMT_OP_PAIR_DEVICE)
+			continue;
+
+		if (cmd->index != hdev->id)
+			continue;
+
+		if (cmd->user_data != conn)
+			continue;
+
+		return cmd;
+	}
+
+	return NULL;
+}
+
+static void pairing_complete(struct pending_cmd *cmd, u8 status)
+{
+	struct mgmt_rp_pair_device rp;
+	struct hci_conn *conn = cmd->user_data;
+
+	rp.index = cmd->index;
+	bacpy(&rp.bdaddr, &conn->dst);
+	rp.status = status;
+
+	cmd_complete(cmd->sk, MGMT_OP_PAIR_DEVICE, &rp, sizeof(rp));
+
+	/* So we don't get further callbacks for this connection */
+	conn->connect_cfm_cb = NULL;
+	conn->security_cfm_cb = NULL;
+	conn->disconn_cfm_cb = NULL;
+
+	hci_conn_put(conn);
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+}
+
+static void pairing_complete_cb(struct hci_conn *conn, u8 status)
+{
+	struct pending_cmd *cmd;
+
+	BT_DBG("status %u", status);
+
+	cmd = find_pairing(conn);
+	if (!cmd) {
+		BT_DBG("Unable to find a pending command");
+		return;
+	}
+
+	pairing_complete(cmd, status);
+}
+
+static int pair_device(struct sock *sk, unsigned char *data, u16 len)
+{
+	struct hci_dev *hdev;
+	struct mgmt_cp_pair_device *cp;
+	struct pending_cmd *cmd;
+	u8 sec_level, auth_type;
+	struct hci_conn *conn;
+	u16 dev_id;
+	int err;
+
+	BT_DBG("");
+
+	cp = (void *) data;
+	dev_id = get_unaligned_le16(&cp->index);
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, MGMT_OP_PAIR_DEVICE, ENODEV);
+
+	hci_dev_lock_bh(hdev);
+
+	if (cp->io_cap == 0x03) {
+		sec_level = BT_SECURITY_MEDIUM;
+		auth_type = HCI_AT_DEDICATED_BONDING;
+	} else {
+		sec_level = BT_SECURITY_HIGH;
+		auth_type = HCI_AT_DEDICATED_BONDING_MITM;
+	}
+
+	conn = hci_connect(hdev, ACL_LINK, &cp->bdaddr, sec_level, auth_type);
+	if (!conn) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	if (conn->connect_cfm_cb) {
+		hci_conn_put(conn);
+		err = cmd_status(sk, MGMT_OP_PAIR_DEVICE, EBUSY);
+		goto unlock;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_PAIR_DEVICE, dev_id, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		hci_conn_put(conn);
+		goto unlock;
+	}
+
+	conn->connect_cfm_cb = pairing_complete_cb;
+	conn->security_cfm_cb = pairing_complete_cb;
+	conn->disconn_cfm_cb = pairing_complete_cb;
+	conn->io_capability = cp->io_cap;
+	cmd->user_data = conn;
+
+	if (conn->state == BT_CONNECTED &&
+				hci_conn_security(conn, sec_level, auth_type))
+		pairing_complete(cmd, 0);
+
+	err = 0;
+
+unlock:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -1148,6 +1278,9 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_SET_IO_CAPABILITY:
 		err = set_io_capability(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_PAIR_DEVICE:
+		err = pair_device(sk, buf + sizeof(*hdr), len);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
-- 
cgit v1.2.3


From a5c296832b4fde7d32c01cff9cdd27d9c7c1c4f5 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Sat, 19 Feb 2011 12:05:57 -0300
Subject: Bluetooth: Add management support for user confirmation request

This patch adds support for the user confirmation (numeric comparison)
Secure Simple Pairing authentication method.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci.h      |  17 +++++++
 include/net/bluetooth/hci_core.h |   4 ++
 include/net/bluetooth/mgmt.h     |  20 ++++++++
 net/bluetooth/hci_event.c        |  50 +++++++++++++++++++
 net/bluetooth/mgmt.c             | 103 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 194 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index a5f8c4684a32..ec6acf2f1c0b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -415,6 +415,17 @@ struct hci_cp_io_capability_reply {
 	__u8     authentication;
 } __packed;
 
+#define HCI_OP_USER_CONFIRM_REPLY		0x042c
+struct hci_cp_user_confirm_reply {
+	bdaddr_t bdaddr;
+} __packed;
+struct hci_rp_user_confirm_reply {
+	__u8     status;
+	bdaddr_t bdaddr;
+} __packed;
+
+#define HCI_OP_USER_CONFIRM_NEG_REPLY	0x042d
+
 #define HCI_OP_IO_CAPABILITY_NEG_REPLY	0x0434
 struct hci_cp_io_capability_neg_reply {
 	bdaddr_t bdaddr;
@@ -936,6 +947,12 @@ struct hci_ev_io_capa_reply {
 	__u8     authentication;
 } __packed;
 
+#define HCI_EV_USER_CONFIRM_REQUEST	0x33
+struct hci_ev_user_confirm_req {
+	bdaddr_t	bdaddr;
+	__le32		passkey;
+} __packed;
+
 #define HCI_EV_SIMPLE_PAIR_COMPLETE	0x36
 struct hci_ev_simple_pair_complete {
 	__u8     status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 506f25089207..05f4706e6c34 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -762,6 +762,10 @@ int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status);
 int mgmt_pin_code_request(u16 index, bdaddr_t *bdaddr);
 int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status);
 int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status);
+int mgmt_user_confirm_request(u16 index, bdaddr_t *bdaddr, __le32 value);
+int mgmt_user_confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status);
+int mgmt_user_confirm_neg_reply_complete(u16 index, bdaddr_t *bdaddr,
+								u8 status);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 1d25c59be2e3..52376a3295ca 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -172,6 +172,19 @@ struct mgmt_rp_pair_device {
 	__u8 status;
 } __packed;
 
+#define MGMT_OP_USER_CONFIRM_REPLY	0x0015
+struct mgmt_cp_user_confirm_reply {
+	__le16 index;
+	bdaddr_t bdaddr;
+} __packed;
+struct mgmt_rp_user_confirm_reply {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 status;
+} __packed;
+
+#define MGMT_OP_USER_CONFIRM_NEG_REPLY	0x0016
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16 opcode;
@@ -239,3 +252,10 @@ struct mgmt_ev_pin_code_request {
 	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
+
+#define MGMT_EV_USER_CONFIRM_REQUEST	0x000F
+struct mgmt_ev_user_confirm_request {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__le32 value;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 98b5764e4315..604c7b5fee97 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -796,6 +796,29 @@ static void hci_cc_le_read_buffer_size(struct hci_dev *hdev,
 	hci_req_complete(hdev, HCI_OP_LE_READ_BUFFER_SIZE, rp->status);
 }
 
+static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_rp_user_confirm_reply *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%x", hdev->name, rp->status);
+
+	if (test_bit(HCI_MGMT, &hdev->flags))
+		mgmt_user_confirm_reply_complete(hdev->id, &rp->bdaddr,
+								rp->status);
+}
+
+static void hci_cc_user_confirm_neg_reply(struct hci_dev *hdev,
+							struct sk_buff *skb)
+{
+	struct hci_rp_user_confirm_reply *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%x", hdev->name, rp->status);
+
+	if (test_bit(HCI_MGMT, &hdev->flags))
+		mgmt_user_confirm_neg_reply_complete(hdev->id, &rp->bdaddr,
+								rp->status);
+}
+
 static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%x", hdev->name, status);
@@ -1728,6 +1751,14 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk
 		hci_cc_le_read_buffer_size(hdev, skb);
 		break;
 
+	case HCI_OP_USER_CONFIRM_REPLY:
+		hci_cc_user_confirm_reply(hdev, skb);
+		break;
+
+	case HCI_OP_USER_CONFIRM_NEG_REPLY:
+		hci_cc_user_confirm_neg_reply(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%x", hdev->name, opcode);
 		break;
@@ -2362,6 +2393,21 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static inline void hci_user_confirm_request_evt(struct hci_dev *hdev,
+							struct sk_buff *skb)
+{
+	struct hci_ev_user_confirm_req *ev = (void *) skb->data;
+
+	BT_DBG("%s", hdev->name);
+
+	hci_dev_lock(hdev);
+
+	if (test_bit(HCI_MGMT, &hdev->flags))
+		mgmt_user_confirm_request(hdev->id, &ev->bdaddr, ev->passkey);
+
+	hci_dev_unlock(hdev);
+}
+
 static inline void hci_simple_pair_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_simple_pair_complete *ev = (void *) skb->data;
@@ -2580,6 +2626,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_io_capa_reply_evt(hdev, skb);
 		break;
 
+	case HCI_EV_USER_CONFIRM_REQUEST:
+		hci_user_confirm_request_evt(hdev, skb);
+		break;
+
 	case HCI_EV_SIMPLE_PAIR_COMPLETE:
 		hci_simple_pair_complete_evt(hdev, skb);
 		break;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d7fc54dcbc9e..fdcc9742bb00 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1193,6 +1193,55 @@ unlock:
 	return err;
 }
 
+static int user_confirm_reply(struct sock *sk, unsigned char *data, u16 len,
+								int success)
+{
+	struct mgmt_cp_user_confirm_reply *cp = (void *) data;
+	u16 dev_id, mgmt_op, hci_op;
+	struct pending_cmd *cmd;
+	struct hci_dev *hdev;
+	int err;
+
+	BT_DBG("");
+
+	dev_id = get_unaligned_le16(&cp->index);
+
+	if (success) {
+		mgmt_op = MGMT_OP_USER_CONFIRM_REPLY;
+		hci_op = HCI_OP_USER_CONFIRM_REPLY;
+	} else {
+		mgmt_op = MGMT_OP_USER_CONFIRM_NEG_REPLY;
+		hci_op = HCI_OP_USER_CONFIRM_NEG_REPLY;
+	}
+
+	hdev = hci_dev_get(dev_id);
+	if (!hdev)
+		return cmd_status(sk, mgmt_op, ENODEV);
+
+	if (!test_bit(HCI_UP, &hdev->flags)) {
+		err = cmd_status(sk, mgmt_op, ENETDOWN);
+		goto failed;
+	}
+
+	cmd = mgmt_pending_add(sk, mgmt_op, dev_id, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	err = hci_send_cmd(hdev, hci_op, sizeof(cp->bdaddr), &cp->bdaddr);
+	if (err < 0) {
+		list_del(&cmd->list);
+		mgmt_pending_free(cmd);
+	}
+
+failed:
+	hci_dev_unlock_bh(hdev);
+	hci_dev_put(hdev);
+
+	return err;
+}
+
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
@@ -1281,6 +1330,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 	case MGMT_OP_PAIR_DEVICE:
 		err = pair_device(sk, buf + sizeof(*hdr), len);
 		break;
+	case MGMT_OP_USER_CONFIRM_REPLY:
+		err = user_confirm_reply(sk, buf + sizeof(*hdr), len, 1);
+		break;
+	case MGMT_OP_USER_CONFIRM_NEG_REPLY:
+		err = user_confirm_reply(sk, buf + sizeof(*hdr), len, 0);
+		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
 		err = cmd_status(sk, opcode, 0x01);
@@ -1541,3 +1596,51 @@ int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
 
 	return err;
 }
+
+int mgmt_user_confirm_request(u16 index, bdaddr_t *bdaddr, __le32 value)
+{
+	struct mgmt_ev_user_confirm_request ev;
+
+	BT_DBG("hci%u", index);
+
+	put_unaligned_le16(index, &ev.index);
+	bacpy(&ev.bdaddr, bdaddr);
+	put_unaligned_le32(value, &ev.value);
+
+	return mgmt_event(MGMT_EV_USER_CONFIRM_REQUEST, &ev, sizeof(ev), NULL);
+}
+
+static int confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status,
+								u8 opcode)
+{
+	struct pending_cmd *cmd;
+	struct mgmt_rp_user_confirm_reply rp;
+	int err;
+
+	cmd = mgmt_pending_find(opcode, index);
+	if (!cmd)
+		return -ENOENT;
+
+	put_unaligned_le16(index, &rp.index);
+	bacpy(&rp.bdaddr, bdaddr);
+	rp.status = status;
+	err = cmd_complete(cmd->sk, opcode, &rp, sizeof(rp));
+
+	list_del(&cmd->list);
+	mgmt_pending_free(cmd);
+
+	return err;
+}
+
+int mgmt_user_confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
+{
+	return confirm_reply_complete(index, bdaddr, status,
+						MGMT_OP_USER_CONFIRM_REPLY);
+}
+
+int mgmt_user_confirm_neg_reply_complete(u16 index, bdaddr_t *bdaddr,
+								u8 status)
+{
+	return confirm_reply_complete(index, bdaddr, status,
+					MGMT_OP_USER_CONFIRM_NEG_REPLY);
+}
-- 
cgit v1.2.3


From ac56fb13c0508181b4227b8ada6d47aaaf72794c Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Sat, 19 Feb 2011 12:05:59 -0300
Subject: Bluetooth: Fix mgmt_pin_code_reply return parameters

The command complete event for mgmt_pin_code_reply &
mgmt_pin_code_neg_reply should have the adapter index, Bluetooth address
as well as the status.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/mgmt.h |  5 +++++
 net/bluetooth/mgmt.c         | 23 +++++++++++++----------
 2 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 52376a3295ca..5aee200e5e36 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -147,6 +147,11 @@ struct mgmt_cp_pin_code_reply {
 	__u8 pin_len;
 	__u8 pin_code[16];
 } __packed;
+struct mgmt_rp_pin_code_reply {
+	__le16 index;
+	bdaddr_t bdaddr;
+	uint8_t status;
+} __packed;
 
 #define MGMT_OP_PIN_CODE_NEG_REPLY	0x0012
 struct mgmt_cp_pin_code_neg_reply {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d1d9b8c3a1b0..0d3d613baac2 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1558,17 +1558,18 @@ int mgmt_pin_code_request(u16 index, bdaddr_t *bdaddr)
 int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
 {
 	struct pending_cmd *cmd;
+	struct mgmt_rp_pin_code_reply rp;
 	int err;
 
 	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_REPLY, index);
 	if (!cmd)
 		return -ENOENT;
 
-	if (status != 0)
-		err = cmd_status(cmd->sk, MGMT_OP_PIN_CODE_REPLY, status);
-	else
-		err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_REPLY,
-						bdaddr, sizeof(*bdaddr));
+	put_unaligned_le16(index, &rp.index);
+	bacpy(&rp.bdaddr, bdaddr);
+	rp.status = status;
+
+	err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_REPLY, &rp, sizeof(rp));
 
 	list_del(&cmd->list);
 	mgmt_pending_free(cmd);
@@ -1579,17 +1580,19 @@ int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
 int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
 {
 	struct pending_cmd *cmd;
+	struct mgmt_rp_pin_code_reply rp;
 	int err;
 
 	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, index);
 	if (!cmd)
 		return -ENOENT;
 
-	if (status != 0)
-		err = cmd_status(cmd->sk, MGMT_OP_PIN_CODE_NEG_REPLY, status);
-	else
-		err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_NEG_REPLY,
-						bdaddr, sizeof(*bdaddr));
+	put_unaligned_le16(index, &rp.index);
+	bacpy(&rp.bdaddr, bdaddr);
+	rp.status = status;
+
+	err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_NEG_REPLY,
+							&rp, sizeof(rp));
 
 	list_del(&cmd->list);
 	mgmt_pending_free(cmd);
-- 
cgit v1.2.3


From 2a61169209c72317d4933f8d22f749a6a61a3d36 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@nokia.com>
Date: Sat, 19 Feb 2011 12:06:00 -0300
Subject: Bluetooth: Add mgmt_auth_failed event

To properly track bonding completion an event to indicate authentication
failure is needed. This event will be sent whenever an authentication
complete HCI event with a non-zero status comes. It will also be sent
when we're acting in acceptor role for SSP authentication in which case
the controller will send a Simple Pairing Complete event.

Signed-off-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/hci_core.h |  1 +
 include/net/bluetooth/mgmt.h     |  7 +++++++
 net/bluetooth/hci_event.c        | 19 ++++++++++++++++---
 net/bluetooth/mgmt.c             | 11 +++++++++++
 4 files changed, 35 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 05f4706e6c34..441dadbf6a89 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -766,6 +766,7 @@ int mgmt_user_confirm_request(u16 index, bdaddr_t *bdaddr, __le32 value);
 int mgmt_user_confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status);
 int mgmt_user_confirm_neg_reply_complete(u16 index, bdaddr_t *bdaddr,
 								u8 status);
+int mgmt_auth_failed(u16 index, bdaddr_t *bdaddr, u8 status);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 5aee200e5e36..1e63c3141a78 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -264,3 +264,10 @@ struct mgmt_ev_user_confirm_request {
 	bdaddr_t bdaddr;
 	__le32 value;
 } __packed;
+
+#define MGMT_EV_AUTH_FAILED		0x0010
+struct mgmt_ev_auth_failed {
+	__le16 index;
+	bdaddr_t bdaddr;
+	__u8 status;
+} __packed;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 604c7b5fee97..3fbfa50c2bff 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1424,8 +1424,10 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s
 		if (!ev->status) {
 			conn->link_mode |= HCI_LM_AUTH;
 			conn->sec_level = conn->pending_sec_level;
-		} else
+		} else {
+			mgmt_auth_failed(hdev->id, &conn->dst, ev->status);
 			conn->sec_level = BT_SECURITY_LOW;
+		}
 
 		clear_bit(HCI_CONN_AUTH_PEND, &conn->pend);
 
@@ -2418,9 +2420,20 @@ static inline void hci_simple_pair_complete_evt(struct hci_dev *hdev, struct sk_
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
-	if (conn)
-		hci_conn_put(conn);
+	if (!conn)
+		goto unlock;
+
+	/* To avoid duplicate auth_failed events to user space we check
+	 * the HCI_CONN_AUTH_PEND flag which will be set if we
+	 * initiated the authentication. A traditional auth_complete
+	 * event gets always produced as initiator and is also mapped to
+	 * the mgmt_auth_failed event */
+	if (!test_bit(HCI_CONN_AUTH_PEND, &conn->pend) && ev->status != 0)
+		mgmt_auth_failed(hdev->id, &conn->dst, ev->status);
 
+	hci_conn_put(conn);
+
+unlock:
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 0d3d613baac2..46e2c39c8956 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1647,3 +1647,14 @@ int mgmt_user_confirm_neg_reply_complete(u16 index, bdaddr_t *bdaddr,
 	return confirm_reply_complete(index, bdaddr, status,
 					MGMT_OP_USER_CONFIRM_NEG_REPLY);
 }
+
+int mgmt_auth_failed(u16 index, bdaddr_t *bdaddr, u8 status)
+{
+	struct mgmt_ev_auth_failed ev;
+
+	put_unaligned_le16(index, &ev.index);
+	bacpy(&ev.bdaddr, bdaddr);
+	ev.status = status;
+
+	return mgmt_event(MGMT_EV_AUTH_FAILED, &ev, sizeof(ev), NULL);
+}
-- 
cgit v1.2.3


From e06383db9ec591696a06654257474b85bac1f8cb Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 14 Dec 2010 19:37:07 -0800
Subject: hrtimers: extend hrtimer base code to handle more then 2 clockids
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The hrtimer code is written mainly with CLOCK_REALTIME and CLOCK_MONOTONIC
in mind. These are clockids 0 and 1 resepctively. However, if we are
to introduce any new hrtimer bases, using new clockids, we have to skip
the cputimers (clockids 2,3) as well as other clockids that may not impelement
timers.

This patch adds a little bit of indirection between the clockid and
the base, so that we can extend the base by one when we add
a new clockid at number 7 or so.

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/hrtimer.h |  6 +++++-
 kernel/hrtimer.c        | 40 +++++++++++++++++++++++++++-------------
 2 files changed, 32 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f376ddc64c4d..20b8e6601a04 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -148,7 +148,11 @@ struct hrtimer_clock_base {
 #endif
 };
 
-#define HRTIMER_MAX_CLOCK_BASES 2
+enum  hrtimer_base_type {
+	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_MAX_CLOCK_BASES,
+};
 
 /*
  * struct hrtimer_cpu_base - the per cpu clock bases
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 57c4d33c9a9d..ca99e2454600 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -53,11 +53,10 @@
 /*
  * The timer bases:
  *
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
@@ -77,6 +76,14 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
+static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	return hrtimer_clock_to_base_table[clock_id];
+}
+
+
 /*
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
@@ -90,8 +97,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 
 	xtim = timespec_to_ktime(xts);
 	tomono = timespec_to_ktime(tom);
-	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
-	base->clock_base[CLOCK_MONOTONIC].softirq_time =
+	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time =
 		ktime_add(xtim, tomono);
 }
 
@@ -179,10 +186,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 	struct hrtimer_cpu_base *new_cpu_base;
 	int this_cpu = smp_processor_id();
 	int cpu = hrtimer_get_target(this_cpu, pinned);
+	int basenum = hrtimer_clockid_to_base(base->index);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &new_cpu_base->clock_base[base->index];
+	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
 		/*
@@ -618,7 +626,7 @@ static void retrigger_next_event(void *arg)
 
 	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[CLOCK_REALTIME].offset =
+	base->clock_base[HRTIMER_BASE_REALTIME].offset =
 		timespec_to_ktime(realtime_offset);
 
 	hrtimer_force_reprogram(base, 0);
@@ -716,8 +724,8 @@ static int hrtimer_switch_to_hres(void)
 		return 0;
 	}
 	base->hres_active = 1;
-	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
-	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -1112,6 +1120,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
@@ -1120,7 +1129,8 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &cpu_base->clock_base[clock_id];
+	base = hrtimer_clockid_to_base(clock_id);
+	timer->base = &cpu_base->clock_base[base];
 	hrtimer_init_timer_hres(timer);
 	timerqueue_init(&timer->node);
 
@@ -1156,9 +1166,10 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base = hrtimer_clockid_to_base(which_clock);
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
 }
@@ -1705,6 +1716,9 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
 
 void __init hrtimers_init(void)
 {
+	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
+	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
-- 
cgit v1.2.3


From abb3a4ea2e0ea7114a4475745da2f32bd9ad5b73 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 14 Feb 2011 17:52:09 -0800
Subject: time: Introduce get_monotonic_boottime and ktime_get_boottime
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds new functions that return the monotonic time since boot
(in other words, CLOCK_MONOTONIC + suspend time).

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/hrtimer.h   |  1 +
 include/linux/time.h      |  1 +
 kernel/time/timekeeping.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 20b8e6601a04..7a9e7ee0f35c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -312,6 +312,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
+extern ktime_t ktime_get_boottime(void);
 
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
diff --git a/include/linux/time.h b/include/linux/time.h
index 379b9037b5b4..fa39150cb816 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -161,6 +161,7 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw,
 		struct timespec *ts_real);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
+extern void get_monotonic_boottime(struct timespec *ts);
 
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6262c1d18397..5fbd9aa7df95 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -907,7 +907,7 @@ static void update_wall_time(void)
  * getboottime - Return the real time of system boot.
  * @ts:		pointer to the timespec to be set
  *
- * Returns the time of day in a timespec.
+ * Returns the wall-time of boot in a timespec.
  *
  * This is based on the wall_to_monotonic offset and the total suspend
  * time. Calls to settimeofday will affect the value returned (which
@@ -925,6 +925,55 @@ void getboottime(struct timespec *ts)
 }
 EXPORT_SYMBOL_GPL(getboottime);
 
+
+/**
+ * get_monotonic_boottime - Returns monotonic time since boot
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the monotonic time since boot in a timespec.
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
+ * includes the time spent in suspend.
+ */
+void get_monotonic_boottime(struct timespec *ts)
+{
+	struct timespec tomono, sleep;
+	unsigned int seq;
+	s64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*ts = xtime;
+		tomono = wall_to_monotonic;
+		sleep = total_sleep_time;
+		nsecs = timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
+			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+}
+EXPORT_SYMBOL_GPL(get_monotonic_boottime);
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in a ktime
+ *
+ * Returns the monotonic time since boot in a ktime
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also
+ * includes the time spent in suspend.
+ */
+ktime_t ktime_get_boottime(void)
+{
+	struct timespec ts;
+
+	get_monotonic_boottime(&ts);
+	return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL_GPL(ktime_get_boottime);
+
 /**
  * monotonic_to_bootbased - Convert the monotonic time to boot based.
  * @ts:		pointer to the timespec to be converted
-- 
cgit v1.2.3


From 314ac37150011ebb398f522db528d2dbcc611189 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 14 Feb 2011 18:43:08 -0800
Subject: time: Extend get_xtime_and_monotonic_offset() to also return sleep
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend get_xtime_and_monotonic_offset to
get_xtime_and_monotonic_and_sleep_offset().

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/time.h      | 3 ++-
 kernel/hrtimer.c          | 9 +++++----
 kernel/time/timekeeping.c | 8 ++++++--
 3 files changed, 13 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index fa39150cb816..02d48fb30b41 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -124,7 +124,8 @@ unsigned long get_seconds(void);
 struct timespec current_kernel_time(void);
 struct timespec __current_kernel_time(void); /* does not take xtime_lock */
 struct timespec get_monotonic_coarse(void);
-void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom);
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+				struct timespec *wtom, struct timespec *sleep);
 
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ca99e2454600..e8bf3ad99063 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -91,9 +91,9 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
 	ktime_t xtim, tomono;
-	struct timespec xts, tom;
+	struct timespec xts, tom, slp;
 
-	get_xtime_and_monotonic_offset(&xts, &tom);
+	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
 
 	xtim = timespec_to_ktime(xts);
 	tomono = timespec_to_ktime(tom);
@@ -614,12 +614,13 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
 	struct hrtimer_cpu_base *base;
-	struct timespec realtime_offset, wtm;
+	struct timespec realtime_offset, wtm, sleep;
 
 	if (!hrtimer_hres_active())
 		return;
 
-	get_xtime_and_monotonic_offset(&realtime_offset, &wtm);
+	get_xtime_and_monotonic_and_sleep_offset(&realtime_offset, &wtm,
+							&sleep);
 	set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
 
 	base = &__get_cpu_var(hrtimer_bases);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 5fbd9aa7df95..3bd7e3d5c632 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1040,11 +1040,14 @@ void do_timer(unsigned long ticks)
 }
 
 /**
- * get_xtime_and_monotonic_offset() - get xtime and wall_to_monotonic
+ * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic,
+ *    and sleep offsets.
  * @xtim:	pointer to timespec to be set with xtime
  * @wtom:	pointer to timespec to be set with wall_to_monotonic
+ * @sleep:	pointer to timespec to be set with time in suspend
  */
-void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom)
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+				struct timespec *wtom, struct timespec *sleep)
 {
 	unsigned long seq;
 
@@ -1052,6 +1055,7 @@ void get_xtime_and_monotonic_offset(struct timespec *xtim, struct timespec *wtom
 		seq = read_seqbegin(&xtime_lock);
 		*xtim = xtime;
 		*wtom = wall_to_monotonic;
+		*sleep = total_sleep_time;
 	} while (read_seqretry(&xtime_lock, seq));
 }
 
-- 
cgit v1.2.3


From 70a08cca1227dc31c784ec930099a4417a06e7d0 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 15 Feb 2011 10:45:16 -0800
Subject: timers: Add CLOCK_BOOTTIME hrtimer base
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

CLOCK_MONOTONIC stops while the system is in suspend. This is because
to applications system suspend is invisible. However, there is a
growing set of applications that are wanting to be suspend-aware,
but do not want to deal with the complications of CLOCK_REALTIME
(which might jump around if settimeofday is called).

For these applications, I propose a new clockid: CLOCK_BOOTTIME.
CLOCK_BOOTTIME is idential to CLOCK_MONOTONIC, except it also
includes any time spent in suspend.

This patch add hrtimer base for CLOCK_BOOTTIME, using
get_monotonic_boottime/ktime_get_boottime, to allow
in kernel users to set timers against.

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/hrtimer.h |  1 +
 include/linux/time.h    |  1 +
 kernel/hrtimer.c        | 16 ++++++++++++----
 3 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 7a9e7ee0f35c..6bc1804bfbfa 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -151,6 +151,7 @@ struct hrtimer_clock_base {
 enum  hrtimer_base_type {
 	HRTIMER_BASE_REALTIME,
 	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_BASE_BOOTTIME,
 	HRTIMER_MAX_CLOCK_BASES,
 };
 
diff --git a/include/linux/time.h b/include/linux/time.h
index 02d48fb30b41..454a26205787 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -293,6 +293,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC_RAW		4
 #define CLOCK_REALTIME_COARSE		5
 #define CLOCK_MONOTONIC_COARSE		6
+#define CLOCK_BOOTTIME			7
 
 /*
  * The IDs of various hardware clocks:
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index e8bf3ad99063..4c53af18734b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -73,6 +73,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get,
 			.resolution = KTIME_LOW_RES,
 		},
+		{
+			.index = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+			.resolution = KTIME_LOW_RES,
+		},
 	}
 };
 
@@ -90,16 +95,17 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
  */
 static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
-	ktime_t xtim, tomono;
+	ktime_t xtim, mono, boot;
 	struct timespec xts, tom, slp;
 
 	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
 
 	xtim = timespec_to_ktime(xts);
-	tomono = timespec_to_ktime(tom);
+	mono = ktime_add(xtim, timespec_to_ktime(tom));
+	boot = ktime_add(mono, timespec_to_ktime(slp));
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
-	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time =
-		ktime_add(xtim, tomono);
+	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
 }
 
 /*
@@ -727,6 +733,7 @@ static int hrtimer_switch_to_hres(void)
 	base->hres_active = 1;
 	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -1719,6 +1726,7 @@ void __init hrtimers_init(void)
 {
 	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
 	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+	hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
 
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
-- 
cgit v1.2.3


From 98562ad8cb03fa6b7ba7f50168cdb34a98abcc1d Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dtor@vmware.com>
Date: Fri, 4 Feb 2011 13:30:10 -0800
Subject: module: explicitly align module_version_attribute structure

We force particular alignment when we generate attribute structures
when generation MODULE_VERSION() data and we need to make sure that
this alignment is followed when we iterate over these structures,
otherwise we may crash on platforms whose natural alignment is not
sizeof(void *), such as m68k.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Dmitry Torokhov <dtor@vmware.com>
[ There are more issues here, but the fixes are incredibly ugly - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/module.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 9bdf27c7615b..5de42043dff0 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -62,7 +62,7 @@ struct module_version_attribute {
 	struct module_attribute mattr;
 	const char *module_name;
 	const char *version;
-};
+} __attribute__ ((__aligned__(sizeof(void *))));
 
 struct module_kobject
 {
-- 
cgit v1.2.3


From 731109e78415b4cc6c2f8de6c11b37f0e40741f8 Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Sat, 19 Feb 2011 18:05:08 +0800
Subject: ipvs: use hlist instead of list

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  2 +-
 net/netfilter/ipvs/ip_vs_conn.c | 52 +++++++++++++++++++++++------------------
 2 files changed, 30 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 93995494dfd4..17b01b2d48f9 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -494,7 +494,7 @@ struct ip_vs_conn_param {
  *	IP_VS structure allocated for each dynamically scheduled connection
  */
 struct ip_vs_conn {
-	struct list_head        c_list;         /* hashed list heads */
+	struct hlist_node	c_list;         /* hashed list heads */
 #ifdef CONFIG_NET_NS
 	struct net              *net;           /* Name space */
 #endif
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 83233fe24a08..9c2a517b69c8 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -59,7 +59,7 @@ static int ip_vs_conn_tab_mask __read_mostly;
 /*
  *  Connection hash table: for input and output packets lookups of IPVS
  */
-static struct list_head *ip_vs_conn_tab __read_mostly;
+static struct hlist_head *ip_vs_conn_tab __read_mostly;
 
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
@@ -201,7 +201,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
 	spin_lock(&cp->lock);
 
 	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
-		list_add(&cp->c_list, &ip_vs_conn_tab[hash]);
+		hlist_add_head(&cp->c_list, &ip_vs_conn_tab[hash]);
 		cp->flags |= IP_VS_CONN_F_HASHED;
 		atomic_inc(&cp->refcnt);
 		ret = 1;
@@ -234,7 +234,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
 	spin_lock(&cp->lock);
 
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
-		list_del(&cp->c_list);
+		hlist_del(&cp->c_list);
 		cp->flags &= ~IP_VS_CONN_F_HASHED;
 		atomic_dec(&cp->refcnt);
 		ret = 1;
@@ -259,12 +259,13 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp;
+	struct hlist_node *n;
 
 	hash = ip_vs_conn_hashkey_param(p, false);
 
 	ct_read_lock(hash);
 
-	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+	hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
 		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
@@ -345,12 +346,13 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp;
+	struct hlist_node *n;
 
 	hash = ip_vs_conn_hashkey_param(p, false);
 
 	ct_read_lock(hash);
 
-	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+	hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 		if (!ip_vs_conn_net_eq(cp, p->net))
 			continue;
 		if (p->pe_data && p->pe->ct_match) {
@@ -394,6 +396,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp, *ret=NULL;
+	struct hlist_node *n;
 
 	/*
 	 *	Check for "full" addressed entries
@@ -402,7 +405,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 	ct_read_lock(hash);
 
-	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+	hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
 		    p->vport == cp->cport && p->cport == cp->dport &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
@@ -818,7 +821,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 		return NULL;
 	}
 
-	INIT_LIST_HEAD(&cp->c_list);
+	INIT_HLIST_NODE(&cp->c_list);
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
 	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
@@ -894,8 +897,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
  */
 #ifdef CONFIG_PROC_FS
 struct ip_vs_iter_state {
-	struct seq_net_private p;
-	struct list_head *l;
+	struct seq_net_private	p;
+	struct hlist_head	*l;
 };
 
 static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
@@ -903,13 +906,14 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 	int idx;
 	struct ip_vs_conn *cp;
 	struct ip_vs_iter_state *iter = seq->private;
+	struct hlist_node *n;
 
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		ct_read_lock_bh(idx);
-		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
+		hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) {
 			if (pos-- == 0) {
 				iter->l = &ip_vs_conn_tab[idx];
-			return cp;
+				return cp;
 			}
 		}
 		ct_read_unlock_bh(idx);
@@ -930,7 +934,8 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_conn *cp = v;
 	struct ip_vs_iter_state *iter = seq->private;
-	struct list_head *e, *l = iter->l;
+	struct hlist_node *e;
+	struct hlist_head *l = iter->l;
 	int idx;
 
 	++*pos;
@@ -938,15 +943,15 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		return ip_vs_conn_array(seq, 0);
 
 	/* more on same hash chain? */
-	if ((e = cp->c_list.next) != l)
-		return list_entry(e, struct ip_vs_conn, c_list);
+	if ((e = cp->c_list.next))
+		return hlist_entry(e, struct ip_vs_conn, c_list);
 
 	idx = l - ip_vs_conn_tab;
 	ct_read_unlock_bh(idx);
 
 	while (++idx < ip_vs_conn_tab_size) {
 		ct_read_lock_bh(idx);
-		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
+		hlist_for_each_entry(cp, e, &ip_vs_conn_tab[idx], c_list) {
 			iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 		}
@@ -959,7 +964,7 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
 {
 	struct ip_vs_iter_state *iter = seq->private;
-	struct list_head *l = iter->l;
+	struct hlist_head *l = iter->l;
 
 	if (l)
 		ct_read_unlock_bh(l - ip_vs_conn_tab);
@@ -1148,13 +1153,14 @@ void ip_vs_random_dropentry(struct net *net)
 	 */
 	for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) {
 		unsigned hash = net_random() & ip_vs_conn_tab_mask;
+		struct hlist_node *n;
 
 		/*
 		 *  Lock is actually needed in this loop.
 		 */
 		ct_write_lock_bh(hash);
 
-		list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+		hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
 				/* connection template */
 				continue;
@@ -1202,12 +1208,14 @@ static void ip_vs_conn_flush(struct net *net)
 
 flush_again:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
+		struct hlist_node *n;
+
 		/*
 		 *  Lock is actually needed in this loop.
 		 */
 		ct_write_lock_bh(idx);
 
-		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
+		hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) {
 			if (!ip_vs_conn_net_eq(cp, net))
 				continue;
 			IP_VS_DBG(4, "del connection\n");
@@ -1265,8 +1273,7 @@ int __init ip_vs_conn_init(void)
 	/*
 	 * Allocate the connection hash table and initialize its list heads
 	 */
-	ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size *
-				 sizeof(struct list_head));
+	ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size * sizeof(*ip_vs_conn_tab));
 	if (!ip_vs_conn_tab)
 		return -ENOMEM;
 
@@ -1286,9 +1293,8 @@ int __init ip_vs_conn_init(void)
 	IP_VS_DBG(0, "Each connection entry needs %Zd bytes at least\n",
 		  sizeof(struct ip_vs_conn));
 
-	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
-		INIT_LIST_HEAD(&ip_vs_conn_tab[idx]);
-	}
+	for (idx = 0; idx < ip_vs_conn_tab_size; idx++)
+		INIT_HLIST_HEAD(&ip_vs_conn_tab[idx]);
 
 	for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++)  {
 		rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
-- 
cgit v1.2.3


From 5ced1339612d1fa095459bd481f1d1f64f76f859 Mon Sep 17 00:00:00 2001
From: Linus Lüssing <linus.luessing@web.de>
Date: Tue, 15 Feb 2011 13:19:20 +0000
Subject: ipv6: Add IPv6 multicast address flag defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit adds the missing IPv6 multicast address flag defines to
complement the already existing multicast address scope defines and to
be able to check these flags nicely in the future.

Signed-off-by: Linus Lüssing <linus.luessing@web.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4a3cd2cd2f5e..96e50e0ce3ca 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -88,6 +88,18 @@
 #define IPV6_ADDR_SCOPE_ORGLOCAL	0x08
 #define IPV6_ADDR_SCOPE_GLOBAL		0x0e
 
+/*
+ *	Addr flags
+ */
+#ifdef __KERNEL__
+#define IPV6_ADDR_MC_FLAG_TRANSIENT(a)	\
+	((a)->s6_addr[1] & 0x10)
+#define IPV6_ADDR_MC_FLAG_PREFIX(a)	\
+	((a)->s6_addr[1] & 0x20)
+#define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a)	\
+	((a)->s6_addr[1] & 0x40)
+#endif
+
 /*
  *	fragmentation header
  */
-- 
cgit v1.2.3


From eaefd1105bc431ef329599e307a07f2a36ae7872 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 18 Feb 2011 03:26:36 +0000
Subject: net: add __rcu annotations to sk_wq and wq

Add proper RCU annotations/verbs to sk_wq and wq members

Fix __sctp_write_space() sk_sleep() abuse (and sock->wq access)

Fix sunrpc sk_sleep() abuse too

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h  |  3 ++-
 include/net/sock.h   |  7 ++++---
 net/sctp/socket.c    |  9 +++++----
 net/socket.c         | 23 ++++++++++++++---------
 net/sunrpc/svcsock.c | 32 ++++++++++++++++++++------------
 net/unix/af_unix.c   |  2 +-
 6 files changed, 46 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index 16faa130088c..94de83c0f877 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -118,6 +118,7 @@ enum sock_shutdown_cmd {
 };
 
 struct socket_wq {
+	/* Note: wait MUST be first field of socket_wq */
 	wait_queue_head_t	wait;
 	struct fasync_struct	*fasync_list;
 	struct rcu_head		rcu;
@@ -142,7 +143,7 @@ struct socket {
 
 	unsigned long		flags;
 
-	struct socket_wq	*wq;
+	struct socket_wq __rcu	*wq;
 
 	struct file		*file;
 	struct sock		*sk;
diff --git a/include/net/sock.h b/include/net/sock.h
index e3893a2b5d25..da0534d3401c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -281,7 +281,7 @@ struct sock {
 	int			sk_rcvbuf;
 
 	struct sk_filter __rcu	*sk_filter;
-	struct socket_wq	*sk_wq;
+	struct socket_wq __rcu	*sk_wq;
 
 #ifdef CONFIG_NET_DMA
 	struct sk_buff_head	sk_async_wait_queue;
@@ -1266,7 +1266,8 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 
 static inline wait_queue_head_t *sk_sleep(struct sock *sk)
 {
-	return &sk->sk_wq->wait;
+	BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
+	return &rcu_dereference_raw(sk->sk_wq)->wait;
 }
 /* Detach socket from process context.
  * Announce socket dead, detach it from wait queue and inode.
@@ -1287,7 +1288,7 @@ static inline void sock_orphan(struct sock *sk)
 static inline void sock_graft(struct sock *sk, struct socket *parent)
 {
 	write_lock_bh(&sk->sk_callback_lock);
-	rcu_assign_pointer(sk->sk_wq, parent->wq);
+	sk->sk_wq = parent->wq;
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
 	security_sock_graft(sk, parent);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 8e02550ff3e8..b53b2ebbb198 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6102,15 +6102,16 @@ static void __sctp_write_space(struct sctp_association *asoc)
 			wake_up_interruptible(&asoc->wait);
 
 		if (sctp_writeable(sk)) {
-			if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-				wake_up_interruptible(sk_sleep(sk));
+			wait_queue_head_t *wq = sk_sleep(sk);
+
+			if (wq && waitqueue_active(wq))
+				wake_up_interruptible(wq);
 
 			/* Note that we try to include the Async I/O support
 			 * here by modeling from the current TCP/UDP code.
 			 * We have not tested with it yet.
 			 */
-			if (sock->wq->fasync_list &&
-			    !(sk->sk_shutdown & SEND_SHUTDOWN))
+			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 				sock_wake_async(sock,
 						SOCK_WAKE_SPACE, POLL_OUT);
 		}
diff --git a/net/socket.c b/net/socket.c
index ac2219f90d5d..9fa1e3b4366e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -240,17 +240,19 @@ static struct kmem_cache *sock_inode_cachep __read_mostly;
 static struct inode *sock_alloc_inode(struct super_block *sb)
 {
 	struct socket_alloc *ei;
+	struct socket_wq *wq;
 
 	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
-	ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL);
-	if (!ei->socket.wq) {
+	wq = kmalloc(sizeof(*wq), GFP_KERNEL);
+	if (!wq) {
 		kmem_cache_free(sock_inode_cachep, ei);
 		return NULL;
 	}
-	init_waitqueue_head(&ei->socket.wq->wait);
-	ei->socket.wq->fasync_list = NULL;
+	init_waitqueue_head(&wq->wait);
+	wq->fasync_list = NULL;
+	RCU_INIT_POINTER(ei->socket.wq, wq);
 
 	ei->socket.state = SS_UNCONNECTED;
 	ei->socket.flags = 0;
@@ -273,9 +275,11 @@ static void wq_free_rcu(struct rcu_head *head)
 static void sock_destroy_inode(struct inode *inode)
 {
 	struct socket_alloc *ei;
+	struct socket_wq *wq;
 
 	ei = container_of(inode, struct socket_alloc, vfs_inode);
-	call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
+	wq = rcu_dereference_protected(ei->socket.wq, 1);
+	call_rcu(&wq->rcu, wq_free_rcu);
 	kmem_cache_free(sock_inode_cachep, ei);
 }
 
@@ -524,7 +528,7 @@ void sock_release(struct socket *sock)
 		module_put(owner);
 	}
 
-	if (sock->wq->fasync_list)
+	if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
 		printk(KERN_ERR "sock_release: fasync list not empty!\n");
 
 	percpu_sub(sockets_in_use, 1);
@@ -1108,15 +1112,16 @@ static int sock_fasync(int fd, struct file *filp, int on)
 {
 	struct socket *sock = filp->private_data;
 	struct sock *sk = sock->sk;
+	struct socket_wq *wq;
 
 	if (sk == NULL)
 		return -EINVAL;
 
 	lock_sock(sk);
+	wq = rcu_dereference_protected(sock->wq, sock_owned_by_user(sk));
+	fasync_helper(fd, filp, on, &wq->fasync_list);
 
-	fasync_helper(fd, filp, on, &sock->wq->fasync_list);
-
-	if (!sock->wq->fasync_list)
+	if (!wq->fasync_list)
 		sock_reset_flag(sk, SOCK_FASYNC);
 	else
 		sock_set_flag(sk, SOCK_FASYNC);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index d802e941d365..b7d435c3f19e 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -420,6 +420,7 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 static void svc_udp_data_ready(struct sock *sk, int count)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
+	wait_queue_head_t *wq = sk_sleep(sk);
 
 	if (svsk) {
 		dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n",
@@ -428,8 +429,8 @@ static void svc_udp_data_ready(struct sock *sk, int count)
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible(sk_sleep(sk));
+	if (wq && waitqueue_active(wq))
+		wake_up_interruptible(wq);
 }
 
 /*
@@ -438,6 +439,7 @@ static void svc_udp_data_ready(struct sock *sk, int count)
 static void svc_write_space(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)(sk->sk_user_data);
+	wait_queue_head_t *wq = sk_sleep(sk);
 
 	if (svsk) {
 		dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
@@ -445,10 +447,10 @@ static void svc_write_space(struct sock *sk)
 		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
 
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) {
+	if (wq && waitqueue_active(wq)) {
 		dprintk("RPC svc_write_space: someone sleeping on %p\n",
 		       svsk);
-		wake_up_interruptible(sk_sleep(sk));
+		wake_up_interruptible(wq);
 	}
 }
 
@@ -739,6 +741,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
+	wait_queue_head_t *wq;
 
 	dprintk("svc: socket %p TCP (listen) state change %d\n",
 		sk, sk->sk_state);
@@ -761,8 +764,9 @@ static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
 			printk("svc: socket %p: no user data\n", sk);
 	}
 
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible_all(sk_sleep(sk));
+	wq = sk_sleep(sk);
+	if (wq && waitqueue_active(wq))
+		wake_up_interruptible_all(wq);
 }
 
 /*
@@ -771,6 +775,7 @@ static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
 static void svc_tcp_state_change(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
+	wait_queue_head_t *wq = sk_sleep(sk);
 
 	dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n",
 		sk, sk->sk_state, sk->sk_user_data);
@@ -781,13 +786,14 @@ static void svc_tcp_state_change(struct sock *sk)
 		set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
 		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible_all(sk_sleep(sk));
+	if (wq && waitqueue_active(wq))
+		wake_up_interruptible_all(wq);
 }
 
 static void svc_tcp_data_ready(struct sock *sk, int count)
 {
 	struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
+	wait_queue_head_t *wq = sk_sleep(sk);
 
 	dprintk("svc: socket %p TCP data ready (svsk %p)\n",
 		sk, sk->sk_user_data);
@@ -795,8 +801,8 @@ static void svc_tcp_data_ready(struct sock *sk, int count)
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		svc_xprt_enqueue(&svsk->sk_xprt);
 	}
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible(sk_sleep(sk));
+	if (wq && waitqueue_active(wq))
+		wake_up_interruptible(wq);
 }
 
 /*
@@ -1531,6 +1537,7 @@ static void svc_sock_detach(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
 	struct sock *sk = svsk->sk_sk;
+	wait_queue_head_t *wq;
 
 	dprintk("svc: svc_sock_detach(%p)\n", svsk);
 
@@ -1539,8 +1546,9 @@ static void svc_sock_detach(struct svc_xprt *xprt)
 	sk->sk_data_ready = svsk->sk_odata;
 	sk->sk_write_space = svsk->sk_owspace;
 
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible(sk_sleep(sk));
+	wq = sk_sleep(sk);
+	if (wq && waitqueue_active(wq))
+		wake_up_interruptible(wq);
 }
 
 /*
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d8d98d5b508c..217fb7f34d52 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1171,7 +1171,7 @@ restart:
 	newsk->sk_type		= sk->sk_type;
 	init_peercred(newsk);
 	newu = unix_sk(newsk);
-	newsk->sk_wq		= &newu->peer_wq;
+	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
 	otheru = unix_sk(other);
 
 	/* copy address information from listening to new sock*/
-- 
cgit v1.2.3


From e8a4e37716dbc964e1cd18bca1a62fbd11805c1d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 17:42:56 -0800
Subject: xfrm: Mark flowi arg const in key extraction helpers.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 1f6e8a0eb544..2de3dae3d297 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -790,7 +790,7 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen)
 }
 
 static __inline__
-__be16 xfrm_flowi_sport(struct flowi *fl)
+__be16 xfrm_flowi_sport(const struct flowi *fl)
 {
 	__be16 port;
 	switch(fl->proto) {
@@ -817,7 +817,7 @@ __be16 xfrm_flowi_sport(struct flowi *fl)
 }
 
 static __inline__
-__be16 xfrm_flowi_dport(struct flowi *fl)
+__be16 xfrm_flowi_dport(const struct flowi *fl)
 {
 	__be16 port;
 	switch(fl->proto) {
@@ -1127,7 +1127,7 @@ static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir,
 #endif
 
 static __inline__
-xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family)
+xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family)
 {
 	switch (family){
 	case AF_INET:
@@ -1139,7 +1139,7 @@ xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family)
 }
 
 static __inline__
-xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family)
+xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family)
 {
 	switch (family){
 	case AF_INET:
@@ -1151,7 +1151,7 @@ xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family)
 }
 
 static __inline__
-void xfrm_flowi_addr_get(struct flowi *fl,
+void xfrm_flowi_addr_get(const struct flowi *fl,
 			 xfrm_address_t *saddr, xfrm_address_t *daddr,
 			 unsigned short family)
 {
@@ -1204,7 +1204,7 @@ xfrm_state_addr_check(struct xfrm_state *x,
 }
 
 static __inline__ int
-xfrm_state_addr_flow_check(struct xfrm_state *x, struct flowi *fl,
+xfrm_state_addr_flow_check(struct xfrm_state *x, const struct flowi *fl,
 			   unsigned short family)
 {
 	switch (family) {
-- 
cgit v1.2.3


From 05d8402576c9c1b85bfc9e4f9d6a21c27ccbd5b1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 17:47:10 -0800
Subject: xfrm: Mark flowi arg to ->get_tos() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h      | 2 +-
 net/ipv4/xfrm4_policy.c | 2 +-
 net/ipv6/xfrm6_policy.c | 2 +-
 net/xfrm/xfrm_policy.c  | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2de3dae3d297..2c0927b04436 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -273,7 +273,7 @@ struct xfrm_policy_afinfo {
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
 						  int reverse);
-	int			(*get_tos)(struct flowi *fl);
+	int			(*get_tos)(const struct flowi *fl);
 	int			(*init_path)(struct xfrm_dst *path,
 					     struct dst_entry *dst,
 					     int nfheader_len);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 19fbdec6baaa..ef12e6830468 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -56,7 +56,7 @@ static int xfrm4_get_saddr(struct net *net,
 	return 0;
 }
 
-static int xfrm4_get_tos(struct flowi *fl)
+static int xfrm4_get_tos(const struct flowi *fl)
 {
 	return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */
 }
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 834dc02f1d4f..753e9a1db379 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -67,7 +67,7 @@ static int xfrm6_get_saddr(struct net *net,
 	return 0;
 }
 
-static int xfrm6_get_tos(struct flowi *fl)
+static int xfrm6_get_tos(const struct flowi *fl)
 {
 	return 0;
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7a8e2c77d08f..f8ccb97b234e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1256,7 +1256,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl,
  * still valid.
  */
 
-static inline int xfrm_get_tos(struct flowi *fl, int family)
+static inline int xfrm_get_tos(const struct flowi *fl, int family)
 {
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
 	int tos;
-- 
cgit v1.2.3


From 0c7b3eefb4ab8df245e94feb0d83c1c3450a3d87 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 17:48:57 -0800
Subject: xfrm: Mark flowi arg to ->fill_dst() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h      | 2 +-
 net/ipv4/xfrm4_policy.c | 2 +-
 net/ipv6/xfrm6_policy.c | 2 +-
 net/xfrm/xfrm_policy.c  | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2c0927b04436..c77407fdfa87 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -279,7 +279,7 @@ struct xfrm_policy_afinfo {
 					     int nfheader_len);
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
-					    struct flowi *fl);
+					    const struct flowi *fl);
 };
 
 extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index ef12e6830468..1e9844d1f8c5 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -68,7 +68,7 @@ static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 }
 
 static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
-			  struct flowi *fl)
+			  const struct flowi *fl)
 {
 	struct rtable *rt = (struct rtable *)xdst->route;
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 753e9a1db379..f2fa904b8a91 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -87,7 +87,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 }
 
 static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
-			  struct flowi *fl)
+			  const struct flowi *fl)
 {
 	struct rt6_info *rt = (struct rt6_info*)xdst->route;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f8ccb97b234e..fa0b7f33874b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1369,7 +1369,7 @@ static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 }
 
 static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
-				struct flowi *fl)
+				const struct flowi *fl)
 {
 	struct xfrm_policy_afinfo *afinfo =
 		xfrm_policy_get_afinfo(xdst->u.dst.ops->family);
-- 
cgit v1.2.3


From 73e5ebb20f2809e2eb0b904448481e010c2599d7 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 17:51:44 -0800
Subject: xfrm: Mark flowi arg to ->init_tempsel() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 3 ++-
 net/ipv4/xfrm4_state.c | 2 +-
 net/ipv6/xfrm6_state.c | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c77407fdfa87..614c296c4532 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -300,7 +300,8 @@ struct xfrm_state_afinfo {
 	const struct xfrm_type	*type_map[IPPROTO_MAX];
 	struct xfrm_mode	*mode_map[XFRM_MODE_MAX];
 	int			(*init_flags)(struct xfrm_state *x);
-	void			(*init_tempsel)(struct xfrm_selector *sel, struct flowi *fl);
+	void			(*init_tempsel)(struct xfrm_selector *sel,
+						const struct flowi *fl);
 	void			(*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
 						xfrm_address_t *daddr, xfrm_address_t *saddr);
 	int			(*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 47947624eccc..19eb56067727 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -21,7 +21,7 @@ static int xfrm4_init_flags(struct xfrm_state *x)
 }
 
 static void
-__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
+__xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 {
 	sel->daddr.a4 = fl->fl4_dst;
 	sel->saddr.a4 = fl->fl4_src;
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index a67575d472a3..68a14c0339db 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -20,7 +20,7 @@
 #include <net/addrconf.h>
 
 static void
-__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
+__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 {
 	/* Initialize temporary selector matching only
 	 * to current session. */
-- 
cgit v1.2.3


From 8f029de281b26ec9fd5cd77294db1d35d9876f1a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 17:59:59 -0800
Subject: xfrm: Mark flowi arg to xfrm_type->reject() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 3 ++-
 net/ipv6/mip6.c        | 3 ++-
 net/xfrm/xfrm_policy.c | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 614c296c4532..cbe00035416d 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -334,7 +334,8 @@ struct xfrm_type {
 	void			(*destructor)(struct xfrm_state *);
 	int			(*input)(struct xfrm_state *, struct sk_buff *skb);
 	int			(*output)(struct xfrm_state *, struct sk_buff *pskb);
-	int			(*reject)(struct xfrm_state *, struct sk_buff *, struct flowi *);
+	int			(*reject)(struct xfrm_state *, struct sk_buff *,
+					  const struct flowi *);
 	int			(*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **);
 	/* Estimate maximal size of result of transformation of a dgram */
 	u32			(*get_mtu)(struct xfrm_state *, int size);
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index d6e9599d0705..f3e3ca938a54 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -203,7 +203,8 @@ static inline int mip6_report_rl_allow(struct timeval *stamp,
 	return allow;
 }
 
-static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl)
+static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
+			       const struct flowi *fl)
 {
 	struct net *net = xs_net(x);
 	struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index fa0b7f33874b..ccd47cf1765c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1907,7 +1907,7 @@ int xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl,
 EXPORT_SYMBOL(xfrm_lookup);
 
 static inline int
-xfrm_secpath_reject(int idx, struct sk_buff *skb, struct flowi *fl)
+xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
 {
 	struct xfrm_state *x;
 
-- 
cgit v1.2.3


From 1744a8fe09e5db7315a57da52fa7c1afa779cfa0 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 18:02:12 -0800
Subject: xfrm: Mark token args to addr_match() const.

Also, make it return a real bool.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index cbe00035416d..2328532f0076 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -765,10 +765,11 @@ static inline void xfrm_state_hold(struct xfrm_state *x)
 	atomic_inc(&x->refcnt);
 }
 
-static __inline__ int addr_match(void *token1, void *token2, int prefixlen)
+static inline bool addr_match(const void *token1, const void *token2,
+			      int prefixlen)
 {
-	__be32 *a1 = token1;
-	__be32 *a2 = token2;
+	const __be32 *a1 = token1;
+	const __be32 *a2 = token2;
 	int pdw;
 	int pbi;
 
@@ -777,7 +778,7 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen)
 
 	if (pdw)
 		if (memcmp(a1, a2, pdw << 2))
-			return 0;
+			return false;
 
 	if (pbi) {
 		__be32 mask;
@@ -785,10 +786,10 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen)
 		mask = htonl((0xffffffff) << (32 - pbi));
 
 		if ((a1[pdw] ^ a2[pdw]) & mask)
-			return 0;
+			return false;
 	}
 
-	return 1;
+	return true;
 }
 
 static __inline__
-- 
cgit v1.2.3


From e1ad2ab2cf0cabcd81861e2c61870fc27bb27ded Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 18:07:39 -0800
Subject: xfrm: Mark flowi arg to xfrm_selector_match() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 3 ++-
 net/xfrm/xfrm_policy.c | 8 ++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2328532f0076..b965ad795b60 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -843,7 +843,8 @@ __be16 xfrm_flowi_dport(const struct flowi *fl)
 	return port;
 }
 
-extern int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl,
+extern int xfrm_selector_match(struct xfrm_selector *sel,
+			       const struct flowi *fl,
 			       unsigned short family);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index ccd47cf1765c..71e6dc25bc5c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -58,7 +58,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
 static inline int
-__xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl)
+__xfrm4_selector_match(struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
@@ -69,7 +69,7 @@ __xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl)
 }
 
 static inline int
-__xfrm6_selector_match(struct xfrm_selector *sel, struct flowi *fl)
+__xfrm6_selector_match(struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
@@ -79,8 +79,8 @@ __xfrm6_selector_match(struct xfrm_selector *sel, struct flowi *fl)
 		(fl->oif == sel->ifindex || !sel->ifindex);
 }
 
-int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl,
-		    unsigned short family)
+int xfrm_selector_match(struct xfrm_selector *sel, const struct flowi *fl,
+			unsigned short family)
 {
 	switch (family) {
 	case AF_INET:
-- 
cgit v1.2.3


From e33f770426674a565a188042caf3f974f8b3722d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 18:13:15 -0800
Subject: xfrm: Mark flowi arg to security_xfrm_state_pol_flow_match() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/security.h        | 7 ++++---
 security/capability.c           | 2 +-
 security/security.c             | 3 ++-
 security/selinux/include/xfrm.h | 2 +-
 security/selinux/xfrm.c         | 2 +-
 5 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index b2b7f9749f5e..9b5f184a7f65 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1623,7 +1623,7 @@ struct security_operations {
 	int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
 	int (*xfrm_state_pol_flow_match) (struct xfrm_state *x,
 					  struct xfrm_policy *xp,
-					  struct flowi *fl);
+					  const struct flowi *fl);
 	int (*xfrm_decode_session) (struct sk_buff *skb, u32 *secid, int ckall);
 #endif	/* CONFIG_SECURITY_NETWORK_XFRM */
 
@@ -2761,7 +2761,8 @@ int security_xfrm_state_delete(struct xfrm_state *x);
 void security_xfrm_state_free(struct xfrm_state *x);
 int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
 int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
-				       struct xfrm_policy *xp, struct flowi *fl);
+				       struct xfrm_policy *xp,
+				       const struct flowi *fl);
 int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid);
 void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl);
 
@@ -2813,7 +2814,7 @@ static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_s
 }
 
 static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
-			struct xfrm_policy *xp, struct flowi *fl)
+			struct xfrm_policy *xp, const struct flowi *fl)
 {
 	return 1;
 }
diff --git a/security/capability.c b/security/capability.c
index 2a5df2b7da83..b8eeaee5c99e 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -760,7 +760,7 @@ static int cap_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 sk_sid, u8 dir)
 
 static int cap_xfrm_state_pol_flow_match(struct xfrm_state *x,
 					 struct xfrm_policy *xp,
-					 struct flowi *fl)
+					 const struct flowi *fl)
 {
 	return 1;
 }
diff --git a/security/security.c b/security/security.c
index 7b7308ace8c5..8ef1f7dff277 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1233,7 +1233,8 @@ int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
 }
 
 int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
-				       struct xfrm_policy *xp, struct flowi *fl)
+				       struct xfrm_policy *xp,
+				       const struct flowi *fl)
 {
 	return security_ops->xfrm_state_pol_flow_match(x, xp, fl);
 }
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 13128f9a3e5a..b43813c9e049 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -19,7 +19,7 @@ void selinux_xfrm_state_free(struct xfrm_state *x);
 int selinux_xfrm_state_delete(struct xfrm_state *x);
 int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
 int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
-			struct xfrm_policy *xp, struct flowi *fl);
+			struct xfrm_policy *xp, const struct flowi *fl);
 
 /*
  * Extract the security blob from the sock (it's actually on the socket)
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index fff78d3b51a2..c43ab542246c 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -112,7 +112,7 @@ int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
  */
 
 int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp,
-			struct flowi *fl)
+			const struct flowi *fl)
 {
 	u32 state_sid;
 	int rc;
-- 
cgit v1.2.3


From b520e9f616f4f29c8d2557ba704b74ce6d79ff07 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 18:24:19 -0800
Subject: xfrm: Mark flowi arg to xfrm_state_find() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h    | 6 ++++--
 net/xfrm/xfrm_state.c | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b965ad795b60..bb824a5d71bf 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1328,8 +1328,10 @@ extern int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 			   int (*func)(struct xfrm_state *, int, void*), void *);
 extern void xfrm_state_walk_done(struct xfrm_state_walk *walk);
 extern struct xfrm_state *xfrm_state_alloc(struct net *net);
-extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, 
-					  struct flowi *fl, struct xfrm_tmpl *tmpl,
+extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr,
+					  xfrm_address_t *saddr, 
+					  const struct flowi *fl,
+					  struct xfrm_tmpl *tmpl,
 					  struct xfrm_policy *pol, int *err,
 					  unsigned short family);
 extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark,
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 674f2780cedd..30a0f178819c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -785,7 +785,7 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 
 struct xfrm_state *
 xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
-		struct flowi *fl, struct xfrm_tmpl *tmpl,
+		const struct flowi *fl, struct xfrm_tmpl *tmpl,
 		struct xfrm_policy *pol, int *err,
 		unsigned short family)
 {
-- 
cgit v1.2.3


From 0730b9a1504cb76f80c97d90ff82f8daeb1243a3 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 18:27:22 -0800
Subject: net: Mark flowi arg to flow_cache_uli_match() const.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 1ae901f24436..f4270d4b22c3 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -112,7 +112,8 @@ extern struct flow_cache_object *flow_cache_lookup(
 extern void flow_cache_flush(void);
 extern atomic_t flow_cache_genid;
 
-static inline int flow_cache_uli_match(struct flowi *fl1, struct flowi *fl2)
+static inline int flow_cache_uli_match(const struct flowi *fl1,
+				       const struct flowi *fl2)
 {
 	return (fl1->proto == fl2->proto &&
 		!memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u)));
-- 
cgit v1.2.3


From dee9f4bceb5fd9dbfcc1567148fccdbf16d6a38a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 22 Feb 2011 18:44:31 -0800
Subject: net: Make flow cache paths use a const struct flowi.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h      | 10 ++++++----
 include/net/flow.h     |  4 ++--
 net/core/flow.c        | 14 +++++++-------
 net/xfrm/xfrm_policy.c | 13 ++++++++-----
 4 files changed, 23 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 23b564d3e110..4fedffd7c56f 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -428,20 +428,22 @@ enum {
 struct flowi;
 #ifndef CONFIG_XFRM
 static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-			      struct flowi *fl, struct sock *sk, int flags)
+			      const struct flowi *fl, struct sock *sk,
+			      int flags)
 {
 	return 0;
 } 
 static inline int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-				struct flowi *fl, struct sock *sk, int flags)
+				const struct flowi *fl, struct sock *sk,
+				int flags)
 {
 	return 0;
 }
 #else
 extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-		       struct flowi *fl, struct sock *sk, int flags);
+		       const struct flowi *fl, struct sock *sk, int flags);
 extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-			 struct flowi *fl, struct sock *sk, int flags);
+			 const struct flowi *fl, struct sock *sk, int flags);
 #endif
 #endif
 
diff --git a/include/net/flow.h b/include/net/flow.h
index f4270d4b22c3..f2080e65276d 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -102,11 +102,11 @@ struct flow_cache_ops {
 };
 
 typedef struct flow_cache_object *(*flow_resolve_t)(
-		struct net *net, struct flowi *key, u16 family,
+		struct net *net, const struct flowi *key, u16 family,
 		u8 dir, struct flow_cache_object *oldobj, void *ctx);
 
 extern struct flow_cache_object *flow_cache_lookup(
-		struct net *net, struct flowi *key, u16 family,
+		struct net *net, const struct flowi *key, u16 family,
 		u8 dir, flow_resolve_t resolver, void *ctx);
 
 extern void flow_cache_flush(void);
diff --git a/net/core/flow.c b/net/core/flow.c
index 127c8a7ffd61..990703b8863b 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -172,9 +172,9 @@ static void flow_new_hash_rnd(struct flow_cache *fc,
 
 static u32 flow_hash_code(struct flow_cache *fc,
 			  struct flow_cache_percpu *fcp,
-			  struct flowi *key)
+			  const struct flowi *key)
 {
-	u32 *k = (u32 *) key;
+	const u32 *k = (const u32 *) key;
 
 	return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd)
 		& (flow_cache_hash_size(fc) - 1);
@@ -186,17 +186,17 @@ typedef unsigned long flow_compare_t;
  * important assumptions that we can here, such as alignment and
  * constant size.
  */
-static int flow_key_compare(struct flowi *key1, struct flowi *key2)
+static int flow_key_compare(const struct flowi *key1, const struct flowi *key2)
 {
-	flow_compare_t *k1, *k1_lim, *k2;
+	const flow_compare_t *k1, *k1_lim, *k2;
 	const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t);
 
 	BUILD_BUG_ON(sizeof(struct flowi) % sizeof(flow_compare_t));
 
-	k1 = (flow_compare_t *) key1;
+	k1 = (const flow_compare_t *) key1;
 	k1_lim = k1 + n_elem;
 
-	k2 = (flow_compare_t *) key2;
+	k2 = (const flow_compare_t *) key2;
 
 	do {
 		if (*k1++ != *k2++)
@@ -207,7 +207,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2)
 }
 
 struct flow_cache_object *
-flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir,
+flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 		  flow_resolve_t resolver, void *ctx)
 {
 	struct flow_cache *fc = &flow_cache_global;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index ef899a8e33ce..28c865adf609 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -954,7 +954,7 @@ __xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir
 }
 
 static struct flow_cache_object *
-xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
+xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family,
 		   u8 dir, struct flow_cache_object *old_obj, void *ctx)
 {
 	struct xfrm_policy *pol;
@@ -990,7 +990,8 @@ static inline int policy_to_flow_dir(int dir)
 	}
 }
 
-static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl)
+static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
+						 const struct flowi *fl)
 {
 	struct xfrm_policy *pol;
 
@@ -1629,7 +1630,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 }
 
 static struct flow_cache_object *
-xfrm_bundle_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir,
+xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 		   struct flow_cache_object *oldflo, void *ctx)
 {
 	struct dst_entry *dst_orig = (struct dst_entry *)ctx;
@@ -1733,7 +1734,8 @@ error:
  * At the moment we eat a raw IP route. Mostly to speed up lookups
  * on interfaces with disabled IPsec.
  */
-int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl,
+int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
+		  const struct flowi *fl,
 		  struct sock *sk, int flags)
 {
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
@@ -1889,7 +1891,8 @@ dropdst:
 }
 EXPORT_SYMBOL(__xfrm_lookup);
 
-int xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl,
+int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
+		const struct flowi *fl,
 		struct sock *sk, int flags)
 {
 	int err = __xfrm_lookup(net, dst_p, fl, sk, flags);
-- 
cgit v1.2.3


From 008536e8458613ce569595e43b0e71afa8b48ae8 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 19 Feb 2011 15:45:29 -0800
Subject: connector: Convert char *name to const char *name

Allow more const declarations.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/connector/cn_queue.c  | 7 ++++---
 drivers/connector/connector.c | 2 +-
 include/linux/connector.h     | 9 ++++++---
 3 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c
index 81270d221e5a..55653aba6735 100644
--- a/drivers/connector/cn_queue.c
+++ b/drivers/connector/cn_queue.c
@@ -48,7 +48,7 @@ void cn_queue_wrapper(struct work_struct *work)
 }
 
 static struct cn_callback_entry *
-cn_queue_alloc_callback_entry(char *name, struct cb_id *id,
+cn_queue_alloc_callback_entry(const char *name, struct cb_id *id,
 			      void (*callback)(struct cn_msg *, struct netlink_skb_parms *))
 {
 	struct cn_callback_entry *cbq;
@@ -78,7 +78,8 @@ int cn_cb_equal(struct cb_id *i1, struct cb_id *i2)
 	return ((i1->idx == i2->idx) && (i1->val == i2->val));
 }
 
-int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id,
+int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
+			  struct cb_id *id,
 			  void (*callback)(struct cn_msg *, struct netlink_skb_parms *))
 {
 	struct cn_callback_entry *cbq, *__cbq;
@@ -135,7 +136,7 @@ void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id)
 	}
 }
 
-struct cn_queue_dev *cn_queue_alloc_dev(char *name, struct sock *nls)
+struct cn_queue_dev *cn_queue_alloc_dev(const char *name, struct sock *nls)
 {
 	struct cn_queue_dev *dev;
 
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 05117f1ad867..f7554de3be5e 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -205,7 +205,7 @@ static void cn_rx_skb(struct sk_buff *__skb)
  *
  * May sleep.
  */
-int cn_add_callback(struct cb_id *id, char *name,
+int cn_add_callback(struct cb_id *id, const char *name,
 		    void (*callback)(struct cn_msg *, struct netlink_skb_parms *))
 {
 	int err;
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 2e9759cdd275..bcafc942e5e4 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -129,14 +129,17 @@ struct cn_dev {
 	struct cn_queue_dev *cbdev;
 };
 
-int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *, struct netlink_skb_parms *));
+int cn_add_callback(struct cb_id *id, const char *name,
+		    void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
 void cn_del_callback(struct cb_id *);
 int cn_netlink_send(struct cn_msg *, u32, gfp_t);
 
-int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
+int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
+			  struct cb_id *id,
+			  void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
 void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id);
 
-struct cn_queue_dev *cn_queue_alloc_dev(char *name, struct sock *);
+struct cn_queue_dev *cn_queue_alloc_dev(const char *name, struct sock *);
 void cn_queue_free_dev(struct cn_queue_dev *dev);
 
 int cn_cb_equal(struct cb_id *, struct cb_id *);
-- 
cgit v1.2.3


From 6ebacbb79d2d05978ba50a24d8cbe2a76ff2014c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 23 Feb 2011 15:06:08 +0100
Subject: mac80211: rename RX_FLAG_TSFT

The flag isn't very descriptive -- the intention
is that the driver provides a TSF timestamp at
the beginning of the MPDU -- make that clearer
by renaming the flag to RX_FLAG_MACTIME_MPDU.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/ath/ath5k/base.c         | 2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_txrx.c | 2 +-
 drivers/net/wireless/ath/ath9k/recv.c         | 2 +-
 drivers/net/wireless/b43/xmit.c               | 2 +-
 drivers/net/wireless/b43legacy/xmit.c         | 2 +-
 drivers/net/wireless/iwlegacy/iwl-4965-lib.c  | 2 +-
 drivers/net/wireless/iwlwifi/iwl-agn-lib.c    | 2 +-
 drivers/net/wireless/p54/txrx.c               | 2 +-
 drivers/net/wireless/rtl818x/rtl8180/dev.c    | 2 +-
 drivers/net/wireless/rtl818x/rtl8187/dev.c    | 2 +-
 drivers/net/wireless/rtlwifi/rtl8192ce/trx.c  | 2 +-
 drivers/net/wireless/rtlwifi/rtl8192cu/trx.c  | 2 +-
 drivers/net/wireless/wl1251/rx.c              | 2 +-
 drivers/staging/brcm80211/sys/wlc_mac80211.c  | 5 ++++-
 include/net/mac80211.h                        | 9 +++++----
 net/mac80211/ibss.c                           | 2 +-
 net/mac80211/rx.c                             | 4 ++--
 17 files changed, 25 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index dbc45e085434..80d9cf0c4cd2 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -1361,7 +1361,7 @@ ath5k_receive_frame(struct ath5k_softc *sc, struct sk_buff *skb,
 	 * right now, so it's not too bad...
 	 */
 	rxs->mactime = ath5k_extend_tsf(sc->ah, rs->rs_tstamp);
-	rxs->flag |= RX_FLAG_TSFT;
+	rxs->flag |= RX_FLAG_MACTIME_MPDU;
 
 	rxs->freq = sc->curchan->center_freq;
 	rxs->band = sc->curchan->band;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 564ac13596f1..4a4f27ba96af 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -616,7 +616,7 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 	rx_status->freq = hw->conf.channel->center_freq;
 	rx_status->signal =  rxbuf->rxstatus.rs_rssi + ATH_DEFAULT_NOISE_FLOOR;
 	rx_status->antenna = rxbuf->rxstatus.rs_antenna;
-	rx_status->flag |= RX_FLAG_TSFT;
+	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
 
 	return true;
 
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index daf171d2f610..cb559e345b86 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -983,7 +983,7 @@ static int ath9k_rx_skb_preprocess(struct ath_common *common,
 	rx_status->freq = hw->conf.channel->center_freq;
 	rx_status->signal = ATH_DEFAULT_NOISE_FLOOR + rx_stats->rs_rssi;
 	rx_status->antenna = rx_stats->rs_antenna;
-	rx_status->flag |= RX_FLAG_TSFT;
+	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index e6b0528f3b52..ad605bcdd40e 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -652,7 +652,7 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		status.mactime += mactime;
 		if (low_mactime_now <= mactime)
 			status.mactime -= 0x10000;
-		status.flag |= RX_FLAG_TSFT;
+		status.flag |= RX_FLAG_MACTIME_MPDU;
 	}
 
 	chanid = (chanstat & B43_RX_CHAN_ID) >> B43_RX_CHAN_ID_SHIFT;
diff --git a/drivers/net/wireless/b43legacy/xmit.c b/drivers/net/wireless/b43legacy/xmit.c
index 7d177d97f1f7..3a95541708a6 100644
--- a/drivers/net/wireless/b43legacy/xmit.c
+++ b/drivers/net/wireless/b43legacy/xmit.c
@@ -572,7 +572,7 @@ void b43legacy_rx(struct b43legacy_wldev *dev,
 		status.mactime += mactime;
 		if (low_mactime_now <= mactime)
 			status.mactime -= 0x10000;
-		status.flag |= RX_FLAG_TSFT;
+		status.flag |= RX_FLAG_MACTIME_MPDU;
 	}
 
 	chanid = (chanstat & B43legacy_RX_CHAN_ID) >>
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
index c1a24946715e..bd9618a4269d 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
@@ -639,7 +639,7 @@ void iwl4965_rx_reply_rx(struct iwl_priv *priv,
 
 	/* TSF isn't reliable. In order to allow smooth user experience,
 	 * this W/A doesn't propagate it to the mac80211 */
-	/*rx_status.flag |= RX_FLAG_TSFT;*/
+	/*rx_status.flag |= RX_FLAG_MACTIME_MPDU;*/
 
 	priv->ucode_beacon_time = le32_to_cpu(phy_res->beacon_time_stamp);
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
index 325ff5c89ee8..0d0572ca7e77 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
@@ -1173,7 +1173,7 @@ void iwlagn_rx_reply_rx(struct iwl_priv *priv,
 
 	/* TSF isn't reliable. In order to allow smooth user experience,
 	 * this W/A doesn't propagate it to the mac80211 */
-	/*rx_status.flag |= RX_FLAG_TSFT;*/
+	/*rx_status.flag |= RX_FLAG_MACTIME_MPDU;*/
 
 	priv->ucode_beacon_time = le32_to_cpu(phy_res->beacon_time_stamp);
 
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index 917d5d948e3c..a408ff333920 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -367,7 +367,7 @@ static int p54_rx_data(struct p54_common *priv, struct sk_buff *skb)
 	rx_status->mactime = ((u64)priv->tsf_high32) << 32 | tsf32;
 	priv->tsf_low32 = tsf32;
 
-	rx_status->flag |= RX_FLAG_TSFT;
+	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
 
 	if (hdr->flags & cpu_to_le16(P54_HDR_FLAG_DATA_ALIGN))
 		header_len += hdr->align[0];
diff --git a/drivers/net/wireless/rtl818x/rtl8180/dev.c b/drivers/net/wireless/rtl818x/rtl8180/dev.c
index 5851cbc1e957..b85debb4f7b1 100644
--- a/drivers/net/wireless/rtl818x/rtl8180/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8180/dev.c
@@ -146,7 +146,7 @@ static void rtl8180_handle_rx(struct ieee80211_hw *dev)
 			rx_status.freq = dev->conf.channel->center_freq;
 			rx_status.band = dev->conf.channel->band;
 			rx_status.mactime = le64_to_cpu(entry->tsft);
-			rx_status.flag |= RX_FLAG_TSFT;
+			rx_status.flag |= RX_FLAG_MACTIME_MPDU;
 			if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 				rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 
diff --git a/drivers/net/wireless/rtl818x/rtl8187/dev.c b/drivers/net/wireless/rtl818x/rtl8187/dev.c
index 6b82cac37ee3..1f5df12cb156 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8187/dev.c
@@ -373,7 +373,7 @@ static void rtl8187_rx_cb(struct urb *urb)
 	rx_status.rate_idx = rate;
 	rx_status.freq = dev->conf.channel->center_freq;
 	rx_status.band = dev->conf.channel->band;
-	rx_status.flag |= RX_FLAG_TSFT;
+	rx_status.flag |= RX_FLAG_MACTIME_MPDU;
 	if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 		rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
index 01b95427fee0..8a67372f71fb 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
@@ -691,7 +691,7 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw,
 	if (GET_RX_DESC_RXHT(pdesc))
 		rx_status->flag |= RX_FLAG_HT;
 
-	rx_status->flag |= RX_FLAG_TSFT;
+	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
 
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
index 9855c3e0a4b2..659e0ca95c64 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
@@ -334,7 +334,7 @@ bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
 		rx_status->flag |= RX_FLAG_40MHZ;
 	if (GET_RX_DESC_RX_HT(pdesc))
 		rx_status->flag |= RX_FLAG_HT;
-	rx_status->flag |= RX_FLAG_TSFT;
+	rx_status->flag |= RX_FLAG_MACTIME_MPDU;
 	if (stats->decrypted)
 		rx_status->flag |= RX_FLAG_DECRYPTED;
 	rx_status->rate_idx = _rtl92c_rate_mapping(hw,
diff --git a/drivers/net/wireless/wl1251/rx.c b/drivers/net/wireless/wl1251/rx.c
index b659e15c78df..c1b3b3f03da2 100644
--- a/drivers/net/wireless/wl1251/rx.c
+++ b/drivers/net/wireless/wl1251/rx.c
@@ -81,7 +81,7 @@ static void wl1251_rx_status(struct wl1251 *wl,
 	status->freq = ieee80211_channel_to_frequency(desc->channel,
 						      status->band);
 
-	status->flag |= RX_FLAG_TSFT;
+	status->flag |= RX_FLAG_MACTIME_MPDU;
 
 	if (desc->flags & RX_DESC_ENCRYPTION_MASK) {
 		status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED;
diff --git a/drivers/staging/brcm80211/sys/wlc_mac80211.c b/drivers/staging/brcm80211/sys/wlc_mac80211.c
index 1d5d01ac0a9b..f305bf948617 100644
--- a/drivers/staging/brcm80211/sys/wlc_mac80211.c
+++ b/drivers/staging/brcm80211/sys/wlc_mac80211.c
@@ -6819,11 +6819,14 @@ prep_mac80211_status(struct wlc_info *wlc, d11rxhdr_t *rxh, struct sk_buff *p,
 	ratespec_t rspec;
 	unsigned char *plcp;
 
+#if 0
+	/* Clearly, this is bogus -- reading the TSF now is wrong */
 	wlc_read_tsf(wlc, &tsf_l, &tsf_h);	/* mactime */
 	rx_status->mactime = tsf_h;
 	rx_status->mactime <<= 32;
 	rx_status->mactime |= tsf_l;
-	rx_status->flag |= RX_FLAG_TSFT;
+	rx_status->flag |= RX_FLAG_MACTIME_MPDU; /* clearly wrong */
+#endif
 
 	channel = WLC_CHAN_CHANNEL(rxh->RxChan);
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8fcd1691cfb7..a13c8d8fca5c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -599,9 +599,10 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	the frame.
  * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on
  *	the frame.
- * @RX_FLAG_TSFT: The timestamp passed in the RX status (@mactime field)
- *	is valid. This is useful in monitor mode and necessary for beacon frames
- *	to enable IBSS merging.
+ * @RX_FLAG_MACTIME_MPDU: The timestamp passed in the RX status (@mactime
+ *	field) is valid and contains the time the first symbol of the MPDU
+ *	was received. This is useful in monitor mode and for proper IBSS
+ *	merging.
  * @RX_FLAG_SHORTPRE: Short preamble was used for this frame
  * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index
  * @RX_FLAG_40MHZ: HT40 (40 MHz) was used
@@ -614,7 +615,7 @@ enum mac80211_rx_flags {
 	RX_FLAG_IV_STRIPPED	= 1<<4,
 	RX_FLAG_FAILED_FCS_CRC	= 1<<5,
 	RX_FLAG_FAILED_PLCP_CRC = 1<<6,
-	RX_FLAG_TSFT		= 1<<7,
+	RX_FLAG_MACTIME_MPDU	= 1<<7,
 	RX_FLAG_SHORTPRE	= 1<<8,
 	RX_FLAG_HT		= 1<<9,
 	RX_FLAG_40MHZ		= 1<<10,
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index a42aa61269ea..463271f9492e 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -355,7 +355,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	if (memcmp(cbss->bssid, sdata->u.ibss.bssid, ETH_ALEN) == 0)
 		goto put_bss;
 
-	if (rx_status->flag & RX_FLAG_TSFT) {
+	if (rx_status->flag & RX_FLAG_MACTIME_MPDU) {
 		/*
 		 * For correct IBSS merging we need mactime; since mactime is
 		 * defined as the time the first data symbol of the frame hits
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index f502634d43af..5b534235d6be 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -77,7 +77,7 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local,
 	/* always present fields */
 	len = sizeof(struct ieee80211_radiotap_header) + 9;
 
-	if (status->flag & RX_FLAG_TSFT)
+	if (status->flag & RX_FLAG_MACTIME_MPDU)
 		len += 8;
 	if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
 		len += 1;
@@ -123,7 +123,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	/* the order of the following fields is important */
 
 	/* IEEE80211_RADIOTAP_TSFT */
-	if (status->flag & RX_FLAG_TSFT) {
+	if (status->flag & RX_FLAG_MACTIME_MPDU) {
 		put_unaligned_le64(status->mactime, pos);
 		rthdr->it_present |=
 			cpu_to_le32(1 << IEEE80211_RADIOTAP_TSFT);
-- 
cgit v1.2.3


From 3bcbaf6e08d8d82cde781997bd2c56dda87049b5 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 22 Feb 2011 21:07:46 +0100
Subject: rtc: cmos: Add OF bindings

This allows to load the OF driver based informations from the device
tree. Systems without BIOS may need to perform some initialization.
PowerPC creates a PNP device from the OF information and performs this
kind of initialization in their private PCI quirk. This looks more
generic.

This patch also avoids registering the platform RTC driver on X86 if
we have a device tree blob. Otherwise we would setup the device based
on the hardcoded information in arch/x86 rather than the device tree
based one.

[ tglx: Changed "int of_have_populated_dt()" to bool as recommended by
        Grant ]

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Dirk Brandewie <dirk.brandewie@gmail.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Cc: sodaville@linutronix.de
Cc: devicetree-discuss@lists.ozlabs.org
Cc: rtc-linux@googlegroups.com
Cc: Alessandro Zummo <a.zummo@towertech.it>
LKML-Reference: <1298405266-1624-12-git-send-email-bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/devicetree/bindings/rtc/rtc-cmos.txt | 28 ++++++++++++++
 arch/x86/kernel/rtc.c                              |  3 ++
 drivers/rtc/rtc-cmos.c                             | 45 ++++++++++++++++++++++
 include/linux/of.h                                 | 12 ++++++
 4 files changed, 88 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/rtc/rtc-cmos.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
new file mode 100644
index 000000000000..7382989b3052
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
@@ -0,0 +1,28 @@
+ Motorola mc146818 compatible RTC
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Required properties:
+  - compatible : "motorola,mc146818"
+  - reg : should contain registers location and length.
+
+Optional properties:
+  - interrupts : should contain interrupt.
+  - interrupt-parent : interrupt source phandle.
+  - ctrl-reg : Contains the initial value of the control register also
+    called "Register B".
+  - freq-reg : Contains the initial value of the frequency register also
+    called "Regsiter A".
+
+"Register A" and "B" are usually initialized by the firmware (BIOS for
+instance). If this is not done, it can be performed by the driver.
+
+ISA Example:
+
+	rtc@70 {
+	         compatible = "motorola,mc146818";
+	         interrupts = <8 3>;
+	         interrupt-parent = <&ioapic1>;
+	         ctrl-reg = <2>;
+	         freq-reg = <0x26>;
+	         reg = <1 0x70 2>;
+	 };
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 6f39cab052d5..3f2ad2640d85 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -6,6 +6,7 @@
 #include <linux/acpi.h>
 #include <linux/bcd.h>
 #include <linux/pnp.h>
+#include <linux/of.h>
 
 #include <asm/vsyscall.h>
 #include <asm/x86_init.h>
@@ -236,6 +237,8 @@ static __init int add_rtc_cmos(void)
 		}
 	}
 #endif
+	if (of_have_populated_dt())
+		return 0;
 
 	platform_device_register(&rtc_device);
 	dev_info(&rtc_device.dev,
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index c7ff8df347e7..159b95e4b420 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -37,6 +37,8 @@
 #include <linux/mod_devicetable.h>
 #include <linux/log2.h>
 #include <linux/pm.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
 
 /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
 #include <asm-generic/rtc.h>
@@ -1123,6 +1125,47 @@ static struct pnp_driver cmos_pnp_driver = {
 
 #endif	/* CONFIG_PNP */
 
+#ifdef CONFIG_OF
+static const struct of_device_id of_cmos_match[] = {
+	{
+		.compatible = "motorola,mc146818",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, of_cmos_match);
+
+static __init void cmos_of_init(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct rtc_time time;
+	int ret;
+	const __be32 *val;
+
+	if (!node)
+		return;
+
+	val = of_get_property(node, "ctrl-reg", NULL);
+	if (val)
+		CMOS_WRITE(be32_to_cpup(val), RTC_CONTROL);
+
+	val = of_get_property(node, "freq-reg", NULL);
+	if (val)
+		CMOS_WRITE(be32_to_cpup(val), RTC_FREQ_SELECT);
+
+	get_rtc_time(&time);
+	ret = rtc_valid_tm(&time);
+	if (ret) {
+		struct rtc_time def_time = {
+			.tm_year = 1,
+			.tm_mday = 1,
+		};
+		set_rtc_time(&def_time);
+	}
+}
+#else
+static inline void cmos_of_init(struct platform_device *pdev) {}
+#define of_cmos_match NULL
+#endif
 /*----------------------------------------------------------------*/
 
 /* Platform setup should have set up an RTC device, when PNP is
@@ -1131,6 +1174,7 @@ static struct pnp_driver cmos_pnp_driver = {
 
 static int __init cmos_platform_probe(struct platform_device *pdev)
 {
+	cmos_of_init(pdev);
 	cmos_wake_setup(&pdev->dev);
 	return cmos_do_probe(&pdev->dev,
 			platform_get_resource(pdev, IORESOURCE_IO, 0),
@@ -1162,6 +1206,7 @@ static struct platform_driver cmos_platform_driver = {
 #ifdef CONFIG_PM
 		.pm		= &cmos_pm_ops,
 #endif
+		.of_match_table = of_cmos_match,
 	}
 };
 
diff --git a/include/linux/of.h b/include/linux/of.h
index d9dd664a6a9c..266db1d0baa9 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -70,6 +70,11 @@ extern struct device_node *allnodes;
 extern struct device_node *of_chosen;
 extern rwlock_t devtree_lock;
 
+static inline bool of_have_populated_dt(void)
+{
+	return allnodes != NULL;
+}
+
 static inline bool of_node_is_root(const struct device_node *node)
 {
 	return node && (node->parent == NULL);
@@ -222,5 +227,12 @@ extern void of_attach_node(struct device_node *);
 extern void of_detach_node(struct device_node *);
 #endif
 
+#else
+
+static inline bool of_have_populated_dt(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_OF */
 #endif /* _LINUX_OF_H */
-- 
cgit v1.2.3


From e13e02a3c68d899169c78d9a18689bd73491d59a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 23 Feb 2011 10:56:17 +0000
Subject: net_sched: SFB flow scheduler

This is the Stochastic Fair Blue scheduler, based on work from :

W. Feng, D. Kandlur, D. Saha, K. Shin. Blue: A New Class of Active Queue
Management Algorithms. U. Michigan CSE-TR-387-99, April 1999.

http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf

This implementation is based on work done by Juliusz Chroboczek

General SFB algorithm can be found in figure 14, page 15:

B[l][n] : L x N array of bins (L levels, N bins per level)
enqueue()
Calculate hash function values h{0}, h{1}, .. h{L-1}
Update bins at each level
for i = 0 to L - 1
   if (B[i][h{i}].qlen > bin_size)
      B[i][h{i}].p_mark += p_increment;
   else if (B[i][h{i}].qlen == 0)
      B[i][h{i}].p_mark -= p_decrement;
p_min = min(B[0][h{0}].p_mark ... B[L-1][h{L-1}].p_mark);
if (p_min == 1.0)
    ratelimit();
else
    mark/drop with probabilty p_min;

I did the adaptation of Juliusz code to meet current kernel standards,
and various changes to address previous comments :

http://thread.gmane.org/gmane.linux.network/90225
http://thread.gmane.org/gmane.linux.network/90375

Default flow classifier is the rxhash introduced by RPS in 2.6.35, but
we can use an external flow classifier if wanted.

tc qdisc add dev $DEV parent 1:11 handle 11:  \
        est 0.5sec 2sec sfb limit 128

tc filter add dev $DEV protocol ip parent 11: handle 3 \
        flow hash keys dst divisor 1024

Notes:

1) SFB default child qdisc is pfifo_fast. It can be changed by another
qdisc but a child qdisc MUST not drop a packet previously queued. This
is because SFB needs to handle a dequeued packet in order to maintain
its virtual queue states. pfifo_head_drop or CHOKe should not be used.

2) ECN is enabled by default, unlike RED/CHOKe/GRED

With help from Patrick McHardy & Andi Kleen

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Juliusz Chroboczek <Juliusz.Chroboczek@pps.jussieu.fr>
CC: Stephen Hemminger <shemminger@vyatta.com>
CC: Patrick McHardy <kaber@trash.net>
CC: Andi Kleen <andi@firstfloor.org>
CC: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/pkt_sched.h |  39 +++
 net/sched/Kconfig         |  11 +
 net/sched/Makefile        |   1 +
 net/sched/sch_sfb.c       | 709 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 760 insertions(+)
 create mode 100644 net/sched/sch_sfb.c

(limited to 'include')

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index d4bb6f58c90c..5afee2b238bd 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -522,4 +522,43 @@ struct tc_mqprio_qopt {
 	__u16	offset[TC_QOPT_MAX_QUEUE];
 };
 
+/* SFB */
+
+enum {
+	TCA_SFB_UNSPEC,
+	TCA_SFB_PARMS,
+	__TCA_SFB_MAX,
+};
+
+#define TCA_SFB_MAX (__TCA_SFB_MAX - 1)
+
+/*
+ * Note: increment, decrement are Q0.16 fixed-point values.
+ */
+struct tc_sfb_qopt {
+	__u32 rehash_interval;	/* delay between hash move, in ms */
+	__u32 warmup_time;	/* double buffering warmup time in ms (warmup_time < rehash_interval) */
+	__u32 max;		/* max len of qlen_min */
+	__u32 bin_size;		/* maximum queue length per bin */
+	__u32 increment;	/* probability increment, (d1 in Blue) */
+	__u32 decrement;	/* probability decrement, (d2 in Blue) */
+	__u32 limit;		/* max SFB queue length */
+	__u32 penalty_rate;	/* inelastic flows are rate limited to 'rate' pps */
+	__u32 penalty_burst;
+};
+
+struct tc_sfb_xstats {
+	__u32 earlydrop;
+	__u32 penaltydrop;
+	__u32 bucketdrop;
+	__u32 queuedrop;
+	__u32 childdrop; /* drops in child qdisc */
+	__u32 marked;
+	__u32 maxqlen;
+	__u32 maxprob;
+	__u32 avgprob;
+};
+
+#define SFB_MAX_PROB 0xFFFF
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 8c19b6e3201e..a7a5583d4f68 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -126,6 +126,17 @@ config NET_SCH_RED
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_red.
 
+config NET_SCH_SFB
+	tristate "Stochastic Fair Blue (SFB)"
+	---help---
+	  Say Y here if you want to use the Stochastic Fair Blue (SFB)
+	  packet scheduling algorithm.
+
+	  See the top of <file:net/sched/sch_sfb.c> for more details.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_sfb.
+
 config NET_SCH_SFQ
 	tristate "Stochastic Fairness Queueing (SFQ)"
 	---help---
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 06c6cdfd1948..2e77b8dba22e 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_NET_SCH_RED)	+= sch_red.o
 obj-$(CONFIG_NET_SCH_GRED)	+= sch_gred.o
 obj-$(CONFIG_NET_SCH_INGRESS)	+= sch_ingress.o 
 obj-$(CONFIG_NET_SCH_DSMARK)	+= sch_dsmark.o
+obj-$(CONFIG_NET_SCH_SFB)	+= sch_sfb.o
 obj-$(CONFIG_NET_SCH_SFQ)	+= sch_sfq.o
 obj-$(CONFIG_NET_SCH_TBF)	+= sch_tbf.o
 obj-$(CONFIG_NET_SCH_TEQL)	+= sch_teql.o
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
new file mode 100644
index 000000000000..0a833d0c1f61
--- /dev/null
+++ b/net/sched/sch_sfb.c
@@ -0,0 +1,709 @@
+/*
+ * net/sched/sch_sfb.c	  Stochastic Fair Blue
+ *
+ * Copyright (c) 2008-2011 Juliusz Chroboczek <jch@pps.jussieu.fr>
+ * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * W. Feng, D. Kandlur, D. Saha, K. Shin. Blue:
+ * A New Class of Active Queue Management Algorithms.
+ * U. Michigan CSE-TR-387-99, April 1999.
+ *
+ * http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/random.h>
+#include <linux/jhash.h>
+#include <net/ip.h>
+#include <net/pkt_sched.h>
+#include <net/inet_ecn.h>
+
+/*
+ * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level)
+ * This implementation uses L = 8 and N = 16
+ * This permits us to split one 32bit hash (provided per packet by rxhash or
+ * external classifier) into 8 subhashes of 4 bits.
+ */
+#define SFB_BUCKET_SHIFT 4
+#define SFB_NUMBUCKETS	(1 << SFB_BUCKET_SHIFT) /* N bins per Level */
+#define SFB_BUCKET_MASK (SFB_NUMBUCKETS - 1)
+#define SFB_LEVELS	(32 / SFB_BUCKET_SHIFT) /* L */
+
+/* SFB algo uses a virtual queue, named "bin" */
+struct sfb_bucket {
+	u16		qlen; /* length of virtual queue */
+	u16		p_mark; /* marking probability */
+};
+
+/* We use a double buffering right before hash change
+ * (Section 4.4 of SFB reference : moving hash functions)
+ */
+struct sfb_bins {
+	u32		  perturbation; /* jhash perturbation */
+	struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS];
+};
+
+struct sfb_sched_data {
+	struct Qdisc	*qdisc;
+	struct tcf_proto *filter_list;
+	unsigned long	rehash_interval;
+	unsigned long	warmup_time;	/* double buffering warmup time in jiffies */
+	u32		max;
+	u32		bin_size;	/* maximum queue length per bin */
+	u32		increment;	/* d1 */
+	u32		decrement;	/* d2 */
+	u32		limit;		/* HARD maximal queue length */
+	u32		penalty_rate;
+	u32		penalty_burst;
+	u32		tokens_avail;
+	unsigned long	rehash_time;
+	unsigned long	token_time;
+
+	u8		slot;		/* current active bins (0 or 1) */
+	bool		double_buffering;
+	struct sfb_bins bins[2];
+
+	struct {
+		u32	earlydrop;
+		u32	penaltydrop;
+		u32	bucketdrop;
+		u32	queuedrop;
+		u32	childdrop;	/* drops in child qdisc */
+		u32	marked;		/* ECN mark */
+	} stats;
+};
+
+/*
+ * Each queued skb might be hashed on one or two bins
+ * We store in skb_cb the two hash values.
+ * (A zero value means double buffering was not used)
+ */
+struct sfb_skb_cb {
+	u32 hashes[2];
+};
+
+static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(skb->cb) <
+		sizeof(struct qdisc_skb_cb) + sizeof(struct sfb_skb_cb));
+	return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+/*
+ * If using 'internal' SFB flow classifier, hash comes from skb rxhash
+ * If using external classifier, hash comes from the classid.
+ */
+static u32 sfb_hash(const struct sk_buff *skb, u32 slot)
+{
+	return sfb_skb_cb(skb)->hashes[slot];
+}
+
+/* Probabilities are coded as Q0.16 fixed-point values,
+ * with 0xFFFF representing 65535/65536 (almost 1.0)
+ * Addition and subtraction are saturating in [0, 65535]
+ */
+static u32 prob_plus(u32 p1, u32 p2)
+{
+	u32 res = p1 + p2;
+
+	return min_t(u32, res, SFB_MAX_PROB);
+}
+
+static u32 prob_minus(u32 p1, u32 p2)
+{
+	return p1 > p2 ? p1 - p2 : 0;
+}
+
+static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q)
+{
+	int i;
+	struct sfb_bucket *b = &q->bins[slot].bins[0][0];
+
+	for (i = 0; i < SFB_LEVELS; i++) {
+		u32 hash = sfbhash & SFB_BUCKET_MASK;
+
+		sfbhash >>= SFB_BUCKET_SHIFT;
+		if (b[hash].qlen < 0xFFFF)
+			b[hash].qlen++;
+		b += SFB_NUMBUCKETS; /* next level */
+	}
+}
+
+static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q)
+{
+	u32 sfbhash;
+
+	sfbhash = sfb_hash(skb, 0);
+	if (sfbhash)
+		increment_one_qlen(sfbhash, 0, q);
+
+	sfbhash = sfb_hash(skb, 1);
+	if (sfbhash)
+		increment_one_qlen(sfbhash, 1, q);
+}
+
+static void decrement_one_qlen(u32 sfbhash, u32 slot,
+			       struct sfb_sched_data *q)
+{
+	int i;
+	struct sfb_bucket *b = &q->bins[slot].bins[0][0];
+
+	for (i = 0; i < SFB_LEVELS; i++) {
+		u32 hash = sfbhash & SFB_BUCKET_MASK;
+
+		sfbhash >>= SFB_BUCKET_SHIFT;
+		if (b[hash].qlen > 0)
+			b[hash].qlen--;
+		b += SFB_NUMBUCKETS; /* next level */
+	}
+}
+
+static void decrement_qlen(const struct sk_buff *skb, struct sfb_sched_data *q)
+{
+	u32 sfbhash;
+
+	sfbhash = sfb_hash(skb, 0);
+	if (sfbhash)
+		decrement_one_qlen(sfbhash, 0, q);
+
+	sfbhash = sfb_hash(skb, 1);
+	if (sfbhash)
+		decrement_one_qlen(sfbhash, 1, q);
+}
+
+static void decrement_prob(struct sfb_bucket *b, struct sfb_sched_data *q)
+{
+	b->p_mark = prob_minus(b->p_mark, q->decrement);
+}
+
+static void increment_prob(struct sfb_bucket *b, struct sfb_sched_data *q)
+{
+	b->p_mark = prob_plus(b->p_mark, q->increment);
+}
+
+static void sfb_zero_all_buckets(struct sfb_sched_data *q)
+{
+	memset(&q->bins, 0, sizeof(q->bins));
+}
+
+/*
+ * compute max qlen, max p_mark, and avg p_mark
+ */
+static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_data *q)
+{
+	int i;
+	u32 qlen = 0, prob = 0, totalpm = 0;
+	const struct sfb_bucket *b = &q->bins[q->slot].bins[0][0];
+
+	for (i = 0; i < SFB_LEVELS * SFB_NUMBUCKETS; i++) {
+		if (qlen < b->qlen)
+			qlen = b->qlen;
+		totalpm += b->p_mark;
+		if (prob < b->p_mark)
+			prob = b->p_mark;
+		b++;
+	}
+	*prob_r = prob;
+	*avgpm_r = totalpm / (SFB_LEVELS * SFB_NUMBUCKETS);
+	return qlen;
+}
+
+
+static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q)
+{
+	q->bins[slot].perturbation = net_random();
+}
+
+static void sfb_swap_slot(struct sfb_sched_data *q)
+{
+	sfb_init_perturbation(q->slot, q);
+	q->slot ^= 1;
+	q->double_buffering = false;
+}
+
+/* Non elastic flows are allowed to use part of the bandwidth, expressed
+ * in "penalty_rate" packets per second, with "penalty_burst" burst
+ */
+static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q)
+{
+	if (q->penalty_rate == 0 || q->penalty_burst == 0)
+		return true;
+
+	if (q->tokens_avail < 1) {
+		unsigned long age = min(10UL * HZ, jiffies - q->token_time);
+
+		q->tokens_avail = (age * q->penalty_rate) / HZ;
+		if (q->tokens_avail > q->penalty_burst)
+			q->tokens_avail = q->penalty_burst;
+		q->token_time = jiffies;
+		if (q->tokens_avail < 1)
+			return true;
+	}
+
+	q->tokens_avail--;
+	return false;
+}
+
+static bool sfb_classify(struct sk_buff *skb, struct sfb_sched_data *q,
+			 int *qerr, u32 *salt)
+{
+	struct tcf_result res;
+	int result;
+
+	result = tc_classify(skb, q->filter_list, &res);
+	if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+		switch (result) {
+		case TC_ACT_STOLEN:
+		case TC_ACT_QUEUED:
+			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+		case TC_ACT_SHOT:
+			return false;
+		}
+#endif
+		*salt = TC_H_MIN(res.classid);
+		return true;
+	}
+	return false;
+}
+
+static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child = q->qdisc;
+	int i;
+	u32 p_min = ~0;
+	u32 minqlen = ~0;
+	u32 r, slot, salt, sfbhash;
+	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+
+	if (q->rehash_interval > 0) {
+		unsigned long limit = q->rehash_time + q->rehash_interval;
+
+		if (unlikely(time_after(jiffies, limit))) {
+			sfb_swap_slot(q);
+			q->rehash_time = jiffies;
+		} else if (unlikely(!q->double_buffering && q->warmup_time > 0 &&
+				    time_after(jiffies, limit - q->warmup_time))) {
+			q->double_buffering = true;
+		}
+	}
+
+	if (q->filter_list) {
+		/* If using external classifiers, get result and record it. */
+		if (!sfb_classify(skb, q, &ret, &salt))
+			goto other_drop;
+	} else {
+		salt = skb_get_rxhash(skb);
+	}
+
+	slot = q->slot;
+
+	sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+	if (!sfbhash)
+		sfbhash = 1;
+	sfb_skb_cb(skb)->hashes[slot] = sfbhash;
+
+	for (i = 0; i < SFB_LEVELS; i++) {
+		u32 hash = sfbhash & SFB_BUCKET_MASK;
+		struct sfb_bucket *b = &q->bins[slot].bins[i][hash];
+
+		sfbhash >>= SFB_BUCKET_SHIFT;
+		if (b->qlen == 0)
+			decrement_prob(b, q);
+		else if (b->qlen >= q->bin_size)
+			increment_prob(b, q);
+		if (minqlen > b->qlen)
+			minqlen = b->qlen;
+		if (p_min > b->p_mark)
+			p_min = b->p_mark;
+	}
+
+	slot ^= 1;
+	sfb_skb_cb(skb)->hashes[slot] = 0;
+
+	if (unlikely(minqlen >= q->max || sch->q.qlen >= q->limit)) {
+		sch->qstats.overlimits++;
+		if (minqlen >= q->max)
+			q->stats.bucketdrop++;
+		else
+			q->stats.queuedrop++;
+		goto drop;
+	}
+
+	if (unlikely(p_min >= SFB_MAX_PROB)) {
+		/* Inelastic flow */
+		if (q->double_buffering) {
+			sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+			if (!sfbhash)
+				sfbhash = 1;
+			sfb_skb_cb(skb)->hashes[slot] = sfbhash;
+
+			for (i = 0; i < SFB_LEVELS; i++) {
+				u32 hash = sfbhash & SFB_BUCKET_MASK;
+				struct sfb_bucket *b = &q->bins[slot].bins[i][hash];
+
+				sfbhash >>= SFB_BUCKET_SHIFT;
+				if (b->qlen == 0)
+					decrement_prob(b, q);
+				else if (b->qlen >= q->bin_size)
+					increment_prob(b, q);
+			}
+		}
+		if (sfb_rate_limit(skb, q)) {
+			sch->qstats.overlimits++;
+			q->stats.penaltydrop++;
+			goto drop;
+		}
+		goto enqueue;
+	}
+
+	r = net_random() & SFB_MAX_PROB;
+
+	if (unlikely(r < p_min)) {
+		if (unlikely(p_min > SFB_MAX_PROB / 2)) {
+			/* If we're marking that many packets, then either
+			 * this flow is unresponsive, or we're badly congested.
+			 * In either case, we want to start dropping packets.
+			 */
+			if (r < (p_min - SFB_MAX_PROB / 2) * 2) {
+				q->stats.earlydrop++;
+				goto drop;
+			}
+		}
+		if (INET_ECN_set_ce(skb)) {
+			q->stats.marked++;
+		} else {
+			q->stats.earlydrop++;
+			goto drop;
+		}
+	}
+
+enqueue:
+	ret = qdisc_enqueue(skb, child);
+	if (likely(ret == NET_XMIT_SUCCESS)) {
+		sch->q.qlen++;
+		increment_qlen(skb, q);
+	} else if (net_xmit_drop_count(ret)) {
+		q->stats.childdrop++;
+		sch->qstats.drops++;
+	}
+	return ret;
+
+drop:
+	qdisc_drop(skb, sch);
+	return NET_XMIT_CN;
+other_drop:
+	if (ret & __NET_XMIT_BYPASS)
+		sch->qstats.drops++;
+	kfree_skb(skb);
+	return ret;
+}
+
+static struct sk_buff *sfb_dequeue(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child = q->qdisc;
+	struct sk_buff *skb;
+
+	skb = child->dequeue(q->qdisc);
+
+	if (skb) {
+		qdisc_bstats_update(sch, skb);
+		sch->q.qlen--;
+		decrement_qlen(skb, q);
+	}
+
+	return skb;
+}
+
+static struct sk_buff *sfb_peek(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child = q->qdisc;
+
+	return child->ops->peek(child);
+}
+
+/* No sfb_drop -- impossible since the child doesn't return the dropped skb. */
+
+static void sfb_reset(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	qdisc_reset(q->qdisc);
+	sch->q.qlen = 0;
+	q->slot = 0;
+	q->double_buffering = false;
+	sfb_zero_all_buckets(q);
+	sfb_init_perturbation(0, q);
+}
+
+static void sfb_destroy(struct Qdisc *sch)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	tcf_destroy_chain(&q->filter_list);
+	qdisc_destroy(q->qdisc);
+}
+
+static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = {
+	[TCA_SFB_PARMS]	= { .len = sizeof(struct tc_sfb_qopt) },
+};
+
+static const struct tc_sfb_qopt sfb_default_ops = {
+	.rehash_interval = 600 * MSEC_PER_SEC,
+	.warmup_time = 60 * MSEC_PER_SEC,
+	.limit = 0,
+	.max = 25,
+	.bin_size = 20,
+	.increment = (SFB_MAX_PROB + 500) / 1000, /* 0.1 % */
+	.decrement = (SFB_MAX_PROB + 3000) / 6000,
+	.penalty_rate = 10,
+	.penalty_burst = 20,
+};
+
+static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *child;
+	struct nlattr *tb[TCA_SFB_MAX + 1];
+	const struct tc_sfb_qopt *ctl = &sfb_default_ops;
+	u32 limit;
+	int err;
+
+	if (opt) {
+		err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy);
+		if (err < 0)
+			return -EINVAL;
+
+		if (tb[TCA_SFB_PARMS] == NULL)
+			return -EINVAL;
+
+		ctl = nla_data(tb[TCA_SFB_PARMS]);
+	}
+
+	limit = ctl->limit;
+	if (limit == 0)
+		limit = max_t(u32, qdisc_dev(sch)->tx_queue_len, 1);
+
+	child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit);
+	if (IS_ERR(child))
+		return PTR_ERR(child);
+
+	sch_tree_lock(sch);
+
+	qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+	qdisc_destroy(q->qdisc);
+	q->qdisc = child;
+
+	q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval);
+	q->warmup_time = msecs_to_jiffies(ctl->warmup_time);
+	q->rehash_time = jiffies;
+	q->limit = limit;
+	q->increment = ctl->increment;
+	q->decrement = ctl->decrement;
+	q->max = ctl->max;
+	q->bin_size = ctl->bin_size;
+	q->penalty_rate = ctl->penalty_rate;
+	q->penalty_burst = ctl->penalty_burst;
+	q->tokens_avail = ctl->penalty_burst;
+	q->token_time = jiffies;
+
+	q->slot = 0;
+	q->double_buffering = false;
+	sfb_zero_all_buckets(q);
+	sfb_init_perturbation(0, q);
+	sfb_init_perturbation(1, q);
+
+	sch_tree_unlock(sch);
+
+	return 0;
+}
+
+static int sfb_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	q->qdisc = &noop_qdisc;
+	return sfb_change(sch, opt);
+}
+
+static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+	struct tc_sfb_qopt opt = {
+		.rehash_interval = jiffies_to_msecs(q->rehash_interval),
+		.warmup_time = jiffies_to_msecs(q->warmup_time),
+		.limit = q->limit,
+		.max = q->max,
+		.bin_size = q->bin_size,
+		.increment = q->increment,
+		.decrement = q->decrement,
+		.penalty_rate = q->penalty_rate,
+		.penalty_burst = q->penalty_burst,
+	};
+
+	sch->qstats.backlog = q->qdisc->qstats.backlog;
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	NLA_PUT(skb, TCA_SFB_PARMS, sizeof(opt), &opt);
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -EMSGSIZE;
+}
+
+static int sfb_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+	struct tc_sfb_xstats st = {
+		.earlydrop = q->stats.earlydrop,
+		.penaltydrop = q->stats.penaltydrop,
+		.bucketdrop = q->stats.bucketdrop,
+		.queuedrop = q->stats.queuedrop,
+		.childdrop = q->stats.childdrop,
+		.marked = q->stats.marked,
+	};
+
+	st.maxqlen = sfb_compute_qlen(&st.maxprob, &st.avgprob, q);
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static int sfb_dump_class(struct Qdisc *sch, unsigned long cl,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	return -ENOSYS;
+}
+
+static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
+		     struct Qdisc **old)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	if (new == NULL)
+		new = &noop_qdisc;
+
+	sch_tree_lock(sch);
+	*old = q->qdisc;
+	q->qdisc = new;
+	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
+	qdisc_reset(*old);
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static struct Qdisc *sfb_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	return q->qdisc;
+}
+
+static unsigned long sfb_get(struct Qdisc *sch, u32 classid)
+{
+	return 1;
+}
+
+static void sfb_put(struct Qdisc *sch, unsigned long arg)
+{
+}
+
+static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
+			    struct nlattr **tca, unsigned long *arg)
+{
+	return -ENOSYS;
+}
+
+static int sfb_delete(struct Qdisc *sch, unsigned long cl)
+{
+	return -ENOSYS;
+}
+
+static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker)
+{
+	if (!walker->stop) {
+		if (walker->count >= walker->skip)
+			if (walker->fn(sch, 1, walker) < 0) {
+				walker->stop = 1;
+				return;
+			}
+		walker->count++;
+	}
+}
+
+static struct tcf_proto **sfb_find_tcf(struct Qdisc *sch, unsigned long cl)
+{
+	struct sfb_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return &q->filter_list;
+}
+
+static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent,
+			      u32 classid)
+{
+	return 0;
+}
+
+
+static const struct Qdisc_class_ops sfb_class_ops = {
+	.graft		=	sfb_graft,
+	.leaf		=	sfb_leaf,
+	.get		=	sfb_get,
+	.put		=	sfb_put,
+	.change		=	sfb_change_class,
+	.delete		=	sfb_delete,
+	.walk		=	sfb_walk,
+	.tcf_chain	=	sfb_find_tcf,
+	.bind_tcf	=	sfb_bind,
+	.unbind_tcf	=	sfb_put,
+	.dump		=	sfb_dump_class,
+};
+
+static struct Qdisc_ops sfb_qdisc_ops __read_mostly = {
+	.id		=	"sfb",
+	.priv_size	=	sizeof(struct sfb_sched_data),
+	.cl_ops		=	&sfb_class_ops,
+	.enqueue	=	sfb_enqueue,
+	.dequeue	=	sfb_dequeue,
+	.peek		=	sfb_peek,
+	.init		=	sfb_init,
+	.reset		=	sfb_reset,
+	.destroy	=	sfb_destroy,
+	.change		=	sfb_change,
+	.dump		=	sfb_dump,
+	.dump_stats	=	sfb_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init sfb_module_init(void)
+{
+	return register_qdisc(&sfb_qdisc_ops);
+}
+
+static void __exit sfb_module_exit(void)
+{
+	unregister_qdisc(&sfb_qdisc_ops);
+}
+
+module_init(sfb_module_init)
+module_exit(sfb_module_exit)
+
+MODULE_DESCRIPTION("Stochastic Fair Blue queue discipline");
+MODULE_AUTHOR("Juliusz Chroboczek");
+MODULE_AUTHOR("Eric Dumazet");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From ecc1058aecd986b9f00ba0b4b6ff3681dfb3ab47 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@suse.de>
Date: Wed, 23 Feb 2011 14:12:25 -0800
Subject: Revert "staging: iio: ak8975: add platform data."

This reverts commit f2f1794835f1d8900d2b15d114c54e70c849809b.

It should not be putting code into the include/input/ directory, and
lots of other people have complained about it.

Cc: Tony SIM <chinyeow.sim.xt@renesas.com>
Cc: Andrew Chew <achew@nvidia.com>
Cc: Jonathan Cameron <jic23@cam.ac.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/staging/iio/magnetometer/ak8975.c |  8 +-------
 include/linux/input/ak8975.h              | 20 --------------------
 2 files changed, 1 insertion(+), 27 deletions(-)
 delete mode 100644 include/linux/input/ak8975.h

(limited to 'include')

diff --git a/drivers/staging/iio/magnetometer/ak8975.c b/drivers/staging/iio/magnetometer/ak8975.c
index 80c0f4137076..420f206cf517 100644
--- a/drivers/staging/iio/magnetometer/ak8975.c
+++ b/drivers/staging/iio/magnetometer/ak8975.c
@@ -29,7 +29,6 @@
 #include <linux/delay.h>
 
 #include <linux/gpio.h>
-#include <linux/input/ak8975.h>
 
 #include "../iio.h"
 #include "magnet.h"
@@ -436,7 +435,6 @@ static int ak8975_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct ak8975_data *data;
-	struct ak8975_platform_data *pdata;
 	int err;
 
 	/* Allocate our device context. */
@@ -454,11 +452,7 @@ static int ak8975_probe(struct i2c_client *client,
 
 	/* Grab and set up the supplied GPIO. */
 	data->eoc_irq = client->irq;
-	pdata = client->dev.platform_data;
-	if (pdata)
-		data->eoc_gpio = pdata->gpio;
-	else
-		data->eoc_gpio = irq_to_gpio(client->irq);
+	data->eoc_gpio = irq_to_gpio(client->irq);
 
 	if (!data->eoc_gpio) {
 		dev_err(&client->dev, "failed, no valid GPIO\n");
diff --git a/include/linux/input/ak8975.h b/include/linux/input/ak8975.h
deleted file mode 100644
index 25d41eb10c3e..000000000000
--- a/include/linux/input/ak8975.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * ak8975 platform support
- *
- * Copyright (C) 2010 Renesas Solutions Corp.
- *
- * Author: Tony SIM <chinyeow.sim.xt@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _AK8975_H
-#define _AK8975_H
-
-struct ak8975_platform_data {
-	int gpio;
-};
-
-#endif
-- 
cgit v1.2.3


From 9e924cf4078e377b84e2fd24ae11a61be7c6f5a3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 23 Feb 2011 07:05:07 +0000
Subject: net_sched: long word align struct qdisc_skb_cb data

netem_skb_cb() does :

return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data;

Unfortunatly struct qdisc_skb_cb data is not long word aligned, so
access to psched_time_t time_to_send uses a non aligned access.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 160a407c1963..04f8556313d5 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -199,7 +199,7 @@ struct tcf_proto {
 
 struct qdisc_skb_cb {
 	unsigned int		pkt_len;
-	char			data[];
+	long			data[];
 };
 
 static inline int qdisc_qlen(struct Qdisc *q)
-- 
cgit v1.2.3


From 39fc0ce5710c53bad14aaba1a789eec810c556f9 Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Tue, 22 Feb 2011 16:52:29 +0000
Subject: net: Implement SFEATURES compatibility for not updated drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use discrete setting ops for not updated drivers. This will not make
them conform to full G/SFEATURES semantics, though.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h |  5 ++++
 net/core/ethtool.c      | 61 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 54d776c2c1b5..aac3e2eeb4fd 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -591,6 +591,9 @@ struct ethtool_sfeatures {
  *      Probably there are other device-specific constraints on some features
  *      in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered
  *      here as though ignored bits were cleared.
+ *   %ETHTOOL_F_COMPAT - some or all changes requested were made by calling
+ *      compatibility functions. Requested offload state cannot be properly
+ *      managed by kernel.
  *
  * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of
  * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands
@@ -600,10 +603,12 @@ struct ethtool_sfeatures {
 enum ethtool_sfeatures_retval_bits {
 	ETHTOOL_F_UNSUPPORTED__BIT,
 	ETHTOOL_F_WISH__BIT,
+	ETHTOOL_F_COMPAT__BIT,
 };
 
 #define ETHTOOL_F_UNSUPPORTED   (1 << ETHTOOL_F_UNSUPPORTED__BIT)
 #define ETHTOOL_F_WISH          (1 << ETHTOOL_F_WISH__BIT)
+#define ETHTOOL_F_COMPAT        (1 << ETHTOOL_F_COMPAT__BIT)
 
 #ifdef __KERNEL__
 
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 69a3edc182f9..c1a71bb738da 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -178,6 +178,64 @@ static void ethtool_get_features_compat(struct net_device *dev,
 	if (dev->ethtool_ops->get_rx_csum)
 		if (dev->ethtool_ops->get_rx_csum(dev))
 			features[0].active |= NETIF_F_RXCSUM;
+
+	/* mark legacy-changeable features */
+	if (dev->ethtool_ops->set_sg)
+		features[0].available |= NETIF_F_SG;
+	if (dev->ethtool_ops->set_tx_csum)
+		features[0].available |= NETIF_F_ALL_CSUM;
+	if (dev->ethtool_ops->set_tso)
+		features[0].available |= NETIF_F_ALL_TSO;
+	if (dev->ethtool_ops->set_rx_csum)
+		features[0].available |= NETIF_F_RXCSUM;
+	if (dev->ethtool_ops->set_flags)
+		features[0].available |= flags_dup_features;
+}
+
+static int ethtool_set_feature_compat(struct net_device *dev,
+	int (*legacy_set)(struct net_device *, u32),
+	struct ethtool_set_features_block *features, u32 mask)
+{
+	u32 do_set;
+
+	if (!legacy_set)
+		return 0;
+
+	if (!(features[0].valid & mask))
+		return 0;
+
+	features[0].valid &= ~mask;
+
+	do_set = !!(features[0].requested & mask);
+
+	if (legacy_set(dev, do_set) < 0)
+		netdev_info(dev,
+			"Legacy feature change (%s) failed for 0x%08x\n",
+			do_set ? "set" : "clear", mask);
+
+	return 1;
+}
+
+static int ethtool_set_features_compat(struct net_device *dev,
+	struct ethtool_set_features_block *features)
+{
+	int compat;
+
+	if (!dev->ethtool_ops)
+		return 0;
+
+	compat  = ethtool_set_feature_compat(dev, dev->ethtool_ops->set_sg,
+		features, NETIF_F_SG);
+	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tx_csum,
+		features, NETIF_F_ALL_CSUM);
+	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tso,
+		features, NETIF_F_ALL_TSO);
+	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum,
+		features, NETIF_F_RXCSUM);
+	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_flags,
+		features, flags_dup_features);
+
+	return compat;
 }
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
@@ -234,6 +292,9 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
 	if (features[0].valid & ~NETIF_F_ETHTOOL_BITS)
 		return -EINVAL;
 
+	if (ethtool_set_features_compat(dev, features))
+		ret |= ETHTOOL_F_COMPAT;
+
 	if (features[0].valid & ~dev->hw_features) {
 		features[0].valid &= dev->hw_features;
 		ret |= ETHTOOL_F_UNSUPPORTED;
-- 
cgit v1.2.3


From 5413b4c6c07b659e52c84a4e40d897b32b89834f Mon Sep 17 00:00:00 2001
From: Allan Stephens <Allan.Stephens@windriver.com>
Date: Tue, 18 Jan 2011 13:24:55 -0500
Subject: tipc: Improve handling of invalid link tolerance values

Enhances TIPC link code to ignore an invalid link tolerance value
contained in an incoming LINK_PROTOCOL message, rather than
processing the value and potentially causing a divide-by-zero error.

Also add a compile-time check that catches attempts to redefine
TIPC's minimum link tolerance value in a manner that might result
in the same divide-by-zero error at run-time.

Signed-off-by: Allan Stephens <Allan.Stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/tipc_config.h | 4 ++++
 net/tipc/link.c             | 3 +++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h
index 7d42460a5e3c..c14102dee22e 100644
--- a/include/linux/tipc_config.h
+++ b/include/linux/tipc_config.h
@@ -193,6 +193,10 @@
 #define TIPC_DEF_LINK_TOL 1500
 #define TIPC_MAX_LINK_TOL 30000
 
+#if (TIPC_MIN_LINK_TOL < 16)
+#error "TIPC_MIN_LINK_TOL is too small (abort limit may be NaN)"
+#endif
+
 /*
  * Link window limits (min, default, max), in packets
  */
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1c5c53a81531..3c1c28cdbaa4 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2617,6 +2617,9 @@ static void link_check_defragm_bufs(struct link *l_ptr)
 
 static void link_set_supervision_props(struct link *l_ptr, u32 tolerance)
 {
+	if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL))
+		return;
+
 	l_ptr->tolerance = tolerance;
 	l_ptr->continuity_interval =
 		((tolerance / 4) > 500) ? 500 : tolerance / 4;
-- 
cgit v1.2.3


From 77c81e0bb8af3f1a0e5d84dd0346fe57dfe3da27 Mon Sep 17 00:00:00 2001
From: Allan Stephens <Allan.Stephens@windriver.com>
Date: Tue, 18 Jan 2011 13:37:09 -0500
Subject: tipc: Clean out all remaining instances of #if 0'd unused code

Remove all instances of legacy or proposed-but-not-implemented code
that lives within an #if 0 ... #endif block.  If some of it is needed
in the future it can recovered out of history, but there is no need
for it to clutter up the active code base.

Signed-off-by: Allan Stephens <Allan.Stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/tipc.h        |  8 +-------
 include/linux/tipc_config.h | 28 +---------------------------
 2 files changed, 2 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/linux/tipc.h b/include/linux/tipc.h
index 1eefa3f6d1f4..a5b994a204d2 100644
--- a/include/linux/tipc.h
+++ b/include/linux/tipc.h
@@ -2,7 +2,7 @@
  * include/linux/tipc.h: Include file for TIPC socket interface
  *
  * Copyright (c) 2003-2006, Ericsson AB
- * Copyright (c) 2005, Wind River Systems
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -130,12 +130,6 @@ static inline unsigned int tipc_node(__u32 addr)
 #define TIPC_SUB_PORTS		0x01	/* filter for port availability */
 #define TIPC_SUB_SERVICE	0x02	/* filter for service availability */
 #define TIPC_SUB_CANCEL		0x04	/* cancel a subscription */
-#if 0
-/* The following filter options are not currently implemented */
-#define TIPC_SUB_NO_BIND_EVTS	0x04	/* filter out "publish" events */
-#define TIPC_SUB_NO_UNBIND_EVTS	0x08	/* filter out "withdraw" events */
-#define TIPC_SUB_SINGLE_EVT	0x10	/* expire after first event */
-#endif
 
 #define TIPC_WAIT_FOREVER	(~0)	/* timeout for permanent subscription */
 
diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h
index c14102dee22e..011556fcef04 100644
--- a/include/linux/tipc_config.h
+++ b/include/linux/tipc_config.h
@@ -2,7 +2,7 @@
  * include/linux/tipc_config.h: Include file for TIPC configuration interface
  *
  * Copyright (c) 2003-2006, Ericsson AB
- * Copyright (c) 2005-2007, Wind River Systems
+ * Copyright (c) 2005-2007, 2010-2011, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -76,13 +76,6 @@
 #define  TIPC_CMD_SHOW_LINK_STATS   0x000B    /* tx link_name, rx ultra_string */
 #define  TIPC_CMD_SHOW_STATS        0x000F    /* tx unsigned, rx ultra_string */
 
-#if 0
-#define  TIPC_CMD_SHOW_PORT_STATS   0x0008    /* tx port_ref, rx ultra_string */
-#define  TIPC_CMD_RESET_PORT_STATS  0x0009    /* tx port_ref, rx none */
-#define  TIPC_CMD_GET_ROUTES        0x000A    /* tx ?, rx ? */
-#define  TIPC_CMD_GET_LINK_PEER     0x000D    /* tx link_name, rx ? */
-#endif
-
 /*
  * Protected commands:
  * May only be issued by "network administration capable" process.
@@ -109,13 +102,6 @@
 #define  TIPC_CMD_DUMP_LOG          0x410B    /* tx none, rx ultra_string */
 #define  TIPC_CMD_RESET_LINK_STATS  0x410C    /* tx link_name, rx none */
 
-#if 0
-#define  TIPC_CMD_CREATE_LINK       0x4103    /* tx link_create, rx none */
-#define  TIPC_CMD_REMOVE_LINK       0x4104    /* tx link_name, rx none */
-#define  TIPC_CMD_BLOCK_LINK        0x4105    /* tx link_name, rx none */
-#define  TIPC_CMD_UNBLOCK_LINK      0x4106    /* tx link_name, rx none */
-#endif
-
 /*
  * Private commands:
  * May only be issued by "network administration capable" process.
@@ -123,9 +109,6 @@
  */
 
 #define  TIPC_CMD_SET_NODE_ADDR     0x8001    /* tx net_addr, rx none */
-#if 0
-#define  TIPC_CMD_SET_ZONE_MASTER   0x8002    /* tx none, rx none */
-#endif
 #define  TIPC_CMD_SET_REMOTE_MNG    0x8003    /* tx unsigned, rx none */
 #define  TIPC_CMD_SET_MAX_PORTS     0x8004    /* tx unsigned, rx none */
 #define  TIPC_CMD_SET_MAX_PUBL      0x8005    /* tx unsigned, rx none */
@@ -251,15 +234,6 @@ struct tipc_name_table_query {
 #define TIPC_CFG_NOT_SUPPORTED  "\x84"	/* request is not supported by TIPC */
 #define TIPC_CFG_INVALID_VALUE  "\x85"  /* request has invalid argument value */
 
-#if 0
-/* prototypes TLV structures for proposed commands */
-struct tipc_link_create {
-	__u32   domain;
-	struct tipc_media_addr peer_addr;
-	char bearer_name[TIPC_MAX_BEARER_NAME];
-};
-#endif
-
 /*
  * A TLV consists of a descriptor, followed by the TLV value.
  * TLV descriptor fields are stored in network byte order;
-- 
cgit v1.2.3


From 2aa15890f3c191326678f1bd68af61ec6b8753ec Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Wed, 23 Feb 2011 13:49:47 +0100
Subject: mm: prevent concurrent unmap_mapping_range() on the same inode

Michael Leun reported that running parallel opens on a fuse filesystem
can trigger a "kernel BUG at mm/truncate.c:475"

Gurudas Pai reported the same bug on NFS.

The reason is, unmap_mapping_range() is not prepared for more than
one concurrent invocation per inode.  For example:

  thread1: going through a big range, stops in the middle of a vma and
     stores the restart address in vm_truncate_count.

  thread2: comes in with a small (e.g. single page) unmap request on
     the same vma, somewhere before restart_address, finds that the
     vma was already unmapped up to the restart address and happily
     returns without doing anything.

Another scenario would be two big unmap requests, both having to
restart the unmapping and each one setting vm_truncate_count to its
own value.  This could go on forever without any of them being able to
finish.

Truncate and hole punching already serialize with i_mutex.  Other
callers of unmap_mapping_range() do not, and it's difficult to get
i_mutex protection for all callers.  In particular ->d_revalidate(),
which calls invalidate_inode_pages2_range() in fuse, may be called
with or without i_mutex.

This patch adds a new mutex to 'struct address_space' to prevent
running multiple concurrent unmap_mapping_range() on the same mapping.

[ We'll hopefully get rid of all this with the upcoming mm
  preemptibility series by Peter Zijlstra, the "mm: Remove i_mmap_mutex
  lockbreak" patch in particular.  But that is for 2.6.39 ]

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reported-by: Michael Leun <lkml20101129@newton.leun.net>
Reported-by: Gurudas Pai <gurudas.pai@oracle.com>
Tested-by: Gurudas Pai <gurudas.pai@oracle.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/gfs2/main.c     |  9 +--------
 fs/inode.c         | 22 +++++++++++++++-------
 fs/nilfs2/btnode.c |  5 -----
 fs/nilfs2/btnode.h |  1 -
 fs/nilfs2/mdt.c    |  4 ++--
 fs/nilfs2/page.c   | 13 -------------
 fs/nilfs2/page.h   |  1 -
 fs/nilfs2/super.c  |  2 +-
 include/linux/fs.h |  2 ++
 mm/memory.c        |  2 ++
 10 files changed, 23 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 85ba027d1c4d..72c31a315d96 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -59,14 +59,7 @@ static void gfs2_init_gl_aspace_once(void *foo)
 	struct address_space *mapping = (struct address_space *)(gl + 1);
 
 	gfs2_init_glock_once(gl);
-	memset(mapping, 0, sizeof(*mapping));
-	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
-	spin_lock_init(&mapping->tree_lock);
-	spin_lock_init(&mapping->i_mmap_lock);
-	INIT_LIST_HEAD(&mapping->private_list);
-	spin_lock_init(&mapping->private_lock);
-	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
-	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+	address_space_init_once(mapping);
 }
 
 /**
diff --git a/fs/inode.c b/fs/inode.c
index da85e56378f3..9c2b795ccc93 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -295,6 +295,20 @@ static void destroy_inode(struct inode *inode)
 		call_rcu(&inode->i_rcu, i_callback);
 }
 
+void address_space_init_once(struct address_space *mapping)
+{
+	memset(mapping, 0, sizeof(*mapping));
+	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
+	spin_lock_init(&mapping->tree_lock);
+	spin_lock_init(&mapping->i_mmap_lock);
+	INIT_LIST_HEAD(&mapping->private_list);
+	spin_lock_init(&mapping->private_lock);
+	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
+	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+	mutex_init(&mapping->unmap_mutex);
+}
+EXPORT_SYMBOL(address_space_init_once);
+
 /*
  * These are initializations that only need to be done
  * once, because the fields are idempotent across use
@@ -308,13 +322,7 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->i_devices);
 	INIT_LIST_HEAD(&inode->i_wb_list);
 	INIT_LIST_HEAD(&inode->i_lru);
-	INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
-	spin_lock_init(&inode->i_data.tree_lock);
-	spin_lock_init(&inode->i_data.i_mmap_lock);
-	INIT_LIST_HEAD(&inode->i_data.private_list);
-	spin_lock_init(&inode->i_data.private_lock);
-	INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);
-	INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear);
+	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
 #ifdef CONFIG_FSNOTIFY
 	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 388e9e8f5286..85f7baa15f5d 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -35,11 +35,6 @@
 #include "btnode.h"
 
 
-void nilfs_btnode_cache_init_once(struct address_space *btnc)
-{
-	nilfs_mapping_init_once(btnc);
-}
-
 static const struct address_space_operations def_btnode_aops = {
 	.sync_page		= block_sync_page,
 };
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index 79037494f1e0..1b8ebd888c28 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -37,7 +37,6 @@ struct nilfs_btnode_chkey_ctxt {
 	struct buffer_head *newbh;
 };
 
-void nilfs_btnode_cache_init_once(struct address_space *);
 void nilfs_btnode_cache_init(struct address_space *, struct backing_dev_info *);
 void nilfs_btnode_cache_clear(struct address_space *);
 struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc,
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 6a0e2a189f60..a0babd2bff6a 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -454,9 +454,9 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 	struct backing_dev_info *bdi = inode->i_sb->s_bdi;
 
 	INIT_LIST_HEAD(&shadow->frozen_buffers);
-	nilfs_mapping_init_once(&shadow->frozen_data);
+	address_space_init_once(&shadow->frozen_data);
 	nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops);
-	nilfs_mapping_init_once(&shadow->frozen_btnodes);
+	address_space_init_once(&shadow->frozen_btnodes);
 	nilfs_mapping_init(&shadow->frozen_btnodes, bdi, &shadow_map_aops);
 	mi->mi_shadow = shadow;
 	return 0;
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 0c432416cfef..a585b35fd6bc 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -492,19 +492,6 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
 	return nc;
 }
 
-void nilfs_mapping_init_once(struct address_space *mapping)
-{
-	memset(mapping, 0, sizeof(*mapping));
-	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
-	spin_lock_init(&mapping->tree_lock);
-	INIT_LIST_HEAD(&mapping->private_list);
-	spin_lock_init(&mapping->private_lock);
-
-	spin_lock_init(&mapping->i_mmap_lock);
-	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
-	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
-}
-
 void nilfs_mapping_init(struct address_space *mapping,
 			struct backing_dev_info *bdi,
 			const struct address_space_operations *aops)
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index 622df27cd891..2a00953ebd5f 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -61,7 +61,6 @@ void nilfs_free_private_page(struct page *);
 int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_dirty_pages(struct address_space *);
-void nilfs_mapping_init_once(struct address_space *mapping);
 void nilfs_mapping_init(struct address_space *mapping,
 			struct backing_dev_info *bdi,
 			const struct address_space_operations *aops);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 58fd707174e1..1673b3d99842 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1279,7 +1279,7 @@ static void nilfs_inode_init_once(void *obj)
 #ifdef CONFIG_NILFS_XATTR
 	init_rwsem(&ii->xattr_sem);
 #endif
-	nilfs_btnode_cache_init_once(&ii->i_btnode_cache);
+	address_space_init_once(&ii->i_btnode_cache);
 	ii->i_bmap = &ii->i_bmap_data;
 	inode_init_once(&ii->vfs_inode);
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bd3215940c37..97d08d8a7de8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -649,6 +649,7 @@ struct address_space {
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
 	struct address_space	*assoc_mapping;	/* ditto */
+	struct mutex		unmap_mutex;    /* to protect unmapping */
 } __attribute__((aligned(sizeof(long))));
 	/*
 	 * On most architectures that alignment is already the case; but
@@ -2225,6 +2226,7 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 
 extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
+extern void address_space_init_once(struct address_space *mapping);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
diff --git a/mm/memory.c b/mm/memory.c
index 8e8c18324863..5823698c2b71 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2648,6 +2648,7 @@ void unmap_mapping_range(struct address_space *mapping,
 		details.last_index = ULONG_MAX;
 	details.i_mmap_lock = &mapping->i_mmap_lock;
 
+	mutex_lock(&mapping->unmap_mutex);
 	spin_lock(&mapping->i_mmap_lock);
 
 	/* Protect against endless unmapping loops */
@@ -2664,6 +2665,7 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
 	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->unmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-- 
cgit v1.2.3


From 93b270f76e7ef3b81001576860c2701931cdc78b Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Thu, 24 Feb 2011 17:25:47 +1100
Subject: Fix over-zealous flush_disk when changing device size.

There are two cases when we call flush_disk.
In one, the device has disappeared (check_disk_change) so any
data will hold becomes irrelevant.
In the oter, the device has changed size (check_disk_size_change)
so data we hold may be irrelevant.

In both cases it makes sense to discard any 'clean' buffers,
so they will be read back from the device if needed.

In the former case it makes sense to discard 'dirty' buffers
as there will never be anywhere safe to write the data.  In the
second case it *does*not* make sense to discard dirty buffers
as that will lead to file system corruption when you simply enlarge
the containing devices.

flush_disk calls __invalidate_devices.
__invalidate_device calls both invalidate_inodes and invalidate_bdev.

invalidate_inodes *does* discard I_DIRTY inodes and this does lead
to fs corruption.

invalidate_bev *does*not* discard dirty pages, but I don't really care
about that at present.

So this patch adds a flag to __invalidate_device (calling it
__invalidate_device2) to indicate whether dirty buffers should be
killed, and this is passed to invalidate_inodes which can choose to
skip dirty inodes.

flusk_disk then passes true from check_disk_change and false from
check_disk_size_change.

dm avoids tripping over this problem by calling i_size_write directly
rathher than using check_disk_size_change.

md does use check_disk_size_change and so is affected.

This regression was introduced by commit 608aeef17a which causes
check_disk_size_change to call flush_disk, so it is suitable for any
kernel since 2.6.27.

Cc: stable@kernel.org
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Cc: Andrew Patterson <andrew.patterson@hp.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NeilBrown <neilb@suse.de>
---
 block/genhd.c          |  2 +-
 drivers/block/floppy.c |  2 +-
 fs/block_dev.c         | 12 ++++++------
 fs/inode.c             |  9 ++++++++-
 fs/internal.h          |  2 +-
 include/linux/fs.h     |  2 +-
 6 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 6a5b772aa201..cbf1112a885c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1355,7 +1355,7 @@ int invalidate_partition(struct gendisk *disk, int partno)
 	struct block_device *bdev = bdget_disk(disk, partno);
 	if (bdev) {
 		fsync_bdev(bdev);
-		res = __invalidate_device(bdev);
+		res = __invalidate_device(bdev, true);
 		bdput(bdev);
 	}
 	return res;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index b9ba04fc2b34..77fc76f8aea9 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3281,7 +3281,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 			struct block_device *bdev = opened_bdev[cnt];
 			if (!bdev || ITYPE(drive_state[cnt].fd_device) != type)
 				continue;
-			__invalidate_device(bdev);
+			__invalidate_device(bdev, true);
 		}
 		mutex_unlock(&open_lock);
 	} else {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 333a7bb4cb9c..5e23152d04ad 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -927,9 +927,9 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
  * when a disk has been changed -- either by a media change or online
  * resize.
  */
-static void flush_disk(struct block_device *bdev)
+static void flush_disk(struct block_device *bdev, bool kill_dirty)
 {
-	if (__invalidate_device(bdev)) {
+	if (__invalidate_device(bdev, kill_dirty)) {
 		char name[BDEVNAME_SIZE] = "";
 
 		if (bdev->bd_disk)
@@ -966,7 +966,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 		       "%s: detected capacity change from %lld to %lld\n",
 		       name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
-		flush_disk(bdev);
+		flush_disk(bdev, false);
 	}
 }
 EXPORT_SYMBOL(check_disk_size_change);
@@ -1019,7 +1019,7 @@ int check_disk_change(struct block_device *bdev)
 	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return 0;
 
-	flush_disk(bdev);
+	flush_disk(bdev, true);
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
 	return 1;
@@ -1601,7 +1601,7 @@ fail:
 }
 EXPORT_SYMBOL(lookup_bdev);
 
-int __invalidate_device(struct block_device *bdev)
+int __invalidate_device(struct block_device *bdev, bool kill_dirty)
 {
 	struct super_block *sb = get_super(bdev);
 	int res = 0;
@@ -1614,7 +1614,7 @@ int __invalidate_device(struct block_device *bdev)
 		 * hold).
 		 */
 		shrink_dcache_sb(sb);
-		res = invalidate_inodes(sb);
+		res = invalidate_inodes(sb, kill_dirty);
 		drop_super(sb);
 	}
 	invalidate_bdev(bdev);
diff --git a/fs/inode.c b/fs/inode.c
index da85e56378f3..c50d7feb87b1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -540,11 +540,14 @@ void evict_inodes(struct super_block *sb)
 /**
  * invalidate_inodes	- attempt to free all inodes on a superblock
  * @sb:		superblock to operate on
+ * @kill_dirty: flag to guide handling of dirty inodes
  *
  * Attempts to free all inodes for a given superblock.  If there were any
  * busy inodes return a non-zero value, else zero.
+ * If @kill_dirty is set, discard dirty inodes too, otherwise treat
+ * them as busy.
  */
-int invalidate_inodes(struct super_block *sb)
+int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 {
 	int busy = 0;
 	struct inode *inode, *next;
@@ -556,6 +559,10 @@ int invalidate_inodes(struct super_block *sb)
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
 			continue;
+		if (inode->i_state & I_DIRTY && !kill_dirty) {
+			busy = 1;
+			continue;
+		}
 		if (atomic_read(&inode->i_count)) {
 			busy = 1;
 			continue;
diff --git a/fs/internal.h b/fs/internal.h
index 0663568b1247..9b976b57d7fe 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -112,4 +112,4 @@ extern void release_open_intent(struct nameidata *);
  */
 extern int get_nr_dirty_inodes(void);
 extern void evict_inodes(struct super_block *);
-extern int invalidate_inodes(struct super_block *);
+extern int invalidate_inodes(struct super_block *, bool);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 32b38cd829d3..683f4c566c82 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2139,7 +2139,7 @@ extern void check_disk_size_change(struct gendisk *disk,
 				   struct block_device *bdev);
 extern int revalidate_disk(struct gendisk *);
 extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *);
+extern int __invalidate_device(struct block_device *, bool);
 extern int invalidate_partition(struct gendisk *, int);
 #endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
-- 
cgit v1.2.3


From 214e005bc32c7045b8554f9f0fb07b3fcce2cd42 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:02:38 -0500
Subject: xfrm: Pass km_event pointers around as const when possible.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h    |  8 ++++----
 net/key/af_key.c      | 16 ++++++++--------
 net/xfrm/xfrm_state.c |  4 ++--
 net/xfrm/xfrm_user.c  | 24 ++++++++++++------------
 4 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index bb824a5d71bf..6ef5c374ef8a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -284,8 +284,8 @@ struct xfrm_policy_afinfo {
 
 extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
 extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo);
-extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c);
-extern void km_state_notify(struct xfrm_state *x, struct km_event *c);
+extern void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c);
+extern void km_state_notify(struct xfrm_state *x, const struct km_event *c);
 
 struct xfrm_tmpl;
 extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
@@ -548,11 +548,11 @@ struct xfrm_migrate {
 struct xfrm_mgr {
 	struct list_head	list;
 	char			*id;
-	int			(*notify)(struct xfrm_state *x, struct km_event *c);
+	int			(*notify)(struct xfrm_state *x, const struct km_event *c);
 	int			(*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir);
 	struct xfrm_policy	*(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir);
 	int			(*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
-	int			(*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c);
+	int			(*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c);
 	int			(*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr);
 	int			(*migrate)(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k);
 };
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 60fd2f13f427..7c5e101e7c28 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1429,7 +1429,7 @@ static inline int event2keytype(int event)
 }
 
 /* ADD/UPD/DEL */
-static int key_notify_sa(struct xfrm_state *x, struct km_event *c)
+static int key_notify_sa(struct xfrm_state *x, const struct km_event *c)
 {
 	struct sk_buff *skb;
 	struct sadb_msg *hdr;
@@ -1688,7 +1688,7 @@ static int unicast_flush_resp(struct sock *sk, struct sadb_msg *ihdr)
 	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk));
 }
 
-static int key_notify_sa_flush(struct km_event *c)
+static int key_notify_sa_flush(const struct km_event *c)
 {
 	struct sk_buff *skb;
 	struct sadb_msg *hdr;
@@ -2123,7 +2123,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, in
 	return 0;
 }
 
-static int key_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c)
+static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 	struct sk_buff *out_skb;
 	struct sadb_msg *out_hdr;
@@ -2660,7 +2660,7 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, struct sadb_msg *
 	return pfkey_do_dump(pfk);
 }
 
-static int key_notify_policy_flush(struct km_event *c)
+static int key_notify_policy_flush(const struct km_event *c)
 {
 	struct sk_buff *skb_out;
 	struct sadb_msg *hdr;
@@ -2914,12 +2914,12 @@ static void dump_esp_combs(struct sk_buff *skb, struct xfrm_tmpl *t)
 	}
 }
 
-static int key_notify_policy_expire(struct xfrm_policy *xp, struct km_event *c)
+static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c)
 {
 	return 0;
 }
 
-static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c)
+static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c)
 {
 	struct sk_buff *out_skb;
 	struct sadb_msg *out_hdr;
@@ -2949,7 +2949,7 @@ static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c)
 	return 0;
 }
 
-static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c)
+static int pfkey_send_notify(struct xfrm_state *x, const struct km_event *c)
 {
 	struct net *net = x ? xs_net(x) : c->net;
 	struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
@@ -2976,7 +2976,7 @@ static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c)
 	return 0;
 }
 
-static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
+static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 	if (xp && xp->type != XFRM_POLICY_TYPE_MAIN)
 		return 0;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 30a0f178819c..7028f063f093 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1727,7 +1727,7 @@ void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
 static LIST_HEAD(xfrm_km_list);
 static DEFINE_RWLOCK(xfrm_km_lock);
 
-void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
+void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 	struct xfrm_mgr *km;
 
@@ -1738,7 +1738,7 @@ void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
 	read_unlock(&xfrm_km_lock);
 }
 
-void km_state_notify(struct xfrm_state *x, struct km_event *c)
+void km_state_notify(struct xfrm_state *x, const struct km_event *c)
 {
 	struct xfrm_mgr *km;
 	read_lock(&xfrm_km_lock);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 61291965c5f6..2cc9dab29887 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1582,7 +1582,7 @@ static inline size_t xfrm_aevent_msgsize(void)
 	       + nla_total_size(4); /* XFRM_AE_ETHR */
 }
 
-static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c)
+static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
 {
 	struct xfrm_aevent_id *id;
 	struct nlmsghdr *nlh;
@@ -2220,7 +2220,7 @@ static inline size_t xfrm_expire_msgsize(void)
 	       + nla_total_size(sizeof(struct xfrm_mark));
 }
 
-static int build_expire(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c)
+static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
 {
 	struct xfrm_user_expire *ue;
 	struct nlmsghdr *nlh;
@@ -2242,7 +2242,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c)
+static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
 {
 	struct net *net = xs_net(x);
 	struct sk_buff *skb;
@@ -2259,7 +2259,7 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c)
 	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
 }
 
-static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c)
+static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c)
 {
 	struct net *net = xs_net(x);
 	struct sk_buff *skb;
@@ -2274,7 +2274,7 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c)
 	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC);
 }
 
-static int xfrm_notify_sa_flush(struct km_event *c)
+static int xfrm_notify_sa_flush(const struct km_event *c)
 {
 	struct net *net = c->net;
 	struct xfrm_usersa_flush *p;
@@ -2330,7 +2330,7 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x)
 	return l;
 }
 
-static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c)
+static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
 {
 	struct net *net = xs_net(x);
 	struct xfrm_usersa_info *p;
@@ -2387,7 +2387,7 @@ nla_put_failure:
 	return -1;
 }
 
-static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c)
+static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c)
 {
 
 	switch (c->event) {
@@ -2546,7 +2546,7 @@ static inline size_t xfrm_polexpire_msgsize(struct xfrm_policy *xp)
 }
 
 static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
-			   int dir, struct km_event *c)
+			   int dir, const struct km_event *c)
 {
 	struct xfrm_user_polexpire *upe;
 	struct nlmsghdr *nlh;
@@ -2576,7 +2576,7 @@ nlmsg_failure:
 	return -EMSGSIZE;
 }
 
-static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
+static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 	struct net *net = xp_net(xp);
 	struct sk_buff *skb;
@@ -2591,7 +2591,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_eve
 	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
 }
 
-static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c)
+static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 	struct net *net = xp_net(xp);
 	struct xfrm_userpolicy_info *p;
@@ -2656,7 +2656,7 @@ nlmsg_failure:
 	return -1;
 }
 
-static int xfrm_notify_policy_flush(struct km_event *c)
+static int xfrm_notify_policy_flush(const struct km_event *c)
 {
 	struct net *net = c->net;
 	struct nlmsghdr *nlh;
@@ -2681,7 +2681,7 @@ nlmsg_failure:
 	return -1;
 }
 
-static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
+static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 
 	switch (c->event) {
-- 
cgit v1.2.3


From 19bd62441c36279ab33e311faebd357ef04ba344 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:07:20 -0500
Subject: xfrm: Const'ify tmpl and address arguments to ->init_temprop()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 6 ++++--
 net/ipv4/xfrm4_state.c | 4 ++--
 net/ipv6/xfrm6_state.c | 4 ++--
 3 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 6ef5c374ef8a..46f44703b611 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -302,8 +302,10 @@ struct xfrm_state_afinfo {
 	int			(*init_flags)(struct xfrm_state *x);
 	void			(*init_tempsel)(struct xfrm_selector *sel,
 						const struct flowi *fl);
-	void			(*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
-						xfrm_address_t *daddr, xfrm_address_t *saddr);
+	void			(*init_temprop)(struct xfrm_state *x,
+						const struct xfrm_tmpl *tmpl,
+						const xfrm_address_t *daddr,
+						const xfrm_address_t *saddr);
 	int			(*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
 	int			(*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n);
 	int			(*output)(struct sk_buff *skb);
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 19eb56067727..983eff248988 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -37,8 +37,8 @@ __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 }
 
 static void
-xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
-		   xfrm_address_t *daddr, xfrm_address_t *saddr)
+xfrm4_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
+		   const xfrm_address_t *daddr, const xfrm_address_t *saddr)
 {
 	x->id = tmpl->id;
 	if (x->id.daddr.a4 == 0)
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 68a14c0339db..a02598e0079a 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -38,8 +38,8 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 }
 
 static void
-xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
-		   xfrm_address_t *daddr, xfrm_address_t *saddr)
+xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
+		   const xfrm_address_t *daddr, const xfrm_address_t *saddr)
 {
 	x->id = tmpl->id;
 	if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
-- 
cgit v1.2.3


From 200ce96e5601391a6d97c87067edf21fa94fb74e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:12:25 -0500
Subject: xfrm: Const'ify selector argument to xfrm_selector_match()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 2 +-
 net/xfrm/xfrm_policy.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 46f44703b611..567f08b559a1 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -845,7 +845,7 @@ __be16 xfrm_flowi_dport(const struct flowi *fl)
 	return port;
 }
 
-extern int xfrm_selector_match(struct xfrm_selector *sel,
+extern int xfrm_selector_match(const struct xfrm_selector *sel,
 			       const struct flowi *fl,
 			       unsigned short family);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 28c865adf609..4827c8db864d 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -58,7 +58,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
 static inline int
-__xfrm4_selector_match(struct xfrm_selector *sel, const struct flowi *fl)
+__xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
@@ -69,7 +69,7 @@ __xfrm4_selector_match(struct xfrm_selector *sel, const struct flowi *fl)
 }
 
 static inline int
-__xfrm6_selector_match(struct xfrm_selector *sel, const struct flowi *fl)
+__xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
@@ -79,7 +79,7 @@ __xfrm6_selector_match(struct xfrm_selector *sel, const struct flowi *fl)
 		(fl->oif == sel->ifindex || !sel->ifindex);
 }
 
-int xfrm_selector_match(struct xfrm_selector *sel, const struct flowi *fl,
+int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
 			unsigned short family)
 {
 	switch (family) {
-- 
cgit v1.2.3


From 5e6b930f21b0a442f9d5db97c8314b4d91be1c27 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:14:45 -0500
Subject: xfrm: Const'ify address arguments to ->dst_lookup()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h      | 4 ++--
 net/ipv4/xfrm4_policy.c | 4 ++--
 net/ipv6/xfrm6_policy.c | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 567f08b559a1..18f115a6fb19 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -267,8 +267,8 @@ struct xfrm_policy_afinfo {
 	struct dst_ops		*dst_ops;
 	void			(*garbage_collect)(struct net *net);
 	struct dst_entry	*(*dst_lookup)(struct net *net, int tos,
-					       xfrm_address_t *saddr,
-					       xfrm_address_t *daddr);
+					       const xfrm_address_t *saddr,
+					       const xfrm_address_t *daddr);
 	int			(*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr);
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 1e9844d1f8c5..63aa88efdcef 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -19,8 +19,8 @@
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
 
 static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
-					  xfrm_address_t *saddr,
-					  xfrm_address_t *daddr)
+					  const xfrm_address_t *saddr,
+					  const xfrm_address_t *daddr)
 {
 	struct flowi fl = {
 		.fl4_dst = daddr->a4,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f2fa904b8a91..c128ca1affe3 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -27,8 +27,8 @@
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
 
 static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
-					  xfrm_address_t *saddr,
-					  xfrm_address_t *daddr)
+					  const xfrm_address_t *saddr,
+					  const xfrm_address_t *daddr)
 {
 	struct flowi fl = {};
 	struct dst_entry *dst;
-- 
cgit v1.2.3


From ff6acd16825d59de3964b036183a5d214213b9a6 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:19:13 -0500
Subject: xfrm: Const'ify address arguments to xfrm_addr_cmp()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 18f115a6fb19..1c82b944803a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1520,7 +1520,8 @@ struct scatterlist;
 typedef int (icv_update_fn_t)(struct hash_desc *, struct scatterlist *,
 			      unsigned int);
 
-static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b,
+static inline int xfrm_addr_cmp(const xfrm_address_t *a,
+				const xfrm_address_t *b,
 				int family)
 {
 	switch (family) {
-- 
cgit v1.2.3


From 6cc329610f2a1698576a2a8a94dbad8f82a66363 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:19:59 -0500
Subject: xfrm: Const'ify address argument to xfrm_addr_any()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 1c82b944803a..b60f9564fb8d 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -954,7 +954,7 @@ secpath_reset(struct sk_buff *skb)
 }
 
 static inline int
-xfrm_addr_any(xfrm_address_t *addr, unsigned short family)
+xfrm_addr_any(const xfrm_address_t *addr, unsigned short family)
 {
 	switch (family) {
 	case AF_INET:
-- 
cgit v1.2.3


From 183cad12785ffc036571c4b789dc084ec61a1bad Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:28:01 -0500
Subject: xfrm: Const'ify pointer args to km_migrate() and implementations.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h    | 12 ++++++++----
 net/key/af_key.c      | 22 +++++++++++-----------
 net/xfrm/xfrm_state.c |  6 +++---
 net/xfrm/xfrm_user.c  | 24 ++++++++++++------------
 4 files changed, 34 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b60f9564fb8d..17b296b19982 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -556,7 +556,11 @@ struct xfrm_mgr {
 	int			(*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
 	int			(*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c);
 	int			(*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr);
-	int			(*migrate)(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k);
+	int			(*migrate)(const struct xfrm_selector *sel,
+					   u8 dir, u8 type,
+					   const struct xfrm_migrate *m,
+					   int num_bundles,
+					   const struct xfrm_kmaddress *k);
 };
 
 extern int xfrm_register_km(struct xfrm_mgr *km);
@@ -1483,9 +1487,9 @@ struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark,
 extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
 
 #ifdef CONFIG_XFRM_MIGRATE
-extern int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
-		      struct xfrm_migrate *m, int num_bundles,
-		      struct xfrm_kmaddress *k);
+extern int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+		      const struct xfrm_migrate *m, int num_bundles,
+		      const struct xfrm_kmaddress *k);
 extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m);
 extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
 					      struct xfrm_migrate *m);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 7c5e101e7c28..56372853142a 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -690,7 +690,7 @@ static inline int pfkey_mode_to_xfrm(int mode)
 	}
 }
 
-static unsigned int pfkey_sockaddr_fill(xfrm_address_t *xaddr, __be16 port,
+static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port,
 				       struct sockaddr *sa,
 				       unsigned short family)
 {
@@ -3318,7 +3318,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 
 #ifdef CONFIG_NET_KEY_MIGRATE
 static int set_sadb_address(struct sk_buff *skb, int sasize, int type,
-			    struct xfrm_selector *sel)
+			    const struct xfrm_selector *sel)
 {
 	struct sadb_address *addr;
 	addr = (struct sadb_address *)skb_put(skb, sizeof(struct sadb_address) + sasize);
@@ -3348,7 +3348,7 @@ static int set_sadb_address(struct sk_buff *skb, int sasize, int type,
 }
 
 
-static int set_sadb_kmaddress(struct sk_buff *skb, struct xfrm_kmaddress *k)
+static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress *k)
 {
 	struct sadb_x_kmaddress *kma;
 	u8 *sa;
@@ -3376,7 +3376,7 @@ static int set_sadb_kmaddress(struct sk_buff *skb, struct xfrm_kmaddress *k)
 static int set_ipsecrequest(struct sk_buff *skb,
 			    uint8_t proto, uint8_t mode, int level,
 			    uint32_t reqid, uint8_t family,
-			    xfrm_address_t *src, xfrm_address_t *dst)
+			    const xfrm_address_t *src, const xfrm_address_t *dst)
 {
 	struct sadb_x_ipsecrequest *rq;
 	u8 *sa;
@@ -3404,9 +3404,9 @@ static int set_ipsecrequest(struct sk_buff *skb,
 #endif
 
 #ifdef CONFIG_NET_KEY_MIGRATE
-static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
-			      struct xfrm_migrate *m, int num_bundles,
-			      struct xfrm_kmaddress *k)
+static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+			      const struct xfrm_migrate *m, int num_bundles,
+			      const struct xfrm_kmaddress *k)
 {
 	int i;
 	int sasize_sel;
@@ -3415,7 +3415,7 @@ static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
 	struct sk_buff *skb;
 	struct sadb_msg *hdr;
 	struct sadb_x_policy *pol;
-	struct xfrm_migrate *mp;
+	const struct xfrm_migrate *mp;
 
 	if (type != XFRM_POLICY_TYPE_MAIN)
 		return 0;
@@ -3513,9 +3513,9 @@ err:
 	return -EINVAL;
 }
 #else
-static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
-			      struct xfrm_migrate *m, int num_bundles,
-			      struct xfrm_kmaddress *k)
+static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+			      const struct xfrm_migrate *m, int num_bundles,
+			      const struct xfrm_kmaddress *k)
 {
 	return -ENOPROTOOPT;
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 7028f063f093..555beddb63f0 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1819,9 +1819,9 @@ void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid)
 EXPORT_SYMBOL(km_policy_expired);
 
 #ifdef CONFIG_XFRM_MIGRATE
-int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
-	       struct xfrm_migrate *m, int num_migrate,
-	       struct xfrm_kmaddress *k)
+int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+	       const struct xfrm_migrate *m, int num_migrate,
+	       const struct xfrm_kmaddress *k)
 {
 	int err = -EINVAL;
 	int ret;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 2cc9dab29887..b43c1b1240d4 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1986,7 +1986,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 #endif
 
 #ifdef CONFIG_XFRM_MIGRATE
-static int copy_to_user_migrate(struct xfrm_migrate *m, struct sk_buff *skb)
+static int copy_to_user_migrate(const struct xfrm_migrate *m, struct sk_buff *skb)
 {
 	struct xfrm_user_migrate um;
 
@@ -2004,7 +2004,7 @@ static int copy_to_user_migrate(struct xfrm_migrate *m, struct sk_buff *skb)
 	return nla_put(skb, XFRMA_MIGRATE, sizeof(um), &um);
 }
 
-static int copy_to_user_kmaddress(struct xfrm_kmaddress *k, struct sk_buff *skb)
+static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff *skb)
 {
 	struct xfrm_user_kmaddress uk;
 
@@ -2025,11 +2025,11 @@ static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma)
 	      + userpolicy_type_attrsize();
 }
 
-static int build_migrate(struct sk_buff *skb, struct xfrm_migrate *m,
-			 int num_migrate, struct xfrm_kmaddress *k,
-			 struct xfrm_selector *sel, u8 dir, u8 type)
+static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m,
+			 int num_migrate, const struct xfrm_kmaddress *k,
+			 const struct xfrm_selector *sel, u8 dir, u8 type)
 {
-	struct xfrm_migrate *mp;
+	const struct xfrm_migrate *mp;
 	struct xfrm_userpolicy_id *pol_id;
 	struct nlmsghdr *nlh;
 	int i;
@@ -2061,9 +2061,9 @@ nlmsg_failure:
 	return -EMSGSIZE;
 }
 
-static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
-			     struct xfrm_migrate *m, int num_migrate,
-			     struct xfrm_kmaddress *k)
+static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+			     const struct xfrm_migrate *m, int num_migrate,
+			     const struct xfrm_kmaddress *k)
 {
 	struct net *net = &init_net;
 	struct sk_buff *skb;
@@ -2079,9 +2079,9 @@ static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
 	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC);
 }
 #else
-static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
-			     struct xfrm_migrate *m, int num_migrate,
-			     struct xfrm_kmaddress *k)
+static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+			     const struct xfrm_migrate *m, int num_migrate,
+			     const struct xfrm_kmaddress *k)
 {
 	return -ENOPROTOOPT;
 }
-- 
cgit v1.2.3


From b4b7c0b389131c34b6c3a6bf3f3c4d17fe59155f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 00:35:06 -0500
Subject: xfrm: Const'ify selector args in xfrm_migrate paths.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 2 +-
 net/xfrm/xfrm_policy.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 17b296b19982..1806c918a15a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1493,7 +1493,7 @@ extern int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m);
 extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
 					      struct xfrm_migrate *m);
-extern int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
+extern int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			struct xfrm_migrate *m, int num_bundles,
 			struct xfrm_kmaddress *k);
 #endif
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0770b3ae5ccb..0c503be3260c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2736,8 +2736,8 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete);
 #endif
 
 #ifdef CONFIG_XFRM_MIGRATE
-static int xfrm_migrate_selector_match(struct xfrm_selector *sel_cmp,
-				       struct xfrm_selector *sel_tgt)
+static int xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
+				       const struct xfrm_selector *sel_tgt)
 {
 	if (sel_cmp->proto == IPSEC_ULPROTO_ANY) {
 		if (sel_tgt->family == sel_cmp->family &&
@@ -2757,7 +2757,7 @@ static int xfrm_migrate_selector_match(struct xfrm_selector *sel_cmp,
 	return 0;
 }
 
-static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel,
+static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel,
 						     u8 dir, u8 type)
 {
 	struct xfrm_policy *pol, *ret = NULL;
@@ -2897,7 +2897,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate)
 	return 0;
 }
 
-int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
+int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
 		 struct xfrm_kmaddress *k)
 {
-- 
cgit v1.2.3


From 63eb23f5d80d7158fa575aaca240cb8497e2c06f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 01:25:19 -0500
Subject: xfrm: Const'ify policy arg to xp_net.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 1806c918a15a..5402a1e2c0de 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -506,7 +506,7 @@ struct xfrm_policy {
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
 };
 
-static inline struct net *xp_net(struct xfrm_policy *xp)
+static inline struct net *xp_net(const struct xfrm_policy *xp)
 {
 	return read_pnet(&xp->xp_net);
 }
-- 
cgit v1.2.3


From 21eddb5c1e972727fadec57d8c340dcf814d7902 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 01:35:16 -0500
Subject: xfrm: Const'ify xfrm_tmpl and xfrm_state args to xfrm_state_addr_cmp.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 5402a1e2c0de..f6d2f635c81d 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -970,21 +970,21 @@ xfrm_addr_any(const xfrm_address_t *addr, unsigned short family)
 }
 
 static inline int
-__xfrm4_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x)
+__xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x)
 {
 	return	(tmpl->saddr.a4 &&
 		 tmpl->saddr.a4 != x->props.saddr.a4);
 }
 
 static inline int
-__xfrm6_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x)
+__xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x)
 {
 	return	(!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) &&
 		 ipv6_addr_cmp((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr));
 }
 
 static inline int
-xfrm_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x, unsigned short family)
+xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family)
 {
 	switch (family) {
 	case AF_INET:
-- 
cgit v1.2.3


From f8848067caff97ce03ee9beef8b6dd5c70f7e736 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 01:42:28 -0500
Subject: xfrm: Const'ify ptr args to xfrm_state_*_check and xfrm_state_kern.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index f6d2f635c81d..3205e5e4379f 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1178,8 +1178,8 @@ void xfrm_flowi_addr_get(const struct flowi *fl,
 }
 
 static __inline__ int
-__xfrm4_state_addr_check(struct xfrm_state *x,
-			 xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm4_state_addr_check(const struct xfrm_state *x,
+			 const xfrm_address_t *daddr, const xfrm_address_t *saddr)
 {
 	if (daddr->a4 == x->id.daddr.a4 &&
 	    (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4))
@@ -1188,8 +1188,8 @@ __xfrm4_state_addr_check(struct xfrm_state *x,
 }
 
 static __inline__ int
-__xfrm6_state_addr_check(struct xfrm_state *x,
-			 xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm6_state_addr_check(const struct xfrm_state *x,
+			 const xfrm_address_t *daddr, const xfrm_address_t *saddr)
 {
 	if (!ipv6_addr_cmp((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) &&
 	    (!ipv6_addr_cmp((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr)|| 
@@ -1200,8 +1200,8 @@ __xfrm6_state_addr_check(struct xfrm_state *x,
 }
 
 static __inline__ int
-xfrm_state_addr_check(struct xfrm_state *x,
-		      xfrm_address_t *daddr, xfrm_address_t *saddr,
+xfrm_state_addr_check(const struct xfrm_state *x,
+		      const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		      unsigned short family)
 {
 	switch (family) {
@@ -1214,23 +1214,23 @@ xfrm_state_addr_check(struct xfrm_state *x,
 }
 
 static __inline__ int
-xfrm_state_addr_flow_check(struct xfrm_state *x, const struct flowi *fl,
+xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl,
 			   unsigned short family)
 {
 	switch (family) {
 	case AF_INET:
 		return __xfrm4_state_addr_check(x,
-						(xfrm_address_t *)&fl->fl4_dst,
-						(xfrm_address_t *)&fl->fl4_src);
+						(const xfrm_address_t *)&fl->fl4_dst,
+						(const xfrm_address_t *)&fl->fl4_src);
 	case AF_INET6:
 		return __xfrm6_state_addr_check(x,
-						(xfrm_address_t *)&fl->fl6_dst,
-						(xfrm_address_t *)&fl->fl6_src);
+						(const xfrm_address_t *)&fl->fl6_dst,
+						(const xfrm_address_t *)&fl->fl6_src);
 	}
 	return 0;
 }
 
-static inline int xfrm_state_kern(struct xfrm_state *x)
+static inline int xfrm_state_kern(const struct xfrm_state *x)
 {
 	return atomic_read(&x->tunnel_users);
 }
-- 
cgit v1.2.3


From 33765d06033cc4ba4d9ae6d3d606ef3f28773c1b Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 01:55:45 -0500
Subject: xfrm: Const'ify xfrm_address_t args to xfrm_state_find.

This required a const'ification in xfrm_init_tempstate() too.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h    | 4 ++--
 net/xfrm/xfrm_state.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 3205e5e4379f..44dccfcf9204 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1334,8 +1334,8 @@ extern int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 			   int (*func)(struct xfrm_state *, int, void*), void *);
 extern void xfrm_state_walk_done(struct xfrm_state_walk *walk);
 extern struct xfrm_state *xfrm_state_alloc(struct net *net);
-extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr,
-					  xfrm_address_t *saddr, 
+extern struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
+					  const xfrm_address_t *saddr,
 					  const struct flowi *fl,
 					  struct xfrm_tmpl *tmpl,
 					  struct xfrm_policy *pol, int *err,
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 9d9ac7ca3dd4..8496b3d3e85b 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -659,7 +659,7 @@ EXPORT_SYMBOL(xfrm_sad_getinfo);
 static int
 xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 		    const struct xfrm_tmpl *tmpl,
-		    xfrm_address_t *daddr, xfrm_address_t *saddr,
+		    const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    unsigned short family)
 {
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
@@ -790,7 +790,7 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 }
 
 struct xfrm_state *
-xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
+xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		const struct flowi *fl, struct xfrm_tmpl *tmpl,
 		struct xfrm_policy *pol, int *err,
 		unsigned short family)
-- 
cgit v1.2.3


From 8bc1f91e1f0e977fb95b11d8fa686f5091888110 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 24 Feb 2011 14:43:06 +0100
Subject: bootmem: Move __alloc_memory_core_early() to nobootmem.c

Now that bootmem.c and nobootmem.c are separate, there's no reason to
define __alloc_memory_core_early(), which is used only by nobootmem,
inside #ifdef in page_alloc.c.  Move it to nobootmem.c and make it
static.

This patch doesn't introduce any behavior change.

-tj: Updated commit description.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/mm.h |  2 --
 mm/nobootmem.c     | 25 +++++++++++++++++++++++++
 mm/page_alloc.c    | 28 ----------------------------
 3 files changed, 25 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6385fc17ad4..679300c050f5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1309,8 +1309,6 @@ int add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid);
 u64 __init find_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit);
-void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
-				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 6a018e49b7be..e2bdb07079ce 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -40,6 +40,31 @@ unsigned long max_pfn;
 unsigned long saved_max_pfn;
 #endif
 
+static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	void *ptr;
+	u64 addr;
+
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
+
+	addr = find_memory_core_early(nid, size, align, goal, limit);
+
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
+
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
+}
+
 /*
  * free_bootmem_late - free bootmem pages directly to page allocator
  * @addr: starting address of the range
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a243a7fd6922..603513609ba5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3780,34 +3780,6 @@ int __init add_from_early_node_map(struct range *range, int az,
 	return nr_range;
 }
 
-#ifdef CONFIG_NO_BOOTMEM
-void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
-					u64 goal, u64 limit)
-{
-	void *ptr;
-	u64 addr;
-
-	if (limit > memblock.current_limit)
-		limit = memblock.current_limit;
-
-	addr = find_memory_core_early(nid, size, align, goal, limit);
-
-	if (addr == MEMBLOCK_ERROR)
-		return NULL;
-
-	ptr = phys_to_virt(addr);
-	memset(ptr, 0, size);
-	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
-	/*
-	 * The min_count is set to 0 so that bootmem allocated blocks
-	 * are never reported as leaks.
-	 */
-	kmemleak_alloc(ptr, size, 0, 0);
-	return ptr;
-}
-#endif
-
-
 void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
 {
 	int i;
-- 
cgit v1.2.3


From 805bdaec1a44155db35f6ee5410d6bbc365324a8 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Thu, 24 Feb 2011 11:10:01 +0100
Subject: PM: Make ACPI wakeup from S5 work again when CONFIG_PM_SLEEP is unset

Commit 074037e (PM / Wakeup: Introduce wakeup source objects and
event statistics (v3)) caused ACPI wakeup to only work if
CONFIG_PM_SLEEP is set, but it also worked for CONFIG_PM_SLEEP unset
before.  This can be fixed by making device_set_wakeup_enable(),
device_init_wakeup() and device_may_wakeup() work in the same way
as before commit 074037e when CONFIG_PM_SLEEP is unset.

Reported-and-tested-by: Justin Maggard <jmaggard10@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
---
 include/linux/pm.h        |  2 ++
 include/linux/pm_wakeup.h | 25 ++++++++++++++-----------
 2 files changed, 16 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index dd9c7ab38270..21415cc91cbb 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -431,6 +431,8 @@ struct dev_pm_info {
 	struct list_head	entry;
 	struct completion	completion;
 	struct wakeup_source	*wakeup;
+#else
+	unsigned int		should_wakeup:1;
 #endif
 #ifdef CONFIG_PM_RUNTIME
 	struct timer_list	suspend_timer;
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
index 9cff00dd6b63..03a67db03d01 100644
--- a/include/linux/pm_wakeup.h
+++ b/include/linux/pm_wakeup.h
@@ -109,11 +109,6 @@ static inline bool device_can_wakeup(struct device *dev)
 	return dev->power.can_wakeup;
 }
 
-static inline bool device_may_wakeup(struct device *dev)
-{
-	return false;
-}
-
 static inline struct wakeup_source *wakeup_source_create(const char *name)
 {
 	return NULL;
@@ -134,24 +129,32 @@ static inline void wakeup_source_unregister(struct wakeup_source *ws) {}
 
 static inline int device_wakeup_enable(struct device *dev)
 {
-	return -EINVAL;
+	dev->power.should_wakeup = true;
+	return 0;
 }
 
 static inline int device_wakeup_disable(struct device *dev)
 {
+	dev->power.should_wakeup = false;
 	return 0;
 }
 
-static inline int device_init_wakeup(struct device *dev, bool val)
+static inline int device_set_wakeup_enable(struct device *dev, bool enable)
 {
-	dev->power.can_wakeup = val;
-	return val ? -EINVAL : 0;
+	dev->power.should_wakeup = enable;
+	return 0;
 }
 
+static inline int device_init_wakeup(struct device *dev, bool val)
+{
+	device_set_wakeup_capable(dev, val);
+	device_set_wakeup_enable(dev, val);
+	return 0;
+}
 
-static inline int device_set_wakeup_enable(struct device *dev, bool enable)
+static inline bool device_may_wakeup(struct device *dev)
 {
-	return -EINVAL;
+	return dev->power.can_wakeup && dev->power.should_wakeup;
 }
 
 static inline void __pm_stay_awake(struct wakeup_source *ws) {}
-- 
cgit v1.2.3


From dca8b089c95d94afa1d715df257de0286350e99d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 24 Feb 2011 13:38:12 -0800
Subject: ipv4: Rearrange how ip_route_newports() gets port keys.

ip_route_newports() is the only place in the entire kernel that
cares about the port members in the routing cache entry's lookup
flow key.

Therefore the only reason we store an entire flow inside of the
struct rtentry is for this one special case.

Rewrite ip_route_newports() such that:

1) The caller passes in the original port values, so we don't need
   to use the rth->fl.fl_ip_{s,d}port values to remember them.

2) The lookup flow is constructed by hand instead of being copied
   from the routing cache entry's flow.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 19 +++++++++++--------
 net/dccp/ipv4.c     | 10 +++++++---
 net/ipv4/tcp_ipv4.c |  6 +++++-
 3 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index bf790c1c6ac8..b3f89ad04e0b 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -200,16 +200,19 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 }
 
 static inline int ip_route_newports(struct rtable **rp, u8 protocol,
+				    __be16 orig_sport, __be16 orig_dport,
 				    __be16 sport, __be16 dport, struct sock *sk)
 {
-	if (sport != (*rp)->fl.fl_ip_sport ||
-	    dport != (*rp)->fl.fl_ip_dport) {
-		struct flowi fl;
-
-		memcpy(&fl, &(*rp)->fl, sizeof(fl));
-		fl.fl_ip_sport = sport;
-		fl.fl_ip_dport = dport;
-		fl.proto = protocol;
+	if (sport != orig_sport || dport != orig_dport) {
+		struct flowi fl = { .oif = (*rp)->fl.oif,
+				    .mark = (*rp)->fl.mark,
+				    .fl4_dst = (*rp)->fl.fl4_dst,
+				    .fl4_src = (*rp)->fl.fl4_src,
+				    .fl4_tos = (*rp)->fl.fl4_tos,
+				    .proto = (*rp)->fl.proto,
+				    .fl_ip_sport = sport,
+				    .fl_ip_dport = dport };
+
 		if (inet_sk(sk)->transparent)
 			fl.flags |= FLOWI_FLAG_ANYSRC;
 		if (protocol == IPPROTO_TCP)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 45a434f94169..937989199c80 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -43,6 +43,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct inet_sock *inet = inet_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
+	__be16 orig_sport, orig_dport;
 	struct rtable *rt;
 	__be32 daddr, nexthop;
 	int tmp;
@@ -63,10 +64,12 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		nexthop = inet->opt->faddr;
 	}
 
+	orig_sport = inet->inet_sport;
+	orig_dport = usin->sin_port;
 	tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
 			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			       IPPROTO_DCCP,
-			       inet->inet_sport, usin->sin_port, sk, 1);
+			       orig_sport, orig_dport, sk, 1);
 	if (tmp < 0)
 		return tmp;
 
@@ -99,8 +102,9 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err != 0)
 		goto failure;
 
-	err = ip_route_newports(&rt, IPPROTO_DCCP, inet->inet_sport,
-				inet->inet_dport, sk);
+	err = ip_route_newports(&rt, IPPROTO_DCCP,
+				orig_sport, orig_dport,
+				inet->inet_sport, inet->inet_dport, sk);
 	if (err != 0)
 		goto failure;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ef5a90beb9b0..27a0cc8cc888 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -149,6 +149,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct inet_sock *inet = inet_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
+	__be16 orig_sport, orig_dport;
 	struct rtable *rt;
 	__be32 daddr, nexthop;
 	int tmp;
@@ -167,10 +168,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		nexthop = inet->opt->faddr;
 	}
 
+	orig_sport = inet->inet_sport;
+	orig_dport = usin->sin_port;
 	tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
 			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			       IPPROTO_TCP,
-			       inet->inet_sport, usin->sin_port, sk, 1);
+			       orig_sport, orig_dport, sk, 1);
 	if (tmp < 0) {
 		if (tmp == -ENETUNREACH)
 			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
@@ -234,6 +237,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		goto failure;
 
 	err = ip_route_newports(&rt, IPPROTO_TCP,
+				orig_sport, orig_dport,
 				inet->inet_sport, inet->inet_dport, sk);
 	if (err)
 		goto failure;
-- 
cgit v1.2.3


From b552f7e3a9524abcbcdf86f0a99b2be58e55a9c6 Mon Sep 17 00:00:00 2001
From: Changli Gao <xiaosuo@gmail.com>
Date: Sat, 19 Feb 2011 17:32:28 +0800
Subject: ipvs: unify the formula to estimate the overhead of processing
 connections

lc and wlc use the same formula, but lblc and lblcr use another one. There
is no reason for using two different formulas for the lc variants.

The formula used by lc is used by all the lc variants in this patch.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Acked-by: Wensong Zhang <wensong@linux-vs.org>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              | 14 ++++++++++++++
 net/netfilter/ipvs/ip_vs_lblc.c  | 13 +++----------
 net/netfilter/ipvs/ip_vs_lblcr.c | 25 +++++++------------------
 net/netfilter/ipvs/ip_vs_lc.c    | 18 +-----------------
 net/netfilter/ipvs/ip_vs_wlc.c   | 20 ++------------------
 5 files changed, 27 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 17b01b2d48f9..e74da41ebd1b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1243,6 +1243,20 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 /* CONFIG_IP_VS_NFCT */
 #endif
 
+static inline unsigned int
+ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
+{
+	/*
+	 * We think the overhead of processing active connections is 256
+	 * times higher than that of inactive connections in average. (This
+	 * 256 times might not be accurate, we will change it later) We
+	 * use the following formula to estimate the overhead now:
+	 *		  dest->activeconns*256 + dest->inactconns
+	 */
+	return (atomic_read(&dest->activeconns) << 8) +
+		atomic_read(&dest->inactconns);
+}
+
 #endif /* __KERNEL__ */
 
 #endif	/* _NET_IP_VS_H */
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 4a9c8cd19690..6bf7a807649c 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -389,12 +389,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 	int loh, doh;
 
 	/*
-	 * We think the overhead of processing active connections is fifty
-	 * times higher than that of inactive connections in average. (This
-	 * fifty times might not be accurate, we will change it later.) We
-	 * use the following formula to estimate the overhead:
-	 *                dest->activeconns*50 + dest->inactconns
-	 * and the load:
+	 * We use the following formula to estimate the load:
 	 *                (dest overhead) / dest->weight
 	 *
 	 * Remember -- no floats in kernel mode!!!
@@ -410,8 +405,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 			continue;
 		if (atomic_read(&dest->weight) > 0) {
 			least = dest;
-			loh = atomic_read(&least->activeconns) * 50
-				+ atomic_read(&least->inactconns);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -425,8 +419,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (loh * atomic_read(&dest->weight) >
 		    doh * atomic_read(&least->weight)) {
 			least = dest;
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index bd329b1e9589..00631765b92a 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -178,8 +178,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 
 		if ((atomic_read(&least->weight) > 0)
 		    && (least->flags & IP_VS_DEST_F_AVAILABLE)) {
-			loh = atomic_read(&least->activeconns) * 50
-				+ atomic_read(&least->inactconns);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -192,8 +191,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if ((loh * atomic_read(&dest->weight) >
 		     doh * atomic_read(&least->weight))
 		    && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
@@ -228,8 +226,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
 	list_for_each_entry(e, &set->list, list) {
 		most = e->dest;
 		if (atomic_read(&most->weight) > 0) {
-			moh = atomic_read(&most->activeconns) * 50
-				+ atomic_read(&most->inactconns);
+			moh = ip_vs_dest_conn_overhead(most);
 			goto nextstage;
 		}
 	}
@@ -239,8 +236,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
   nextstage:
 	list_for_each_entry(e, &set->list, list) {
 		dest = e->dest;
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		/* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */
 		if ((moh * atomic_read(&dest->weight) <
 		     doh * atomic_read(&most->weight))
@@ -563,12 +559,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 	int loh, doh;
 
 	/*
-	 * We think the overhead of processing active connections is fifty
-	 * times higher than that of inactive connections in average. (This
-	 * fifty times might not be accurate, we will change it later.) We
-	 * use the following formula to estimate the overhead:
-	 *                dest->activeconns*50 + dest->inactconns
-	 * and the load:
+	 * We use the following formula to estimate the load:
 	 *                (dest overhead) / dest->weight
 	 *
 	 * Remember -- no floats in kernel mode!!!
@@ -585,8 +576,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 
 		if (atomic_read(&dest->weight) > 0) {
 			least = dest;
-			loh = atomic_read(&least->activeconns) * 50
-				+ atomic_read(&least->inactconns);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -600,8 +590,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (loh * atomic_read(&dest->weight) >
 		    doh * atomic_read(&least->weight)) {
 			least = dest;
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 60638007c6c7..f391819c0cca 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -22,22 +22,6 @@
 
 #include <net/ip_vs.h>
 
-
-static inline unsigned int
-ip_vs_lc_dest_overhead(struct ip_vs_dest *dest)
-{
-	/*
-	 * We think the overhead of processing active connections is 256
-	 * times higher than that of inactive connections in average. (This
-	 * 256 times might not be accurate, we will change it later) We
-	 * use the following formula to estimate the overhead now:
-	 *		  dest->activeconns*256 + dest->inactconns
-	 */
-	return (atomic_read(&dest->activeconns) << 8) +
-		atomic_read(&dest->inactconns);
-}
-
-
 /*
  *	Least Connection scheduling
  */
@@ -62,7 +46,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		if ((dest->flags & IP_VS_DEST_F_OVERLOAD) ||
 		    atomic_read(&dest->weight) == 0)
 			continue;
-		doh = ip_vs_lc_dest_overhead(dest);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (!least || doh < loh) {
 			least = dest;
 			loh = doh;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index fdf0f58962a4..bc1bfc48a17f 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -27,22 +27,6 @@
 
 #include <net/ip_vs.h>
 
-
-static inline unsigned int
-ip_vs_wlc_dest_overhead(struct ip_vs_dest *dest)
-{
-	/*
-	 * We think the overhead of processing active connections is 256
-	 * times higher than that of inactive connections in average. (This
-	 * 256 times might not be accurate, we will change it later) We
-	 * use the following formula to estimate the overhead now:
-	 *		  dest->activeconns*256 + dest->inactconns
-	 */
-	return (atomic_read(&dest->activeconns) << 8) +
-		atomic_read(&dest->inactconns);
-}
-
-
 /*
  *	Weighted Least Connection scheduling
  */
@@ -71,7 +55,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
 		    atomic_read(&dest->weight) > 0) {
 			least = dest;
-			loh = ip_vs_wlc_dest_overhead(least);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -85,7 +69,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	list_for_each_entry_continue(dest, &svc->destinations, n_list) {
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
-		doh = ip_vs_wlc_dest_overhead(dest);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (loh * atomic_read(&dest->weight) >
 		    doh * atomic_read(&least->weight)) {
 			least = dest;
-- 
cgit v1.2.3


From df173bda2639ac744ccf596ec1f8f7e66fe4c343 Mon Sep 17 00:00:00 2001
From: stephen hemminger <shemminger@vyatta.com>
Date: Wed, 23 Feb 2011 13:04:19 +0000
Subject: netem: define NETEM_DIST_MAX

Rather than magic constant in code, expose the maximum size of
packet distribution table in API. In iproute2, q_netem defines
MAX_DIST as 16K already.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/pkt_sched.h | 1 +
 net/sched/sch_netem.c     | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index 5afee2b238bd..891382268fe1 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -495,6 +495,7 @@ struct tc_netem_corrupt {
 };
 
 #define NETEM_DIST_SCALE	8192
+#define NETEM_DIST_MAX		16384
 
 /* DRR */
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 86dad1eee549..289febd3ccac 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -332,7 +332,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
 	int i;
 	size_t s;
 
-	if (n > 65536)
+	if (n > NETEM_DIST_MAX)
 		return -EINVAL;
 
 	s = sizeof(struct disttable) + n * sizeof(s16);
-- 
cgit v1.2.3


From 661b79725fea030803a89a16cda506bac8eeca78 Mon Sep 17 00:00:00 2001
From: stephen hemminger <shemminger@vyatta.com>
Date: Wed, 23 Feb 2011 13:04:21 +0000
Subject: netem: revised correlated loss generator

This is a patch originated with Stefano Salsano and Fabio Ludovici.
It provides several alternative loss models for use with netem.
This patch adds two state machine based loss models.

See: http://netgroup.uniroma2.it/twiki/bin/view.cgi/Main/NetemCLG

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/pkt_sched.h |  26 +++++
 net/sched/sch_netem.c     | 274 +++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 296 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index 891382268fe1..b1032a3fafdc 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -464,6 +464,7 @@ enum {
 	TCA_NETEM_DELAY_DIST,
 	TCA_NETEM_REORDER,
 	TCA_NETEM_CORRUPT,
+	TCA_NETEM_LOSS,
 	__TCA_NETEM_MAX,
 };
 
@@ -494,6 +495,31 @@ struct tc_netem_corrupt {
 	__u32	correlation;
 };
 
+enum {
+	NETEM_LOSS_UNSPEC,
+	NETEM_LOSS_GI,		/* General Intuitive - 4 state model */
+	NETEM_LOSS_GE,		/* Gilbert Elliot models */
+	__NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probablities for 4 state model */
+struct tc_netem_gimodel {
+	__u32	p13;
+	__u32	p31;
+	__u32	p32;
+	__u32	p14;
+	__u32	p23;
+};
+
+/* Gilbert-Elliot models */
+struct tc_netem_gemodel {
+	__u32 p;
+	__u32 r;
+	__u32 h;
+	__u32 k1;
+};
+
 #define NETEM_DIST_SCALE	8192
 #define NETEM_DIST_MAX		16384
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index f176890eeef0..5bbcccc353d0 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -47,6 +47,20 @@
 	 layering other disciplines.  It does not need to do bandwidth
 	 control either since that can be handled by using token
 	 bucket or other rate control.
+
+     Correlated Loss Generator models
+
+	Added generation of correlated loss according to the
+	"Gilbert-Elliot" model, a 4-state markov model.
+
+	References:
+	[1] NetemCLG Home http://netgroup.uniroma2.it/NetemCLG
+	[2] S. Salsano, F. Ludovici, A. Ordine, "Definition of a general
+	and intuitive loss model for packet networks and its implementation
+	in the Netem module in the Linux kernel", available in [1]
+
+	Authors: Stefano Salsano <stefano.salsano at uniroma2.it
+		 Fabio Ludovici <fabio.ludovici at yahoo.it>
 */
 
 struct netem_sched_data {
@@ -73,6 +87,26 @@ struct netem_sched_data {
 		u32  size;
 		s16 table[0];
 	} *delay_dist;
+
+	enum  {
+		CLG_RANDOM,
+		CLG_4_STATES,
+		CLG_GILB_ELL,
+	} loss_model;
+
+	/* Correlated Loss Generation models */
+	struct clgstate {
+		/* state of the Markov chain */
+		u8 state;
+
+		/* 4-states and Gilbert-Elliot models */
+		u32 a1;	/* p13 for 4-states or p for GE */
+		u32 a2;	/* p31 for 4-states or r for GE */
+		u32 a3;	/* p32 for 4-states or h for GE */
+		u32 a4;	/* p14 for 4-states or 1-k for GE */
+		u32 a5; /* p23 used only in 4-states */
+	} clg;
+
 };
 
 /* Time stamp put into socket buffer control block */
@@ -115,6 +149,122 @@ static u32 get_crandom(struct crndstate *state)
 	return answer;
 }
 
+/* loss_4state - 4-state model loss generator
+ * Generates losses according to the 4-state Markov chain adopted in
+ * the GI (General and Intuitive) loss model.
+ */
+static bool loss_4state(struct netem_sched_data *q)
+{
+	struct clgstate *clg = &q->clg;
+	u32 rnd = net_random();
+
+	/*
+	 * Makes a comparision between rnd and the transition
+	 * probabilities outgoing from the current state, then decides the
+	 * next state and if the next packet has to be transmitted or lost.
+	 * The four states correspond to:
+	 *   1 => successfully transmitted packets within a gap period
+	 *   4 => isolated losses within a gap period
+	 *   3 => lost packets within a burst period
+	 *   2 => successfully transmitted packets within a burst period
+	 */
+	switch (clg->state) {
+	case 1:
+		if (rnd < clg->a4) {
+			clg->state = 4;
+			return true;
+		} else if (clg->a4 < rnd && rnd < clg->a1) {
+			clg->state = 3;
+			return true;
+		} else if (clg->a1 < rnd)
+			clg->state = 1;
+
+		break;
+	case 2:
+		if (rnd < clg->a5) {
+			clg->state = 3;
+			return true;
+		} else
+			clg->state = 2;
+
+		break;
+	case 3:
+		if (rnd < clg->a3)
+			clg->state = 2;
+		else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) {
+			clg->state = 1;
+			return true;
+		} else if (clg->a2 + clg->a3 < rnd) {
+			clg->state = 3;
+			return true;
+		}
+		break;
+	case 4:
+		clg->state = 1;
+		break;
+	}
+
+	return false;
+}
+
+/* loss_gilb_ell - Gilbert-Elliot model loss generator
+ * Generates losses according to the Gilbert-Elliot loss model or
+ * its special cases  (Gilbert or Simple Gilbert)
+ *
+ * Makes a comparision between random number and the transition
+ * probabilities outgoing from the current state, then decides the
+ * next state. A second random number is extracted and the comparision
+ * with the loss probability of the current state decides if the next
+ * packet will be transmitted or lost.
+ */
+static bool loss_gilb_ell(struct netem_sched_data *q)
+{
+	struct clgstate *clg = &q->clg;
+
+	switch (clg->state) {
+	case 1:
+		if (net_random() < clg->a1)
+			clg->state = 2;
+		if (net_random() < clg->a4)
+			return true;
+	case 2:
+		if (net_random() < clg->a2)
+			clg->state = 1;
+		if (clg->a3 > net_random())
+			return true;
+	}
+
+	return false;
+}
+
+static bool loss_event(struct netem_sched_data *q)
+{
+	switch (q->loss_model) {
+	case CLG_RANDOM:
+		/* Random packet drop 0 => none, ~0 => all */
+		return q->loss && q->loss >= get_crandom(&q->loss_cor);
+
+	case CLG_4_STATES:
+		/* 4state loss model algorithm (used also for GI model)
+		* Extracts a value from the markov 4 state loss generator,
+		* if it is 1 drops a packet and if needed writes the event in
+		* the kernel logs
+		*/
+		return loss_4state(q);
+
+	case CLG_GILB_ELL:
+		/* Gilbert-Elliot loss model algorithm
+		* Extracts a value from the Gilbert-Elliot loss generator,
+		* if it is 1 drops a packet and if needed writes the event in
+		* the kernel logs
+		*/
+		return loss_gilb_ell(q);
+	}
+
+	return false;	/* not reached */
+}
+
+
 /* tabledist - return a pseudo-randomly distributed value with mean mu and
  * std deviation sigma.  Uses table lookup to approximate the desired
  * distribution, and a uniformly-distributed pseudo-random source.
@@ -167,8 +317,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
 		++count;
 
-	/* Random packet drop 0 => none, ~0 => all */
-	if (q->loss && q->loss >= get_crandom(&q->loss_cor))
+	/* Drop packet? */
+	if (loss_event(q))
 		--count;
 
 	if (count == 0) {
@@ -385,10 +535,66 @@ static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
 	init_crandom(&q->corrupt_cor, r->correlation);
 }
 
+static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
+{
+	struct netem_sched_data *q = qdisc_priv(sch);
+	const struct nlattr *la;
+	int rem;
+
+	nla_for_each_nested(la, attr, rem) {
+		u16 type = nla_type(la);
+
+		switch(type) {
+		case NETEM_LOSS_GI: {
+			const struct tc_netem_gimodel *gi = nla_data(la);
+
+			if (nla_len(la) != sizeof(struct tc_netem_gimodel)) {
+				pr_info("netem: incorrect gi model size\n");
+				return -EINVAL;
+			}
+
+			q->loss_model = CLG_4_STATES;
+
+			q->clg.state = 1;
+			q->clg.a1 = gi->p13;
+			q->clg.a2 = gi->p31;
+			q->clg.a3 = gi->p32;
+			q->clg.a4 = gi->p14;
+			q->clg.a5 = gi->p23;
+			break;
+		}
+
+		case NETEM_LOSS_GE: {
+			const struct tc_netem_gemodel *ge = nla_data(la);
+
+			if (nla_len(la) != sizeof(struct tc_netem_gemodel)) {
+				pr_info("netem: incorrect gi model size\n");
+				return -EINVAL;
+			}
+
+			q->loss_model = CLG_GILB_ELL;
+			q->clg.state = 1;
+			q->clg.a1 = ge->p;
+			q->clg.a2 = ge->r;
+			q->clg.a3 = ge->h;
+			q->clg.a4 = ge->k1;
+			break;
+		}
+
+		default:
+			pr_info("netem: unknown loss type %u\n", type);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_CORR]	= { .len = sizeof(struct tc_netem_corr) },
 	[TCA_NETEM_REORDER]	= { .len = sizeof(struct tc_netem_reorder) },
 	[TCA_NETEM_CORRUPT]	= { .len = sizeof(struct tc_netem_corrupt) },
+	[TCA_NETEM_LOSS]	= { .type = NLA_NESTED },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -396,11 +602,15 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 {
 	int nested_len = nla_len(nla) - NLA_ALIGN(len);
 
-	if (nested_len < 0)
+	if (nested_len < 0) {
+		pr_info("netem: invalid attributes len %d\n", nested_len);
 		return -EINVAL;
+	}
+
 	if (nested_len >= nla_attr_size(0))
 		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
 				 nested_len, policy);
+
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 	return 0;
 }
@@ -456,7 +666,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_NETEM_CORRUPT])
 		get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
 
-	return 0;
+	q->loss_model = CLG_RANDOM;
+	if (tb[TCA_NETEM_LOSS])
+		ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
+
+	return ret;
 }
 
 /*
@@ -551,6 +765,7 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt)
 
 	qdisc_watchdog_init(&q->watchdog, sch);
 
+	q->loss_model = CLG_RANDOM;
 	q->qdisc = qdisc_create_dflt(sch->dev_queue, &tfifo_qdisc_ops,
 				     TC_H_MAKE(sch->handle, 1));
 	if (!q->qdisc) {
@@ -575,6 +790,54 @@ static void netem_destroy(struct Qdisc *sch)
 	dist_free(q->delay_dist);
 }
 
+static int dump_loss_model(const struct netem_sched_data *q,
+			   struct sk_buff *skb)
+{
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, TCA_NETEM_LOSS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	switch (q->loss_model) {
+	case CLG_RANDOM:
+		/* legacy loss model */
+		nla_nest_cancel(skb, nest);
+		return 0;	/* no data */
+
+	case CLG_4_STATES: {
+		struct tc_netem_gimodel gi = {
+			.p13 = q->clg.a1,
+			.p31 = q->clg.a2,
+			.p32 = q->clg.a3,
+			.p14 = q->clg.a4,
+			.p23 = q->clg.a5,
+		};
+
+		NLA_PUT(skb, NETEM_LOSS_GI, sizeof(gi), &gi);
+		break;
+	}
+	case CLG_GILB_ELL: {
+		struct tc_netem_gemodel ge = {
+			.p = q->clg.a1,
+			.r = q->clg.a2,
+			.h = q->clg.a3,
+			.k1 = q->clg.a4,
+		};
+
+		NLA_PUT(skb, NETEM_LOSS_GE, sizeof(ge), &ge);
+		break;
+	}
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
 static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	const struct netem_sched_data *q = qdisc_priv(sch);
@@ -605,6 +868,9 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	corrupt.correlation = q->corrupt_cor.rho;
 	NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt);
 
+	if (dump_loss_model(q, skb) != 0)
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, nla);
 
 nla_put_failure:
-- 
cgit v1.2.3


From c80a420995e721099906607b07c09a24543b31d9 Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Thu, 2 Dec 2010 17:55:00 +0000
Subject: xen-blkfront: handle Xen major numbers other than XENVBD

This patch makes sure blkfront handles correctly virtual device numbers
corresponding to Xen emulated IDE and SCSI disks: in those cases
blkfront translates the major number to XENVBD and the minor number to a
low xvd minor.

Note: this behaviour is different from what old xenlinux PV guests used
to do: they used to steal an IDE or SCSI major number and use it
instead.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Jeremy Fitzhardinge <jeremy@goop.org>
---
 drivers/block/xen-blkfront.c     | 79 +++++++++++++++++++++++++++++++++++++---
 include/xen/interface/io/blkif.h | 21 +++++++++++
 2 files changed, 95 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d7aa39e349a6..64d9c6dfc634 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -120,6 +120,10 @@ static DEFINE_SPINLOCK(minor_lock);
 #define EXTENDED (1<<EXT_SHIFT)
 #define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
 #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
+#define EMULATED_HD_DISK_MINOR_OFFSET (0)
+#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
+#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
@@ -434,6 +438,65 @@ static void xlvbd_flush(struct blkfront_info *info)
 	       info->feature_flush ? "enabled" : "disabled");
 }
 
+static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
+{
+	int major;
+	major = BLKIF_MAJOR(vdevice);
+	*minor = BLKIF_MINOR(vdevice);
+	switch (major) {
+		case XEN_IDE0_MAJOR:
+			*offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
+			*minor = ((*minor / 64) * PARTS_PER_DISK) +
+				EMULATED_HD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_IDE1_MAJOR:
+			*offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
+			*minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
+				EMULATED_HD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK0_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK1_MAJOR:
+		case XEN_SCSI_DISK2_MAJOR:
+		case XEN_SCSI_DISK3_MAJOR:
+		case XEN_SCSI_DISK4_MAJOR:
+		case XEN_SCSI_DISK5_MAJOR:
+		case XEN_SCSI_DISK6_MAJOR:
+		case XEN_SCSI_DISK7_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + 
+				((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
+				EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor +
+				((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
+				EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK8_MAJOR:
+		case XEN_SCSI_DISK9_MAJOR:
+		case XEN_SCSI_DISK10_MAJOR:
+		case XEN_SCSI_DISK11_MAJOR:
+		case XEN_SCSI_DISK12_MAJOR:
+		case XEN_SCSI_DISK13_MAJOR:
+		case XEN_SCSI_DISK14_MAJOR:
+		case XEN_SCSI_DISK15_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + 
+				((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
+				EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor +
+				((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
+				EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XENVBD_MAJOR:
+			*offset = *minor / PARTS_PER_DISK;
+			break;
+		default:
+			printk(KERN_WARNING "blkfront: your disk configuration is "
+					"incorrect, please use an xvd device instead\n");
+			return -ENODEV;
+	}
+	return 0;
+}
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 			       struct blkfront_info *info,
@@ -441,7 +504,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 {
 	struct gendisk *gd;
 	int nr_minors = 1;
-	int err = -ENODEV;
+	int err;
 	unsigned int offset;
 	int minor;
 	int nr_parts;
@@ -456,12 +519,20 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	}
 
 	if (!VDEV_IS_EXTENDED(info->vdevice)) {
-		minor = BLKIF_MINOR(info->vdevice);
-		nr_parts = PARTS_PER_DISK;
+		err = xen_translate_vdev(info->vdevice, &minor, &offset);
+		if (err)
+			return err;		
+ 		nr_parts = PARTS_PER_DISK;
 	} else {
 		minor = BLKIF_MINOR_EXT(info->vdevice);
 		nr_parts = PARTS_PER_EXT_DISK;
+		offset = minor / nr_parts;
+		if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+			printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
+					"emulated IDE disks,\n\t choose an xvd device name"
+					"from xvde on\n", info->vdevice);
 	}
+	err = -ENODEV;
 
 	if ((minor % nr_parts) == 0)
 		nr_minors = nr_parts;
@@ -475,8 +546,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (gd == NULL)
 		goto release;
 
-	offset = minor / nr_parts;
-
 	if (nr_minors > 1) {
 		if (offset < 26)
 			sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index c2d1fa4dc1ee..68dd2b49635c 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -91,4 +91,25 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
 #define VDISK_REMOVABLE    0x2
 #define VDISK_READONLY     0x4
 
+/* Xen-defined major numbers for virtual disks, they look strangely
+ * familiar */
+#define XEN_IDE0_MAJOR	3
+#define XEN_IDE1_MAJOR	22
+#define XEN_SCSI_DISK0_MAJOR	8
+#define XEN_SCSI_DISK1_MAJOR	65
+#define XEN_SCSI_DISK2_MAJOR	66
+#define XEN_SCSI_DISK3_MAJOR	67
+#define XEN_SCSI_DISK4_MAJOR	68
+#define XEN_SCSI_DISK5_MAJOR	69
+#define XEN_SCSI_DISK6_MAJOR	70
+#define XEN_SCSI_DISK7_MAJOR	71
+#define XEN_SCSI_DISK8_MAJOR	128
+#define XEN_SCSI_DISK9_MAJOR	129
+#define XEN_SCSI_DISK10_MAJOR	130
+#define XEN_SCSI_DISK11_MAJOR	131
+#define XEN_SCSI_DISK12_MAJOR	132
+#define XEN_SCSI_DISK13_MAJOR	133
+#define XEN_SCSI_DISK14_MAJOR	134
+#define XEN_SCSI_DISK15_MAJOR	135
+
 #endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
-- 
cgit v1.2.3


From a8b7458363b9174f3c2196ca6085630b4b30b7a1 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Thu, 17 Feb 2011 11:04:20 +0000
Subject: xen: switch to new schedop hypercall by default.

Rename old interface to sched_op_compat and rename sched_op_new to
simply sched_op.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/include/asm/xen/hypercall.h | 4 ++--
 include/xen/interface/xen.h          | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a7d5823862b4..8508bfe52296 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -287,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set)
 static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
-	return _hypercall2(int, sched_op_new, cmd, arg);
+	return _hypercall2(int, sched_op, cmd, arg);
 }
 
 static inline long
@@ -432,7 +432,7 @@ HYPERVISOR_suspend(unsigned long start_info_mfn)
 	 * hypercall calling convention this is the third hypercall
 	 * argument, which is start_info_mfn here.
 	 */
-	return _hypercall3(int, sched_op_new, SCHEDOP_shutdown, &r, start_info_mfn);
+	return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
 }
 
 static inline int
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 2befa3e2f1bc..b33257bc7e83 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -30,7 +30,7 @@
 #define __HYPERVISOR_stack_switch          3
 #define __HYPERVISOR_set_callbacks         4
 #define __HYPERVISOR_fpu_taskswitch        5
-#define __HYPERVISOR_sched_op              6
+#define __HYPERVISOR_sched_op_compat       6
 #define __HYPERVISOR_dom0_op               7
 #define __HYPERVISOR_set_debugreg          8
 #define __HYPERVISOR_get_debugreg          9
@@ -52,7 +52,7 @@
 #define __HYPERVISOR_mmuext_op            26
 #define __HYPERVISOR_acm_op               27
 #define __HYPERVISOR_nmi_op               28
-#define __HYPERVISOR_sched_op_new         29
+#define __HYPERVISOR_sched_op             29
 #define __HYPERVISOR_callback_op          30
 #define __HYPERVISOR_xenoprof_op          31
 #define __HYPERVISOR_event_channel_op     32
-- 
cgit v1.2.3


From 03c8142bd2fb3b87effa6ecb2f8957be588bc85f Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Thu, 17 Feb 2011 11:04:20 +0000
Subject: xen: suspend: add "arch" to pre/post suspend hooks

xen_pre_device_suspend is unused on ia64.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/ia64/xen/suspend.c | 9 ++-------
 arch/x86/xen/suspend.c  | 6 +++---
 drivers/xen/manage.c    | 6 +++---
 include/xen/xen-ops.h   | 6 +++---
 4 files changed, 11 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/xen/suspend.c b/arch/ia64/xen/suspend.c
index fd66b048c6fa..419c8620945a 100644
--- a/arch/ia64/xen/suspend.c
+++ b/arch/ia64/xen/suspend.c
@@ -37,19 +37,14 @@ xen_mm_unpin_all(void)
 	/* nothing */
 }
 
-void xen_pre_device_suspend(void)
-{
-	/* nothing */
-}
-
 void
-xen_pre_suspend()
+xen_arch_pre_suspend()
 {
 	/* nothing */
 }
 
 void
-xen_post_suspend(int suspend_cancelled)
+xen_arch_post_suspend(int suspend_cancelled)
 {
 	if (suspend_cancelled)
 		return;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 4a3d3dd3dd30..45329c8c226e 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -12,7 +12,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-void xen_pre_suspend(void)
+void xen_arch_pre_suspend(void)
 {
 	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
 	xen_start_info->console.domU.mfn =
@@ -26,7 +26,7 @@ void xen_pre_suspend(void)
 		BUG();
 }
 
-void xen_hvm_post_suspend(int suspend_cancelled)
+void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
@@ -41,7 +41,7 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 #endif
 }
 
-void xen_post_suspend(int suspend_cancelled)
+void xen_arch_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
 
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 6ce6b91e7645..134eb73ca596 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -61,7 +61,7 @@ static int xen_hvm_suspend(void *data)
 	 */
 	si->cancelled = HYPERVISOR_suspend(si->arg);
 
-	xen_hvm_post_suspend(si->cancelled);
+	xen_arch_hvm_post_suspend(si->cancelled);
 	gnttab_resume();
 
 	if (!si->cancelled) {
@@ -91,7 +91,7 @@ static int xen_suspend(void *data)
 
 	xen_mm_pin_all();
 	gnttab_suspend();
-	xen_pre_suspend();
+	xen_arch_pre_suspend();
 
 	/*
 	 * This hypercall returns 1 if suspend was cancelled
@@ -100,7 +100,7 @@ static int xen_suspend(void *data)
 	 */
 	si->cancelled = HYPERVISOR_suspend(si->arg);
 
-	xen_post_suspend(si->cancelled);
+	xen_arch_post_suspend(si->cancelled);
 	gnttab_resume();
 	xen_mm_unpin_all();
 
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b92154a264..03c85d7387fb 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -5,9 +5,9 @@
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
-void xen_pre_suspend(void);
-void xen_post_suspend(int suspend_cancelled);
-void xen_hvm_post_suspend(int suspend_cancelled);
+void xen_arch_pre_suspend(void);
+void xen_arch_post_suspend(int suspend_cancelled);
+void xen_arch_hvm_post_suspend(int suspend_cancelled);
 
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);
-- 
cgit v1.2.3


From a8059512b120362b15424f152b2548fe8b11bd0c Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Thu, 24 Feb 2011 23:14:57 +0000
Subject: Phonet: implement per-socket destination/peer address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/phonet.h |  1 +
 net/phonet/af_phonet.c      | 19 ++++++++++++++-----
 net/phonet/socket.c         |  4 ++--
 3 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h
index 5395e09187df..68e509750caa 100644
--- a/include/net/phonet/phonet.h
+++ b/include/net/phonet/phonet.h
@@ -36,6 +36,7 @@
 struct pn_sock {
 	struct sock	sk;
 	u16		sobject;
+	u16		dobject;
 	u8		resource;
 };
 
diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 1072b2c19d31..30cc676c35fd 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -110,6 +110,7 @@ static int pn_socket_create(struct net *net, struct socket *sock, int protocol,
 	sk->sk_protocol = protocol;
 	pn = pn_sk(sk);
 	pn->sobject = 0;
+	pn->dobject = 0;
 	pn->resource = 0;
 	sk->sk_prot->init(sk);
 	err = 0;
@@ -242,8 +243,18 @@ int pn_skb_send(struct sock *sk, struct sk_buff *skb,
 	struct net_device *dev;
 	struct pn_sock *pn = pn_sk(sk);
 	int err;
-	u16 src;
-	u8 daddr = pn_sockaddr_get_addr(target), saddr = PN_NO_ADDR;
+	u16 src, dst;
+	u8 daddr, saddr, res;
+
+	src = pn->sobject;
+	if (target != NULL) {
+		dst = pn_sockaddr_get_object(target);
+		res = pn_sockaddr_get_resource(target);
+	} else {
+		dst = pn->dobject;
+		res = pn->resource;
+	}
+	daddr = pn_addr(dst);
 
 	err = -EHOSTUNREACH;
 	if (sk->sk_bound_dev_if)
@@ -271,12 +282,10 @@ int pn_skb_send(struct sock *sk, struct sk_buff *skb,
 	if (saddr == PN_NO_ADDR)
 		goto drop;
 
-	src = pn->sobject;
 	if (!pn_addr(src))
 		src = pn_object(saddr, pn_obj(src));
 
-	err = pn_send(skb, dev, pn_sockaddr_get_object(target),
-			src, pn_sockaddr_get_resource(target), 0);
+	err = pn_send(skb, dev, dst, src, res, 0);
 	dev_put(dev);
 	return err;
 
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index ceb5143f5ef9..65a03338769e 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -633,8 +633,8 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v)
 
 		seq_printf(seq, "%2d %04X:%04X:%02X %02X %08X:%08X %5d %lu "
 			"%d %p %d%n",
-			sk->sk_protocol, pn->sobject, 0, pn->resource,
-			sk->sk_state,
+			sk->sk_protocol, pn->sobject, pn->dobject,
+			pn->resource, sk->sk_state,
 			sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk),
 			sock_i_uid(sk), sock_i_ino(sk),
 			atomic_read(&sk->sk_refcnt), sk,
-- 
cgit v1.2.3


From 14ba8faebcc241e4d60a4ef4a7d3fdef1c2e846f Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Thu, 24 Feb 2011 23:14:58 +0000
Subject: Phonet: use socket destination in pipe protocol
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pep.h |  1 -
 net/phonet/pep.c         | 41 ++++++++++++++++-------------------------
 2 files changed, 16 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h
index b60b28c99e87..788ccf353582 100644
--- a/include/net/phonet/pep.h
+++ b/include/net/phonet/pep.h
@@ -47,7 +47,6 @@ struct pep_sock {
 	u8			aligned;
 #ifdef CONFIG_PHONET_PIPECTRLR
 	u8			pipe_state;
-	struct sockaddr_pn	remote_pep;
 #endif
 };
 
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 3e60f2e4e6c2..4fce882d001a 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -50,11 +50,6 @@
 #define CREDITS_MAX	10
 #define CREDITS_THR	7
 
-static const struct sockaddr_pn pipe_srv = {
-	.spn_family = AF_PHONET,
-	.spn_resource = 0xD9, /* pipe service */
-};
-
 #define pep_sb_size(s) (((s) + 5) & ~3) /* 2-bytes head, 32-bits aligned */
 
 /* Get the next TLV sub-block. */
@@ -88,6 +83,7 @@ static int pep_reply(struct sock *sk, struct sk_buff *oskb,
 	const struct pnpipehdr *oph = pnp_hdr(oskb);
 	struct pnpipehdr *ph;
 	struct sk_buff *skb;
+	struct sockaddr_pn peer;
 
 	skb = alloc_skb(MAX_PNPIPE_HEADER + len, priority);
 	if (!skb)
@@ -105,7 +101,8 @@ static int pep_reply(struct sock *sk, struct sk_buff *oskb,
 	ph->pipe_handle = oph->pipe_handle;
 	ph->error_code = code;
 
-	return pn_skb_send(sk, skb, &pipe_srv);
+	pn_skb_get_src_sockaddr(oskb, &peer);
+	return pn_skb_send(sk, skb, &peer);
 }
 
 #define PAD 0x00
@@ -220,7 +217,7 @@ static int pipe_handler_send_req(struct sock *sk, u8 utid,
 	ph->pipe_handle = pn->pipe_handle;
 	ph->error_code = PN_PIPE_NO_ERROR;
 
-	return pn_skb_send(sk, skb, &pn->remote_pep);
+	return pn_skb_send(sk, skb, NULL);
 }
 
 static int pipe_handler_send_created_ind(struct sock *sk,
@@ -262,7 +259,7 @@ static int pipe_handler_send_created_ind(struct sock *sk,
 	ph->pipe_handle = pn->pipe_handle;
 	ph->error_code = err_code;
 
-	return pn_skb_send(sk, skb, &pn->remote_pep);
+	return pn_skb_send(sk, skb, NULL);
 }
 
 static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id)
@@ -295,7 +292,7 @@ static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id)
 	ph->pipe_handle = pn->pipe_handle;
 	ph->error_code = err_code;
 
-	return pn_skb_send(sk, skb, &pn->remote_pep);
+	return pn_skb_send(sk, skb, NULL);
 }
 
 static int pipe_handler_enable_pipe(struct sock *sk, int enable)
@@ -396,11 +393,7 @@ static int pipe_snd_status(struct sock *sk, u8 type, u8 status, gfp_t priority)
 	ph->data[3] = PAD;
 	ph->data[4] = status;
 
-#ifdef CONFIG_PHONET_PIPECTRLR
-	return pn_skb_send(sk, skb, &pn->remote_pep);
-#else
-	return pn_skb_send(sk, skb, &pipe_srv);
-#endif
+	return pn_skb_send(sk, skb, NULL);
 }
 
 /* Send our RX flow control information to the sender.
@@ -722,7 +715,7 @@ static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb)
 	struct sock *newsk;
 	struct pep_sock *newpn, *pn = pep_sk(sk);
 	struct pnpipehdr *hdr;
-	struct sockaddr_pn dst;
+	struct sockaddr_pn dst, src;
 	u16 peer_type;
 	u8 pipe_handle, enabled, n_sb;
 	u8 aligned = 0;
@@ -789,8 +782,10 @@ static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb)
 
 	newpn = pep_sk(newsk);
 	pn_skb_get_dst_sockaddr(skb, &dst);
+	pn_skb_get_src_sockaddr(skb, &src);
 	newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst);
-	newpn->pn_sk.resource = pn->pn_sk.resource;
+	newpn->pn_sk.dobject = pn_sockaddr_get_object(&src);
+	newpn->pn_sk.resource = pn_sockaddr_get_resource(&dst);
 	skb_queue_head_init(&newpn->ctrlreq_queue);
 	newpn->pipe_handle = pipe_handle;
 	atomic_set(&newpn->tx_credits, 0);
@@ -925,7 +920,7 @@ static int pipe_do_remove(struct sock *sk)
 	ph->pipe_handle = pn->pipe_handle;
 	ph->data[0] = PAD;
 
-	return pn_skb_send(sk, skb, &pipe_srv);
+	return pn_skb_send(sk, skb, NULL);
 }
 
 /* associated socket ceases to exist */
@@ -1042,10 +1037,10 @@ out:
 static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len)
 {
 	struct pep_sock *pn = pep_sk(sk);
-	struct sockaddr_pn *spn =  (struct sockaddr_pn *)addr;
-
-	memcpy(&pn->remote_pep, spn, sizeof(struct sockaddr_pn));
+	const struct sockaddr_pn *spn = (struct sockaddr_pn *)addr;
 
+	pn->pn_sk.dobject = pn_sockaddr_get_object(spn);
+	pn->pn_sk.resource = pn_sockaddr_get_resource(spn);
 	return pipe_handler_send_req(sk,
 			PNS_PEP_CONNECT_UTID, PNS_PEP_CONNECT_REQ,
 			GFP_ATOMIC);
@@ -1222,11 +1217,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb)
 	} else
 		ph->message_id = PNS_PIPE_DATA;
 	ph->pipe_handle = pn->pipe_handle;
-#ifdef CONFIG_PHONET_PIPECTRLR
-	err = pn_skb_send(sk, skb, &pn->remote_pep);
-#else
-	err = pn_skb_send(sk, skb, &pipe_srv);
-#endif
+	err = pn_skb_send(sk, skb, NULL);
 
 	if (err && pn_flow_safe(pn->tx_fc))
 		atomic_inc(&pn->tx_credits);
-- 
cgit v1.2.3


From 2feb61816f7f0be57f4bc61137555e9a8cb4f322 Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Thu, 24 Feb 2011 23:14:59 +0000
Subject: Phonet: remove redumdant pep->pipe_state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sk->sk_state already contains the pipe state.

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pep.h |  9 ---------
 net/phonet/pep.c         | 25 ++++++-------------------
 2 files changed, 6 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h
index 788ccf353582..4c48ed80bc07 100644
--- a/include/net/phonet/pep.h
+++ b/include/net/phonet/pep.h
@@ -45,9 +45,6 @@ struct pep_sock {
 	u8			tx_fc;	/* TX flow control */
 	u8			init_enable;	/* auto-enable at creation */
 	u8			aligned;
-#ifdef CONFIG_PHONET_PIPECTRLR
-	u8			pipe_state;
-#endif
 };
 
 static inline struct pep_sock *pep_sk(struct sock *sk)
@@ -177,12 +174,6 @@ enum {
 #define PNS_PIPE_DISABLED_IND_UTID     0x11
 #define PNS_PEP_DISCONNECT_UTID        0x06
 
-/* Used for tracking state of a pipe */
-enum {
-	PIPE_IDLE,
-	PIPE_DISABLED,
-	PIPE_ENABLED,
-};
 #endif /* CONFIG_PHONET_PIPECTRLR */
 
 #endif
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 4fce882d001a..15775a74b6f6 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -527,7 +527,6 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNS_PEP_DISCONNECT_RESP:
-		pn->pipe_state = PIPE_IDLE;
 		sk->sk_state = TCP_CLOSE;
 		break;
 #endif
@@ -539,7 +538,6 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNS_PEP_ENABLE_RESP:
-		pn->pipe_state = PIPE_ENABLED;
 		pipe_handler_send_ind(sk, PNS_PIPE_ENABLED_IND_UTID,
 				PNS_PIPE_ENABLED_IND);
 
@@ -574,7 +572,6 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNS_PEP_DISABLE_RESP:
-		pn->pipe_state = PIPE_DISABLED;
 		atomic_set(&pn->tx_credits, 0);
 		pipe_handler_send_ind(sk, PNS_PIPE_DISABLED_IND_UTID,
 				PNS_PIPE_DISABLED_IND);
@@ -692,7 +689,6 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 			remote_pref_rx_fc,
 			sizeof(host_pref_rx_fc));
 
-	pn->pipe_state = PIPE_DISABLED;
 	sk->sk_state = TCP_SYN_RECV;
 	sk->sk_backlog_rcv = pipe_do_rcv;
 	sk->sk_destruct = pipe_destruct;
@@ -941,21 +937,18 @@ static void pep_sock_close(struct sock *sk, long timeout)
 		sk_for_each_safe(sknode, p, n, &pn->ackq)
 			sk_del_node_init(sknode);
 		sk->sk_state = TCP_CLOSE;
-	} else if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED))
+	} else if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED)) {
+#ifndef CONFIG_PHONET_PIPECTRLR
 		/* Forcefully remove dangling Phonet pipe */
 		pipe_do_remove(sk);
-
-#ifdef CONFIG_PHONET_PIPECTRLR
-	if (pn->pipe_state != PIPE_IDLE) {
+#else
 		/* send pep disconnect request */
 		pipe_handler_send_req(sk,
 				PNS_PEP_DISCONNECT_UTID, PNS_PEP_DISCONNECT_REQ,
 				GFP_KERNEL);
-
-		pn->pipe_state = PIPE_IDLE;
 		sk->sk_state = TCP_CLOSE;
-	}
 #endif
+	}
 
 	ifindex = pn->ifindex;
 	pn->ifindex = 0;
@@ -1101,10 +1094,6 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNPIPE_PIPE_HANDLE:
 		if (val) {
-			if (pn->pipe_state > PIPE_IDLE) {
-				err = -EFAULT;
-				break;
-			}
 			pn->pipe_handle = val;
 			break;
 		}
@@ -1138,7 +1127,7 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNPIPE_ENABLE:
-		if (pn->pipe_state <= PIPE_IDLE) {
+		if ((1 << sk->sk_state) & ~(TCPF_SYN_RECV|TCPF_ESTABLISHED)) {
 			err = -ENOTCONN;
 			break;
 		}
@@ -1177,9 +1166,7 @@ static int pep_getsockopt(struct sock *sk, int level, int optname,
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNPIPE_ENABLE:
-		if (pn->pipe_state <= PIPE_IDLE)
-			return -ENOTCONN;
-		val = pn->pipe_state != PIPE_DISABLED;
+		val = sk->sk_state == TCP_ESTABLISHED;
 		break;
 #endif
 
-- 
cgit v1.2.3


From 0165d69bcb18c5aa220538389c872852243f9725 Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Thu, 24 Feb 2011 23:15:00 +0000
Subject: Phonet: don't bother with transaction IDs (especially for
 indications)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pep.h | 11 -----------
 net/phonet/pep.c         | 49 ++++++++++++++----------------------------------
 2 files changed, 14 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h
index 4c48ed80bc07..37f23dc05de8 100644
--- a/include/net/phonet/pep.h
+++ b/include/net/phonet/pep.h
@@ -165,15 +165,4 @@ enum {
 	PEP_IND_READY,
 };
 
-#ifdef CONFIG_PHONET_PIPECTRLR
-#define PNS_PEP_CONNECT_UTID           0x02
-#define PNS_PIPE_CREATED_IND_UTID      0x04
-#define PNS_PIPE_ENABLE_UTID           0x0A
-#define PNS_PIPE_ENABLED_IND_UTID      0x0C
-#define PNS_PIPE_DISABLE_UTID          0x0F
-#define PNS_PIPE_DISABLED_IND_UTID     0x11
-#define PNS_PEP_DISCONNECT_UTID        0x06
-
-#endif /* CONFIG_PHONET_PIPECTRLR */
-
 #endif
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 15775a74b6f6..0ecab59963e0 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -172,8 +172,7 @@ static int pipe_get_flow_info(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
-static int pipe_handler_send_req(struct sock *sk, u8 utid,
-		u8 msg_id, gfp_t priority)
+static int pipe_handler_send_req(struct sock *sk, u8 msg_id, gfp_t priority)
 {
 	int len;
 	struct pnpipehdr *ph;
@@ -212,7 +211,7 @@ static int pipe_handler_send_req(struct sock *sk, u8 utid,
 	__skb_push(skb, sizeof(*ph));
 	skb_reset_transport_header(skb);
 	ph = pnp_hdr(skb);
-	ph->utid = utid;
+	ph->utid = msg_id; /* whatever */
 	ph->message_id = msg_id;
 	ph->pipe_handle = pn->pipe_handle;
 	ph->error_code = PN_PIPE_NO_ERROR;
@@ -220,8 +219,7 @@ static int pipe_handler_send_req(struct sock *sk, u8 utid,
 	return pn_skb_send(sk, skb, NULL);
 }
 
-static int pipe_handler_send_created_ind(struct sock *sk,
-		u8 utid, u8 msg_id)
+static int pipe_handler_send_created_ind(struct sock *sk, u8 msg_id)
 {
 	int err_code;
 	struct pnpipehdr *ph;
@@ -254,7 +252,7 @@ static int pipe_handler_send_created_ind(struct sock *sk,
 	__skb_push(skb, sizeof(*ph));
 	skb_reset_transport_header(skb);
 	ph = pnp_hdr(skb);
-	ph->utid = utid;
+	ph->utid = 0;
 	ph->message_id = msg_id;
 	ph->pipe_handle = pn->pipe_handle;
 	ph->error_code = err_code;
@@ -262,7 +260,7 @@ static int pipe_handler_send_created_ind(struct sock *sk,
 	return pn_skb_send(sk, skb, NULL);
 }
 
-static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id)
+static int pipe_handler_send_ind(struct sock *sk, u8 msg_id)
 {
 	int err_code;
 	struct pnpipehdr *ph;
@@ -287,7 +285,7 @@ static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id)
 	__skb_push(skb, sizeof(*ph));
 	skb_reset_transport_header(skb);
 	ph = pnp_hdr(skb);
-	ph->utid = utid;
+	ph->utid = 0;
 	ph->message_id = msg_id;
 	ph->pipe_handle = pn->pipe_handle;
 	ph->error_code = err_code;
@@ -297,16 +295,9 @@ static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id)
 
 static int pipe_handler_enable_pipe(struct sock *sk, int enable)
 {
-	int utid, req;
-
-	if (enable) {
-		utid = PNS_PIPE_ENABLE_UTID;
-		req = PNS_PEP_ENABLE_REQ;
-	} else {
-		utid = PNS_PIPE_DISABLE_UTID;
-		req = PNS_PEP_DISABLE_REQ;
-	}
-	return pipe_handler_send_req(sk, utid, req, GFP_ATOMIC);
+	u8 id = enable ? PNS_PEP_ENABLE_REQ : PNS_PEP_DISABLE_REQ;
+
+	return pipe_handler_send_req(sk, id, GFP_KERNEL);
 }
 #endif
 
@@ -538,8 +529,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNS_PEP_ENABLE_RESP:
-		pipe_handler_send_ind(sk, PNS_PIPE_ENABLED_IND_UTID,
-				PNS_PIPE_ENABLED_IND);
+		pipe_handler_send_ind(sk, PNS_PIPE_ENABLED_IND);
 
 		if (!pn_flow_safe(pn->tx_fc)) {
 			atomic_set(&pn->tx_credits, 1);
@@ -573,8 +563,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNS_PEP_DISABLE_RESP:
 		atomic_set(&pn->tx_credits, 0);
-		pipe_handler_send_ind(sk, PNS_PIPE_DISABLED_IND_UTID,
-				PNS_PIPE_DISABLED_IND);
+		pipe_handler_send_ind(sk, PNS_PIPE_DISABLED_IND);
 		sk->sk_state = TCP_SYN_RECV;
 		pn->rx_credits = 0;
 		break;
@@ -678,7 +667,6 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 	u8 host_pref_rx_fc[3] = {3, 2, 1}, host_req_tx_fc[3] = {3, 2, 1};
 	u8 remote_pref_rx_fc[3], remote_req_tx_fc[3];
 	u8 negotiated_rx_fc, negotiated_tx_fc;
-	int ret;
 
 	pipe_get_flow_info(sk, skb, remote_pref_rx_fc,
 			remote_req_tx_fc);
@@ -697,12 +685,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 	pn->tx_fc = negotiated_tx_fc;
 	sk->sk_state_change(sk);
 
-	ret = pipe_handler_send_created_ind(sk,
-			PNS_PIPE_CREATED_IND_UTID,
-			PNS_PIPE_CREATED_IND
-			);
-
-	return ret;
+	return pipe_handler_send_created_ind(sk, PNS_PIPE_CREATED_IND);
 }
 #endif
 
@@ -943,9 +926,7 @@ static void pep_sock_close(struct sock *sk, long timeout)
 		pipe_do_remove(sk);
 #else
 		/* send pep disconnect request */
-		pipe_handler_send_req(sk,
-				PNS_PEP_DISCONNECT_UTID, PNS_PEP_DISCONNECT_REQ,
-				GFP_KERNEL);
+		pipe_handler_send_req(sk, PNS_PEP_DISCONNECT_REQ, GFP_KERNEL);
 		sk->sk_state = TCP_CLOSE;
 #endif
 	}
@@ -1034,9 +1015,7 @@ static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len)
 
 	pn->pn_sk.dobject = pn_sockaddr_get_object(spn);
 	pn->pn_sk.resource = pn_sockaddr_get_resource(spn);
-	return pipe_handler_send_req(sk,
-			PNS_PEP_CONNECT_UTID, PNS_PEP_CONNECT_REQ,
-			GFP_ATOMIC);
+	return pipe_handler_send_req(sk, PNS_PEP_CONNECT_REQ, GFP_KERNEL);
 }
 #endif
 
-- 
cgit v1.2.3


From 8f44fcc72a454c5eb7cbc138bd53f0963f23e87f Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Thu, 24 Feb 2011 23:15:01 +0000
Subject: Phonet: fix flawed "SYN/ACK" logic
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Do not fail if the peer supports more or less than 3 algorithms.
 * Ignore unknown congestion control algorithms instead of failing.
 * Simplify congestion algorithm negotiation (largest is best).
 * Do not use a static buffer.
 * Fix off-by-two read overflow.
 * Avoid extra memory copy (in addition to skb_copy_bits()).

The previous code really made no sense.

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pep.h |   1 +
 net/phonet/pep.c         | 125 ++++++++++++++++++-----------------------------
 2 files changed, 48 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h
index 37f23dc05de8..38eed1be6ffd 100644
--- a/include/net/phonet/pep.h
+++ b/include/net/phonet/pep.h
@@ -154,6 +154,7 @@ enum {
 	PN_LEGACY_FLOW_CONTROL,
 	PN_ONE_CREDIT_FLOW_CONTROL,
 	PN_MULTI_CREDIT_FLOW_CONTROL,
+	PN_MAX_FLOW_CONTROL,
 };
 
 #define pn_flow_safe(fc) ((fc) >> 1)
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 0ecab59963e0..b8c31fc928e1 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -108,70 +108,6 @@ static int pep_reply(struct sock *sk, struct sk_buff *oskb,
 #define PAD 0x00
 
 #ifdef CONFIG_PHONET_PIPECTRLR
-static u8 pipe_negotiate_fc(u8 *host_fc, u8 *remote_fc, int len)
-{
-	int i, j;
-	u8 base_fc, final_fc;
-
-	for (i = 0; i < len; i++) {
-		base_fc = host_fc[i];
-		for (j = 0; j < len; j++) {
-			if (remote_fc[j] == base_fc) {
-				final_fc = base_fc;
-				goto done;
-			}
-		}
-	}
-	return -EINVAL;
-
-done:
-	return final_fc;
-
-}
-
-static int pipe_get_flow_info(struct sock *sk, struct sk_buff *skb,
-		u8 *pref_rx_fc, u8 *req_tx_fc)
-{
-	struct pnpipehdr *hdr;
-	u8 n_sb;
-
-	if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
-		return -EINVAL;
-
-	hdr = pnp_hdr(skb);
-	n_sb = hdr->data[4];
-
-	__skb_pull(skb, sizeof(*hdr) + 4);
-	while (n_sb > 0) {
-		u8 type, buf[3], len = sizeof(buf);
-		u8 *data = pep_get_sb(skb, &type, &len, buf);
-
-		if (data == NULL)
-			return -EINVAL;
-
-		switch (type) {
-		case PN_PIPE_SB_REQUIRED_FC_TX:
-			if (len < 3 || (data[2] | data[3] | data[4]) > 3)
-				break;
-			req_tx_fc[0] = data[2];
-			req_tx_fc[1] = data[3];
-			req_tx_fc[2] = data[4];
-			break;
-
-		case PN_PIPE_SB_PREFERRED_FC_RX:
-			if (len < 3 || (data[2] | data[3] | data[4]) > 3)
-				break;
-			pref_rx_fc[0] = data[2];
-			pref_rx_fc[1] = data[3];
-			pref_rx_fc[2] = data[4];
-			break;
-
-		}
-		n_sb--;
-	}
-	return 0;
-}
-
 static int pipe_handler_send_req(struct sock *sk, u8 msg_id, gfp_t priority)
 {
 	int len;
@@ -661,28 +597,61 @@ static void pipe_destruct(struct sock *sk)
 }
 
 #ifdef CONFIG_PHONET_PIPECTRLR
+static u8 pipe_negotiate_fc(const u8 *fcs, unsigned n)
+{
+	unsigned i;
+	u8 final_fc = PN_NO_FLOW_CONTROL;
+
+	for (i = 0; i < n; i++) {
+		u8 fc = fcs[i];
+
+		if (fc > final_fc && fc < PN_MAX_FLOW_CONTROL)
+			final_fc = fc;
+	}
+	return final_fc;
+}
+
 static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	struct pep_sock *pn = pep_sk(sk);
-	u8 host_pref_rx_fc[3] = {3, 2, 1}, host_req_tx_fc[3] = {3, 2, 1};
-	u8 remote_pref_rx_fc[3], remote_req_tx_fc[3];
-	u8 negotiated_rx_fc, negotiated_tx_fc;
-
-	pipe_get_flow_info(sk, skb, remote_pref_rx_fc,
-			remote_req_tx_fc);
-	negotiated_tx_fc = pipe_negotiate_fc(remote_req_tx_fc,
-			host_pref_rx_fc,
-			sizeof(host_pref_rx_fc));
-	negotiated_rx_fc = pipe_negotiate_fc(host_req_tx_fc,
-			remote_pref_rx_fc,
-			sizeof(host_pref_rx_fc));
+	struct pnpipehdr *hdr;
+	u8 n_sb;
+
+	if (!pskb_pull(skb, sizeof(*hdr) + 4))
+		return -EINVAL;
+
+	hdr = pnp_hdr(skb);
+
+	/* Parse sub-blocks */
+	n_sb = hdr->data[4];
+	while (n_sb > 0) {
+		u8 type, buf[6], len = sizeof(buf);
+		const u8 *data = pep_get_sb(skb, &type, &len, buf);
+
+		if (data == NULL)
+			return -EINVAL;
+
+		switch (type) {
+		case PN_PIPE_SB_REQUIRED_FC_TX:
+			if (len < 2 || len < data[0])
+				break;
+			pn->tx_fc = pipe_negotiate_fc(data + 2, len - 2);
+			break;
+
+		case PN_PIPE_SB_PREFERRED_FC_RX:
+			if (len < 2 || len < data[0])
+				break;
+			pn->rx_fc = pipe_negotiate_fc(data + 2, len - 2);
+			break;
+
+		}
+		n_sb--;
+	}
 
 	sk->sk_state = TCP_SYN_RECV;
 	sk->sk_backlog_rcv = pipe_do_rcv;
 	sk->sk_destruct = pipe_destruct;
 	pn->rx_credits = 0;
-	pn->rx_fc = negotiated_rx_fc;
-	pn->tx_fc = negotiated_tx_fc;
 	sk->sk_state_change(sk);
 
 	return pipe_handler_send_created_ind(sk, PNS_PIPE_CREATED_IND);
-- 
cgit v1.2.3


From b5faba21a6805c33b40e258d36f57997ee1de131 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 23 Feb 2011 23:52:13 +0000
Subject: genirq: Prepare the handling of shared oneshot interrupts

For level type interrupts we need to track how many threads are on
flight to avoid useless interrupt storms when not all thread handlers
have finished yet. Keep track of the woken threads and only unmask
when there are no more threads in flight.

Yes, I'm lazy and using a bitfield. But not only because I'm lazy, the
main reason is that it's way simpler than using a refcount. A refcount
based solution would need to keep track of various things like
crashing the irq thread, spurious interrupts coming in,
disables/enables, free_irq() and some more. The bitfield keeps the
tracking simple and makes things just work. It's also nicely confined
to the thread code pathes and does not require additional checks all
over the place.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.388095876@linutronix.de>
---
 include/linux/interrupt.h |  2 ++
 include/linux/irqdesc.h   |  2 ++
 kernel/irq/handle.c       | 76 +++++++++++++++++++++++++++++++++++++++--------
 kernel/irq/manage.c       | 54 +++++++++++++++++++++++++++++----
 4 files changed, 115 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 8da6643e39a6..e116fef274cd 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -99,6 +99,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @thread_fn:	interupt handler function for threaded interrupts
  * @thread:	thread pointer for threaded interrupts
  * @thread_flags:	flags related to @thread
+ * @thread_mask:	bitmask for keeping track of @thread activity
  */
 struct irqaction {
 	irq_handler_t handler;
@@ -109,6 +110,7 @@ struct irqaction {
 	irq_handler_t thread_fn;
 	struct task_struct *thread;
 	unsigned long thread_flags;
+	unsigned long thread_mask;
 	const char *name;
 	struct proc_dir_entry *dir;
 } ____cacheline_internodealigned_in_smp;
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 2f87d6441302..9eb9cd313052 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -28,6 +28,7 @@ struct timer_rand_state;
  * @lock:		locking for SMP
  * @affinity_notify:	context for notification of affinity changes
  * @pending_mask:	pending rebalanced interrupts
+ * @threads_oneshot:	bitfield to handle shared oneshot threads
  * @threads_active:	number of irqaction threads currently running
  * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
  * @dir:		/proc/irq/ procfs entry
@@ -86,6 +87,7 @@ struct irq_desc {
 	cpumask_var_t		pending_mask;
 #endif
 #endif
+	unsigned long		threads_oneshot;
 	atomic_t		threads_active;
 	wait_queue_head_t       wait_for_threads;
 #ifdef CONFIG_PROC_FS
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index b110c835e070..517561fc7317 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -51,6 +51,68 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 	       "but no thread function available.", irq, action->name);
 }
 
+static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+{
+	/*
+	 * Wake up the handler thread for this action. In case the
+	 * thread crashed and was killed we just pretend that we
+	 * handled the interrupt. The hardirq handler has disabled the
+	 * device interrupt, so no irq storm is lurking. If the
+	 * RUNTHREAD bit is already set, nothing to do.
+	 */
+	if (test_bit(IRQTF_DIED, &action->thread_flags) ||
+	    test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		return;
+
+	/*
+	 * It's safe to OR the mask lockless here. We have only two
+	 * places which write to threads_oneshot: This code and the
+	 * irq thread.
+	 *
+	 * This code is the hard irq context and can never run on two
+	 * cpus in parallel. If it ever does we have more serious
+	 * problems than this bitmask.
+	 *
+	 * The irq threads of this irq which clear their "running" bit
+	 * in threads_oneshot are serialized via desc->lock against
+	 * each other and they are serialized against this code by
+	 * IRQS_INPROGRESS.
+	 *
+	 * Hard irq handler:
+	 *
+	 *	spin_lock(desc->lock);
+	 *	desc->state |= IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *	set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+	 *	desc->threads_oneshot |= mask;
+	 *	spin_lock(desc->lock);
+	 *	desc->state &= ~IRQS_INPROGRESS;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * irq thread:
+	 *
+	 * again:
+	 *	spin_lock(desc->lock);
+	 *	if (desc->state & IRQS_INPROGRESS) {
+	 *		spin_unlock(desc->lock);
+	 *		while(desc->state & IRQS_INPROGRESS)
+	 *			cpu_relax();
+	 *		goto again;
+	 *	}
+	 *	if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	 *		desc->threads_oneshot &= ~mask;
+	 *	spin_unlock(desc->lock);
+	 *
+	 * So either the thread waits for us to clear IRQS_INPROGRESS
+	 * or we are waiting in the flow handler for desc->lock to be
+	 * released before we reach this point. The thread also checks
+	 * IRQTF_RUNTHREAD under desc->lock. If set it leaves
+	 * threads_oneshot untouched and runs the thread another time.
+	 */
+	desc->threads_oneshot |= action->thread_mask;
+	wake_up_process(action->thread);
+}
+
 irqreturn_t
 handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
@@ -85,19 +147,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 				break;
 			}
 
-			/*
-			 * Wake up the handler thread for this
-			 * action. In case the thread crashed and was
-			 * killed we just pretend that we handled the
-			 * interrupt. The hardirq handler above has
-			 * disabled the device interrupt, so no irq
-			 * storm is lurking.
-			 */
-			if (likely(!test_bit(IRQTF_DIED,
-					     &action->thread_flags))) {
-				set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
-				wake_up_process(action->thread);
-			}
+			irq_wake_thread(desc, action);
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 01f8a9519e63..2301de19ac7d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -617,8 +617,11 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  * handler finished. unmask if the interrupt has not been disabled and
  * is marked MASKED.
  */
-static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
+static void irq_finalize_oneshot(struct irq_desc *desc,
+				 struct irqaction *action, bool force)
 {
+	if (!(desc->istate & IRQS_ONESHOT))
+		return;
 again:
 	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
@@ -631,6 +634,11 @@ again:
 	 * on the other CPU. If we unmask the irq line then the
 	 * interrupt can come in again and masks the line, leaves due
 	 * to IRQS_INPROGRESS and the irq line is masked forever.
+	 *
+	 * This also serializes the state of shared oneshot handlers
+	 * versus "desc->threads_onehsot |= action->thread_mask;" in
+	 * irq_wake_thread(). See the comment there which explains the
+	 * serialization.
 	 */
 	if (unlikely(desc->istate & IRQS_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
@@ -639,11 +647,23 @@ again:
 		goto again;
 	}
 
-	if (!(desc->istate & IRQS_DISABLED) && (desc->istate & IRQS_MASKED)) {
+	/*
+	 * Now check again, whether the thread should run. Otherwise
+	 * we would clear the threads_oneshot bit of this thread which
+	 * was just set.
+	 */
+	if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		goto out_unlock;
+
+	desc->threads_oneshot &= ~action->thread_mask;
+
+	if (!desc->threads_oneshot && !(desc->istate & IRQS_DISABLED) &&
+	    (desc->istate & IRQS_MASKED)) {
 		irq_compat_clr_masked(desc);
 		desc->istate &= ~IRQS_MASKED;
 		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
+out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
 	chip_bus_sync_unlock(desc);
 }
@@ -691,7 +711,7 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	int wake, oneshot = desc->istate & IRQS_ONESHOT;
+	int wake;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
@@ -719,8 +739,7 @@ static int irq_thread(void *data)
 
 			action->thread_fn(action->irq, action->dev_id);
 
-			if (oneshot)
-				irq_finalize_oneshot(action->irq, desc);
+			irq_finalize_oneshot(desc, action, false);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -729,6 +748,9 @@ static int irq_thread(void *data)
 			wake_up(&desc->wait_for_threads);
 	}
 
+	/* Prevent a stale desc->threads_oneshot */
+	irq_finalize_oneshot(desc, action, true);
+
 	/*
 	 * Clear irqaction. Otherwise exit_irq_thread() would make
 	 * fuzz about an active irq thread going into nirvana.
@@ -743,6 +765,7 @@ static int irq_thread(void *data)
 void exit_irq_thread(void)
 {
 	struct task_struct *tsk = current;
+	struct irq_desc *desc;
 
 	if (!tsk->irqaction)
 		return;
@@ -751,6 +774,14 @@ void exit_irq_thread(void)
 	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
 	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
 
+	desc = irq_to_desc(tsk->irqaction->irq);
+
+	/*
+	 * Prevent a stale desc->threads_oneshot. Must be called
+	 * before setting the IRQTF_DIED flag.
+	 */
+	irq_finalize_oneshot(desc, tsk->irqaction, true);
+
 	/*
 	 * Set the THREAD DIED flag to prevent further wakeups of the
 	 * soon to be gone threaded handler.
@@ -767,7 +798,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
 	struct irqaction *old, **old_ptr;
 	const char *old_name = NULL;
-	unsigned long flags;
+	unsigned long flags, thread_mask = 0;
 	int ret, nested, shared = 0;
 	cpumask_var_t mask;
 
@@ -865,12 +896,23 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 		/* add new interrupt at end of irq queue */
 		do {
+			thread_mask |= old->thread_mask;
 			old_ptr = &old->next;
 			old = *old_ptr;
 		} while (old);
 		shared = 1;
 	}
 
+	/*
+	 * Setup the thread mask for this irqaction. Unlikely to have
+	 * 32 resp 64 irqs sharing one line, but who knows.
+	 */
+	if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
+		ret = -EBUSY;
+		goto out_mask;
+	}
+	new->thread_mask = 1 << ffz(thread_mask);
+
 	if (!shared) {
 		irq_chip_set_defaults(desc->irq_data.chip);
 
-- 
cgit v1.2.3


From 0c4602ff88d6d6ef0ee6d228ee9acaa6448ff6f5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 23 Feb 2011 23:52:18 +0000
Subject: genirq: Add IRQF_NO_THREAD

Some low level interrupts cannot be threaded even when we force thread
all interrupt handlers. Add a flag to annotate such interrupts. Add
all timer interrupts to this category by default.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.578893460@linutronix.de>
---
 include/linux/interrupt.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index e116fef274cd..0fc3eb9397b4 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -58,6 +58,7 @@
  *                irq line disabled until the threaded handler has been run.
  * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
  * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
+ * IRQF_NO_THREAD - Interrupt cannot be threaded
  */
 #define IRQF_DISABLED		0x00000020
 #define IRQF_SAMPLE_RANDOM	0x00000040
@@ -70,8 +71,9 @@
 #define IRQF_ONESHOT		0x00002000
 #define IRQF_NO_SUSPEND		0x00004000
 #define IRQF_FORCE_RESUME	0x00008000
+#define IRQF_NO_THREAD		0x00010000
 
-#define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND)
+#define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
 /*
  * These values can be returned by request_any_context_irq() and
-- 
cgit v1.2.3


From 969e3033ae7733a0af8f7742ca74cd16c0857e71 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Wed, 23 Feb 2011 15:28:18 -0500
Subject: USB: serial drivers need to use larger bulk-in buffers

When a driver doesn't know how much data a device is going to send,
the buffer size should be at least as big as the endpoint's maxpacket
value.  The serial drivers don't follow this rule; many of them
request only 256-byte bulk-in buffers.  As a result, they suffer
overflow errors if a high-speed device wants to send a lot of data,
because high-speed bulk endpoints are required to have a maxpacket
size of 512.

This patch (as1450) fixes the problem by using the driver's
bulk_in_size value as a minimum, always allocating buffers no smaller
than the endpoint's maxpacket size.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Flynn Marquardt <flynn@flynnux.de>
CC: <stable@kernel.org> [after .39-rc1 is out]
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/serial/usb-serial.c | 5 ++---
 include/linux/usb/serial.h      | 3 ++-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 546a52179bec..2ff90a9c8f47 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -911,9 +911,8 @@ int usb_serial_probe(struct usb_interface *interface,
 			dev_err(&interface->dev, "No free urbs available\n");
 			goto probe_error;
 		}
-		buffer_size = serial->type->bulk_in_size;
-		if (!buffer_size)
-			buffer_size = le16_to_cpu(endpoint->wMaxPacketSize);
+		buffer_size = max_t(int, serial->type->bulk_in_size,
+				le16_to_cpu(endpoint->wMaxPacketSize));
 		port->bulk_in_size = buffer_size;
 		port->bulk_in_endpointAddress = endpoint->bEndpointAddress;
 		port->bulk_in_buffer = kmalloc(buffer_size, GFP_KERNEL);
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index c9049139a7a5..45f3b9db4258 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -191,7 +191,8 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data)
  * @id_table: pointer to a list of usb_device_id structures that define all
  *	of the devices this structure can support.
  * @num_ports: the number of different ports this device will have.
- * @bulk_in_size: bytes to allocate for bulk-in buffer (0 = end-point size)
+ * @bulk_in_size: minimum number of bytes to allocate for bulk-in buffer
+ *	(0 = end-point size)
  * @bulk_out_size: bytes to allocate for bulk-out buffer (0 = end-point size)
  * @calc_num_ports: pointer to a function to determine how many ports this
  *	device has dynamically.  It will be called after the probe()
-- 
cgit v1.2.3


From c9642374d0e969e8c17f4f31cd1a2bd111634227 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dtor@vmware.com>
Date: Wed, 23 Feb 2011 14:38:20 -0800
Subject: USB: fix unsafe USB_SS_MAX_STREAMS() definition

Macro arguments used in expressions need to be enclosed in parenthesis
to avoid unpleasant surprises.

Signed-off-by: Dmitry Torokhov <dtor@vmware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/usb/ch9.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h
index ab461948b579..34316ba05f29 100644
--- a/include/linux/usb/ch9.h
+++ b/include/linux/usb/ch9.h
@@ -584,7 +584,7 @@ struct usb_ss_ep_comp_descriptor {
 
 #define USB_DT_SS_EP_COMP_SIZE		6
 /* Bits 4:0 of bmAttributes if this is a bulk endpoint */
-#define USB_SS_MAX_STREAMS(p)		(1 << (p & 0x1f))
+#define USB_SS_MAX_STREAMS(p)		(1 << ((p) & 0x1f))
 
 /*-------------------------------------------------------------------------*/
 
-- 
cgit v1.2.3


From 93c890dbe5287d146007083021148e7318058e37 Mon Sep 17 00:00:00 2001
From: Mike Waychison <mikew@google.com>
Date: Tue, 22 Feb 2011 17:53:15 -0800
Subject: firmware: Add DMI entry types to the headers

In preparation for the upcoming commits, introduce the DMI entry types to
the headers.  These type names are based on those specified in the DMTF
SMBIOS specification version 2.7.1.

Signed-off-by: Mike Waychison <mikew@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/dmi.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

(limited to 'include')

diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index 90e087f8d951..f156cca25ad0 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -23,6 +23,53 @@ enum dmi_device_type {
 	DMI_DEV_TYPE_DEV_ONBOARD = -3,
 };
 
+enum dmi_entry_type {
+	DMI_ENTRY_BIOS = 0,
+	DMI_ENTRY_SYSTEM,
+	DMI_ENTRY_BASEBOARD,
+	DMI_ENTRY_CHASSIS,
+	DMI_ENTRY_PROCESSOR,
+	DMI_ENTRY_MEM_CONTROLLER,
+	DMI_ENTRY_MEM_MODULE,
+	DMI_ENTRY_CACHE,
+	DMI_ENTRY_PORT_CONNECTOR,
+	DMI_ENTRY_SYSTEM_SLOT,
+	DMI_ENTRY_ONBOARD_DEVICE,
+	DMI_ENTRY_OEMSTRINGS,
+	DMI_ENTRY_SYSCONF,
+	DMI_ENTRY_BIOS_LANG,
+	DMI_ENTRY_GROUP_ASSOC,
+	DMI_ENTRY_SYSTEM_EVENT_LOG,
+	DMI_ENTRY_PHYS_MEM_ARRAY,
+	DMI_ENTRY_MEM_DEVICE,
+	DMI_ENTRY_32_MEM_ERROR,
+	DMI_ENTRY_MEM_ARRAY_MAPPED_ADDR,
+	DMI_ENTRY_MEM_DEV_MAPPED_ADDR,
+	DMI_ENTRY_BUILTIN_POINTING_DEV,
+	DMI_ENTRY_PORTABLE_BATTERY,
+	DMI_ENTRY_SYSTEM_RESET,
+	DMI_ENTRY_HW_SECURITY,
+	DMI_ENTRY_SYSTEM_POWER_CONTROLS,
+	DMI_ENTRY_VOLTAGE_PROBE,
+	DMI_ENTRY_COOLING_DEV,
+	DMI_ENTRY_TEMP_PROBE,
+	DMI_ENTRY_ELECTRICAL_CURRENT_PROBE,
+	DMI_ENTRY_OOB_REMOTE_ACCESS,
+	DMI_ENTRY_BIS_ENTRY,
+	DMI_ENTRY_SYSTEM_BOOT,
+	DMI_ENTRY_MGMT_DEV,
+	DMI_ENTRY_MGMT_DEV_COMPONENT,
+	DMI_ENTRY_MGMT_DEV_THRES,
+	DMI_ENTRY_MEM_CHANNEL,
+	DMI_ENTRY_IPMI_DEV,
+	DMI_ENTRY_SYS_POWER_SUPPLY,
+	DMI_ENTRY_ADDITIONAL,
+	DMI_ENTRY_ONBOARD_DEV_EXT,
+	DMI_ENTRY_MGMT_CONTROLLER_HOST,
+	DMI_ENTRY_INACTIVE = 126,
+	DMI_ENTRY_END_OF_TABLE = 127,
+};
+
 struct dmi_header {
 	u8 type;
 	u8 length;
-- 
cgit v1.2.3


From 7bb4568372856688bc070917265bce0b88bb7d4d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 24 Feb 2011 14:42:06 +0100
Subject: mac80211: make tx() operation return void

The return value of the tx operation is commonly
misused by drivers, leading to errors. All drivers
will drop frames if they fail to TX the frame, and
they must also properly manage the queues (if they
didn't, mac80211 would already warn).

Removing the ability for drivers to return a BUSY
value also allows significant cleanups of the TX
TX handling code in mac80211.

Note that this also fixes a bug in ath9k_htc, the
old "return -1" there was wrong.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Tested-by: Sedat Dilek <sedat.dilek@googlemail.com> [ath5k]
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com> [rt2x00]
Acked-by: Larry Finger <Larry.Finger@lwfinger.net> [b43, rtl8187, rtlwifi]
Acked-by: Luciano Coelho <coelho@ti.com> [wl12xx]
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/adm8211.c                |   4 +-
 drivers/net/wireless/at76c50x-usb.c           |   7 +-
 drivers/net/wireless/ath/ar9170/ar9170.h      |   2 +-
 drivers/net/wireless/ath/ar9170/main.c        |   5 +-
 drivers/net/wireless/ath/ath5k/ath5k.h        |   4 +-
 drivers/net/wireless/ath/ath5k/base.c         |   5 +-
 drivers/net/wireless/ath/ath5k/mac80211-ops.c |   6 +-
 drivers/net/wireless/ath/ath9k/htc_drv_main.c |   7 +-
 drivers/net/wireless/ath/ath9k/main.c         |   6 +-
 drivers/net/wireless/ath/carl9170/carl9170.h  |   2 +-
 drivers/net/wireless/ath/carl9170/tx.c        |   5 +-
 drivers/net/wireless/b43/main.c               |   6 +-
 drivers/net/wireless/b43legacy/main.c         |   5 +-
 drivers/net/wireless/iwlegacy/iwl-4965.h      |   2 +-
 drivers/net/wireless/iwlegacy/iwl3945-base.c  |   3 +-
 drivers/net/wireless/iwlegacy/iwl4965-base.c  |   3 +-
 drivers/net/wireless/iwlwifi/iwl-agn.c        |   3 +-
 drivers/net/wireless/iwlwifi/iwl-agn.h        |   2 +-
 drivers/net/wireless/libertas_tf/main.c       |   3 +-
 drivers/net/wireless/mac80211_hwsim.c         |   5 +-
 drivers/net/wireless/mwl8k.c                  |  15 +--
 drivers/net/wireless/p54/lmac.h               |   2 +-
 drivers/net/wireless/p54/main.c               |   2 +-
 drivers/net/wireless/p54/txrx.c               |  11 +-
 drivers/net/wireless/rt2x00/rt2x00.h          |   2 +-
 drivers/net/wireless/rt2x00/rt2x00mac.c       |   5 +-
 drivers/net/wireless/rtl818x/rtl8180/dev.c    |   8 +-
 drivers/net/wireless/rtl818x/rtl8187/dev.c    |   6 +-
 drivers/net/wireless/rtlwifi/core.c           |   5 +-
 drivers/net/wireless/wl1251/main.c            |   4 +-
 drivers/net/wireless/wl12xx/main.c            |   4 +-
 drivers/net/wireless/zd1211rw/zd_mac.c        |   5 +-
 drivers/staging/brcm80211/sys/wl_mac80211.c   |  28 +----
 drivers/staging/winbond/wbusb.c               |   7 +-
 include/net/mac80211.h                        |   2 +-
 net/mac80211/driver-ops.h                     |   4 +-
 net/mac80211/tx.c                             | 164 +++++++++-----------------
 37 files changed, 122 insertions(+), 237 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/adm8211.c b/drivers/net/wireless/adm8211.c
index f9aa1bc0a947..afe2cbc6cb24 100644
--- a/drivers/net/wireless/adm8211.c
+++ b/drivers/net/wireless/adm8211.c
@@ -1658,7 +1658,7 @@ static void adm8211_tx_raw(struct ieee80211_hw *dev, struct sk_buff *skb,
 }
 
 /* Put adm8211_tx_hdr on skb and transmit */
-static int adm8211_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
+static void adm8211_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 {
 	struct adm8211_tx_hdr *txhdr;
 	size_t payload_len, hdrlen;
@@ -1707,8 +1707,6 @@ static int adm8211_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 	txhdr->retry_limit = info->control.rates[0].count;
 
 	adm8211_tx_raw(dev, skb, plcp_signal, hdrlen);
-
-	return NETDEV_TX_OK;
 }
 
 static int adm8211_alloc_rings(struct ieee80211_hw *dev)
diff --git a/drivers/net/wireless/at76c50x-usb.c b/drivers/net/wireless/at76c50x-usb.c
index 1476314afa8a..10b4393d7fe0 100644
--- a/drivers/net/wireless/at76c50x-usb.c
+++ b/drivers/net/wireless/at76c50x-usb.c
@@ -1728,7 +1728,7 @@ static void at76_mac80211_tx_callback(struct urb *urb)
 	ieee80211_wake_queues(priv->hw);
 }
 
-static int at76_mac80211_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void at76_mac80211_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct at76_priv *priv = hw->priv;
 	struct at76_tx_buffer *tx_buffer = priv->bulk_out_buffer;
@@ -1741,7 +1741,8 @@ static int at76_mac80211_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	if (priv->tx_urb->status == -EINPROGRESS) {
 		wiphy_err(priv->hw->wiphy,
 			  "%s called while tx urb is pending\n", __func__);
-		return NETDEV_TX_BUSY;
+		dev_kfree_skb_any(skb);
+		return;
 	}
 
 	/* The following code lines are important when the device is going to
@@ -1795,8 +1796,6 @@ static int at76_mac80211_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 				  priv->tx_urb,
 				  priv->tx_urb->hcpriv, priv->tx_urb->complete);
 	}
-
-	return 0;
 }
 
 static int at76_mac80211_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/ath/ar9170/ar9170.h b/drivers/net/wireless/ath/ar9170/ar9170.h
index 4f845f80c098..371e4ce49528 100644
--- a/drivers/net/wireless/ath/ar9170/ar9170.h
+++ b/drivers/net/wireless/ath/ar9170/ar9170.h
@@ -224,7 +224,7 @@ void ar9170_handle_command_response(struct ar9170 *ar, void *buf, u32 len);
 int ar9170_nag_limiter(struct ar9170 *ar);
 
 /* MAC */
-int ar9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
+void ar9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
 int ar9170_init_mac(struct ar9170 *ar);
 int ar9170_set_qos(struct ar9170 *ar);
 int ar9170_update_multicast(struct ar9170 *ar, const u64 mc_hast);
diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c
index a9111e1161fd..b761fec0d721 100644
--- a/drivers/net/wireless/ath/ar9170/main.c
+++ b/drivers/net/wireless/ath/ar9170/main.c
@@ -1475,7 +1475,7 @@ static void ar9170_tx(struct ar9170 *ar)
 				     msecs_to_jiffies(AR9170_JANITOR_DELAY));
 }
 
-int ar9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+void ar9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct ar9170 *ar = hw->priv;
 	struct ieee80211_tx_info *info;
@@ -1493,11 +1493,10 @@ int ar9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	skb_queue_tail(&ar->tx_pending[queue], skb);
 
 	ar9170_tx(ar);
-	return NETDEV_TX_OK;
+	return;
 
 err_free:
 	dev_kfree_skb_any(skb);
-	return NETDEV_TX_OK;
 }
 
 static int ar9170_op_add_interface(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/ath/ath5k/ath5k.h b/drivers/net/wireless/ath/ath5k/ath5k.h
index 70abb61e9eff..0ee54eb333de 100644
--- a/drivers/net/wireless/ath/ath5k/ath5k.h
+++ b/drivers/net/wireless/ath/ath5k/ath5k.h
@@ -1164,8 +1164,8 @@ struct ath5k_txq;
 
 void set_beacon_filter(struct ieee80211_hw *hw, bool enable);
 bool ath_any_vif_assoc(struct ath5k_softc *sc);
-int ath5k_tx_queue(struct ieee80211_hw *hw, struct sk_buff *skb,
-		   struct ath5k_txq *txq);
+void ath5k_tx_queue(struct ieee80211_hw *hw, struct sk_buff *skb,
+		    struct ath5k_txq *txq);
 int ath5k_init_hw(struct ath5k_softc *sc);
 int ath5k_stop_hw(struct ath5k_softc *sc);
 void ath5k_mode_setup(struct ath5k_softc *sc, struct ieee80211_vif *vif);
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index 80d9cf0c4cd2..91411e9b4b68 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -1518,7 +1518,7 @@ unlock:
 * TX Handling *
 \*************/
 
-int
+void
 ath5k_tx_queue(struct ieee80211_hw *hw, struct sk_buff *skb,
 	       struct ath5k_txq *txq)
 {
@@ -1567,11 +1567,10 @@ ath5k_tx_queue(struct ieee80211_hw *hw, struct sk_buff *skb,
 		spin_unlock_irqrestore(&sc->txbuflock, flags);
 		goto drop_packet;
 	}
-	return NETDEV_TX_OK;
+	return;
 
 drop_packet:
 	dev_kfree_skb_any(skb);
-	return NETDEV_TX_OK;
 }
 
 static void
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index a60a726a140c..1fbe3c0b9f08 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -52,7 +52,7 @@ extern int ath5k_modparam_nohwcrypt;
 * Mac80211 functions *
 \********************/
 
-static int
+static void
 ath5k_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct ath5k_softc *sc = hw->priv;
@@ -60,10 +60,10 @@ ath5k_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 	if (WARN_ON(qnum >= sc->ah->ah_capabilities.cap_queues.q_tx_num)) {
 		dev_kfree_skb_any(skb);
-		return 0;
+		return;
 	}
 
-	return ath5k_tx_queue(hw, skb, &sc->txqs[qnum]);
+	ath5k_tx_queue(hw, skb, &sc->txqs[qnum]);
 }
 
 
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 7367d6c1c649..71adab34006c 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1036,7 +1036,7 @@ set_timer:
 /* mac80211 Callbacks */
 /**********************/
 
-static int ath9k_htc_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void ath9k_htc_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr;
 	struct ath9k_htc_priv *priv = hw->priv;
@@ -1049,7 +1049,7 @@ static int ath9k_htc_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	padsize = padpos & 3;
 	if (padsize && skb->len > padpos) {
 		if (skb_headroom(skb) < padsize)
-			return -1;
+			goto fail_tx;
 		skb_push(skb, padsize);
 		memmove(skb->data, skb->data + padsize, padpos);
 	}
@@ -1070,11 +1070,10 @@ static int ath9k_htc_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 		goto fail_tx;
 	}
 
-	return 0;
+	return;
 
 fail_tx:
 	dev_kfree_skb_any(skb);
-	return 0;
 }
 
 static int ath9k_htc_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index a71550049d84..39a72ae80970 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1142,8 +1142,7 @@ mutex_unlock:
 	return r;
 }
 
-static int ath9k_tx(struct ieee80211_hw *hw,
-		    struct sk_buff *skb)
+static void ath9k_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
@@ -1200,10 +1199,9 @@ static int ath9k_tx(struct ieee80211_hw *hw,
 		goto exit;
 	}
 
-	return 0;
+	return;
 exit:
 	dev_kfree_skb_any(skb);
-	return 0;
 }
 
 static void ath9k_stop(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h
index 420d437f9580..c6a5fae634a0 100644
--- a/drivers/net/wireless/ath/carl9170/carl9170.h
+++ b/drivers/net/wireless/ath/carl9170/carl9170.h
@@ -534,7 +534,7 @@ void carl9170_rx(struct ar9170 *ar, void *buf, unsigned int len);
 void carl9170_handle_command_response(struct ar9170 *ar, void *buf, u32 len);
 
 /* TX */
-int carl9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
+void carl9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
 void carl9170_tx_janitor(struct work_struct *work);
 void carl9170_tx_process_status(struct ar9170 *ar,
 				const struct carl9170_rsp *cmd);
diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c
index 6f41e21d3a1c..0ef70b6fc512 100644
--- a/drivers/net/wireless/ath/carl9170/tx.c
+++ b/drivers/net/wireless/ath/carl9170/tx.c
@@ -1339,7 +1339,7 @@ err_unlock_rcu:
 	return false;
 }
 
-int carl9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+void carl9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct ar9170 *ar = hw->priv;
 	struct ieee80211_tx_info *info;
@@ -1373,12 +1373,11 @@ int carl9170_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	}
 
 	carl9170_tx(ar);
-	return NETDEV_TX_OK;
+	return;
 
 err_free:
 	ar->tx_dropped++;
 	dev_kfree_skb_any(skb);
-	return NETDEV_TX_OK;
 }
 
 void carl9170_tx_scheduler(struct ar9170 *ar)
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index 22bc9f17f634..57eb5b649730 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -3203,7 +3203,7 @@ static void b43_tx_work(struct work_struct *work)
 	mutex_unlock(&wl->mutex);
 }
 
-static int b43_op_tx(struct ieee80211_hw *hw,
+static void b43_op_tx(struct ieee80211_hw *hw,
 		     struct sk_buff *skb)
 {
 	struct b43_wl *wl = hw_to_b43_wl(hw);
@@ -3211,14 +3211,12 @@ static int b43_op_tx(struct ieee80211_hw *hw,
 	if (unlikely(skb->len < 2 + 2 + 6)) {
 		/* Too short, this can't be a valid frame. */
 		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
+		return;
 	}
 	B43_WARN_ON(skb_shinfo(skb)->nr_frags);
 
 	skb_queue_tail(&wl->tx_queue, skb);
 	ieee80211_queue_work(wl->hw, &wl->tx_work);
-
-	return NETDEV_TX_OK;
 }
 
 static void b43_qos_params_upload(struct b43_wldev *dev,
diff --git a/drivers/net/wireless/b43legacy/main.c b/drivers/net/wireless/b43legacy/main.c
index 1f11e1670bf0..c7fd73e3ad76 100644
--- a/drivers/net/wireless/b43legacy/main.c
+++ b/drivers/net/wireless/b43legacy/main.c
@@ -2442,8 +2442,8 @@ static int b43legacy_rng_init(struct b43legacy_wl *wl)
 	return err;
 }
 
-static int b43legacy_op_tx(struct ieee80211_hw *hw,
-			   struct sk_buff *skb)
+static void b43legacy_op_tx(struct ieee80211_hw *hw,
+			    struct sk_buff *skb)
 {
 	struct b43legacy_wl *wl = hw_to_b43legacy_wl(hw);
 	struct b43legacy_wldev *dev = wl->current_dev;
@@ -2466,7 +2466,6 @@ out:
 		/* Drop the packet. */
 		dev_kfree_skb_any(skb);
 	}
-	return NETDEV_TX_OK;
 }
 
 static int b43legacy_op_conf_tx(struct ieee80211_hw *hw, u16 queue,
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965.h b/drivers/net/wireless/iwlegacy/iwl-4965.h
index 79e206770f71..01f8163daf16 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965.h
+++ b/drivers/net/wireless/iwlegacy/iwl-4965.h
@@ -253,7 +253,7 @@ void iwl4965_eeprom_release_semaphore(struct iwl_priv *priv);
 int  iwl4965_eeprom_check_version(struct iwl_priv *priv);
 
 /* mac80211 handlers (for 4965) */
-int iwl4965_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
+void iwl4965_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
 int iwl4965_mac_start(struct ieee80211_hw *hw);
 void iwl4965_mac_stop(struct ieee80211_hw *hw);
 void iwl4965_configure_filter(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/iwlegacy/iwl3945-base.c b/drivers/net/wireless/iwlegacy/iwl3945-base.c
index ef94d161b783..a6af9817efce 100644
--- a/drivers/net/wireless/iwlegacy/iwl3945-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl3945-base.c
@@ -3170,7 +3170,7 @@ static void iwl3945_mac_stop(struct ieee80211_hw *hw)
 	IWL_DEBUG_MAC80211(priv, "leave\n");
 }
 
-static int iwl3945_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void iwl3945_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct iwl_priv *priv = hw->priv;
 
@@ -3183,7 +3183,6 @@ static int iwl3945_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 		dev_kfree_skb_any(skb);
 
 	IWL_DEBUG_MAC80211(priv, "leave\n");
-	return NETDEV_TX_OK;
 }
 
 void iwl3945_config_ap(struct iwl_priv *priv)
diff --git a/drivers/net/wireless/iwlegacy/iwl4965-base.c b/drivers/net/wireless/iwlegacy/iwl4965-base.c
index c0e07685059a..4d53d0ff5fc7 100644
--- a/drivers/net/wireless/iwlegacy/iwl4965-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl4965-base.c
@@ -2631,7 +2631,7 @@ void iwl4965_mac_stop(struct ieee80211_hw *hw)
 	IWL_DEBUG_MAC80211(priv, "leave\n");
 }
 
-int iwl4965_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+void iwl4965_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct iwl_priv *priv = hw->priv;
 
@@ -2644,7 +2644,6 @@ int iwl4965_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 		dev_kfree_skb_any(skb);
 
 	IWL_DEBUG_MACDUMP(priv, "leave\n");
-	return NETDEV_TX_OK;
 }
 
 void iwl4965_mac_update_tkip_key(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index d08fa938501a..8cdbd8c4027f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -3330,7 +3330,7 @@ void iwlagn_mac_stop(struct ieee80211_hw *hw)
 	IWL_DEBUG_MAC80211(priv, "leave\n");
 }
 
-int iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+void iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct iwl_priv *priv = hw->priv;
 
@@ -3343,7 +3343,6 @@ int iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 		dev_kfree_skb_any(skb);
 
 	IWL_DEBUG_MACDUMP(priv, "leave\n");
-	return NETDEV_TX_OK;
 }
 
 void iwlagn_mac_update_tkip_key(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h
index d00e1ea50a8d..88c7210dfb91 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.h
@@ -356,7 +356,7 @@ iwlagn_remove_notification(struct iwl_priv *priv,
 			   struct iwl_notification_wait *wait_entry);
 
 /* mac80211 handlers (for 4965) */
-int iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
+void iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
 int iwlagn_mac_start(struct ieee80211_hw *hw);
 void iwlagn_mac_stop(struct ieee80211_hw *hw);
 void iwlagn_configure_filter(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/libertas_tf/main.c b/drivers/net/wireless/libertas_tf/main.c
index 9278b3c8ee30..d4005081f1df 100644
--- a/drivers/net/wireless/libertas_tf/main.c
+++ b/drivers/net/wireless/libertas_tf/main.c
@@ -225,7 +225,7 @@ static void lbtf_free_adapter(struct lbtf_private *priv)
 	lbtf_deb_leave(LBTF_DEB_MAIN);
 }
 
-static int lbtf_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void lbtf_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct lbtf_private *priv = hw->priv;
 
@@ -236,7 +236,6 @@ static int lbtf_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	 * there are no buffered multicast frames to send
 	 */
 	ieee80211_stop_queues(priv->hw);
-	return NETDEV_TX_OK;
 }
 
 static void lbtf_tx_work(struct work_struct *work)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 5d39b2840584..56f439d58013 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -541,7 +541,7 @@ static bool mac80211_hwsim_tx_frame(struct ieee80211_hw *hw,
 }
 
 
-static int mac80211_hwsim_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void mac80211_hwsim_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	bool ack;
 	struct ieee80211_tx_info *txi;
@@ -551,7 +551,7 @@ static int mac80211_hwsim_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	if (skb->len < 10) {
 		/* Should not happen; just a sanity check for addr1 use */
 		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
+		return;
 	}
 
 	ack = mac80211_hwsim_tx_frame(hw, skb);
@@ -571,7 +571,6 @@ static int mac80211_hwsim_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	if (!(txi->flags & IEEE80211_TX_CTL_NO_ACK) && ack)
 		txi->flags |= IEEE80211_TX_STAT_ACK;
 	ieee80211_tx_status_irqsafe(hw, skb);
-	return NETDEV_TX_OK;
 }
 
 
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 03f2584aed12..df5959f36d0b 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -1573,7 +1573,7 @@ static void mwl8k_txq_deinit(struct ieee80211_hw *hw, int index)
 	txq->txd = NULL;
 }
 
-static int
+static void
 mwl8k_txq_xmit(struct ieee80211_hw *hw, int index, struct sk_buff *skb)
 {
 	struct mwl8k_priv *priv = hw->priv;
@@ -1635,7 +1635,7 @@ mwl8k_txq_xmit(struct ieee80211_hw *hw, int index, struct sk_buff *skb)
 		wiphy_debug(hw->wiphy,
 			    "failed to dma map skb, dropping TX frame.\n");
 		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
+		return;
 	}
 
 	spin_lock_bh(&priv->tx_lock);
@@ -1672,8 +1672,6 @@ mwl8k_txq_xmit(struct ieee80211_hw *hw, int index, struct sk_buff *skb)
 	mwl8k_tx_start(priv);
 
 	spin_unlock_bh(&priv->tx_lock);
-
-	return NETDEV_TX_OK;
 }
 
 
@@ -3742,22 +3740,19 @@ static void mwl8k_rx_poll(unsigned long data)
 /*
  * Core driver operations.
  */
-static int mwl8k_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void mwl8k_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct mwl8k_priv *priv = hw->priv;
 	int index = skb_get_queue_mapping(skb);
-	int rc;
 
 	if (!priv->radio_on) {
 		wiphy_debug(hw->wiphy,
 			    "dropped TX frame since radio disabled\n");
 		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
+		return;
 	}
 
-	rc = mwl8k_txq_xmit(hw, index, skb);
-
-	return rc;
+	mwl8k_txq_xmit(hw, index, skb);
 }
 
 static int mwl8k_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/p54/lmac.h b/drivers/net/wireless/p54/lmac.h
index 5ca117e6f95b..eb581abc1079 100644
--- a/drivers/net/wireless/p54/lmac.h
+++ b/drivers/net/wireless/p54/lmac.h
@@ -526,7 +526,7 @@ int p54_init_leds(struct p54_common *priv);
 void p54_unregister_leds(struct p54_common *priv);
 
 /* xmit functions */
-int p54_tx_80211(struct ieee80211_hw *dev, struct sk_buff *skb);
+void p54_tx_80211(struct ieee80211_hw *dev, struct sk_buff *skb);
 int p54_tx_cancel(struct p54_common *priv, __le32 req_id);
 void p54_tx(struct p54_common *priv, struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/p54/main.c b/drivers/net/wireless/p54/main.c
index d7a92af24dd5..356e6bb443a6 100644
--- a/drivers/net/wireless/p54/main.c
+++ b/drivers/net/wireless/p54/main.c
@@ -157,7 +157,7 @@ static int p54_beacon_update(struct p54_common *priv,
 	 * to cancel the old beacon template by hand, instead the firmware
 	 * will release the previous one through the feedback mechanism.
 	 */
-	WARN_ON(p54_tx_80211(priv->hw, beacon));
+	p54_tx_80211(priv->hw, beacon);
 	priv->tsf_high32 = 0;
 	priv->tsf_low32 = 0;
 
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index a408ff333920..7834c26c2954 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -696,7 +696,7 @@ static u8 p54_convert_algo(u32 cipher)
 	}
 }
 
-int p54_tx_80211(struct ieee80211_hw *dev, struct sk_buff *skb)
+void p54_tx_80211(struct ieee80211_hw *dev, struct sk_buff *skb)
 {
 	struct p54_common *priv = dev->priv;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -717,12 +717,8 @@ int p54_tx_80211(struct ieee80211_hw *dev, struct sk_buff *skb)
 			    &hdr_flags, &aid, &burst_allowed);
 
 	if (p54_tx_qos_accounting_alloc(priv, skb, queue)) {
-		if (!IS_QOS_QUEUE(queue)) {
-			dev_kfree_skb_any(skb);
-			return NETDEV_TX_OK;
-		} else {
-			return NETDEV_TX_BUSY;
-		}
+		dev_kfree_skb_any(skb);
+		return;
 	}
 
 	padding = (unsigned long)(skb->data - (sizeof(*hdr) + sizeof(*txhdr))) & 3;
@@ -865,5 +861,4 @@ int p54_tx_80211(struct ieee80211_hw *dev, struct sk_buff *skb)
 	p54info->extra_len = extra_len;
 
 	p54_tx(priv, skb);
-	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index 1df432c1f2c7..19453d23e90d 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -1185,7 +1185,7 @@ void rt2x00lib_rxdone(struct queue_entry *entry);
 /*
  * mac80211 handlers.
  */
-int rt2x00mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
+void rt2x00mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
 int rt2x00mac_start(struct ieee80211_hw *hw);
 void rt2x00mac_stop(struct ieee80211_hw *hw);
 int rt2x00mac_add_interface(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index 1b3edef9e3d2..c2c35838c2f3 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -99,7 +99,7 @@ static int rt2x00mac_tx_rts_cts(struct rt2x00_dev *rt2x00dev,
 	return retval;
 }
 
-int rt2x00mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+void rt2x00mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct rt2x00_dev *rt2x00dev = hw->priv;
 	struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb);
@@ -155,12 +155,11 @@ int rt2x00mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	if (rt2x00queue_threshold(queue))
 		rt2x00queue_pause_queue(queue);
 
-	return NETDEV_TX_OK;
+	return;
 
  exit_fail:
 	ieee80211_stop_queue(rt2x00dev->hw, qid);
 	dev_kfree_skb_any(skb);
-	return NETDEV_TX_OK;
 }
 EXPORT_SYMBOL_GPL(rt2x00mac_tx);
 
diff --git a/drivers/net/wireless/rtl818x/rtl8180/dev.c b/drivers/net/wireless/rtl818x/rtl8180/dev.c
index b85debb4f7b1..80db5cabc9b9 100644
--- a/drivers/net/wireless/rtl818x/rtl8180/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8180/dev.c
@@ -240,7 +240,7 @@ static irqreturn_t rtl8180_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int rtl8180_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
+static void rtl8180_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
@@ -321,8 +321,6 @@ static int rtl8180_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	rtl818x_iowrite8(priv, &priv->map->TX_DMA_POLLING, (1 << (prio + 4)));
-
-	return 0;
 }
 
 void rtl8180_set_anaparam(struct rtl8180_priv *priv, u32 anaparam)
@@ -687,7 +685,6 @@ static void rtl8180_beacon_work(struct work_struct *work)
 	struct ieee80211_hw *dev = vif_priv->dev;
 	struct ieee80211_mgmt *mgmt;
 	struct sk_buff *skb;
-	int err = 0;
 
 	/* don't overflow the tx ring */
 	if (ieee80211_queue_stopped(dev, 0))
@@ -708,8 +705,7 @@ static void rtl8180_beacon_work(struct work_struct *work)
 	/* TODO: use actual beacon queue */
 	skb_set_queue_mapping(skb, 0);
 
-	err = rtl8180_tx(dev, skb);
-	WARN_ON(err);
+	rtl8180_tx(dev, skb);
 
 resched:
 	/*
diff --git a/drivers/net/wireless/rtl818x/rtl8187/dev.c b/drivers/net/wireless/rtl818x/rtl8187/dev.c
index 1f5df12cb156..c5a5e788f25f 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8187/dev.c
@@ -227,7 +227,7 @@ static void rtl8187_tx_cb(struct urb *urb)
 	}
 }
 
-static int rtl8187_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
+static void rtl8187_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 {
 	struct rtl8187_priv *priv = dev->priv;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -241,7 +241,7 @@ static int rtl8187_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 	urb = usb_alloc_urb(0, GFP_ATOMIC);
 	if (!urb) {
 		kfree_skb(skb);
-		return NETDEV_TX_OK;
+		return;
 	}
 
 	flags = skb->len;
@@ -309,8 +309,6 @@ static int rtl8187_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 	}
 	usb_free_urb(urb);
-
-	return NETDEV_TX_OK;
 }
 
 static void rtl8187_rx_cb(struct urb *urb)
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index b0996bf8a214..059ab036b01d 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -82,7 +82,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw)
 	mutex_unlock(&rtlpriv->locks.conf_mutex);
 }
 
-static int rtl_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void rtl_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
@@ -97,11 +97,10 @@ static int rtl_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 	rtlpriv->intf_ops->adapter_tx(hw, skb);
 
-	return NETDEV_TX_OK;
+	return;
 
 err_free:
 	dev_kfree_skb_any(skb);
-	return NETDEV_TX_OK;
 }
 
 static int rtl_op_add_interface(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/wl1251/main.c b/drivers/net/wireless/wl1251/main.c
index 5a1c13878eaf..12c9e635a6d6 100644
--- a/drivers/net/wireless/wl1251/main.c
+++ b/drivers/net/wireless/wl1251/main.c
@@ -375,7 +375,7 @@ out:
 	mutex_unlock(&wl->mutex);
 }
 
-static int wl1251_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void wl1251_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct wl1251 *wl = hw->priv;
 	unsigned long flags;
@@ -401,8 +401,6 @@ static int wl1251_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 		wl->tx_queue_stopped = true;
 		spin_unlock_irqrestore(&wl->wl_lock, flags);
 	}
-
-	return NETDEV_TX_OK;
 }
 
 static int wl1251_op_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/wl12xx/main.c b/drivers/net/wireless/wl12xx/main.c
index 95aa19ae84e5..947491a1d9cc 100644
--- a/drivers/net/wireless/wl12xx/main.c
+++ b/drivers/net/wireless/wl12xx/main.c
@@ -1034,7 +1034,7 @@ int wl1271_plt_stop(struct wl1271 *wl)
 	return ret;
 }
 
-static int wl1271_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void wl1271_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct wl1271 *wl = hw->priv;
 	unsigned long flags;
@@ -1073,8 +1073,6 @@ static int wl1271_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 	if (!test_bit(WL1271_FLAG_FW_TX_BUSY, &wl->flags))
 		ieee80211_queue_work(wl->hw, &wl->tx_work);
-
-	return NETDEV_TX_OK;
 }
 
 static struct notifier_block wl1271_dev_notifier = {
diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c
index 74a269ebbeb9..5037c8b2b415 100644
--- a/drivers/net/wireless/zd1211rw/zd_mac.c
+++ b/drivers/net/wireless/zd1211rw/zd_mac.c
@@ -850,7 +850,7 @@ static int fill_ctrlset(struct zd_mac *mac,
  * control block of the skbuff will be initialized. If necessary the incoming
  * mac80211 queues will be stopped.
  */
-static int zd_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void zd_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct zd_mac *mac = zd_hw_mac(hw);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -865,11 +865,10 @@ static int zd_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 	r = zd_usb_tx(&mac->chip.usb, skb);
 	if (r)
 		goto fail;
-	return 0;
+	return;
 
 fail:
 	dev_kfree_skb(skb);
-	return 0;
 }
 
 /**
diff --git a/drivers/staging/brcm80211/sys/wl_mac80211.c b/drivers/staging/brcm80211/sys/wl_mac80211.c
index bdd629d72a75..c83bdcc640a5 100644
--- a/drivers/staging/brcm80211/sys/wl_mac80211.c
+++ b/drivers/staging/brcm80211/sys/wl_mac80211.c
@@ -104,9 +104,6 @@ static int wl_request_fw(struct wl_info *wl, struct pci_dev *pdev);
 static void wl_release_fw(struct wl_info *wl);
 
 /* local prototypes */
-static int wl_start(struct sk_buff *skb, struct wl_info *wl);
-static int wl_start_int(struct wl_info *wl, struct ieee80211_hw *hw,
-			struct sk_buff *skb);
 static void wl_dpc(unsigned long data);
 
 MODULE_AUTHOR("Broadcom Corporation");
@@ -135,7 +132,6 @@ module_param(phymsglevel, int, 0);
 
 #define HW_TO_WL(hw)	 (hw->priv)
 #define WL_TO_HW(wl)	  (wl->pub->ieee_hw)
-static int wl_ops_tx(struct ieee80211_hw *hw, struct sk_buff *skb);
 static int wl_ops_start(struct ieee80211_hw *hw);
 static void wl_ops_stop(struct ieee80211_hw *hw);
 static int wl_ops_add_interface(struct ieee80211_hw *hw,
@@ -173,20 +169,18 @@ static int wl_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			   enum ieee80211_ampdu_mlme_action action,
 			   struct ieee80211_sta *sta, u16 tid, u16 *ssn);
 
-static int wl_ops_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
+static void wl_ops_tx(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
-	int status;
 	struct wl_info *wl = hw->priv;
 	WL_LOCK(wl);
 	if (!wl->pub->up) {
 		WL_ERROR("ops->tx called while down\n");
-		status = -ENETDOWN;
+		kfree_skb(skb);
 		goto done;
 	}
-	status = wl_start(skb, wl);
+	wlc_sendpkt_mac80211(wl->wlc, skb, hw);
  done:
 	WL_UNLOCK(wl);
-	return status;
 }
 
 static int wl_ops_start(struct ieee80211_hw *hw)
@@ -1316,22 +1310,6 @@ void wl_free(struct wl_info *wl)
 	osl_detach(osh);
 }
 
-/* transmit a packet */
-static int BCMFASTPATH wl_start(struct sk_buff *skb, struct wl_info *wl)
-{
-	if (!wl)
-		return -ENETDOWN;
-
-	return wl_start_int(wl, WL_TO_HW(wl), skb);
-}
-
-static int BCMFASTPATH
-wl_start_int(struct wl_info *wl, struct ieee80211_hw *hw, struct sk_buff *skb)
-{
-	wlc_sendpkt_mac80211(wl->wlc, skb, hw);
-	return NETDEV_TX_OK;
-}
-
 void wl_txflowcontrol(struct wl_info *wl, struct wl_if *wlif, bool state,
 		      int prio)
 {
diff --git a/drivers/staging/winbond/wbusb.c b/drivers/staging/winbond/wbusb.c
index 2163d60c2eaf..3724e1e67ec2 100644
--- a/drivers/staging/winbond/wbusb.c
+++ b/drivers/staging/winbond/wbusb.c
@@ -118,13 +118,14 @@ static void wbsoft_configure_filter(struct ieee80211_hw *dev,
 	*total_flags = new_flags;
 }
 
-static int wbsoft_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
+static void wbsoft_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 {
 	struct wbsoft_priv *priv = dev->priv;
 
 	if (priv->sMlmeFrame.IsInUsed != PACKET_FREE_TO_USE) {
 		priv->sMlmeFrame.wNumTxMMPDUDiscarded++;
-		return NETDEV_TX_BUSY;
+		kfree_skb(skb);
+		return;
 	}
 
 	priv->sMlmeFrame.IsInUsed = PACKET_COME_FROM_MLME;
@@ -140,8 +141,6 @@ static int wbsoft_tx(struct ieee80211_hw *dev, struct sk_buff *skb)
 	 */
 
 	Mds_Tx(priv);
-
-	return NETDEV_TX_OK;
 }
 
 static int wbsoft_start(struct ieee80211_hw *dev)
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a13c8d8fca5c..96cc7ed35169 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1801,7 +1801,7 @@ enum ieee80211_ampdu_mlme_action {
  *	aborted before it expires. This callback may sleep.
  */
 struct ieee80211_ops {
-	int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb);
+	void (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb);
 	int (*start)(struct ieee80211_hw *hw);
 	void (*stop)(struct ieee80211_hw *hw);
 	int (*add_interface)(struct ieee80211_hw *hw,
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 78af32d4bc58..32f05c1abbaf 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -5,9 +5,9 @@
 #include "ieee80211_i.h"
 #include "driver-trace.h"
 
-static inline int drv_tx(struct ieee80211_local *local, struct sk_buff *skb)
+static inline void drv_tx(struct ieee80211_local *local, struct sk_buff *skb)
 {
-	return local->ops->tx(&local->hw, skb);
+	local->ops->tx(&local->hw, skb);
 }
 
 static inline int drv_start(struct ieee80211_local *local)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 34edf7f22b0e..081dcaf6577b 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -33,10 +33,6 @@
 #include "wme.h"
 #include "rate.h"
 
-#define IEEE80211_TX_OK		0
-#define IEEE80211_TX_AGAIN	1
-#define IEEE80211_TX_PENDING	2
-
 /* misc utils */
 
 static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, int group_addr,
@@ -1285,16 +1281,17 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	return TX_CONTINUE;
 }
 
-static int __ieee80211_tx(struct ieee80211_local *local,
-			  struct sk_buff **skbp,
-			  struct sta_info *sta,
-			  bool txpending)
+/*
+ * Returns false if the frame couldn't be transmitted but was queued instead.
+ */
+static bool __ieee80211_tx(struct ieee80211_local *local, struct sk_buff **skbp,
+			   struct sta_info *sta, bool txpending)
 {
 	struct sk_buff *skb = *skbp, *next;
 	struct ieee80211_tx_info *info;
 	struct ieee80211_sub_if_data *sdata;
 	unsigned long flags;
-	int ret, len;
+	int len;
 	bool fragm = false;
 
 	while (skb) {
@@ -1302,13 +1299,37 @@ static int __ieee80211_tx(struct ieee80211_local *local,
 		__le16 fc;
 
 		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
-		ret = IEEE80211_TX_OK;
 		if (local->queue_stop_reasons[q] ||
-		    (!txpending && !skb_queue_empty(&local->pending[q])))
-			ret = IEEE80211_TX_PENDING;
+		    (!txpending && !skb_queue_empty(&local->pending[q]))) {
+			/*
+			 * Since queue is stopped, queue up frames for later
+			 * transmission from the tx-pending tasklet when the
+			 * queue is woken again.
+			 */
+
+			do {
+				next = skb->next;
+				skb->next = NULL;
+				/*
+				 * NB: If txpending is true, next must already
+				 * be NULL since we must've gone through this
+				 * loop before already; therefore we can just
+				 * queue the frame to the head without worrying
+				 * about reordering of fragments.
+				 */
+				if (unlikely(txpending))
+					__skb_queue_head(&local->pending[q],
+							 skb);
+				else
+					__skb_queue_tail(&local->pending[q],
+							 skb);
+			} while ((skb = next));
+
+			spin_unlock_irqrestore(&local->queue_stop_reason_lock,
+					       flags);
+			return false;
+		}
 		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
-		if (ret != IEEE80211_TX_OK)
-			return ret;
 
 		info = IEEE80211_SKB_CB(skb);
 
@@ -1343,15 +1364,7 @@ static int __ieee80211_tx(struct ieee80211_local *local,
 			info->control.sta = NULL;
 
 		fc = ((struct ieee80211_hdr *)skb->data)->frame_control;
-		ret = drv_tx(local, skb);
-		if (WARN_ON(ret != NETDEV_TX_OK && skb->len != len)) {
-			dev_kfree_skb(skb);
-			ret = NETDEV_TX_OK;
-		}
-		if (ret != NETDEV_TX_OK) {
-			info->control.vif = &sdata->vif;
-			return IEEE80211_TX_AGAIN;
-		}
+		drv_tx(local, skb);
 
 		ieee80211_tpt_led_trig_tx(local, fc, len);
 		*skbp = skb = next;
@@ -1359,7 +1372,7 @@ static int __ieee80211_tx(struct ieee80211_local *local,
 		fragm = true;
 	}
 
-	return IEEE80211_TX_OK;
+	return true;
 }
 
 /*
@@ -1419,23 +1432,24 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx)
 	return 0;
 }
 
-static void ieee80211_tx(struct ieee80211_sub_if_data *sdata,
+/*
+ * Returns false if the frame couldn't be transmitted but was queued instead.
+ */
+static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 			 struct sk_buff *skb, bool txpending)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_data tx;
 	ieee80211_tx_result res_prepare;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct sk_buff *next;
-	unsigned long flags;
-	int ret, retries;
 	u16 queue;
+	bool result = true;
 
 	queue = skb_get_queue_mapping(skb);
 
 	if (unlikely(skb->len < 10)) {
 		dev_kfree_skb(skb);
-		return;
+		return true;
 	}
 
 	rcu_read_lock();
@@ -1445,85 +1459,19 @@ static void ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 
 	if (unlikely(res_prepare == TX_DROP)) {
 		dev_kfree_skb(skb);
-		rcu_read_unlock();
-		return;
+		goto out;
 	} else if (unlikely(res_prepare == TX_QUEUED)) {
-		rcu_read_unlock();
-		return;
+		goto out;
 	}
 
 	tx.channel = local->hw.conf.channel;
 	info->band = tx.channel->band;
 
-	if (invoke_tx_handlers(&tx))
-		goto out;
-
-	retries = 0;
- retry:
-	ret = __ieee80211_tx(local, &tx.skb, tx.sta, txpending);
-	switch (ret) {
-	case IEEE80211_TX_OK:
-		break;
-	case IEEE80211_TX_AGAIN:
-		/*
-		 * Since there are no fragmented frames on A-MPDU
-		 * queues, there's no reason for a driver to reject
-		 * a frame there, warn and drop it.
-		 */
-		if (WARN_ON(info->flags & IEEE80211_TX_CTL_AMPDU))
-			goto drop;
-		/* fall through */
-	case IEEE80211_TX_PENDING:
-		skb = tx.skb;
-
-		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
-
-		if (local->queue_stop_reasons[queue] ||
-		    !skb_queue_empty(&local->pending[queue])) {
-			/*
-			 * if queue is stopped, queue up frames for later
-			 * transmission from the tasklet
-			 */
-			do {
-				next = skb->next;
-				skb->next = NULL;
-				if (unlikely(txpending))
-					__skb_queue_head(&local->pending[queue],
-							 skb);
-				else
-					__skb_queue_tail(&local->pending[queue],
-							 skb);
-			} while ((skb = next));
-
-			spin_unlock_irqrestore(&local->queue_stop_reason_lock,
-					       flags);
-		} else {
-			/*
-			 * otherwise retry, but this is a race condition or
-			 * a driver bug (which we warn about if it persists)
-			 */
-			spin_unlock_irqrestore(&local->queue_stop_reason_lock,
-					       flags);
-
-			retries++;
-			if (WARN(retries > 10, "tx refused but queue active\n"))
-				goto drop;
-			goto retry;
-		}
-	}
+	if (!invoke_tx_handlers(&tx))
+		result = __ieee80211_tx(local, &tx.skb, tx.sta, txpending);
  out:
 	rcu_read_unlock();
-	return;
-
- drop:
-	rcu_read_unlock();
-
-	skb = tx.skb;
-	while (skb) {
-		next = skb->next;
-		dev_kfree_skb(skb);
-		skb = next;
-	}
+	return result;
 }
 
 /* device xmit handlers */
@@ -2070,6 +2018,11 @@ void ieee80211_clear_tx_pending(struct ieee80211_local *local)
 		skb_queue_purge(&local->pending[i]);
 }
 
+/*
+ * Returns false if the frame couldn't be transmitted but was queued instead,
+ * which in this case means re-queued -- take as an indication to stop sending
+ * more pending frames.
+ */
 static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 				     struct sk_buff *skb)
 {
@@ -2077,20 +2030,17 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 	struct ieee80211_sub_if_data *sdata;
 	struct sta_info *sta;
 	struct ieee80211_hdr *hdr;
-	int ret;
-	bool result = true;
+	bool result;
 
 	sdata = vif_to_sdata(info->control.vif);
 
 	if (info->flags & IEEE80211_TX_INTFL_NEED_TXPROCESSING) {
-		ieee80211_tx(sdata, skb, true);
+		result = ieee80211_tx(sdata, skb, true);
 	} else {
 		hdr = (struct ieee80211_hdr *)skb->data;
 		sta = sta_info_get(sdata, hdr->addr1);
 
-		ret = __ieee80211_tx(local, &skb, sta, true);
-		if (ret != IEEE80211_TX_OK)
-			result = false;
+		result = __ieee80211_tx(local, &skb, sta, true);
 	}
 
 	return result;
@@ -2132,8 +2082,6 @@ void ieee80211_tx_pending(unsigned long data)
 						flags);
 
 			txok = ieee80211_tx_pending_skb(local, skb);
-			if (!txok)
-				__skb_queue_head(&local->pending[i], skb);
 			spin_lock_irqsave(&local->queue_stop_reason_lock,
 					  flags);
 			if (!txok)
-- 
cgit v1.2.3


From 5f16a43617d46cf255a66f4dc193a7f5b2540aaf Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Feb 2011 15:36:57 +0100
Subject: mac80211: support direct offchannel TX offload

For devices supported by iwlwifi sometimes
off-channel transmissions need to be handled
by the device completely. To support this
mac80211 needs to pass the frame directly
to the driver and not through the TX path
as the driver needs the frame and channel
information at the same time.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/mac80211.h      | 10 ++++++++++
 net/mac80211/cfg.c          | 39 +++++++++++++++++++++++++++++++++++++++
 net/mac80211/driver-ops.h   | 31 +++++++++++++++++++++++++++++++
 net/mac80211/driver-trace.h | 33 +++++++++++++++++++++++++++++++++
 net/mac80211/ieee80211_i.h  |  1 +
 net/mac80211/status.c       |  4 ++++
 6 files changed, 118 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 96cc7ed35169..2b072fa99399 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1799,6 +1799,11 @@ enum ieee80211_ampdu_mlme_action {
  *	ieee80211_remain_on_channel_expired(). This callback may sleep.
  * @cancel_remain_on_channel: Requests that an ongoing off-channel period is
  *	aborted before it expires. This callback may sleep.
+ * @offchannel_tx: Transmit frame on another channel, wait for a response
+ *	and return. Reliable TX status must be reported for the frame. If the
+ *	return value is 1, then the @remain_on_channel will be used with a
+ *	regular transmission (if supported.)
+ * @offchannel_tx_cancel_wait: cancel wait associated with offchannel TX
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb);
@@ -1878,6 +1883,11 @@ struct ieee80211_ops {
 				 enum nl80211_channel_type channel_type,
 				 int duration);
 	int (*cancel_remain_on_channel)(struct ieee80211_hw *hw);
+	int (*offchannel_tx)(struct ieee80211_hw *hw, struct sk_buff *skb,
+			     struct ieee80211_channel *chan,
+			     enum nl80211_channel_type channel_type,
+			     unsigned int wait);
+	int (*offchannel_tx_cancel_wait)(struct ieee80211_hw *hw);
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 140503d4c97a..8b436c768c4e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1800,6 +1800,33 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev,
 
 	*cookie = (unsigned long) skb;
 
+	if (is_offchan && local->ops->offchannel_tx) {
+		int ret;
+
+		IEEE80211_SKB_CB(skb)->band = chan->band;
+
+		mutex_lock(&local->mtx);
+
+		if (local->hw_offchan_tx_cookie) {
+			mutex_unlock(&local->mtx);
+			return -EBUSY;
+		}
+
+		/* TODO: bitrate control, TX processing? */
+		ret = drv_offchannel_tx(local, skb, chan, channel_type, wait);
+
+		if (ret == 0)
+			local->hw_offchan_tx_cookie = *cookie;
+		mutex_unlock(&local->mtx);
+
+		/*
+		 * Allow driver to return 1 to indicate it wants to have the
+		 * frame transmitted with a remain_on_channel + regular TX.
+		 */
+		if (ret != 1)
+			return ret;
+	}
+
 	if (is_offchan && local->ops->remain_on_channel) {
 		unsigned int duration;
 		int ret;
@@ -1886,6 +1913,18 @@ static int ieee80211_mgmt_tx_cancel_wait(struct wiphy *wiphy,
 
 	mutex_lock(&local->mtx);
 
+	if (local->ops->offchannel_tx_cancel_wait &&
+	    local->hw_offchan_tx_cookie == cookie) {
+		ret = drv_offchannel_tx_cancel_wait(local);
+
+		if (!ret)
+			local->hw_offchan_tx_cookie = 0;
+
+		mutex_unlock(&local->mtx);
+
+		return ret;
+	}
+
 	if (local->ops->cancel_remain_on_channel) {
 		cookie ^= 2;
 		ret = ieee80211_cancel_remain_on_channel_hw(local, cookie);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 32f05c1abbaf..3729296f6f95 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -495,4 +495,35 @@ static inline int drv_cancel_remain_on_channel(struct ieee80211_local *local)
 	return ret;
 }
 
+static inline int drv_offchannel_tx(struct ieee80211_local *local,
+				    struct sk_buff *skb,
+				    struct ieee80211_channel *chan,
+				    enum nl80211_channel_type channel_type,
+				    unsigned int wait)
+{
+	int ret;
+
+	might_sleep();
+
+	trace_drv_offchannel_tx(local, skb, chan, channel_type, wait);
+	ret = local->ops->offchannel_tx(&local->hw, skb, chan,
+					channel_type, wait);
+	trace_drv_return_int(local, ret);
+
+	return ret;
+}
+
+static inline int drv_offchannel_tx_cancel_wait(struct ieee80211_local *local)
+{
+	int ret;
+
+	might_sleep();
+
+	trace_drv_offchannel_tx_cancel_wait(local);
+	ret = local->ops->offchannel_tx_cancel_wait(&local->hw);
+	trace_drv_return_int(local, ret);
+
+	return ret;
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h
index e5cce19a7d65..520fe2444893 100644
--- a/net/mac80211/driver-trace.h
+++ b/net/mac80211/driver-trace.h
@@ -884,6 +884,39 @@ DEFINE_EVENT(local_only_evt, drv_cancel_remain_on_channel,
 	TP_ARGS(local)
 );
 
+TRACE_EVENT(drv_offchannel_tx,
+	TP_PROTO(struct ieee80211_local *local, struct sk_buff *skb,
+		 struct ieee80211_channel *chan,
+		 enum nl80211_channel_type channel_type,
+		 unsigned int wait),
+
+	TP_ARGS(local, skb, chan, channel_type, wait),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(int, center_freq)
+		__field(int, channel_type)
+		__field(unsigned int, wait)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->center_freq = chan->center_freq;
+		__entry->channel_type = channel_type;
+		__entry->wait = wait;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT " freq:%dMHz, wait:%dms",
+		LOCAL_PR_ARG, __entry->center_freq, __entry->wait
+	)
+);
+
+DEFINE_EVENT(local_only_evt, drv_offchannel_tx_cancel_wait,
+	TP_PROTO(struct ieee80211_local *local),
+	TP_ARGS(local)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 0a570a111a84..a40401701424 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -957,6 +957,7 @@ struct ieee80211_local {
 	unsigned int hw_roc_duration;
 	u32 hw_roc_cookie;
 	bool hw_roc_for_tx;
+	unsigned long hw_offchan_tx_cookie;
 
 	/* dummy netdev for use w/ NAPI */
 	struct net_device napi_dev;
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 865185127f51..b936dd29e92b 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -341,6 +341,10 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			cookie = local->hw_roc_cookie ^ 2;
 			local->hw_roc_skb_for_status = NULL;
 		}
+
+		if (cookie == local->hw_offchan_tx_cookie)
+			local->hw_offchan_tx_cookie = 0;
+
 		cfg80211_mgmt_tx_status(
 			skb->dev, cookie, skb->data, skb->len,
 			!!(info->flags & IEEE80211_TX_STAT_ACK), GFP_ATOMIC);
-- 
cgit v1.2.3


From fe41947e1aa12e96a50edaee123b4e4de03b668b Mon Sep 17 00:00:00 2001
From: Alexandre Bounine <alexandre.bounine@idt.com>
Date: Fri, 25 Feb 2011 14:44:31 -0800
Subject: rapidio: fix sysfs config attribute to access 16MB of maint space

Fixes sysfs config attribute to allow access to entire 16MB maintenance
space of RapidIO devices.

Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Li Yang <leoli@freescale.com>
Cc: Thomas Moll <thomas.moll@sysgo.com>
Cc: Micha Nelissen <micha@neli.hopto.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rapidio/rio-sysfs.c | 12 ++++++------
 include/linux/rio_regs.h    |  4 +++-
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c
index 76b41853a877..1269fbd2deca 100644
--- a/drivers/rapidio/rio-sysfs.c
+++ b/drivers/rapidio/rio-sysfs.c
@@ -77,9 +77,9 @@ rio_read_config(struct file *filp, struct kobject *kobj,
 
 	/* Several chips lock up trying to read undefined config space */
 	if (capable(CAP_SYS_ADMIN))
-		size = 0x200000;
+		size = RIO_MAINT_SPACE_SZ;
 
-	if (off > size)
+	if (off >= size)
 		return 0;
 	if (off + count > size) {
 		size -= off;
@@ -147,10 +147,10 @@ rio_write_config(struct file *filp, struct kobject *kobj,
 	loff_t init_off = off;
 	u8 *data = (u8 *) buf;
 
-	if (off > 0x200000)
+	if (off >= RIO_MAINT_SPACE_SZ)
 		return 0;
-	if (off + count > 0x200000) {
-		size = 0x200000 - off;
+	if (off + count > RIO_MAINT_SPACE_SZ) {
+		size = RIO_MAINT_SPACE_SZ - off;
 		count = size;
 	}
 
@@ -200,7 +200,7 @@ static struct bin_attribute rio_config_attr = {
 		 .name = "config",
 		 .mode = S_IRUGO | S_IWUSR,
 		 },
-	.size = 0x200000,
+	.size = RIO_MAINT_SPACE_SZ,
 	.read = rio_read_config,
 	.write = rio_write_config,
 };
diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h
index d63dcbaea169..9026b30238f3 100644
--- a/include/linux/rio_regs.h
+++ b/include/linux/rio_regs.h
@@ -14,10 +14,12 @@
 #define LINUX_RIO_REGS_H
 
 /*
- * In RapidIO, each device has a 2MB configuration space that is
+ * In RapidIO, each device has a 16MB configuration space that is
  * accessed via maintenance transactions.  Portions of configuration
  * space are standardized and/or reserved.
  */
+#define RIO_MAINT_SPACE_SZ	0x1000000 /* 16MB of RapidIO mainenance space */
+
 #define RIO_DEV_ID_CAR		0x00	/* [I] Device Identity CAR */
 #define RIO_DEV_INFO_CAR	0x04	/* [I] Device Information CAR */
 #define RIO_ASM_ID_CAR		0x08	/* [I] Assembly Identity CAR */
-- 
cgit v1.2.3


From 8d32a307e4faa8b123dc8a9cd56d1a7525f69ad3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 23 Feb 2011 23:52:23 +0000
Subject: genirq: Provide forced interrupt threading

Add a commandline parameter "threadirqs" which forces all interrupts except
those marked IRQF_NO_THREAD to run threaded. That's mostly a debug option to
allow retrieving better debug data from crashing interrupt handlers. If
"threadirqs" is not enabled on the kernel command line, then there is no
impact in the interrupt hotpath.

Architecture code needs to select CONFIG_IRQ_FORCED_THREADING after
marking the interrupts which cant be threaded IRQF_NO_THREAD. All
interrupts which have IRQF_TIMER set are implict marked
IRQF_NO_THREAD. Also all PER_CPU interrupts are excluded.

Forced threading hard interrupts also forces all soft interrupt
handling into thread context.

When enabled it might slow down things a bit, but for debugging problems in
interrupt code it's a reasonable penalty as it does not immediately
crash and burn the machine when an interrupt handler is buggy.

Some test results on a Core2Duo machine:

Cache cold run of:
 # time git grep irq_desc

      non-threaded       threaded
 real 1m18.741s          1m19.061s
 user 0m1.874s           0m1.757s
 sys  0m5.843s           0m5.427s

 # iperf -c server
non-threaded
[  3]  0.0-10.0 sec  1.09 GBytes   933 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   934 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   933 Mbits/sec
threaded
[  3]  0.0-10.0 sec  1.09 GBytes   939 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   934 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   937 Mbits/sec

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.772668648@linutronix.de>
---
 Documentation/kernel-parameters.txt |  4 +++
 include/linux/interrupt.h           |  7 ++++
 kernel/irq/Kconfig                  |  3 ++
 kernel/irq/internals.h              |  2 ++
 kernel/irq/manage.c                 | 67 ++++++++++++++++++++++++++++++++++---
 kernel/softirq.c                    | 16 +++++++--
 6 files changed, 93 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 89835a4766a6..cac6cf9a588c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2436,6 +2436,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			<deci-seconds>: poll all this frequency
 			0: no polling (default)
 
+	threadirqs	[KNL]
+			Force threading of all interrupt handlers except those
+			marked explicitely IRQF_NO_THREAD.
+
 	topology=	[S390]
 			Format: {off | on}
 			Specify if the kernel should make use of the cpu
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 0fc3eb9397b4..f8a8af108e0c 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -383,6 +383,13 @@ static inline int disable_irq_wake(unsigned int irq)
 }
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
+
+#ifdef CONFIG_IRQ_FORCED_THREADING
+extern bool force_irqthreads;
+#else
+#define force_irqthreads	(0)
+#endif
+
 #ifndef __ARCH_SET_SOFTIRQ_PENDING
 #define set_softirq_pending(x) (local_softirq_pending() = (x))
 #define or_softirq_pending(x)  (local_softirq_pending() |= (x))
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 355b8c7957f5..144db9dcfcde 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -38,6 +38,9 @@ config HARDIRQS_SW_RESEND
 config IRQ_PREFLOW_FASTEOI
        bool
 
+config IRQ_FORCED_THREADING
+       bool
+
 config SPARSE_IRQ
 	bool "Support sparse irq numbering"
 	depends on HAVE_SPARSE_IRQ
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 935bec4bfa87..6c6ec9a49027 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -27,12 +27,14 @@ extern int noirqdebug;
  * IRQTF_DIED      - handler thread died
  * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
  * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
+ * IRQTF_FORCED_THREAD  - irq action is force threaded
  */
 enum {
 	IRQTF_RUNTHREAD,
 	IRQTF_DIED,
 	IRQTF_WARNED,
 	IRQTF_AFFINITY,
+	IRQTF_FORCED_THREAD,
 };
 
 /*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 58c861367300..acd599a43bfb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -17,6 +17,17 @@
 
 #include "internals.h"
 
+#ifdef CONFIG_IRQ_FORCED_THREADING
+__read_mostly bool force_irqthreads;
+
+static int __init setup_forced_irqthreads(char *arg)
+{
+	force_irqthreads = true;
+	return 0;
+}
+early_param("threadirqs", setup_forced_irqthreads);
+#endif
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -701,6 +712,32 @@ static inline void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
 #endif
 
+/*
+ * Interrupts which are not explicitely requested as threaded
+ * interrupts rely on the implicit bh/preempt disable of the hard irq
+ * context. So we need to disable bh here to avoid deadlocks and other
+ * side effects.
+ */
+static void
+irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	local_bh_disable();
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+	local_bh_enable();
+}
+
+/*
+ * Interrupts explicitely requested as threaded interupts want to be
+ * preemtible - many of them need to sleep and wait for slow busses to
+ * complete.
+ */
+static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+{
+	action->thread_fn(action->irq, action->dev_id);
+	irq_finalize_oneshot(desc, action, false);
+}
+
 /*
  * Interrupt handler thread
  */
@@ -711,8 +748,15 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
+	void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
 	int wake;
 
+	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
+					&action->thread_flags))
+		handler_fn = irq_forced_thread_fn;
+	else
+		handler_fn = irq_thread_fn;
+
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
 
@@ -736,10 +780,7 @@ static int irq_thread(void *data)
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
 			raw_spin_unlock_irq(&desc->lock);
-
-			action->thread_fn(action->irq, action->dev_id);
-
-			irq_finalize_oneshot(desc, action, false);
+			handler_fn(desc, action);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -789,6 +830,22 @@ void exit_irq_thread(void)
 	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
 }
 
+static void irq_setup_forced_threading(struct irqaction *new)
+{
+	if (!force_irqthreads)
+		return;
+	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
+		return;
+
+	new->flags |= IRQF_ONESHOT;
+
+	if (!new->thread_fn) {
+		set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
+		new->thread_fn = new->handler;
+		new->handler = irq_default_primary_handler;
+	}
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -838,6 +895,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * dummy function which warns when called.
 		 */
 		new->handler = irq_nested_primary_handler;
+	} else {
+		irq_setup_forced_threading(new);
 	}
 
 	/*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c0490464e92f..a33fb2911248 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -311,9 +311,21 @@ void irq_enter(void)
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
-# define invoke_softirq()	__do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		__do_softirq();
+	else
+		wakeup_softirqd();
+}
 #else
-# define invoke_softirq()	do_softirq()
+static inline void invoke_softirq(void)
+{
+	if (!force_irqthreads)
+		do_softirq();
+	else
+		wakeup_softirqd();
+}
 #endif
 
 /*
-- 
cgit v1.2.3


From 4e51eae9cdda4bf096e73a4ebe23f8f96a17596a Mon Sep 17 00:00:00 2001
From: Szymon Janc <szymon.janc@tieto.com>
Date: Fri, 25 Feb 2011 19:05:48 +0100
Subject: Bluetooth: Move index to common header in management interface

Most mgmt commands and event are related to hci adapter. Moving index to
common header allow to easily use it in command status while reporting errors.
For those not related to adapter use MGMT_INDEX_NONE (0xFFFF) as index.

Signed-off-by: Szymon Janc <szymon.janc@tieto.com>
Acked-by: Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
---
 include/net/bluetooth/mgmt.h |  43 +----
 net/bluetooth/mgmt.c         | 407 +++++++++++++++++++------------------------
 2 files changed, 183 insertions(+), 267 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 1e63c3141a78..5fabfa886b3e 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -21,11 +21,13 @@
    SOFTWARE IS DISCLAIMED.
 */
 
+#define MGMT_INDEX_NONE			0xFFFF
+
 struct mgmt_hdr {
 	__le16 opcode;
+	__le16 index;
 	__le16 len;
 } __packed;
-#define MGMT_HDR_SIZE			4
 
 #define MGMT_OP_READ_VERSION		0x0001
 struct mgmt_rp_read_version {
@@ -40,11 +42,7 @@ struct mgmt_rp_read_index_list {
 } __packed;
 
 #define MGMT_OP_READ_INFO		0x0004
-struct mgmt_cp_read_info {
-	__le16 index;
-} __packed;
 struct mgmt_rp_read_info {
-	__le16 index;
 	__u8 type;
 	__u8 powered;
 	__u8 connectable;
@@ -60,7 +58,6 @@ struct mgmt_rp_read_info {
 } __packed;
 
 struct mgmt_mode {
-	__le16 index;
 	__u8 val;
 } __packed;
 
@@ -74,27 +71,23 @@ struct mgmt_mode {
 
 #define MGMT_OP_ADD_UUID		0x0009
 struct mgmt_cp_add_uuid {
-	__le16 index;
 	__u8 uuid[16];
 	__u8 svc_hint;
 } __packed;
 
 #define MGMT_OP_REMOVE_UUID		0x000A
 struct mgmt_cp_remove_uuid {
-	__le16 index;
 	__u8 uuid[16];
 } __packed;
 
 #define MGMT_OP_SET_DEV_CLASS		0x000B
 struct mgmt_cp_set_dev_class {
-	__le16 index;
 	__u8 major;
 	__u8 minor;
 } __packed;
 
 #define MGMT_OP_SET_SERVICE_CACHE	0x000C
 struct mgmt_cp_set_service_cache {
-	__le16 index;
 	__u8 enable;
 } __packed;
 
@@ -107,7 +100,6 @@ struct mgmt_key_info {
 
 #define MGMT_OP_LOAD_KEYS		0x000D
 struct mgmt_cp_load_keys {
-	__le16 index;
 	__u8 debug_keys;
 	__le16 key_count;
 	struct mgmt_key_info keys[0];
@@ -115,75 +107,60 @@ struct mgmt_cp_load_keys {
 
 #define MGMT_OP_REMOVE_KEY		0x000E
 struct mgmt_cp_remove_key {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 disconnect;
 } __packed;
 
 #define MGMT_OP_DISCONNECT		0x000F
 struct mgmt_cp_disconnect {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 struct mgmt_rp_disconnect {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 
 #define MGMT_OP_GET_CONNECTIONS		0x0010
-struct mgmt_cp_get_connections {
-	__le16 index;
-} __packed;
 struct mgmt_rp_get_connections {
-	__le16 index;
 	__le16 conn_count;
 	bdaddr_t conn[0];
 } __packed;
 
 #define MGMT_OP_PIN_CODE_REPLY		0x0011
 struct mgmt_cp_pin_code_reply {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 pin_len;
 	__u8 pin_code[16];
 } __packed;
 struct mgmt_rp_pin_code_reply {
-	__le16 index;
 	bdaddr_t bdaddr;
 	uint8_t status;
 } __packed;
 
 #define MGMT_OP_PIN_CODE_NEG_REPLY	0x0012
 struct mgmt_cp_pin_code_neg_reply {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 
 #define MGMT_OP_SET_IO_CAPABILITY	0x0013
 struct mgmt_cp_set_io_capability {
-	__le16 index;
 	__u8 io_capability;
 } __packed;
 
 #define MGMT_OP_PAIR_DEVICE		0x0014
 struct mgmt_cp_pair_device {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 io_cap;
 } __packed;
 struct mgmt_rp_pair_device {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 status;
 } __packed;
 
 #define MGMT_OP_USER_CONFIRM_REPLY	0x0015
 struct mgmt_cp_user_confirm_reply {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 struct mgmt_rp_user_confirm_reply {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 status;
 } __packed;
@@ -204,19 +181,12 @@ struct mgmt_ev_cmd_status {
 
 #define MGMT_EV_CONTROLLER_ERROR	0x0003
 struct mgmt_ev_controller_error {
-	__le16 index;
 	__u8 error_code;
 } __packed;
 
 #define MGMT_EV_INDEX_ADDED		0x0004
-struct mgmt_ev_index_added {
-	__le16 index;
-} __packed;
 
 #define MGMT_EV_INDEX_REMOVED		0x0005
-struct mgmt_ev_index_removed {
-	__le16 index;
-} __packed;
 
 #define MGMT_EV_POWERED			0x0006
 
@@ -228,46 +198,39 @@ struct mgmt_ev_index_removed {
 
 #define MGMT_EV_NEW_KEY			0x000A
 struct mgmt_ev_new_key {
-	__le16 index;
 	struct mgmt_key_info key;
 	__u8 old_key_type;
 } __packed;
 
 #define MGMT_EV_CONNECTED		0x000B
 struct mgmt_ev_connected {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 
 #define MGMT_EV_DISCONNECTED		0x000C
 struct mgmt_ev_disconnected {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 
 #define MGMT_EV_CONNECT_FAILED		0x000D
 struct mgmt_ev_connect_failed {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 status;
 } __packed;
 
 #define MGMT_EV_PIN_CODE_REQUEST	0x000E
 struct mgmt_ev_pin_code_request {
-	__le16 index;
 	bdaddr_t bdaddr;
 } __packed;
 
 #define MGMT_EV_USER_CONFIRM_REQUEST	0x000F
 struct mgmt_ev_user_confirm_request {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__le32 value;
 } __packed;
 
 #define MGMT_EV_AUTH_FAILED		0x0010
 struct mgmt_ev_auth_failed {
-	__le16 index;
 	bdaddr_t bdaddr;
 	__u8 status;
 } __packed;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 4543ede4ddf3..98c92aee6239 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -43,7 +43,7 @@ struct pending_cmd {
 
 LIST_HEAD(cmd_list);
 
-static int cmd_status(struct sock *sk, u16 cmd, u8 status)
+static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status)
 {
 	struct sk_buff *skb;
 	struct mgmt_hdr *hdr;
@@ -58,6 +58,7 @@ static int cmd_status(struct sock *sk, u16 cmd, u8 status)
 	hdr = (void *) skb_put(skb, sizeof(*hdr));
 
 	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS);
+	hdr->index = cpu_to_le16(index);
 	hdr->len = cpu_to_le16(sizeof(*ev));
 
 	ev = (void *) skb_put(skb, sizeof(*ev));
@@ -70,7 +71,8 @@ static int cmd_status(struct sock *sk, u16 cmd, u8 status)
 	return 0;
 }
 
-static int cmd_complete(struct sock *sk, u16 cmd, void *rp, size_t rp_len)
+static int cmd_complete(struct sock *sk, u16 index, u16 cmd, void *rp,
+								size_t rp_len)
 {
 	struct sk_buff *skb;
 	struct mgmt_hdr *hdr;
@@ -85,6 +87,7 @@ static int cmd_complete(struct sock *sk, u16 cmd, void *rp, size_t rp_len)
 	hdr = (void *) skb_put(skb, sizeof(*hdr));
 
 	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->index = cpu_to_le16(index);
 	hdr->len = cpu_to_le16(sizeof(*ev) + rp_len);
 
 	ev = (void *) skb_put(skb, sizeof(*ev) + rp_len);
@@ -106,7 +109,8 @@ static int read_version(struct sock *sk)
 	rp.version = MGMT_VERSION;
 	put_unaligned_le16(MGMT_REVISION, &rp.revision);
 
-	return cmd_complete(sk, MGMT_OP_READ_VERSION, &rp, sizeof(rp));
+	return cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, &rp,
+								sizeof(rp));
 }
 
 static int read_index_list(struct sock *sk)
@@ -152,32 +156,24 @@ static int read_index_list(struct sock *sk)
 
 	read_unlock(&hci_dev_list_lock);
 
-	err = cmd_complete(sk, MGMT_OP_READ_INDEX_LIST, rp, rp_len);
+	err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST, rp,
+									rp_len);
 
 	kfree(rp);
 
 	return err;
 }
 
-static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
+static int read_controller_info(struct sock *sk, u16 index)
 {
 	struct mgmt_rp_read_info rp;
-	struct mgmt_cp_read_info *cp = (void *) data;
 	struct hci_dev *hdev;
-	u16 dev_id;
 
-	BT_DBG("sock %p", sk);
-
-	if (len != 2)
-		return cmd_status(sk, MGMT_OP_READ_INFO, EINVAL);
-
-	dev_id = get_unaligned_le16(&cp->index);
+	BT_DBG("sock %p hci%u", sk, index);
 
-	BT_DBG("request for hci%u", dev_id);
-
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_READ_INFO, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_READ_INFO, ENODEV);
 
 	hci_del_off_timer(hdev);
 
@@ -185,7 +181,6 @@ static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
 
 	set_bit(HCI_MGMT, &hdev->flags);
 
-	put_unaligned_le16(hdev->id, &rp.index);
 	rp.type = hdev->dev_type;
 
 	rp.powered = test_bit(HCI_UP, &hdev->flags);
@@ -210,7 +205,7 @@ static int read_controller_info(struct sock *sk, unsigned char *data, u16 len)
 	hci_dev_unlock_bh(hdev);
 	hci_dev_put(hdev);
 
-	return cmd_complete(sk, MGMT_OP_READ_INFO, &rp, sizeof(rp));
+	return cmd_complete(sk, index, MGMT_OP_READ_INFO, &rp, sizeof(rp));
 }
 
 static void mgmt_pending_free(struct pending_cmd *cmd)
@@ -296,37 +291,35 @@ static void mgmt_pending_remove(struct pending_cmd *cmd)
 	mgmt_pending_free(cmd);
 }
 
-static int set_powered(struct sock *sk, unsigned char *data, u16 len)
+static int set_powered(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct mgmt_mode *cp;
 	struct hci_dev *hdev;
 	struct pending_cmd *cmd;
-	u16 dev_id;
 	int err, up;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_POWERED, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_POWERED, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	up = test_bit(HCI_UP, &hdev->flags);
 	if ((cp->val && up) || (!cp->val && !up)) {
-		err = cmd_status(sk, MGMT_OP_SET_POWERED, EALREADY);
+		err = cmd_status(sk, index, MGMT_OP_SET_POWERED, EALREADY);
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_POWERED, dev_id)) {
-		err = cmd_status(sk, MGMT_OP_SET_POWERED, EBUSY);
+	if (mgmt_pending_find(MGMT_OP_SET_POWERED, index)) {
+		err = cmd_status(sk, index, MGMT_OP_SET_POWERED, EBUSY);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_SET_POWERED, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_POWERED, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
@@ -345,44 +338,43 @@ failed:
 	return err;
 }
 
-static int set_discoverable(struct sock *sk, unsigned char *data, u16 len)
+static int set_discoverable(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct mgmt_mode *cp;
 	struct hci_dev *hdev;
 	struct pending_cmd *cmd;
-	u16 dev_id;
 	u8 scan;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_DISCOVERABLE, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, ENETDOWN);
+		err = cmd_status(sk, index, MGMT_OP_SET_DISCOVERABLE, ENETDOWN);
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, dev_id) ||
-			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, dev_id)) {
-		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, EBUSY);
+	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, index) ||
+			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, index)) {
+		err = cmd_status(sk, index, MGMT_OP_SET_DISCOVERABLE, EBUSY);
 		goto failed;
 	}
 
 	if (cp->val == test_bit(HCI_ISCAN, &hdev->flags) &&
 					test_bit(HCI_PSCAN, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_SET_DISCOVERABLE, EALREADY);
+		err = cmd_status(sk, index, MGMT_OP_SET_DISCOVERABLE, EALREADY);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_SET_DISCOVERABLE, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_DISCOVERABLE, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
@@ -404,43 +396,42 @@ failed:
 	return err;
 }
 
-static int set_connectable(struct sock *sk, unsigned char *data, u16 len)
+static int set_connectable(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct mgmt_mode *cp;
 	struct hci_dev *hdev;
 	struct pending_cmd *cmd;
-	u16 dev_id;
 	u8 scan;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_CONNECTABLE, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_CONNECTABLE, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, ENETDOWN);
+		err = cmd_status(sk, index, MGMT_OP_SET_CONNECTABLE, ENETDOWN);
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, dev_id) ||
-			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, dev_id)) {
-		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, EBUSY);
+	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, index) ||
+			mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, index)) {
+		err = cmd_status(sk, index, MGMT_OP_SET_CONNECTABLE, EBUSY);
 		goto failed;
 	}
 
 	if (cp->val == test_bit(HCI_PSCAN, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_SET_CONNECTABLE, EALREADY);
+		err = cmd_status(sk, index, MGMT_OP_SET_CONNECTABLE, EALREADY);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_SET_CONNECTABLE, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_CONNECTABLE, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
@@ -462,7 +453,8 @@ failed:
 	return err;
 }
 
-static int mgmt_event(u16 event, void *data, u16 data_len, struct sock *skip_sk)
+static int mgmt_event(u16 event, u16 index, void *data, u16 data_len,
+							struct sock *skip_sk)
 {
 	struct sk_buff *skb;
 	struct mgmt_hdr *hdr;
@@ -475,9 +467,11 @@ static int mgmt_event(u16 event, void *data, u16 data_len, struct sock *skip_sk)
 
 	hdr = (void *) skb_put(skb, sizeof(*hdr));
 	hdr->opcode = cpu_to_le16(event);
+	hdr->index = cpu_to_le16(index);
 	hdr->len = cpu_to_le16(data_len);
 
-	memcpy(skb_put(skb, data_len), data, data_len);
+	if (data)
+		memcpy(skb_put(skb, data_len), data, data_len);
 
 	hci_send_to_sock(NULL, skb, skip_sk);
 	kfree_skb(skb);
@@ -489,27 +483,25 @@ static int send_mode_rsp(struct sock *sk, u16 opcode, u16 index, u8 val)
 {
 	struct mgmt_mode rp;
 
-	put_unaligned_le16(index, &rp.index);
 	rp.val = val;
 
-	return cmd_complete(sk, opcode, &rp, sizeof(rp));
+	return cmd_complete(sk, index, opcode, &rp, sizeof(rp));
 }
 
-static int set_pairable(struct sock *sk, unsigned char *data, u16 len)
+static int set_pairable(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct mgmt_mode *cp, ev;
 	struct hci_dev *hdev;
-	u16 dev_id;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_PAIRABLE, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_PAIRABLE, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -518,14 +510,13 @@ static int set_pairable(struct sock *sk, unsigned char *data, u16 len)
 	else
 		clear_bit(HCI_PAIRABLE, &hdev->flags);
 
-	err = send_mode_rsp(sk, MGMT_OP_SET_PAIRABLE, dev_id, cp->val);
+	err = send_mode_rsp(sk, MGMT_OP_SET_PAIRABLE, index, cp->val);
 	if (err < 0)
 		goto failed;
 
-	put_unaligned_le16(dev_id, &ev.index);
 	ev.val = cp->val;
 
-	err = mgmt_event(MGMT_EV_PAIRABLE, &ev, sizeof(ev), sk);
+	err = mgmt_event(MGMT_EV_PAIRABLE, index, &ev, sizeof(ev), sk);
 
 failed:
 	hci_dev_unlock_bh(hdev);
@@ -567,22 +558,20 @@ static int update_class(struct hci_dev *hdev)
 	return hci_send_cmd(hdev, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod);
 }
 
-static int add_uuid(struct sock *sk, unsigned char *data, u16 len)
+static int add_uuid(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct mgmt_cp_add_uuid *cp;
 	struct hci_dev *hdev;
 	struct bt_uuid *uuid;
-	u16 dev_id;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_ADD_UUID, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_ADD_UUID, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -601,7 +590,7 @@ static int add_uuid(struct sock *sk, unsigned char *data, u16 len)
 	if (err < 0)
 		goto failed;
 
-	err = cmd_complete(sk, MGMT_OP_ADD_UUID, &dev_id, sizeof(dev_id));
+	err = cmd_complete(sk, index, MGMT_OP_ADD_UUID, NULL, 0);
 
 failed:
 	hci_dev_unlock_bh(hdev);
@@ -610,23 +599,21 @@ failed:
 	return err;
 }
 
-static int remove_uuid(struct sock *sk, unsigned char *data, u16 len)
+static int remove_uuid(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct list_head *p, *n;
 	struct mgmt_cp_remove_uuid *cp;
 	struct hci_dev *hdev;
 	u8 bt_uuid_any[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
-	u16 dev_id;
 	int err, found;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_REMOVE_UUID, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_REMOVE_UUID, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -648,7 +635,7 @@ static int remove_uuid(struct sock *sk, unsigned char *data, u16 len)
 	}
 
 	if (found == 0) {
-		err = cmd_status(sk, MGMT_OP_REMOVE_UUID, ENOENT);
+		err = cmd_status(sk, index, MGMT_OP_REMOVE_UUID, ENOENT);
 		goto unlock;
 	}
 
@@ -656,7 +643,7 @@ static int remove_uuid(struct sock *sk, unsigned char *data, u16 len)
 	if (err < 0)
 		goto unlock;
 
-	err = cmd_complete(sk, MGMT_OP_REMOVE_UUID, &dev_id, sizeof(dev_id));
+	err = cmd_complete(sk, index, MGMT_OP_REMOVE_UUID, NULL, 0);
 
 unlock:
 	hci_dev_unlock_bh(hdev);
@@ -665,21 +652,20 @@ unlock:
 	return err;
 }
 
-static int set_dev_class(struct sock *sk, unsigned char *data, u16 len)
+static int set_dev_class(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_set_dev_class *cp;
-	u16 dev_id;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	BT_DBG("request for hci%u", dev_id);
+	BT_DBG("request for hci%u", index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_DEV_CLASS, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_DEV_CLASS, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -689,8 +675,7 @@ static int set_dev_class(struct sock *sk, unsigned char *data, u16 len)
 	err = update_class(hdev);
 
 	if (err == 0)
-		err = cmd_complete(sk, MGMT_OP_SET_DEV_CLASS, &dev_id,
-							sizeof(dev_id));
+		err = cmd_complete(sk, index, MGMT_OP_SET_DEV_CLASS, NULL, 0);
 
 	hci_dev_unlock_bh(hdev);
 	hci_dev_put(hdev);
@@ -698,23 +683,22 @@ static int set_dev_class(struct sock *sk, unsigned char *data, u16 len)
 	return err;
 }
 
-static int set_service_cache(struct sock *sk, unsigned char *data, u16 len)
+static int set_service_cache(struct sock *sk, u16 index,  unsigned char *data,
+									u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_set_service_cache *cp;
-	u16 dev_id;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_SERVICE_CACHE, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_SERVICE_CACHE, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
-	BT_DBG("hci%u enable %d", dev_id, cp->enable);
+	BT_DBG("hci%u enable %d", index, cp->enable);
 
 	if (cp->enable) {
 		set_bit(HCI_SERVICE_CACHE, &hdev->flags);
@@ -725,8 +709,8 @@ static int set_service_cache(struct sock *sk, unsigned char *data, u16 len)
 	}
 
 	if (err == 0)
-		err = cmd_complete(sk, MGMT_OP_SET_SERVICE_CACHE, &dev_id,
-							sizeof(dev_id));
+		err = cmd_complete(sk, index, MGMT_OP_SET_SERVICE_CACHE, NULL,
+									0);
 
 	hci_dev_unlock_bh(hdev);
 	hci_dev_put(hdev);
@@ -734,15 +718,14 @@ static int set_service_cache(struct sock *sk, unsigned char *data, u16 len)
 	return err;
 }
 
-static int load_keys(struct sock *sk, unsigned char *data, u16 len)
+static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_load_keys *cp;
-	u16 dev_id, key_count, expected_len;
+	u16 key_count, expected_len;
 	int i;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 	key_count = get_unaligned_le16(&cp->key_count);
 
 	expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_key_info);
@@ -752,11 +735,11 @@ static int load_keys(struct sock *sk, unsigned char *data, u16 len)
 		return -EINVAL;
 	}
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_LOAD_KEYS, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_LOAD_KEYS, ENODEV);
 
-	BT_DBG("hci%u debug_keys %u key_count %u", dev_id, cp->debug_keys,
+	BT_DBG("hci%u debug_keys %u key_count %u", index, cp->debug_keys,
 								key_count);
 
 	hci_dev_lock_bh(hdev);
@@ -783,26 +766,24 @@ static int load_keys(struct sock *sk, unsigned char *data, u16 len)
 	return 0;
 }
 
-static int remove_key(struct sock *sk, unsigned char *data, u16 len)
+static int remove_key(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_remove_key *cp;
 	struct hci_conn *conn;
-	u16 dev_id;
 	int err;
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_REMOVE_KEY, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_REMOVE_KEY, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	err = hci_remove_link_key(hdev, &cp->bdaddr);
 	if (err < 0) {
-		err = cmd_status(sk, MGMT_OP_REMOVE_KEY, -err);
+		err = cmd_status(sk, index, MGMT_OP_REMOVE_KEY, -err);
 		goto unlock;
 	}
 
@@ -827,44 +808,42 @@ unlock:
 	return err;
 }
 
-static int disconnect(struct sock *sk, unsigned char *data, u16 len)
+static int disconnect(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_disconnect *cp;
 	struct hci_cp_disconnect dc;
 	struct pending_cmd *cmd;
 	struct hci_conn *conn;
-	u16 dev_id;
 	int err;
 
 	BT_DBG("");
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_DISCONNECT, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_DISCONNECT, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_DISCONNECT, ENETDOWN);
+		err = cmd_status(sk, index, MGMT_OP_DISCONNECT, ENETDOWN);
 		goto failed;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_DISCONNECT, dev_id)) {
-		err = cmd_status(sk, MGMT_OP_DISCONNECT, EBUSY);
+	if (mgmt_pending_find(MGMT_OP_DISCONNECT, index)) {
+		err = cmd_status(sk, index, MGMT_OP_DISCONNECT, EBUSY);
 		goto failed;
 	}
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr);
 	if (!conn) {
-		err = cmd_status(sk, MGMT_OP_DISCONNECT, ENOTCONN);
+		err = cmd_status(sk, index, MGMT_OP_DISCONNECT, ENOTCONN);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_DISCONNECT, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, MGMT_OP_DISCONNECT, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
@@ -884,24 +863,24 @@ failed:
 	return err;
 }
 
-static int get_connections(struct sock *sk, unsigned char *data, u16 len)
+static int get_connections(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct mgmt_cp_get_connections *cp;
 	struct mgmt_rp_get_connections *rp;
 	struct hci_dev *hdev;
 	struct list_head *p;
 	size_t rp_len;
-	u16 dev_id, count;
+	u16 count;
 	int i, err;
 
 	BT_DBG("");
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_GET_CONNECTIONS, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_GET_CONNECTIONS, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -917,7 +896,6 @@ static int get_connections(struct sock *sk, unsigned char *data, u16 len)
 		goto unlock;
 	}
 
-	put_unaligned_le16(dev_id, &rp->index);
 	put_unaligned_le16(count, &rp->conn_count);
 
 	read_lock(&hci_dev_list_lock);
@@ -931,7 +909,7 @@ static int get_connections(struct sock *sk, unsigned char *data, u16 len)
 
 	read_unlock(&hci_dev_list_lock);
 
-	err = cmd_complete(sk, MGMT_OP_GET_CONNECTIONS, rp, rp_len);
+	err = cmd_complete(sk, index, MGMT_OP_GET_CONNECTIONS, rp, rp_len);
 
 unlock:
 	kfree(rp);
@@ -940,32 +918,31 @@ unlock:
 	return err;
 }
 
-static int pin_code_reply(struct sock *sk, unsigned char *data, u16 len)
+static int pin_code_reply(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_pin_code_reply *cp;
 	struct hci_cp_pin_code_reply reply;
 	struct pending_cmd *cmd;
-	u16 dev_id;
 	int err;
 
 	BT_DBG("");
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_PIN_CODE_REPLY, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_PIN_CODE_REPLY, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_PIN_CODE_REPLY, ENETDOWN);
+		err = cmd_status(sk, index, MGMT_OP_PIN_CODE_REPLY, ENETDOWN);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_REPLY, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_REPLY, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
@@ -986,31 +963,32 @@ failed:
 	return err;
 }
 
-static int pin_code_neg_reply(struct sock *sk, unsigned char *data, u16 len)
+static int pin_code_neg_reply(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_pin_code_neg_reply *cp;
 	struct pending_cmd *cmd;
-	u16 dev_id;
 	int err;
 
 	BT_DBG("");
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_PIN_CODE_NEG_REPLY, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_PIN_CODE_NEG_REPLY,
+									ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_status(sk, MGMT_OP_PIN_CODE_NEG_REPLY, ENETDOWN);
+		err = cmd_status(sk, index, MGMT_OP_PIN_CODE_NEG_REPLY,
+								ENETDOWN);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, dev_id,
+	cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, index,
 								data, len);
 	if (!cmd) {
 		err = -ENOMEM;
@@ -1029,20 +1007,19 @@ failed:
 	return err;
 }
 
-static int set_io_capability(struct sock *sk, unsigned char *data, u16 len)
+static int set_io_capability(struct sock *sk, u16 index, unsigned char *data,
+									u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_set_io_capability *cp;
-	u16 dev_id;
 
 	BT_DBG("");
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_SET_IO_CAPABILITY, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_SET_IO_CAPABILITY, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -1054,8 +1031,7 @@ static int set_io_capability(struct sock *sk, unsigned char *data, u16 len)
 	hci_dev_unlock_bh(hdev);
 	hci_dev_put(hdev);
 
-	return cmd_complete(sk, MGMT_OP_SET_IO_CAPABILITY,
-						&dev_id, sizeof(dev_id));
+	return cmd_complete(sk, index, MGMT_OP_SET_IO_CAPABILITY, NULL, 0);
 }
 
 static inline struct pending_cmd *find_pairing(struct hci_conn *conn)
@@ -1088,11 +1064,10 @@ static void pairing_complete(struct pending_cmd *cmd, u8 status)
 	struct mgmt_rp_pair_device rp;
 	struct hci_conn *conn = cmd->user_data;
 
-	rp.index = cmd->index;
 	bacpy(&rp.bdaddr, &conn->dst);
 	rp.status = status;
 
-	cmd_complete(cmd->sk, MGMT_OP_PAIR_DEVICE, &rp, sizeof(rp));
+	cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE, &rp, sizeof(rp));
 
 	/* So we don't get further callbacks for this connection */
 	conn->connect_cfm_cb = NULL;
@@ -1119,24 +1094,22 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status)
 	pairing_complete(cmd, status);
 }
 
-static int pair_device(struct sock *sk, unsigned char *data, u16 len)
+static int pair_device(struct sock *sk, u16 index, unsigned char *data, u16 len)
 {
 	struct hci_dev *hdev;
 	struct mgmt_cp_pair_device *cp;
 	struct pending_cmd *cmd;
 	u8 sec_level, auth_type;
 	struct hci_conn *conn;
-	u16 dev_id;
 	int err;
 
 	BT_DBG("");
 
 	cp = (void *) data;
-	dev_id = get_unaligned_le16(&cp->index);
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, MGMT_OP_PAIR_DEVICE, ENODEV);
+		return cmd_status(sk, index, MGMT_OP_PAIR_DEVICE, ENODEV);
 
 	hci_dev_lock_bh(hdev);
 
@@ -1156,11 +1129,11 @@ static int pair_device(struct sock *sk, unsigned char *data, u16 len)
 
 	if (conn->connect_cfm_cb) {
 		hci_conn_put(conn);
-		err = cmd_status(sk, MGMT_OP_PAIR_DEVICE, EBUSY);
+		err = cmd_status(sk, index, MGMT_OP_PAIR_DEVICE, EBUSY);
 		goto unlock;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_PAIR_DEVICE, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, MGMT_OP_PAIR_DEVICE, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		hci_conn_put(conn);
@@ -1186,19 +1159,17 @@ unlock:
 	return err;
 }
 
-static int user_confirm_reply(struct sock *sk, unsigned char *data, u16 len,
-								int success)
+static int user_confirm_reply(struct sock *sk, u16 index, unsigned char *data,
+							u16 len, int success)
 {
 	struct mgmt_cp_user_confirm_reply *cp = (void *) data;
-	u16 dev_id, mgmt_op, hci_op;
+	u16 mgmt_op, hci_op;
 	struct pending_cmd *cmd;
 	struct hci_dev *hdev;
 	int err;
 
 	BT_DBG("");
 
-	dev_id = get_unaligned_le16(&cp->index);
-
 	if (success) {
 		mgmt_op = MGMT_OP_USER_CONFIRM_REPLY;
 		hci_op = HCI_OP_USER_CONFIRM_REPLY;
@@ -1207,16 +1178,16 @@ static int user_confirm_reply(struct sock *sk, unsigned char *data, u16 len,
 		hci_op = HCI_OP_USER_CONFIRM_NEG_REPLY;
 	}
 
-	hdev = hci_dev_get(dev_id);
+	hdev = hci_dev_get(index);
 	if (!hdev)
-		return cmd_status(sk, mgmt_op, ENODEV);
+		return cmd_status(sk, index, mgmt_op, ENODEV);
 
 	if (!test_bit(HCI_UP, &hdev->flags)) {
-		err = cmd_status(sk, mgmt_op, ENETDOWN);
+		err = cmd_status(sk, index, mgmt_op, ENETDOWN);
 		goto failed;
 	}
 
-	cmd = mgmt_pending_add(sk, mgmt_op, dev_id, data, len);
+	cmd = mgmt_pending_add(sk, mgmt_op, index, data, len);
 	if (!cmd) {
 		err = -ENOMEM;
 		goto failed;
@@ -1237,7 +1208,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 {
 	unsigned char *buf;
 	struct mgmt_hdr *hdr;
-	u16 opcode, len;
+	u16 opcode, index, len;
 	int err;
 
 	BT_DBG("got %zu bytes", msglen);
@@ -1256,6 +1227,7 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 
 	hdr = (struct mgmt_hdr *) buf;
 	opcode = get_unaligned_le16(&hdr->opcode);
+	index = get_unaligned_le16(&hdr->index);
 	len = get_unaligned_le16(&hdr->len);
 
 	if (len != msglen - sizeof(*hdr)) {
@@ -1271,65 +1243,65 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 		err = read_index_list(sk);
 		break;
 	case MGMT_OP_READ_INFO:
-		err = read_controller_info(sk, buf + sizeof(*hdr), len);
+		err = read_controller_info(sk, index);
 		break;
 	case MGMT_OP_SET_POWERED:
-		err = set_powered(sk, buf + sizeof(*hdr), len);
+		err = set_powered(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_SET_DISCOVERABLE:
-		err = set_discoverable(sk, buf + sizeof(*hdr), len);
+		err = set_discoverable(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_SET_CONNECTABLE:
-		err = set_connectable(sk, buf + sizeof(*hdr), len);
+		err = set_connectable(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_SET_PAIRABLE:
-		err = set_pairable(sk, buf + sizeof(*hdr), len);
+		err = set_pairable(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_ADD_UUID:
-		err = add_uuid(sk, buf + sizeof(*hdr), len);
+		err = add_uuid(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_REMOVE_UUID:
-		err = remove_uuid(sk, buf + sizeof(*hdr), len);
+		err = remove_uuid(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_SET_DEV_CLASS:
-		err = set_dev_class(sk, buf + sizeof(*hdr), len);
+		err = set_dev_class(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_SET_SERVICE_CACHE:
-		err = set_service_cache(sk, buf + sizeof(*hdr), len);
+		err = set_service_cache(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_LOAD_KEYS:
-		err = load_keys(sk, buf + sizeof(*hdr), len);
+		err = load_keys(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_REMOVE_KEY:
-		err = remove_key(sk, buf + sizeof(*hdr), len);
+		err = remove_key(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_DISCONNECT:
-		err = disconnect(sk, buf + sizeof(*hdr), len);
+		err = disconnect(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_GET_CONNECTIONS:
-		err = get_connections(sk, buf + sizeof(*hdr), len);
+		err = get_connections(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_PIN_CODE_REPLY:
-		err = pin_code_reply(sk, buf + sizeof(*hdr), len);
+		err = pin_code_reply(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_PIN_CODE_NEG_REPLY:
-		err = pin_code_neg_reply(sk, buf + sizeof(*hdr), len);
+		err = pin_code_neg_reply(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_SET_IO_CAPABILITY:
-		err = set_io_capability(sk, buf + sizeof(*hdr), len);
+		err = set_io_capability(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_PAIR_DEVICE:
-		err = pair_device(sk, buf + sizeof(*hdr), len);
+		err = pair_device(sk, index, buf + sizeof(*hdr), len);
 		break;
 	case MGMT_OP_USER_CONFIRM_REPLY:
-		err = user_confirm_reply(sk, buf + sizeof(*hdr), len, 1);
+		err = user_confirm_reply(sk, index, buf + sizeof(*hdr), len, 1);
 		break;
 	case MGMT_OP_USER_CONFIRM_NEG_REPLY:
-		err = user_confirm_reply(sk, buf + sizeof(*hdr), len, 0);
+		err = user_confirm_reply(sk, index, buf + sizeof(*hdr), len, 0);
 		break;
 	default:
 		BT_DBG("Unknown op %u", opcode);
-		err = cmd_status(sk, opcode, 0x01);
+		err = cmd_status(sk, index, opcode, 0x01);
 		break;
 	}
 
@@ -1345,20 +1317,12 @@ done:
 
 int mgmt_index_added(u16 index)
 {
-	struct mgmt_ev_index_added ev;
-
-	put_unaligned_le16(index, &ev.index);
-
-	return mgmt_event(MGMT_EV_INDEX_ADDED, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_INDEX_ADDED, index, NULL, 0, NULL);
 }
 
 int mgmt_index_removed(u16 index)
 {
-	struct mgmt_ev_index_added ev;
-
-	put_unaligned_le16(index, &ev.index);
-
-	return mgmt_event(MGMT_EV_INDEX_REMOVED, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_INDEX_REMOVED, index, NULL, 0, NULL);
 }
 
 struct cmd_lookup {
@@ -1394,10 +1358,9 @@ int mgmt_powered(u16 index, u8 powered)
 
 	mgmt_pending_foreach(MGMT_OP_SET_POWERED, index, mode_rsp, &match);
 
-	put_unaligned_le16(index, &ev.index);
 	ev.val = powered;
 
-	ret = mgmt_event(MGMT_EV_POWERED, &ev, sizeof(ev), match.sk);
+	ret = mgmt_event(MGMT_EV_POWERED, index, &ev, sizeof(ev), match.sk);
 
 	if (match.sk)
 		sock_put(match.sk);
@@ -1414,10 +1377,10 @@ int mgmt_discoverable(u16 index, u8 discoverable)
 	mgmt_pending_foreach(MGMT_OP_SET_DISCOVERABLE, index,
 							mode_rsp, &match);
 
-	put_unaligned_le16(index, &ev.index);
 	ev.val = discoverable;
 
-	ret = mgmt_event(MGMT_EV_DISCOVERABLE, &ev, sizeof(ev), match.sk);
+	ret = mgmt_event(MGMT_EV_DISCOVERABLE, index, &ev, sizeof(ev),
+								match.sk);
 
 	if (match.sk)
 		sock_put(match.sk);
@@ -1433,10 +1396,9 @@ int mgmt_connectable(u16 index, u8 connectable)
 
 	mgmt_pending_foreach(MGMT_OP_SET_CONNECTABLE, index, mode_rsp, &match);
 
-	put_unaligned_le16(index, &ev.index);
 	ev.val = connectable;
 
-	ret = mgmt_event(MGMT_EV_CONNECTABLE, &ev, sizeof(ev), match.sk);
+	ret = mgmt_event(MGMT_EV_CONNECTABLE, index, &ev, sizeof(ev), match.sk);
 
 	if (match.sk)
 		sock_put(match.sk);
@@ -1450,25 +1412,22 @@ int mgmt_new_key(u16 index, struct link_key *key, u8 old_key_type)
 
 	memset(&ev, 0, sizeof(ev));
 
-	put_unaligned_le16(index, &ev.index);
-
 	bacpy(&ev.key.bdaddr, &key->bdaddr);
 	ev.key.type = key->type;
 	memcpy(ev.key.val, key->val, 16);
 	ev.key.pin_len = key->pin_len;
 	ev.old_key_type = old_key_type;
 
-	return mgmt_event(MGMT_EV_NEW_KEY, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_NEW_KEY, index, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_connected(u16 index, bdaddr_t *bdaddr)
 {
 	struct mgmt_ev_connected ev;
 
-	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 
-	return mgmt_event(MGMT_EV_CONNECTED, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_CONNECTED, index, &ev, sizeof(ev), NULL);
 }
 
 static void disconnect_rsp(struct pending_cmd *cmd, void *data)
@@ -1477,10 +1436,9 @@ static void disconnect_rsp(struct pending_cmd *cmd, void *data)
 	struct sock **sk = data;
 	struct mgmt_rp_disconnect rp;
 
-	put_unaligned_le16(cmd->index, &rp.index);
 	bacpy(&rp.bdaddr, &cp->bdaddr);
 
-	cmd_complete(cmd->sk, MGMT_OP_DISCONNECT, &rp, sizeof(rp));
+	cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT, &rp, sizeof(rp));
 
 	*sk = cmd->sk;
 	sock_hold(*sk);
@@ -1496,10 +1454,9 @@ int mgmt_disconnected(u16 index, bdaddr_t *bdaddr)
 
 	mgmt_pending_foreach(MGMT_OP_DISCONNECT, index, disconnect_rsp, &sk);
 
-	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 
-	err = mgmt_event(MGMT_EV_DISCONNECTED, &ev, sizeof(ev), sk);
+	err = mgmt_event(MGMT_EV_DISCONNECTED, index, &ev, sizeof(ev), sk);
 
 	if (sk)
 		sock_put(sk);
@@ -1516,7 +1473,7 @@ int mgmt_disconnect_failed(u16 index)
 	if (!cmd)
 		return -ENOENT;
 
-	err = cmd_status(cmd->sk, MGMT_OP_DISCONNECT, EIO);
+	err = cmd_status(cmd->sk, index, MGMT_OP_DISCONNECT, EIO);
 
 	mgmt_pending_remove(cmd);
 
@@ -1527,21 +1484,20 @@ int mgmt_connect_failed(u16 index, bdaddr_t *bdaddr, u8 status)
 {
 	struct mgmt_ev_connect_failed ev;
 
-	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 	ev.status = status;
 
-	return mgmt_event(MGMT_EV_CONNECT_FAILED, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_CONNECT_FAILED, index, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_pin_code_request(u16 index, bdaddr_t *bdaddr)
 {
 	struct mgmt_ev_pin_code_request ev;
 
-	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 
-	return mgmt_event(MGMT_EV_PIN_CODE_REQUEST, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_PIN_CODE_REQUEST, index, &ev, sizeof(ev),
+									NULL);
 }
 
 int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
@@ -1554,11 +1510,11 @@ int mgmt_pin_code_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
 	if (!cmd)
 		return -ENOENT;
 
-	put_unaligned_le16(index, &rp.index);
 	bacpy(&rp.bdaddr, bdaddr);
 	rp.status = status;
 
-	err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_REPLY, &rp, sizeof(rp));
+	err = cmd_complete(cmd->sk, index, MGMT_OP_PIN_CODE_REPLY, &rp,
+								sizeof(rp));
 
 	mgmt_pending_remove(cmd);
 
@@ -1575,12 +1531,11 @@ int mgmt_pin_code_neg_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status)
 	if (!cmd)
 		return -ENOENT;
 
-	put_unaligned_le16(index, &rp.index);
 	bacpy(&rp.bdaddr, bdaddr);
 	rp.status = status;
 
-	err = cmd_complete(cmd->sk, MGMT_OP_PIN_CODE_NEG_REPLY,
-							&rp, sizeof(rp));
+	err = cmd_complete(cmd->sk, index, MGMT_OP_PIN_CODE_NEG_REPLY, &rp,
+								sizeof(rp));
 
 	mgmt_pending_remove(cmd);
 
@@ -1593,11 +1548,11 @@ int mgmt_user_confirm_request(u16 index, bdaddr_t *bdaddr, __le32 value)
 
 	BT_DBG("hci%u", index);
 
-	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 	put_unaligned_le32(value, &ev.value);
 
-	return mgmt_event(MGMT_EV_USER_CONFIRM_REQUEST, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_USER_CONFIRM_REQUEST, index, &ev, sizeof(ev),
+									NULL);
 }
 
 static int confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status,
@@ -1611,10 +1566,9 @@ static int confirm_reply_complete(u16 index, bdaddr_t *bdaddr, u8 status,
 	if (!cmd)
 		return -ENOENT;
 
-	put_unaligned_le16(index, &rp.index);
 	bacpy(&rp.bdaddr, bdaddr);
 	rp.status = status;
-	err = cmd_complete(cmd->sk, opcode, &rp, sizeof(rp));
+	err = cmd_complete(cmd->sk, index, opcode, &rp, sizeof(rp));
 
 	mgmt_pending_remove(cmd);
 
@@ -1638,9 +1592,8 @@ int mgmt_auth_failed(u16 index, bdaddr_t *bdaddr, u8 status)
 {
 	struct mgmt_ev_auth_failed ev;
 
-	put_unaligned_le16(index, &ev.index);
 	bacpy(&ev.bdaddr, bdaddr);
 	ev.status = status;
 
-	return mgmt_event(MGMT_EV_AUTH_FAILED, &ev, sizeof(ev), NULL);
+	return mgmt_event(MGMT_EV_AUTH_FAILED, index, &ev, sizeof(ev), NULL);
 }
-- 
cgit v1.2.3


From 080e4130b1fb6a02e75149a1cccc8192e734713d Mon Sep 17 00:00:00 2001
From: Amerigo Wang <amwang@redhat.com>
Date: Thu, 17 Feb 2011 23:43:33 +0000
Subject: netpoll: remove IFF_IN_NETPOLL flag

V4: rebase to net-next-2.6

This patch removes the flag IFF_IN_NETPOLL, we don't need it any more since
we have netpoll_tx_running() now.

Signed-off-by: WANG Cong <amwang@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 6 ++----
 drivers/net/bonding/bonding.h   | 2 +-
 include/linux/if.h              | 9 ++++-----
 net/core/netpoll.c              | 2 --
 4 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2ed662464cac..c75126ddc646 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -423,11 +423,9 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
 {
 	skb->dev = slave_dev;
 	skb->priority = 1;
-	if (unlikely(netpoll_tx_running(slave_dev))) {
-		slave_dev->priv_flags |= IFF_IN_NETPOLL;
+	if (unlikely(netpoll_tx_running(slave_dev)))
 		bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
-		slave_dev->priv_flags &= ~IFF_IN_NETPOLL;
-	} else
+	else
 		dev_queue_xmit(skb);
 
 	return 0;
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 0a3e00b220b7..a401b8df84f0 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -133,7 +133,7 @@ static inline void unblock_netpoll_tx(void)
 
 static inline int is_netpoll_tx_blocked(struct net_device *dev)
 {
-	if (unlikely(dev->priv_flags & IFF_IN_NETPOLL))
+	if (unlikely(netpoll_tx_running(dev)))
 		return atomic_read(&netpoll_block_tx);
 	return 0;
 }
diff --git a/include/linux/if.h b/include/linux/if.h
index 123959927745..3bc63e6a02f7 100644
--- a/include/linux/if.h
+++ b/include/linux/if.h
@@ -71,11 +71,10 @@
 					 * release skb->dst
 					 */
 #define IFF_DONT_BRIDGE 0x800		/* disallow bridging this ether dev */
-#define IFF_IN_NETPOLL	0x1000		/* whether we are processing netpoll */
-#define IFF_DISABLE_NETPOLL	0x2000	/* disable netpoll at run-time */
-#define IFF_MACVLAN_PORT	0x4000	/* device used as macvlan port */
-#define IFF_BRIDGE_PORT	0x8000		/* device used as bridge port */
-#define IFF_OVS_DATAPATH	0x10000	/* device used as Open vSwitch
+#define IFF_DISABLE_NETPOLL	0x1000	/* disable netpoll at run-time */
+#define IFF_MACVLAN_PORT	0x2000	/* device used as macvlan port */
+#define IFF_BRIDGE_PORT	0x4000		/* device used as bridge port */
+#define IFF_OVS_DATAPATH	0x8000	/* device used as Open vSwitch
 					 * datapath port */
 
 #define IF_GET_IFACE	0x0001		/* for querying only */
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 02dc2cbcbe86..f68e6949294e 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -313,9 +313,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 		     tries > 0; --tries) {
 			if (__netif_tx_trylock(txq)) {
 				if (!netif_tx_queue_stopped(txq)) {
-					dev->priv_flags |= IFF_IN_NETPOLL;
 					status = ops->ndo_start_xmit(skb, dev);
-					dev->priv_flags &= ~IFF_IN_NETPOLL;
 					if (status == NETDEV_TX_OK)
 						txq_trans_update(txq);
 				}
-- 
cgit v1.2.3


From 1922756124ddd53846877416d92ba4a802bc658f Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 24 Feb 2011 08:35:06 +1000
Subject: drm: fix unsigned vs signed comparison issue in modeset ctl ioctl.

This fixes CVE-2011-1013.

Reported-by: Matthiew Herrb (OpenBSD X.org team)
Cc: stable@kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_irq.c | 3 ++-
 include/drm/drmP.h        | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 53120a72a48c..28d1d3c24d65 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -1012,7 +1012,8 @@ int drm_modeset_ctl(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv)
 {
 	struct drm_modeset_ctl *modeset = data;
-	int crtc, ret = 0;
+	int ret = 0;
+	unsigned int crtc;
 
 	/* If drm_vblank_init() hasn't been called yet, just no-op */
 	if (!dev->num_crtcs)
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index fe29aadb129d..348843b80150 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1101,7 +1101,7 @@ struct drm_device {
 	struct platform_device *platformdev; /**< Platform device struture */
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
-	int num_crtcs;                  /**< Number of CRTCs on this device */
+	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
 	void *dev_private;		/**< device private data */
 	void *mm_private;
 	struct address_space *dev_mapping;
-- 
cgit v1.2.3


From 6f2f19ed955e62a6789495da512d510f26ad4885 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 27 Feb 2011 23:04:45 -0800
Subject: xfrm: Pass name as const to xfrm_*_get_byname().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h   | 8 ++++----
 net/xfrm/xfrm_algo.c | 8 ++++----
 net/xfrm/xfrm_user.c | 2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 44dccfcf9204..86ecfc1004b4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1513,10 +1513,10 @@ extern struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx);
 extern struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id);
 extern struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id);
 extern struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id);
-extern struct xfrm_algo_desc *xfrm_aalg_get_byname(char *name, int probe);
-extern struct xfrm_algo_desc *xfrm_ealg_get_byname(char *name, int probe);
-extern struct xfrm_algo_desc *xfrm_calg_get_byname(char *name, int probe);
-extern struct xfrm_algo_desc *xfrm_aead_get_byname(char *name, int icv_len,
+extern struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe);
+extern struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe);
+extern struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe);
+extern struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len,
 						   int probe);
 
 struct hash_desc;
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 8b4d6e3246e5..58064d9e565d 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -618,21 +618,21 @@ static int xfrm_alg_name_match(const struct xfrm_algo_desc *entry,
 			(entry->compat && !strcmp(name, entry->compat)));
 }
 
-struct xfrm_algo_desc *xfrm_aalg_get_byname(char *name, int probe)
+struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe)
 {
 	return xfrm_find_algo(&xfrm_aalg_list, xfrm_alg_name_match, name,
 			      probe);
 }
 EXPORT_SYMBOL_GPL(xfrm_aalg_get_byname);
 
-struct xfrm_algo_desc *xfrm_ealg_get_byname(char *name, int probe)
+struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe)
 {
 	return xfrm_find_algo(&xfrm_ealg_list, xfrm_alg_name_match, name,
 			      probe);
 }
 EXPORT_SYMBOL_GPL(xfrm_ealg_get_byname);
 
-struct xfrm_algo_desc *xfrm_calg_get_byname(char *name, int probe)
+struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe)
 {
 	return xfrm_find_algo(&xfrm_calg_list, xfrm_alg_name_match, name,
 			      probe);
@@ -654,7 +654,7 @@ static int xfrm_aead_name_match(const struct xfrm_algo_desc *entry,
 	       !strcmp(name, entry->name);
 }
 
-struct xfrm_algo_desc *xfrm_aead_get_byname(char *name, int icv_len, int probe)
+struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe)
 {
 	struct xfrm_aead_name data = {
 		.name = name,
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b43c1b1240d4..673698d380d7 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -234,7 +234,7 @@ out:
 }
 
 static int attach_one_algo(struct xfrm_algo **algpp, u8 *props,
-			   struct xfrm_algo_desc *(*get_byname)(char *, int),
+			   struct xfrm_algo_desc *(*get_byname)(const char *, int),
 			   struct nlattr *rta)
 {
 	struct xfrm_algo *p, *ualg;
-- 
cgit v1.2.3


From 851586218f5d463bbd62af40dfa264c5e3539572 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 27 Feb 2011 23:07:02 -0800
Subject: xfrm: Pass const arg to xfrm_alg_len and xfrm_alg_auth_len.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 86ecfc1004b4..15e310fae282 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1558,12 +1558,12 @@ static inline int xfrm_aevent_is_on(struct net *net)
 }
 #endif
 
-static inline int xfrm_alg_len(struct xfrm_algo *alg)
+static inline int xfrm_alg_len(const struct xfrm_algo *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
 }
 
-static inline int xfrm_alg_auth_len(struct xfrm_algo_auth *alg)
+static inline int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg)
 {
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
 }
-- 
cgit v1.2.3


From a70486f0e669730bad6713063e3f59e2e870044f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 27 Feb 2011 23:17:24 -0800
Subject: xfrm: Pass const xfrm_address_t objects to xfrm_state_lookup* and
 xfrm_find_acq.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h    | 10 +++++-----
 net/xfrm/xfrm_state.c | 12 ++++++++----
 2 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 15e310fae282..437c289649ca 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1350,11 +1350,11 @@ extern void xfrm_state_insert(struct xfrm_state *x);
 extern int xfrm_state_add(struct xfrm_state *x);
 extern int xfrm_state_update(struct xfrm_state *x);
 extern struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark,
-					    xfrm_address_t *daddr, __be32 spi,
+					    const xfrm_address_t *daddr, __be32 spi,
 					    u8 proto, unsigned short family);
 extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
-						   xfrm_address_t *daddr,
-						   xfrm_address_t *saddr,
+						   const xfrm_address_t *daddr,
+						   const xfrm_address_t *saddr,
 						   u8 proto,
 						   unsigned short family);
 #ifdef CONFIG_XFRM_SUB_POLICY
@@ -1481,8 +1481,8 @@ u32 xfrm_get_acqseq(void);
 extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
 struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark,
 				 u8 mode, u32 reqid, u8 proto,
-				 xfrm_address_t *daddr,
-				 xfrm_address_t *saddr, int create,
+				 const xfrm_address_t *daddr,
+				 const xfrm_address_t *saddr, int create,
 				 unsigned short family);
 extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8496b3d3e85b..81221d9cbf06 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -997,7 +997,11 @@ void xfrm_state_insert(struct xfrm_state *x)
 EXPORT_SYMBOL(xfrm_state_insert);
 
 /* xfrm_state_lock is held */
-static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, unsigned short family, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create)
+static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m,
+					  unsigned short family, u8 mode,
+					  u32 reqid, u8 proto,
+					  const xfrm_address_t *daddr,
+					  const xfrm_address_t *saddr, int create)
 {
 	unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
 	struct hlist_node *entry;
@@ -1375,7 +1379,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 EXPORT_SYMBOL(xfrm_state_check_expire);
 
 struct xfrm_state *
-xfrm_state_lookup(struct net *net, u32 mark, xfrm_address_t *daddr, __be32 spi,
+xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
 		  u8 proto, unsigned short family)
 {
 	struct xfrm_state *x;
@@ -1389,7 +1393,7 @@ EXPORT_SYMBOL(xfrm_state_lookup);
 
 struct xfrm_state *
 xfrm_state_lookup_byaddr(struct net *net, u32 mark,
-			 xfrm_address_t *daddr, xfrm_address_t *saddr,
+			 const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 			 u8 proto, unsigned short family)
 {
 	struct xfrm_state *x;
@@ -1403,7 +1407,7 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
 
 struct xfrm_state *
 xfrm_find_acq(struct net *net, struct xfrm_mark *mark, u8 mode, u32 reqid, u8 proto,
-	      xfrm_address_t *daddr, xfrm_address_t *saddr,
+	      const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	      int create, unsigned short family)
 {
 	struct xfrm_state *x;
-- 
cgit v1.2.3


From e3dfa389fd2c79526b4bbf295726b66d21001664 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 27 Feb 2011 23:20:19 -0800
Subject: xfrm: Pass const xfrm_mark to xfrm_mark_put().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 437c289649ca..efded23dc4ae 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1611,7 +1611,7 @@ static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m)
 	return m->v & m->m;
 }
 
-static inline int xfrm_mark_put(struct sk_buff *skb, struct xfrm_mark *m)
+static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m)
 {
 	if (m->m | m->v)
 		NLA_PUT(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m);
-- 
cgit v1.2.3


From 3d6b88282751a3329d7b041a8d18db87641db9e8 Mon Sep 17 00:00:00 2001
From: Lennert Buytenhek <buytenh@wantstofly.org>
Date: Tue, 22 Feb 2011 18:18:51 +0100
Subject: dt: Typo fix.

Signed-off-by: Lennert Buytenhek <buytenh@secretlab.ca>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 include/linux/of.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index d9dd664a6a9c..c004753d4c1b 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -103,7 +103,7 @@ extern void of_node_put(struct device_node *node);
 #endif
 
 /*
- * OF address retreival & translation
+ * OF address retrieval & translation
  */
 
 /* Helper to read a big number; size is in cells (not bytes) */
-- 
cgit v1.2.3


From b826291c14c396e7aa5d84523aafac117f430902 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Thu, 17 Feb 2011 02:37:15 -0700
Subject: drivercore/dt: add a match table pointer to struct device

Add a new .of_match field to struct device which points at the
matching device driver .of_match_table entry when a device is probed
via the device tree

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/device.h    | 1 +
 include/linux/of_device.h | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index ca5d25225aab..8d8e2675d07f 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -441,6 +441,7 @@ struct device {
 	struct dev_archdata	archdata;
 
 	struct device_node	*of_node; /* associated device tree node */
+	const struct of_device_id *of_match; /* matching of_device_id from driver */
 
 	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 975d347079d9..8bfe6c1d4365 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -18,10 +18,11 @@ extern void of_device_make_bus_id(struct device *dev);
  * @drv: the device_driver structure to test
  * @dev: the device structure to match against
  */
-static inline int of_driver_match_device(const struct device *dev,
+static inline int of_driver_match_device(struct device *dev,
 					 const struct device_driver *drv)
 {
-	return of_match_device(drv->of_match_table, dev) != NULL;
+	dev->of_match = of_match_device(drv->of_match_table, dev);
+	return dev->of_match != NULL;
 }
 
 extern struct platform_device *of_dev_get(struct platform_device *dev);
-- 
cgit v1.2.3


From 710ac54be44e0cc53f5bf29b03d12c8706e7077a Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Thu, 17 Feb 2011 00:26:57 -0700
Subject: dt/powerpc: move of_bus_type infrastructure to ibmebus

arch/powerpc/kernel/ibmebus.c is the only remaining user of the
of_bus_type support code for initializing the bus and registering
drivers.  All others have either been switched to the vanilla platform
bus or already have their own infrastructure.

This patch moves the functionality that ibmebus is using out of
drivers/of/{platform,device}.c and into ibmebus.c where it is actually
used.  Also renames the moved symbols from of_platform_* to
ibmebus_bus_* to reflect the actual usage.

This patch is part of moving all of the of_platform_bus_type users
over to the platform_bus_type.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/powerpc/kernel/ibmebus.c | 404 +++++++++++++++++++++++++++++++++++++++++-
 drivers/of/device.c           |  34 ----
 drivers/of/platform.c         | 393 ----------------------------------------
 include/linux/of_platform.h   |   6 -
 4 files changed, 400 insertions(+), 437 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index f62efdfd1769..c00d4ca1ee15 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -201,13 +201,14 @@ int ibmebus_register_driver(struct of_platform_driver *drv)
 	/* If the driver uses devices that ibmebus doesn't know, add them */
 	ibmebus_create_devices(drv->driver.of_match_table);
 
-	return of_register_driver(drv, &ibmebus_bus_type);
+	drv->driver.bus = &ibmebus_bus_type;
+	return driver_register(&drv->driver);
 }
 EXPORT_SYMBOL(ibmebus_register_driver);
 
 void ibmebus_unregister_driver(struct of_platform_driver *drv)
 {
-	of_unregister_driver(drv);
+	driver_unregister(&drv->driver);
 }
 EXPORT_SYMBOL(ibmebus_unregister_driver);
 
@@ -308,15 +309,410 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
 	}
 }
 
+
 static struct bus_attribute ibmebus_bus_attrs[] = {
 	__ATTR(probe, S_IWUSR, NULL, ibmebus_store_probe),
 	__ATTR(remove, S_IWUSR, NULL, ibmebus_store_remove),
 	__ATTR_NULL
 };
 
+static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
+{
+	const struct of_device_id *matches = drv->of_match_table;
+
+	if (!matches)
+		return 0;
+
+	return of_match_device(matches, dev) != NULL;
+}
+
+static int ibmebus_bus_device_probe(struct device *dev)
+{
+	int error = -ENODEV;
+	struct of_platform_driver *drv;
+	struct platform_device *of_dev;
+	const struct of_device_id *match;
+
+	drv = to_of_platform_driver(dev->driver);
+	of_dev = to_platform_device(dev);
+
+	if (!drv->probe)
+		return error;
+
+	of_dev_get(of_dev);
+
+	match = of_match_device(drv->driver.of_match_table, dev);
+	if (match)
+		error = drv->probe(of_dev, match);
+	if (error)
+		of_dev_put(of_dev);
+
+	return error;
+}
+
+static int ibmebus_bus_device_remove(struct device *dev)
+{
+	struct platform_device *of_dev = to_platform_device(dev);
+	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+
+	if (dev->driver && drv->remove)
+		drv->remove(of_dev);
+	return 0;
+}
+
+static void ibmebus_bus_device_shutdown(struct device *dev)
+{
+	struct platform_device *of_dev = to_platform_device(dev);
+	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+
+	if (dev->driver && drv->shutdown)
+		drv->shutdown(of_dev);
+}
+
+/*
+ * ibmebus_bus_device_attrs
+ */
+static ssize_t devspec_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct platform_device *ofdev;
+
+	ofdev = to_platform_device(dev);
+	return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name);
+}
+
+static ssize_t name_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct platform_device *ofdev;
+
+	ofdev = to_platform_device(dev);
+	return sprintf(buf, "%s\n", ofdev->dev.of_node->name);
+}
+
+static ssize_t modalias_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	ssize_t len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2);
+	buf[len] = '\n';
+	buf[len+1] = 0;
+	return len+1;
+}
+
+struct device_attribute ibmebus_bus_device_attrs[] = {
+	__ATTR_RO(devspec),
+	__ATTR_RO(name),
+	__ATTR_RO(modalias),
+	__ATTR_NULL
+};
+
+#ifdef CONFIG_PM_SLEEP
+static int ibmebus_bus_legacy_suspend(struct device *dev, pm_message_t mesg)
+{
+	struct platform_device *of_dev = to_platform_device(dev);
+	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+	int ret = 0;
+
+	if (dev->driver && drv->suspend)
+		ret = drv->suspend(of_dev, mesg);
+	return ret;
+}
+
+static int ibmebus_bus_legacy_resume(struct device *dev)
+{
+	struct platform_device *of_dev = to_platform_device(dev);
+	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+	int ret = 0;
+
+	if (dev->driver && drv->resume)
+		ret = drv->resume(of_dev);
+	return ret;
+}
+
+static int ibmebus_bus_pm_prepare(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (drv && drv->pm && drv->pm->prepare)
+		ret = drv->pm->prepare(dev);
+
+	return ret;
+}
+
+static void ibmebus_bus_pm_complete(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv && drv->pm && drv->pm->complete)
+		drv->pm->complete(dev);
+}
+
+#ifdef CONFIG_SUSPEND
+
+static int ibmebus_bus_pm_suspend(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->suspend)
+			ret = drv->pm->suspend(dev);
+	} else {
+		ret = ibmebus_bus_legacy_suspend(dev, PMSG_SUSPEND);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_suspend_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->suspend_noirq)
+			ret = drv->pm->suspend_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_resume(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->resume)
+			ret = drv->pm->resume(dev);
+	} else {
+		ret = ibmebus_bus_legacy_resume(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_resume_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->resume_noirq)
+			ret = drv->pm->resume_noirq(dev);
+	}
+
+	return ret;
+}
+
+#else /* !CONFIG_SUSPEND */
+
+#define ibmebus_bus_pm_suspend		NULL
+#define ibmebus_bus_pm_resume		NULL
+#define ibmebus_bus_pm_suspend_noirq	NULL
+#define ibmebus_bus_pm_resume_noirq	NULL
+
+#endif /* !CONFIG_SUSPEND */
+
+#ifdef CONFIG_HIBERNATION
+
+static int ibmebus_bus_pm_freeze(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->freeze)
+			ret = drv->pm->freeze(dev);
+	} else {
+		ret = ibmebus_bus_legacy_suspend(dev, PMSG_FREEZE);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_freeze_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->freeze_noirq)
+			ret = drv->pm->freeze_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_thaw(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->thaw)
+			ret = drv->pm->thaw(dev);
+	} else {
+		ret = ibmebus_bus_legacy_resume(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_thaw_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->thaw_noirq)
+			ret = drv->pm->thaw_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_poweroff(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->poweroff)
+			ret = drv->pm->poweroff(dev);
+	} else {
+		ret = ibmebus_bus_legacy_suspend(dev, PMSG_HIBERNATE);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_poweroff_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->poweroff_noirq)
+			ret = drv->pm->poweroff_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_restore(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->restore)
+			ret = drv->pm->restore(dev);
+	} else {
+		ret = ibmebus_bus_legacy_resume(dev);
+	}
+
+	return ret;
+}
+
+static int ibmebus_bus_pm_restore_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->restore_noirq)
+			ret = drv->pm->restore_noirq(dev);
+	}
+
+	return ret;
+}
+
+#else /* !CONFIG_HIBERNATION */
+
+#define ibmebus_bus_pm_freeze		NULL
+#define ibmebus_bus_pm_thaw		NULL
+#define ibmebus_bus_pm_poweroff		NULL
+#define ibmebus_bus_pm_restore		NULL
+#define ibmebus_bus_pm_freeze_noirq	NULL
+#define ibmebus_bus_pm_thaw_noirq		NULL
+#define ibmebus_bus_pm_poweroff_noirq	NULL
+#define ibmebus_bus_pm_restore_noirq	NULL
+
+#endif /* !CONFIG_HIBERNATION */
+
+static struct dev_pm_ops ibmebus_bus_dev_pm_ops = {
+	.prepare = ibmebus_bus_pm_prepare,
+	.complete = ibmebus_bus_pm_complete,
+	.suspend = ibmebus_bus_pm_suspend,
+	.resume = ibmebus_bus_pm_resume,
+	.freeze = ibmebus_bus_pm_freeze,
+	.thaw = ibmebus_bus_pm_thaw,
+	.poweroff = ibmebus_bus_pm_poweroff,
+	.restore = ibmebus_bus_pm_restore,
+	.suspend_noirq = ibmebus_bus_pm_suspend_noirq,
+	.resume_noirq = ibmebus_bus_pm_resume_noirq,
+	.freeze_noirq = ibmebus_bus_pm_freeze_noirq,
+	.thaw_noirq = ibmebus_bus_pm_thaw_noirq,
+	.poweroff_noirq = ibmebus_bus_pm_poweroff_noirq,
+	.restore_noirq = ibmebus_bus_pm_restore_noirq,
+};
+
+#define IBMEBUS_BUS_PM_OPS_PTR	(&ibmebus_bus_dev_pm_ops)
+
+#else /* !CONFIG_PM_SLEEP */
+
+#define IBMEBUS_BUS_PM_OPS_PTR	NULL
+
+#endif /* !CONFIG_PM_SLEEP */
+
 struct bus_type ibmebus_bus_type = {
+	.name      = "ibmebus",
 	.uevent    = of_device_uevent,
-	.bus_attrs = ibmebus_bus_attrs
+	.bus_attrs = ibmebus_bus_attrs,
+	.match     = ibmebus_bus_bus_match,
+	.probe     = ibmebus_bus_device_probe,
+	.remove    = ibmebus_bus_device_remove,
+	.shutdown  = ibmebus_bus_device_shutdown,
+	.dev_attrs = ibmebus_bus_device_attrs,
+	.pm        = IBMEBUS_BUS_PM_OPS_PTR,
 };
 EXPORT_SYMBOL(ibmebus_bus_type);
 
@@ -326,7 +722,7 @@ static int __init ibmebus_bus_init(void)
 
 	printk(KERN_INFO "IBM eBus Device Driver\n");
 
-	err = of_bus_type_init(&ibmebus_bus_type, "ibmebus");
+	err = bus_register(&ibmebus_bus_type);
 	if (err) {
 		printk(KERN_ERR "%s: failed to register IBM eBus.\n",
 		       __func__);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 45d86530799f..62b4b32ac887 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -47,40 +47,6 @@ void of_dev_put(struct platform_device *dev)
 }
 EXPORT_SYMBOL(of_dev_put);
 
-static ssize_t devspec_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct platform_device *ofdev;
-
-	ofdev = to_platform_device(dev);
-	return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name);
-}
-
-static ssize_t name_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct platform_device *ofdev;
-
-	ofdev = to_platform_device(dev);
-	return sprintf(buf, "%s\n", ofdev->dev.of_node->name);
-}
-
-static ssize_t modalias_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	ssize_t len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2);
-	buf[len] = '\n';
-	buf[len+1] = 0;
-	return len+1;
-}
-
-struct device_attribute of_platform_device_attrs[] = {
-	__ATTR_RO(devspec),
-	__ATTR_RO(name),
-	__ATTR_RO(modalias),
-	__ATTR_NULL
-};
-
 int of_device_add(struct platform_device *ofdev)
 {
 	BUG_ON(ofdev->dev.of_node == NULL);
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index c01cd1ac7617..b71d0cdc4209 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -114,399 +114,6 @@ EXPORT_SYMBOL(of_unregister_platform_driver);
 #include <asm/dcr.h>
 #endif
 
-extern struct device_attribute of_platform_device_attrs[];
-
-static int of_platform_bus_match(struct device *dev, struct device_driver *drv)
-{
-	const struct of_device_id *matches = drv->of_match_table;
-
-	if (!matches)
-		return 0;
-
-	return of_match_device(matches, dev) != NULL;
-}
-
-static int of_platform_device_probe(struct device *dev)
-{
-	int error = -ENODEV;
-	struct of_platform_driver *drv;
-	struct platform_device *of_dev;
-	const struct of_device_id *match;
-
-	drv = to_of_platform_driver(dev->driver);
-	of_dev = to_platform_device(dev);
-
-	if (!drv->probe)
-		return error;
-
-	of_dev_get(of_dev);
-
-	match = of_match_device(drv->driver.of_match_table, dev);
-	if (match)
-		error = drv->probe(of_dev, match);
-	if (error)
-		of_dev_put(of_dev);
-
-	return error;
-}
-
-static int of_platform_device_remove(struct device *dev)
-{
-	struct platform_device *of_dev = to_platform_device(dev);
-	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
-
-	if (dev->driver && drv->remove)
-		drv->remove(of_dev);
-	return 0;
-}
-
-static void of_platform_device_shutdown(struct device *dev)
-{
-	struct platform_device *of_dev = to_platform_device(dev);
-	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
-
-	if (dev->driver && drv->shutdown)
-		drv->shutdown(of_dev);
-}
-
-#ifdef CONFIG_PM_SLEEP
-
-static int of_platform_legacy_suspend(struct device *dev, pm_message_t mesg)
-{
-	struct platform_device *of_dev = to_platform_device(dev);
-	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
-	int ret = 0;
-
-	if (dev->driver && drv->suspend)
-		ret = drv->suspend(of_dev, mesg);
-	return ret;
-}
-
-static int of_platform_legacy_resume(struct device *dev)
-{
-	struct platform_device *of_dev = to_platform_device(dev);
-	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
-	int ret = 0;
-
-	if (dev->driver && drv->resume)
-		ret = drv->resume(of_dev);
-	return ret;
-}
-
-static int of_platform_pm_prepare(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (drv && drv->pm && drv->pm->prepare)
-		ret = drv->pm->prepare(dev);
-
-	return ret;
-}
-
-static void of_platform_pm_complete(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-
-	if (drv && drv->pm && drv->pm->complete)
-		drv->pm->complete(dev);
-}
-
-#ifdef CONFIG_SUSPEND
-
-static int of_platform_pm_suspend(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->suspend)
-			ret = drv->pm->suspend(dev);
-	} else {
-		ret = of_platform_legacy_suspend(dev, PMSG_SUSPEND);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_suspend_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->suspend_noirq)
-			ret = drv->pm->suspend_noirq(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_resume(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->resume)
-			ret = drv->pm->resume(dev);
-	} else {
-		ret = of_platform_legacy_resume(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_resume_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->resume_noirq)
-			ret = drv->pm->resume_noirq(dev);
-	}
-
-	return ret;
-}
-
-#else /* !CONFIG_SUSPEND */
-
-#define of_platform_pm_suspend		NULL
-#define of_platform_pm_resume		NULL
-#define of_platform_pm_suspend_noirq	NULL
-#define of_platform_pm_resume_noirq	NULL
-
-#endif /* !CONFIG_SUSPEND */
-
-#ifdef CONFIG_HIBERNATION
-
-static int of_platform_pm_freeze(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->freeze)
-			ret = drv->pm->freeze(dev);
-	} else {
-		ret = of_platform_legacy_suspend(dev, PMSG_FREEZE);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_freeze_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->freeze_noirq)
-			ret = drv->pm->freeze_noirq(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_thaw(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->thaw)
-			ret = drv->pm->thaw(dev);
-	} else {
-		ret = of_platform_legacy_resume(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_thaw_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->thaw_noirq)
-			ret = drv->pm->thaw_noirq(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_poweroff(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->poweroff)
-			ret = drv->pm->poweroff(dev);
-	} else {
-		ret = of_platform_legacy_suspend(dev, PMSG_HIBERNATE);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_poweroff_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->poweroff_noirq)
-			ret = drv->pm->poweroff_noirq(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_restore(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->restore)
-			ret = drv->pm->restore(dev);
-	} else {
-		ret = of_platform_legacy_resume(dev);
-	}
-
-	return ret;
-}
-
-static int of_platform_pm_restore_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->restore_noirq)
-			ret = drv->pm->restore_noirq(dev);
-	}
-
-	return ret;
-}
-
-#else /* !CONFIG_HIBERNATION */
-
-#define of_platform_pm_freeze		NULL
-#define of_platform_pm_thaw		NULL
-#define of_platform_pm_poweroff		NULL
-#define of_platform_pm_restore		NULL
-#define of_platform_pm_freeze_noirq	NULL
-#define of_platform_pm_thaw_noirq		NULL
-#define of_platform_pm_poweroff_noirq	NULL
-#define of_platform_pm_restore_noirq	NULL
-
-#endif /* !CONFIG_HIBERNATION */
-
-static struct dev_pm_ops of_platform_dev_pm_ops = {
-	.prepare = of_platform_pm_prepare,
-	.complete = of_platform_pm_complete,
-	.suspend = of_platform_pm_suspend,
-	.resume = of_platform_pm_resume,
-	.freeze = of_platform_pm_freeze,
-	.thaw = of_platform_pm_thaw,
-	.poweroff = of_platform_pm_poweroff,
-	.restore = of_platform_pm_restore,
-	.suspend_noirq = of_platform_pm_suspend_noirq,
-	.resume_noirq = of_platform_pm_resume_noirq,
-	.freeze_noirq = of_platform_pm_freeze_noirq,
-	.thaw_noirq = of_platform_pm_thaw_noirq,
-	.poweroff_noirq = of_platform_pm_poweroff_noirq,
-	.restore_noirq = of_platform_pm_restore_noirq,
-};
-
-#define OF_PLATFORM_PM_OPS_PTR	(&of_platform_dev_pm_ops)
-
-#else /* !CONFIG_PM_SLEEP */
-
-#define OF_PLATFORM_PM_OPS_PTR	NULL
-
-#endif /* !CONFIG_PM_SLEEP */
-
-int of_bus_type_init(struct bus_type *bus, const char *name)
-{
-	bus->name = name;
-	bus->match = of_platform_bus_match;
-	bus->probe = of_platform_device_probe;
-	bus->remove = of_platform_device_remove;
-	bus->shutdown = of_platform_device_shutdown;
-	bus->dev_attrs = of_platform_device_attrs;
-	bus->pm = OF_PLATFORM_PM_OPS_PTR;
-	return bus_register(bus);
-}
-
-int of_register_driver(struct of_platform_driver *drv, struct bus_type *bus)
-{
-	/*
-	 * Temporary: of_platform_bus used to be distinct from the platform
-	 * bus.  It isn't anymore, and so drivers on the platform bus need
-	 * to be registered in a special way.
-	 *
-	 * After all of_platform_bus_type drivers are converted to
-	 * platform_drivers, this exception can be removed.
-	 */
-	if (bus == &platform_bus_type)
-		return of_register_platform_driver(drv);
-
-	/* register with core */
-	drv->driver.bus = bus;
-	return driver_register(&drv->driver);
-}
-EXPORT_SYMBOL(of_register_driver);
-
-void of_unregister_driver(struct of_platform_driver *drv)
-{
-	if (drv->driver.bus == &platform_bus_type)
-		of_unregister_platform_driver(drv);
-	else
-		driver_unregister(&drv->driver);
-}
-EXPORT_SYMBOL(of_unregister_driver);
-
 #if !defined(CONFIG_SPARC)
 /*
  * The following routines scan a subtree and registers a device for
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index a68716ad38ce..048949fa1d10 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -47,10 +47,6 @@ struct of_platform_driver
 #define	to_of_platform_driver(drv) \
 	container_of(drv,struct of_platform_driver, driver)
 
-extern int of_register_driver(struct of_platform_driver *drv,
-			      struct bus_type *bus);
-extern void of_unregister_driver(struct of_platform_driver *drv);
-
 /* Platform drivers register/unregister */
 extern int of_register_platform_driver(struct of_platform_driver *drv);
 extern void of_unregister_platform_driver(struct of_platform_driver *drv);
@@ -60,8 +56,6 @@ extern struct platform_device *of_device_alloc(struct device_node *np,
 					 struct device *parent);
 extern struct platform_device *of_find_device_by_node(struct device_node *np);
 
-extern int of_bus_type_init(struct bus_type *bus, const char *name);
-
 #if !defined(CONFIG_SPARC) /* SPARC has its own device registration method */
 /* Platform devices and busses creation */
 extern struct platform_device *of_platform_device_create(struct device_node *np,
-- 
cgit v1.2.3


From 7c3343392172ba98d9d90a83edcc4c2e80897009 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Mon, 28 Feb 2011 11:02:24 +0100
Subject: percpu: Generic support for this_cpu_cmpxchg_double()

Introduce this_cpu_cmpxchg_double().  this_cpu_cmpxchg_double() allows
the comparison between two consecutive words and replaces them if
there is a match.

	bool this_cpu_cmpxchg_double(pcp1, pcp2,
		old_word1, old_word2, new_word1, new_word2)

this_cpu_cmpxchg_double does not return the old value (difficult since
there are two words) but a boolean indicating if the operation was
successful.

The first percpu variable must be double word aligned!

-tj: Updated to return bool instead of int, converted size check to
     BUILD_BUG_ON() instead of VM_BUG_ON() and other cosmetic changes.

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/percpu.h | 128 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 128 insertions(+)

(limited to 'include')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 27c3c6fcfad3..3a5c4449fd36 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -255,6 +255,30 @@ extern void __bad_size_call_parameter(void);
 	pscr2_ret__;							\
 })
 
+/*
+ * Special handling for cmpxchg_double.  cmpxchg_double is passed two
+ * percpu variables.  The first has to be aligned to a double word
+ * boundary and the second has to follow directly thereafter.
+ */
+#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
+({									\
+	bool pdcrb_ret__;						\
+	__verify_pcpu_ptr(&pcp1);					\
+	BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2));			\
+	VM_BUG_ON((unsigned long)(&pcp1) % (2 * sizeof(pcp1)));		\
+	VM_BUG_ON((unsigned long)(&pcp2) !=				\
+		  (unsigned long)(&pcp1) + sizeof(pcp1));		\
+	switch(sizeof(pcp1)) {						\
+	case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break;	\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pdcrb_ret__;							\
+})
+
 #define __pcpu_size_call(stem, variable, ...)				\
 do {									\
 	__verify_pcpu_ptr(&(variable));					\
@@ -500,6 +524,45 @@ do {									\
 	__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
 #endif
 
+/*
+ * cmpxchg_double replaces two adjacent scalars at once.  The first
+ * two parameters are per cpu variables which have to be of the same
+ * size.  A truth value is returned to indicate success or failure
+ * (since a double register result is difficult to handle).  There is
+ * very limited hardware support for these operations, so only certain
+ * sizes may work.
+ */
+#define _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int ret__;							\
+	preempt_disable();						\
+	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_cmpxchg_double
+# ifndef this_cpu_cmpxchg_double_1
+#  define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef this_cpu_cmpxchg_double_2
+#  define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef this_cpu_cmpxchg_double_4
+#  define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef this_cpu_cmpxchg_double_8
+#  define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
 /*
  * Generic percpu operations that do not require preemption handling.
  * Either we do not care about races or the caller has the
@@ -703,6 +766,39 @@ do {									\
 	__pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval)
 #endif
 
+#define __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int __ret = 0;							\
+	if (__this_cpu_read(pcp1) == (oval1) &&				\
+			 __this_cpu_read(pcp2)  == (oval2)) {		\
+		__this_cpu_write(pcp1, (nval1));			\
+		__this_cpu_write(pcp2, (nval2));			\
+		__ret = 1;						\
+	}								\
+	(__ret);							\
+})
+
+#ifndef __this_cpu_cmpxchg_double
+# ifndef __this_cpu_cmpxchg_double_1
+#  define __this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef __this_cpu_cmpxchg_double_2
+#  define __this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef __this_cpu_cmpxchg_double_4
+#  define __this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef __this_cpu_cmpxchg_double_8
+#  define __this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_bool(__this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
 /*
  * IRQ safe versions of the per cpu RMW operations. Note that these operations
  * are *not* safe against modification of the same variable from another
@@ -823,4 +919,36 @@ do {									\
 	__pcpu_size_call_return2(irqsafe_cpu_cmpxchg_, (pcp), oval, nval)
 #endif
 
+#define irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int ret__;							\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
+	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	local_irq_restore(flags);					\
+	ret__;								\
+})
+
+#ifndef irqsafe_cpu_cmpxchg_double
+# ifndef irqsafe_cpu_cmpxchg_double_1
+#  define irqsafe_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_double_2
+#  define irqsafe_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_double_4
+#  define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_double_8
+#  define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# endif
+# define irqsafe_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_int(irqsafe_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
 #endif /* __LINUX_PERCPU_H */
-- 
cgit v1.2.3


From 2e820f58f7ad8eaca2f194ccdfea0de63e9c6d78 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Mon, 9 Feb 2009 12:05:50 -0800
Subject: xen/irq: implement bind_interdomain_evtchn_to_irqhandler for backend
 drivers

Impact: new Xen-internal API

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/events.c | 38 ++++++++++++++++++++++++++++++++++++++
 include/xen/events.h |  6 ++++++
 2 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 74681478100a..a41601675633 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -864,6 +864,21 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 	return irq;
 }
 
+static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+					  unsigned int remote_port)
+{
+	struct evtchn_bind_interdomain bind_interdomain;
+	int err;
+
+	bind_interdomain.remote_dom  = remote_domain;
+	bind_interdomain.remote_port = remote_port;
+
+	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+					  &bind_interdomain);
+
+	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+}
+
 
 int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 {
@@ -959,6 +974,29 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn,
 }
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
 
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+					  unsigned int remote_port,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname,
+					  void *dev_id)
+{
+	int irq, retval;
+
+	irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+	if (irq < 0)
+		return irq;
+
+	retval = request_irq(irq, handler, irqflags, devname, dev_id);
+	if (retval != 0) {
+		unbind_from_irq(irq);
+		return retval;
+	}
+
+	return irq;
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
+
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
 			    unsigned long irqflags, const char *devname, void *dev_id)
diff --git a/include/xen/events.h b/include/xen/events.h
index 00f53ddcc062..bd03b1e4a2f4 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -23,6 +23,12 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 			   unsigned long irqflags,
 			   const char *devname,
 			   void *dev_id);
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+					  unsigned int remote_port,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname,
+					  void *dev_id);
 
 /*
  * Common unbind function for all event sources. Takes IRQ to unbind from.
-- 
cgit v1.2.3


From 52208ae3fc60cbcb214c10fb8b82304199e2cc3a Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu, 24 Feb 2011 16:58:20 -0800
Subject: [SCSI] target: Fix t_transport_aborted handling in LUN_RESET + active
 I/O shutdown

This patch addresses two outstanding bugs related to
T_TASK(cmd)->t_transport_aborted handling during TMR LUN_RESET and
active I/O shutdown.

This first involves adding two explict t_transport_aborted=1
assignments in core_tmr_lun_reset() in order to signal the task has
been aborted, and updating transport_generic_wait_for_tasks() to skip
sleeping when t_transport_aborted=1 has been set.  This fixes an issue
where transport_generic_wait_for_tasks() would end up sleeping
indefinately when called from fabric module context while TMR
LUN_RESET was happening with long outstanding backend struct se_task
not yet being completed.

The second adds a missing call to
transport_remove_task_from_execute_queue() when
task->task_execute_queue=1 is set in order to fix an OOPs when
task->t_execute_list has not been dropped.  It also fixes the same
case in transport_processing_shutdown() to prevent the issue from
happening during active I/O struct se_device shutdown.

Signed-off-by: Nicholas A. Bellinger <nab@linux-iscsi.org>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
---
 drivers/target/target_core_tmr.c       | 5 +++++
 drivers/target/target_core_transport.c | 8 ++++++--
 include/target/target_core_transport.h | 2 ++
 3 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 158cecbec718..4a109835e420 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -282,6 +282,9 @@ int core_tmr_lun_reset(
 
 			atomic_set(&task->task_active, 0);
 			atomic_set(&task->task_stop, 0);
+		} else {
+			if (atomic_read(&task->task_execute_queue) != 0)
+				transport_remove_task_from_execute_queue(task, dev);
 		}
 		__transport_stop_task_timer(task, &flags);
 
@@ -301,6 +304,7 @@ int core_tmr_lun_reset(
 			DEBUG_LR("LUN_RESET: got t_transport_active = 1 for"
 				" task: %p, t_fe_count: %d dev: %p\n", task,
 				fe_count, dev);
+			atomic_set(&T_TASK(cmd)->t_transport_aborted, 1);
 			spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock,
 						flags);
 			core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
@@ -310,6 +314,7 @@ int core_tmr_lun_reset(
 		}
 		DEBUG_LR("LUN_RESET: Got t_transport_active = 0 for task: %p,"
 			" t_fe_count: %d dev: %p\n", task, fe_count, dev);
+		atomic_set(&T_TASK(cmd)->t_transport_aborted, 1);
 		spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock, flags);
 		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count);
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 236e22d8cfae..4bbf6c147f89 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1207,7 +1207,7 @@ transport_get_task_from_execute_queue(struct se_device *dev)
  *
  *
  */
-static void transport_remove_task_from_execute_queue(
+void transport_remove_task_from_execute_queue(
 	struct se_task *task,
 	struct se_device *dev)
 {
@@ -5549,7 +5549,8 @@ static void transport_generic_wait_for_tasks(
 
 		atomic_set(&T_TASK(cmd)->transport_lun_stop, 0);
 	}
-	if (!atomic_read(&T_TASK(cmd)->t_transport_active))
+	if (!atomic_read(&T_TASK(cmd)->t_transport_active) ||
+	     atomic_read(&T_TASK(cmd)->t_transport_aborted))
 		goto remove;
 
 	atomic_set(&T_TASK(cmd)->t_transport_stop, 1);
@@ -5956,6 +5957,9 @@ static void transport_processing_shutdown(struct se_device *dev)
 
 			atomic_set(&task->task_active, 0);
 			atomic_set(&task->task_stop, 0);
+		} else {
+			if (atomic_read(&task->task_execute_queue) != 0)
+				transport_remove_task_from_execute_queue(task, dev);
 		}
 		__transport_stop_task_timer(task, &flags);
 
diff --git a/include/target/target_core_transport.h b/include/target/target_core_transport.h
index 246940511579..2e8ec51f0615 100644
--- a/include/target/target_core_transport.h
+++ b/include/target/target_core_transport.h
@@ -135,6 +135,8 @@ extern void transport_complete_task(struct se_task *, int);
 extern void transport_add_task_to_execute_queue(struct se_task *,
 						struct se_task *,
 						struct se_device *);
+extern void transport_remove_task_from_execute_queue(struct se_task *,
+						struct se_device *);
 unsigned char *transport_dump_cmd_direction(struct se_cmd *);
 extern void transport_dump_dev_state(struct se_device *, char *, int *);
 extern void transport_dump_dev_info(struct se_device *, struct se_lun *,
-- 
cgit v1.2.3


From fbd71844852c9458bf73c7cbdae7189c2d4b377c Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 27 Feb 2011 05:41:35 +0000
Subject: mm: <asm-generic/pgtable.h> must include <linux/mm_types.h>

Commit e2cda3226481 ("thp: add pmd mangling generic functions") replaced
some macros in <asm-generic/pgtable.h> with inline functions.

If the functions are to be defined (not all architectures need them)
then struct vm_area_struct must be defined first.  So include
<linux/mm_types.h>.

Fixes a build failure seen in Debian:

    CC [M]  drivers/media/dvb/mantis/mantis_pci.o
  In file included from arch/arm/include/asm/pgtable.h:460,
                   from drivers/media/dvb/mantis/mantis_pci.c:25:
  include/asm-generic/pgtable.h: In function 'ptep_test_and_clear_young':
  include/asm-generic/pgtable.h:29: error: dereferencing pointer to incomplete type

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/pgtable.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 31b6188df221..b4bfe338ea0e 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -4,6 +4,8 @@
 #ifndef __ASSEMBLY__
 #ifdef CONFIG_MMU
 
+#include <linux/mm_types.h>
+
 #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
-- 
cgit v1.2.3


From af06216a8ef1c430cc6ad22b562f3a11a512c5dd Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Tue, 1 Mar 2011 01:12:19 +0100
Subject: ACPI: Fix build for CONFIG_NET unset

Several ACPI drivers fail to build if CONFIG_NET is unset, because
they refer to things depending on CONFIG_THERMAL that in turn depends
on CONFIG_NET.  However, CONFIG_THERMAL doesn't really need to depend
on CONFIG_NET, because the only part of it requiring CONFIG_NET is
the netlink interface in thermal_sys.c.

Put the netlink interface in thermal_sys.c under #ifdef CONFIG_NET
and remove the dependency of CONFIG_THERMAL on CONFIG_NET from
drivers/thermal/Kconfig.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Len Brown <lenb@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Luming Yu <luming.yu@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/thermal/Kconfig       |  1 -
 drivers/thermal/thermal_sys.c | 40 +++++++++++++++++++++-------------------
 include/linux/thermal.h       |  8 ++++++++
 3 files changed, 29 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index f7a5dba3ca23..bf7c687519ef 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -4,7 +4,6 @@
 
 menuconfig THERMAL
 	tristate "Generic Thermal sysfs driver"
-	depends on NET
 	help
 	  Generic Thermal Sysfs driver offers a generic mechanism for
 	  thermal management. Usually it's made up of one or more thermal
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index 7d0e63c79280..713b7ea4a607 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -62,20 +62,6 @@ static DEFINE_MUTEX(thermal_list_lock);
 
 static unsigned int thermal_event_seqnum;
 
-static struct genl_family thermal_event_genl_family = {
-	.id = GENL_ID_GENERATE,
-	.name = THERMAL_GENL_FAMILY_NAME,
-	.version = THERMAL_GENL_VERSION,
-	.maxattr = THERMAL_GENL_ATTR_MAX,
-};
-
-static struct genl_multicast_group thermal_event_mcgrp = {
-	.name = THERMAL_GENL_MCAST_GROUP_NAME,
-};
-
-static int genetlink_init(void);
-static void genetlink_exit(void);
-
 static int get_idr(struct idr *idr, struct mutex *lock, int *id)
 {
 	int err;
@@ -1225,6 +1211,18 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
 EXPORT_SYMBOL(thermal_zone_device_unregister);
 
+#ifdef CONFIG_NET
+static struct genl_family thermal_event_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.name = THERMAL_GENL_FAMILY_NAME,
+	.version = THERMAL_GENL_VERSION,
+	.maxattr = THERMAL_GENL_ATTR_MAX,
+};
+
+static struct genl_multicast_group thermal_event_mcgrp = {
+	.name = THERMAL_GENL_MCAST_GROUP_NAME,
+};
+
 int generate_netlink_event(u32 orig, enum events event)
 {
 	struct sk_buff *skb;
@@ -1301,6 +1299,15 @@ static int genetlink_init(void)
 	return result;
 }
 
+static void genetlink_exit(void)
+{
+	genl_unregister_family(&thermal_event_genl_family);
+}
+#else /* !CONFIG_NET */
+static inline int genetlink_init(void) { return 0; }
+static inline void genetlink_exit(void) {}
+#endif /* !CONFIG_NET */
+
 static int __init thermal_init(void)
 {
 	int result = 0;
@@ -1316,11 +1323,6 @@ static int __init thermal_init(void)
 	return result;
 }
 
-static void genetlink_exit(void)
-{
-	genl_unregister_family(&thermal_event_genl_family);
-}
-
 static void __exit thermal_exit(void)
 {
 	class_unregister(&thermal_class);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 8651556dbd52..d3ec89fb4122 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -172,6 +172,14 @@ void thermal_zone_device_update(struct thermal_zone_device *);
 struct thermal_cooling_device *thermal_cooling_device_register(char *, void *,
 		const struct thermal_cooling_device_ops *);
 void thermal_cooling_device_unregister(struct thermal_cooling_device *);
+
+#ifdef CONFIG_NET
 extern int generate_netlink_event(u32 orig, enum events event);
+#else
+static inline int generate_netlink_event(u32 orig, enum events event)
+{
+	return 0;
+}
+#endif
 
 #endif /* __THERMAL_H__ */
-- 
cgit v1.2.3


From d714d1979d7b4df7e2c127407f4014ce71f73cd0 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Tue, 22 Feb 2011 20:22:44 -0700
Subject: dt: eliminate of_platform_driver shim code

Commit eca393016, "of: Merge of_platform_bus_type with
platform_bus_type" added a shim to allow of_platform_drivers to get
registers onto the platform bus so that there was time to migrate the
existing drivers to the platform_bus_type.

This patch removes the shim since there are no more users of the old
interface.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/of/platform.c       | 68 ---------------------------------------------
 include/linux/of_platform.h | 12 +-------
 2 files changed, 1 insertion(+), 79 deletions(-)

(limited to 'include')

diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index b71d0cdc4209..1ce4c45c4ab2 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -42,74 +42,6 @@ struct platform_device *of_find_device_by_node(struct device_node *np)
 }
 EXPORT_SYMBOL(of_find_device_by_node);
 
-static int platform_driver_probe_shim(struct platform_device *pdev)
-{
-	struct platform_driver *pdrv;
-	struct of_platform_driver *ofpdrv;
-	const struct of_device_id *match;
-
-	pdrv = container_of(pdev->dev.driver, struct platform_driver, driver);
-	ofpdrv = container_of(pdrv, struct of_platform_driver, platform_driver);
-
-	/* There is an unlikely chance that an of_platform driver might match
-	 * on a non-OF platform device.  If so, then of_match_device() will
-	 * come up empty.  Return -EINVAL in this case so other drivers get
-	 * the chance to bind. */
-	match = of_match_device(pdev->dev.driver->of_match_table, &pdev->dev);
-	return match ? ofpdrv->probe(pdev, match) : -EINVAL;
-}
-
-static void platform_driver_shutdown_shim(struct platform_device *pdev)
-{
-	struct platform_driver *pdrv;
-	struct of_platform_driver *ofpdrv;
-
-	pdrv = container_of(pdev->dev.driver, struct platform_driver, driver);
-	ofpdrv = container_of(pdrv, struct of_platform_driver, platform_driver);
-	ofpdrv->shutdown(pdev);
-}
-
-/**
- * of_register_platform_driver
- */
-int of_register_platform_driver(struct of_platform_driver *drv)
-{
-	char *of_name;
-
-	/* setup of_platform_driver to platform_driver adaptors */
-	drv->platform_driver.driver = drv->driver;
-
-	/* Prefix the driver name with 'of:' to avoid namespace collisions
-	 * and bogus matches.  There are some drivers in the tree that
-	 * register both an of_platform_driver and a platform_driver with
-	 * the same name.  This is a temporary measure until they are all
-	 * cleaned up --gcl July 29, 2010 */
-	of_name = kmalloc(strlen(drv->driver.name) + 5, GFP_KERNEL);
-	if (!of_name)
-		return -ENOMEM;
-	sprintf(of_name, "of:%s", drv->driver.name);
-	drv->platform_driver.driver.name = of_name;
-
-	if (drv->probe)
-		drv->platform_driver.probe = platform_driver_probe_shim;
-	drv->platform_driver.remove = drv->remove;
-	if (drv->shutdown)
-		drv->platform_driver.shutdown = platform_driver_shutdown_shim;
-	drv->platform_driver.suspend = drv->suspend;
-	drv->platform_driver.resume = drv->resume;
-
-	return platform_driver_register(&drv->platform_driver);
-}
-EXPORT_SYMBOL(of_register_platform_driver);
-
-void of_unregister_platform_driver(struct of_platform_driver *drv)
-{
-	platform_driver_unregister(&drv->platform_driver);
-	kfree(drv->platform_driver.driver.name);
-	drv->platform_driver.driver.name = NULL;
-}
-EXPORT_SYMBOL(of_unregister_platform_driver);
-
 #if defined(CONFIG_PPC_DCR)
 #include <asm/dcr.h>
 #endif
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index 048949fa1d10..17c7e21c0bd7 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -23,13 +23,7 @@
  * of_platform_driver - Legacy of-aware driver for platform devices.
  *
  * An of_platform_driver driver is attached to a basic platform_device on
- * ether the "platform bus" (platform_bus_type), or the ibm ebus
- * (ibmebus_bus_type).
- *
- * of_platform_driver is being phased out when used with the platform_bus_type,
- * and regular platform_drivers should be used instead.  When the transition
- * is complete, only ibmebus will be using this structure, and the
- * platform_driver member of this structure will be removed.
+ * the ibm ebus (ibmebus_bus_type).
  */
 struct of_platform_driver
 {
@@ -42,15 +36,11 @@ struct of_platform_driver
 	int	(*shutdown)(struct platform_device* dev);
 
 	struct device_driver	driver;
-	struct platform_driver	platform_driver;
 };
 #define	to_of_platform_driver(drv) \
 	container_of(drv,struct of_platform_driver, driver)
 
 /* Platform drivers register/unregister */
-extern int of_register_platform_driver(struct of_platform_driver *drv);
-extern void of_unregister_platform_driver(struct of_platform_driver *drv);
-
 extern struct platform_device *of_device_alloc(struct device_node *np,
 					 const char *bus_id,
 					 struct device *parent);
-- 
cgit v1.2.3


From 450adcbe518ab3a3953d8475309525d22de77cba Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Tue, 1 Mar 2011 13:40:54 -0500
Subject: blk-throttle: Do not use kblockd workqueue for throtl work

o Dominik Klein reported a system hang issue while doing some blkio
  throttling testing.

  https://lkml.org/lkml/2011/2/24/173

o Some tracing revealed that CFQ was not dispatching any more jobs as
  queue unplug was not happening. And queue unplug was not happening
  because unplug work was not being called as there was one throttling
  work on same cpu which as not finished yet. And throttling work had not
  finished as it was tyring to dispatch a bio to CFQ but all the request
  descriptors were consume to it was put to sleep.

o So basically it is a cyclic dependecny between CFQ unplug work and
  throtl dispatch work. Tejun suggested that use separate workqueue for
  such cases.

o This patch uses a separate workqueue for throttle related work and
  does not rely on kblockd workqueue anymore.

Cc: stable@kernel.org
Reported-by: Dominik Klein <dk@in-telegence.net>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c       |  7 -------
 block/blk-throttle.c   | 29 ++++++++++++++++++-----------
 include/linux/blkdev.h |  3 ---
 3 files changed, 18 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 2f4002f79a24..792ece276160 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2610,13 +2610,6 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
-int kblockd_schedule_delayed_work(struct request_queue *q,
-			struct delayed_work *dwork, unsigned long delay)
-{
-	return queue_delayed_work(kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work);
-
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a89043a3caa4..e36cc10a346c 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -20,6 +20,11 @@ static int throtl_quantum = 32;
 /* Throttling is performed over 100ms slice and after that slice is renewed */
 static unsigned long throtl_slice = HZ/10;	/* 100 ms */
 
+/* A workqueue to queue throttle related work */
+static struct workqueue_struct *kthrotld_workqueue;
+static void throtl_schedule_delayed_work(struct throtl_data *td,
+				unsigned long delay);
+
 struct throtl_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
@@ -345,10 +350,9 @@ static void throtl_schedule_next_dispatch(struct throtl_data *td)
 	update_min_dispatch_time(st);
 
 	if (time_before_eq(st->min_disptime, jiffies))
-		throtl_schedule_delayed_work(td->queue, 0);
+		throtl_schedule_delayed_work(td, 0);
 	else
-		throtl_schedule_delayed_work(td->queue,
-				(st->min_disptime - jiffies));
+		throtl_schedule_delayed_work(td, (st->min_disptime - jiffies));
 }
 
 static inline void
@@ -815,10 +819,10 @@ void blk_throtl_work(struct work_struct *work)
 }
 
 /* Call with queue lock held */
-void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
+static void
+throtl_schedule_delayed_work(struct throtl_data *td, unsigned long delay)
 {
 
-	struct throtl_data *td = q->td;
 	struct delayed_work *dwork = &td->throtl_work;
 
 	if (total_nr_queued(td) > 0) {
@@ -827,12 +831,11 @@ void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
 		 * Cancel that and schedule a new one.
 		 */
 		__cancel_delayed_work(dwork);
-		kblockd_schedule_delayed_work(q, dwork, delay);
+		queue_delayed_work(kthrotld_workqueue, dwork, delay);
 		throtl_log(td, "schedule work. delay=%lu jiffies=%lu",
 				delay, jiffies);
 	}
 }
-EXPORT_SYMBOL(throtl_schedule_delayed_work);
 
 static void
 throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
@@ -920,7 +923,7 @@ static void throtl_update_blkio_group_read_bps(void *key,
 	smp_mb__after_atomic_inc();
 
 	/* Schedule a work now to process the limit change */
-	throtl_schedule_delayed_work(td->queue, 0);
+	throtl_schedule_delayed_work(td, 0);
 }
 
 static void throtl_update_blkio_group_write_bps(void *key,
@@ -934,7 +937,7 @@ static void throtl_update_blkio_group_write_bps(void *key,
 	smp_mb__before_atomic_inc();
 	atomic_inc(&td->limits_changed);
 	smp_mb__after_atomic_inc();
-	throtl_schedule_delayed_work(td->queue, 0);
+	throtl_schedule_delayed_work(td, 0);
 }
 
 static void throtl_update_blkio_group_read_iops(void *key,
@@ -948,7 +951,7 @@ static void throtl_update_blkio_group_read_iops(void *key,
 	smp_mb__before_atomic_inc();
 	atomic_inc(&td->limits_changed);
 	smp_mb__after_atomic_inc();
-	throtl_schedule_delayed_work(td->queue, 0);
+	throtl_schedule_delayed_work(td, 0);
 }
 
 static void throtl_update_blkio_group_write_iops(void *key,
@@ -962,7 +965,7 @@ static void throtl_update_blkio_group_write_iops(void *key,
 	smp_mb__before_atomic_inc();
 	atomic_inc(&td->limits_changed);
 	smp_mb__after_atomic_inc();
-	throtl_schedule_delayed_work(td->queue, 0);
+	throtl_schedule_delayed_work(td, 0);
 }
 
 void throtl_shutdown_timer_wq(struct request_queue *q)
@@ -1135,6 +1138,10 @@ void blk_throtl_exit(struct request_queue *q)
 
 static int __init throtl_init(void)
 {
+	kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
+	if (!kthrotld_workqueue)
+		panic("Failed to create kthrotld\n");
+
 	blkio_policy_register(&blkio_policy_throtl);
 	return 0;
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4d18ff34670a..dd8cd0f47e3a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1088,7 +1088,6 @@ static inline void put_dev_sector(Sector p)
 
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
-int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
 /*
@@ -1136,7 +1135,6 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 extern int blk_throtl_init(struct request_queue *q);
 extern void blk_throtl_exit(struct request_queue *q);
 extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
-extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay);
 extern void throtl_shutdown_timer_wq(struct request_queue *q);
 #else /* CONFIG_BLK_DEV_THROTTLING */
 static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
@@ -1146,7 +1144,6 @@ static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
 
 static inline int blk_throtl_init(struct request_queue *q) { return 0; }
 static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
-static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {}
 static inline void throtl_shutdown_timer_wq(struct request_queue *q) {}
 #endif /* CONFIG_BLK_DEV_THROTTLING */
 
-- 
cgit v1.2.3


From c8dcfd8a046c1f49af0c15726761af17b957962d Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Sun, 27 Feb 2011 22:08:00 +0100
Subject: cfg80211: add a field for the bitrate of the last rx data packet from
 a station

Also fix a typo in the STATION_INFO_TX_BITRATE description

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/nl80211.h |  3 +++
 include/net/cfg80211.h  |  5 ++++-
 net/wireless/nl80211.c  | 56 ++++++++++++++++++++++++++++++++-----------------
 3 files changed, 44 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h
index 821ffb954f14..30022189104d 100644
--- a/include/linux/nl80211.h
+++ b/include/linux/nl80211.h
@@ -1243,6 +1243,8 @@ enum nl80211_rate_info {
  * @NL80211_STA_INFO_LLID: the station's mesh LLID
  * @NL80211_STA_INFO_PLID: the station's mesh PLID
  * @NL80211_STA_INFO_PLINK_STATE: peer link state for the station
+ * @NL80211_STA_INFO_RX_BITRATE: last unicast data frame rx rate, nested
+ *	attribute, like NL80211_STA_INFO_TX_BITRATE.
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -1261,6 +1263,7 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_TX_RETRIES,
 	NL80211_STA_INFO_TX_FAILED,
 	NL80211_STA_INFO_SIGNAL_AVG,
+	NL80211_STA_INFO_RX_BITRATE,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 679a0494b5f2..1ac5786da14b 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -413,7 +413,7 @@ struct station_parameters {
  * @STATION_INFO_PLID: @plid filled
  * @STATION_INFO_PLINK_STATE: @plink_state filled
  * @STATION_INFO_SIGNAL: @signal filled
- * @STATION_INFO_TX_BITRATE: @tx_bitrate fields are filled
+ * @STATION_INFO_TX_BITRATE: @txrate fields are filled
  *  (tx_bitrate, tx_bitrate_flags and tx_bitrate_mcs)
  * @STATION_INFO_RX_PACKETS: @rx_packets filled
  * @STATION_INFO_TX_PACKETS: @tx_packets filled
@@ -421,6 +421,7 @@ struct station_parameters {
  * @STATION_INFO_TX_FAILED: @tx_failed filled
  * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled
  * @STATION_INFO_SIGNAL_AVG: @signal_avg filled
+ * @STATION_INFO_RX_BITRATE: @rxrate fields are filled
  */
 enum station_info_flags {
 	STATION_INFO_INACTIVE_TIME	= 1<<0,
@@ -437,6 +438,7 @@ enum station_info_flags {
 	STATION_INFO_TX_FAILED		= 1<<11,
 	STATION_INFO_RX_DROP_MISC	= 1<<12,
 	STATION_INFO_SIGNAL_AVG		= 1<<13,
+	STATION_INFO_RX_BITRATE		= 1<<14,
 };
 
 /**
@@ -506,6 +508,7 @@ struct station_info {
 	s8 signal;
 	s8 signal_avg;
 	struct rate_info txrate;
+	struct rate_info rxrate;
 	u32 rx_packets;
 	u32 tx_packets;
 	u32 tx_retries;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 864ddfbeff2f..4ebce4284e9d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1968,13 +1968,41 @@ static int parse_station_flags(struct genl_info *info,
 	return 0;
 }
 
+static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
+				 int attr)
+{
+	struct nlattr *rate;
+	u16 bitrate;
+
+	rate = nla_nest_start(msg, attr);
+	if (!rate)
+		goto nla_put_failure;
+
+	/* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */
+	bitrate = cfg80211_calculate_bitrate(info);
+	if (bitrate > 0)
+		NLA_PUT_U16(msg, NL80211_RATE_INFO_BITRATE, bitrate);
+
+	if (info->flags & RATE_INFO_FLAGS_MCS)
+		NLA_PUT_U8(msg, NL80211_RATE_INFO_MCS, info->mcs);
+	if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH)
+		NLA_PUT_FLAG(msg, NL80211_RATE_INFO_40_MHZ_WIDTH);
+	if (info->flags & RATE_INFO_FLAGS_SHORT_GI)
+		NLA_PUT_FLAG(msg, NL80211_RATE_INFO_SHORT_GI);
+
+	nla_nest_end(msg, rate);
+	return true;
+
+nla_put_failure:
+	return false;
+}
+
 static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq,
 				int flags, struct net_device *dev,
 				const u8 *mac_addr, struct station_info *sinfo)
 {
 	void *hdr;
-	struct nlattr *sinfoattr, *txrate;
-	u16 bitrate;
+	struct nlattr *sinfoattr;
 
 	hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_STATION);
 	if (!hdr)
@@ -2013,24 +2041,14 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq,
 		NLA_PUT_U8(msg, NL80211_STA_INFO_SIGNAL_AVG,
 			   sinfo->signal_avg);
 	if (sinfo->filled & STATION_INFO_TX_BITRATE) {
-		txrate = nla_nest_start(msg, NL80211_STA_INFO_TX_BITRATE);
-		if (!txrate)
+		if (!nl80211_put_sta_rate(msg, &sinfo->txrate,
+					  NL80211_STA_INFO_TX_BITRATE))
+			goto nla_put_failure;
+	}
+	if (sinfo->filled & STATION_INFO_RX_BITRATE) {
+		if (!nl80211_put_sta_rate(msg, &sinfo->rxrate,
+					  NL80211_STA_INFO_RX_BITRATE))
 			goto nla_put_failure;
-
-		/* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */
-		bitrate = cfg80211_calculate_bitrate(&sinfo->txrate);
-		if (bitrate > 0)
-			NLA_PUT_U16(msg, NL80211_RATE_INFO_BITRATE, bitrate);
-
-		if (sinfo->txrate.flags & RATE_INFO_FLAGS_MCS)
-			NLA_PUT_U8(msg, NL80211_RATE_INFO_MCS,
-				    sinfo->txrate.mcs);
-		if (sinfo->txrate.flags & RATE_INFO_FLAGS_40_MHZ_WIDTH)
-			NLA_PUT_FLAG(msg, NL80211_RATE_INFO_40_MHZ_WIDTH);
-		if (sinfo->txrate.flags & RATE_INFO_FLAGS_SHORT_GI)
-			NLA_PUT_FLAG(msg, NL80211_RATE_INFO_SHORT_GI);
-
-		nla_nest_end(msg, txrate);
 	}
 	if (sinfo->filled & STATION_INFO_RX_PACKETS)
 		NLA_PUT_U32(msg, NL80211_STA_INFO_RX_PACKETS,
-- 
cgit v1.2.3


From 1470ddf7f8cecf776921e5ccee72e3d2b3d60cbc Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 1 Mar 2011 02:36:47 +0000
Subject: inet: Remove explicit write references to sk/inet in ip_append_data

In order to allow simultaneous calls to ip_append_data on the same
socket, it must not modify any shared state in sk or inet (other
than those that are designed to allow that such as atomic counters).

This patch abstracts out write references to sk and inet_sk in
ip_append_data and its friends so that we may use the underlying
code in parallel.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  23 +++--
 net/ipv4/ip_output.c    | 238 ++++++++++++++++++++++++++++--------------------
 2 files changed, 154 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 6e6dfd757682..7a37369f8ea3 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -86,6 +86,19 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 	return (struct inet_request_sock *)sk;
 }
 
+struct inet_cork {
+	unsigned int		flags;
+	unsigned int		fragsize;
+	struct ip_options	*opt;
+	struct dst_entry	*dst;
+	int			length; /* Total length of all frames */
+	__be32			addr;
+	struct flowi		fl;
+	struct page		*page;
+	u32			off;
+	u8			tx_flags;
+};
+
 struct ip_mc_socklist;
 struct ipv6_pinfo;
 struct rtable;
@@ -143,15 +156,7 @@ struct inet_sock {
 	int			mc_index;
 	__be32			mc_addr;
 	struct ip_mc_socklist __rcu	*mc_list;
-	struct {
-		unsigned int		flags;
-		unsigned int		fragsize;
-		struct ip_options	*opt;
-		struct dst_entry	*dst;
-		int			length; /* Total length of all frames */
-		__be32			addr;
-		struct flowi		fl;
-	} cork;
+	struct inet_cork	cork;
 };
 
 #define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d3a4540cd308..1dd5ecc9a27e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -733,6 +733,7 @@ csum_page(struct page *page, int offset, int copy)
 }
 
 static inline int ip_ufo_append_data(struct sock *sk,
+			struct sk_buff_head *queue,
 			int getfrag(void *from, char *to, int offset, int len,
 			       int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
@@ -745,7 +746,7 @@ static inline int ip_ufo_append_data(struct sock *sk,
 	 * device, so create one single skb packet containing complete
 	 * udp datagram
 	 */
-	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
+	if ((skb = skb_peek_tail(queue)) == NULL) {
 		skb = sock_alloc_send_skb(sk,
 			hh_len + fragheaderlen + transhdrlen + 20,
 			(flags & MSG_DONTWAIT), &err);
@@ -771,35 +772,24 @@ static inline int ip_ufo_append_data(struct sock *sk,
 		/* specify the length of each IP datagram fragment */
 		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-		__skb_queue_tail(&sk->sk_write_queue, skb);
+		__skb_queue_tail(queue, skb);
 	}
 
 	return skb_append_datato_frags(sk, skb, getfrag, from,
 				       (length - transhdrlen));
 }
 
-/*
- *	ip_append_data() and ip_append_page() can make one large IP datagram
- *	from many pieces of data. Each pieces will be holded on the socket
- *	until ip_push_pending_frames() is called. Each piece can be a page
- *	or non-page data.
- *
- *	Not only UDP, other transport protocols - e.g. raw sockets - can use
- *	this interface potentially.
- *
- *	LATER: length must be adjusted by pad at tail, when it is required.
- */
-int ip_append_data(struct sock *sk,
-		   int getfrag(void *from, char *to, int offset, int len,
-			       int odd, struct sk_buff *skb),
-		   void *from, int length, int transhdrlen,
-		   struct ipcm_cookie *ipc, struct rtable **rtp,
-		   unsigned int flags)
+static int __ip_append_data(struct sock *sk, struct sk_buff_head *queue,
+			    struct inet_cork *cork,
+			    int getfrag(void *from, char *to, int offset,
+					int len, int odd, struct sk_buff *skb),
+			    void *from, int length, int transhdrlen,
+			    unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sk_buff *skb;
 
-	struct ip_options *opt = NULL;
+	struct ip_options *opt = inet->cork.opt;
 	int hh_len;
 	int exthdrlen;
 	int mtu;
@@ -808,58 +798,19 @@ int ip_append_data(struct sock *sk,
 	int offset = 0;
 	unsigned int maxfraglen, fragheaderlen;
 	int csummode = CHECKSUM_NONE;
-	struct rtable *rt;
-
-	if (flags&MSG_PROBE)
-		return 0;
+	struct rtable *rt = (struct rtable *)cork->dst;
 
-	if (skb_queue_empty(&sk->sk_write_queue)) {
-		/*
-		 * setup for corking.
-		 */
-		opt = ipc->opt;
-		if (opt) {
-			if (inet->cork.opt == NULL) {
-				inet->cork.opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation);
-				if (unlikely(inet->cork.opt == NULL))
-					return -ENOBUFS;
-			}
-			memcpy(inet->cork.opt, opt, sizeof(struct ip_options)+opt->optlen);
-			inet->cork.flags |= IPCORK_OPT;
-			inet->cork.addr = ipc->addr;
-		}
-		rt = *rtp;
-		if (unlikely(!rt))
-			return -EFAULT;
-		/*
-		 * We steal reference to this route, caller should not release it
-		 */
-		*rtp = NULL;
-		inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ?
-					    rt->dst.dev->mtu :
-					    dst_mtu(rt->dst.path);
-		inet->cork.dst = &rt->dst;
-		inet->cork.length = 0;
-		sk->sk_sndmsg_page = NULL;
-		sk->sk_sndmsg_off = 0;
-		exthdrlen = rt->dst.header_len;
-		length += exthdrlen;
-		transhdrlen += exthdrlen;
-	} else {
-		rt = (struct rtable *)inet->cork.dst;
-		if (inet->cork.flags & IPCORK_OPT)
-			opt = inet->cork.opt;
+	exthdrlen = transhdrlen ? rt->dst.header_len : 0;
+	length += exthdrlen;
+	transhdrlen += exthdrlen;
+	mtu = inet->cork.fragsize;
 
-		transhdrlen = 0;
-		exthdrlen = 0;
-		mtu = inet->cork.fragsize;
-	}
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
 
-	if (inet->cork.length + length > 0xFFFF - fragheaderlen) {
+	if (cork->length + length > 0xFFFF - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport,
 			       mtu-exthdrlen);
 		return -EMSGSIZE;
@@ -875,15 +826,15 @@ int ip_append_data(struct sock *sk,
 	    !exthdrlen)
 		csummode = CHECKSUM_PARTIAL;
 
-	skb = skb_peek_tail(&sk->sk_write_queue);
+	skb = skb_peek_tail(queue);
 
-	inet->cork.length += length;
+	cork->length += length;
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
-		err = ip_ufo_append_data(sk, getfrag, from, length, hh_len,
-					 fragheaderlen, transhdrlen, mtu,
-					 flags);
+		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
+					 hh_len, fragheaderlen, transhdrlen,
+					 mtu, flags);
 		if (err)
 			goto error;
 		return 0;
@@ -960,7 +911,7 @@ alloc_new_skb:
 				else
 					/* only the initial fragment is
 					   time stamped */
-					ipc->tx_flags = 0;
+					cork->tx_flags = 0;
 			}
 			if (skb == NULL)
 				goto error;
@@ -971,7 +922,7 @@ alloc_new_skb:
 			skb->ip_summed = csummode;
 			skb->csum = 0;
 			skb_reserve(skb, hh_len);
-			skb_shinfo(skb)->tx_flags = ipc->tx_flags;
+			skb_shinfo(skb)->tx_flags = cork->tx_flags;
 
 			/*
 			 *	Find where to start putting bytes.
@@ -1008,7 +959,7 @@ alloc_new_skb:
 			/*
 			 * Put the packet on the pending queue.
 			 */
-			__skb_queue_tail(&sk->sk_write_queue, skb);
+			__skb_queue_tail(queue, skb);
 			continue;
 		}
 
@@ -1028,8 +979,8 @@ alloc_new_skb:
 		} else {
 			int i = skb_shinfo(skb)->nr_frags;
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
-			struct page *page = sk->sk_sndmsg_page;
-			int off = sk->sk_sndmsg_off;
+			struct page *page = cork->page;
+			int off = cork->off;
 			unsigned int left;
 
 			if (page && (left = PAGE_SIZE - off) > 0) {
@@ -1041,7 +992,7 @@ alloc_new_skb:
 						goto error;
 					}
 					get_page(page);
-					skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
+					skb_fill_page_desc(skb, i, page, off, 0);
 					frag = &skb_shinfo(skb)->frags[i];
 				}
 			} else if (i < MAX_SKB_FRAGS) {
@@ -1052,8 +1003,8 @@ alloc_new_skb:
 					err = -ENOMEM;
 					goto error;
 				}
-				sk->sk_sndmsg_page = page;
-				sk->sk_sndmsg_off = 0;
+				cork->page = page;
+				cork->off = 0;
 
 				skb_fill_page_desc(skb, i, page, 0, 0);
 				frag = &skb_shinfo(skb)->frags[i];
@@ -1065,7 +1016,7 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-			sk->sk_sndmsg_off += copy;
+			cork->off += copy;
 			frag->size += copy;
 			skb->len += copy;
 			skb->data_len += copy;
@@ -1079,11 +1030,87 @@ alloc_new_skb:
 	return 0;
 
 error:
-	inet->cork.length -= length;
+	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
 
+static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
+			 struct ipcm_cookie *ipc, struct rtable **rtp)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ip_options *opt;
+	struct rtable *rt;
+
+	/*
+	 * setup for corking.
+	 */
+	opt = ipc->opt;
+	if (opt) {
+		if (cork->opt == NULL) {
+			cork->opt = kmalloc(sizeof(struct ip_options) + 40,
+					    sk->sk_allocation);
+			if (unlikely(cork->opt == NULL))
+				return -ENOBUFS;
+		}
+		memcpy(cork->opt, opt, sizeof(struct ip_options) + opt->optlen);
+		cork->flags |= IPCORK_OPT;
+		cork->addr = ipc->addr;
+	}
+	rt = *rtp;
+	if (unlikely(!rt))
+		return -EFAULT;
+	/*
+	 * We steal reference to this route, caller should not release it
+	 */
+	*rtp = NULL;
+	cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ?
+			 rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+	cork->dst = &rt->dst;
+	cork->length = 0;
+	cork->tx_flags = ipc->tx_flags;
+	cork->page = NULL;
+	cork->off = 0;
+
+	return 0;
+}
+
+/*
+ *	ip_append_data() and ip_append_page() can make one large IP datagram
+ *	from many pieces of data. Each pieces will be holded on the socket
+ *	until ip_push_pending_frames() is called. Each piece can be a page
+ *	or non-page data.
+ *
+ *	Not only UDP, other transport protocols - e.g. raw sockets - can use
+ *	this interface potentially.
+ *
+ *	LATER: length must be adjusted by pad at tail, when it is required.
+ */
+int ip_append_data(struct sock *sk,
+		   int getfrag(void *from, char *to, int offset, int len,
+			       int odd, struct sk_buff *skb),
+		   void *from, int length, int transhdrlen,
+		   struct ipcm_cookie *ipc, struct rtable **rtp,
+		   unsigned int flags)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	int err;
+
+	if (flags&MSG_PROBE)
+		return 0;
+
+	if (skb_queue_empty(&sk->sk_write_queue)) {
+		err = ip_setup_cork(sk, &inet->cork, ipc, rtp);
+		if (err)
+			return err;
+	} else {
+		transhdrlen = 0;
+	}
+
+	return __ip_append_data(sk, &sk->sk_write_queue, &inet->cork, getfrag,
+				from, length, transhdrlen, flags);
+}
+
 ssize_t	ip_append_page(struct sock *sk, struct page *page,
 		       int offset, size_t size, int flags)
 {
@@ -1227,40 +1254,42 @@ error:
 	return err;
 }
 
-static void ip_cork_release(struct inet_sock *inet)
+static void ip_cork_release(struct inet_cork *cork)
 {
-	inet->cork.flags &= ~IPCORK_OPT;
-	kfree(inet->cork.opt);
-	inet->cork.opt = NULL;
-	dst_release(inet->cork.dst);
-	inet->cork.dst = NULL;
+	cork->flags &= ~IPCORK_OPT;
+	kfree(cork->opt);
+	cork->opt = NULL;
+	dst_release(cork->dst);
+	cork->dst = NULL;
 }
 
 /*
  *	Combined all pending IP fragments on the socket as one IP datagram
  *	and push them out.
  */
-int ip_push_pending_frames(struct sock *sk)
+static int __ip_push_pending_frames(struct sock *sk,
+				    struct sk_buff_head *queue,
+				    struct inet_cork *cork)
 {
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
 	struct ip_options *opt = NULL;
-	struct rtable *rt = (struct rtable *)inet->cork.dst;
+	struct rtable *rt = (struct rtable *)cork->dst;
 	struct iphdr *iph;
 	__be16 df = 0;
 	__u8 ttl;
 	int err = 0;
 
-	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
+	if ((skb = __skb_dequeue(queue)) == NULL)
 		goto out;
 	tail_skb = &(skb_shinfo(skb)->frag_list);
 
 	/* move skb->data to ip header from ext header */
 	if (skb->data < skb_network_header(skb))
 		__skb_pull(skb, skb_network_offset(skb));
-	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+	while ((tmp_skb = __skb_dequeue(queue)) != NULL) {
 		__skb_pull(tmp_skb, skb_network_header_len(skb));
 		*tail_skb = tmp_skb;
 		tail_skb = &(tmp_skb->next);
@@ -1286,8 +1315,8 @@ int ip_push_pending_frames(struct sock *sk)
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
 
-	if (inet->cork.flags & IPCORK_OPT)
-		opt = inet->cork.opt;
+	if (cork->flags & IPCORK_OPT)
+		opt = cork->opt;
 
 	if (rt->rt_type == RTN_MULTICAST)
 		ttl = inet->mc_ttl;
@@ -1299,7 +1328,7 @@ int ip_push_pending_frames(struct sock *sk)
 	iph->ihl = 5;
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
-		ip_options_build(skb, opt, inet->cork.addr, rt, 0);
+		ip_options_build(skb, opt, cork->addr, rt, 0);
 	}
 	iph->tos = inet->tos;
 	iph->frag_off = df;
@@ -1315,7 +1344,7 @@ int ip_push_pending_frames(struct sock *sk)
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
 	 */
-	inet->cork.dst = NULL;
+	cork->dst = NULL;
 	skb_dst_set(skb, &rt->dst);
 
 	if (iph->protocol == IPPROTO_ICMP)
@@ -1332,7 +1361,7 @@ int ip_push_pending_frames(struct sock *sk)
 	}
 
 out:
-	ip_cork_release(inet);
+	ip_cork_release(cork);
 	return err;
 
 error:
@@ -1340,17 +1369,30 @@ error:
 	goto out;
 }
 
+int ip_push_pending_frames(struct sock *sk)
+{
+	return __ip_push_pending_frames(sk, &sk->sk_write_queue,
+					&inet_sk(sk)->cork);
+}
+
 /*
  *	Throw away all pending data on the socket.
  */
-void ip_flush_pending_frames(struct sock *sk)
+static void __ip_flush_pending_frames(struct sock *sk,
+				      struct sk_buff_head *queue,
+				      struct inet_cork *cork)
 {
 	struct sk_buff *skb;
 
-	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
+	while ((skb = __skb_dequeue_tail(queue)) != NULL)
 		kfree_skb(skb);
 
-	ip_cork_release(inet_sk(sk));
+	ip_cork_release(cork);
+}
+
+void ip_flush_pending_frames(struct sock *sk)
+{
+	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
 }
 
 
-- 
cgit v1.2.3


From 1c32c5ad6fac8cee1a77449f5abf211e911ff830 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 1 Mar 2011 02:36:47 +0000
Subject: inet: Add ip_make_skb and ip_finish_skb

This patch adds the helper ip_make_skb which is like ip_append_data
and ip_push_pending_frames all rolled into one, except that it does
not send the skb produced.  The sending part is carried out by
ip_send_skb, which the transport protocol can call after it has
tweaked the skb.

It is meant to be called in cases where corking is not used should
have a one-to-one correspondence to sendmsg.

This patch also adds the helper ip_finish_skb which is meant to
be replace ip_push_pending_frames when corking is required.
Previously the protocol stack would peek at the socket write
queue and add its header to the first packet.  With ip_finish_skb,
the protocol stack can directly operate on the final skb instead,
just like the non-corking case with ip_make_skb.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h     | 16 +++++++++++++
 net/ipv4/ip_output.c | 65 +++++++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 67 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index 67fac78a186b..a4f631108c54 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -116,8 +116,24 @@ extern int		ip_append_data(struct sock *sk,
 extern int		ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb);
 extern ssize_t		ip_append_page(struct sock *sk, struct page *page,
 				int offset, size_t size, int flags);
+extern struct sk_buff  *__ip_make_skb(struct sock *sk,
+				      struct sk_buff_head *queue,
+				      struct inet_cork *cork);
+extern int		ip_send_skb(struct sk_buff *skb);
 extern int		ip_push_pending_frames(struct sock *sk);
 extern void		ip_flush_pending_frames(struct sock *sk);
+extern struct sk_buff  *ip_make_skb(struct sock *sk,
+				    int getfrag(void *from, char *to, int offset, int len,
+						int odd, struct sk_buff *skb),
+				    void *from, int length, int transhdrlen,
+				    struct ipcm_cookie *ipc,
+				    struct rtable **rtp,
+				    unsigned int flags);
+
+static inline struct sk_buff *ip_finish_skb(struct sock *sk)
+{
+	return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
+}
 
 /* datagram.c */
 extern int		ip4_datagram_connect(struct sock *sk, 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1dd5ecc9a27e..460308c35028 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1267,9 +1267,9 @@ static void ip_cork_release(struct inet_cork *cork)
  *	Combined all pending IP fragments on the socket as one IP datagram
  *	and push them out.
  */
-static int __ip_push_pending_frames(struct sock *sk,
-				    struct sk_buff_head *queue,
-				    struct inet_cork *cork)
+struct sk_buff *__ip_make_skb(struct sock *sk,
+			      struct sk_buff_head *queue,
+			      struct inet_cork *cork)
 {
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
@@ -1280,7 +1280,6 @@ static int __ip_push_pending_frames(struct sock *sk,
 	struct iphdr *iph;
 	__be16 df = 0;
 	__u8 ttl;
-	int err = 0;
 
 	if ((skb = __skb_dequeue(queue)) == NULL)
 		goto out;
@@ -1351,28 +1350,37 @@ static int __ip_push_pending_frames(struct sock *sk,
 		icmp_out_count(net, ((struct icmphdr *)
 			skb_transport_header(skb))->type);
 
-	/* Netfilter gets whole the not fragmented skb. */
+	ip_cork_release(cork);
+out:
+	return skb;
+}
+
+int ip_send_skb(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	int err;
+
 	err = ip_local_out(skb);
 	if (err) {
 		if (err > 0)
 			err = net_xmit_errno(err);
 		if (err)
-			goto error;
+			IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
 	}
 
-out:
-	ip_cork_release(cork);
 	return err;
-
-error:
-	IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
-	goto out;
 }
 
 int ip_push_pending_frames(struct sock *sk)
 {
-	return __ip_push_pending_frames(sk, &sk->sk_write_queue,
-					&inet_sk(sk)->cork);
+	struct sk_buff *skb;
+
+	skb = ip_finish_skb(sk);
+	if (!skb)
+		return 0;
+
+	/* Netfilter gets whole the not fragmented skb. */
+	return ip_send_skb(skb);
 }
 
 /*
@@ -1395,6 +1403,35 @@ void ip_flush_pending_frames(struct sock *sk)
 	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
 }
 
+struct sk_buff *ip_make_skb(struct sock *sk,
+			    int getfrag(void *from, char *to, int offset,
+					int len, int odd, struct sk_buff *skb),
+			    void *from, int length, int transhdrlen,
+			    struct ipcm_cookie *ipc, struct rtable **rtp,
+			    unsigned int flags)
+{
+	struct inet_cork cork = {};
+	struct sk_buff_head queue;
+	int err;
+
+	if (flags & MSG_PROBE)
+		return NULL;
+
+	__skb_queue_head_init(&queue);
+
+	err = ip_setup_cork(sk, &cork, ipc, rtp);
+	if (err)
+		return ERR_PTR(err);
+
+	err = __ip_append_data(sk, &queue, &cork, getfrag,
+			       from, length, transhdrlen, flags);
+	if (err) {
+		__ip_flush_pending_frames(sk, &queue, &cork);
+		return ERR_PTR(err);
+	}
+
+	return __ip_make_skb(sk, &queue, &cork);
+}
 
 /*
  *	Fetch data from kernel space and fill in checksum if needed.
-- 
cgit v1.2.3


From f6b9664f8b711cf4fd53e70aa0d21f72d5bf806c Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 1 Mar 2011 02:36:48 +0000
Subject: udp: Switch to ip_finish_skb

This patch converts UDP to use the new ip_finish_skb API.  This
would then allows us to more easily use ip_make_skb which allows
UDP to run without a socket lock.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h     | 11 +++++++
 include/net/udplite.h | 12 ++++++++
 net/ipv4/udp.c        | 83 +++++++++++++++++++++++++++++++--------------------
 3 files changed, 73 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/net/udp.h b/include/net/udp.h
index e82f3a8c0f8f..67ea6fcb3ec0 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -144,6 +144,17 @@ static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb)
 	return csum;
 }
 
+static inline __wsum udp_csum(struct sk_buff *skb)
+{
+	__wsum csum = csum_partial(skb_transport_header(skb),
+				   sizeof(struct udphdr), skb->csum);
+
+	for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) {
+		csum = csum_add(csum, skb->csum);
+	}
+	return csum;
+}
+
 /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
 static inline void udp_lib_hash(struct sock *sk)
 {
diff --git a/include/net/udplite.h b/include/net/udplite.h
index afdffe607b24..673a024c6b2a 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -115,6 +115,18 @@ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb)
 	return csum;
 }
 
+static inline __wsum udplite_csum(struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb));
+	const int off = skb_transport_offset(skb);
+	const int len = skb->len - off;
+
+	skb->ip_summed = CHECKSUM_NONE;     /* no HW support for checksumming */
+
+	return skb_checksum(skb, off, min(cscov, len), 0);
+}
+
 extern void	udplite4_register(void);
 extern int 	udplite_get_port(struct sock *sk, unsigned short snum,
 			int (*scmp)(const struct sock *, const struct sock *));
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d37baaa1dbe3..61c22ee7d4ba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -663,75 +663,72 @@ void udp_flush_pending_frames(struct sock *sk)
 EXPORT_SYMBOL(udp_flush_pending_frames);
 
 /**
- * 	udp4_hwcsum_outgoing  -  handle outgoing HW checksumming
- * 	@sk: 	socket we are sending on
+ * 	udp4_hwcsum  -  handle outgoing HW checksumming
  * 	@skb: 	sk_buff containing the filled-in UDP header
  * 	        (checksum field must be zeroed out)
+ *	@src:	source IP address
+ *	@dst:	destination IP address
  */
-static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
-				 __be32 src, __be32 dst, int len)
+static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 {
-	unsigned int offset;
 	struct udphdr *uh = udp_hdr(skb);
+	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
+	int offset = skb_transport_offset(skb);
+	int len = skb->len - offset;
+	int hlen = len;
 	__wsum csum = 0;
 
-	if (skb_queue_len(&sk->sk_write_queue) == 1) {
+	if (!frags) {
 		/*
 		 * Only one fragment on the socket.
 		 */
 		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct udphdr, check);
-		uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0);
+		uh->check = ~csum_tcpudp_magic(src, dst, len,
+					       IPPROTO_UDP, 0);
 	} else {
 		/*
 		 * HW-checksum won't work as there are two or more
 		 * fragments on the socket so that all csums of sk_buffs
 		 * should be together
 		 */
-		offset = skb_transport_offset(skb);
-		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+		do {
+			csum = csum_add(csum, frags->csum);
+			hlen -= frags->len;
+		} while ((frags = frags->next));
 
+		csum = skb_checksum(skb, offset, hlen, csum);
 		skb->ip_summed = CHECKSUM_NONE;
 
-		skb_queue_walk(&sk->sk_write_queue, skb) {
-			csum = csum_add(csum, skb->csum);
-		}
-
 		uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
 		if (uh->check == 0)
 			uh->check = CSUM_MANGLED_0;
 	}
 }
 
-/*
- * Push out all pending data as one UDP datagram. Socket is locked.
- */
-static int udp_push_pending_frames(struct sock *sk)
+static int udp_send_skb(struct sk_buff *skb, __be32 daddr, __be32 dport)
 {
-	struct udp_sock  *up = udp_sk(sk);
+	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
-	struct flowi *fl = &inet->cork.fl;
-	struct sk_buff *skb;
 	struct udphdr *uh;
+	struct rtable *rt = (struct rtable *)skb_dst(skb);
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
+	int offset = skb_transport_offset(skb);
+	int len = skb->len - offset;
 	__wsum csum = 0;
 
-	/* Grab the skbuff where UDP header space exists. */
-	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
-		goto out;
-
 	/*
 	 * Create a UDP header
 	 */
 	uh = udp_hdr(skb);
-	uh->source = fl->fl_ip_sport;
-	uh->dest = fl->fl_ip_dport;
-	uh->len = htons(up->len);
+	uh->source = inet->inet_sport;
+	uh->dest = dport;
+	uh->len = htons(len);
 	uh->check = 0;
 
 	if (is_udplite)  				 /*     UDP-Lite      */
-		csum  = udplite_csum_outgoing(sk, skb);
+		csum = udplite_csum(skb);
 
 	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */
 
@@ -740,20 +737,20 @@ static int udp_push_pending_frames(struct sock *sk)
 
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
 
-		udp4_hwcsum_outgoing(sk, skb, fl->fl4_src, fl->fl4_dst, up->len);
+		udp4_hwcsum(skb, rt->rt_src, daddr);
 		goto send;
 
-	} else						 /*   `normal' UDP    */
-		csum = udp_csum_outgoing(sk, skb);
+	} else
+		csum = udp_csum(skb);
 
 	/* add protocol-dependent pseudo-header */
-	uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len,
+	uh->check = csum_tcpudp_magic(rt->rt_src, daddr, len,
 				      sk->sk_protocol, csum);
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
 send:
-	err = ip_push_pending_frames(sk);
+	err = ip_send_skb(skb);
 	if (err) {
 		if (err == -ENOBUFS && !inet->recverr) {
 			UDP_INC_STATS_USER(sock_net(sk),
@@ -763,6 +760,26 @@ send:
 	} else
 		UDP_INC_STATS_USER(sock_net(sk),
 				   UDP_MIB_OUTDATAGRAMS, is_udplite);
+	return err;
+}
+
+/*
+ * Push out all pending data as one UDP datagram. Socket is locked.
+ */
+static int udp_push_pending_frames(struct sock *sk)
+{
+	struct udp_sock  *up = udp_sk(sk);
+	struct inet_sock *inet = inet_sk(sk);
+	struct flowi *fl = &inet->cork.fl;
+	struct sk_buff *skb;
+	int err = 0;
+
+	skb = ip_finish_skb(sk);
+	if (!skb)
+		goto out;
+
+	err = udp_send_skb(skb, fl->fl4_dst, fl->fl_ip_dport);
+
 out:
 	up->len = 0;
 	up->pending = 0;
-- 
cgit v1.2.3


From 68d0c6d34d586a893292d4fb633a3bf8c547b222 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 13:19:07 -0800
Subject: ipv6: Consolidate route lookup sequences.

Route lookups follow a general pattern in the ipv6 code wherein
we first find the non-IPSEC route, potentially override the
flow destination address due to ipv6 options settings, and then
finally make an IPSEC search using either xfrm_lookup() or
__xfrm_lookup().

__xfrm_lookup() is used when we want to generate a blackhole route
if the key manager needs to resolve the IPSEC rules (in this case
-EREMOTE is returned and the original 'dst' is left unchanged).

Otherwise plain xfrm_lookup() is used and when asynchronous IPSEC
resolution is necessary, we simply fail the lookup completely.

All of these cases are encapsulated into two routines,
ip6_dst_lookup_flow and ip6_sk_dst_lookup_flow.  The latter of which
handles unconnected UDP datagram sockets.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h               | 11 ++++--
 net/dccp/ipv6.c                  | 65 ++++++++++----------------------
 net/ipv6/af_inet6.c              | 17 +++------
 net/ipv6/datagram.c              | 15 ++------
 net/ipv6/inet6_connection_sock.c | 25 +++----------
 net/ipv6/ip6_output.c            | 80 ++++++++++++++++++++++++++++++++++------
 net/ipv6/raw.c                   | 15 ++------
 net/ipv6/syncookies.c            |  7 +---
 net/ipv6/tcp_ipv6.c              | 57 +++++++++++-----------------
 net/ipv6/udp.c                   | 15 ++------
 10 files changed, 142 insertions(+), 165 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4a3cd2cd2f5e..1fc5631cf1a2 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -512,12 +512,17 @@ extern void			ip6_flush_pending_frames(struct sock *sk);
 extern int			ip6_dst_lookup(struct sock *sk,
 					       struct dst_entry **dst,
 					       struct flowi *fl);
+extern struct dst_entry *	ip6_dst_lookup_flow(struct sock *sk,
+						    struct flowi *fl,
+						    const struct in6_addr *final_dst,
+						    bool want_blackhole);
+extern struct dst_entry *	ip6_sk_dst_lookup_flow(struct sock *sk,
+						       struct flowi *fl,
+						       const struct in6_addr *final_dst,
+						       bool want_blackhole);
 extern int			ip6_dst_blackhole(struct sock *sk,
 						  struct dst_entry **dst,
 						  struct flowi *fl);
-extern int			ip6_sk_dst_lookup(struct sock *sk,
-						  struct dst_entry **dst,
-						  struct flowi *fl);
 
 /*
  *	skb processing functions
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 460d545a6509..5efc57f5e605 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -162,15 +162,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			fl.fl_ip_sport = inet->inet_sport;
 			security_sk_classify_flow(sk, &fl);
 
-			err = ip6_dst_lookup(sk, &dst, &fl);
-			if (err) {
-				sk->sk_err_soft = -err;
-				goto out;
-			}
-
-			err = xfrm_lookup(net, &dst, &fl, sk, 0);
-			if (err < 0) {
-				sk->sk_err_soft = -err;
+			dst = ip6_dst_lookup_flow(sk, &fl, NULL, false);
+			if (IS_ERR(dst)) {
+				sk->sk_err_soft = -PTR_ERR(dst);
 				goto out;
 			}
 		} else
@@ -267,16 +261,12 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 
 	final_p = fl6_update_dst(&fl, opt, &final);
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
-	if (err)
-		goto done;
-
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0);
-	if (err < 0)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		dst = NULL;
 		goto done;
+	}
 
 	skb = dccp_make_response(sk, dst, req);
 	if (skb != NULL) {
@@ -338,14 +328,13 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 	security_skb_classify_flow(rxskb, &fl);
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
-	if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) {
-		if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) {
-			skb_dst_set(skb, dst);
-			ip6_xmit(ctl_sk, skb, &fl, NULL);
-			DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
-			DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
-			return;
-		}
+	dst = ip6_dst_lookup_flow(ctl_sk, &fl, NULL, false);
+	if (!IS_ERR(dst)) {
+		skb_dst_set(skb, dst);
+		ip6_xmit(ctl_sk, skb, &fl, NULL);
+		DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
+		DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
+		return;
 	}
 
 	kfree_skb(skb);
@@ -550,13 +539,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		fl.fl_ip_sport = inet_rsk(req)->loc_port;
 		security_sk_classify_flow(sk, &fl);
 
-		if (ip6_dst_lookup(sk, &dst, &fl))
-			goto out;
-
-		if (final_p)
-			ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-		if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
+		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		if (IS_ERR(dst))
 			goto out;
 	}
 
@@ -979,19 +963,10 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	final_p = fl6_update_dst(&fl, np->opt, &final);
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
-	if (err)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
 		goto failure;
-
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
-	if (err < 0) {
-		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, &fl);
-		if (err < 0)
-			goto failure;
 	}
 
 	if (saddr == NULL) {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3194aa909872..a88b2e9d25f1 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -644,9 +644,8 @@ EXPORT_SYMBOL(inet6_unregister_protosw);
 
 int inet6_sk_rebuild_header(struct sock *sk)
 {
-	int err;
-	struct dst_entry *dst;
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct dst_entry *dst;
 
 	dst = __sk_dst_check(sk, np->dst_cookie);
 
@@ -668,17 +667,11 @@ int inet6_sk_rebuild_header(struct sock *sk)
 
 		final_p = fl6_update_dst(&fl, np->opt, &final);
 
-		err = ip6_dst_lookup(sk, &dst, &fl);
-		if (err) {
+		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		if (IS_ERR(dst)) {
 			sk->sk_route_caps = 0;
-			return err;
-		}
-		if (final_p)
-			ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-		if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) {
-			sk->sk_err_soft = -err;
-			return err;
+			sk->sk_err_soft = -PTR_ERR(dst);
+			return PTR_ERR(dst);
 		}
 
 		__ip6_dst_store(sk, dst, NULL, NULL);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 320bdb877eed..be3a781c0085 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,18 +162,11 @@ ipv4_connected:
 	opt = flowlabel ? flowlabel->opt : np->opt;
 	final_p = fl6_update_dst(&fl, opt, &final);
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
-	if (err)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	err = 0;
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
 		goto out;
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
-	if (err < 0) {
-		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, &fl);
-		if (err < 0)
-			goto out;
 	}
 
 	/* source address lookup done in ip6_dst_lookup */
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index d144e629d2b4..d687e1397333 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -74,13 +74,8 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	fl.fl_ip_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
 
-	if (ip6_dst_lookup(sk, &dst, &fl))
-		return NULL;
-
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+	if (IS_ERR(dst))
 		return NULL;
 
 	return dst;
@@ -234,21 +229,13 @@ int inet6_csk_xmit(struct sk_buff *skb)
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 
 	if (dst == NULL) {
-		int err = ip6_dst_lookup(sk, &dst, &fl);
-
-		if (err) {
-			sk->sk_err_soft = -err;
-			kfree_skb(skb);
-			return err;
-		}
-
-		if (final_p)
-			ipv6_addr_copy(&fl.fl6_dst, final_p);
+		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
 
-		if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) {
+		if (IS_ERR(dst)) {
+			sk->sk_err_soft = -PTR_ERR(dst);
 			sk->sk_route_caps = 0;
 			kfree_skb(skb);
-			return err;
+			return PTR_ERR(dst);
 		}
 
 		__inet6_csk_dst_store(sk, dst, NULL, NULL);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5c618f20523e..28209b2d254d 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1002,29 +1002,87 @@ int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
 EXPORT_SYMBOL_GPL(ip6_dst_lookup);
 
 /**
- *	ip6_sk_dst_lookup - perform socket cached route lookup on flow
+ *	ip6_dst_lookup_flow - perform route lookup on flow with ipsec
+ *	@sk: socket which provides route info
+ *	@fl: flow to lookup
+ *	@final_dst: final destination address for ipsec lookup
+ *	@want_blackhole: IPSEC blackhole handling desired
+ *
+ *	This function performs a route lookup on the given flow.
+ *
+ *	It returns a valid dst pointer on success, or a pointer encoded
+ *	error code.
+ */
+struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
+				      const struct in6_addr *final_dst,
+				      bool want_blackhole)
+{
+	struct dst_entry *dst = NULL;
+	int err;
+
+	err = ip6_dst_lookup_tail(sk, &dst, fl);
+	if (err)
+		return ERR_PTR(err);
+	if (final_dst)
+		ipv6_addr_copy(&fl->fl6_dst, final_dst);
+	if (want_blackhole) {
+		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
+		if (err == -EREMOTE)
+			err = ip6_dst_blackhole(sk, &dst, fl);
+		if (err)
+			return ERR_PTR(err);
+	} else {
+		err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
+		if (err)
+			return ERR_PTR(err);
+	}
+	return dst;
+}
+EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
+
+/**
+ *	ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow
  *	@sk: socket which provides the dst cache and route info
- *	@dst: pointer to dst_entry * for result
  *	@fl: flow to lookup
+ *	@final_dst: final destination address for ipsec lookup
+ *	@want_blackhole: IPSEC blackhole handling desired
  *
  *	This function performs a route lookup on the given flow with the
  *	possibility of using the cached route in the socket if it is valid.
  *	It will take the socket dst lock when operating on the dst cache.
  *	As a result, this function can only be used in process context.
  *
- *	It returns zero on success, or a standard errno code on error.
+ *	It returns a valid dst pointer on success, or a pointer encoded
+ *	error code.
  */
-int ip6_sk_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
+					 const struct in6_addr *final_dst,
+					 bool want_blackhole)
 {
-	*dst = NULL;
-	if (sk) {
-		*dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-		*dst = ip6_sk_dst_check(sk, *dst, fl);
-	}
+	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
+	int err;
 
-	return ip6_dst_lookup_tail(sk, dst, fl);
+	dst = ip6_sk_dst_check(sk, dst, fl);
+
+	err = ip6_dst_lookup_tail(sk, &dst, fl);
+	if (err)
+		return ERR_PTR(err);
+	if (final_dst)
+		ipv6_addr_copy(&fl->fl6_dst, final_dst);
+	if (want_blackhole) {
+		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
+		if (err == -EREMOTE)
+			err = ip6_dst_blackhole(sk, &dst, fl);
+		if (err)
+			return ERR_PTR(err);
+	} else {
+		err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
+		if (err)
+			return ERR_PTR(err);
+	}
+	return dst;
 }
-EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup);
+EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
 static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 364e86683388..dc29b07caf42 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -856,20 +856,11 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		fl.oif = np->mcast_oif;
 	security_sk_classify_flow(sk, &fl);
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
-	if (err)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
 		goto out;
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
-	if (err < 0) {
-		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, &fl);
-		if (err < 0)
-			goto out;
 	}
-
 	if (hlimit < 0) {
 		if (ipv6_addr_is_multicast(&fl.fl6_dst))
 			hlimit = np->mcast_hops;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 09fd34f0dbf2..0b4cf350631b 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -243,12 +243,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
 		fl.fl_ip_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, &fl);
-		if (ip6_dst_lookup(sk, &dst, &fl))
-			goto out_free;
 
-		if (final_p)
-			ipv6_addr_copy(&fl.fl6_dst, final_p);
-		if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
+		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		if (IS_ERR(dst))
 			goto out_free;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 1d0ab5570904..e59a31c48baf 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -255,18 +255,10 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	security_sk_classify_flow(sk, &fl);
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
-	if (err)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
 		goto failure;
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
-	if (err < 0) {
-		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, &fl);
-		if (err < 0)
-			goto failure;
 	}
 
 	if (saddr == NULL) {
@@ -385,7 +377,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == ICMPV6_PKT_TOOBIG) {
-		struct dst_entry *dst = NULL;
+		struct dst_entry *dst;
 
 		if (sock_owned_by_user(sk))
 			goto out;
@@ -413,13 +405,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			fl.fl_ip_sport = inet->inet_sport;
 			security_skb_classify_flow(skb, &fl);
 
-			if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
-				sk->sk_err_soft = -err;
-				goto out;
-			}
-
-			if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) {
-				sk->sk_err_soft = -err;
+			dst = ip6_dst_lookup_flow(sk, &fl, NULL, false);
+			if (IS_ERR(dst)) {
+				sk->sk_err_soft = -PTR_ERR(dst);
 				goto out;
 			}
 
@@ -496,7 +484,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	struct in6_addr * final_p, final;
 	struct flowi fl;
 	struct dst_entry *dst;
-	int err = -1;
+	int err;
 
 	memset(&fl, 0, sizeof(fl));
 	fl.proto = IPPROTO_TCP;
@@ -512,15 +500,13 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	opt = np->opt;
 	final_p = fl6_update_dst(&fl, opt, &final);
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
-	if (err)
+	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
 		goto done;
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-	if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
-		goto done;
-
+	}
 	skb = tcp_make_synack(sk, dst, req, rvp);
+	err = -ENOMEM;
 	if (skb) {
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
@@ -1079,15 +1065,14 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) {
-		if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) {
-			skb_dst_set(buff, dst);
-			ip6_xmit(ctl_sk, buff, &fl, NULL);
-			TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
-			if (rst)
-				TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
-			return;
-		}
+	dst = ip6_dst_lookup_flow(ctl_sk, &fl, NULL, false);
+	if (!IS_ERR(dst)) {
+		skb_dst_set(buff, dst);
+		ip6_xmit(ctl_sk, buff, &fl, NULL);
+		TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
+		if (rst)
+			TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
+		return;
 	}
 
 	kfree_skb(buff);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a419a787eb69..d86d7f67a597 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1125,18 +1125,11 @@ do_udp_sendmsg:
 
 	security_sk_classify_flow(sk, &fl);
 
-	err = ip6_sk_dst_lookup(sk, &dst, &fl);
-	if (err)
+	dst = ip6_sk_dst_lookup_flow(sk, &fl, final_p, true);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		dst = NULL;
 		goto out;
-	if (final_p)
-		ipv6_addr_copy(&fl.fl6_dst, final_p);
-
-	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
-	if (err < 0) {
-		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, &fl);
-		if (err < 0)
-			goto out;
 	}
 
 	if (hlimit < 0) {
-- 
cgit v1.2.3


From abdf7e7239da270e68262728f125ea94b9b7d42d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:15:24 -0800
Subject: ipv4: Can final ip_route_connect() arg to boolean "can_sleep".

Since that's what the current vague "flags" thing means.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 4 ++--
 net/dccp/ipv4.c     | 2 +-
 net/ipv4/af_inet.c  | 2 +-
 net/ipv4/datagram.c | 2 +-
 net/ipv4/tcp_ipv4.c | 2 +-
 net/l2tp/l2tp_ip.c  | 2 +-
 6 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index b3f89ad04e0b..5e0826d1c0e0 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -168,7 +168,7 @@ static inline char rt_tos2priority(u8 tos)
 static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 				   __be32 src, u32 tos, int oif, u8 protocol,
 				   __be16 sport, __be16 dport, struct sock *sk,
-				   int flags)
+				   bool can_sleep)
 {
 	struct flowi fl = { .oif = oif,
 			    .mark = sk->sk_mark,
@@ -196,7 +196,7 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 		*rp = NULL;
 	}
 	security_sk_classify_flow(sk, &fl);
-	return ip_route_output_flow(net, rp, &fl, sk, flags);
+	return ip_route_output_flow(net, rp, &fl, sk, can_sleep ? 1 : 0);
 }
 
 static inline int ip_route_newports(struct rtable **rp, u8 protocol,
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 937989199c80..8372d5c571a0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -69,7 +69,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
 			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			       IPPROTO_DCCP,
-			       orig_sport, orig_dport, sk, 1);
+			       orig_sport, orig_dport, sk, true);
 	if (tmp < 0)
 		return tmp;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7ceb80447631..d16687db9713 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1115,7 +1115,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 			       RT_CONN_FLAGS(sk),
 			       sk->sk_bound_dev_if,
 			       sk->sk_protocol,
-			       inet->inet_sport, inet->inet_dport, sk, 0);
+			       inet->inet_sport, inet->inet_dport, sk, false);
 	if (err)
 		return err;
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 174be6caa5c8..eaee1edd2dd7 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -49,7 +49,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr,
 			       RT_CONN_FLAGS(sk), oif,
 			       sk->sk_protocol,
-			       inet->inet_sport, usin->sin_port, sk, 1);
+			       inet->inet_sport, usin->sin_port, sk, true);
 	if (err) {
 		if (err == -ENETUNREACH)
 			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 27a0cc8cc888..05bc6d9455fc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -173,7 +173,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
 			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			       IPPROTO_TCP,
-			       orig_sport, orig_dport, sk, 1);
+			       orig_sport, orig_dport, sk, true);
 	if (tmp < 0) {
 		if (tmp == -ENETUNREACH)
 			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 110efb704c9b..28e876a6b1dd 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -323,7 +323,7 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	rc = ip_route_connect(&rt, lsa->l2tp_addr.s_addr, saddr,
 			      RT_CONN_FLAGS(sk), oif,
 			      IPPROTO_L2TP,
-			      0, 0, sk, 1);
+			      0, 0, sk, true);
 	if (rc) {
 		if (rc == -ENETUNREACH)
 			IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES);
-- 
cgit v1.2.3


From 420d44daa7aa1cc847e9e527f0a27a9ce61768ca Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:19:23 -0800
Subject: ipv4: Make final arg to ip_route_output_flow to be boolean
 "can_sleep"

Since that is what the current vague "flags" argument means.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/cxgb3/iwch_cm.c | 2 +-
 drivers/infiniband/hw/cxgb4/cm.c      | 2 +-
 drivers/scsi/cxgbi/libcxgbi.c         | 2 +-
 include/net/route.h                   | 6 +++---
 net/dccp/ipv4.c                       | 2 +-
 net/ipv4/af_inet.c                    | 2 +-
 net/ipv4/inet_connection_sock.c       | 2 +-
 net/ipv4/ip_output.c                  | 2 +-
 net/ipv4/raw.c                        | 2 +-
 net/ipv4/route.c                      | 6 +++---
 net/ipv4/udp.c                        | 2 +-
 net/l2tp/l2tp_ip.c                    | 2 +-
 12 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index d02dcc6e5963..c7f776c8b2b8 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -354,7 +354,7 @@ static struct rtable *find_route(struct t3cdev *dev, __be32 local_ip,
 			  }
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0))
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, false))
 		return NULL;
 	return rt;
 }
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 8b00e6c46f01..5542c994338d 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -331,7 +331,7 @@ static struct rtable *find_route(struct c4iw_dev *dev, __be32 local_ip,
 			  }
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0))
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, false))
 		return NULL;
 	return rt;
 }
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index d2ad3d676724..fabca75ac2f2 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -470,7 +470,7 @@ static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
 			}
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0))
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, false))
 		return NULL;
 
 	return rt;
diff --git a/include/net/route.h b/include/net/route.h
index 5e0826d1c0e0..6de4333d6002 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -120,7 +120,7 @@ extern void		rt_cache_flush(struct net *net, int how);
 extern void		rt_cache_flush_batch(struct net *net);
 extern int		__ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
 extern int		ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
-extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);
+extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, bool can_sleep);
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin, bool noref);
@@ -196,7 +196,7 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 		*rp = NULL;
 	}
 	security_sk_classify_flow(sk, &fl);
-	return ip_route_output_flow(net, rp, &fl, sk, can_sleep ? 1 : 0);
+	return ip_route_output_flow(net, rp, &fl, sk, can_sleep);
 }
 
 static inline int ip_route_newports(struct rtable **rp, u8 protocol,
@@ -220,7 +220,7 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol,
 		ip_rt_put(*rp);
 		*rp = NULL;
 		security_sk_classify_flow(sk, &fl);
-		return ip_route_output_flow(sock_net(sk), rp, &fl, sk, 0);
+		return ip_route_output_flow(sock_net(sk), rp, &fl, sk, false);
 	}
 	return 0;
 }
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8372d5c571a0..3d4b82f6adfd 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -475,7 +475,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 			  };
 
 	security_skb_classify_flow(skb, &fl);
-	if (ip_route_output_flow(net, &rt, &fl, sk, 0)) {
+	if (ip_route_output_flow(net, &rt, &fl, sk, false)) {
 		IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
 		return NULL;
 	}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d16687db9713..7d90fe0ee5a6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1174,7 +1174,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	};
 
 	security_sk_classify_flow(sk, &fl);
-	err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0);
+	err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, false);
 }
 	if (!err)
 		sk_setup_caps(sk, &rt->dst);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 97e5fb765265..0caeb69de4b1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -369,7 +369,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct net *net = sock_net(sk);
 
 	security_req_classify_flow(req, &fl);
-	if (ip_route_output_flow(net, &rt, &fl, sk, 0))
+	if (ip_route_output_flow(net, &rt, &fl, sk, false))
 		goto no_route;
 	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
 		goto route_err;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 460308c35028..e6905c562fb7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -355,7 +355,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 			 * itself out.
 			 */
 			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0))
+			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, false))
 				goto no_route;
 		}
 		sk_setup_caps(sk, &rt->dst);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6390ba299b3d..e1857658964d 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -563,7 +563,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 1);
+		err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, true);
 	}
 	if (err)
 		goto done;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 52b077d45208..1ac3ecaf36e8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2720,7 +2720,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi
 }
 
 int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
-			 struct sock *sk, int flags)
+			 struct sock *sk, bool can_sleep)
 {
 	int err;
 
@@ -2733,7 +2733,7 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
 		err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk,
-				    flags ? XFRM_LOOKUP_WAIT : 0);
+				    can_sleep ? XFRM_LOOKUP_WAIT : 0);
 		if (err == -EREMOTE)
 			err = ipv4_dst_blackhole(net, rp, flp);
 
@@ -2746,7 +2746,7 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
 {
-	return ip_route_output_flow(net, rp, flp, NULL, 0);
+	return ip_route_output_flow(net, rp, flp, NULL, false);
 }
 EXPORT_SYMBOL(ip_route_output_key);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8155d6eda376..790187b5c308 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -920,7 +920,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		struct net *net = sock_net(sk);
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(net, &rt, &fl, sk, 1);
+		err = ip_route_output_flow(net, &rt, &fl, sk, true);
 		if (err) {
 			if (err == -ENETUNREACH)
 				IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 28e876a6b1dd..7744a8e4b4c6 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -489,7 +489,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 			 * itself out.
 			 */
 			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0))
+			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, false))
 				goto no_route;
 		}
 		sk_setup_caps(sk, &rt->dst);
-- 
cgit v1.2.3


From 5df65e5567a497a28067019b8ff08f98fb026629 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:22:19 -0800
Subject: net: Add FLOWI_FLAG_CAN_SLEEP.

And set is in contexts where the route resolution can sleep.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h    | 1 +
 include/net/route.h   | 2 ++
 net/ipv4/raw.c        | 3 ++-
 net/ipv4/udp.c        | 6 ++++--
 net/ipv6/ip6_output.c | 2 ++
 5 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index f2080e65276d..fd0413873b8e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -50,6 +50,7 @@ struct flowi {
 	__u8	flags;
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_PRECOW_METRICS	0x02
+#define FLOWI_FLAG_CAN_SLEEP		0x04
 	union {
 		struct {
 			__be16	sport;
diff --git a/include/net/route.h b/include/net/route.h
index 6de4333d6002..1be5c05a0905 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -185,6 +185,8 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 		fl.flags |= FLOWI_FLAG_ANYSRC;
 	if (protocol == IPPROTO_TCP)
 		fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
+	if (can_sleep)
+		fl.flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	if (!dst || !src) {
 		err = __ip_route_output_key(net, rp, &fl);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index e1857658964d..e8e8613bcbcc 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -555,7 +555,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				    .fl4_tos = tos,
 				    .proto = inet->hdrincl ? IPPROTO_RAW :
 							     sk->sk_protocol,
-				  };
+				    .flags = FLOWI_FLAG_CAN_SLEEP,
+		};
 		if (!inet->hdrincl) {
 			err = raw_probe_proto_opt(&fl, msg);
 			if (err)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 790187b5c308..c6bcc93debd5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -914,9 +914,11 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				    .fl4_src = saddr,
 				    .fl4_tos = tos,
 				    .proto = sk->sk_protocol,
-				    .flags = inet_sk_flowi_flags(sk),
+				    .flags = (inet_sk_flowi_flags(sk) |
+					      FLOWI_FLAG_CAN_SLEEP),
 				    .fl_ip_sport = inet->inet_sport,
-				    .fl_ip_dport = dport };
+				    .fl_ip_dport = dport
+		};
 		struct net *net = sock_net(sk);
 
 		security_sk_classify_flow(sk, &fl);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 28209b2d254d..77b1942f335b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1026,6 +1026,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
 	if (want_blackhole) {
+		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
 		if (err == -EREMOTE)
 			err = ip6_dst_blackhole(sk, &dst, fl);
@@ -1070,6 +1071,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
 	if (want_blackhole) {
+		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
 		if (err == -EREMOTE)
 			err = ip6_dst_blackhole(sk, &dst, fl);
-- 
cgit v1.2.3


From 273447b352e69c327efdecfd6e1d6fe3edbdcd14 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:27:04 -0800
Subject: ipv4: Kill can_sleep arg to ip_route_output_flow()

This boolean state is now available in the flow flags.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/cxgb3/iwch_cm.c | 2 +-
 drivers/infiniband/hw/cxgb4/cm.c      | 2 +-
 drivers/scsi/cxgbi/libcxgbi.c         | 2 +-
 include/net/route.h                   | 6 +++---
 net/dccp/ipv4.c                       | 2 +-
 net/ipv4/af_inet.c                    | 2 +-
 net/ipv4/inet_connection_sock.c       | 2 +-
 net/ipv4/ip_output.c                  | 2 +-
 net/ipv4/raw.c                        | 2 +-
 net/ipv4/route.c                      | 7 ++++---
 net/ipv4/udp.c                        | 2 +-
 net/l2tp/l2tp_ip.c                    | 2 +-
 12 files changed, 17 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index c7f776c8b2b8..e654285aa6ba 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -354,7 +354,7 @@ static struct rtable *find_route(struct t3cdev *dev, __be32 local_ip,
 			  }
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, false))
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL))
 		return NULL;
 	return rt;
 }
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 5542c994338d..7e0484f18db5 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -331,7 +331,7 @@ static struct rtable *find_route(struct c4iw_dev *dev, __be32 local_ip,
 			  }
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, false))
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL))
 		return NULL;
 	return rt;
 }
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index fabca75ac2f2..261aa817bdd5 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -470,7 +470,7 @@ static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
 			}
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, false))
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL))
 		return NULL;
 
 	return rt;
diff --git a/include/net/route.h b/include/net/route.h
index 1be5c05a0905..923e670586d4 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -120,7 +120,7 @@ extern void		rt_cache_flush(struct net *net, int how);
 extern void		rt_cache_flush_batch(struct net *net);
 extern int		__ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
 extern int		ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
-extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, bool can_sleep);
+extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk);
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin, bool noref);
@@ -198,7 +198,7 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 		*rp = NULL;
 	}
 	security_sk_classify_flow(sk, &fl);
-	return ip_route_output_flow(net, rp, &fl, sk, can_sleep);
+	return ip_route_output_flow(net, rp, &fl, sk);
 }
 
 static inline int ip_route_newports(struct rtable **rp, u8 protocol,
@@ -222,7 +222,7 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol,
 		ip_rt_put(*rp);
 		*rp = NULL;
 		security_sk_classify_flow(sk, &fl);
-		return ip_route_output_flow(sock_net(sk), rp, &fl, sk, false);
+		return ip_route_output_flow(sock_net(sk), rp, &fl, sk);
 	}
 	return 0;
 }
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 3d4b82f6adfd..a8ff95502081 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -475,7 +475,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 			  };
 
 	security_skb_classify_flow(skb, &fl);
-	if (ip_route_output_flow(net, &rt, &fl, sk, false)) {
+	if (ip_route_output_flow(net, &rt, &fl, sk)) {
 		IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
 		return NULL;
 	}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7d90fe0ee5a6..44513bb8ac2e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1174,7 +1174,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	};
 
 	security_sk_classify_flow(sk, &fl);
-	err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, false);
+	err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk);
 }
 	if (!err)
 		sk_setup_caps(sk, &rt->dst);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0caeb69de4b1..7f85d4aec26a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -369,7 +369,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct net *net = sock_net(sk);
 
 	security_req_classify_flow(req, &fl);
-	if (ip_route_output_flow(net, &rt, &fl, sk, false))
+	if (ip_route_output_flow(net, &rt, &fl, sk))
 		goto no_route;
 	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
 		goto route_err;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e6905c562fb7..68dbe2d93d9d 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -355,7 +355,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 			 * itself out.
 			 */
 			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, false))
+			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk))
 				goto no_route;
 		}
 		sk_setup_caps(sk, &rt->dst);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index e8e8613bcbcc..d7a2d1eaec09 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -564,7 +564,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, true);
+		err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk);
 	}
 	if (err)
 		goto done;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1ac3ecaf36e8..78462658fccb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2720,7 +2720,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi
 }
 
 int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
-			 struct sock *sk, bool can_sleep)
+			 struct sock *sk)
 {
 	int err;
 
@@ -2733,7 +2733,8 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
 		err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk,
-				    can_sleep ? XFRM_LOOKUP_WAIT : 0);
+				    ((flp->flags & FLOWI_FLAG_CAN_SLEEP) ?
+				     XFRM_LOOKUP_WAIT : 0));
 		if (err == -EREMOTE)
 			err = ipv4_dst_blackhole(net, rp, flp);
 
@@ -2746,7 +2747,7 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
 {
-	return ip_route_output_flow(net, rp, flp, NULL, false);
+	return ip_route_output_flow(net, rp, flp, NULL);
 }
 EXPORT_SYMBOL(ip_route_output_key);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c6bcc93debd5..ed9a5b7bee53 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -922,7 +922,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		struct net *net = sock_net(sk);
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(net, &rt, &fl, sk, true);
+		err = ip_route_output_flow(net, &rt, &fl, sk);
 		if (err) {
 			if (err == -ENETUNREACH)
 				IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 7744a8e4b4c6..5381cebe516d 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -489,7 +489,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 			 * itself out.
 			 */
 			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, false))
+			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk))
 				goto no_route;
 		}
 		sk_setup_caps(sk, &rt->dst);
-- 
cgit v1.2.3


From a1414715f0ac905fb4b3a158ff6548d37bbe6165 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:32:04 -0800
Subject: ipv6: Change final dst lookup arg name to "can_sleep"

Since it indicates whether we are invoked from a sleepable
context or not.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h    |  4 ++--
 net/ipv6/ip6_output.c | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 1fc5631cf1a2..8f78aace0a9d 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -515,11 +515,11 @@ extern int			ip6_dst_lookup(struct sock *sk,
 extern struct dst_entry *	ip6_dst_lookup_flow(struct sock *sk,
 						    struct flowi *fl,
 						    const struct in6_addr *final_dst,
-						    bool want_blackhole);
+						    bool can_sleep);
 extern struct dst_entry *	ip6_sk_dst_lookup_flow(struct sock *sk,
 						       struct flowi *fl,
 						       const struct in6_addr *final_dst,
-						       bool want_blackhole);
+						       bool can_sleep);
 extern int			ip6_dst_blackhole(struct sock *sk,
 						  struct dst_entry **dst,
 						  struct flowi *fl);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 77b1942f335b..b5f8769dbdf4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1006,7 +1006,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	@sk: socket which provides route info
  *	@fl: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
- *	@want_blackhole: IPSEC blackhole handling desired
+ *	@can_sleep: we are in a sleepable context
  *
  *	This function performs a route lookup on the given flow.
  *
@@ -1015,7 +1015,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  */
 struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 				      const struct in6_addr *final_dst,
-				      bool want_blackhole)
+				      bool can_sleep)
 {
 	struct dst_entry *dst = NULL;
 	int err;
@@ -1025,7 +1025,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		return ERR_PTR(err);
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
-	if (want_blackhole) {
+	if (can_sleep) {
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
 		if (err == -EREMOTE)
@@ -1046,7 +1046,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *	@sk: socket which provides the dst cache and route info
  *	@fl: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
- *	@want_blackhole: IPSEC blackhole handling desired
+ *	@can_sleep: we are in a sleepable context
  *
  *	This function performs a route lookup on the given flow with the
  *	possibility of using the cached route in the socket if it is valid.
@@ -1058,7 +1058,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  */
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 					 const struct in6_addr *final_dst,
-					 bool want_blackhole)
+					 bool can_sleep)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
 	int err;
@@ -1070,7 +1070,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		return ERR_PTR(err);
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
-	if (want_blackhole) {
+	if (can_sleep) {
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
 		if (err == -EREMOTE)
-- 
cgit v1.2.3


From 80c0bc9e37adfc892af82cb6aa8cace79f8a96cb Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:36:37 -0800
Subject: xfrm: Kill XFRM_LOOKUP_WAIT flag.

This can be determined from the flow flags instead.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h      | 3 +--
 net/decnet/dn_route.c  | 5 +++--
 net/ipv4/route.c       | 4 +---
 net/ipv6/ip6_output.c  | 4 ++--
 net/xfrm/xfrm_policy.c | 2 +-
 5 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 4fedffd7c56f..15d67c8d3ce8 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -421,8 +421,7 @@ extern void		dst_init(void);
 
 /* Flags for xfrm_lookup flags argument. */
 enum {
-	XFRM_LOOKUP_WAIT = 1 << 0,
-	XFRM_LOOKUP_ICMP = 1 << 1,
+	XFRM_LOOKUP_ICMP = 1 << 0,
 };
 
 struct flowi;
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 06c054d5ccba..0877147d2167 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1233,8 +1233,9 @@ int dn_route_output_sock(struct dst_entry **pprt, struct flowi *fl, struct sock
 
 	err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD);
 	if (err == 0 && fl->proto) {
-		err = xfrm_lookup(&init_net, pprt, fl, sk,
-				 (flags & MSG_DONTWAIT) ? 0 : XFRM_LOOKUP_WAIT);
+		if (!(flags & MSG_DONTWAIT))
+			fl->flags |= FLOWI_FLAG_CAN_SLEEP;
+		err = xfrm_lookup(&init_net, pprt, fl, sk, 0);
 	}
 	return err;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 78462658fccb..23d205043d92 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2732,9 +2732,7 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
 			flp->fl4_src = (*rp)->rt_src;
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
-		err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk,
-				    ((flp->flags & FLOWI_FLAG_CAN_SLEEP) ?
-				     XFRM_LOOKUP_WAIT : 0));
+		err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk, 0);
 		if (err == -EREMOTE)
 			err = ipv4_dst_blackhole(net, rp, flp);
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b5f8769dbdf4..faf7b9d1d536 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1027,7 +1027,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
 	if (can_sleep) {
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
-		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
+		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
 		if (err == -EREMOTE)
 			err = ip6_dst_blackhole(sk, &dst, fl);
 		if (err)
@@ -1072,7 +1072,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
 	if (can_sleep) {
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
-		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, XFRM_LOOKUP_WAIT);
+		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
 		if (err == -EREMOTE)
 			err = ip6_dst_blackhole(sk, &dst, fl);
 		if (err)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 41a91d27d3ea..f4c7467a614e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1831,7 +1831,7 @@ restart:
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 			return -EREMOTE;
 		}
-		if (flags & XFRM_LOOKUP_WAIT) {
+		if (fl->flags & FLOWI_FLAG_CAN_SLEEP) {
 			DECLARE_WAITQUEUE(wait, current);
 
 			add_wait_queue(&net->xfrm.km_waitq, &wait);
-- 
cgit v1.2.3


From 69ead7afdf6028184f713a77376ee26f8aaafdcd Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:45:33 -0800
Subject: ipv6: Normalize arguments to ip6_dst_blackhole().

Return a dst pointer which is potentitally error encoded.

Don't pass original dst pointer by reference, pass a struct net
instead of a socket, and elide the flow argument since it is
unnecessary.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h    |  5 ++---
 net/ipv6/ip6_output.c |  4 ++--
 net/ipv6/route.c      | 12 +++++-------
 3 files changed, 9 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8f78aace0a9d..5d125c1293a9 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -520,9 +520,8 @@ extern struct dst_entry *	ip6_sk_dst_lookup_flow(struct sock *sk,
 						       struct flowi *fl,
 						       const struct in6_addr *final_dst,
 						       bool can_sleep);
-extern int			ip6_dst_blackhole(struct sock *sk,
-						  struct dst_entry **dst,
-						  struct flowi *fl);
+extern struct dst_entry *	ip6_dst_blackhole(struct net *net,
+						  struct dst_entry *orig_dst);
 
 /*
  *	skb processing functions
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index faf7b9d1d536..ac16f3b2a029 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1029,7 +1029,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
 		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, fl);
+			return ip6_dst_blackhole(sock_net(sk), dst);
 		if (err)
 			return ERR_PTR(err);
 	} else {
@@ -1074,7 +1074,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
 		if (err == -EREMOTE)
-			err = ip6_dst_blackhole(sk, &dst, fl);
+			return ip6_dst_blackhole(sock_net(sk), dst);
 		if (err)
 			return ERR_PTR(err);
 	} else {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7e9443f835f9..cf6fdeabb6f2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -870,11 +870,10 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
 
 EXPORT_SYMBOL(ip6_route_output);
 
-int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl)
+struct dst_entry *ip6_dst_blackhole(struct net *net, struct dst_entry *dst_orig)
 {
-	struct rt6_info *ort = (struct rt6_info *) *dstp;
-	struct rt6_info *rt = (struct rt6_info *)
-		dst_alloc(&ip6_dst_blackhole_ops, 1);
+	struct rt6_info *rt = dst_alloc(&ip6_dst_blackhole_ops, 1);
+	struct rt6_info *ort = (struct rt6_info *) dst_orig;
 	struct dst_entry *new = NULL;
 
 	if (rt) {
@@ -905,9 +904,8 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl
 		dst_free(new);
 	}
 
-	dst_release(*dstp);
-	*dstp = new;
-	return new ? 0 : -ENOMEM;
+	dst_release(dst_orig);
+	return new ? new : ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_blackhole);
 
-- 
cgit v1.2.3


From 2774c131b1d19920b4587db1cfbd6f0750ad1f15 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 1 Mar 2011 14:59:04 -0800
Subject: xfrm: Handle blackhole route creation via afinfo.

That way we don't have to potentially do this in every xfrm_lookup()
caller.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h       |  8 --------
 include/net/ipv6.h      |  4 ++--
 include/net/route.h     |  1 +
 include/net/xfrm.h      |  1 +
 net/ipv4/route.c        | 20 +++++++-------------
 net/ipv4/xfrm4_policy.c |  1 +
 net/ipv6/ip6_output.c   | 32 ++++++++++----------------------
 net/ipv6/route.c        |  3 +--
 net/ipv6/xfrm6_policy.c |  1 +
 net/xfrm/xfrm_policy.c  | 46 ++++++++++++++++++++++++++--------------------
 10 files changed, 50 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 15d67c8d3ce8..8948452132ad 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -432,17 +432,9 @@ static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
 {
 	return 0;
 } 
-static inline int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-				const struct flowi *fl, struct sock *sk,
-				int flags)
-{
-	return 0;
-}
 #else
 extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
 		       const struct flowi *fl, struct sock *sk, int flags);
-extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-			 const struct flowi *fl, struct sock *sk, int flags);
 #endif
 #endif
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 5d125c1293a9..d6d077d7f2cf 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -520,8 +520,8 @@ extern struct dst_entry *	ip6_sk_dst_lookup_flow(struct sock *sk,
 						       struct flowi *fl,
 						       const struct in6_addr *final_dst,
 						       bool can_sleep);
-extern struct dst_entry *	ip6_dst_blackhole(struct net *net,
-						  struct dst_entry *orig_dst);
+extern struct dst_entry *	ip6_blackhole_route(struct net *net,
+						    struct dst_entry *orig_dst);
 
 /*
  *	skb processing functions
diff --git a/include/net/route.h b/include/net/route.h
index 923e670586d4..707cfc8eccdc 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -121,6 +121,7 @@ extern void		rt_cache_flush_batch(struct net *net);
 extern int		__ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
 extern int		ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
 extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk);
+extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin, bool noref);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index efded23dc4ae..d5dcf3974636 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -280,6 +280,7 @@ struct xfrm_policy_afinfo {
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
 					    const struct flowi *fl);
+	struct dst_entry	*(*blackhole_route)(struct net *net, struct dst_entry *orig);
 };
 
 extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 23d205043d92..e24e4cf2a112 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2675,12 +2675,10 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
 };
 
-
-static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi *flp)
+struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-	struct rtable *ort = *rp;
-	struct rtable *rt = (struct rtable *)
-		dst_alloc(&ipv4_dst_blackhole_ops, 1);
+	struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1);
+	struct rtable *ort = (struct rtable *) dst_orig;
 
 	if (rt) {
 		struct dst_entry *new = &rt->dst;
@@ -2714,9 +2712,9 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi
 		dst_free(new);
 	}
 
-	dst_release(&(*rp)->dst);
-	*rp = rt;
-	return rt ? 0 : -ENOMEM;
+	dst_release(dst_orig);
+
+	return rt ? &rt->dst : ERR_PTR(-ENOMEM);
 }
 
 int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
@@ -2732,11 +2730,7 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
 			flp->fl4_src = (*rp)->rt_src;
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
-		err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk, 0);
-		if (err == -EREMOTE)
-			err = ipv4_dst_blackhole(net, rp, flp);
-
-		return err;
+		return xfrm_lookup(net, (struct dst_entry **)rp, flp, sk, 0);
 	}
 
 	return 0;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 63aa88efdcef..5f0f058dc376 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -234,6 +234,7 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.get_tos =		xfrm4_get_tos,
 	.init_path =		xfrm4_init_path,
 	.fill_dst =		xfrm4_fill_dst,
+	.blackhole_route =	ipv4_blackhole_route,
 };
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ac16f3b2a029..35a4ad90a0f5 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1025,18 +1025,12 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		return ERR_PTR(err);
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
-	if (can_sleep) {
+	if (can_sleep)
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
-		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
-		if (err == -EREMOTE)
-			return ip6_dst_blackhole(sock_net(sk), dst);
-		if (err)
-			return ERR_PTR(err);
-	} else {
-		err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
-		if (err)
-			return ERR_PTR(err);
-	}
+
+	err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
+	if (err)
+		return ERR_PTR(err);
 	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
@@ -1070,18 +1064,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 		return ERR_PTR(err);
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
-	if (can_sleep) {
+	if (can_sleep)
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
-		err = __xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
-		if (err == -EREMOTE)
-			return ip6_dst_blackhole(sock_net(sk), dst);
-		if (err)
-			return ERR_PTR(err);
-	} else {
-		err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
-		if (err)
-			return ERR_PTR(err);
-	}
+
+	err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
+	if (err)
+		return ERR_PTR(err);
 	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cf6fdeabb6f2..053a92ebf2d5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -870,7 +870,7 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
 
 EXPORT_SYMBOL(ip6_route_output);
 
-struct dst_entry *ip6_dst_blackhole(struct net *net, struct dst_entry *dst_orig)
+struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
 	struct rt6_info *rt = dst_alloc(&ip6_dst_blackhole_ops, 1);
 	struct rt6_info *ort = (struct rt6_info *) dst_orig;
@@ -907,7 +907,6 @@ struct dst_entry *ip6_dst_blackhole(struct net *net, struct dst_entry *dst_orig)
 	dst_release(dst_orig);
 	return new ? new : ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL_GPL(ip6_dst_blackhole);
 
 /*
  *	Destination cache support functions
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c128ca1affe3..48ce496802fd 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -274,6 +274,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.get_tos =		xfrm6_get_tos,
 	.init_path =		xfrm6_init_path,
 	.fill_dst =		xfrm6_fill_dst,
+	.blackhole_route =	ip6_blackhole_route,
 };
 
 static int __init xfrm6_policy_init(void)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f4c7467a614e..0248afa11cda 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1735,14 +1735,31 @@ error:
 	return ERR_PTR(err);
 }
 
+static struct dst_entry *make_blackhole(struct net *net, u16 family,
+					struct dst_entry *dst_orig)
+{
+	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	struct dst_entry *ret;
+
+	if (!afinfo) {
+		dst_release(dst_orig);
+		ret = ERR_PTR(-EINVAL);
+	} else {
+		ret = afinfo->blackhole_route(net, dst_orig);
+	}
+	xfrm_policy_put_afinfo(afinfo);
+
+	return ret;
+}
+
 /* Main function: finds/creates a bundle for given flow.
  *
  * At the moment we eat a raw IP route. Mostly to speed up lookups
  * on interfaces with disabled IPsec.
  */
-int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-		  const struct flowi *fl,
-		  struct sock *sk, int flags)
+int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
+		const struct flowi *fl,
+		struct sock *sk, int flags)
 {
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	struct flow_cache_object *flo;
@@ -1829,7 +1846,12 @@ restart:
 			dst_release(dst);
 			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-			return -EREMOTE;
+
+			dst = make_blackhole(net, family, dst_orig);
+			if (IS_ERR(dst))
+				return PTR_ERR(dst);
+			*dst_p = dst;
+			return 0;
 		}
 		if (fl->flags & FLOWI_FLAG_CAN_SLEEP) {
 			DECLARE_WAITQUEUE(wait, current);
@@ -1895,22 +1917,6 @@ dropdst:
 	xfrm_pols_put(pols, drop_pols);
 	return err;
 }
-EXPORT_SYMBOL(__xfrm_lookup);
-
-int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-		const struct flowi *fl,
-		struct sock *sk, int flags)
-{
-	int err = __xfrm_lookup(net, dst_p, fl, sk, flags);
-
-	if (err == -EREMOTE) {
-		dst_release(*dst_p);
-		*dst_p = NULL;
-		err = -EAGAIN;
-	}
-
-	return err;
-}
 EXPORT_SYMBOL(xfrm_lookup);
 
 static inline int
-- 
cgit v1.2.3


From f51b452bed4ae5c20e1f8a790e4ed8663d909a40 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Jan 2011 21:54:50 +0100
Subject: tracing: don't trace the BKL

No reason to trace it when the last user is gone.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 include/trace/events/bkl.h | 61 ----------------------------------------------
 lib/kernel_lock.c          |  7 ------
 2 files changed, 68 deletions(-)
 delete mode 100644 include/trace/events/bkl.h

(limited to 'include')

diff --git a/include/trace/events/bkl.h b/include/trace/events/bkl.h
deleted file mode 100644
index 1af72dc24278..000000000000
--- a/include/trace/events/bkl.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM bkl
-
-#if !defined(_TRACE_BKL_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_BKL_H
-
-#include <linux/tracepoint.h>
-
-TRACE_EVENT(lock_kernel,
-
-	TP_PROTO(const char *func, const char *file, int line),
-
-	TP_ARGS(func, file, line),
-
-	TP_STRUCT__entry(
-		__field(	int,		depth			)
-		__field_ext(	const char *,	func, FILTER_PTR_STRING	)
-		__field_ext(	const char *,	file, FILTER_PTR_STRING	)
-		__field(	int,		line			)
-	),
-
-	TP_fast_assign(
-		/* We want to record the lock_depth after lock is acquired */
-		__entry->depth = current->lock_depth + 1;
-		__entry->func = func;
-		__entry->file = file;
-		__entry->line = line;
-	),
-
-	TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth,
-		  __entry->file, __entry->line, __entry->func)
-);
-
-TRACE_EVENT(unlock_kernel,
-
-	TP_PROTO(const char *func, const char *file, int line),
-
-	TP_ARGS(func, file, line),
-
-	TP_STRUCT__entry(
-		__field(int,		depth		)
-		__field(const char *,	func		)
-		__field(const char *,	file		)
-		__field(int,		line		)
-	),
-
-	TP_fast_assign(
-		__entry->depth = current->lock_depth;
-		__entry->func = func;
-		__entry->file = file;
-		__entry->line = line;
-	),
-
-	TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth,
-		  __entry->file, __entry->line, __entry->func)
-);
-
-#endif /* _TRACE_BKL_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index b135d04aa48a..d80e12265862 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -10,9 +10,6 @@
 #include <linux/semaphore.h>
 #include <linux/smp_lock.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/bkl.h>
-
 /*
  * The 'big kernel lock'
  *
@@ -120,8 +117,6 @@ void __lockfunc _lock_kernel(const char *func, const char *file, int line)
 {
 	int depth = current->lock_depth + 1;
 
-	trace_lock_kernel(func, file, line);
-
 	if (likely(!depth)) {
 		might_sleep();
 		__lock_kernel();
@@ -134,8 +129,6 @@ void __lockfunc _unlock_kernel(const char *func, const char *file, int line)
 	BUG_ON(current->lock_depth < 0);
 	if (likely(--current->lock_depth < 0))
 		__unlock_kernel();
-
-	trace_unlock_kernel(func, file, line);
 }
 
 EXPORT_SYMBOL(_lock_kernel);
-- 
cgit v1.2.3


From 0e0b494ca8c54a7297d0cc549405091019b3b77e Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@suse.de>
Date: Sun, 23 Jan 2011 09:42:50 -0600
Subject: libata: separate error handler into usable components

Right at the moment, the libata error handler is incredibly
monolithic.  This makes it impossible to use from composite drivers
like libsas and ipr which have to handle error themselves in the first
instance.

The essence of the change is to split the monolithic error handler
into two components: one which handles a queue of ata commands for
processing and the other which handles the back end of readying a
port.  This allows the upper error handler fine grained control in
calling libsas functions (and making sure they only get called for ATA
commands whose lower errors have been fixed up).

Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-eh.c | 53 ++++++++++++++++++++++++++++++++++++++++---------
 include/linux/libata.h  |  2 ++
 2 files changed, 46 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 073b88156b3c..df3f3140c9c7 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -587,7 +587,6 @@ static void ata_eh_unload(struct ata_port *ap)
 void ata_scsi_error(struct Scsi_Host *host)
 {
 	struct ata_port *ap = ata_shost_to_port(host);
-	int i;
 	unsigned long flags;
 	LIST_HEAD(eh_work_q);
 
@@ -597,6 +596,34 @@ void ata_scsi_error(struct Scsi_Host *host)
 	list_splice_init(&host->eh_cmd_q, &eh_work_q);
 	spin_unlock_irqrestore(host->host_lock, flags);
 
+	ata_scsi_cmd_error_handler(host, ap, &eh_work_q);
+
+	/* If we timed raced normal completion and there is nothing to
+	   recover nr_timedout == 0 why exactly are we doing error recovery ? */
+	ata_scsi_port_error_handler(host, ap);
+
+	/* finish or retry handled scmd's and clean up */
+	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+
+	DPRINTK("EXIT\n");
+}
+
+/**
+ * ata_scsi_cmd_error_handler - error callback for a list of commands
+ * @host:	scsi host containing the port
+ * @ap:		ATA port within the host
+ * @eh_work_q:	list of commands to process
+ *
+ * process the given list of commands and return those finished to the
+ * ap->eh_done_q.  This function is the first part of the libata error
+ * handler which processes a given list of failed commands.
+ */
+void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
+				struct list_head *eh_work_q)
+{
+	int i;
+	unsigned long flags;
+
 	/* make sure sff pio task is not running */
 	ata_sff_flush_pio_task(ap);
 
@@ -632,7 +659,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 		if (ap->ops->lost_interrupt)
 			ap->ops->lost_interrupt(ap);
 
-		list_for_each_entry_safe(scmd, tmp, &eh_work_q, eh_entry) {
+		list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
 			struct ata_queued_cmd *qc;
 
 			for (i = 0; i < ATA_MAX_QUEUE; i++) {
@@ -676,8 +703,20 @@ void ata_scsi_error(struct Scsi_Host *host)
 	} else
 		spin_unlock_wait(ap->lock);
 
-	/* If we timed raced normal completion and there is nothing to
-	   recover nr_timedout == 0 why exactly are we doing error recovery ? */
+}
+EXPORT_SYMBOL(ata_scsi_cmd_error_handler);
+
+/**
+ * ata_scsi_port_error_handler - recover the port after the commands
+ * @host:	SCSI host containing the port
+ * @ap:		the ATA port
+ *
+ * Handle the recovery of the port @ap after all the commands
+ * have been recovered.
+ */
+void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap)
+{
+	unsigned long flags;
 
 	/* invoke error handler */
 	if (ap->ops->error_handler) {
@@ -766,9 +805,6 @@ void ata_scsi_error(struct Scsi_Host *host)
 		ap->ops->eng_timeout(ap);
 	}
 
-	/* finish or retry handled scmd's and clean up */
-	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
-
 	scsi_eh_flush_done_q(&ap->eh_done_q);
 
 	/* clean up */
@@ -789,9 +825,8 @@ void ata_scsi_error(struct Scsi_Host *host)
 	wake_up_all(&ap->eh_wait_q);
 
 	spin_unlock_irqrestore(ap->lock, flags);
-
-	DPRINTK("EXIT\n");
 }
+EXPORT_SYMBOL_GPL(ata_scsi_port_error_handler);
 
 /**
  *	ata_port_wait_eh - Wait for the currently pending EH to complete
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c9c5d7ad1a2b..9739317c707a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1050,6 +1050,8 @@ extern int ata_scsi_change_queue_depth(struct scsi_device *sdev,
 				       int queue_depth, int reason);
 extern struct ata_device *ata_dev_pair(struct ata_device *adev);
 extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
+extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
+extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q);
 
 extern int ata_cable_40wire(struct ata_port *ap);
 extern int ata_cable_80wire(struct ata_port *ap);
-- 
cgit v1.2.3


From 00dd4998a60599d98b4d6635820a1fbeafa5b021 Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@suse.de>
Date: Sun, 23 Jan 2011 09:44:12 -0600
Subject: libsas: convert to libata new error handler

The conversion is quite complex given that the libata new error
handler has to be hooked into the current libsas timeout and error
handling.  The way this is done is to process all the failed commands
via libsas first, but if they have no underlying sas task (and they're
on a sata device) assume they are destined for the libata error
handler and send them accordingly.

Finally, activate the port recovery of the libata error handler for
each port known to the host.  This is somewhat suboptimal, since that
port may not need recovering, but given the current architecture of
the libata error handler, it's the only way; and the spurious
activation is harmless.

Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/scsi/libsas/sas_ata.c       | 87 ++++++++++++++++++++++++++++++++++---
 drivers/scsi/libsas/sas_scsi_host.c | 14 +++++-
 include/scsi/sas_ata.h              | 22 ++++++++++
 3 files changed, 115 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index e1a395b438ee..8f56d5fbf6ec 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -238,37 +238,43 @@ static bool sas_ata_qc_fill_rtf(struct ata_queued_cmd *qc)
 	return true;
 }
 
-static void sas_ata_phy_reset(struct ata_port *ap)
+static int sas_ata_hard_reset(struct ata_link *link, unsigned int *class,
+			       unsigned long deadline)
 {
+	struct ata_port *ap = link->ap;
 	struct domain_device *dev = ap->private_data;
 	struct sas_internal *i =
 		to_sas_internal(dev->port->ha->core.shost->transportt);
 	int res = TMF_RESP_FUNC_FAILED;
+	int ret = 0;
 
 	if (i->dft->lldd_I_T_nexus_reset)
 		res = i->dft->lldd_I_T_nexus_reset(dev);
 
-	if (res != TMF_RESP_FUNC_COMPLETE)
+	if (res != TMF_RESP_FUNC_COMPLETE) {
 		SAS_DPRINTK("%s: Unable to reset I T nexus?\n", __func__);
+		ret = -EAGAIN;
+	}
 
 	switch (dev->sata_dev.command_set) {
 		case ATA_COMMAND_SET:
 			SAS_DPRINTK("%s: Found ATA device.\n", __func__);
-			ap->link.device[0].class = ATA_DEV_ATA;
+			*class = ATA_DEV_ATA;
 			break;
 		case ATAPI_COMMAND_SET:
 			SAS_DPRINTK("%s: Found ATAPI device.\n", __func__);
-			ap->link.device[0].class = ATA_DEV_ATAPI;
+			*class = ATA_DEV_ATAPI;
 			break;
 		default:
 			SAS_DPRINTK("%s: Unknown SATA command set: %d.\n",
 				    __func__,
 				    dev->sata_dev.command_set);
-			ap->link.device[0].class = ATA_DEV_UNKNOWN;
+			*class = ATA_DEV_UNKNOWN;
 			break;
 	}
 
 	ap->cbl = ATA_CBL_SATA;
+	return ret;
 }
 
 static void sas_ata_post_internal(struct ata_queued_cmd *qc)
@@ -349,7 +355,11 @@ static int sas_ata_scr_read(struct ata_link *link, unsigned int sc_reg_in,
 }
 
 static struct ata_port_operations sas_sata_ops = {
-	.phy_reset		= sas_ata_phy_reset,
+	.prereset		= ata_std_prereset,
+	.softreset		= NULL,
+	.hardreset		= sas_ata_hard_reset,
+	.postreset		= ata_std_postreset,
+	.error_handler		= ata_std_error_handler,
 	.post_internal_cmd	= sas_ata_post_internal,
 	.qc_defer               = ata_std_qc_defer,
 	.qc_prep		= ata_noop_qc_prep,
@@ -781,3 +791,68 @@ int sas_discover_sata(struct domain_device *dev)
 
 	return res;
 }
+
+void sas_ata_strategy_handler(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+
+	shost_for_each_device(sdev, shost) {
+		struct domain_device *ddev = sdev_to_domain_dev(sdev);
+		struct ata_port *ap = ddev->sata_dev.ap;
+
+		if (!dev_is_sata(ddev))
+			continue;
+		
+		ata_port_printk(ap, KERN_DEBUG, "sas eh calling libata port error handler");
+		ata_scsi_port_error_handler(shost, ap);
+	}
+}
+
+int sas_ata_timed_out(struct scsi_cmnd *cmd, struct sas_task *task,
+		      enum blk_eh_timer_return *rtn)
+{
+	struct domain_device *ddev = cmd_to_domain_dev(cmd);
+
+	if (!dev_is_sata(ddev) || task)
+		return 0;
+
+	/* we're a sata device with no task, so this must be a libata
+	 * eh timeout.  Ideally should hook into libata timeout
+	 * handling, but there's no point, it just wants to activate
+	 * the eh thread */
+	*rtn = BLK_EH_NOT_HANDLED;
+	return 1;
+}
+
+int sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q,
+	       struct list_head *done_q)
+{
+	int rtn = 0;
+	struct scsi_cmnd *cmd, *n;
+	struct ata_port *ap;
+
+	do {
+		LIST_HEAD(sata_q);
+
+		ap = NULL;
+		
+		list_for_each_entry_safe(cmd, n, work_q, eh_entry) {
+			struct domain_device *ddev = cmd_to_domain_dev(cmd);
+
+			if (!dev_is_sata(ddev) || TO_SAS_TASK(cmd))
+				continue;
+			if(ap && ap != ddev->sata_dev.ap)
+				continue;
+			ap = ddev->sata_dev.ap;
+			rtn = 1;
+			list_move(&cmd->eh_entry, &sata_q);
+		}
+
+		if (!list_empty(&sata_q)) {
+			ata_port_printk(ap, KERN_DEBUG,"sas eh calling libata cmd error handler\n");
+			ata_scsi_cmd_error_handler(shost, ap, &sata_q);
+		}
+	} while (ap);
+
+	return rtn;
+}
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 9a7aaf5f1311..67758ea8eb7f 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -663,11 +663,16 @@ void sas_scsi_recover_host(struct Scsi_Host *shost)
 	 * scsi_unjam_host does, but we skip scsi_eh_abort_cmds because any
 	 * command we see here has no sas_task and is thus unknown to the HA.
 	 */
-	if (!scsi_eh_get_sense(&eh_work_q, &ha->eh_done_q))
-		scsi_eh_ready_devs(shost, &eh_work_q, &ha->eh_done_q);
+	if (!sas_ata_eh(shost, &eh_work_q, &ha->eh_done_q))
+		if (!scsi_eh_get_sense(&eh_work_q, &ha->eh_done_q))
+			scsi_eh_ready_devs(shost, &eh_work_q, &ha->eh_done_q);
 
 out:
+	/* now link into libata eh --- if we have any ata devices */
+	sas_ata_strategy_handler(shost);
+
 	scsi_eh_flush_done_q(&ha->eh_done_q);
+
 	SAS_DPRINTK("--- Exit %s\n", __func__);
 	return;
 }
@@ -676,6 +681,11 @@ enum blk_eh_timer_return sas_scsi_timed_out(struct scsi_cmnd *cmd)
 {
 	struct sas_task *task = TO_SAS_TASK(cmd);
 	unsigned long flags;
+	enum blk_eh_timer_return rtn; 
+
+	if (sas_ata_timed_out(cmd, task, &rtn))
+		return rtn;
+	
 
 	if (!task) {
 		cmd->request->timeout /= 2;
diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h
index c583193ae929..9c159f74c6d0 100644
--- a/include/scsi/sas_ata.h
+++ b/include/scsi/sas_ata.h
@@ -39,6 +39,11 @@ int sas_ata_init_host_and_port(struct domain_device *found_dev,
 			       struct scsi_target *starget);
 
 void sas_ata_task_abort(struct sas_task *task);
+void sas_ata_strategy_handler(struct Scsi_Host *shost);
+int sas_ata_timed_out(struct scsi_cmnd *cmd, struct sas_task *task,
+		      enum blk_eh_timer_return *rtn);
+int sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q,
+	       struct list_head *done_q);
 
 #else
 
@@ -55,6 +60,23 @@ static inline int sas_ata_init_host_and_port(struct domain_device *found_dev,
 static inline void sas_ata_task_abort(struct sas_task *task)
 {
 }
+
+static inline void sas_ata_strategy_handler(struct Scsi_Host *shost)
+{
+}
+
+static inline int sas_ata_timed_out(struct scsi_cmnd *cmd,
+				    struct sas_task *task,
+				    enum blk_eh_timer_return *rtn)
+{
+	return 0;
+}
+static inline int sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q,
+			     struct list_head *done_q)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _SAS_ATA_H_ */
-- 
cgit v1.2.3


From c10f97b9d8df818e51e6073be1b96454630595c1 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Date: Fri, 4 Feb 2011 22:03:34 +0300
Subject: libata: remove ATA_FLAG_{SRST|SATA_RESET}

These flags are marked as obsolete and the checks for them have been removed
by commit 294440887b32c58d220fb54b73b7a58079b78f20 (libata-sff: kill unused
ata_bus_reset()), so I think it's time to finally get rid of them...

Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/pata_acpi.c       | 2 +-
 drivers/ata/pata_sis.c        | 2 +-
 drivers/ata/sata_sx4.c        | 4 ++--
 drivers/scsi/ipr.c            | 4 ++--
 drivers/scsi/libsas/sas_ata.c | 4 ++--
 include/linux/libata.h        | 2 --
 6 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/pata_acpi.c b/drivers/ata/pata_acpi.c
index c8d47034d5e9..91949d997555 100644
--- a/drivers/ata/pata_acpi.c
+++ b/drivers/ata/pata_acpi.c
@@ -245,7 +245,7 @@ static struct ata_port_operations pacpi_ops = {
 static int pacpi_init_one (struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	static const struct ata_port_info info = {
-		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+		.flags		= ATA_FLAG_SLAVE_POSS,
 
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
diff --git a/drivers/ata/pata_sis.c b/drivers/ata/pata_sis.c
index 60cea13cccce..c04abc393fc5 100644
--- a/drivers/ata/pata_sis.c
+++ b/drivers/ata/pata_sis.c
@@ -593,7 +593,7 @@ static const struct ata_port_info sis_info133 = {
 	.port_ops	= &sis_133_ops,
 };
 const struct ata_port_info sis_info133_for_sata = {
-	.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_SRST,
+	.flags		= ATA_FLAG_SLAVE_POSS,
 	.pio_mask	= ATA_PIO4,
 	/* No MWDMA */
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index bedd5188e5b0..76384d077b2d 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -274,8 +274,8 @@ static const struct ata_port_info pdc_port_info[] = {
 	/* board_20621 */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_SRST | ATA_FLAG_MMIO |
-				  ATA_FLAG_NO_ATAPI | ATA_FLAG_PIO_POLLING,
+				  ATA_FLAG_MMIO | ATA_FLAG_NO_ATAPI |
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 081d14a326fe..6443ce7c41ae 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6219,8 +6219,8 @@ static struct ata_port_operations ipr_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_SATA_RESET |
-	ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA,
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO |
+			  ATA_FLAG_PIO_DMA,
 	.pio_mask	= ATA_PIO4_ONLY,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index fc6bdc51a047..996dbda47141 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -372,8 +372,8 @@ static struct ata_port_operations sas_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_SATA_RESET |
-		ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ,
+	.flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO |
+		 ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ,
 	.pio_mask = ATA_PIO4,
 	.mwdma_mask = ATA_MWDMA2,
 	.udma_mask = ATA_UDMA6,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 9739317c707a..51ec439f75ad 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -181,8 +181,6 @@ enum {
 	ATA_FLAG_SATA		= (1 << 1),
 	ATA_FLAG_NO_LEGACY	= (1 << 2), /* no legacy mode check */
 	ATA_FLAG_MMIO		= (1 << 3), /* use MMIO, not PIO */
-	ATA_FLAG_SRST		= (1 << 4), /* (obsolete) use ATA SRST, not E.D.D. */
-	ATA_FLAG_SATA_RESET	= (1 << 5), /* (obsolete) use COMRESET */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
 	ATA_FLAG_PIO_LBA48	= (1 << 8), /* Host DMA engine is LBA28 only */
-- 
cgit v1.2.3


From 3696df309971b3427cb9cb039138a1732a865a0b Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Date: Fri, 4 Feb 2011 22:04:17 +0300
Subject: libata: remove ATA_FLAG_MMIO

Commit 0d5ff566779f894ca9937231a181eb31e4adff0e (libata: convert to iomap)
removed all checks of ATA_FLAG_MMIO but neglected to remove the flag itself.
Do it now, at last...

Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/ahci.c            |  2 +-
 drivers/ata/ahci.h            |  2 +-
 drivers/ata/libata-acpi.c     |  3 +--
 drivers/ata/pata_at32.c       |  2 +-
 drivers/ata/pata_bf54x.c      |  1 -
 drivers/ata/pata_ixp4xx_cf.c  |  2 +-
 drivers/ata/pata_macio.c      |  3 +--
 drivers/ata/pata_octeon_cf.c  |  4 ++--
 drivers/ata/pata_palmld.c     |  2 +-
 drivers/ata/pata_pdc2027x.c   |  6 ++----
 drivers/ata/pata_pxa.c        |  1 -
 drivers/ata/pata_rb532_cf.c   |  2 +-
 drivers/ata/pata_samsung_cf.c |  1 -
 drivers/ata/pata_scc.c        |  2 +-
 drivers/ata/pdc_adma.c        |  3 +--
 drivers/ata/sata_dwc_460ex.c  |  2 +-
 drivers/ata/sata_fsl.c        |  4 ++--
 drivers/ata/sata_mv.c         |  2 +-
 drivers/ata/sata_nv.c         |  2 +-
 drivers/ata/sata_promise.c    |  1 -
 drivers/ata/sata_qstor.c      |  2 +-
 drivers/ata/sata_sil.c        |  3 +--
 drivers/ata/sata_sil24.c      |  6 +++---
 drivers/ata/sata_svw.c        | 10 ++++------
 drivers/ata/sata_sx4.c        |  3 +--
 drivers/ata/sata_vsc.c        |  3 +--
 drivers/scsi/ipr.c            |  3 +--
 drivers/scsi/libsas/sas_ata.c |  4 ++--
 include/linux/libata.h        |  1 -
 29 files changed, 33 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index b8d96ce37fc9..3a0435181f77 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -176,7 +176,7 @@ static const struct ata_port_info ahci_port_info[] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ | AHCI_HFLAG_NO_MSI |
 				 AHCI_HFLAG_MV_PATA | AHCI_HFLAG_NO_PMP),
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA,
+				  ATA_FLAG_PIO_DMA,
 		.pio_mask	= ATA_PIO4,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 3e606c34f57b..9a323417907e 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -214,7 +214,7 @@ enum {
 	/* ap->flags bits */
 
 	AHCI_FLAG_COMMON		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-					  ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA |
+					  ATA_FLAG_PIO_DMA |
 					  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN |
 					  ATA_FLAG_LPM,
 
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 8b5ea399a4f4..a791b8ce6294 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -660,8 +660,7 @@ static int ata_acpi_filter_tf(struct ata_device *dev,
  * @dev: target ATA device
  * @gtf: raw ATA taskfile register set (0x1f1 - 0x1f7)
  *
- * Outputs ATA taskfile to standard ATA host controller using MMIO
- * or PIO as indicated by the ATA_FLAG_MMIO flag.
+ * Outputs ATA taskfile to standard ATA host controller.
  * Writes the control, feature, nsect, lbal, lbam, and lbah registers.
  * Optionally (ATA_TFLAG_LBA48) writes hob_feature, hob_nsect,
  * hob_lbal, hob_lbam, and hob_lbah.
diff --git a/drivers/ata/pata_at32.c b/drivers/ata/pata_at32.c
index 66ce6a526f27..36f189c7ee8c 100644
--- a/drivers/ata/pata_at32.c
+++ b/drivers/ata/pata_at32.c
@@ -194,7 +194,7 @@ static int __init pata_at32_init_one(struct device *dev,
 	/* Setup ATA bindings */
 	ap->ops	     = &at32_port_ops;
 	ap->pio_mask = PIO_MASK;
-	ap->flags   |= ATA_FLAG_MMIO | ATA_FLAG_SLAVE_POSS;
+	ap->flags   |= ATA_FLAG_SLAVE_POSS;
 
 	/*
 	 * Since all 8-bit taskfile transfers has to go on the lower
diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c
index 7aed5c792597..1086cacf3cf5 100644
--- a/drivers/ata/pata_bf54x.c
+++ b/drivers/ata/pata_bf54x.c
@@ -1455,7 +1455,6 @@ static struct ata_port_operations bfin_pata_ops = {
 static struct ata_port_info bfin_port_info[] = {
 	{
 		.flags		= ATA_FLAG_SLAVE_POSS
-				| ATA_FLAG_MMIO
 				| ATA_FLAG_NO_LEGACY,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= 0,
diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c
index ba54b089f98c..783ec4fc1119 100644
--- a/drivers/ata/pata_ixp4xx_cf.c
+++ b/drivers/ata/pata_ixp4xx_cf.c
@@ -177,7 +177,7 @@ static __devinit int ixp4xx_pata_probe(struct platform_device *pdev)
 
 	ap->ops	= &ixp4xx_port_ops;
 	ap->pio_mask = ATA_PIO4;
-	ap->flags |= ATA_FLAG_MMIO | ATA_FLAG_NO_LEGACY | ATA_FLAG_NO_ATAPI;
+	ap->flags |= ATA_FLAG_NO_LEGACY | ATA_FLAG_NO_ATAPI;
 
 	ixp4xx_setup_port(ap, data, cs0->start, cs1->start);
 
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 75b49d01780b..7f7b883c008e 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -1053,8 +1053,7 @@ static int __devinit pata_macio_common_init(struct pata_macio_priv	*priv,
 	/* Allocate libata host for 1 port */
 	memset(&pinfo, 0, sizeof(struct ata_port_info));
 	pmac_macio_calc_timing_masks(priv, &pinfo);
-	pinfo.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_MMIO |
-				  ATA_FLAG_NO_LEGACY;
+	pinfo.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_LEGACY;
 	pinfo.port_ops		= &pata_macio_ops;
 	pinfo.private_data	= priv;
 
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index fa1b95a9a7ff..18703e2e51c6 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -848,8 +848,8 @@ static int __devinit octeon_cf_probe(struct platform_device *pdev)
 	cf_port->ap = ap;
 	ap->ops = &octeon_cf_ops;
 	ap->pio_mask = ATA_PIO6;
-	ap->flags |= ATA_FLAG_MMIO | ATA_FLAG_NO_LEGACY
-		  | ATA_FLAG_NO_ATAPI | ATA_FLAG_PIO_POLLING;
+	ap->flags |= ATA_FLAG_NO_LEGACY | ATA_FLAG_NO_ATAPI
+ 		  | ATA_FLAG_PIO_POLLING;
 
 	base = cs0 + ocd->base_region_bias;
 	if (!ocd->is16bit) {
diff --git a/drivers/ata/pata_palmld.c b/drivers/ata/pata_palmld.c
index 11fb4ccc74b4..462a5fcebab9 100644
--- a/drivers/ata/pata_palmld.c
+++ b/drivers/ata/pata_palmld.c
@@ -85,7 +85,7 @@ static __devinit int palmld_pata_probe(struct platform_device *pdev)
 	ap = host->ports[0];
 	ap->ops	= &palmld_port_ops;
 	ap->pio_mask = ATA_PIO4;
-	ap->flags |= ATA_FLAG_MMIO | ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_POLLING;
+	ap->flags |= ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_POLLING;
 
 	/* memory mapping voodoo */
 	ap->ioaddr.cmd_addr = mem + 0x10;
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index b18351122525..57ef92ce1a5c 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -150,8 +150,7 @@ static struct ata_port_operations pdc2027x_pata133_ops = {
 static struct ata_port_info pdc2027x_port_info[] = {
 	/* PDC_UDMA_100 */
 	{
-		.flags		= ATA_FLAG_NO_LEGACY | ATA_FLAG_SLAVE_POSS |
-		                  ATA_FLAG_MMIO,
+		.flags		= ATA_FLAG_NO_LEGACY | ATA_FLAG_SLAVE_POSS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA5,
@@ -159,8 +158,7 @@ static struct ata_port_info pdc2027x_port_info[] = {
 	},
 	/* PDC_UDMA_133 */
 	{
-		.flags		= ATA_FLAG_NO_LEGACY | ATA_FLAG_SLAVE_POSS |
-                        	  ATA_FLAG_MMIO,
+		.flags		= ATA_FLAG_NO_LEGACY | ATA_FLAG_SLAVE_POSS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 1898c6ed4b4e..b4ede40f8ae1 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -292,7 +292,6 @@ static int __devinit pxa_ata_probe(struct platform_device *pdev)
 	ap->ops		= &pxa_ata_port_ops;
 	ap->pio_mask	= ATA_PIO4;
 	ap->mwdma_mask	= ATA_MWDMA2;
-	ap->flags	= ATA_FLAG_MMIO;
 
 	ap->ioaddr.cmd_addr	= devm_ioremap(&pdev->dev, cmd_res->start,
 						resource_size(cmd_res));
diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c
index 0ffd631000b7..0365a5d714f6 100644
--- a/drivers/ata/pata_rb532_cf.c
+++ b/drivers/ata/pata_rb532_cf.c
@@ -91,7 +91,7 @@ static void rb532_pata_setup_ports(struct ata_host *ah)
 
 	ap->ops		= &rb532_pata_port_ops;
 	ap->pio_mask	= ATA_PIO4;
-	ap->flags	= ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO;
+	ap->flags	= ATA_FLAG_NO_LEGACY;
 
 	ap->ioaddr.cmd_addr	= info->iobase + RB500_CF_REG_BASE;
 	ap->ioaddr.ctl_addr	= info->iobase + RB500_CF_REG_CTRL;
diff --git a/drivers/ata/pata_samsung_cf.c b/drivers/ata/pata_samsung_cf.c
index 8a51d673e5b2..c446ae6055a3 100644
--- a/drivers/ata/pata_samsung_cf.c
+++ b/drivers/ata/pata_samsung_cf.c
@@ -531,7 +531,6 @@ static int __init pata_s3c_probe(struct platform_device *pdev)
 	}
 
 	ap = host->ports[0];
-	ap->flags |= ATA_FLAG_MMIO;
 	ap->pio_mask = ATA_PIO4;
 
 	if (cpu_type == TYPE_S3C64XX) {
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index 093715c3273a..5eb050086f38 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -959,7 +959,7 @@ static struct ata_port_operations scc_pata_ops = {
 
 static struct ata_port_info scc_port_info[] = {
 	{
-		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_MMIO | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_LEGACY,
 		.pio_mask	= ATA_PIO4,
 		/* No MWDMA */
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index adbe0426c8f0..384f202fbdec 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -167,8 +167,7 @@ static struct ata_port_info adma_port_info[] = {
 	/* board_1841_idx */
 	{
 		.flags		= ATA_FLAG_SLAVE_POSS |
-				  ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO |
-				  ATA_FLAG_PIO_POLLING,
+				  ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4_ONLY,
 		.udma_mask	= ATA_UDMA4,
 		.port_ops	= &adma_ata_ops,
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 843af13606e1..8c37b0e7fad8 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -1619,7 +1619,7 @@ static struct ata_port_operations sata_dwc_ops = {
 static const struct ata_port_info sata_dwc_port_info[] = {
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_NCQ,
+				  ATA_FLAG_NCQ,
 		.pio_mask	= ATA_PIO4,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &sata_dwc_ops,
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index b0214d00d50b..1d70cf714275 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -34,8 +34,8 @@ enum {
 	SATA_FSL_MAX_PRD_DIRECT	= 16,	/* Direct PRDT entries */
 
 	SATA_FSL_HOST_FLAGS	= (ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA |
-				ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN),
+				ATA_FLAG_PIO_DMA | ATA_FLAG_PMP |
+				ATA_FLAG_NCQ | ATA_FLAG_AN),
 
 	SATA_FSL_MAX_CMDS	= SATA_FSL_QUEUE_DEPTH,
 	SATA_FSL_CMD_HDR_SIZE	= 16,	/* 4 DWORDS */
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index bf74a36d3cc3..a2193fc52763 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -161,7 +161,7 @@ enum {
 	MV_FLAG_DUAL_HC		= (1 << 30),  /* two SATA Host Controllers */
 
 	MV_COMMON_FLAGS		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_PIO_POLLING,
+				  ATA_FLAG_PIO_POLLING,
 
 	MV_GEN_I_FLAGS		= MV_COMMON_FLAGS | ATA_FLAG_NO_ATAPI,
 
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 7254e255fd78..cca96e89339d 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -567,7 +567,7 @@ static const struct ata_port_info nv_port_info[] = {
 	/* ADMA */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_NCQ,
+				  ATA_FLAG_NCQ,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index f03ad48273ff..b0cba3cd9361 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -135,7 +135,6 @@ enum {
 	PDC_RESET		= (1 << 11), /* HDMA reset */
 
 	PDC_COMMON_FLAGS	= ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO |
 				  ATA_FLAG_PIO_POLLING,
 
 	/* ap->flags bits */
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index daeebf19a6a9..5e30a7994391 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -156,7 +156,7 @@ static const struct ata_port_info qs_port_info[] = {
 	/* board_2068_idx */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_PIO_POLLING,
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4_ONLY,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &qs_ata_ops,
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 3a4f84219719..0742d3d968e0 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -61,8 +61,7 @@ enum {
 	SIL_FLAG_RERR_ON_DMA_ACT = (1 << 29),
 	SIL_FLAG_MOD15WRITE	= (1 << 30),
 
-	SIL_DFL_PORT_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO,
+	SIL_DFL_PORT_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
 
 	/*
 	 * Controller IDs
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index af41c6fd1254..1ad7b94f0b38 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -245,9 +245,9 @@ enum {
 
 	/* host flags */
 	SIL24_COMMON_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA |
-				  ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA |
-				  ATA_FLAG_AN | ATA_FLAG_PMP,
+				  ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ |
+				  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN |
+				  ATA_FLAG_PMP,
 	SIL24_FLAG_PCIX_IRQ_WOC	= (1 << 24), /* IRQ loss errata on PCI-X */
 
 	IRQ_STAT_4PORTS		= 0xf,
diff --git a/drivers/ata/sata_svw.c b/drivers/ata/sata_svw.c
index 7d9db4aaf07e..adc913a35189 100644
--- a/drivers/ata/sata_svw.c
+++ b/drivers/ata/sata_svw.c
@@ -360,7 +360,7 @@ static const struct ata_port_info k2_port_info[] = {
 	/* chip_svw4 */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | K2_FLAG_NO_ATAPI_DMA,
+				  K2_FLAG_NO_ATAPI_DMA,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
@@ -369,8 +369,7 @@ static const struct ata_port_info k2_port_info[] = {
 	/* chip_svw8 */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | K2_FLAG_NO_ATAPI_DMA |
-				  K2_FLAG_SATA_8_PORTS,
+				  K2_FLAG_NO_ATAPI_DMA | K2_FLAG_SATA_8_PORTS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
@@ -379,7 +378,7 @@ static const struct ata_port_info k2_port_info[] = {
 	/* chip_svw42 */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | K2_FLAG_BAR_POS_3,
+				  K2_FLAG_BAR_POS_3,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
@@ -387,8 +386,7 @@ static const struct ata_port_info k2_port_info[] = {
 	},
 	/* chip_svw43 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 76384d077b2d..d58e656bef70 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -274,8 +274,7 @@ static const struct ata_port_info pdc_port_info[] = {
 	/* board_20621 */
 	{
 		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO | ATA_FLAG_NO_ATAPI |
-				  ATA_FLAG_PIO_POLLING,
+				  ATA_FLAG_NO_ATAPI | ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_vsc.c b/drivers/ata/sata_vsc.c
index e079cf29ed5d..192bdc7d8f6e 100644
--- a/drivers/ata/sata_vsc.c
+++ b/drivers/ata/sata_vsc.c
@@ -340,8 +340,7 @@ static int __devinit vsc_sata_init_one(struct pci_dev *pdev,
 				       const struct pci_device_id *ent)
 {
 	static const struct ata_port_info pi = {
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_MMIO,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 6443ce7c41ae..e437c8ae9d41 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6219,8 +6219,7 @@ static struct ata_port_operations ipr_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO |
-			  ATA_FLAG_PIO_DMA,
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_DMA,
 	.pio_mask	= ATA_PIO4_ONLY,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 996dbda47141..7538b6ffb3fe 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -372,8 +372,8 @@ static struct ata_port_operations sas_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_MMIO |
-		 ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ,
+	.flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_DMA |
+		 ATA_FLAG_NCQ,
 	.pio_mask = ATA_PIO4,
 	.mwdma_mask = ATA_MWDMA2,
 	.udma_mask = ATA_UDMA6,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 51ec439f75ad..0c3d9e144891 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -180,7 +180,6 @@ enum {
 					    /* (doesn't imply presence) */
 	ATA_FLAG_SATA		= (1 << 1),
 	ATA_FLAG_NO_LEGACY	= (1 << 2), /* no legacy mode check */
-	ATA_FLAG_MMIO		= (1 << 3), /* use MMIO, not PIO */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
 	ATA_FLAG_PIO_LBA48	= (1 << 8), /* Host DMA engine is LBA28 only */
-- 
cgit v1.2.3


From 9cbe056f6c467e7395d5aec39aceec47812eb98e Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Date: Fri, 4 Feb 2011 22:05:48 +0300
Subject: libata: remove ATA_FLAG_NO_LEGACY

All checks of ATA_FLAG_NO_LEGACY have been removed by the commits
c791c30670ea61f19eec390124128bf278e854fe ([libata] minor PCI IDE probe
fixes and cleanups) and f0d36efdc624beb3d9e29b9ab9e9537bf0f25d5b (libata:
update libata core layer to use devres), so I think it's time to finally
get rid of this flag...

Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/ahci.c            |  3 +--
 drivers/ata/ahci.h            |  3 +--
 drivers/ata/pata_bf54x.c      |  3 +--
 drivers/ata/pata_ixp4xx_cf.c  |  2 +-
 drivers/ata/pata_macio.c      |  2 +-
 drivers/ata/pata_octeon_cf.c  |  3 +--
 drivers/ata/pata_palmld.c     |  2 +-
 drivers/ata/pata_pdc2027x.c   |  4 ++--
 drivers/ata/pata_rb532_cf.c   |  1 -
 drivers/ata/pata_scc.c        |  2 +-
 drivers/ata/pdc_adma.c        |  3 +--
 drivers/ata/sata_dwc_460ex.c  |  3 +--
 drivers/ata/sata_fsl.c        |  5 ++---
 drivers/ata/sata_mv.c         |  3 +--
 drivers/ata/sata_nv.c         | 14 ++++++--------
 drivers/ata/sata_promise.c    |  3 +--
 drivers/ata/sata_qstor.c      |  3 +--
 drivers/ata/sata_sil.c        |  2 +-
 drivers/ata/sata_sil24.c      |  7 +++----
 drivers/ata/sata_sis.c        |  2 +-
 drivers/ata/sata_svw.c        | 12 +++++-------
 drivers/ata/sata_sx4.c        |  4 ++--
 drivers/ata/sata_uli.c        |  3 +--
 drivers/ata/sata_via.c        |  9 ++++-----
 drivers/ata/sata_vsc.c        |  2 +-
 drivers/scsi/ipr.c            |  2 +-
 drivers/scsi/libsas/sas_ata.c |  3 +--
 include/linux/libata.h        |  1 -
 28 files changed, 43 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 3a0435181f77..6856d877a69b 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -175,8 +175,7 @@ static const struct ata_port_info ahci_port_info[] = {
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ | AHCI_HFLAG_NO_MSI |
 				 AHCI_HFLAG_MV_PATA | AHCI_HFLAG_NO_PMP),
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_PIO_DMA,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA,
 		.pio_mask	= ATA_PIO4,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 9a323417907e..fd75844fb009 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -213,8 +213,7 @@ enum {
 
 	/* ap->flags bits */
 
-	AHCI_FLAG_COMMON		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-					  ATA_FLAG_PIO_DMA |
+	AHCI_FLAG_COMMON		= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
 					  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN |
 					  ATA_FLAG_LPM,
 
diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c
index 1086cacf3cf5..e0b58b8dfe6f 100644
--- a/drivers/ata/pata_bf54x.c
+++ b/drivers/ata/pata_bf54x.c
@@ -1454,8 +1454,7 @@ static struct ata_port_operations bfin_pata_ops = {
 
 static struct ata_port_info bfin_port_info[] = {
 	{
-		.flags		= ATA_FLAG_SLAVE_POSS
-				| ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SLAVE_POSS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= 0,
 		.udma_mask	= 0,
diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c
index 783ec4fc1119..5253b271b3fe 100644
--- a/drivers/ata/pata_ixp4xx_cf.c
+++ b/drivers/ata/pata_ixp4xx_cf.c
@@ -177,7 +177,7 @@ static __devinit int ixp4xx_pata_probe(struct platform_device *pdev)
 
 	ap->ops	= &ixp4xx_port_ops;
 	ap->pio_mask = ATA_PIO4;
-	ap->flags |= ATA_FLAG_NO_LEGACY | ATA_FLAG_NO_ATAPI;
+	ap->flags |= ATA_FLAG_NO_ATAPI;
 
 	ixp4xx_setup_port(ap, data, cs0->start, cs1->start);
 
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 7f7b883c008e..46f589edccdb 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -1053,7 +1053,7 @@ static int __devinit pata_macio_common_init(struct pata_macio_priv	*priv,
 	/* Allocate libata host for 1 port */
 	memset(&pinfo, 0, sizeof(struct ata_port_info));
 	pmac_macio_calc_timing_masks(priv, &pinfo);
-	pinfo.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_LEGACY;
+	pinfo.flags		= ATA_FLAG_SLAVE_POSS;
 	pinfo.port_ops		= &pata_macio_ops;
 	pinfo.private_data	= priv;
 
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index 18703e2e51c6..220ddc90608f 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -848,8 +848,7 @@ static int __devinit octeon_cf_probe(struct platform_device *pdev)
 	cf_port->ap = ap;
 	ap->ops = &octeon_cf_ops;
 	ap->pio_mask = ATA_PIO6;
-	ap->flags |= ATA_FLAG_NO_LEGACY | ATA_FLAG_NO_ATAPI
- 		  | ATA_FLAG_PIO_POLLING;
+	ap->flags |= ATA_FLAG_NO_ATAPI | ATA_FLAG_PIO_POLLING;
 
 	base = cs0 + ocd->base_region_bias;
 	if (!ocd->is16bit) {
diff --git a/drivers/ata/pata_palmld.c b/drivers/ata/pata_palmld.c
index 462a5fcebab9..a2a73d953840 100644
--- a/drivers/ata/pata_palmld.c
+++ b/drivers/ata/pata_palmld.c
@@ -85,7 +85,7 @@ static __devinit int palmld_pata_probe(struct platform_device *pdev)
 	ap = host->ports[0];
 	ap->ops	= &palmld_port_ops;
 	ap->pio_mask = ATA_PIO4;
-	ap->flags |= ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_POLLING;
+	ap->flags |= ATA_FLAG_PIO_POLLING;
 
 	/* memory mapping voodoo */
 	ap->ioaddr.cmd_addr = mem + 0x10;
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index 57ef92ce1a5c..9765ace16921 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -150,7 +150,7 @@ static struct ata_port_operations pdc2027x_pata133_ops = {
 static struct ata_port_info pdc2027x_port_info[] = {
 	/* PDC_UDMA_100 */
 	{
-		.flags		= ATA_FLAG_NO_LEGACY | ATA_FLAG_SLAVE_POSS,
+		.flags		= ATA_FLAG_SLAVE_POSS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA5,
@@ -158,7 +158,7 @@ static struct ata_port_info pdc2027x_port_info[] = {
 	},
 	/* PDC_UDMA_133 */
 	{
-		.flags		= ATA_FLAG_NO_LEGACY | ATA_FLAG_SLAVE_POSS,
+		.flags		= ATA_FLAG_SLAVE_POSS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c
index 0365a5d714f6..baeaf938d55b 100644
--- a/drivers/ata/pata_rb532_cf.c
+++ b/drivers/ata/pata_rb532_cf.c
@@ -91,7 +91,6 @@ static void rb532_pata_setup_ports(struct ata_host *ah)
 
 	ap->ops		= &rb532_pata_port_ops;
 	ap->pio_mask	= ATA_PIO4;
-	ap->flags	= ATA_FLAG_NO_LEGACY;
 
 	ap->ioaddr.cmd_addr	= info->iobase + RB500_CF_REG_BASE;
 	ap->ioaddr.ctl_addr	= info->iobase + RB500_CF_REG_CTRL;
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index 5eb050086f38..88ea9b677b47 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -959,7 +959,7 @@ static struct ata_port_operations scc_pata_ops = {
 
 static struct ata_port_info scc_port_info[] = {
 	{
-		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SLAVE_POSS,
 		.pio_mask	= ATA_PIO4,
 		/* No MWDMA */
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index 384f202fbdec..1111712b3d7d 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -166,8 +166,7 @@ static struct ata_port_operations adma_ata_ops = {
 static struct ata_port_info adma_port_info[] = {
 	/* board_1841_idx */
 	{
-		.flags		= ATA_FLAG_SLAVE_POSS |
-				  ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_POLLING,
+		.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4_ONLY,
 		.udma_mask	= ATA_UDMA4,
 		.port_ops	= &adma_ata_ops,
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 8c37b0e7fad8..712ab5a4922e 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -1618,8 +1618,7 @@ static struct ata_port_operations sata_dwc_ops = {
 
 static const struct ata_port_info sata_dwc_port_info[] = {
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_NCQ,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NCQ,
 		.pio_mask	= ATA_PIO4,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &sata_dwc_ops,
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 1d70cf714275..beef37134a04 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -33,9 +33,8 @@ enum {
 	SATA_FSL_MAX_PRD_USABLE	= SATA_FSL_MAX_PRD - 1,
 	SATA_FSL_MAX_PRD_DIRECT	= 16,	/* Direct PRDT entries */
 
-	SATA_FSL_HOST_FLAGS	= (ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				ATA_FLAG_PIO_DMA | ATA_FLAG_PMP |
-				ATA_FLAG_NCQ | ATA_FLAG_AN),
+	SATA_FSL_HOST_FLAGS	= (ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
+				ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN),
 
 	SATA_FSL_MAX_CMDS	= SATA_FSL_QUEUE_DEPTH,
 	SATA_FSL_CMD_HDR_SIZE	= 16,	/* 4 DWORDS */
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index a2193fc52763..cd40651e9b72 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -160,8 +160,7 @@ enum {
 	/* Host Flags */
 	MV_FLAG_DUAL_HC		= (1 << 30),  /* two SATA Host Controllers */
 
-	MV_COMMON_FLAGS		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_PIO_POLLING,
+	MV_COMMON_FLAGS		= ATA_FLAG_SATA | ATA_FLAG_PIO_POLLING,
 
 	MV_GEN_I_FLAGS		= MV_COMMON_FLAGS | ATA_FLAG_NO_ATAPI,
 
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index cca96e89339d..42344e3c686d 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -539,7 +539,7 @@ struct nv_pi_priv {
 static const struct ata_port_info nv_port_info[] = {
 	/* generic */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -548,7 +548,7 @@ static const struct ata_port_info nv_port_info[] = {
 	},
 	/* nforce2/3 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -557,7 +557,7 @@ static const struct ata_port_info nv_port_info[] = {
 	},
 	/* ck804 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -566,8 +566,7 @@ static const struct ata_port_info nv_port_info[] = {
 	},
 	/* ADMA */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_NCQ,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NCQ,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -576,7 +575,7 @@ static const struct ata_port_info nv_port_info[] = {
 	},
 	/* MCP5x */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
@@ -585,8 +584,7 @@ static const struct ata_port_info nv_port_info[] = {
 	},
 	/* SWNCQ */
 	{
-		.flags	        = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_NCQ,
+		.flags	        = ATA_FLAG_SATA | ATA_FLAG_NCQ,
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index b0cba3cd9361..a004b1e0ea6d 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -134,8 +134,7 @@ enum {
 	PDC_IRQ_DISABLE		= (1 << 10),
 	PDC_RESET		= (1 << 11), /* HDMA reset */
 
-	PDC_COMMON_FLAGS	= ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_PIO_POLLING,
+	PDC_COMMON_FLAGS	= ATA_FLAG_PIO_POLLING,
 
 	/* ap->flags bits */
 	PDC_FLAG_GEN_II		= (1 << 24),
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index 5e30a7994391..c5603265fa58 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -155,8 +155,7 @@ static struct ata_port_operations qs_ata_ops = {
 static const struct ata_port_info qs_port_info[] = {
 	/* board_2068_idx */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_PIO_POLLING,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4_ONLY,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &qs_ata_ops,
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 0742d3d968e0..b42edaaf3a53 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -61,7 +61,7 @@ enum {
 	SIL_FLAG_RERR_ON_DMA_ACT = (1 << 29),
 	SIL_FLAG_MOD15WRITE	= (1 << 30),
 
-	SIL_DFL_PORT_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+	SIL_DFL_PORT_FLAGS	= ATA_FLAG_SATA,
 
 	/*
 	 * Controller IDs
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 1ad7b94f0b38..06c564e55051 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -244,10 +244,9 @@ enum {
 	BID_SIL3131		= 2,
 
 	/* host flags */
-	SIL24_COMMON_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ |
-				  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN |
-				  ATA_FLAG_PMP,
+	SIL24_COMMON_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
+				  ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA |
+				  ATA_FLAG_AN | ATA_FLAG_PMP,
 	SIL24_FLAG_PCIX_IRQ_WOC	= (1 << 24), /* IRQ loss errata on PCI-X */
 
 	IRQ_STAT_4PORTS		= 0xf,
diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
index 2bfe3ae03976..cdcc13e9cf51 100644
--- a/drivers/ata/sata_sis.c
+++ b/drivers/ata/sata_sis.c
@@ -96,7 +96,7 @@ static struct ata_port_operations sis_ops = {
 };
 
 static const struct ata_port_info sis_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+	.flags		= ATA_FLAG_SATA,
 	.pio_mask	= ATA_PIO4,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_svw.c b/drivers/ata/sata_svw.c
index adc913a35189..35eabcf34568 100644
--- a/drivers/ata/sata_svw.c
+++ b/drivers/ata/sata_svw.c
@@ -359,8 +359,7 @@ static struct ata_port_operations k2_sata_ops = {
 static const struct ata_port_info k2_port_info[] = {
 	/* chip_svw4 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  K2_FLAG_NO_ATAPI_DMA,
+		.flags		= ATA_FLAG_SATA | K2_FLAG_NO_ATAPI_DMA,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
@@ -368,8 +367,8 @@ static const struct ata_port_info k2_port_info[] = {
 	},
 	/* chip_svw8 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  K2_FLAG_NO_ATAPI_DMA | K2_FLAG_SATA_8_PORTS,
+		.flags		= ATA_FLAG_SATA | K2_FLAG_NO_ATAPI_DMA |
+				  K2_FLAG_SATA_8_PORTS,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
@@ -377,8 +376,7 @@ static const struct ata_port_info k2_port_info[] = {
 	},
 	/* chip_svw42 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  K2_FLAG_BAR_POS_3,
+		.flags		= ATA_FLAG_SATA | K2_FLAG_BAR_POS_3,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
@@ -386,7 +384,7 @@ static const struct ata_port_info k2_port_info[] = {
 	},
 	/* chip_svw43 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index d58e656bef70..8fd3b7252bda 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -273,8 +273,8 @@ static struct ata_port_operations pdc_20621_ops = {
 static const struct ata_port_info pdc_port_info[] = {
 	/* board_20621 */
 	{
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_NO_ATAPI | ATA_FLAG_PIO_POLLING,
+		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_ATAPI |
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_uli.c b/drivers/ata/sata_uli.c
index b8578c32d344..235be717a713 100644
--- a/drivers/ata/sata_uli.c
+++ b/drivers/ata/sata_uli.c
@@ -88,8 +88,7 @@ static struct ata_port_operations uli_ops = {
 };
 
 static const struct ata_port_info uli_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-			  ATA_FLAG_IGN_SIMPLEX,
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_IGN_SIMPLEX,
 	.pio_mask       = ATA_PIO4,
 	.udma_mask      = ATA_UDMA6,
 	.port_ops       = &uli_ops,
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index 8b677bbf2d37..21242c5709a0 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -148,7 +148,7 @@ static struct ata_port_operations vt8251_ops = {
 };
 
 static const struct ata_port_info vt6420_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+	.flags		= ATA_FLAG_SATA,
 	.pio_mask	= ATA_PIO4,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
@@ -156,7 +156,7 @@ static const struct ata_port_info vt6420_port_info = {
 };
 
 static struct ata_port_info vt6421_sport_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+	.flags		= ATA_FLAG_SATA,
 	.pio_mask	= ATA_PIO4,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
@@ -164,7 +164,7 @@ static struct ata_port_info vt6421_sport_info = {
 };
 
 static struct ata_port_info vt6421_pport_info = {
-	.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_LEGACY,
+	.flags		= ATA_FLAG_SLAVE_POSS,
 	.pio_mask	= ATA_PIO4,
 	/* No MWDMA */
 	.udma_mask	= ATA_UDMA6,
@@ -172,8 +172,7 @@ static struct ata_port_info vt6421_pport_info = {
 };
 
 static struct ata_port_info vt8251_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_SLAVE_POSS |
-			  ATA_FLAG_NO_LEGACY,
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_SLAVE_POSS,
 	.pio_mask	= ATA_PIO4,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/ata/sata_vsc.c b/drivers/ata/sata_vsc.c
index 192bdc7d8f6e..7c987371136e 100644
--- a/drivers/ata/sata_vsc.c
+++ b/drivers/ata/sata_vsc.c
@@ -340,7 +340,7 @@ static int __devinit vsc_sata_init_one(struct pci_dev *pdev,
 				       const struct pci_device_id *ent)
 {
 	static const struct ata_port_info pi = {
-		.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY,
+		.flags		= ATA_FLAG_SATA,
 		.pio_mask	= ATA_PIO4,
 		.mwdma_mask	= ATA_MWDMA2,
 		.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index e437c8ae9d41..d841e98a8bd5 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6219,7 +6219,7 @@ static struct ata_port_operations ipr_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_DMA,
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA,
 	.pio_mask	= ATA_PIO4_ONLY,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 7538b6ffb3fe..4d3b704ede1c 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -372,8 +372,7 @@ static struct ata_port_operations sas_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | ATA_FLAG_PIO_DMA |
-		 ATA_FLAG_NCQ,
+	.flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ,
 	.pio_mask = ATA_PIO4,
 	.mwdma_mask = ATA_MWDMA2,
 	.udma_mask = ATA_UDMA6,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 0c3d9e144891..26d80479c75f 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -179,7 +179,6 @@ enum {
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
 					    /* (doesn't imply presence) */
 	ATA_FLAG_SATA		= (1 << 1),
-	ATA_FLAG_NO_LEGACY	= (1 << 2), /* no legacy mode check */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
 	ATA_FLAG_PIO_LBA48	= (1 << 8), /* Host DMA engine is LBA28 only */
-- 
cgit v1.2.3


From 1a0f6b7ecdcd810f8991ea26c95d93ff965e8f41 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Date: Fri, 4 Feb 2011 22:08:22 +0300
Subject: libata: remove ATA_FLAG_LPM

Commit 6b7ae9545ad9875a289f4191c0216b473e313cb9 (libata: reimplement link power
management) removed the check of ATA_FLAG_LPM but neglected to remove the flag
itself.  Do it now...

Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/ahci.h     | 3 +--
 include/linux/libata.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index fd75844fb009..ccaf08122058 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -214,8 +214,7 @@ enum {
 	/* ap->flags bits */
 
 	AHCI_FLAG_COMMON		= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
-					  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN |
-					  ATA_FLAG_LPM,
+					  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN,
 
 	ICH_MAP				= 0x90, /* ICH MAP register */
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 26d80479c75f..71333aa39532 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -194,7 +194,6 @@ enum {
 	ATA_FLAG_ACPI_SATA	= (1 << 17), /* need native SATA ACPI layout */
 	ATA_FLAG_AN		= (1 << 18), /* controller supports AN */
 	ATA_FLAG_PMP		= (1 << 19), /* controller supports PMP */
-	ATA_FLAG_LPM		= (1 << 20), /* driver can handle LPM */
 	ATA_FLAG_EM		= (1 << 21), /* driver supports enclosure
 					      * management */
 	ATA_FLAG_SW_ACTIVITY	= (1 << 22), /* driver supports sw activity
-- 
cgit v1.2.3


From 77bd70e9009eab6dbdef3ee08afe87ab26df8dac Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Fri, 4 Feb 2011 14:57:43 +0000
Subject: mfd: Don't suspend WM8994 if the CODEC is not suspended

ASoC supports keeping the audio subsysetm active over suspend in order
to support use cases such as audio passthrough from a cellular modem
with the main CPU suspended. Ensure that we don't power down the CODEC
when this is happening by checking to see if VMID is up and skipping
suspend and resume when it is. If the CODEC has suspended then it'll
turn VMID off before the core suspend() gets called.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/wm8994-core.c       | 18 ++++++++++++++++++
 include/linux/mfd/wm8994/core.h |  1 +
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 41233c7fa581..f4016a075fd6 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -246,6 +246,16 @@ static int wm8994_suspend(struct device *dev)
 	struct wm8994 *wm8994 = dev_get_drvdata(dev);
 	int ret;
 
+	/* Don't actually go through with the suspend if the CODEC is
+	 * still active (eg, for audio passthrough from CP. */
+	ret = wm8994_reg_read(wm8994, WM8994_POWER_MANAGEMENT_1);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read power status: %d\n", ret);
+	} else if (ret & WM8994_VMID_SEL_MASK) {
+		dev_dbg(dev, "CODEC still active, ignoring suspend\n");
+		return 0;
+	}
+
 	/* GPIO configuration state is saved here since we may be configuring
 	 * the GPIO alternate functions even if we're not using the gpiolib
 	 * driver for them.
@@ -261,6 +271,8 @@ static int wm8994_suspend(struct device *dev)
 	if (ret < 0)
 		dev_err(dev, "Failed to save LDO registers: %d\n", ret);
 
+	wm8994->suspended = true;
+
 	ret = regulator_bulk_disable(wm8994->num_supplies,
 				     wm8994->supplies);
 	if (ret != 0) {
@@ -276,6 +288,10 @@ static int wm8994_resume(struct device *dev)
 	struct wm8994 *wm8994 = dev_get_drvdata(dev);
 	int ret;
 
+	/* We may have lied to the PM core about suspending */
+	if (!wm8994->suspended)
+		return 0;
+
 	ret = regulator_bulk_enable(wm8994->num_supplies,
 				    wm8994->supplies);
 	if (ret != 0) {
@@ -298,6 +314,8 @@ static int wm8994_resume(struct device *dev)
 	if (ret < 0)
 		dev_err(dev, "Failed to restore GPIO registers: %d\n", ret);
 
+	wm8994->suspended = false;
+
 	return 0;
 }
 #endif
diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h
index 3fd36845ca45..ef4f0b6083a3 100644
--- a/include/linux/mfd/wm8994/core.h
+++ b/include/linux/mfd/wm8994/core.h
@@ -71,6 +71,7 @@ struct wm8994 {
 	u16 irq_masks_cache[WM8994_NUM_IRQ_REGS];
 
 	/* Used over suspend/resume */
+	bool suspended;
 	u16 ldo_regs[WM8994_NUM_LDO_REGS];
 	u16 gpio_regs[WM8994_NUM_GPIO_REGS];
 
-- 
cgit v1.2.3


From 1654e7411a1ad4999fe7890ef51d2a2bbb1fcf76 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 2 Mar 2011 08:48:05 -0500
Subject: block: add @force_kblockd to __blk_run_queue()

__blk_run_queue() automatically either calls q->request_fn() directly
or schedules kblockd depending on whether the function is recursed.
blk-flush implementation needs to be able to explicitly choose
kblockd.  Add @force_kblockd.

All the current users are converted to specify %false for the
parameter and this patch doesn't introduce any behavior change.

stable: This is prerequisite for fixing ide oops caused by the new
        blk-flush implementation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jan Beulich <JBeulich@novell.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 block/blk-core.c                 | 11 ++++++-----
 block/blk-flush.c                |  2 +-
 block/cfq-iosched.c              |  6 +++---
 block/elevator.c                 |  4 ++--
 drivers/scsi/scsi_lib.c          |  2 +-
 drivers/scsi/scsi_transport_fc.c |  2 +-
 include/linux/blkdev.h           |  2 +-
 7 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 792ece276160..518dd423a5fe 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -352,7 +352,7 @@ void blk_start_queue(struct request_queue *q)
 	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-	__blk_run_queue(q);
+	__blk_run_queue(q, false);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -403,13 +403,14 @@ EXPORT_SYMBOL(blk_sync_queue);
 /**
  * __blk_run_queue - run a single device queue
  * @q:	The queue to run
+ * @force_kblockd: Don't run @q->request_fn directly.  Use kblockd.
  *
  * Description:
  *    See @blk_run_queue. This variant must be called with the queue lock
  *    held and interrupts disabled.
  *
  */
-void __blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q, bool force_kblockd)
 {
 	blk_remove_plug(q);
 
@@ -423,7 +424,7 @@ void __blk_run_queue(struct request_queue *q)
 	 * Only recurse once to avoid overrunning the stack, let the unplug
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
-	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+	if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 		q->request_fn(q);
 		queue_flag_clear(QUEUE_FLAG_REENTER, q);
 	} else {
@@ -446,7 +447,7 @@ void blk_run_queue(struct request_queue *q)
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_run_queue(q);
+	__blk_run_queue(q, false);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -1053,7 +1054,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 
 	drive_stat_acct(rq, 1);
 	__elv_add_request(q, rq, where, 0);
-	__blk_run_queue(q);
+	__blk_run_queue(q, false);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 54b123d6563e..56adaa8d55cd 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -69,7 +69,7 @@ static void blk_flush_complete_seq_end_io(struct request_queue *q,
 	 * queue.  Kick the queue in those cases.
 	 */
 	if (was_empty && next_rq)
-		__blk_run_queue(q);
+		__blk_run_queue(q, false);
 }
 
 static void pre_flush_end_io(struct request *rq, int error)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7be4c7959625..ea83a4f0c27d 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3355,7 +3355,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			    cfqd->busy_queues > 1) {
 				cfq_del_timer(cfqd, cfqq);
 				cfq_clear_cfqq_wait_request(cfqq);
-				__blk_run_queue(cfqd->queue);
+				__blk_run_queue(cfqd->queue, false);
 			} else {
 				cfq_blkiocg_update_idle_time_stats(
 						&cfqq->cfqg->blkg);
@@ -3370,7 +3370,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		__blk_run_queue(cfqd->queue);
+		__blk_run_queue(cfqd->queue, false);
 	}
 }
 
@@ -3731,7 +3731,7 @@ static void cfq_kick_queue(struct work_struct *work)
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(cfqd->queue);
+	__blk_run_queue(cfqd->queue, false);
 	spin_unlock_irq(q->queue_lock);
 }
 
diff --git a/block/elevator.c b/block/elevator.c
index 2569512830d3..236e93c1f46c 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -602,7 +602,7 @@ void elv_quiesce_start(struct request_queue *q)
 	 */
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
-		__blk_run_queue(q);
+		__blk_run_queue(q, false);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
@@ -651,7 +651,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
-		__blk_run_queue(q);
+		__blk_run_queue(q, false);
 		break;
 
 	case ELEVATOR_INSERT_SORT:
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 9045c52abd25..fb2bb35c62cb 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -443,7 +443,7 @@ static void scsi_run_queue(struct request_queue *q)
 					&sdev->request_queue->queue_flags);
 		if (flagset)
 			queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue);
-		__blk_run_queue(sdev->request_queue);
+		__blk_run_queue(sdev->request_queue, false);
 		if (flagset)
 			queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue);
 		spin_unlock(sdev->request_queue->queue_lock);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 998c01be3234..5c3ccfc6b622 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -3829,7 +3829,7 @@ fc_bsg_goose_queue(struct fc_rport *rport)
 		  !test_bit(QUEUE_FLAG_REENTER, &rport->rqst_q->queue_flags);
 	if (flagset)
 		queue_flag_set(QUEUE_FLAG_REENTER, rport->rqst_q);
-	__blk_run_queue(rport->rqst_q);
+	__blk_run_queue(rport->rqst_q, false);
 	if (flagset)
 		queue_flag_clear(QUEUE_FLAG_REENTER, rport->rqst_q);
 	spin_unlock_irqrestore(rport->rqst_q->queue_lock, flags);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index dd8cd0f47e3a..d5063e1b5555 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -699,7 +699,7 @@ extern void blk_start_queue(struct request_queue *q);
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
-extern void __blk_run_queue(struct request_queue *);
+extern void __blk_run_queue(struct request_queue *q, bool force_kblockd);
 extern void blk_run_queue(struct request_queue *);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
 			   struct rq_map_data *, void __user *, unsigned long,
-- 
cgit v1.2.3


From 452edd598f60522c11f7f88fdbab27eb36509d1a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 2 Mar 2011 13:27:41 -0800
Subject: xfrm: Return dst directly from xfrm_lookup()

Instead of on the stack.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h                | 14 ++++++++------
 net/decnet/dn_route.c            | 12 ++++++++++--
 net/ipv4/icmp.c                  | 36 ++++++++++++++----------------------
 net/ipv4/netfilter.c             |  6 ++++--
 net/ipv4/route.c                 |  7 ++++++-
 net/ipv6/icmp.c                  | 37 ++++++++++++++++++-------------------
 net/ipv6/ip6_output.c            | 10 ++--------
 net/ipv6/ip6_tunnel.c            |  8 +++++++-
 net/ipv6/mcast.c                 | 13 ++++++++++---
 net/ipv6/ndisc.c                 |  8 ++++----
 net/ipv6/netfilter.c             |  3 ++-
 net/ipv6/netfilter/ip6t_REJECT.c |  3 ++-
 net/netfilter/ipvs/ip_vs_xmit.c  |  9 +++++++--
 net/xfrm/xfrm_policy.c           | 34 +++++++++++++++++-----------------
 14 files changed, 111 insertions(+), 89 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 8948452132ad..2a46cbaef92d 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -426,15 +426,17 @@ enum {
 
 struct flowi;
 #ifndef CONFIG_XFRM
-static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-			      const struct flowi *fl, struct sock *sk,
-			      int flags)
+static inline struct dst_entry *xfrm_lookup(struct net *net,
+					    struct dst_entry *dst_orig,
+					    const struct flowi *fl, struct sock *sk,
+					    int flags)
 {
-	return 0;
+	return dst_orig;
 } 
 #else
-extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-		       const struct flowi *fl, struct sock *sk, int flags);
+extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+				     const struct flowi *fl, struct sock *sk,
+				     int flags);
 #endif
 #endif
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 0877147d2167..484fdbf92bd8 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1222,7 +1222,11 @@ static int dn_route_output_key(struct dst_entry **pprt, struct flowi *flp, int f
 
 	err = __dn_route_output_key(pprt, flp, flags);
 	if (err == 0 && flp->proto) {
-		err = xfrm_lookup(&init_net, pprt, flp, NULL, 0);
+		*pprt = xfrm_lookup(&init_net, *pprt, flp, NULL, 0);
+		if (IS_ERR(*pprt)) {
+			err = PTR_ERR(*pprt);
+			*pprt = NULL;
+		}
 	}
 	return err;
 }
@@ -1235,7 +1239,11 @@ int dn_route_output_sock(struct dst_entry **pprt, struct flowi *fl, struct sock
 	if (err == 0 && fl->proto) {
 		if (!(flags & MSG_DONTWAIT))
 			fl->flags |= FLOWI_FLAG_CAN_SLEEP;
-		err = xfrm_lookup(&init_net, pprt, fl, sk, 0);
+		*pprt = xfrm_lookup(&init_net, *pprt, fl, sk, 0);
+		if (IS_ERR(*pprt)) {
+			err = PTR_ERR(*pprt);
+			*pprt = NULL;
+		}
 	}
 	return err;
 }
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 2a86c8951dcd..c23bd8cdeee0 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -398,18 +398,14 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 	if (!fl.fl4_src)
 		fl.fl4_src = rt->rt_src;
 
-	err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0);
-	switch (err) {
-	case 0:
+	rt = (struct rtable *) xfrm_lookup(net, &rt->dst, &fl, NULL, 0);
+	if (!IS_ERR(rt)) {
 		if (rt != rt2)
 			return rt;
-		break;
-	case -EPERM:
+	} else if (PTR_ERR(rt) == -EPERM) {
 		rt = NULL;
-		break;
-	default:
-		return ERR_PTR(err);
-	}
+	} else
+		return rt;
 
 	err = xfrm_decode_session_reverse(skb_in, &fl, AF_INET);
 	if (err)
@@ -438,22 +434,18 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 	if (err)
 		goto relookup_failed;
 
-	err = xfrm_lookup(net, (struct dst_entry **)&rt2, &fl, NULL,
-			  XFRM_LOOKUP_ICMP);
-	switch (err) {
-	case 0:
+	rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, &fl, NULL, XFRM_LOOKUP_ICMP);
+	if (!IS_ERR(rt2)) {
 		dst_release(&rt->dst);
 		rt = rt2;
-		break;
-	case -EPERM:
-		return ERR_PTR(err);
-	default:
-		if (!rt)
-			return ERR_PTR(err);
-		break;
+	} else if (PTR_ERR(rt2) == -EPERM) {
+		if (rt)
+			dst_release(&rt->dst);
+		return rt2;
+	} else {
+		err = PTR_ERR(rt2);
+		goto relookup_failed;
 	}
-
-
 	return rt;
 
 relookup_failed:
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 994a1f29ebbc..9770bb427952 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -69,7 +69,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	    xfrm_decode_session(skb, &fl, AF_INET) == 0) {
 		struct dst_entry *dst = skb_dst(skb);
 		skb_dst_set(skb, NULL);
-		if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
+		dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
+		if (IS_ERR(dst))
 			return -1;
 		skb_dst_set(skb, dst);
 	}
@@ -102,7 +103,8 @@ int ip_xfrm_me_harder(struct sk_buff *skb)
 		dst = ((struct xfrm_dst *)dst)->route;
 	dst_hold(dst);
 
-	if (xfrm_lookup(dev_net(dst->dev), &dst, &fl, skb->sk, 0) < 0)
+	dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0);
+	if (IS_ERR(dst))
 		return -1;
 
 	skb_dst_drop(skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e24e4cf2a112..63d37004ee66 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2730,7 +2730,12 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
 			flp->fl4_src = (*rp)->rt_src;
 		if (!flp->fl4_dst)
 			flp->fl4_dst = (*rp)->rt_dst;
-		return xfrm_lookup(net, (struct dst_entry **)rp, flp, sk, 0);
+		*rp = (struct rtable *) xfrm_lookup(net, &(*rp)->dst, flp, sk, 0);
+		if (IS_ERR(*rp)) {
+			err = PTR_ERR(*rp);
+			*rp = NULL;
+			return err;
+		}
 	}
 
 	return 0;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index e332bae104ee..55665956b3a8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -324,17 +324,15 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *sk
 	/* No need to clone since we're just using its address. */
 	dst2 = dst;
 
-	err = xfrm_lookup(net, &dst, fl, sk, 0);
-	switch (err) {
-	case 0:
+	dst = xfrm_lookup(net, dst, fl, sk, 0);
+	if (!IS_ERR(dst)) {
 		if (dst != dst2)
 			return dst;
-		break;
-	case -EPERM:
-		dst = NULL;
-		break;
-	default:
-		return ERR_PTR(err);
+	} else {
+		if (PTR_ERR(dst) == -EPERM)
+			dst = NULL;
+		else
+			return dst;
 	}
 
 	err = xfrm_decode_session_reverse(skb, &fl2, AF_INET6);
@@ -345,17 +343,17 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *sk
 	if (err)
 		goto relookup_failed;
 
-	err = xfrm_lookup(net, &dst2, &fl2, sk, XFRM_LOOKUP_ICMP);
-	switch (err) {
-	case 0:
+	dst2 = xfrm_lookup(net, dst2, &fl2, sk, XFRM_LOOKUP_ICMP);
+	if (!IS_ERR(dst2)) {
 		dst_release(dst);
 		dst = dst2;
-		break;
-	case -EPERM:
-		dst_release(dst);
-		return ERR_PTR(err);
-	default:
-		goto relookup_failed;
+	} else {
+		err = PTR_ERR(dst2);
+		if (err == -EPERM) {
+			dst_release(dst);
+			return dst2;
+		} else
+			goto relookup_failed;
 	}
 
 relookup_failed:
@@ -560,7 +558,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	err = ip6_dst_lookup(sk, &dst, &fl);
 	if (err)
 		goto out;
-	if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0)
+	dst = xfrm_lookup(net, dst, &fl, sk, 0);
+	if (IS_ERR(dst))
 		goto out;
 
 	if (ipv6_addr_is_multicast(&fl.fl6_dst))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 35a4ad90a0f5..adaffaf84555 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1028,10 +1028,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 	if (can_sleep)
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 
-	err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
-	if (err)
-		return ERR_PTR(err);
-	return dst;
+	return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
 
@@ -1067,10 +1064,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 	if (can_sleep)
 		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
 
-	err = xfrm_lookup(sock_net(sk), &dst, fl, sk, 0);
-	if (err)
-		return ERR_PTR(err);
-	return dst;
+	return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4f4483e697bd..da43038ae18e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -903,8 +903,14 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	else {
 		dst = ip6_route_output(net, NULL, fl);
 
-		if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0)
+		if (dst->error)
 			goto tx_err_link_failure;
+		dst = xfrm_lookup(net, dst, fl, NULL, 0);
+		if (IS_ERR(dst)) {
+			err = PTR_ERR(dst);
+			dst = NULL;
+			goto tx_err_link_failure;
+		}
 	}
 
 	tdev = dst->dev;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 49f986d626a0..7b27d08ee281 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1429,7 +1429,12 @@ static void mld_sendpack(struct sk_buff *skb)
 			 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
 			 skb->dev->ifindex);
 
-	err = xfrm_lookup(net, &dst, &fl, NULL, 0);
+	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	err = 0;
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		dst = NULL;
+	}
 	skb_dst_set(skb, dst);
 	if (err)
 		goto err_out;
@@ -1796,9 +1801,11 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 			 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
 			 skb->dev->ifindex);
 
-	err = xfrm_lookup(net, &dst, &fl, NULL, 0);
-	if (err)
+	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
 		goto err_out;
+	}
 
 	skb_dst_set(skb, dst);
 	err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 7254ce364006..9360d3be94f0 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -529,8 +529,8 @@ void ndisc_send_skb(struct sk_buff *skb,
 		return;
 	}
 
-	err = xfrm_lookup(net, &dst, &fl, NULL, 0);
-	if (err < 0) {
+	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	if (IS_ERR(dst)) {
 		kfree_skb(skb);
 		return;
 	}
@@ -1542,8 +1542,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	if (dst == NULL)
 		return;
 
-	err = xfrm_lookup(net, &dst, &fl, NULL, 0);
-	if (err)
+	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	if (IS_ERR(dst))
 		return;
 
 	rt = (struct rt6_info *) dst;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 35915e8617f0..8d74116ae27d 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -39,7 +39,8 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
 	    xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
 		skb_dst_set(skb, NULL);
-		if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
+		dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
+		if (IS_ERR(dst))
 			return -1;
 		skb_dst_set(skb, dst);
 	}
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index bf998feac14e..91f6a61cefab 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -101,7 +101,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 		dst_release(dst);
 		return;
 	}
-	if (xfrm_lookup(net, &dst, &fl, NULL, 0))
+	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	if (IS_ERR(dst))
 		return;
 
 	hh_len = (dst->dev->hard_header_len + 15)&~15;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index a48239aba33b..6264219f0a42 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -218,8 +218,13 @@ __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
 	    ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
 			       &fl.fl6_dst, 0, &fl.fl6_src) < 0)
 		goto out_err;
-	if (do_xfrm && xfrm_lookup(net, &dst, &fl, NULL, 0) < 0)
-		goto out_err;
+	if (do_xfrm) {
+		dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+		if (IS_ERR(dst)) {
+			dst = NULL;
+			goto out_err;
+		}
+	}
 	ipv6_addr_copy(ret_saddr, &fl.fl6_src);
 	return dst;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0248afa11cda..b1932a629ef8 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1757,14 +1757,14 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family,
  * At the moment we eat a raw IP route. Mostly to speed up lookups
  * on interfaces with disabled IPsec.
  */
-int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
-		const struct flowi *fl,
-		struct sock *sk, int flags)
+struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+			      const struct flowi *fl,
+			      struct sock *sk, int flags)
 {
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	struct flow_cache_object *flo;
 	struct xfrm_dst *xdst;
-	struct dst_entry *dst, *dst_orig = *dst_p, *route;
+	struct dst_entry *dst, *route;
 	u16 family = dst_orig->ops->family;
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
 	int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
@@ -1847,11 +1847,7 @@ restart:
 			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 
-			dst = make_blackhole(net, family, dst_orig);
-			if (IS_ERR(dst))
-				return PTR_ERR(dst);
-			*dst_p = dst;
-			return 0;
+			return make_blackhole(net, family, dst_orig);
 		}
 		if (fl->flags & FLOWI_FLAG_CAN_SLEEP) {
 			DECLARE_WAITQUEUE(wait, current);
@@ -1895,27 +1891,28 @@ no_transform:
 		goto error;
 	} else if (num_xfrms > 0) {
 		/* Flow transformed */
-		*dst_p = dst;
 		dst_release(dst_orig);
 	} else {
 		/* Flow passes untransformed */
 		dst_release(dst);
+		dst = dst_orig;
 	}
 ok:
 	xfrm_pols_put(pols, drop_pols);
-	return 0;
+	return dst;
 
 nopol:
-	if (!(flags & XFRM_LOOKUP_ICMP))
+	if (!(flags & XFRM_LOOKUP_ICMP)) {
+		dst = dst_orig;
 		goto ok;
+	}
 	err = -ENOENT;
 error:
 	dst_release(dst);
 dropdst:
 	dst_release(dst_orig);
-	*dst_p = NULL;
 	xfrm_pols_put(pols, drop_pols);
-	return err;
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(xfrm_lookup);
 
@@ -2175,7 +2172,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 	struct net *net = dev_net(skb->dev);
 	struct flowi fl;
 	struct dst_entry *dst;
-	int res;
+	int res = 0;
 
 	if (xfrm_decode_session(skb, &fl, family) < 0) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
@@ -2183,9 +2180,12 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 	}
 
 	skb_dst_force(skb);
-	dst = skb_dst(skb);
 
-	res = xfrm_lookup(net, &dst, &fl, NULL, 0) == 0;
+	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0);
+	if (IS_ERR(dst)) {
+		res = 1;
+		dst = NULL;
+	}
 	skb_dst_set(skb, dst);
 	return res;
 }
-- 
cgit v1.2.3


From b23dd4fe42b455af5c6e20966b7d6959fa8352ea Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 2 Mar 2011 14:31:35 -0800
Subject: ipv4: Make output route lookup return rtable directly.

Instead of on the stack.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c        |   7 ++-
 drivers/infiniband/hw/cxgb3/iwch_cm.c |   3 +-
 drivers/infiniband/hw/cxgb4/cm.c      |   3 +-
 drivers/infiniband/hw/nes/nes_cm.c    |   3 +-
 drivers/net/bonding/bond_main.c       |   6 +-
 drivers/net/cnic.c                    |   7 ++-
 drivers/net/pptp.c                    |   8 +--
 drivers/scsi/cxgbi/libcxgbi.c         |   3 +-
 include/net/route.h                   |  58 ++++++++++----------
 net/atm/clip.c                        |   6 +-
 net/bridge/br_netfilter.c             |   9 +--
 net/dccp/ipv4.c                       |  27 ++++-----
 net/ipv4/af_inet.c                    |  30 +++++-----
 net/ipv4/arp.c                        |  19 +++----
 net/ipv4/datagram.c                   |  11 ++--
 net/ipv4/icmp.c                       |  19 ++++---
 net/ipv4/igmp.c                       |  16 ++++--
 net/ipv4/inet_connection_sock.c       |   3 +-
 net/ipv4/ip_gre.c                     |  11 ++--
 net/ipv4/ip_output.c                  |   6 +-
 net/ipv4/ipip.c                       |   7 ++-
 net/ipv4/ipmr.c                       |   8 +--
 net/ipv4/netfilter.c                  |  12 +++-
 net/ipv4/raw.c                        |   8 ++-
 net/ipv4/route.c                      | 100 +++++++++++++++++-----------------
 net/ipv4/syncookies.c                 |   3 +-
 net/ipv4/tcp_ipv4.c                   |  28 +++++-----
 net/ipv4/udp.c                        |   5 +-
 net/ipv4/xfrm4_policy.c               |  12 ++--
 net/ipv6/ip6_tunnel.c                 |  11 ++--
 net/ipv6/sit.c                        |   8 ++-
 net/l2tp/l2tp_ip.c                    |   8 ++-
 net/netfilter/ipvs/ip_vs_xmit.c       |   9 ++-
 net/netfilter/xt_TEE.c                |   3 +-
 net/rxrpc/ar-peer.c                   |   7 +--
 net/sctp/protocol.c                   |   7 ++-
 36 files changed, 267 insertions(+), 224 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 8aba0ba57de5..2d749937a969 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -193,10 +193,11 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 	fl.nl_u.ip4_u.saddr = src_ip;
 	fl.oif = addr->bound_dev_if;
 
-	ret = ip_route_output_key(&init_net, &rt, &fl);
-	if (ret)
+	rt = ip_route_output_key(&init_net, &fl);
+	if (IS_ERR(rt)) {
+		ret = PTR_ERR(rt);
 		goto out;
-
+	}
 	src_in->sin_family = AF_INET;
 	src_in->sin_addr.s_addr = rt->rt_src;
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index e654285aa6ba..e0ccbc53fbcc 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -354,7 +354,8 @@ static struct rtable *find_route(struct t3cdev *dev, __be32 local_ip,
 			  }
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL))
+	rt = ip_route_output_flow(&init_net, &fl, NULL);
+	if (IS_ERR(rt))
 		return NULL;
 	return rt;
 }
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 7e0484f18db5..77b0eef2aad9 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -331,7 +331,8 @@ static struct rtable *find_route(struct c4iw_dev *dev, __be32 local_ip,
 			  }
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL))
+	rt = ip_route_output_flow(&init_net, &fl, NULL);
+	if (IS_ERR(rt))
 		return NULL;
 	return rt;
 }
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index ec3aa11c36cb..e81599cb1fe6 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1112,7 +1112,8 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 
 	memset(&fl, 0, sizeof fl);
 	fl.nl_u.ip4_u.daddr = htonl(dst_ip);
-	if (ip_route_output_key(&init_net, &rt, &fl)) {
+	rt = ip_route_output_key(&init_net, &fl);
+	if (IS_ERR(rt)) {
 		printk(KERN_ERR "%s: ip_route_output_key failed for 0x%08X\n",
 				__func__, dst_ip);
 		return rc;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 584f97b73060..0592e6da15a6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2681,7 +2681,7 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_
 
 static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 {
-	int i, vlan_id, rv;
+	int i, vlan_id;
 	__be32 *targets = bond->params.arp_targets;
 	struct vlan_entry *vlan;
 	struct net_device *vlan_dev;
@@ -2708,8 +2708,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		fl.fl4_dst = targets[i];
 		fl.fl4_tos = RTO_ONLINK;
 
-		rv = ip_route_output_key(dev_net(bond->dev), &rt, &fl);
-		if (rv) {
+		rt = ip_route_output_key(dev_net(bond->dev), &fl);
+		if (IS_ERR(rt)) {
 			if (net_ratelimit()) {
 				pr_warning("%s: no route to arp_ip_target %pI4\n",
 					   bond->dev->name, &fl.fl4_dst);
diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c
index 5274de3e1bb9..25f08880ae0f 100644
--- a/drivers/net/cnic.c
+++ b/drivers/net/cnic.c
@@ -3397,9 +3397,12 @@ static int cnic_get_v4_route(struct sockaddr_in *dst_addr,
 	memset(&fl, 0, sizeof(fl));
 	fl.nl_u.ip4_u.daddr = dst_addr->sin_addr.s_addr;
 
-	err = ip_route_output_key(&init_net, &rt, &fl);
-	if (!err)
+	rt = ip_route_output_key(&init_net, &fl);
+	err = 0;
+	if (!IS_ERR(rt))
 		*dst = &rt->dst;
+	else
+		err = PTR_ERR(rt);
 	return err;
 #else
 	return -ENETUNREACH;
diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c
index 164cfad6ce79..1af549c89d51 100644
--- a/drivers/net/pptp.c
+++ b/drivers/net/pptp.c
@@ -175,7 +175,6 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	struct pptp_opt *opt = &po->proto.pptp;
 	struct pptp_gre_header *hdr;
 	unsigned int header_len = sizeof(*hdr);
-	int err = 0;
 	int islcp;
 	int len;
 	unsigned char *data;
@@ -198,8 +197,8 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 					.saddr = opt->src_addr.sin_addr.s_addr,
 					.tos = RT_TOS(0) } },
 			.proto = IPPROTO_GRE };
-		err = ip_route_output_key(&init_net, &rt, &fl);
-		if (err)
+		rt = ip_route_output_key(&init_net, &fl);
+		if (IS_ERR(rt))
 			goto tx_error;
 	}
 	tdev = rt->dst.dev;
@@ -477,7 +476,8 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 					.tos = RT_CONN_FLAGS(sk) } },
 			.proto = IPPROTO_GRE };
 		security_sk_classify_flow(sk, &fl);
-		if (ip_route_output_key(&init_net, &rt, &fl)) {
+		rt = ip_route_output_key(&init_net, &fl);
+		if (IS_ERR(rt)) {
 			error = -EHOSTUNREACH;
 			goto end;
 		}
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 261aa817bdd5..889199aa1f5b 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -470,7 +470,8 @@ static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
 			}
 	};
 
-	if (ip_route_output_flow(&init_net, &rt, &fl, NULL))
+	rt = ip_route_output_flow(&init_net, &fl, NULL);
+	if (IS_ERR(rt))
 		return NULL;
 
 	return rt;
diff --git a/include/net/route.h b/include/net/route.h
index 707cfc8eccdc..088a1867348f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -118,9 +118,10 @@ extern void		ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
 				       __be32 src, struct net_device *dev);
 extern void		rt_cache_flush(struct net *net, int how);
 extern void		rt_cache_flush_batch(struct net *net);
-extern int		__ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
-extern int		ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
-extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk);
+extern struct rtable *__ip_route_output_key(struct net *, const struct flowi *flp);
+extern struct rtable *ip_route_output_key(struct net *, struct flowi *flp);
+extern struct rtable *ip_route_output_flow(struct net *, struct flowi *flp,
+					   struct sock *sk);
 extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
@@ -166,10 +167,10 @@ static inline char rt_tos2priority(u8 tos)
 	return ip_tos2prio[IPTOS_TOS(tos)>>1];
 }
 
-static inline int ip_route_connect(struct rtable **rp, __be32 dst,
-				   __be32 src, u32 tos, int oif, u8 protocol,
-				   __be16 sport, __be16 dport, struct sock *sk,
-				   bool can_sleep)
+static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos,
+					      int oif, u8 protocol,
+					      __be16 sport, __be16 dport,
+					      struct sock *sk, bool can_sleep)
 {
 	struct flowi fl = { .oif = oif,
 			    .mark = sk->sk_mark,
@@ -179,8 +180,8 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 			    .proto = protocol,
 			    .fl_ip_sport = sport,
 			    .fl_ip_dport = dport };
-	int err;
 	struct net *net = sock_net(sk);
+	struct rtable *rt;
 
 	if (inet_sk(sk)->transparent)
 		fl.flags |= FLOWI_FLAG_ANYSRC;
@@ -190,29 +191,29 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst,
 		fl.flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	if (!dst || !src) {
-		err = __ip_route_output_key(net, rp, &fl);
-		if (err)
-			return err;
-		fl.fl4_dst = (*rp)->rt_dst;
-		fl.fl4_src = (*rp)->rt_src;
-		ip_rt_put(*rp);
-		*rp = NULL;
+		rt = __ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
+			return rt;
+		fl.fl4_dst = rt->rt_dst;
+		fl.fl4_src = rt->rt_src;
+		ip_rt_put(rt);
 	}
 	security_sk_classify_flow(sk, &fl);
-	return ip_route_output_flow(net, rp, &fl, sk);
+	return ip_route_output_flow(net, &fl, sk);
 }
 
-static inline int ip_route_newports(struct rtable **rp, u8 protocol,
-				    __be16 orig_sport, __be16 orig_dport,
-				    __be16 sport, __be16 dport, struct sock *sk)
+static inline struct rtable *ip_route_newports(struct rtable *rt,
+					       u8 protocol, __be16 orig_sport,
+					       __be16 orig_dport, __be16 sport,
+					       __be16 dport, struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
-		struct flowi fl = { .oif = (*rp)->fl.oif,
-				    .mark = (*rp)->fl.mark,
-				    .fl4_dst = (*rp)->fl.fl4_dst,
-				    .fl4_src = (*rp)->fl.fl4_src,
-				    .fl4_tos = (*rp)->fl.fl4_tos,
-				    .proto = (*rp)->fl.proto,
+		struct flowi fl = { .oif = rt->fl.oif,
+				    .mark = rt->fl.mark,
+				    .fl4_dst = rt->fl.fl4_dst,
+				    .fl4_src = rt->fl.fl4_src,
+				    .fl4_tos = rt->fl.fl4_tos,
+				    .proto = rt->fl.proto,
 				    .fl_ip_sport = sport,
 				    .fl_ip_dport = dport };
 
@@ -220,12 +221,11 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol,
 			fl.flags |= FLOWI_FLAG_ANYSRC;
 		if (protocol == IPPROTO_TCP)
 			fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
-		ip_rt_put(*rp);
-		*rp = NULL;
+		ip_rt_put(rt);
 		security_sk_classify_flow(sk, &fl);
-		return ip_route_output_flow(sock_net(sk), rp, &fl, sk);
+		return ip_route_output_flow(sock_net(sk), &fl, sk);
 	}
-	return 0;
+	return rt;
 }
 
 extern void rt_bind_peer(struct rtable *rt, int create);
diff --git a/net/atm/clip.c b/net/atm/clip.c
index d257da50fcfb..810a1294eddb 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -520,9 +520,9 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 		unlink_clip_vcc(clip_vcc);
 		return 0;
 	}
-	error = ip_route_output_key(&init_net, &rt, &fl);
-	if (error)
-		return error;
+	rt = ip_route_output_key(&init_net, &fl);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
 	neigh = __neigh_lookup(&clip_tbl, &ip, rt->dst.dev, 1);
 	ip_rt_put(rt);
 	if (!neigh)
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 4b5b66d07bba..45b57b173f70 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -428,14 +428,15 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 			if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
 				goto free_skb;
 
-			if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
+			rt = ip_route_output_key(dev_net(dev), &fl);
+			if (!IS_ERR(rt)) {
 				/* - Bridged-and-DNAT'ed traffic doesn't
 				 *   require ip_forwarding. */
-				if (((struct dst_entry *)rt)->dev == dev) {
-					skb_dst_set(skb, (struct dst_entry *)rt);
+				if (rt->dst.dev == dev) {
+					skb_dst_set(skb, &rt->dst);
 					goto bridged_dnat;
 				}
-				dst_release((struct dst_entry *)rt);
+				ip_rt_put(rt);
 			}
 free_skb:
 			kfree_skb(skb);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index a8ff95502081..7882377bc62e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -46,7 +46,6 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	__be16 orig_sport, orig_dport;
 	struct rtable *rt;
 	__be32 daddr, nexthop;
-	int tmp;
 	int err;
 
 	dp->dccps_role = DCCP_ROLE_CLIENT;
@@ -66,12 +65,12 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	orig_sport = inet->inet_sport;
 	orig_dport = usin->sin_port;
-	tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
-			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
-			       IPPROTO_DCCP,
-			       orig_sport, orig_dport, sk, true);
-	if (tmp < 0)
-		return tmp;
+	rt = ip_route_connect(nexthop, inet->inet_saddr,
+			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
+			      IPPROTO_DCCP,
+			      orig_sport, orig_dport, sk, true);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
 
 	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
 		ip_rt_put(rt);
@@ -102,12 +101,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err != 0)
 		goto failure;
 
-	err = ip_route_newports(&rt, IPPROTO_DCCP,
-				orig_sport, orig_dport,
-				inet->inet_sport, inet->inet_dport, sk);
-	if (err != 0)
+	rt = ip_route_newports(rt, IPPROTO_DCCP,
+			       orig_sport, orig_dport,
+			       inet->inet_sport, inet->inet_dport, sk);
+	if (IS_ERR(rt)) {
+		rt = NULL;
 		goto failure;
-
+	}
 	/* OK, now commit destination to socket.  */
 	sk_setup_caps(sk, &rt->dst);
 
@@ -475,7 +475,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 			  };
 
 	security_skb_classify_flow(skb, &fl);
-	if (ip_route_output_flow(net, &rt, &fl, sk)) {
+	rt = ip_route_output_flow(net, &fl, sk);
+	if (IS_ERR(rt)) {
 		IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
 		return NULL;
 	}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 44513bb8ac2e..35a502055018 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1101,23 +1101,20 @@ int sysctl_ip_dynaddr __read_mostly;
 static int inet_sk_reselect_saddr(struct sock *sk)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	int err;
-	struct rtable *rt;
 	__be32 old_saddr = inet->inet_saddr;
-	__be32 new_saddr;
 	__be32 daddr = inet->inet_daddr;
+	struct rtable *rt;
+	__be32 new_saddr;
 
 	if (inet->opt && inet->opt->srr)
 		daddr = inet->opt->faddr;
 
 	/* Query new route. */
-	err = ip_route_connect(&rt, daddr, 0,
-			       RT_CONN_FLAGS(sk),
-			       sk->sk_bound_dev_if,
-			       sk->sk_protocol,
-			       inet->inet_sport, inet->inet_dport, sk, false);
-	if (err)
-		return err;
+	rt = ip_route_connect(daddr, 0, RT_CONN_FLAGS(sk),
+			      sk->sk_bound_dev_if, sk->sk_protocol,
+			      inet->inet_sport, inet->inet_dport, sk, false);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
 
 	sk_setup_caps(sk, &rt->dst);
 
@@ -1160,7 +1157,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	daddr = inet->inet_daddr;
 	if (inet->opt && inet->opt->srr)
 		daddr = inet->opt->faddr;
-{
+	{
 	struct flowi fl = {
 		.oif = sk->sk_bound_dev_if,
 		.mark = sk->sk_mark,
@@ -1174,11 +1171,14 @@ int inet_sk_rebuild_header(struct sock *sk)
 	};
 
 	security_sk_classify_flow(sk, &fl);
-	err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk);
-}
-	if (!err)
+	rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+	}
+	if (!IS_ERR(rt)) {
+		err = 0;
 		sk_setup_caps(sk, &rt->dst);
-	else {
+	} else {
+		err = PTR_ERR(rt);
+
 		/* Routing failed... */
 		sk->sk_route_caps = 0;
 		/*
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7927589813b5..fa9988da1da4 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -440,7 +440,8 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 	/*unsigned long now; */
 	struct net *net = dev_net(dev);
 
-	if (ip_route_output_key(net, &rt, &fl) < 0)
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
 		return 1;
 	if (rt->dst.dev != dev) {
 		NET_INC_STATS_BH(net, LINUX_MIB_ARPFILTER);
@@ -1063,10 +1064,10 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 	if (dev == NULL) {
 		struct flowi fl = { .fl4_dst = ip,
 				    .fl4_tos = RTO_ONLINK };
-		struct rtable *rt;
-		err = ip_route_output_key(net, &rt, &fl);
-		if (err != 0)
-			return err;
+		struct rtable *rt = ip_route_output_key(net, &fl);
+
+		if (IS_ERR(rt))
+			return PTR_ERR(rt);
 		dev = rt->dst.dev;
 		ip_rt_put(rt);
 		if (!dev)
@@ -1177,7 +1178,6 @@ static int arp_req_delete_public(struct net *net, struct arpreq *r,
 static int arp_req_delete(struct net *net, struct arpreq *r,
 			  struct net_device *dev)
 {
-	int err;
 	__be32 ip;
 
 	if (r->arp_flags & ATF_PUBL)
@@ -1187,10 +1187,9 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
 	if (dev == NULL) {
 		struct flowi fl = { .fl4_dst = ip,
 				    .fl4_tos = RTO_ONLINK };
-		struct rtable *rt;
-		err = ip_route_output_key(net, &rt, &fl);
-		if (err != 0)
-			return err;
+		struct rtable *rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
+			return PTR_ERR(rt);
 		dev = rt->dst.dev;
 		ip_rt_put(rt);
 		if (!dev)
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index eaee1edd2dd7..85bd24ca4f6d 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -46,11 +46,12 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		if (!saddr)
 			saddr = inet->mc_addr;
 	}
-	err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr,
-			       RT_CONN_FLAGS(sk), oif,
-			       sk->sk_protocol,
-			       inet->inet_sport, usin->sin_port, sk, true);
-	if (err) {
+	rt = ip_route_connect(usin->sin_addr.s_addr, saddr,
+			      RT_CONN_FLAGS(sk), oif,
+			      sk->sk_protocol,
+			      inet->inet_sport, usin->sin_port, sk, true);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
 			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 		return err;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index c23bd8cdeee0..994a785d98f9 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -358,7 +358,8 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 				    .fl4_tos = RT_TOS(ip_hdr(skb)->tos),
 				    .proto = IPPROTO_ICMP };
 		security_skb_classify_flow(skb, &fl);
-		if (ip_route_output_key(net, &rt, &fl))
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			goto out_unlock;
 	}
 	if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type,
@@ -388,9 +389,9 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 	int err;
 
 	security_skb_classify_flow(skb_in, &fl);
-	err = __ip_route_output_key(net, &rt, &fl);
-	if (err)
-		return ERR_PTR(err);
+	rt = __ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
+		return rt;
 
 	/* No need to clone since we're just using its address. */
 	rt2 = rt;
@@ -412,15 +413,19 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 		goto relookup_failed;
 
 	if (inet_addr_type(net, fl.fl4_src) == RTN_LOCAL) {
-		err = __ip_route_output_key(net, &rt2, &fl);
+		rt2 = __ip_route_output_key(net, &fl);
+		if (IS_ERR(rt2))
+			err = PTR_ERR(rt2);
 	} else {
 		struct flowi fl2 = {};
 		unsigned long orefdst;
 
 		fl2.fl4_dst = fl.fl4_src;
-		err = ip_route_output_key(net, &rt2, &fl2);
-		if (err)
+		rt2 = ip_route_output_key(net, &fl2);
+		if (IS_ERR(rt2)) {
+			err = PTR_ERR(rt2);
 			goto relookup_failed;
+		}
 		/* Ugh! */
 		orefdst = skb_in->_skb_refdst; /* save old refdst */
 		err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index e0e77e297de3..44ba9068b72f 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -325,7 +325,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 		struct flowi fl = { .oif = dev->ifindex,
 				    .fl4_dst = IGMPV3_ALL_MCR,
 				    .proto = IPPROTO_IGMP };
-		if (ip_route_output_key(net, &rt, &fl)) {
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt)) {
 			kfree_skb(skb);
 			return NULL;
 		}
@@ -670,7 +671,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 		struct flowi fl = { .oif = dev->ifindex,
 				    .fl4_dst = dst,
 				    .proto = IPPROTO_IGMP };
-		if (ip_route_output_key(net, &rt, &fl))
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			return -1;
 	}
 	if (rt->rt_src == 0) {
@@ -1440,7 +1442,6 @@ void ip_mc_destroy_dev(struct in_device *in_dev)
 static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
 {
 	struct flowi fl = { .fl4_dst = imr->imr_multiaddr.s_addr };
-	struct rtable *rt;
 	struct net_device *dev = NULL;
 	struct in_device *idev = NULL;
 
@@ -1454,9 +1455,12 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
 			return NULL;
 	}
 
-	if (!dev && !ip_route_output_key(net, &rt, &fl)) {
-		dev = rt->dst.dev;
-		ip_rt_put(rt);
+	if (!dev) {
+		struct rtable *rt = ip_route_output_key(net, &fl);
+		if (!IS_ERR(rt)) {
+			dev = rt->dst.dev;
+			ip_rt_put(rt);
+		}
 	}
 	if (dev) {
 		imr->imr_ifindex = dev->ifindex;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7f85d4aec26a..e4e301a61c5b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -369,7 +369,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct net *net = sock_net(sk);
 
 	security_req_classify_flow(req, &fl);
-	if (ip_route_output_flow(net, &rt, &fl, sk))
+	rt = ip_route_output_flow(net, &fl, sk);
+	if (IS_ERR(rt))
 		goto no_route;
 	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
 		goto route_err;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6613edfac28c..f9af98dd7561 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -778,7 +778,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			.proto = IPPROTO_GRE,
 			.fl_gre_key = tunnel->parms.o_key
 		};
-		if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
+		rt = ip_route_output_key(dev_net(dev), &fl);
+		if (IS_ERR(rt)) {
 			dev->stats.tx_carrier_errors++;
 			goto tx_error;
 		}
@@ -953,9 +954,9 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
 			.proto = IPPROTO_GRE,
 			.fl_gre_key = tunnel->parms.o_key
 		};
-		struct rtable *rt;
+		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
 
-		if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
+		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
 			ip_rt_put(rt);
 		}
@@ -1215,9 +1216,9 @@ static int ipgre_open(struct net_device *dev)
 			.proto = IPPROTO_GRE,
 			.fl_gre_key = t->parms.o_key
 		};
-		struct rtable *rt;
+		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
 
-		if (ip_route_output_key(dev_net(dev), &rt, &fl))
+		if (IS_ERR(rt))
 			return -EADDRNOTAVAIL;
 		dev = rt->dst.dev;
 		ip_rt_put(rt);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 33316b3534ca..171f483b21d5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -355,7 +355,8 @@ int ip_queue_xmit(struct sk_buff *skb)
 			 * itself out.
 			 */
 			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk))
+			rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+			if (IS_ERR(rt))
 				goto no_route;
 		}
 		sk_setup_caps(sk, &rt->dst);
@@ -1489,7 +1490,8 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 				    .proto = sk->sk_protocol,
 				    .flags = ip_reply_arg_flowi_flags(arg) };
 		security_skb_classify_flow(skb, &fl);
-		if (ip_route_output_key(sock_net(sk), &rt, &fl))
+		rt = ip_route_output_key(sock_net(sk), &fl);
+		if (IS_ERR(rt))
 			return;
 	}
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 988f52fba54a..e1e17576baa6 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -469,7 +469,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			.proto = IPPROTO_IPIP
 		};
 
-		if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
+		rt = ip_route_output_key(dev_net(dev), &fl);
+		if (IS_ERR(rt)) {
 			dev->stats.tx_carrier_errors++;
 			goto tx_error_icmp;
 		}
@@ -590,9 +591,9 @@ static void ipip_tunnel_bind_dev(struct net_device *dev)
 			.fl4_tos = RT_TOS(iph->tos),
 			.proto = IPPROTO_IPIP
 		};
-		struct rtable *rt;
+		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
 
-		if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
+		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
 			ip_rt_put(rt);
 		}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8b65a12654e7..26ca2f2d37ce 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1618,8 +1618,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 			.fl4_tos = RT_TOS(iph->tos),
 			.proto = IPPROTO_IPIP
 		};
-
-		if (ip_route_output_key(net, &rt, &fl))
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			goto out_free;
 		encap = sizeof(struct iphdr);
 	} else {
@@ -1629,8 +1629,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 			.fl4_tos = RT_TOS(iph->tos),
 			.proto = IPPROTO_IPIP
 		};
-
-		if (ip_route_output_key(net, &rt, &fl))
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			goto out_free;
 	}
 
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 9770bb427952..67bf709180de 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -38,7 +38,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 		fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
 		fl.mark = skb->mark;
 		fl.flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
-		if (ip_route_output_key(net, &rt, &fl) != 0)
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			return -1;
 
 		/* Drop old route. */
@@ -48,7 +49,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 		/* non-local src, find valid iif to satisfy
 		 * rp-filter when calling ip_route_input. */
 		fl.fl4_dst = iph->saddr;
-		if (ip_route_output_key(net, &rt, &fl) != 0)
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			return -1;
 
 		orefdst = skb->_skb_refdst;
@@ -221,7 +223,11 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
 
 static int nf_ip_route(struct dst_entry **dst, struct flowi *fl)
 {
-	return ip_route_output_key(&init_net, (struct rtable **)dst, fl);
+	struct rtable *rt = ip_route_output_key(&init_net, fl);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+	*dst = &rt->dst;
+	return 0;
 }
 
 static const struct nf_afinfo nf_ip_afinfo = {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index d7a2d1eaec09..467d570d087a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -564,10 +564,12 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk);
+		rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+		if (IS_ERR(rt)) {
+			err = PTR_ERR(rt);
+			goto done;
+		}
 	}
-	if (err)
-		goto done;
 
 	err = -EACCES;
 	if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 63d37004ee66..5090e956f6b8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1014,8 +1014,8 @@ static int slow_chain_length(const struct rtable *head)
 	return length >> FRACT_BITS;
 }
 
-static int rt_intern_hash(unsigned hash, struct rtable *rt,
-			  struct rtable **rp, struct sk_buff *skb, int ifindex)
+static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt,
+				     struct sk_buff *skb, int ifindex)
 {
 	struct rtable	*rth, *cand;
 	struct rtable __rcu **rthp, **candp;
@@ -1056,7 +1056,7 @@ restart:
 					printk(KERN_WARNING
 					    "Neighbour table failure & not caching routes.\n");
 				ip_rt_put(rt);
-				return err;
+				return ERR_PTR(err);
 			}
 		}
 
@@ -1093,11 +1093,9 @@ restart:
 			spin_unlock_bh(rt_hash_lock_addr(hash));
 
 			rt_drop(rt);
-			if (rp)
-				*rp = rth;
-			else
+			if (skb)
 				skb_dst_set(skb, &rth->dst);
-			return 0;
+			return rth;
 		}
 
 		if (!atomic_read(&rth->dst.__refcnt)) {
@@ -1154,7 +1152,7 @@ restart:
 
 			if (err != -ENOBUFS) {
 				rt_drop(rt);
-				return err;
+				return ERR_PTR(err);
 			}
 
 			/* Neighbour tables are full and nothing
@@ -1175,7 +1173,7 @@ restart:
 			if (net_ratelimit())
 				printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
 			rt_drop(rt);
-			return -ENOBUFS;
+			return ERR_PTR(-ENOBUFS);
 		}
 	}
 
@@ -1201,11 +1199,9 @@ restart:
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 
 skip_hashing:
-	if (rp)
-		*rp = rt;
-	else
+	if (skb)
 		skb_dst_set(skb, &rt->dst);
-	return 0;
+	return rt;
 }
 
 static atomic_t __rt_peer_genid = ATOMIC_INIT(0);
@@ -1896,7 +1892,10 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	RT_CACHE_STAT_INC(in_slow_mc);
 
 	hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
-	return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
+	rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
+	err = 0;
+	if (IS_ERR(rth))
+		err = PTR_ERR(rth);
 
 e_nobufs:
 	return -ENOBUFS;
@@ -2051,7 +2050,10 @@ static int ip_mkroute_input(struct sk_buff *skb,
 	/* put it into the cache */
 	hash = rt_hash(daddr, saddr, fl->iif,
 		       rt_genid(dev_net(rth->dst.dev)));
-	return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
+	rth = rt_intern_hash(hash, rth, skb, fl->iif);
+	if (IS_ERR(rth))
+		return PTR_ERR(rth);
+	return 0;
 }
 
 /*
@@ -2194,7 +2196,10 @@ local_input:
 	}
 	rth->rt_type	= res.type;
 	hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
-	err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
+	rth = rt_intern_hash(hash, rth, skb, fl.iif);
+	err = 0;
+	if (IS_ERR(rth))
+		err = PTR_ERR(rth);
 	goto out;
 
 no_route:
@@ -2422,8 +2427,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
  * called with rcu_read_lock();
  */
 
-static int ip_route_output_slow(struct net *net, struct rtable **rp,
-				const struct flowi *oldflp)
+static struct rtable *ip_route_output_slow(struct net *net,
+					   const struct flowi *oldflp)
 {
 	u32 tos	= RT_FL_TOS(oldflp);
 	struct flowi fl = { .fl4_dst = oldflp->fl4_dst,
@@ -2438,8 +2443,6 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 	unsigned int flags = 0;
 	struct net_device *dev_out = NULL;
 	struct rtable *rth;
-	int err;
-
 
 	res.fi		= NULL;
 #ifdef CONFIG_IP_MULTIPLE_TABLES
@@ -2448,7 +2451,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 
 	rcu_read_lock();
 	if (oldflp->fl4_src) {
-		err = -EINVAL;
+		rth = ERR_PTR(-EINVAL);
 		if (ipv4_is_multicast(oldflp->fl4_src) ||
 		    ipv4_is_lbcast(oldflp->fl4_src) ||
 		    ipv4_is_zeronet(oldflp->fl4_src))
@@ -2499,13 +2502,13 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 
 	if (oldflp->oif) {
 		dev_out = dev_get_by_index_rcu(net, oldflp->oif);
-		err = -ENODEV;
+		rth = ERR_PTR(-ENODEV);
 		if (dev_out == NULL)
 			goto out;
 
 		/* RACE: Check return value of inet_select_addr instead. */
 		if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
-			err = -ENETUNREACH;
+			rth = ERR_PTR(-ENETUNREACH);
 			goto out;
 		}
 		if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
@@ -2563,7 +2566,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 			res.type = RTN_UNICAST;
 			goto make_route;
 		}
-		err = -ENETUNREACH;
+		rth = ERR_PTR(-ENETUNREACH);
 		goto out;
 	}
 
@@ -2598,23 +2601,20 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
 
 make_route:
 	rth = __mkroute_output(&res, &fl, oldflp, dev_out, flags);
-	if (IS_ERR(rth))
-		err = PTR_ERR(rth);
-	else {
+	if (!IS_ERR(rth)) {
 		unsigned int hash;
 
 		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
 			       rt_genid(dev_net(dev_out)));
-		err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
+		rth = rt_intern_hash(hash, rth, NULL, oldflp->oif);
 	}
 
 out:
 	rcu_read_unlock();
-	return err;
+	return rth;
 }
 
-int __ip_route_output_key(struct net *net, struct rtable **rp,
-			  const struct flowi *flp)
+struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
 {
 	struct rtable *rth;
 	unsigned int hash;
@@ -2639,15 +2639,14 @@ int __ip_route_output_key(struct net *net, struct rtable **rp,
 			dst_use(&rth->dst, jiffies);
 			RT_CACHE_STAT_INC(out_hit);
 			rcu_read_unlock_bh();
-			*rp = rth;
-			return 0;
+			return rth;
 		}
 		RT_CACHE_STAT_INC(out_hlist_search);
 	}
 	rcu_read_unlock_bh();
 
 slow_output:
-	return ip_route_output_slow(net, rp, flp);
+	return ip_route_output_slow(net, flp);
 }
 EXPORT_SYMBOL_GPL(__ip_route_output_key);
 
@@ -2717,34 +2716,29 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 	return rt ? &rt->dst : ERR_PTR(-ENOMEM);
 }
 
-int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
-			 struct sock *sk)
+struct rtable *ip_route_output_flow(struct net *net, struct flowi *flp,
+				    struct sock *sk)
 {
-	int err;
+	struct rtable *rt = __ip_route_output_key(net, flp);
 
-	if ((err = __ip_route_output_key(net, rp, flp)) != 0)
-		return err;
+	if (IS_ERR(rt))
+		return rt;
 
 	if (flp->proto) {
 		if (!flp->fl4_src)
-			flp->fl4_src = (*rp)->rt_src;
+			flp->fl4_src = rt->rt_src;
 		if (!flp->fl4_dst)
-			flp->fl4_dst = (*rp)->rt_dst;
-		*rp = (struct rtable *) xfrm_lookup(net, &(*rp)->dst, flp, sk, 0);
-		if (IS_ERR(*rp)) {
-			err = PTR_ERR(*rp);
-			*rp = NULL;
-			return err;
-		}
+			flp->fl4_dst = rt->rt_dst;
+		rt = (struct rtable *) xfrm_lookup(net, &rt->dst, flp, sk, 0);
 	}
 
-	return 0;
+	return rt;
 }
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
-int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
+struct rtable *ip_route_output_key(struct net *net, struct flowi *flp)
 {
-	return ip_route_output_flow(net, rp, flp, NULL);
+	return ip_route_output_flow(net, flp, NULL);
 }
 EXPORT_SYMBOL(ip_route_output_key);
 
@@ -2915,7 +2909,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 			.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
 			.mark = mark,
 		};
-		err = ip_route_output_key(net, &rt, &fl);
+		rt = ip_route_output_key(net, &fl);
+
+		err = 0;
+		if (IS_ERR(rt))
+			err = PTR_ERR(rt);
 	}
 
 	if (err)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 47519205a014..0ad6ddf638a7 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 				    .fl_ip_sport = th->dest,
 				    .fl_ip_dport = th->source };
 		security_req_classify_flow(req, &fl);
-		if (ip_route_output_key(sock_net(sk), &rt, &fl)) {
+		rt = ip_route_output_key(sock_net(sk), &fl);
+		if (IS_ERR(rt)) {
 			reqsk_free(req);
 			goto out;
 		}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 05bc6d9455fc..f7e6c2c2d2bb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -152,7 +152,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	__be16 orig_sport, orig_dport;
 	struct rtable *rt;
 	__be32 daddr, nexthop;
-	int tmp;
 	int err;
 
 	if (addr_len < sizeof(struct sockaddr_in))
@@ -170,14 +169,15 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	orig_sport = inet->inet_sport;
 	orig_dport = usin->sin_port;
-	tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
-			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
-			       IPPROTO_TCP,
-			       orig_sport, orig_dport, sk, true);
-	if (tmp < 0) {
-		if (tmp == -ENETUNREACH)
+	rt = ip_route_connect(nexthop, inet->inet_saddr,
+			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
+			      IPPROTO_TCP,
+			      orig_sport, orig_dport, sk, true);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		if (err == -ENETUNREACH)
 			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
-		return tmp;
+		return err;
 	}
 
 	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
@@ -236,12 +236,14 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (err)
 		goto failure;
 
-	err = ip_route_newports(&rt, IPPROTO_TCP,
-				orig_sport, orig_dport,
-				inet->inet_sport, inet->inet_dport, sk);
-	if (err)
+	rt = ip_route_newports(rt, IPPROTO_TCP,
+			       orig_sport, orig_dport,
+			       inet->inet_sport, inet->inet_dport, sk);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		rt = NULL;
 		goto failure;
-
+	}
 	/* OK, now commit destination to socket.  */
 	sk->sk_gso_type = SKB_GSO_TCPV4;
 	sk_setup_caps(sk, &rt->dst);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ed9a5b7bee53..95e0c2c194a1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -922,8 +922,9 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		struct net *net = sock_net(sk);
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(net, &rt, &fl, sk);
-		if (err) {
+		rt = ip_route_output_flow(net, &fl, sk);
+		if (IS_ERR(rt)) {
+			err = PTR_ERR(rt);
 			if (err == -ENETUNREACH)
 				IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
 			goto out;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 5f0f058dc376..45b821480427 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -26,18 +26,16 @@ static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
 		.fl4_dst = daddr->a4,
 		.fl4_tos = tos,
 	};
-	struct dst_entry *dst;
 	struct rtable *rt;
-	int err;
 
 	if (saddr)
 		fl.fl4_src = saddr->a4;
 
-	err = __ip_route_output_key(net, &rt, &fl);
-	dst = &rt->dst;
-	if (err)
-		dst = ERR_PTR(err);
-	return dst;
+	rt = __ip_route_output_key(net, &fl);
+	if (!IS_ERR(rt))
+		return &rt->dst;
+
+	return ERR_CAST(rt);
 }
 
 static int xfrm4_get_saddr(struct net *net,
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index da43038ae18e..02730ef26b0f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -581,7 +581,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	fl.fl4_dst = eiph->saddr;
 	fl.fl4_tos = RT_TOS(eiph->tos);
 	fl.proto = IPPROTO_IPIP;
-	if (ip_route_output_key(dev_net(skb->dev), &rt, &fl))
+	rt = ip_route_output_key(dev_net(skb->dev), &fl);
+	if (IS_ERR(rt))
 		goto out;
 
 	skb2->dev = rt->dst.dev;
@@ -593,12 +594,14 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		fl.fl4_dst = eiph->daddr;
 		fl.fl4_src = eiph->saddr;
 		fl.fl4_tos = eiph->tos;
-		if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) ||
+		rt = ip_route_output_key(dev_net(skb->dev), &fl);
+		if (IS_ERR(rt) ||
 		    rt->dst.dev->type != ARPHRD_TUNNEL) {
-			ip_rt_put(rt);
+			if (!IS_ERR(rt))
+				ip_rt_put(rt);
 			goto out;
 		}
-		skb_dst_set(skb2, (struct dst_entry *)rt);
+		skb_dst_set(skb2, &rt->dst);
 	} else {
 		ip_rt_put(rt);
 		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b1599a345c10..b8c8adbd7cf6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -738,7 +738,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 				    .fl4_tos = RT_TOS(tos),
 				    .oif = tunnel->parms.link,
 				    .proto = IPPROTO_IPV6 };
-		if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
+		rt = ip_route_output_key(dev_net(dev), &fl);
+		if (IS_ERR(rt)) {
 			dev->stats.tx_carrier_errors++;
 			goto tx_error_icmp;
 		}
@@ -862,8 +863,9 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 				    .fl4_tos = RT_TOS(iph->tos),
 				    .oif = tunnel->parms.link,
 				    .proto = IPPROTO_IPV6 };
-		struct rtable *rt;
-		if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
+		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
+
+		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
 			ip_rt_put(rt);
 		}
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 5381cebe516d..2a698ff89db6 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -320,11 +320,12 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	if (ipv4_is_multicast(lsa->l2tp_addr.s_addr))
 		goto out;
 
-	rc = ip_route_connect(&rt, lsa->l2tp_addr.s_addr, saddr,
+	rt = ip_route_connect(lsa->l2tp_addr.s_addr, saddr,
 			      RT_CONN_FLAGS(sk), oif,
 			      IPPROTO_L2TP,
 			      0, 0, sk, true);
-	if (rc) {
+	if (IS_ERR(rt)) {
+		rc = PTR_ERR(rt);
 		if (rc == -ENETUNREACH)
 			IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES);
 		goto out;
@@ -489,7 +490,8 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 			 * itself out.
 			 */
 			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk))
+			rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+			if (IS_ERR(rt))
 				goto no_route;
 		}
 		sk_setup_caps(sk, &rt->dst);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 6264219f0a42..878f6dd9dbad 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -103,7 +103,8 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 				.fl4_tos = rtos,
 			};
 
-			if (ip_route_output_key(net, &rt, &fl)) {
+			rt = ip_route_output_key(net, &fl);
+			if (IS_ERR(rt)) {
 				spin_unlock(&dest->dst_lock);
 				IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
 					     &dest->addr.ip);
@@ -121,7 +122,8 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 			.fl4_tos = rtos,
 		};
 
-		if (ip_route_output_key(net, &rt, &fl)) {
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt)) {
 			IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
 				     &daddr);
 			return NULL;
@@ -180,7 +182,8 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 			.mark = skb->mark,
 		};
 
-		if (ip_route_output_key(net, &rt, &fl))
+		rt = ip_route_output_key(net, &fl);
+		if (IS_ERR(rt))
 			return 0;
 		if (!(rt->rt_flags & RTCF_LOCAL)) {
 			ip_rt_put(rt);
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 5128a6c4cb2c..624725b5286f 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -73,7 +73,8 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	fl.fl4_dst = info->gw.ip;
 	fl.fl4_tos = RT_TOS(iph->tos);
 	fl.fl4_scope = RT_SCOPE_UNIVERSE;
-	if (ip_route_output_key(net, &rt, &fl) != 0)
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
 		return false;
 
 	skb_dst_drop(skb);
diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c
index a53fb25a64ed..3620c569275f 100644
--- a/net/rxrpc/ar-peer.c
+++ b/net/rxrpc/ar-peer.c
@@ -37,7 +37,6 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
 {
 	struct rtable *rt;
 	struct flowi fl;
-	int ret;
 
 	peer->if_mtu = 1500;
 
@@ -58,9 +57,9 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
 		BUG();
 	}
 
-	ret = ip_route_output_key(&init_net, &rt, &fl);
-	if (ret < 0) {
-		_leave(" [route err %d]", ret);
+	rt = ip_route_output_key(&init_net, &fl);
+	if (IS_ERR(rt)) {
+		_leave(" [route err %ld]", PTR_ERR(rt));
 		return;
 	}
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e58f9476f29c..4e55e6c49ec9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -491,9 +491,9 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 	SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ",
 			  __func__, &fl.fl4_dst, &fl.fl4_src);
 
-	if (!ip_route_output_key(&init_net, &rt, &fl)) {
+	rt = ip_route_output_key(&init_net, &fl);
+	if (!IS_ERR(rt))
 		dst = &rt->dst;
-	}
 
 	/* If there is no association or if a source address is passed, no
 	 * more validation is required.
@@ -535,7 +535,8 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 		    (AF_INET == laddr->a.sa.sa_family)) {
 			fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
 			fl.fl_ip_sport = laddr->a.v4.sin_port;
-			if (!ip_route_output_key(&init_net, &rt, &fl)) {
+			rt = ip_route_output_key(&init_net, &fl);
+			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
 				goto out_unlock;
 			}
-- 
cgit v1.2.3


From 5bfa787fb2c29cce0722500f90df29e049ff07fc Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 2 Mar 2011 14:56:30 -0800
Subject: ipv4: ip_route_output_key() is better as an inline.

This avoid a stack frame at zero cost.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 6 +++++-
 net/ipv4/route.c    | 6 ------
 2 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index 088a1867348f..60daf745216a 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -119,11 +119,15 @@ extern void		ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
 extern void		rt_cache_flush(struct net *net, int how);
 extern void		rt_cache_flush_batch(struct net *net);
 extern struct rtable *__ip_route_output_key(struct net *, const struct flowi *flp);
-extern struct rtable *ip_route_output_key(struct net *, struct flowi *flp);
 extern struct rtable *ip_route_output_flow(struct net *, struct flowi *flp,
 					   struct sock *sk);
 extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
 
+static inline struct rtable *ip_route_output_key(struct net *net, struct flowi *flp)
+{
+	return ip_route_output_flow(net, flp, NULL);
+}
+
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin, bool noref);
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5090e956f6b8..432eee645648 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2736,12 +2736,6 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi *flp,
 }
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
-struct rtable *ip_route_output_key(struct net *net, struct flowi *flp)
-{
-	return ip_route_output_flow(net, flp, NULL);
-}
-EXPORT_SYMBOL(ip_route_output_key);
-
 static int rt_fill_info(struct net *net,
 			struct sk_buff *skb, u32 pid, u32 seq, int event,
 			int nowait, unsigned int flags)
-- 
cgit v1.2.3


From 23b41168fc942a4a041325a04ecc1bd17d031a3e Mon Sep 17 00:00:00 2001
From: Vlad Dogaru <ddvlad@rosedu.org>
Date: Sat, 26 Feb 2011 22:39:12 +0000
Subject: netdevice: make initial group visible to userspace

INIT_NETDEV_GROUP is needed by userspace, move it outside __KERNEL__
guards.

Signed-off-by: Vlad Dogaru <ddvlad@rosedu.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ffe56c16df8a..8be4056ad251 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -75,9 +75,6 @@ struct wireless_dev;
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
-/* Initial net device group. All devices belong to group 0 by default. */
-#define INIT_NETDEV_GROUP	0
-
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -141,6 +138,9 @@ static inline bool dev_xmit_complete(int rc)
 
 #define MAX_ADDR_LEN	32		/* Largest hardware address length */
 
+/* Initial net device group. All devices belong to group 0 by default. */
+#define INIT_NETDEV_GROUP	0
+
 #ifdef  __KERNEL__
 /*
  *	Compute the worst case header length according to the protocols
-- 
cgit v1.2.3


From eed84713bc47ce2f7d675914f297ad9b6227a587 Mon Sep 17 00:00:00 2001
From: Shmulik Ravid <shmulikr@broadcom.com>
Date: Sun, 27 Feb 2011 05:04:31 +0000
Subject: dcbnl: add support for retrieving peer configuration - ieee

These 2 patches add the support for retrieving the remote or peer DCBX
configuration via dcbnl for embedded DCBX stacks. The peer configuration
is part of the DCBX MIB and is useful for debugging and diagnostics of
the overall DCB configuration. The first patch add this support for IEEE
802.1Qaz standard the second patch add the same support for the older
CEE standard. Diff for v2 - the peer-app-info is CEE specific.

Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dcbnl.h | 28 +++++++++++++++++++++
 include/net/dcbnl.h   |  6 +++++
 net/dcb/dcbnl.c       | 69 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 103 insertions(+)

(limited to 'include')

diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 4c5b26e0cc48..2542685f8b3e 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -110,6 +110,20 @@ struct dcb_app {
 	__u16	protocol;
 };
 
+/**
+ * struct dcb_peer_app_info - APP feature information sent by the peer
+ *
+ * @willing: willing bit in the peer APP tlv
+ * @error: error bit in the peer APP tlv
+ *
+ * In addition to this information the full peer APP tlv also contains
+ * a table of 'app_count' APP objects defined above.
+ */
+struct dcb_peer_app_info {
+	__u8	willing;
+	__u8	error;
+};
+
 struct dcbmsg {
 	__u8               dcb_family;
 	__u8               cmd;
@@ -235,11 +249,25 @@ enum dcbnl_attrs {
 	DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
 };
 
+/**
+ * enum ieee_attrs - IEEE 802.1Qaz get/set attributes
+ *
+ * @DCB_ATTR_IEEE_UNSPEC: unspecified
+ * @DCB_ATTR_IEEE_ETS: negotiated ETS configuration
+ * @DCB_ATTR_IEEE_PFC: negotiated PFC configuration
+ * @DCB_ATTR_IEEE_APP_TABLE: negotiated APP configuration
+ * @DCB_ATTR_IEEE_PEER_ETS: peer ETS configuration - get only
+ * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only
+ * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only
+ */
 enum ieee_attrs {
 	DCB_ATTR_IEEE_UNSPEC,
 	DCB_ATTR_IEEE_ETS,
 	DCB_ATTR_IEEE_PFC,
 	DCB_ATTR_IEEE_APP_TABLE,
+	DCB_ATTR_IEEE_PEER_ETS,
+	DCB_ATTR_IEEE_PEER_PFC,
+	DCB_ATTR_IEEE_PEER_APP,
 	__DCB_ATTR_IEEE_MAX
 };
 #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1)
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index a8e7852b10ab..7b7180e692ef 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -43,6 +43,8 @@ struct dcbnl_rtnl_ops {
 	int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *);
 	int (*ieee_getapp) (struct net_device *, struct dcb_app *);
 	int (*ieee_setapp) (struct net_device *, struct dcb_app *);
+	int (*ieee_peer_getets) (struct net_device *, struct ieee_ets *);
+	int (*ieee_peer_getpfc) (struct net_device *, struct ieee_pfc *);
 
 	/* CEE std */
 	u8   (*getstate)(struct net_device *);
@@ -77,6 +79,10 @@ struct dcbnl_rtnl_ops {
 	u8   (*getdcbx)(struct net_device *);
 	u8   (*setdcbx)(struct net_device *, u8);
 
+	/* peer apps */
+	int (*peer_getappinfo)(struct net_device *, struct dcb_peer_app_info *,
+			       u16 *);
+	int (*peer_getapptable)(struct net_device *, struct dcb_app *);
 
 };
 
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index d5074a567289..2e6dcf2967e2 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1224,6 +1224,54 @@ err:
 	return err;
 }
 
+static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb)
+{
+	struct dcb_peer_app_info info;
+	struct dcb_app *table = NULL;
+	const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
+	u16 app_count;
+	int err;
+
+
+	/**
+	 * retrieve the peer app configuration form the driver. If the driver
+	 * handlers fail exit without doing anything
+	 */
+	err = ops->peer_getappinfo(netdev, &info, &app_count);
+	if (!err && app_count) {
+		table = kmalloc(sizeof(struct dcb_app) * app_count, GFP_KERNEL);
+		if (!table)
+			return -ENOMEM;
+
+		err = ops->peer_getapptable(netdev, table);
+	}
+
+	if (!err) {
+		u16 i;
+		struct nlattr *app;
+
+		/**
+		 * build the message, from here on the only possible failure
+		 * is due to the skb size
+		 */
+		err = -EMSGSIZE;
+
+		app = nla_nest_start(skb, DCB_ATTR_IEEE_PEER_APP);
+		if (!app)
+			goto nla_put_failure;
+
+		for (i = 0; i < app_count; i++)
+			NLA_PUT(skb, DCB_ATTR_IEEE_APP, sizeof(struct dcb_app),
+				&table[i]);
+
+		nla_nest_end(skb, app);
+	}
+	err = 0;
+
+nla_put_failure:
+	kfree(table);
+	return err;
+}
 
 /* Handle IEEE 802.1Qaz GET commands. */
 static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
@@ -1288,6 +1336,27 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
 	spin_unlock(&dcb_lock);
 	nla_nest_end(skb, app);
 
+	/* get peer info if available */
+	if (ops->ieee_peer_getets) {
+		struct ieee_ets ets;
+		err = ops->ieee_peer_getets(netdev, &ets);
+		if (!err)
+			NLA_PUT(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets);
+	}
+
+	if (ops->ieee_peer_getpfc) {
+		struct ieee_pfc pfc;
+		err = ops->ieee_peer_getpfc(netdev, &pfc);
+		if (!err)
+			NLA_PUT(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc);
+	}
+
+	if (ops->peer_getappinfo && ops->peer_getapptable) {
+		err = dcbnl_build_peer_app(netdev, skb);
+		if (err)
+			goto nla_put_failure;
+	}
+
 	nla_nest_end(skb, ieee);
 	nlmsg_end(skb, nlh);
 
-- 
cgit v1.2.3


From dc6ed1df5a5f84e45e77e2acb6fd99b995414956 Mon Sep 17 00:00:00 2001
From: Shmulik Ravid <shmulikr@broadcom.com>
Date: Sun, 27 Feb 2011 05:04:38 +0000
Subject: dcbnl: add support for retrieving peer configuration - cee

This patch adds the support for retrieving the remote or peer DCBX
configuration via dcbnl for embedded DCBX stacks supporting the CEE DCBX
standard.

Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dcbnl.h | 71 ++++++++++++++++++++++++++++++++++++++++++
 include/net/dcbnl.h   |  3 ++
 net/dcb/dcbnl.c       | 85 ++++++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 155 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 2542685f8b3e..a3680a16718f 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -87,6 +87,45 @@ struct ieee_pfc {
 	__u64	indications[IEEE_8021QAZ_MAX_TCS];
 };
 
+/* CEE DCBX std supported values */
+#define CEE_DCBX_MAX_PGS	8
+#define CEE_DCBX_MAX_PRIO	8
+
+/**
+ * struct cee_pg - CEE Prioity-Group managed object
+ *
+ * @willing: willing bit in the PG tlv
+ * @error: error bit in the PG tlv
+ * @pg_en: enable bit of the PG feature
+ * @tcs_supported: number of traffic classes supported
+ * @pg_bw: bandwidth percentage for each priority group
+ * @prio_pg: priority to PG mapping indexed by priority
+ */
+struct cee_pg {
+	__u8    willing;
+	__u8    error;
+	__u8    pg_en;
+	__u8    tcs_supported;
+	__u8    pg_bw[CEE_DCBX_MAX_PGS];
+	__u8    prio_pg[CEE_DCBX_MAX_PGS];
+};
+
+/**
+ * struct cee_pfc - CEE PFC managed object
+ *
+ * @willing: willing bit in the PFC tlv
+ * @error: error bit in the PFC tlv
+ * @pfc_en: bitmap indicating pfc enabled traffic classes
+ * @tcs_supported: number of traffic classes supported
+ */
+struct cee_pfc {
+	__u8    willing;
+	__u8    error;
+	__u8    pfc_en;
+	__u8    tcs_supported;
+};
+
+
 /* This structure contains the IEEE 802.1Qaz APP managed object. This
  * object is also used for the CEE std as well. There is no difference
  * between the objects.
@@ -158,6 +197,7 @@ struct dcbmsg {
  * @DCB_CMD_SDCBX: set DCBX engine configuration
  * @DCB_CMD_GFEATCFG: get DCBX features flags
  * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags
+ * @DCB_CMD_CEE_GET: get CEE aggregated configuration
  */
 enum dcbnl_commands {
 	DCB_CMD_UNDEFINED,
@@ -200,6 +240,8 @@ enum dcbnl_commands {
 	DCB_CMD_GFEATCFG,
 	DCB_CMD_SFEATCFG,
 
+	DCB_CMD_CEE_GET,
+
 	__DCB_CMD_ENUM_MAX,
 	DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
 };
@@ -222,6 +264,7 @@ enum dcbnl_commands {
  * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED)
  * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8)
  * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED)
+ * @DCB_ATTR_CEE: CEE std supported attributes (NLA_NESTED)
  */
 enum dcbnl_attrs {
 	DCB_ATTR_UNDEFINED,
@@ -245,6 +288,9 @@ enum dcbnl_attrs {
 	DCB_ATTR_DCBX,
 	DCB_ATTR_FEATCFG,
 
+	/* CEE nested attributes */
+	DCB_ATTR_CEE,
+
 	__DCB_ATTR_ENUM_MAX,
 	DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
 };
@@ -279,6 +325,31 @@ enum ieee_attrs_app {
 };
 #define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1)
 
+/**
+ * enum cee_attrs - CEE DCBX get attributes
+ *
+ * @DCB_ATTR_CEE_UNSPEC: unspecified
+ * @DCB_ATTR_CEE_PEER_PG: peer PG configuration - get only
+ * @DCB_ATTR_CEE_PEER_PFC: peer PFC configuration - get only
+ * @DCB_ATTR_CEE_PEER_APP: peer APP tlv - get only
+ */
+enum cee_attrs {
+	DCB_ATTR_CEE_UNSPEC,
+	DCB_ATTR_CEE_PEER_PG,
+	DCB_ATTR_CEE_PEER_PFC,
+	DCB_ATTR_CEE_PEER_APP_TABLE,
+	__DCB_ATTR_CEE_MAX
+};
+#define DCB_ATTR_CEE_MAX (__DCB_ATTR_CEE_MAX - 1)
+
+enum peer_app_attr {
+	DCB_ATTR_CEE_PEER_APP_UNSPEC,
+	DCB_ATTR_CEE_PEER_APP_INFO,
+	DCB_ATTR_CEE_PEER_APP,
+	__DCB_ATTR_CEE_PEER_APP_MAX
+};
+#define DCB_ATTR_CEE_PEER_APP_MAX (__DCB_ATTR_CEE_PEER_APP_MAX - 1)
+
 /**
  * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs
  *
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index 7b7180e692ef..e5983c9053dc 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -84,6 +84,9 @@ struct dcbnl_rtnl_ops {
 			       u16 *);
 	int (*peer_getapptable)(struct net_device *, struct dcb_app *);
 
+	/* CEE peer */
+	int (*cee_peer_getpg) (struct net_device *, struct cee_pg *);
+	int (*cee_peer_getpfc) (struct net_device *, struct cee_pfc *);
 };
 
 #endif /* __NET_DCBNL_H__ */
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 2e6dcf2967e2..d8b4f725b778 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1224,7 +1224,9 @@ err:
 	return err;
 }
 
-static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb)
+static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb,
+				int app_nested_type, int app_info_type,
+				int app_entry_type)
 {
 	struct dcb_peer_app_info info;
 	struct dcb_app *table = NULL;
@@ -1256,12 +1258,15 @@ static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb)
 		 */
 		err = -EMSGSIZE;
 
-		app = nla_nest_start(skb, DCB_ATTR_IEEE_PEER_APP);
+		app = nla_nest_start(skb, app_nested_type);
 		if (!app)
 			goto nla_put_failure;
 
+		if (app_info_type)
+			NLA_PUT(skb, app_info_type, sizeof(info), &info);
+
 		for (i = 0; i < app_count; i++)
-			NLA_PUT(skb, DCB_ATTR_IEEE_APP, sizeof(struct dcb_app),
+			NLA_PUT(skb, app_entry_type, sizeof(struct dcb_app),
 				&table[i]);
 
 		nla_nest_end(skb, app);
@@ -1352,7 +1357,10 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
 	}
 
 	if (ops->peer_getappinfo && ops->peer_getapptable) {
-		err = dcbnl_build_peer_app(netdev, skb);
+		err = dcbnl_build_peer_app(netdev, skb,
+					   DCB_ATTR_IEEE_PEER_APP,
+					   DCB_ATTR_IEEE_APP_UNSPEC,
+					   DCB_ATTR_IEEE_APP);
 		if (err)
 			goto nla_put_failure;
 	}
@@ -1510,6 +1518,71 @@ err:
 	return ret;
 }
 
+/* Handle CEE DCBX GET commands. */
+static int dcbnl_cee_get(struct net_device *netdev, struct nlattr **tb,
+			 u32 pid, u32 seq, u16 flags)
+{
+	struct sk_buff *skb;
+	struct nlmsghdr *nlh;
+	struct dcbmsg *dcb;
+	struct nlattr *cee;
+	const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
+	int err;
+
+	if (!ops)
+		return -EOPNOTSUPP;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	nlh = NLMSG_NEW(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+	dcb = NLMSG_DATA(nlh);
+	dcb->dcb_family = AF_UNSPEC;
+	dcb->cmd = DCB_CMD_CEE_GET;
+
+	NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name);
+
+	cee = nla_nest_start(skb, DCB_ATTR_CEE);
+	if (!cee)
+		goto nla_put_failure;
+
+	/* get peer info if available */
+	if (ops->cee_peer_getpg) {
+		struct cee_pg pg;
+		err = ops->cee_peer_getpg(netdev, &pg);
+		if (!err)
+			NLA_PUT(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg);
+	}
+
+	if (ops->cee_peer_getpfc) {
+		struct cee_pfc pfc;
+		err = ops->cee_peer_getpfc(netdev, &pfc);
+		if (!err)
+			NLA_PUT(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc);
+	}
+
+	if (ops->peer_getappinfo && ops->peer_getapptable) {
+		err = dcbnl_build_peer_app(netdev, skb,
+					   DCB_ATTR_CEE_PEER_APP_TABLE,
+					   DCB_ATTR_CEE_PEER_APP_INFO,
+					   DCB_ATTR_CEE_PEER_APP);
+		if (err)
+			goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, cee);
+	nlmsg_end(skb, nlh);
+
+	return rtnl_unicast(skb, &init_net, pid);
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+nlmsg_failure:
+	kfree_skb(skb);
+	return -1;
+}
+
 static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 {
 	struct net *net = sock_net(skb->sk);
@@ -1639,6 +1712,10 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 		ret = dcbnl_setfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
 				       nlh->nlmsg_flags);
 		goto out;
+	case DCB_CMD_CEE_GET:
+		ret = dcbnl_cee_get(netdev, tb, pid, nlh->nlmsg_seq,
+				    nlh->nlmsg_flags);
+		goto out;
 	default:
 		goto errout;
 	}
-- 
cgit v1.2.3


From f009918a1c1bbf8607b8aab3959876913a30193a Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@au1.ibm.com>
Date: Mon, 28 Feb 2011 03:27:53 +0000
Subject: RxRPC: Fix v1 keys

commit 339412841d7 (RxRPC: Allow key payloads to be passed in XDR form)
broke klog for me. I notice the v1 key struct had a kif_version field
added:

-struct rxkad_key {
-       u16     security_index;         /* RxRPC header security index */
-       u16     ticket_len;             /* length of ticket[] */
-       u32     expiry;                 /* time at which expires */
-       u32     kvno;                   /* key version number */
-       u8      session_key[8];         /* DES session key */
-       u8      ticket[0];              /* the encrypted ticket */
-};

+struct rxrpc_key_data_v1 {
+       u32             kif_version;            /* 1 */
+       u16             security_index;
+       u16             ticket_length;
+       u32             expiry;                 /* time_t */
+       u32             kvno;
+       u8              session_key[8];
+       u8              ticket[0];
+};

However the code in rxrpc_instantiate strips it away:

	data += sizeof(kver);
	datalen -= sizeof(kver);

Removing kif_version fixes my problem.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/keys/rxrpc-type.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/keys/rxrpc-type.h b/include/keys/rxrpc-type.h
index 5cb86c307f5d..fc4875433817 100644
--- a/include/keys/rxrpc-type.h
+++ b/include/keys/rxrpc-type.h
@@ -99,7 +99,6 @@ struct rxrpc_key_token {
  * structure of raw payloads passed to add_key() or instantiate key
  */
 struct rxrpc_key_data_v1 {
-	u32		kif_version;		/* 1 */
 	u16		security_index;
 	u16		ticket_length;
 	u32		expiry;			/* time_t */
-- 
cgit v1.2.3


From 2d3a8497f8cc5aca14b722cd37d51f6c15ff9f74 Mon Sep 17 00:00:00 2001
From: Tao Ma <boyu.mt@taobao.com>
Date: Thu, 3 Mar 2011 10:53:20 -0500
Subject: blktrace: Remove blk_fill_rwbs_rq.

If we enable trace events to trace block actions, We use
blk_fill_rwbs_rq to analyze the corresponding actions
in request's cmd_flags, but we only choose the minor 2 bits
from it, so most of other flags(e.g, REQ_SYNC) are missing.
For example, with a sync write we get:
write_test-2409  [001]   160.013869: block_rq_insert: 3,64 W 0 () 258135 + =
8 [write_test]

Since now we have integrated the flags of both bio and request,
it is safe to pass rq->cmd_flags directly to blk_fill_rwbs and
blk_fill_rwbs_rq isn't needed any more.

With this patch, after a sync write we get:
write_test-2417  [000]   226.603878: block_rq_insert: 3,64 WS 0 () 258135 +=
 8 [write_test]

Signed-off-by: Tao Ma <boyu.mt@taobao.com>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---
 include/linux/blktrace_api.h |  1 -
 include/trace/events/block.h |  6 +++---
 kernel/trace/blktrace.c      | 16 ----------------
 3 files changed, 3 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 3395cf7130f5..b22fb0d3db0f 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -245,7 +245,6 @@ static inline int blk_cmd_buf_len(struct request *rq)
 
 extern void blk_dump_cmd(char *buf, struct request *rq);
 extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
-extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
 
 #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
 
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index aba421d68f6f..78f18adb49c8 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -31,7 +31,7 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 					0 : blk_rq_sectors(rq);
 		__entry->errors    = rq->errors;
 
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 		blk_dump_cmd(__get_str(cmd), rq);
 	),
 
@@ -118,7 +118,7 @@ DECLARE_EVENT_CLASS(block_rq,
 		__entry->bytes     = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
 					blk_rq_bytes(rq) : 0;
 
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 		blk_dump_cmd(__get_str(cmd), rq);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
@@ -563,7 +563,7 @@ TRACE_EVENT(block_rq_remap,
 		__entry->nr_sector	= blk_rq_sectors(rq);
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 	),
 
 	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d95721f33702..cbafed7d4f38 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1827,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 	rwbs[i] = '\0';
 }
 
-void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
-{
-	int rw = rq->cmd_flags & 0x03;
-	int bytes;
-
-	if (rq->cmd_flags & REQ_DISCARD)
-		rw |= REQ_DISCARD;
-
-	if (rq->cmd_flags & REQ_SECURE)
-		rw |= REQ_SECURE;
-
-	bytes = blk_rq_bytes(rq);
-
-	blk_fill_rwbs(rwbs, rw, bytes);
-}
-
 #endif /* CONFIG_EVENT_TRACING */
 
-- 
cgit v1.2.3


From c53fa1ed92cd671a1dfb1e7569e9ab672612ddc6 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 3 Mar 2011 10:55:40 -0800
Subject: netlink: kill loginuid/sessionid/sid members from struct
 netlink_skb_parms

Netlink message processing in the kernel is synchronous these days, the
session information can be collected when needed.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h      |  3 ---
 kernel/audit.c               |  6 ++---
 kernel/auditfilter.c         | 10 +++++---
 net/netlabel/netlabel_user.h |  6 ++---
 net/netlink/af_netlink.c     |  3 ---
 net/xfrm/xfrm_user.c         | 56 +++++++++++++++++++++++++-------------------
 security/selinux/hooks.c     |  6 +++--
 7 files changed, 49 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index e2b9e63afa68..66823b862022 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -161,9 +161,6 @@ struct netlink_skb_parms {
 	__u32			pid;
 	__u32			dst_group;
 	kernel_cap_t		eff_cap;
-	__u32			loginuid;	/* Login (audit) uid */
-	__u32			sessionid;	/* Session id (audit) */
-	__u32			sid;		/* SELinux security id */
 };
 
 #define NETLINK_CB(skb)		(*(struct netlink_skb_parms*)&((skb)->cb))
diff --git a/kernel/audit.c b/kernel/audit.c
index 162e88e33bc9..939500317066 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -673,9 +673,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	pid  = NETLINK_CREDS(skb)->pid;
 	uid  = NETLINK_CREDS(skb)->uid;
-	loginuid = NETLINK_CB(skb).loginuid;
-	sessionid = NETLINK_CB(skb).sessionid;
-	sid  = NETLINK_CB(skb).sid;
+	loginuid = audit_get_loginuid(current);
+	sessionid = audit_get_sessionid(current);
+	security_task_getsecid(current, &sid);
 	seq  = nlh->nlmsg_seq;
 	data = NLMSG_DATA(nlh);
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index add2819af71b..f8277c80d678 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1238,6 +1238,7 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
 	for (i = 0; i < rule->field_count; i++) {
 		struct audit_field *f = &rule->fields[i];
 		int result = 0;
+		u32 sid;
 
 		switch (f->type) {
 		case AUDIT_PID:
@@ -1250,19 +1251,22 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
 			result = audit_comparator(cb->creds.gid, f->op, f->val);
 			break;
 		case AUDIT_LOGINUID:
-			result = audit_comparator(cb->loginuid, f->op, f->val);
+			result = audit_comparator(audit_get_loginuid(current),
+						  f->op, f->val);
 			break;
 		case AUDIT_SUBJ_USER:
 		case AUDIT_SUBJ_ROLE:
 		case AUDIT_SUBJ_TYPE:
 		case AUDIT_SUBJ_SEN:
 		case AUDIT_SUBJ_CLR:
-			if (f->lsm_rule)
-				result = security_audit_rule_match(cb->sid,
+			if (f->lsm_rule) {
+				security_task_getsecid(current, &sid);
+				result = security_audit_rule_match(sid,
 								   f->type,
 								   f->op,
 								   f->lsm_rule,
 								   NULL);
+			}
 			break;
 		}
 
diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h
index 6caef8b20611..f4fc4c9ad567 100644
--- a/net/netlabel/netlabel_user.h
+++ b/net/netlabel/netlabel_user.h
@@ -49,9 +49,9 @@
 static inline void netlbl_netlink_auditinfo(struct sk_buff *skb,
 					    struct netlbl_audit *audit_info)
 {
-	audit_info->secid = NETLINK_CB(skb).sid;
-	audit_info->loginuid = NETLINK_CB(skb).loginuid;
-	audit_info->sessionid = NETLINK_CB(skb).sessionid;
+	security_task_getsecid(current, &audit_info->secid);
+	audit_info->loginuid = audit_get_loginuid(current);
+	audit_info->sessionid = audit_get_sessionid(current);
 }
 
 /* NetLabel NETLINK I/O functions */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 478181d53c55..97ecd923d7ee 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1362,9 +1362,6 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 	NETLINK_CB(skb).pid	= nlk->pid;
 	NETLINK_CB(skb).dst_group = dst_group;
-	NETLINK_CB(skb).loginuid = audit_get_loginuid(current);
-	NETLINK_CB(skb).sessionid = audit_get_sessionid(current);
-	security_task_getsecid(current, &(NETLINK_CB(skb).sid));
 	memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
 
 	/* What can I do? Netlink is asynchronous, so that
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 673698d380d7..468ab60d3dc0 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -497,9 +497,9 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_state *x;
 	int err;
 	struct km_event c;
-	uid_t loginuid = NETLINK_CB(skb).loginuid;
-	u32 sessionid = NETLINK_CB(skb).sessionid;
-	u32 sid = NETLINK_CB(skb).sid;
+	uid_t loginuid = audit_get_loginuid(current);
+	u32 sessionid = audit_get_sessionid(current);
+	u32 sid;
 
 	err = verify_newsa_info(p, attrs);
 	if (err)
@@ -515,6 +515,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else
 		err = xfrm_state_update(x);
 
+	security_task_getsecid(current, &sid);
 	xfrm_audit_state_add(x, err ? 0 : 1, loginuid, sessionid, sid);
 
 	if (err < 0) {
@@ -575,9 +576,9 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err = -ESRCH;
 	struct km_event c;
 	struct xfrm_usersa_id *p = nlmsg_data(nlh);
-	uid_t loginuid = NETLINK_CB(skb).loginuid;
-	u32 sessionid = NETLINK_CB(skb).sessionid;
-	u32 sid = NETLINK_CB(skb).sid;
+	uid_t loginuid = audit_get_loginuid(current);
+	u32 sessionid = audit_get_sessionid(current);
+	u32 sid;
 
 	x = xfrm_user_state_lookup(net, p, attrs, &err);
 	if (x == NULL)
@@ -602,6 +603,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	km_state_notify(x, &c);
 
 out:
+	security_task_getsecid(current, &sid);
 	xfrm_audit_state_delete(x, err ? 0 : 1, loginuid, sessionid, sid);
 	xfrm_state_put(x);
 	return err;
@@ -1265,9 +1267,9 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct km_event c;
 	int err;
 	int excl;
-	uid_t loginuid = NETLINK_CB(skb).loginuid;
-	u32 sessionid = NETLINK_CB(skb).sessionid;
-	u32 sid = NETLINK_CB(skb).sid;
+	uid_t loginuid = audit_get_loginuid(current);
+	u32 sessionid = audit_get_sessionid(current);
+	u32 sid;
 
 	err = verify_newpolicy_info(p);
 	if (err)
@@ -1286,6 +1288,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	 * a type XFRM_MSG_UPDPOLICY - JHS */
 	excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY;
 	err = xfrm_policy_insert(p->dir, xp, excl);
+	security_task_getsecid(current, &sid);
 	xfrm_audit_policy_add(xp, err ? 0 : 1, loginuid, sessionid, sid);
 
 	if (err) {
@@ -1522,10 +1525,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 					    NETLINK_CB(skb).pid);
 		}
 	} else {
-		uid_t loginuid = NETLINK_CB(skb).loginuid;
-		u32 sessionid = NETLINK_CB(skb).sessionid;
-		u32 sid = NETLINK_CB(skb).sid;
+		uid_t loginuid = audit_get_loginuid(current);
+		u32 sessionid = audit_get_sessionid(current);
+		u32 sid;
 
+		security_task_getsecid(current, &sid);
 		xfrm_audit_policy_delete(xp, err ? 0 : 1, loginuid, sessionid,
 					 sid);
 
@@ -1553,9 +1557,9 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_audit audit_info;
 	int err;
 
-	audit_info.loginuid = NETLINK_CB(skb).loginuid;
-	audit_info.sessionid = NETLINK_CB(skb).sessionid;
-	audit_info.secid = NETLINK_CB(skb).sid;
+	audit_info.loginuid = audit_get_loginuid(current);
+	audit_info.sessionid = audit_get_sessionid(current);
+	security_task_getsecid(current, &audit_info.secid);
 	err = xfrm_state_flush(net, p->proto, &audit_info);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
@@ -1720,9 +1724,9 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		return err;
 
-	audit_info.loginuid = NETLINK_CB(skb).loginuid;
-	audit_info.sessionid = NETLINK_CB(skb).sessionid;
-	audit_info.secid = NETLINK_CB(skb).sid;
+	audit_info.loginuid = audit_get_loginuid(current);
+	audit_info.sessionid = audit_get_sessionid(current);
+	security_task_getsecid(current, &audit_info.secid);
 	err = xfrm_policy_flush(net, type, &audit_info);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
@@ -1789,9 +1793,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	err = 0;
 	if (up->hard) {
-		uid_t loginuid = NETLINK_CB(skb).loginuid;
-		uid_t sessionid = NETLINK_CB(skb).sessionid;
-		u32 sid = NETLINK_CB(skb).sid;
+		uid_t loginuid = audit_get_loginuid(current);
+		u32 sessionid = audit_get_sessionid(current);
+		u32 sid;
+
+		security_task_getsecid(current, &sid);
 		xfrm_policy_delete(xp, p->dir);
 		xfrm_audit_policy_delete(xp, 1, loginuid, sessionid, sid);
 
@@ -1830,9 +1836,11 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	km_state_expired(x, ue->hard, current->pid);
 
 	if (ue->hard) {
-		uid_t loginuid = NETLINK_CB(skb).loginuid;
-		uid_t sessionid = NETLINK_CB(skb).sessionid;
-		u32 sid = NETLINK_CB(skb).sid;
+		uid_t loginuid = audit_get_loginuid(current);
+		u32 sessionid = audit_get_sessionid(current);
+		u32 sid;
+
+		security_task_getsecid(current, &sid);
 		__xfrm_state_delete(x);
 		xfrm_audit_state_delete(x, 1, loginuid, sessionid, sid);
 	}
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c8d699270687..cef42f5d69a2 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4669,6 +4669,7 @@ static int selinux_netlink_recv(struct sk_buff *skb, int capability)
 {
 	int err;
 	struct common_audit_data ad;
+	u32 sid;
 
 	err = cap_netlink_recv(skb, capability);
 	if (err)
@@ -4677,8 +4678,9 @@ static int selinux_netlink_recv(struct sk_buff *skb, int capability)
 	COMMON_AUDIT_DATA_INIT(&ad, CAP);
 	ad.u.cap = capability;
 
-	return avc_has_perm(NETLINK_CB(skb).sid, NETLINK_CB(skb).sid,
-			    SECCLASS_CAPABILITY, CAP_TO_MASK(capability), &ad);
+	security_task_getsecid(current, &sid);
+	return avc_has_perm(sid, sid, SECCLASS_CAPABILITY,
+			    CAP_TO_MASK(capability), &ad);
 }
 
 static int ipc_alloc_security(struct task_struct *task,
-- 
cgit v1.2.3


From d276055c4e90a7278cd5167ba9755c9b214bcff7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 3 Mar 2011 11:10:02 -0800
Subject: net_sched: reduce fifo qdisc size

Because of various alignements [SLUB / qdisc], we use 512 bytes of
memory for one {p|b}fifo qdisc, instead of 256 bytes on 64bit arches and
192 bytes on 32bit ones.

Move the "u32 limit" inside "struct Qdisc" (no impact on other qdiscs)

Change qdisc_alloc(), first trying a regular allocation before an
oversized one.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  1 +
 net/sched/sch_fifo.c      | 34 +++++++++++-----------------------
 net/sched/sch_generic.c   | 18 +++++++++++-------
 3 files changed, 23 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 16626a04cb03..1934634f8896 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -83,6 +83,7 @@ struct Qdisc {
 	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	spinlock_t		busylock;
+	u32			limit;
 };
 
 static inline bool qdisc_is_running(const struct Qdisc *qdisc)
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index be33f9ddf9dd..66effe2da8e0 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -19,15 +19,9 @@
 
 /* 1 band FIFO pseudo-"scheduler" */
 
-struct fifo_sched_data {
-	u32 limit;
-};
-
 static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
-	struct fifo_sched_data *q = qdisc_priv(sch);
-
-	if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= q->limit))
+	if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
 	return qdisc_reshape_fail(skb, sch);
@@ -35,9 +29,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
-	struct fifo_sched_data *q = qdisc_priv(sch);
-
-	if (likely(skb_queue_len(&sch->q) < q->limit))
+	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
 	return qdisc_reshape_fail(skb, sch);
@@ -45,9 +37,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
-	struct fifo_sched_data *q = qdisc_priv(sch);
-
-	if (likely(skb_queue_len(&sch->q) < q->limit))
+	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
 	/* queue full, remove one skb to fulfill the limit */
@@ -60,7 +50,6 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
 {
-	struct fifo_sched_data *q = qdisc_priv(sch);
 	bool bypass;
 	bool is_bfifo = sch->ops == &bfifo_qdisc_ops;
 
@@ -70,20 +59,20 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
 		if (is_bfifo)
 			limit *= psched_mtu(qdisc_dev(sch));
 
-		q->limit = limit;
+		sch->limit = limit;
 	} else {
 		struct tc_fifo_qopt *ctl = nla_data(opt);
 
 		if (nla_len(opt) < sizeof(*ctl))
 			return -EINVAL;
 
-		q->limit = ctl->limit;
+		sch->limit = ctl->limit;
 	}
 
 	if (is_bfifo)
-		bypass = q->limit >= psched_mtu(qdisc_dev(sch));
+		bypass = sch->limit >= psched_mtu(qdisc_dev(sch));
 	else
-		bypass = q->limit >= 1;
+		bypass = sch->limit >= 1;
 
 	if (bypass)
 		sch->flags |= TCQ_F_CAN_BYPASS;
@@ -94,8 +83,7 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt)
 
 static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
-	struct fifo_sched_data *q = qdisc_priv(sch);
-	struct tc_fifo_qopt opt = { .limit = q->limit };
+	struct tc_fifo_qopt opt = { .limit = sch->limit };
 
 	NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
 	return skb->len;
@@ -106,7 +94,7 @@ nla_put_failure:
 
 struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
 	.id		=	"pfifo",
-	.priv_size	=	sizeof(struct fifo_sched_data),
+	.priv_size	=	0,
 	.enqueue	=	pfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
@@ -121,7 +109,7 @@ EXPORT_SYMBOL(pfifo_qdisc_ops);
 
 struct Qdisc_ops bfifo_qdisc_ops __read_mostly = {
 	.id		=	"bfifo",
-	.priv_size	=	sizeof(struct fifo_sched_data),
+	.priv_size	=	0,
 	.enqueue	=	bfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
@@ -136,7 +124,7 @@ EXPORT_SYMBOL(bfifo_qdisc_ops);
 
 struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = {
 	.id		=	"pfifo_head_drop",
-	.priv_size	=	sizeof(struct fifo_sched_data),
+	.priv_size	=	0,
 	.enqueue	=	pfifo_tail_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 0da09d508737..a854cab03f1e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -550,21 +550,25 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 {
 	void *p;
 	struct Qdisc *sch;
-	unsigned int size;
+	unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
 	int err = -ENOBUFS;
 
-	/* ensure that the Qdisc and the private data are 64-byte aligned */
-	size = QDISC_ALIGN(sizeof(*sch));
-	size += ops->priv_size + (QDISC_ALIGNTO - 1);
-
 	p = kzalloc_node(size, GFP_KERNEL,
 			 netdev_queue_numa_node_read(dev_queue));
 
 	if (!p)
 		goto errout;
 	sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
-	sch->padded = (char *) sch - (char *) p;
-
+	/* if we got non aligned memory, ask more and do alignment ourself */
+	if (sch != p) {
+		kfree(p);
+		p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL,
+				 netdev_queue_numa_node_read(dev_queue));
+		if (!p)
+			goto errout;
+		sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
+		sch->padded = (char *) sch - (char *) p;
+	}
 	INIT_LIST_HEAD(&sch->list);
 	skb_queue_head_init(&sch->q);
 	spin_lock_init(&sch->busylock);
-- 
cgit v1.2.3


From ff36fe2c845cab2102e4826c1ffa0a6ebf487c65 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Thu, 3 Mar 2011 16:09:14 -0500
Subject: LSM: Pass -o remount options to the LSM

The VFS mount code passes the mount options to the LSM.  The LSM will remove
options it understands from the data and the VFS will then pass the remaining
options onto the underlying filesystem.  This is how options like the
SELinux context= work.  The problem comes in that -o remount never calls
into LSM code.  So if you include an LSM specific option it will get passed
to the filesystem and will cause the remount to fail.  An example of where
this is a problem is the 'seclabel' option.  The SELinux LSM hook will
print this word in /proc/mounts if the filesystem is being labeled using
xattrs.  If you pass this word on mount it will be silently stripped and
ignored.  But if you pass this word on remount the LSM never gets called
and it will be passed to the FS.  The FS doesn't know what seclabel means
and thus should fail the mount.  For example an ext3 fs mounted over loop

# mount -o loop /tmp/fs /mnt/tmp
# cat /proc/mounts | grep /mnt/tmp
/dev/loop0 /mnt/tmp ext3 rw,seclabel,relatime,errors=continue,barrier=0,data=ordered 0 0
# mount -o remount /mnt/tmp
mount: /mnt/tmp not mounted already, or bad option
# dmesg
EXT3-fs (loop0): error: unrecognized mount option "seclabel" or missing value

This patch passes the remount mount options to an new LSM hook.

Signed-off-by: Eric Paris <eparis@redhat.com>
Reviewed-by: James Morris <jmorris@namei.org>
---
 fs/namespace.c           |  4 ++++
 include/linux/security.h | 13 +++++++++++++
 security/capability.c    |  6 ++++++
 security/security.c      |  5 +++++
 4 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 3ddfd9046c44..1b3f2ac59c5e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1800,6 +1800,10 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
+	err = security_sb_remount(sb, data);
+	if (err)
+		return err;
+
 	down_write(&sb->s_umount);
 	if (flags & MS_BIND)
 		err = change_mount_flags(path->mnt, flags);
diff --git a/include/linux/security.h b/include/linux/security.h
index 14167f2eb35a..d11ac43ecc49 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -268,6 +268,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@orig the original mount data copied from userspace.
  *	@copy copied data which will be passed to the security module.
  *	Returns 0 if the copy was successful.
+ * @sb_remount:
+ *	Extracts security system specifc mount options and verifys no changes
+ *	are being made to those options.
+ *	@sb superblock being remounted
+ *	@data contains the filesystem-specific data.
+ *	Return 0 if permission is granted.
  * @sb_umount:
  *	Check permission before the @mnt file system is unmounted.
  *	@mnt contains the mounted file system.
@@ -1394,6 +1400,7 @@ struct security_operations {
 	int (*sb_alloc_security) (struct super_block *sb);
 	void (*sb_free_security) (struct super_block *sb);
 	int (*sb_copy_data) (char *orig, char *copy);
+	int (*sb_remount) (struct super_block *sb, void *data);
 	int (*sb_kern_mount) (struct super_block *sb, int flags, void *data);
 	int (*sb_show_options) (struct seq_file *m, struct super_block *sb);
 	int (*sb_statfs) (struct dentry *dentry);
@@ -1676,6 +1683,7 @@ int security_bprm_secureexec(struct linux_binprm *bprm);
 int security_sb_alloc(struct super_block *sb);
 void security_sb_free(struct super_block *sb);
 int security_sb_copy_data(char *orig, char *copy);
+int security_sb_remount(struct super_block *sb, void *data);
 int security_sb_kern_mount(struct super_block *sb, int flags, void *data);
 int security_sb_show_options(struct seq_file *m, struct super_block *sb);
 int security_sb_statfs(struct dentry *dentry);
@@ -1955,6 +1963,11 @@ static inline int security_sb_copy_data(char *orig, char *copy)
 	return 0;
 }
 
+static inline int security_sb_remount(struct super_block *sb, void *data)
+{
+	return 0;
+}
+
 static inline int security_sb_kern_mount(struct super_block *sb, int flags, void *data)
 {
 	return 0;
diff --git a/security/capability.c b/security/capability.c
index 85b67c8632df..ab3d807accc3 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -54,6 +54,11 @@ static int cap_sb_copy_data(char *orig, char *copy)
 	return 0;
 }
 
+static int cap_sb_remount(struct super_block *sb, void *data)
+{
+	return 0;
+}
+
 static int cap_sb_kern_mount(struct super_block *sb, int flags, void *data)
 {
 	return 0;
@@ -887,6 +892,7 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, sb_alloc_security);
 	set_to_cap_if_null(ops, sb_free_security);
 	set_to_cap_if_null(ops, sb_copy_data);
+	set_to_cap_if_null(ops, sb_remount);
 	set_to_cap_if_null(ops, sb_kern_mount);
 	set_to_cap_if_null(ops, sb_show_options);
 	set_to_cap_if_null(ops, sb_statfs);
diff --git a/security/security.c b/security/security.c
index 8f28685ee0d9..b1d6134548bc 100644
--- a/security/security.c
+++ b/security/security.c
@@ -267,6 +267,11 @@ int security_sb_copy_data(char *orig, char *copy)
 }
 EXPORT_SYMBOL(security_sb_copy_data);
 
+int security_sb_remount(struct super_block *sb, void *data)
+{
+	return security_ops->sb_remount(sb, data);
+}
+
 int security_sb_kern_mount(struct super_block *sb, int flags, void *data)
 {
 	return security_ops->sb_kern_mount(sb, flags, data);
-- 
cgit v1.2.3


From 01a16b21d6adf992aa863186c3c4e561a57c1714 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 3 Mar 2011 13:32:07 -0800
Subject: netlink: kill eff_cap from struct netlink_skb_parms

Netlink message processing in the kernel is synchronous these days,
capabilities can be checked directly in security_netlink_recv() from
the current process.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Reviewed-by: James Morris <jmorris@namei.org>
[chrisw: update to include pohmelfs and uvesafb]
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/drbd/drbd_nl.c           | 2 +-
 drivers/md/dm-log-userspace-transfer.c | 2 +-
 drivers/staging/pohmelfs/config.c      | 2 +-
 drivers/video/uvesafb.c                | 2 +-
 include/linux/netlink.h                | 1 -
 net/netlink/af_netlink.c               | 6 ------
 security/commoncap.c                   | 3 +--
 7 files changed, 5 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 8cbfaa687d72..fe81c851ca88 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2177,7 +2177,7 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms
 		return;
 	}
 
-	if (!cap_raised(nsp->eff_cap, CAP_SYS_ADMIN)) {
+	if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) {
 		retcode = ERR_PERM;
 		goto fail;
 	}
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 049eaf12aaab..1f23e048f077 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -134,7 +134,7 @@ static void cn_ulog_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
 {
 	struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1);
 
-	if (!cap_raised(nsp->eff_cap, CAP_SYS_ADMIN))
+	if (!cap_raised(current_cap(), CAP_SYS_ADMIN))
 		return;
 
 	spin_lock(&receiving_list_lock);
diff --git a/drivers/staging/pohmelfs/config.c b/drivers/staging/pohmelfs/config.c
index 89279ba1b737..39413b7d387d 100644
--- a/drivers/staging/pohmelfs/config.c
+++ b/drivers/staging/pohmelfs/config.c
@@ -525,7 +525,7 @@ static void pohmelfs_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *n
 {
 	int err;
 
-	if (!cap_raised(nsp->eff_cap, CAP_SYS_ADMIN))
+	if (!cap_raised(current_cap(), CAP_SYS_ADMIN))
 		return;
 
 	switch (msg->flags) {
diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c
index 52ec0959d462..5180a215d781 100644
--- a/drivers/video/uvesafb.c
+++ b/drivers/video/uvesafb.c
@@ -73,7 +73,7 @@ static void uvesafb_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *ns
 	struct uvesafb_task *utask;
 	struct uvesafb_ktask *task;
 
-	if (!cap_raised(nsp->eff_cap, CAP_SYS_ADMIN))
+	if (!cap_raised(current_cap(), CAP_SYS_ADMIN))
 		return;
 
 	if (msg->seq >= UVESAFB_TASKS_MAX)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 66823b862022..4c4ac3f3ce5a 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -160,7 +160,6 @@ struct netlink_skb_parms {
 	struct ucred		creds;		/* Skb credentials	*/
 	__u32			pid;
 	__u32			dst_group;
-	kernel_cap_t		eff_cap;
 };
 
 #define NETLINK_CB(skb)		(*(struct netlink_skb_parms*)&((skb)->cb))
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 97ecd923d7ee..a808fb1e877d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1364,12 +1364,6 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	NETLINK_CB(skb).dst_group = dst_group;
 	memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
 
-	/* What can I do? Netlink is asynchronous, so that
-	   we will have to save current capabilities to
-	   check them, when this message will be delivered
-	   to corresponding kernel module.   --ANK (980802)
-	 */
-
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
 		kfree_skb(skb);
diff --git a/security/commoncap.c b/security/commoncap.c
index 64c2ed9c9015..a83e607d91c3 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -52,13 +52,12 @@ static void warn_setuid_and_fcaps_mixed(const char *fname)
 
 int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-	NETLINK_CB(skb).eff_cap = current_cap();
 	return 0;
 }
 
 int cap_netlink_recv(struct sk_buff *skb, int cap)
 {
-	if (!cap_raised(NETLINK_CB(skb).eff_cap, cap))
+	if (!cap_raised(current_cap(), cap))
 		return -EPERM;
 	return 0;
 }
-- 
cgit v1.2.3


From a7e3ed1e470116c9d12c2f778431a481a6be8ab6 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 3 Mar 2011 10:34:47 +0800
Subject: perf: Add support for supplementary event registers

Change logs against Andi's original version:

- Extends perf_event_attr:config to config{,1,2} (Peter Zijlstra)
- Fixed a major event scheduling issue. There cannot be a ref++ on an
  event that has already done ref++ once and without calling
  put_constraint() in between. (Stephane Eranian)
- Use thread_cpumask for percore allocation. (Lin Ming)
- Use MSR names in the extra reg lists. (Lin Ming)
- Remove redundant "c = NULL" in intel_percore_constraints
- Fix comment of perf_event_attr::config1

Intel Nehalem/Westmere have a special OFFCORE_RESPONSE event
that can be used to monitor any offcore accesses from a core.
This is a very useful event for various tunings, and it's
also needed to implement the generic LLC-* events correctly.

Unfortunately this event requires programming a mask in a separate
register. And worse this separate register is per core, not per
CPU thread.

This patch:

- Teaches perf_events that OFFCORE_RESPONSE needs extra parameters.
  The extra parameters are passed by user space in the
  perf_event_attr::config1 field.

- Adds support to the Intel perf_event core to schedule per
  core resources. This adds fairly generic infrastructure that
  can be also used for other per core resources.
  The basic code has is patterned after the similar AMD northbridge
  constraints code.

Thanks to Stephane Eranian who pointed out some problems
in the original version and suggested improvements.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1299119690-13991-2-git-send-email-ming.m.lin@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/msr-index.h       |   3 +
 arch/x86/kernel/cpu/perf_event.c       |  64 +++++++++++
 arch/x86/kernel/cpu/perf_event_intel.c | 198 +++++++++++++++++++++++++++++++++
 include/linux/perf_event.h             |  13 ++-
 4 files changed, 276 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4d0dfa0d998e..d25e74cc1a50 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -47,6 +47,9 @@
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
 
+#define MSR_OFFCORE_RSP_0		0x000001a6
+#define MSR_OFFCORE_RSP_1		0x000001a7
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index ea03c725e465..ec6a6db07332 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -93,6 +93,8 @@ struct amd_nb {
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
+struct intel_percore;
+
 #define MAX_LBR_ENTRIES		16
 
 struct cpu_hw_events {
@@ -127,6 +129,13 @@ struct cpu_hw_events {
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 
+	/*
+	 * Intel percore register state.
+	 * Coordinate shared resources between HT threads.
+	 */
+	int				percore_used; /* Used by this CPU? */
+	struct intel_percore		*per_core;
+
 	/*
 	 * AMD specific bits
 	 */
@@ -177,6 +186,28 @@ struct cpu_hw_events {
 #define for_each_event_constraint(e, c)	\
 	for ((e) = (c); (e)->weight; (e)++)
 
+/*
+ * Extra registers for specific events.
+ * Some events need large masks and require external MSRs.
+ * Define a mapping to these extra registers.
+ */
+struct extra_reg {
+	unsigned int		event;
+	unsigned int		msr;
+	u64			config_mask;
+	u64			valid_mask;
+};
+
+#define EVENT_EXTRA_REG(e, ms, m, vm) {	\
+	.event = (e),		\
+	.msr = (ms),		\
+	.config_mask = (m),	\
+	.valid_mask = (vm),	\
+	}
+#define INTEL_EVENT_EXTRA_REG(event, msr, vm)	\
+	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm)
+#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0)
+
 union perf_capabilities {
 	struct {
 		u64	lbr_format    : 6;
@@ -221,6 +252,7 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+	struct event_constraint *percore_constraints;
 	void		(*quirks)(void);
 	int		perfctr_second_write;
 
@@ -249,6 +281,11 @@ struct x86_pmu {
 	 */
 	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
 	int		lbr_nr;			   /* hardware stack size */
+
+	/*
+	 * Extra registers for events
+	 */
+	struct extra_reg *extra_regs;
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -341,6 +378,31 @@ static inline unsigned int x86_pmu_event_addr(int index)
 	return x86_pmu.perfctr + x86_pmu_addr_offset(index);
 }
 
+/*
+ * Find and validate any extra registers to set up.
+ */
+static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
+{
+	struct extra_reg *er;
+
+	event->hw.extra_reg = 0;
+	event->hw.extra_config = 0;
+
+	if (!x86_pmu.extra_regs)
+		return 0;
+
+	for (er = x86_pmu.extra_regs; er->msr; er++) {
+		if (er->event != (config & er->config_mask))
+			continue;
+		if (event->attr.config1 & ~er->valid_mask)
+			return -EINVAL;
+		event->hw.extra_reg = er->msr;
+		event->hw.extra_config = event->attr.config1;
+		break;
+	}
+	return 0;
+}
+
 static atomic_t active_events;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
@@ -665,6 +727,8 @@ static void x86_pmu_disable(struct pmu *pmu)
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 					  u64 enable_mask)
 {
+	if (hwc->extra_reg)
+		wrmsrl(hwc->extra_reg, hwc->extra_config);
 	wrmsrl(hwc->config_base, hwc->config | enable_mask);
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index c3ce053ecb46..13cb6cf013f6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1,5 +1,27 @@
 #ifdef CONFIG_CPU_SUP_INTEL
 
+#define MAX_EXTRA_REGS 2
+
+/*
+ * Per register state.
+ */
+struct er_account {
+	int			ref;		/* reference count */
+	unsigned int		extra_reg;	/* extra MSR number */
+	u64			extra_config;	/* extra MSR config */
+};
+
+/*
+ * Per core state
+ * This used to coordinate shared registers for HT threads.
+ */
+struct intel_percore {
+	raw_spinlock_t		lock;		/* protect structure */
+	struct er_account	regs[MAX_EXTRA_REGS];
+	int			refcnt;		/* number of threads */
+	unsigned		core_id;
+};
+
 /*
  * Intel PerfMon, used on Core and later.
  */
@@ -64,6 +86,18 @@ static struct event_constraint intel_nehalem_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_nehalem_extra_regs[] =
+{
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+	EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_nehalem_percore_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0xb7, 0),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_westmere_event_constraints[] =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -89,6 +123,20 @@ static struct event_constraint intel_snb_event_constraints[] =
 	EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_westmere_extra_regs[] =
+{
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff),
+	EVENT_EXTRA_END
+};
+
+static struct event_constraint intel_westmere_percore_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0xb7, 0),
+	INTEL_EVENT_CONSTRAINT(0xbb, 0),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_gen_event_constraints[] =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -906,6 +954,67 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
+static struct event_constraint *
+intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT;
+	struct event_constraint *c;
+	struct intel_percore *pc;
+	struct er_account *era;
+	int i;
+	int free_slot;
+	int found;
+
+	if (!x86_pmu.percore_constraints || hwc->extra_alloc)
+		return NULL;
+
+	for (c = x86_pmu.percore_constraints; c->cmask; c++) {
+		if (e != c->code)
+			continue;
+
+		/*
+		 * Allocate resource per core.
+		 */
+		pc = cpuc->per_core;
+		if (!pc)
+			break;
+		c = &emptyconstraint;
+		raw_spin_lock(&pc->lock);
+		free_slot = -1;
+		found = 0;
+		for (i = 0; i < MAX_EXTRA_REGS; i++) {
+			era = &pc->regs[i];
+			if (era->ref > 0 && hwc->extra_reg == era->extra_reg) {
+				/* Allow sharing same config */
+				if (hwc->extra_config == era->extra_config) {
+					era->ref++;
+					cpuc->percore_used = 1;
+					hwc->extra_alloc = 1;
+					c = NULL;
+				}
+				/* else conflict */
+				found = 1;
+				break;
+			} else if (era->ref == 0 && free_slot == -1)
+				free_slot = i;
+		}
+		if (!found && free_slot != -1) {
+			era = &pc->regs[free_slot];
+			era->ref = 1;
+			era->extra_reg = hwc->extra_reg;
+			era->extra_config = hwc->extra_config;
+			cpuc->percore_used = 1;
+			hwc->extra_alloc = 1;
+			c = NULL;
+		}
+		raw_spin_unlock(&pc->lock);
+		return c;
+	}
+
+	return NULL;
+}
+
 static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
@@ -919,9 +1028,51 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
 	if (c)
 		return c;
 
+	c = intel_percore_constraints(cpuc, event);
+	if (c)
+		return c;
+
 	return x86_get_event_constraints(cpuc, event);
 }
 
+static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
+					struct perf_event *event)
+{
+	struct extra_reg *er;
+	struct intel_percore *pc;
+	struct er_account *era;
+	struct hw_perf_event *hwc = &event->hw;
+	int i, allref;
+
+	if (!cpuc->percore_used)
+		return;
+
+	for (er = x86_pmu.extra_regs; er->msr; er++) {
+		if (er->event != (hwc->config & er->config_mask))
+			continue;
+
+		pc = cpuc->per_core;
+		raw_spin_lock(&pc->lock);
+		for (i = 0; i < MAX_EXTRA_REGS; i++) {
+			era = &pc->regs[i];
+			if (era->ref > 0 &&
+			    era->extra_config == hwc->extra_config &&
+			    era->extra_reg == er->msr) {
+				era->ref--;
+				hwc->extra_alloc = 0;
+				break;
+			}
+		}
+		allref = 0;
+		for (i = 0; i < MAX_EXTRA_REGS; i++)
+			allref += pc->regs[i].ref;
+		if (allref == 0)
+			cpuc->percore_used = 0;
+		raw_spin_unlock(&pc->lock);
+		break;
+	}
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -993,11 +1144,43 @@ static __initconst const struct x86_pmu core_pmu = {
 	 */
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
 };
 
+static int intel_pmu_cpu_prepare(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	cpuc->per_core = kzalloc_node(sizeof(struct intel_percore),
+				      GFP_KERNEL, cpu_to_node(cpu));
+	if (!cpuc->per_core)
+		return NOTIFY_BAD;
+
+	raw_spin_lock_init(&cpuc->per_core->lock);
+	cpuc->per_core->core_id = -1;
+	return NOTIFY_OK;
+}
+
 static void intel_pmu_cpu_starting(int cpu)
 {
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	int core_id = topology_core_id(cpu);
+	int i;
+
+	for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core;
+
+		if (pc && pc->core_id == core_id) {
+			kfree(cpuc->per_core);
+			cpuc->per_core = pc;
+			break;
+		}
+	}
+
+	cpuc->per_core->core_id = core_id;
+	cpuc->per_core->refcnt++;
+
 	init_debug_store_on_cpu(cpu);
 	/*
 	 * Deal with CPUs that don't clear their LBRs on power-up.
@@ -1007,6 +1190,15 @@ static void intel_pmu_cpu_starting(int cpu)
 
 static void intel_pmu_cpu_dying(int cpu)
 {
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct intel_percore *pc = cpuc->per_core;
+
+	if (pc) {
+		if (pc->core_id == -1 || --pc->refcnt == 0)
+			kfree(pc);
+		cpuc->per_core = NULL;
+	}
+
 	fini_debug_store_on_cpu(cpu);
 }
 
@@ -1031,7 +1223,9 @@ static __initconst const struct x86_pmu intel_pmu = {
 	 */
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
 
+	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 };
@@ -1151,7 +1345,9 @@ static __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_nehalem_event_constraints;
 		x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
+		x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
+		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 		pr_cont("Nehalem events, ");
 		break;
 
@@ -1174,8 +1370,10 @@ static __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_nhm();
 
 		x86_pmu.event_constraints = intel_westmere_event_constraints;
+		x86_pmu.percore_constraints = intel_westmere_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_westmere_extra_regs;
 		pr_cont("Westmere events, ");
 		break;
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8ceb5a6fd9c9..614615b8d42b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -225,8 +225,14 @@ struct perf_event_attr {
 	};
 
 	__u32			bp_type;
-	__u64			bp_addr;
-	__u64			bp_len;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
 };
 
 /*
@@ -541,6 +547,9 @@ struct hw_perf_event {
 			unsigned long	event_base;
 			int		idx;
 			int		last_cpu;
+			unsigned int	extra_reg;
+			u64		extra_config;
+			int		extra_alloc;
 		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
-- 
cgit v1.2.3


From e3e89cc535223433a619d0969db3fa05cdd946b8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 4 Mar 2011 09:23:30 -0800
Subject: Mark ptrace_{traceme,attach,detach} static

They are only used inside kernel/ptrace.c, and have been for a long
time.  We don't want to go back to the bad-old-days when architectures
did things on their own, so make them static and private.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ptrace.h | 3 ---
 kernel/ptrace.c        | 6 +++---
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 092a04f874a8..a1147e5dd245 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -102,11 +102,8 @@
 
 extern long arch_ptrace(struct task_struct *child, long request,
 			unsigned long addr, unsigned long data);
-extern int ptrace_traceme(void);
 extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
 extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len);
-extern int ptrace_attach(struct task_struct *tsk);
-extern int ptrace_detach(struct task_struct *, unsigned int);
 extern void ptrace_disable(struct task_struct *);
 extern int ptrace_check_attach(struct task_struct *task, int kill);
 extern int ptrace_request(struct task_struct *child, long request,
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1708b1e2972d..e2302e40b360 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 	return !err;
 }
 
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
 {
 	int retval;
 
@@ -219,7 +219,7 @@ out:
  * Performs checks and sets PT_PTRACED.
  * Should be used by all ptrace implementations for PTRACE_TRACEME.
  */
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
 {
 	int ret = -EPERM;
 
@@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 	return false;
 }
 
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
 {
 	bool dead = false;
 
-- 
cgit v1.2.3


From 60bf8bf8815e6adea4c1d0423578c3b8000e2ec8 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Fri, 4 Mar 2011 12:24:28 -0800
Subject: libceph: fix msgr backoff

With commit f363e45f we replaced a bunch of hacky workqueue mutual
exclusion logic with the WQ_NON_REENTRANT flag.  One pieces of fallout is
that the exponential backoff breaks in certain cases:

 * con_work attempts to connect.
 * we get an immediate failure, and the socket state change handler queues
   immediate work.
 * con_work calls con_fault, we decide to back off, but can't queue delayed
   work.

In this case, we add a BACKOFF bit to make con_work reschedule delayed work
next time it runs (which should be immediately).

Signed-off-by: Sage Weil <sage@newdream.net>
---
 include/linux/ceph/messenger.h |  1 +
 net/ceph/messenger.c           | 30 ++++++++++++++++++++++++++++--
 2 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index c3011beac30d..eb31e108a64d 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -123,6 +123,7 @@ struct ceph_msg_pos {
 #define SOCK_CLOSED	11 /* socket state changed to closed */
 #define OPENING         13 /* open connection w/ (possibly new) peer */
 #define DEAD            14 /* dead, about to kfree */
+#define BACKOFF         15
 
 /*
  * A single connection with another host.
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 6bd5025f6220..46fbc422ba74 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1949,6 +1949,19 @@ static void con_work(struct work_struct *work)
 						   work.work);
 
 	mutex_lock(&con->mutex);
+	if (test_and_clear_bit(BACKOFF, &con->state)) {
+		dout("con_work %p backing off\n", con);
+		if (queue_delayed_work(ceph_msgr_wq, &con->work,
+				       round_jiffies_relative(con->delay))) {
+			dout("con_work %p backoff %lu\n", con, con->delay);
+			mutex_unlock(&con->mutex);
+			return;
+		} else {
+			con->ops->put(con);
+			dout("con_work %p FAILED to back off %lu\n", con,
+			     con->delay);
+		}
+	}
 
 	if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
 		dout("con_work CLOSED\n");
@@ -2017,11 +2030,24 @@ static void ceph_fault(struct ceph_connection *con)
 			con->delay = BASE_DELAY_INTERVAL;
 		else if (con->delay < MAX_DELAY_INTERVAL)
 			con->delay *= 2;
-		dout("fault queueing %p delay %lu\n", con, con->delay);
 		con->ops->get(con);
 		if (queue_delayed_work(ceph_msgr_wq, &con->work,
-				       round_jiffies_relative(con->delay)) == 0)
+				       round_jiffies_relative(con->delay))) {
+			dout("fault queued %p delay %lu\n", con, con->delay);
+		} else {
 			con->ops->put(con);
+			dout("fault failed to queue %p delay %lu, backoff\n",
+			     con, con->delay);
+			/*
+			 * In many cases we see a socket state change
+			 * while con_work is running and end up
+			 * queuing (non-delayed) work, such that we
+			 * can't backoff with a delay.  Set a flag so
+			 * that when con_work restarts we schedule the
+			 * delay then.
+			 */
+			set_bit(BACKOFF, &con->state);
+		}
 	}
 
 out_unlock:
-- 
cgit v1.2.3


From e76661d0a59e53e5cc4dccbe4b755d1dc8a968ec Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Thu, 3 Mar 2011 10:10:15 -0800
Subject: libceph: fix msgr keepalive flag

There was some broken keepalive code using a dead variable.  Shift to using
the proper bit flag.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 include/linux/ceph/messenger.h | 1 -
 net/ceph/messenger.c           | 9 ++++-----
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index eb31e108a64d..31d91a64838b 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -161,7 +161,6 @@ struct ceph_connection {
 	struct list_head out_queue;
 	struct list_head out_sent;   /* sending or sent but unacked */
 	u64 out_seq;		     /* last message queued for send */
-	bool out_keepalive_pending;
 
 	u64 in_seq, in_seq_acked;  /* last message received, acked */
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 46fbc422ba74..3252ea974e8f 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -336,7 +336,6 @@ static void reset_connection(struct ceph_connection *con)
 		ceph_msg_put(con->out_msg);
 		con->out_msg = NULL;
 	}
-	con->out_keepalive_pending = false;
 	con->in_seq = 0;
 	con->in_seq_acked = 0;
 }
@@ -2019,10 +2018,10 @@ static void ceph_fault(struct ceph_connection *con)
 	/* Requeue anything that hasn't been acked */
 	list_splice_init(&con->out_sent, &con->out_queue);
 
-	/* If there are no messages in the queue, place the connection
-	 * in a STANDBY state (i.e., don't try to reconnect just yet). */
-	if (list_empty(&con->out_queue) && !con->out_keepalive_pending) {
-		dout("fault setting STANDBY\n");
+	/* If there are no messages queued or keepalive pending, place
+	 * the connection in a STANDBY state */
+	if (list_empty(&con->out_queue) &&
+	    !test_bit(KEEPALIVE_PENDING, &con->state)) {
 		set_bit(STANDBY, &con->state);
 	} else {
 		/* retry after a delay. */
-- 
cgit v1.2.3


From 2f5f9486f8c12e3aa40fe3775a18cb14efc5cea2 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Fri, 4 Mar 2011 17:36:29 -0800
Subject: mm: change alloc_pages_vma to pass down the policy node for local
 policy

Currently alloc_pages_vma() always uses the local node as policy node for
the LOCAL policy.  Pass this node down as an argument instead.

No behaviour change from this patch, but will be needed for followons.

Acked-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h |  9 +++++----
 mm/huge_memory.c    |  2 +-
 mm/mempolicy.c      | 11 +++++------
 3 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0b84c61607e8..37b8af5db091 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -332,16 +332,17 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 	return alloc_pages_current(gfp_mask, order);
 }
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
-			struct vm_area_struct *vma, unsigned long addr);
+			struct vm_area_struct *vma, unsigned long addr,
+			int node);
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr)	\
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node)	\
 	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
-#define alloc_page_vma(gfp_mask, vma, addr)	\
-	alloc_pages_vma(gfp_mask, 0, vma, addr)
+#define alloc_page_vma(gfp_mask, vma, addr)			\
+	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3e29781ee762..c7c2cd925599 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -653,7 +653,7 @@ static inline struct page *alloc_hugepage_vma(int defrag,
 					      unsigned long haddr)
 {
 	return alloc_pages_vma(alloc_hugepage_gfpmask(defrag),
-			       HPAGE_PMD_ORDER, vma, haddr);
+			       HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
 }
 
 #ifndef CONFIG_NUMA
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 49355a970be2..25a5a9146619 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1524,10 +1524,9 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 }
 
 /* Return a zonelist indicated by gfp for node representing a mempolicy */
-static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
+static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy,
+	int nd)
 {
-	int nd = numa_node_id();
-
 	switch (policy->mode) {
 	case MPOL_PREFERRED:
 		if (!(policy->flags & MPOL_F_LOCAL))
@@ -1679,7 +1678,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
 				huge_page_shift(hstate_vma(vma))), gfp_flags);
 	} else {
-		zl = policy_zonelist(gfp_flags, *mpol);
+		zl = policy_zonelist(gfp_flags, *mpol, numa_node_id());
 		if ((*mpol)->mode == MPOL_BIND)
 			*nodemask = &(*mpol)->v.nodes;
 	}
@@ -1820,7 +1819,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr)
+		unsigned long addr, int node)
 {
 	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 	struct zonelist *zl;
@@ -1836,7 +1835,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		put_mems_allowed();
 		return page;
 	}
-	zl = policy_zonelist(gfp, pol);
+	zl = policy_zonelist(gfp, pol, node);
 	if (unlikely(mpol_needs_cond_ref(pol))) {
 		/*
 		 * slow path: ref counted shared policy
-- 
cgit v1.2.3


From 236344d6b417d05a3080477639234fd9ca97568d Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Fri, 4 Mar 2011 17:36:30 -0800
Subject: mm: add alloc_page_vma_node()

Add a alloc_page_vma_node that allows passing the "local" node in.  Used
in a followon patch.

Acked-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 37b8af5db091..dca31761b311 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -343,6 +343,8 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
 	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
+#define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
+	alloc_pages_vma(gfp_mask, 0, vma, addr, node)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
-- 
cgit v1.2.3


From 4157434c23f8f5126a2ffd3cc7b2c3bd928be075 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 4 Mar 2011 21:31:48 -0800
Subject: ipv4: Use passed-in protocol in ip_route_newports().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index 60daf745216a..8905d90e0044 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -217,7 +217,7 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 				    .fl4_dst = rt->fl.fl4_dst,
 				    .fl4_src = rt->fl.fl4_src,
 				    .fl4_tos = rt->fl.fl4_tos,
-				    .proto = rt->fl.proto,
+				    .proto = protocol,
 				    .fl_ip_sport = sport,
 				    .fl_ip_dport = dport };
 
-- 
cgit v1.2.3


From 5e2b61f78411be25f0b84f97d5b5d312f184dfd1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 4 Mar 2011 21:47:09 -0800
Subject: ipv4: Remove flowi from struct rtable.

The only necessary parts are the src/dst addresses, the
interface indexes, the TOS, and the mark.

The rest is unnecessary bloat, which amounts to nearly
50 bytes on 64-bit.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h     |  22 ++++---
 net/ipv4/icmp.c         |   2 +-
 net/ipv4/ipmr.c         |  52 ++++++++++++----
 net/ipv4/route.c        | 153 ++++++++++++++++++++++++++----------------------
 net/ipv4/xfrm4_policy.c |   7 ++-
 net/sched/cls_route.c   |   2 +-
 net/sched/em_meta.c     |   2 +-
 7 files changed, 146 insertions(+), 94 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index 8905d90e0044..9257f5f17337 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -53,16 +53,20 @@ struct fib_info;
 struct rtable {
 	struct dst_entry	dst;
 
-	/* Cache lookup keys */
-	struct flowi		fl;
+	/* Lookup key. */
+	__be32			rt_key_dst;
+	__be32			rt_key_src;
 
 	int			rt_genid;
 	unsigned		rt_flags;
 	__u16			rt_type;
+	__u8			rt_tos;
 
 	__be32			rt_dst;	/* Path destination	*/
 	__be32			rt_src;	/* Path source		*/
 	int			rt_iif;
+	int			rt_oif;
+	__u32			rt_mark;
 
 	/* Info on neighbour */
 	__be32			rt_gateway;
@@ -76,12 +80,12 @@ struct rtable {
 
 static inline bool rt_is_input_route(struct rtable *rt)
 {
-	return rt->fl.iif != 0;
+	return rt->rt_iif != 0;
 }
 
 static inline bool rt_is_output_route(struct rtable *rt)
 {
-	return rt->fl.iif == 0;
+	return rt->rt_iif == 0;
 }
 
 struct ip_rt_acct {
@@ -212,11 +216,11 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 					       __be16 dport, struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
-		struct flowi fl = { .oif = rt->fl.oif,
-				    .mark = rt->fl.mark,
-				    .fl4_dst = rt->fl.fl4_dst,
-				    .fl4_src = rt->fl.fl4_src,
-				    .fl4_tos = rt->fl.fl4_tos,
+		struct flowi fl = { .oif = rt->rt_oif,
+				    .mark = rt->rt_mark,
+				    .fl4_dst = rt->rt_key_dst,
+				    .fl4_src = rt->rt_key_src,
+				    .fl4_tos = rt->rt_tos,
 				    .proto = protocol,
 				    .fl_ip_sport = sport,
 				    .fl_ip_dport = dport };
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 994a785d98f9..1771ce662548 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -563,7 +563,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		rcu_read_lock();
 		if (rt_is_input_route(rt) &&
 		    net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
-			dev = dev_get_by_index_rcu(net, rt->fl.iif);
+			dev = dev_get_by_index_rcu(net, rt->rt_iif);
 
 		if (dev)
 			saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 26ca2f2d37ce..9d5f6340af13 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1813,12 +1813,22 @@ int ip_mr_input(struct sk_buff *skb)
 	if (IPCB(skb)->flags & IPSKB_FORWARDED)
 		goto dont_forward;
 
-	err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt);
-	if (err < 0) {
-		kfree_skb(skb);
-		return err;
+	{
+		struct rtable *rt = skb_rtable(skb);
+		struct flowi fl = {
+			.fl4_dst = rt->rt_key_dst,
+			.fl4_src = rt->rt_key_src,
+			.fl4_tos = rt->rt_tos,
+			.oif = rt->rt_oif,
+			.iif = rt->rt_iif,
+			.mark = rt->rt_mark,
+		};
+		err = ipmr_fib_lookup(net, &fl, &mrt);
+		if (err < 0) {
+			kfree_skb(skb);
+			return err;
+		}
 	}
-
 	if (!local) {
 		if (IPCB(skb)->opt.router_alert) {
 			if (ip_call_ra_chain(skb))
@@ -1946,9 +1956,19 @@ int pim_rcv_v1(struct sk_buff *skb)
 
 	pim = igmp_hdr(skb);
 
-	if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0)
-		goto drop;
-
+	{
+		struct rtable *rt = skb_rtable(skb);
+		struct flowi fl = {
+			.fl4_dst = rt->rt_key_dst,
+			.fl4_src = rt->rt_key_src,
+			.fl4_tos = rt->rt_tos,
+			.oif = rt->rt_oif,
+			.iif = rt->rt_iif,
+			.mark = rt->rt_mark,
+		};
+		if (ipmr_fib_lookup(net, &fl, &mrt) < 0)
+			goto drop;
+	}
 	if (!mrt->mroute_do_pim ||
 	    pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER)
 		goto drop;
@@ -1978,9 +1998,19 @@ static int pim_rcv(struct sk_buff *skb)
 	     csum_fold(skb_checksum(skb, 0, skb->len, 0))))
 		goto drop;
 
-	if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0)
-		goto drop;
-
+	{
+		struct rtable *rt = skb_rtable(skb);
+		struct flowi fl = {
+			.fl4_dst = rt->rt_key_dst,
+			.fl4_src = rt->rt_key_src,
+			.fl4_tos = rt->rt_tos,
+			.oif = rt->rt_oif,
+			.iif = rt->rt_iif,
+			.mark = rt->rt_mark,
+		};
+		if (ipmr_fib_lookup(net, &fl, &mrt) < 0)
+			goto drop;
+	}
 	if (__pim_rcv(mrt, skb, sizeof(*pim))) {
 drop:
 		kfree_skb(skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 602473c92019..92a24ea34c1b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -424,7 +424,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			dst_metric(&r->dst, RTAX_WINDOW),
 			(int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
 			      dst_metric(&r->dst, RTAX_RTTVAR)),
-			r->fl.fl4_tos,
+			r->rt_tos,
 			r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
 			r->dst.hh ? (r->dst.hh->hh_output ==
 				       dev_queue_xmit) : 0,
@@ -711,22 +711,22 @@ static inline bool rt_caching(const struct net *net)
 		net->ipv4.sysctl_rt_cache_rebuild_count;
 }
 
-static inline bool compare_hash_inputs(const struct flowi *fl1,
-					const struct flowi *fl2)
+static inline bool compare_hash_inputs(const struct rtable *rt1,
+				       const struct rtable *rt2)
 {
-	return ((((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
-		((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
-		(fl1->iif ^ fl2->iif)) == 0);
+	return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
+		((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
+		(rt1->rt_iif ^ rt2->rt_iif)) == 0);
 }
 
-static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
+static inline int compare_keys(struct rtable *rt1, struct rtable *rt2)
 {
-	return (((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
-		((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
-		(fl1->mark ^ fl2->mark) |
-		(*(u16 *)&fl1->fl4_tos ^ *(u16 *)&fl2->fl4_tos) |
-		(fl1->oif ^ fl2->oif) |
-		(fl1->iif ^ fl2->iif)) == 0;
+	return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
+		((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
+		(rt1->rt_mark ^ rt2->rt_mark) |
+		(rt1->rt_tos ^ rt2->rt_tos) |
+		(rt1->rt_oif ^ rt2->rt_oif) |
+		(rt1->rt_iif ^ rt2->rt_iif)) == 0;
 }
 
 static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
@@ -813,7 +813,7 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth)
 	const struct rtable *aux = head;
 
 	while (aux != rth) {
-		if (compare_hash_inputs(&aux->fl, &rth->fl))
+		if (compare_hash_inputs(aux, rth))
 			return 0;
 		aux = rcu_dereference_protected(aux->dst.rt_next, 1);
 	}
@@ -1073,7 +1073,7 @@ restart:
 			rt_free(rth);
 			continue;
 		}
-		if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {
+		if (compare_keys(rth, rt) && compare_netns(rth, rt)) {
 			/* Put it first */
 			*rthp = rth->dst.rt_next;
 			/*
@@ -1136,7 +1136,7 @@ restart:
 			rt_emergency_hash_rebuild(net);
 			spin_unlock_bh(rt_hash_lock_addr(hash));
 
-			hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
+			hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
 					ifindex, rt_genid(net));
 			goto restart;
 		}
@@ -1344,12 +1344,12 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 			ip_rt_put(rt);
 			ret = NULL;
 		} else if (rt->rt_flags & RTCF_REDIRECTED) {
-			unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
-						rt->fl.oif,
+			unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
+						rt->rt_oif,
 						rt_genid(dev_net(dst->dev)));
 #if RT_CACHE_DEBUG >= 1
 			printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n",
-				&rt->rt_dst, rt->fl.fl4_tos);
+				&rt->rt_dst, rt->rt_tos);
 #endif
 			rt_del(hash, rt);
 			ret = NULL;
@@ -1697,8 +1697,17 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 	if (rt_is_output_route(rt))
 		src = rt->rt_src;
 	else {
+		struct flowi fl = {
+			.fl4_dst = rt->rt_key_dst,
+			.fl4_src = rt->rt_key_src,
+			.fl4_tos = rt->rt_tos,
+			.oif = rt->rt_oif,
+			.iif = rt->rt_iif,
+			.mark = rt->rt_mark,
+		};
+
 		rcu_read_lock();
-		if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0)
+		if (fib_lookup(dev_net(rt->dst.dev), &fl, &res) == 0)
 			src = FIB_RES_PREFSRC(res);
 		else
 			src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
@@ -1748,7 +1757,8 @@ static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
 	return mtu;
 }
 
-static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
+static void rt_init_metrics(struct rtable *rt, const struct flowi *oldflp,
+			    struct fib_info *fi)
 {
 	struct inet_peer *peer;
 	int create = 0;
@@ -1756,7 +1766,7 @@ static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
 	/* If a peer entry exists for this destination, we must hook
 	 * it up in order to get at cached metrics.
 	 */
-	if (rt->fl.flags & FLOWI_FLAG_PRECOW_METRICS)
+	if (oldflp && (oldflp->flags & FLOWI_FLAG_PRECOW_METRICS))
 		create = 1;
 
 	rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
@@ -1783,7 +1793,8 @@ static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
 	}
 }
 
-static void rt_set_nexthop(struct rtable *rt, const struct fib_result *res,
+static void rt_set_nexthop(struct rtable *rt, const struct flowi *oldflp,
+			   const struct fib_result *res,
 			   struct fib_info *fi, u16 type, u32 itag)
 {
 	struct dst_entry *dst = &rt->dst;
@@ -1792,7 +1803,7 @@ static void rt_set_nexthop(struct rtable *rt, const struct fib_result *res,
 		if (FIB_RES_GW(*res) &&
 		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
 			rt->rt_gateway = FIB_RES_GW(*res);
-		rt_init_metrics(rt, fi);
+		rt_init_metrics(rt, oldflp, fi);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
 #endif
@@ -1861,20 +1872,19 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	rth->dst.output = ip_rt_bug;
 
-	rth->fl.fl4_dst	= daddr;
+	rth->rt_key_dst	= daddr;
 	rth->rt_dst	= daddr;
-	rth->fl.fl4_tos	= tos;
-	rth->fl.mark    = skb->mark;
-	rth->fl.fl4_src	= saddr;
+	rth->rt_tos	= tos;
+	rth->rt_mark    = skb->mark;
+	rth->rt_key_src	= saddr;
 	rth->rt_src	= saddr;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
-	rth->rt_iif	=
-	rth->fl.iif	= dev->ifindex;
+	rth->rt_iif	= dev->ifindex;
 	rth->dst.dev	= init_net.loopback_dev;
 	dev_hold(rth->dst.dev);
-	rth->fl.oif	= 0;
+	rth->rt_oif	= 0;
 	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
 	rth->rt_genid	= rt_genid(dev_net(dev));
@@ -1999,25 +2009,24 @@ static int __mkroute_input(struct sk_buff *skb,
 		goto cleanup;
 	}
 
-	rth->fl.fl4_dst	= daddr;
+	rth->rt_key_dst	= daddr;
 	rth->rt_dst	= daddr;
-	rth->fl.fl4_tos	= tos;
-	rth->fl.mark    = skb->mark;
-	rth->fl.fl4_src	= saddr;
+	rth->rt_tos	= tos;
+	rth->rt_mark    = skb->mark;
+	rth->rt_key_src	= saddr;
 	rth->rt_src	= saddr;
 	rth->rt_gateway	= daddr;
-	rth->rt_iif 	=
-		rth->fl.iif	= in_dev->dev->ifindex;
+	rth->rt_iif 	= in_dev->dev->ifindex;
 	rth->dst.dev	= (out_dev)->dev;
 	dev_hold(rth->dst.dev);
-	rth->fl.oif 	= 0;
+	rth->rt_oif 	= 0;
 	rth->rt_spec_dst= spec_dst;
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
 	rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
 
-	rt_set_nexthop(rth, res, res->fi, res->type, itag);
+	rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
 
 	rth->rt_flags = flags;
 
@@ -2172,17 +2181,16 @@ local_input:
 	rth->dst.output= ip_rt_bug;
 	rth->rt_genid = rt_genid(net);
 
-	rth->fl.fl4_dst	= daddr;
+	rth->rt_key_dst	= daddr;
 	rth->rt_dst	= daddr;
-	rth->fl.fl4_tos	= tos;
-	rth->fl.mark    = skb->mark;
-	rth->fl.fl4_src	= saddr;
+	rth->rt_tos	= tos;
+	rth->rt_mark    = skb->mark;
+	rth->rt_key_src	= saddr;
 	rth->rt_src	= saddr;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
-	rth->rt_iif	=
-	rth->fl.iif	= dev->ifindex;
+	rth->rt_iif	= dev->ifindex;
 	rth->dst.dev	= net->loopback_dev;
 	dev_hold(rth->dst.dev);
 	rth->rt_gateway	= daddr;
@@ -2261,12 +2269,12 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
 	     rth = rcu_dereference(rth->dst.rt_next)) {
-		if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
-		     ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
-		     (rth->fl.iif ^ iif) |
-		     rth->fl.oif |
-		     (rth->fl.fl4_tos ^ tos)) == 0 &&
-		    rth->fl.mark == skb->mark &&
+		if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) |
+		     ((__force u32)rth->rt_key_src ^ (__force u32)saddr) |
+		     (rth->rt_iif ^ iif) |
+		     rth->rt_oif |
+		     (rth->rt_tos ^ tos)) == 0 &&
+		    rth->rt_mark == skb->mark &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
 			if (noref) {
@@ -2374,11 +2382,11 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
-	rth->fl.fl4_dst	= oldflp->fl4_dst;
-	rth->fl.fl4_tos	= tos;
-	rth->fl.fl4_src	= oldflp->fl4_src;
-	rth->fl.oif	= oldflp->oif;
-	rth->fl.mark    = oldflp->mark;
+	rth->rt_key_dst	= oldflp->fl4_dst;
+	rth->rt_tos	= tos;
+	rth->rt_key_src	= oldflp->fl4_src;
+	rth->rt_oif	= oldflp->oif;
+	rth->rt_mark    = oldflp->mark;
 	rth->rt_dst	= fl->fl4_dst;
 	rth->rt_src	= fl->fl4_src;
 	rth->rt_iif	= 0;
@@ -2416,7 +2424,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 #endif
 	}
 
-	rt_set_nexthop(rth, res, fi, type, 0);
+	rt_set_nexthop(rth, oldflp, res, fi, type, 0);
 
 	rth->rt_flags = flags;
 	return rth;
@@ -2629,12 +2637,12 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
 	rcu_read_lock_bh();
 	for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
 		rth = rcu_dereference_bh(rth->dst.rt_next)) {
-		if (rth->fl.fl4_dst == flp->fl4_dst &&
-		    rth->fl.fl4_src == flp->fl4_src &&
+		if (rth->rt_key_dst == flp->fl4_dst &&
+		    rth->rt_key_src == flp->fl4_src &&
 		    rt_is_output_route(rth) &&
-		    rth->fl.oif == flp->oif &&
-		    rth->fl.mark == flp->mark &&
-		    !((rth->fl.fl4_tos ^ flp->fl4_tos) &
+		    rth->rt_oif == flp->oif &&
+		    rth->rt_mark == flp->mark &&
+		    !((rth->rt_tos ^ flp->fl4_tos) &
 			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
@@ -2693,7 +2701,12 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		if (new->dev)
 			dev_hold(new->dev);
 
-		rt->fl = ort->fl;
+		rt->rt_key_dst = ort->rt_key_dst;
+		rt->rt_key_src = ort->rt_key_src;
+		rt->rt_tos = ort->rt_tos;
+		rt->rt_iif = ort->rt_iif;
+		rt->rt_oif = ort->rt_oif;
+		rt->rt_mark = ort->rt_mark;
 
 		rt->rt_genid = rt_genid(net);
 		rt->rt_flags = ort->rt_flags;
@@ -2756,7 +2769,7 @@ static int rt_fill_info(struct net *net,
 	r->rtm_family	 = AF_INET;
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
-	r->rtm_tos	= rt->fl.fl4_tos;
+	r->rtm_tos	= rt->rt_tos;
 	r->rtm_table	= RT_TABLE_MAIN;
 	NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN);
 	r->rtm_type	= rt->rt_type;
@@ -2768,9 +2781,9 @@ static int rt_fill_info(struct net *net,
 
 	NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
 
-	if (rt->fl.fl4_src) {
+	if (rt->rt_key_src) {
 		r->rtm_src_len = 32;
-		NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src);
+		NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src);
 	}
 	if (rt->dst.dev)
 		NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
@@ -2780,7 +2793,7 @@ static int rt_fill_info(struct net *net,
 #endif
 	if (rt_is_input_route(rt))
 		NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
-	else if (rt->rt_src != rt->fl.fl4_src)
+	else if (rt->rt_src != rt->rt_key_src)
 		NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
 
 	if (rt->rt_dst != rt->rt_gateway)
@@ -2789,8 +2802,8 @@ static int rt_fill_info(struct net *net,
 	if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
 		goto nla_put_failure;
 
-	if (rt->fl.mark)
-		NLA_PUT_BE32(skb, RTA_MARK, rt->fl.mark);
+	if (rt->rt_mark)
+		NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark);
 
 	error = rt->dst.error;
 	expires = (rt->peer && rt->peer->pmtu_expires) ?
@@ -2824,7 +2837,7 @@ static int rt_fill_info(struct net *net,
 			}
 		} else
 #endif
-			NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif);
+			NLA_PUT_U32(skb, RTA_IIF, rt->rt_iif);
 	}
 
 	if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 45b821480427..c70c42e7e77b 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -70,7 +70,12 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 {
 	struct rtable *rt = (struct rtable *)xdst->route;
 
-	xdst->u.rt.fl = *fl;
+	rt->rt_key_dst = fl->fl4_dst;
+	rt->rt_key_src = fl->fl4_src;
+	rt->rt_tos = fl->fl4_tos;
+	rt->rt_iif = fl->iif;
+	rt->rt_oif = fl->oif;
+	rt->rt_mark = fl->mark;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index d580cdfca093..a907905376df 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -143,7 +143,7 @@ static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp,
 	if (head == NULL)
 		goto old_method;
 
-	iif = ((struct rtable *)dst)->fl.iif;
+	iif = ((struct rtable *)dst)->rt_iif;
 
 	h = route4_fastmap_hash(id, iif);
 	if (id == head->fastmap[h].id &&
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index e5e174782677..a4de67eca824 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -264,7 +264,7 @@ META_COLLECTOR(int_rtiif)
 	if (unlikely(skb_rtable(skb) == NULL))
 		*err = -1;
 	else
-		dst->value = skb_rtable(skb)->fl.iif;
+		dst->value = skb_rtable(skb)->rt_iif;
 }
 
 /**************************************************************************
-- 
cgit v1.2.3


From 4ba8216cd90560bc402f52076f64d8546e8aefcb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Jan 2011 22:52:22 +0100
Subject: BKL: That's all, folks

This removes the implementation of the big kernel lock,
at last. A lot of people have worked on this in the
past, I so the credit for this patch should be with
everyone who participated in the hunt.

The names on the Cc list are the people that were the
most active in this, according to the recorded git
history, in alphabetical order.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Alan Cox <alan@linux.intel.com>
Cc: Alessio Igor Bogani <abogani@texware.it>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Hendry <andrew.hendry@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Hans Verkuil <hverkuil@xs4all.nl>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Jan Blunck <jblunck@infradead.org>
Cc: John Kacur <jkacur@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Oliver Neukum <oliver@neukum.org>
Cc: Paul Menage <menage@google.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/hardirq.h  |   9 +---
 include/linux/smp_lock.h |  65 ----------------------
 init/Kconfig             |   5 --
 kernel/sched.c           |   9 +---
 lib/Kconfig.debug        |   9 ----
 lib/Makefile             |   1 -
 lib/kernel_lock.c        | 136 -----------------------------------------------
 7 files changed, 2 insertions(+), 232 deletions(-)
 delete mode 100644 include/linux/smp_lock.h
 delete mode 100644 lib/kernel_lock.c

(limited to 'include')

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 32f9fd6619b4..ba362171e8ae 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -93,13 +93,6 @@
  */
 #define in_nmi()	(preempt_count() & NMI_MASK)
 
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_BKL)
-# include <linux/sched.h>
-# define PREEMPT_INATOMIC_BASE (current->lock_depth >= 0)
-#else
-# define PREEMPT_INATOMIC_BASE 0
-#endif
-
 #if defined(CONFIG_PREEMPT)
 # define PREEMPT_CHECK_OFFSET 1
 #else
@@ -113,7 +106,7 @@
  * used in the general case to determine whether sleeping is possible.
  * Do not use in_atomic() in driver code.
  */
-#define in_atomic()	((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_INATOMIC_BASE)
+#define in_atomic()	((preempt_count() & ~PREEMPT_ACTIVE) != 0)
 
 /*
  * Check whether we were atomic before we did preempt_disable():
diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h
deleted file mode 100644
index 3a1988202731..000000000000
--- a/include/linux/smp_lock.h
+++ /dev/null
@@ -1,65 +0,0 @@
-#ifndef __LINUX_SMPLOCK_H
-#define __LINUX_SMPLOCK_H
-
-#ifdef CONFIG_LOCK_KERNEL
-#include <linux/sched.h>
-
-extern int __lockfunc __reacquire_kernel_lock(void);
-extern void __lockfunc __release_kernel_lock(void);
-
-/*
- * Release/re-acquire global kernel lock for the scheduler
- */
-#define release_kernel_lock(tsk) do { 		\
-	if (unlikely((tsk)->lock_depth >= 0))	\
-		__release_kernel_lock();	\
-} while (0)
-
-static inline int reacquire_kernel_lock(struct task_struct *task)
-{
-	if (unlikely(task->lock_depth >= 0))
-		return __reacquire_kernel_lock();
-	return 0;
-}
-
-extern void __lockfunc
-_lock_kernel(const char *func, const char *file, int line)
-__acquires(kernel_lock);
-
-extern void __lockfunc
-_unlock_kernel(const char *func, const char *file, int line)
-__releases(kernel_lock);
-
-#define lock_kernel() do {					\
-	_lock_kernel(__func__, __FILE__, __LINE__);		\
-} while (0)
-
-#define unlock_kernel()	do {					\
-	_unlock_kernel(__func__, __FILE__, __LINE__);		\
-} while (0)
-
-/*
- * Various legacy drivers don't really need the BKL in a specific
- * function, but they *do* need to know that the BKL became available.
- * This function just avoids wrapping a bunch of lock/unlock pairs
- * around code which doesn't really need it.
- */
-static inline void cycle_kernel_lock(void)
-{
-	lock_kernel();
-	unlock_kernel();
-}
-
-#else
-
-#ifdef CONFIG_BKL /* provoke build bug if not set */
-#define lock_kernel()
-#define unlock_kernel()
-#define cycle_kernel_lock()			do { } while(0)
-#endif /* CONFIG_BKL */
-
-#define release_kernel_lock(task)		do { } while(0)
-#define reacquire_kernel_lock(task)		0
-
-#endif /* CONFIG_LOCK_KERNEL */
-#endif /* __LINUX_SMPLOCK_H */
diff --git a/init/Kconfig b/init/Kconfig
index be788c0957d4..a88d1c919a4d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -69,11 +69,6 @@ config BROKEN_ON_SMP
 	depends on BROKEN || !SMP
 	default y
 
-config LOCK_KERNEL
-	bool
-	depends on (SMP || PREEMPT) && BKL
-	default y
-
 config INIT_ENV_ARG_LIMIT
 	int
 	default 32 if !UML
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..827c170c6017 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -32,7 +32,6 @@
 #include <linux/init.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
-#include <linux/smp_lock.h>
 #include <asm/mmu_context.h>
 #include <linux/interrupt.h>
 #include <linux/capability.h>
@@ -3945,9 +3944,6 @@ need_resched:
 	rcu_note_context_switch(cpu);
 	prev = rq->curr;
 
-	release_kernel_lock(prev);
-need_resched_nonpreemptible:
-
 	schedule_debug(prev);
 
 	if (sched_feat(HRTICK))
@@ -4010,9 +4006,6 @@ need_resched_nonpreemptible:
 
 	post_schedule(rq);
 
-	if (unlikely(reacquire_kernel_lock(prev)))
-		goto need_resched_nonpreemptible;
-
 	preempt_enable_no_resched();
 	if (need_resched())
 		goto need_resched;
@@ -8074,7 +8067,7 @@ static inline int preempt_count_equals(int preempt_offset)
 {
 	int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
 
-	return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+	return (nested == preempt_offset);
 }
 
 void __might_sleep(const char *file, int line, int preempt_offset)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2b97418c67e2..6f440d82b58d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -470,15 +470,6 @@ config DEBUG_MUTEXES
 	 This feature allows mutex semantics violations to be detected and
 	 reported.
 
-config BKL
-	bool "Big Kernel Lock" if (SMP || PREEMPT)
-	default y
-	help
-	  This is the traditional lock that is used in old code instead
-	  of proper locking. All drivers that use the BKL should depend
-	  on this symbol.
-	  Say Y here unless you are working on removing the BKL.
-
 config DEBUG_LOCK_ALLOC
 	bool "Lock debugging: detect incorrect freeing of live locks"
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
diff --git a/lib/Makefile b/lib/Makefile
index cbb774f7d41d..de6c609bb4e4 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -43,7 +43,6 @@ obj-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o
 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
-obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
 obj-$(CONFIG_BTREE) += btree.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 obj-$(CONFIG_DEBUG_LIST) += list_debug.o
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
deleted file mode 100644
index d80e12265862..000000000000
--- a/lib/kernel_lock.c
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- * lib/kernel_lock.c
- *
- * This is the traditional BKL - big kernel lock. Largely
- * relegated to obsolescence, but used by various less
- * important (or lazy) subsystems.
- */
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/semaphore.h>
-#include <linux/smp_lock.h>
-
-/*
- * The 'big kernel lock'
- *
- * This spinlock is taken and released recursively by lock_kernel()
- * and unlock_kernel().  It is transparently dropped and reacquired
- * over schedule().  It is used to protect legacy code that hasn't
- * been migrated to a proper locking design yet.
- *
- * Don't use in new code.
- */
-static  __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(kernel_flag);
-
-
-/*
- * Acquire/release the underlying lock from the scheduler.
- *
- * This is called with preemption disabled, and should
- * return an error value if it cannot get the lock and
- * TIF_NEED_RESCHED gets set.
- *
- * If it successfully gets the lock, it should increment
- * the preemption count like any spinlock does.
- *
- * (This works on UP too - do_raw_spin_trylock will never
- * return false in that case)
- */
-int __lockfunc __reacquire_kernel_lock(void)
-{
-	while (!do_raw_spin_trylock(&kernel_flag)) {
-		if (need_resched())
-			return -EAGAIN;
-		cpu_relax();
-	}
-	preempt_disable();
-	return 0;
-}
-
-void __lockfunc __release_kernel_lock(void)
-{
-	do_raw_spin_unlock(&kernel_flag);
-	preempt_enable_no_resched();
-}
-
-/*
- * These are the BKL spinlocks - we try to be polite about preemption.
- * If SMP is not on (ie UP preemption), this all goes away because the
- * do_raw_spin_trylock() will always succeed.
- */
-#ifdef CONFIG_PREEMPT
-static inline void __lock_kernel(void)
-{
-	preempt_disable();
-	if (unlikely(!do_raw_spin_trylock(&kernel_flag))) {
-		/*
-		 * If preemption was disabled even before this
-		 * was called, there's nothing we can be polite
-		 * about - just spin.
-		 */
-		if (preempt_count() > 1) {
-			do_raw_spin_lock(&kernel_flag);
-			return;
-		}
-
-		/*
-		 * Otherwise, let's wait for the kernel lock
-		 * with preemption enabled..
-		 */
-		do {
-			preempt_enable();
-			while (raw_spin_is_locked(&kernel_flag))
-				cpu_relax();
-			preempt_disable();
-		} while (!do_raw_spin_trylock(&kernel_flag));
-	}
-}
-
-#else
-
-/*
- * Non-preemption case - just get the spinlock
- */
-static inline void __lock_kernel(void)
-{
-	do_raw_spin_lock(&kernel_flag);
-}
-#endif
-
-static inline void __unlock_kernel(void)
-{
-	/*
-	 * the BKL is not covered by lockdep, so we open-code the
-	 * unlocking sequence (and thus avoid the dep-chain ops):
-	 */
-	do_raw_spin_unlock(&kernel_flag);
-	preempt_enable();
-}
-
-/*
- * Getting the big kernel lock.
- *
- * This cannot happen asynchronously, so we only need to
- * worry about other CPU's.
- */
-void __lockfunc _lock_kernel(const char *func, const char *file, int line)
-{
-	int depth = current->lock_depth + 1;
-
-	if (likely(!depth)) {
-		might_sleep();
-		__lock_kernel();
-	}
-	current->lock_depth = depth;
-}
-
-void __lockfunc _unlock_kernel(const char *func, const char *file, int line)
-{
-	BUG_ON(current->lock_depth < 0);
-	if (likely(--current->lock_depth < 0))
-		__unlock_kernel();
-}
-
-EXPORT_SYMBOL(_lock_kernel);
-EXPORT_SYMBOL(_unlock_kernel);
-
-- 
cgit v1.2.3


From 550462378515a82279e07f12e2c105f617f112f8 Mon Sep 17 00:00:00 2001
From: Mayank Rana <mrana@codeaurora.org>
Date: Mon, 7 Mar 2011 10:28:42 +0530
Subject: serial: msm_serial_hs: Add MSM high speed UART driver

This driver supports UART-DM HW on MSM platforms. It uses the on
chip DMA to drive data transfers and has optional support for UART
power management independent of Linux suspend/resume and wakeup
from Rx.

The driver was originally developed by Google. It is functionally
equivalent to the version available at:
http://android.git.kernel.org/?p=kernel/experimental.git
the differences being:
1) Remove wakelocks and change unsupported DMA API.
2) Replace clock selection register codes by macros.
3) Fix checkpatch errors and add inline documentation.
4) Add runtime PM hooks for active power state transitions.
5) Handle error path and cleanup resources if required.

CC: Nick Pelly <npelly@google.com>
Signed-off-by: Sankalp Bose <sankalpb@codeaurora.org>
Signed-off-by: Mayank Rana <mrana@codeaurora.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/tty/serial/Kconfig                  |   12 +
 drivers/tty/serial/Makefile                 |    1 +
 drivers/tty/serial/msm_serial_hs.c          | 1880 +++++++++++++++++++++++++++
 include/linux/platform_data/msm_serial_hs.h |   49 +
 4 files changed, 1942 insertions(+)
 create mode 100644 drivers/tty/serial/msm_serial_hs.c
 create mode 100644 include/linux/platform_data/msm_serial_hs.h

(limited to 'include')

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 90d939a4ee5d..d9ccbf825095 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1319,6 +1319,18 @@ config SERIAL_MSM_CONSOLE
 	depends on SERIAL_MSM=y
 	select SERIAL_CORE_CONSOLE
 
+config SERIAL_MSM_HS
+	tristate "MSM UART High Speed: Serial Driver"
+	depends on ARCH_MSM
+	select SERIAL_CORE
+	help
+	  If you have a machine based on MSM family of SoCs, you
+	  can enable its onboard high speed serial port by enabling
+	  this option.
+
+	  Choose M here to compile it as a module. The module will be
+	  called msm_serial_hs.
+
 config SERIAL_VT8500
 	bool "VIA VT8500 on-chip serial port support"
 	depends on ARM && ARCH_VT8500
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index 0c6aefb55acf..d94dc005c8a6 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -76,6 +76,7 @@ obj-$(CONFIG_SERIAL_SGI_IOC3) += ioc3_serial.o
 obj-$(CONFIG_SERIAL_ATMEL) += atmel_serial.o
 obj-$(CONFIG_SERIAL_UARTLITE) += uartlite.o
 obj-$(CONFIG_SERIAL_MSM) += msm_serial.o
+obj-$(CONFIG_SERIAL_MSM_HS) += msm_serial_hs.o
 obj-$(CONFIG_SERIAL_NETX) += netx-serial.o
 obj-$(CONFIG_SERIAL_OF_PLATFORM) += of_serial.o
 obj-$(CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL) += nwpserial.o
diff --git a/drivers/tty/serial/msm_serial_hs.c b/drivers/tty/serial/msm_serial_hs.c
new file mode 100644
index 000000000000..2e7fc9cee9cc
--- /dev/null
+++ b/drivers/tty/serial/msm_serial_hs.c
@@ -0,0 +1,1880 @@
+/*
+ * MSM 7k/8k High speed uart driver
+ *
+ * Copyright (c) 2007-2011, Code Aurora Forum. All rights reserved.
+ * Copyright (c) 2008 Google Inc.
+ * Modified: Nick Pelly <npelly@google.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * Has optional support for uart power management independent of linux
+ * suspend/resume:
+ *
+ * RX wakeup.
+ * UART wakeup can be triggered by RX activity (using a wakeup GPIO on the
+ * UART RX pin). This should only be used if there is not a wakeup
+ * GPIO on the UART CTS, and the first RX byte is known (for example, with the
+ * Bluetooth Texas Instruments HCILL protocol), since the first RX byte will
+ * always be lost. RTS will be asserted even while the UART is off in this mode
+ * of operation. See msm_serial_hs_platform_data.rx_wakeup_irq.
+ */
+
+#include <linux/module.h>
+
+#include <linux/serial.h>
+#include <linux/serial_core.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
+#include <linux/atomic.h>
+#include <asm/irq.h>
+#include <asm/system.h>
+
+#include <mach/hardware.h>
+#include <mach/dma.h>
+#include <linux/platform_data/msm_serial_hs.h>
+
+/* HSUART Registers */
+#define UARTDM_MR1_ADDR 0x0
+#define UARTDM_MR2_ADDR 0x4
+
+/* Data Mover result codes */
+#define RSLT_FIFO_CNTR_BMSK (0xE << 28)
+#define RSLT_VLD            BIT(1)
+
+/* write only register */
+#define UARTDM_CSR_ADDR 0x8
+#define UARTDM_CSR_115200 0xFF
+#define UARTDM_CSR_57600  0xEE
+#define UARTDM_CSR_38400  0xDD
+#define UARTDM_CSR_28800  0xCC
+#define UARTDM_CSR_19200  0xBB
+#define UARTDM_CSR_14400  0xAA
+#define UARTDM_CSR_9600   0x99
+#define UARTDM_CSR_7200   0x88
+#define UARTDM_CSR_4800   0x77
+#define UARTDM_CSR_3600   0x66
+#define UARTDM_CSR_2400   0x55
+#define UARTDM_CSR_1200   0x44
+#define UARTDM_CSR_600    0x33
+#define UARTDM_CSR_300    0x22
+#define UARTDM_CSR_150    0x11
+#define UARTDM_CSR_75     0x00
+
+/* write only register */
+#define UARTDM_TF_ADDR 0x70
+#define UARTDM_TF2_ADDR 0x74
+#define UARTDM_TF3_ADDR 0x78
+#define UARTDM_TF4_ADDR 0x7C
+
+/* write only register */
+#define UARTDM_CR_ADDR 0x10
+#define UARTDM_IMR_ADDR 0x14
+
+#define UARTDM_IPR_ADDR 0x18
+#define UARTDM_TFWR_ADDR 0x1c
+#define UARTDM_RFWR_ADDR 0x20
+#define UARTDM_HCR_ADDR 0x24
+#define UARTDM_DMRX_ADDR 0x34
+#define UARTDM_IRDA_ADDR 0x38
+#define UARTDM_DMEN_ADDR 0x3c
+
+/* UART_DM_NO_CHARS_FOR_TX */
+#define UARTDM_NCF_TX_ADDR 0x40
+
+#define UARTDM_BADR_ADDR 0x44
+
+#define UARTDM_SIM_CFG_ADDR 0x80
+/* Read Only register */
+#define UARTDM_SR_ADDR 0x8
+
+/* Read Only register */
+#define UARTDM_RF_ADDR  0x70
+#define UARTDM_RF2_ADDR 0x74
+#define UARTDM_RF3_ADDR 0x78
+#define UARTDM_RF4_ADDR 0x7C
+
+/* Read Only register */
+#define UARTDM_MISR_ADDR 0x10
+
+/* Read Only register */
+#define UARTDM_ISR_ADDR 0x14
+#define UARTDM_RX_TOTAL_SNAP_ADDR 0x38
+
+#define UARTDM_RXFS_ADDR 0x50
+
+/* Register field Mask Mapping */
+#define UARTDM_SR_PAR_FRAME_BMSK        BIT(5)
+#define UARTDM_SR_OVERRUN_BMSK          BIT(4)
+#define UARTDM_SR_TXEMT_BMSK            BIT(3)
+#define UARTDM_SR_TXRDY_BMSK            BIT(2)
+#define UARTDM_SR_RXRDY_BMSK            BIT(0)
+
+#define UARTDM_CR_TX_DISABLE_BMSK       BIT(3)
+#define UARTDM_CR_RX_DISABLE_BMSK       BIT(1)
+#define UARTDM_CR_TX_EN_BMSK            BIT(2)
+#define UARTDM_CR_RX_EN_BMSK            BIT(0)
+
+/* UARTDM_CR channel_comman bit value (register field is bits 8:4) */
+#define RESET_RX                0x10
+#define RESET_TX                0x20
+#define RESET_ERROR_STATUS      0x30
+#define RESET_BREAK_INT         0x40
+#define START_BREAK             0x50
+#define STOP_BREAK              0x60
+#define RESET_CTS               0x70
+#define RESET_STALE_INT         0x80
+#define RFR_LOW                 0xD0
+#define RFR_HIGH                0xE0
+#define CR_PROTECTION_EN        0x100
+#define STALE_EVENT_ENABLE      0x500
+#define STALE_EVENT_DISABLE     0x600
+#define FORCE_STALE_EVENT       0x400
+#define CLEAR_TX_READY          0x300
+#define RESET_TX_ERROR          0x800
+#define RESET_TX_DONE           0x810
+
+#define UARTDM_MR1_AUTO_RFR_LEVEL1_BMSK 0xffffff00
+#define UARTDM_MR1_AUTO_RFR_LEVEL0_BMSK 0x3f
+#define UARTDM_MR1_CTS_CTL_BMSK 0x40
+#define UARTDM_MR1_RX_RDY_CTL_BMSK 0x80
+
+#define UARTDM_MR2_ERROR_MODE_BMSK 0x40
+#define UARTDM_MR2_BITS_PER_CHAR_BMSK 0x30
+
+/* bits per character configuration */
+#define FIVE_BPC  (0 << 4)
+#define SIX_BPC   (1 << 4)
+#define SEVEN_BPC (2 << 4)
+#define EIGHT_BPC (3 << 4)
+
+#define UARTDM_MR2_STOP_BIT_LEN_BMSK 0xc
+#define STOP_BIT_ONE (1 << 2)
+#define STOP_BIT_TWO (3 << 2)
+
+#define UARTDM_MR2_PARITY_MODE_BMSK 0x3
+
+/* Parity configuration */
+#define NO_PARITY 0x0
+#define EVEN_PARITY 0x1
+#define ODD_PARITY 0x2
+#define SPACE_PARITY 0x3
+
+#define UARTDM_IPR_STALE_TIMEOUT_MSB_BMSK 0xffffff80
+#define UARTDM_IPR_STALE_LSB_BMSK 0x1f
+
+/* These can be used for both ISR and IMR register */
+#define UARTDM_ISR_TX_READY_BMSK        BIT(7)
+#define UARTDM_ISR_CURRENT_CTS_BMSK     BIT(6)
+#define UARTDM_ISR_DELTA_CTS_BMSK       BIT(5)
+#define UARTDM_ISR_RXLEV_BMSK           BIT(4)
+#define UARTDM_ISR_RXSTALE_BMSK         BIT(3)
+#define UARTDM_ISR_RXBREAK_BMSK         BIT(2)
+#define UARTDM_ISR_RXHUNT_BMSK          BIT(1)
+#define UARTDM_ISR_TXLEV_BMSK           BIT(0)
+
+/* Field definitions for UART_DM_DMEN*/
+#define UARTDM_TX_DM_EN_BMSK 0x1
+#define UARTDM_RX_DM_EN_BMSK 0x2
+
+#define UART_FIFOSIZE 64
+#define UARTCLK 7372800
+
+/* Rx DMA request states */
+enum flush_reason {
+	FLUSH_NONE,
+	FLUSH_DATA_READY,
+	FLUSH_DATA_INVALID,  /* values after this indicate invalid data */
+	FLUSH_IGNORE = FLUSH_DATA_INVALID,
+	FLUSH_STOP,
+	FLUSH_SHUTDOWN,
+};
+
+/* UART clock states */
+enum msm_hs_clk_states_e {
+	MSM_HS_CLK_PORT_OFF,     /* port not in use */
+	MSM_HS_CLK_OFF,          /* clock disabled */
+	MSM_HS_CLK_REQUEST_OFF,  /* disable after TX and RX flushed */
+	MSM_HS_CLK_ON,           /* clock enabled */
+};
+
+/* Track the forced RXSTALE flush during clock off sequence.
+ * These states are only valid during MSM_HS_CLK_REQUEST_OFF */
+enum msm_hs_clk_req_off_state_e {
+	CLK_REQ_OFF_START,
+	CLK_REQ_OFF_RXSTALE_ISSUED,
+	CLK_REQ_OFF_FLUSH_ISSUED,
+	CLK_REQ_OFF_RXSTALE_FLUSHED,
+};
+
+/**
+ * struct msm_hs_tx
+ * @tx_ready_int_en: ok to dma more tx?
+ * @dma_in_flight: tx dma in progress
+ * @xfer: top level DMA command pointer structure
+ * @command_ptr: third level command struct pointer
+ * @command_ptr_ptr: second level command list struct pointer
+ * @mapped_cmd_ptr: DMA view of third level command struct
+ * @mapped_cmd_ptr_ptr: DMA view of second level command list struct
+ * @tx_count: number of bytes to transfer in DMA transfer
+ * @dma_base: DMA view of UART xmit buffer
+ *
+ * This structure describes a single Tx DMA transaction. MSM DMA
+ * commands have two levels of indirection. The top level command
+ * ptr points to a list of command ptr which in turn points to a
+ * single DMA 'command'. In our case each Tx transaction consists
+ * of a single second level pointer pointing to a 'box type' command.
+ */
+struct msm_hs_tx {
+	unsigned int tx_ready_int_en;
+	unsigned int dma_in_flight;
+	struct msm_dmov_cmd xfer;
+	dmov_box *command_ptr;
+	u32 *command_ptr_ptr;
+	dma_addr_t mapped_cmd_ptr;
+	dma_addr_t mapped_cmd_ptr_ptr;
+	int tx_count;
+	dma_addr_t dma_base;
+};
+
+/**
+ * struct msm_hs_rx
+ * @flush: Rx DMA request state
+ * @xfer: top level DMA command pointer structure
+ * @cmdptr_dmaaddr: DMA view of second level command structure
+ * @command_ptr: third level DMA command pointer structure
+ * @command_ptr_ptr: second level DMA command list pointer
+ * @mapped_cmd_ptr: DMA view of the third level command structure
+ * @wait: wait for DMA completion before shutdown
+ * @buffer: destination buffer for RX DMA
+ * @rbuffer: DMA view of buffer
+ * @pool: dma pool out of which coherent rx buffer is allocated
+ * @tty_work: private work-queue for tty flip buffer push task
+ *
+ * This structure describes a single Rx DMA transaction. Rx DMA
+ * transactions use box mode DMA commands.
+ */
+struct msm_hs_rx {
+	enum flush_reason flush;
+	struct msm_dmov_cmd xfer;
+	dma_addr_t cmdptr_dmaaddr;
+	dmov_box *command_ptr;
+	u32 *command_ptr_ptr;
+	dma_addr_t mapped_cmd_ptr;
+	wait_queue_head_t wait;
+	dma_addr_t rbuffer;
+	unsigned char *buffer;
+	struct dma_pool *pool;
+	struct work_struct tty_work;
+};
+
+/**
+ * struct msm_hs_rx_wakeup
+ * @irq: IRQ line to be configured as interrupt source on Rx activity
+ * @ignore: boolean value. 1 = ignore the wakeup interrupt
+ * @rx_to_inject: extra character to be inserted to Rx tty on wakeup
+ * @inject_rx: 1 = insert rx_to_inject. 0 = do not insert extra character
+ *
+ * This is an optional structure required for UART Rx GPIO IRQ based
+ * wakeup from low power state. UART wakeup can be triggered by RX activity
+ * (using a wakeup GPIO on the UART RX pin). This should only be used if
+ * there is not a wakeup GPIO on the UART CTS, and the first RX byte is
+ * known (eg., with the Bluetooth Texas Instruments HCILL protocol),
+ * since the first RX byte will always be lost. RTS will be asserted even
+ * while the UART is clocked off in this mode of operation.
+ */
+struct msm_hs_rx_wakeup {
+	int irq;  /* < 0 indicates low power wakeup disabled */
+	unsigned char ignore;
+	unsigned char inject_rx;
+	char rx_to_inject;
+};
+
+/**
+ * struct msm_hs_port
+ * @uport: embedded uart port structure
+ * @imr_reg: shadow value of UARTDM_IMR
+ * @clk: uart input clock handle
+ * @tx: Tx transaction related data structure
+ * @rx: Rx transaction related data structure
+ * @dma_tx_channel: Tx DMA command channel
+ * @dma_rx_channel Rx DMA command channel
+ * @dma_tx_crci: Tx channel rate control interface number
+ * @dma_rx_crci: Rx channel rate control interface number
+ * @clk_off_timer: Timer to poll DMA event completion before clock off
+ * @clk_off_delay: clk_off_timer poll interval
+ * @clk_state: overall clock state
+ * @clk_req_off_state: post flush clock states
+ * @rx_wakeup: optional rx_wakeup feature related data
+ * @exit_lpm_cb: optional callback to exit low power mode
+ *
+ * Low level serial port structure.
+ */
+struct msm_hs_port {
+	struct uart_port uport;
+	unsigned long imr_reg;
+	struct clk *clk;
+	struct msm_hs_tx tx;
+	struct msm_hs_rx rx;
+
+	int dma_tx_channel;
+	int dma_rx_channel;
+	int dma_tx_crci;
+	int dma_rx_crci;
+
+	struct hrtimer clk_off_timer;
+	ktime_t clk_off_delay;
+	enum msm_hs_clk_states_e clk_state;
+	enum msm_hs_clk_req_off_state_e clk_req_off_state;
+
+	struct msm_hs_rx_wakeup rx_wakeup;
+	void (*exit_lpm_cb)(struct uart_port *);
+};
+
+#define MSM_UARTDM_BURST_SIZE 16   /* DM burst size (in bytes) */
+#define UARTDM_TX_BUF_SIZE UART_XMIT_SIZE
+#define UARTDM_RX_BUF_SIZE 512
+
+#define UARTDM_NR 2
+
+static struct msm_hs_port q_uart_port[UARTDM_NR];
+static struct platform_driver msm_serial_hs_platform_driver;
+static struct uart_driver msm_hs_driver;
+static struct uart_ops msm_hs_ops;
+static struct workqueue_struct *msm_hs_workqueue;
+
+#define UARTDM_TO_MSM(uart_port) \
+	container_of((uart_port), struct msm_hs_port, uport)
+
+static unsigned int use_low_power_rx_wakeup(struct msm_hs_port
+						   *msm_uport)
+{
+	return (msm_uport->rx_wakeup.irq >= 0);
+}
+
+static unsigned int msm_hs_read(struct uart_port *uport,
+				       unsigned int offset)
+{
+	return ioread32(uport->membase + offset);
+}
+
+static void msm_hs_write(struct uart_port *uport, unsigned int offset,
+				 unsigned int value)
+{
+	iowrite32(value, uport->membase + offset);
+}
+
+static void msm_hs_release_port(struct uart_port *port)
+{
+	iounmap(port->membase);
+}
+
+static int msm_hs_request_port(struct uart_port *port)
+{
+	port->membase = ioremap(port->mapbase, PAGE_SIZE);
+	if (unlikely(!port->membase))
+		return -ENOMEM;
+
+	/* configure the CR Protection to Enable */
+	msm_hs_write(port, UARTDM_CR_ADDR, CR_PROTECTION_EN);
+	return 0;
+}
+
+static int __devexit msm_hs_remove(struct platform_device *pdev)
+{
+
+	struct msm_hs_port *msm_uport;
+	struct device *dev;
+
+	if (pdev->id < 0 || pdev->id >= UARTDM_NR) {
+		printk(KERN_ERR "Invalid plaform device ID = %d\n", pdev->id);
+		return -EINVAL;
+	}
+
+	msm_uport = &q_uart_port[pdev->id];
+	dev = msm_uport->uport.dev;
+
+	dma_unmap_single(dev, msm_uport->rx.mapped_cmd_ptr, sizeof(dmov_box),
+			 DMA_TO_DEVICE);
+	dma_pool_free(msm_uport->rx.pool, msm_uport->rx.buffer,
+		      msm_uport->rx.rbuffer);
+	dma_pool_destroy(msm_uport->rx.pool);
+
+	dma_unmap_single(dev, msm_uport->rx.cmdptr_dmaaddr, sizeof(u32 *),
+			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, msm_uport->tx.mapped_cmd_ptr_ptr, sizeof(u32 *),
+			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, msm_uport->tx.mapped_cmd_ptr, sizeof(dmov_box),
+			 DMA_TO_DEVICE);
+
+	uart_remove_one_port(&msm_hs_driver, &msm_uport->uport);
+	clk_put(msm_uport->clk);
+
+	/* Free the tx resources */
+	kfree(msm_uport->tx.command_ptr);
+	kfree(msm_uport->tx.command_ptr_ptr);
+
+	/* Free the rx resources */
+	kfree(msm_uport->rx.command_ptr);
+	kfree(msm_uport->rx.command_ptr_ptr);
+
+	iounmap(msm_uport->uport.membase);
+
+	return 0;
+}
+
+static int msm_hs_init_clk_locked(struct uart_port *uport)
+{
+	int ret;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	ret = clk_enable(msm_uport->clk);
+	if (ret) {
+		printk(KERN_ERR "Error could not turn on UART clk\n");
+		return ret;
+	}
+
+	/* Set up the MREG/NREG/DREG/MNDREG */
+	ret = clk_set_rate(msm_uport->clk, uport->uartclk);
+	if (ret) {
+		printk(KERN_WARNING "Error setting clock rate on UART\n");
+		clk_disable(msm_uport->clk);
+		return ret;
+	}
+
+	msm_uport->clk_state = MSM_HS_CLK_ON;
+	return 0;
+}
+
+/* Enable and Disable clocks  (Used for power management) */
+static void msm_hs_pm(struct uart_port *uport, unsigned int state,
+		      unsigned int oldstate)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	if (use_low_power_rx_wakeup(msm_uport) ||
+	    msm_uport->exit_lpm_cb)
+		return;  /* ignore linux PM states,
+			    use msm_hs_request_clock API */
+
+	switch (state) {
+	case 0:
+		clk_enable(msm_uport->clk);
+		break;
+	case 3:
+		clk_disable(msm_uport->clk);
+		break;
+	default:
+		dev_err(uport->dev, "msm_serial: Unknown PM state %d\n",
+			state);
+	}
+}
+
+/*
+ * programs the UARTDM_CSR register with correct bit rates
+ *
+ * Interrupts should be disabled before we are called, as
+ * we modify Set Baud rate
+ * Set receive stale interrupt level, dependant on Bit Rate
+ * Goal is to have around 8 ms before indicate stale.
+ * roundup (((Bit Rate * .008) / 10) + 1
+ */
+static void msm_hs_set_bps_locked(struct uart_port *uport,
+				  unsigned int bps)
+{
+	unsigned long rxstale;
+	unsigned long data;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	switch (bps) {
+	case 300:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_75);
+		rxstale = 1;
+		break;
+	case 600:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_150);
+		rxstale = 1;
+		break;
+	case 1200:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_300);
+		rxstale = 1;
+		break;
+	case 2400:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_600);
+		rxstale = 1;
+		break;
+	case 4800:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_1200);
+		rxstale = 1;
+		break;
+	case 9600:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_2400);
+		rxstale = 2;
+		break;
+	case 14400:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_3600);
+		rxstale = 3;
+		break;
+	case 19200:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_4800);
+		rxstale = 4;
+		break;
+	case 28800:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_7200);
+		rxstale = 6;
+		break;
+	case 38400:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_9600);
+		rxstale = 8;
+		break;
+	case 57600:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_14400);
+		rxstale = 16;
+		break;
+	case 76800:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_19200);
+		rxstale = 16;
+		break;
+	case 115200:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_28800);
+		rxstale = 31;
+		break;
+	case 230400:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_57600);
+		rxstale = 31;
+		break;
+	case 460800:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_115200);
+		rxstale = 31;
+		break;
+	case 4000000:
+	case 3686400:
+	case 3200000:
+	case 3500000:
+	case 3000000:
+	case 2500000:
+	case 1500000:
+	case 1152000:
+	case 1000000:
+	case 921600:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_115200);
+		rxstale = 31;
+		break;
+	default:
+		msm_hs_write(uport, UARTDM_CSR_ADDR, UARTDM_CSR_2400);
+		/* default to 9600 */
+		bps = 9600;
+		rxstale = 2;
+		break;
+	}
+	if (bps > 460800)
+		uport->uartclk = bps * 16;
+	else
+		uport->uartclk = UARTCLK;
+
+	if (clk_set_rate(msm_uport->clk, uport->uartclk)) {
+		printk(KERN_WARNING "Error setting clock rate on UART\n");
+		return;
+	}
+
+	data = rxstale & UARTDM_IPR_STALE_LSB_BMSK;
+	data |= UARTDM_IPR_STALE_TIMEOUT_MSB_BMSK & (rxstale << 2);
+
+	msm_hs_write(uport, UARTDM_IPR_ADDR, data);
+}
+
+/*
+ * termios :  new ktermios
+ * oldtermios:  old ktermios previous setting
+ *
+ * Configure the serial port
+ */
+static void msm_hs_set_termios(struct uart_port *uport,
+			       struct ktermios *termios,
+			       struct ktermios *oldtermios)
+{
+	unsigned int bps;
+	unsigned long data;
+	unsigned long flags;
+	unsigned int c_cflag = termios->c_cflag;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	spin_lock_irqsave(&uport->lock, flags);
+	clk_enable(msm_uport->clk);
+
+	/* 300 is the minimum baud support by the driver  */
+	bps = uart_get_baud_rate(uport, termios, oldtermios, 200, 4000000);
+
+	/* Temporary remapping  200 BAUD to 3.2 mbps */
+	if (bps == 200)
+		bps = 3200000;
+
+	msm_hs_set_bps_locked(uport, bps);
+
+	data = msm_hs_read(uport, UARTDM_MR2_ADDR);
+	data &= ~UARTDM_MR2_PARITY_MODE_BMSK;
+	/* set parity */
+	if (PARENB == (c_cflag & PARENB)) {
+		if (PARODD == (c_cflag & PARODD))
+			data |= ODD_PARITY;
+		else if (CMSPAR == (c_cflag & CMSPAR))
+			data |= SPACE_PARITY;
+		else
+			data |= EVEN_PARITY;
+	}
+
+	/* Set bits per char */
+	data &= ~UARTDM_MR2_BITS_PER_CHAR_BMSK;
+
+	switch (c_cflag & CSIZE) {
+	case CS5:
+		data |= FIVE_BPC;
+		break;
+	case CS6:
+		data |= SIX_BPC;
+		break;
+	case CS7:
+		data |= SEVEN_BPC;
+		break;
+	default:
+		data |= EIGHT_BPC;
+		break;
+	}
+	/* stop bits */
+	if (c_cflag & CSTOPB) {
+		data |= STOP_BIT_TWO;
+	} else {
+		/* otherwise 1 stop bit */
+		data |= STOP_BIT_ONE;
+	}
+	data |= UARTDM_MR2_ERROR_MODE_BMSK;
+	/* write parity/bits per char/stop bit configuration */
+	msm_hs_write(uport, UARTDM_MR2_ADDR, data);
+
+	/* Configure HW flow control */
+	data = msm_hs_read(uport, UARTDM_MR1_ADDR);
+
+	data &= ~(UARTDM_MR1_CTS_CTL_BMSK | UARTDM_MR1_RX_RDY_CTL_BMSK);
+
+	if (c_cflag & CRTSCTS) {
+		data |= UARTDM_MR1_CTS_CTL_BMSK;
+		data |= UARTDM_MR1_RX_RDY_CTL_BMSK;
+	}
+
+	msm_hs_write(uport, UARTDM_MR1_ADDR, data);
+
+	uport->ignore_status_mask = termios->c_iflag & INPCK;
+	uport->ignore_status_mask |= termios->c_iflag & IGNPAR;
+	uport->read_status_mask = (termios->c_cflag & CREAD);
+
+	msm_hs_write(uport, UARTDM_IMR_ADDR, 0);
+
+	/* Set Transmit software time out */
+	uart_update_timeout(uport, c_cflag, bps);
+
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_RX);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_TX);
+
+	if (msm_uport->rx.flush == FLUSH_NONE) {
+		msm_uport->rx.flush = FLUSH_IGNORE;
+		msm_dmov_stop_cmd(msm_uport->dma_rx_channel, NULL, 1);
+	}
+
+	msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+
+	clk_disable(msm_uport->clk);
+	spin_unlock_irqrestore(&uport->lock, flags);
+}
+
+/*
+ *  Standard API, Transmitter
+ *  Any character in the transmit shift register is sent
+ */
+static unsigned int msm_hs_tx_empty(struct uart_port *uport)
+{
+	unsigned int data;
+	unsigned int ret = 0;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	clk_enable(msm_uport->clk);
+
+	data = msm_hs_read(uport, UARTDM_SR_ADDR);
+	if (data & UARTDM_SR_TXEMT_BMSK)
+		ret = TIOCSER_TEMT;
+
+	clk_disable(msm_uport->clk);
+
+	return ret;
+}
+
+/*
+ *  Standard API, Stop transmitter.
+ *  Any character in the transmit shift register is sent as
+ *  well as the current data mover transfer .
+ */
+static void msm_hs_stop_tx_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	msm_uport->tx.tx_ready_int_en = 0;
+}
+
+/*
+ *  Standard API, Stop receiver as soon as possible.
+ *
+ *  Function immediately terminates the operation of the
+ *  channel receiver and any incoming characters are lost. None
+ *  of the receiver status bits are affected by this command and
+ *  characters that are already in the receive FIFO there.
+ */
+static void msm_hs_stop_rx_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+	unsigned int data;
+
+	clk_enable(msm_uport->clk);
+
+	/* disable dlink */
+	data = msm_hs_read(uport, UARTDM_DMEN_ADDR);
+	data &= ~UARTDM_RX_DM_EN_BMSK;
+	msm_hs_write(uport, UARTDM_DMEN_ADDR, data);
+
+	/* Disable the receiver */
+	if (msm_uport->rx.flush == FLUSH_NONE)
+		msm_dmov_stop_cmd(msm_uport->dma_rx_channel, NULL, 1);
+
+	if (msm_uport->rx.flush != FLUSH_SHUTDOWN)
+		msm_uport->rx.flush = FLUSH_STOP;
+
+	clk_disable(msm_uport->clk);
+}
+
+/*  Transmit the next chunk of data */
+static void msm_hs_submit_tx_locked(struct uart_port *uport)
+{
+	int left;
+	int tx_count;
+	dma_addr_t src_addr;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+	struct msm_hs_tx *tx = &msm_uport->tx;
+	struct circ_buf *tx_buf = &msm_uport->uport.state->xmit;
+
+	if (uart_circ_empty(tx_buf) || uport->state->port.tty->stopped) {
+		msm_hs_stop_tx_locked(uport);
+		return;
+	}
+
+	tx->dma_in_flight = 1;
+
+	tx_count = uart_circ_chars_pending(tx_buf);
+
+	if (UARTDM_TX_BUF_SIZE < tx_count)
+		tx_count = UARTDM_TX_BUF_SIZE;
+
+	left = UART_XMIT_SIZE - tx_buf->tail;
+
+	if (tx_count > left)
+		tx_count = left;
+
+	src_addr = tx->dma_base + tx_buf->tail;
+	dma_sync_single_for_device(uport->dev, src_addr, tx_count,
+				   DMA_TO_DEVICE);
+
+	tx->command_ptr->num_rows = (((tx_count + 15) >> 4) << 16) |
+				     ((tx_count + 15) >> 4);
+	tx->command_ptr->src_row_addr = src_addr;
+
+	dma_sync_single_for_device(uport->dev, tx->mapped_cmd_ptr,
+				   sizeof(dmov_box), DMA_TO_DEVICE);
+
+	*tx->command_ptr_ptr = CMD_PTR_LP | DMOV_CMD_ADDR(tx->mapped_cmd_ptr);
+
+	dma_sync_single_for_device(uport->dev, tx->mapped_cmd_ptr_ptr,
+				   sizeof(u32 *), DMA_TO_DEVICE);
+
+	/* Save tx_count to use in Callback */
+	tx->tx_count = tx_count;
+	msm_hs_write(uport, UARTDM_NCF_TX_ADDR, tx_count);
+
+	/* Disable the tx_ready interrupt */
+	msm_uport->imr_reg &= ~UARTDM_ISR_TX_READY_BMSK;
+	msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+	msm_dmov_enqueue_cmd(msm_uport->dma_tx_channel, &tx->xfer);
+}
+
+/* Start to receive the next chunk of data */
+static void msm_hs_start_rx_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_STALE_INT);
+	msm_hs_write(uport, UARTDM_DMRX_ADDR, UARTDM_RX_BUF_SIZE);
+	msm_hs_write(uport, UARTDM_CR_ADDR, STALE_EVENT_ENABLE);
+	msm_uport->imr_reg |= UARTDM_ISR_RXLEV_BMSK;
+	msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+
+	msm_uport->rx.flush = FLUSH_NONE;
+	msm_dmov_enqueue_cmd(msm_uport->dma_rx_channel, &msm_uport->rx.xfer);
+
+	/* might have finished RX and be ready to clock off */
+	hrtimer_start(&msm_uport->clk_off_timer, msm_uport->clk_off_delay,
+			HRTIMER_MODE_REL);
+}
+
+/* Enable the transmitter Interrupt */
+static void msm_hs_start_tx_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	clk_enable(msm_uport->clk);
+
+	if (msm_uport->exit_lpm_cb)
+		msm_uport->exit_lpm_cb(uport);
+
+	if (msm_uport->tx.tx_ready_int_en == 0) {
+		msm_uport->tx.tx_ready_int_en = 1;
+		msm_hs_submit_tx_locked(uport);
+	}
+
+	clk_disable(msm_uport->clk);
+}
+
+/*
+ *  This routine is called when we are done with a DMA transfer
+ *
+ *  This routine is registered with Data mover when we set
+ *  up a Data Mover transfer. It is called from Data mover ISR
+ *  when the DMA transfer is done.
+ */
+static void msm_hs_dmov_tx_callback(struct msm_dmov_cmd *cmd_ptr,
+					unsigned int result,
+					struct msm_dmov_errdata *err)
+{
+	unsigned long flags;
+	struct msm_hs_port *msm_uport;
+
+	/* DMA did not finish properly */
+	WARN_ON((((result & RSLT_FIFO_CNTR_BMSK) >> 28) == 1) &&
+		!(result & RSLT_VLD));
+
+	msm_uport = container_of(cmd_ptr, struct msm_hs_port, tx.xfer);
+
+	spin_lock_irqsave(&msm_uport->uport.lock, flags);
+	clk_enable(msm_uport->clk);
+
+	msm_uport->imr_reg |= UARTDM_ISR_TX_READY_BMSK;
+	msm_hs_write(&msm_uport->uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+
+	clk_disable(msm_uport->clk);
+	spin_unlock_irqrestore(&msm_uport->uport.lock, flags);
+}
+
+/*
+ * This routine is called when we are done with a DMA transfer or the
+ * a flush has been sent to the data mover driver.
+ *
+ * This routine is registered with Data mover when we set up a Data Mover
+ *  transfer. It is called from Data mover ISR when the DMA transfer is done.
+ */
+static void msm_hs_dmov_rx_callback(struct msm_dmov_cmd *cmd_ptr,
+					unsigned int result,
+					struct msm_dmov_errdata *err)
+{
+	int retval;
+	int rx_count;
+	unsigned long status;
+	unsigned int error_f = 0;
+	unsigned long flags;
+	unsigned int flush;
+	struct tty_struct *tty;
+	struct uart_port *uport;
+	struct msm_hs_port *msm_uport;
+
+	msm_uport = container_of(cmd_ptr, struct msm_hs_port, rx.xfer);
+	uport = &msm_uport->uport;
+
+	spin_lock_irqsave(&uport->lock, flags);
+	clk_enable(msm_uport->clk);
+
+	tty = uport->state->port.tty;
+
+	msm_hs_write(uport, UARTDM_CR_ADDR, STALE_EVENT_DISABLE);
+
+	status = msm_hs_read(uport, UARTDM_SR_ADDR);
+
+	/* overflow is not connect to data in a FIFO */
+	if (unlikely((status & UARTDM_SR_OVERRUN_BMSK) &&
+		     (uport->read_status_mask & CREAD))) {
+		tty_insert_flip_char(tty, 0, TTY_OVERRUN);
+		uport->icount.buf_overrun++;
+		error_f = 1;
+	}
+
+	if (!(uport->ignore_status_mask & INPCK))
+		status = status & ~(UARTDM_SR_PAR_FRAME_BMSK);
+
+	if (unlikely(status & UARTDM_SR_PAR_FRAME_BMSK)) {
+		/* Can not tell difference between parity & frame error */
+		uport->icount.parity++;
+		error_f = 1;
+		if (uport->ignore_status_mask & IGNPAR)
+			tty_insert_flip_char(tty, 0, TTY_PARITY);
+	}
+
+	if (error_f)
+		msm_hs_write(uport, UARTDM_CR_ADDR, RESET_ERROR_STATUS);
+
+	if (msm_uport->clk_req_off_state == CLK_REQ_OFF_FLUSH_ISSUED)
+		msm_uport->clk_req_off_state = CLK_REQ_OFF_RXSTALE_FLUSHED;
+
+	flush = msm_uport->rx.flush;
+	if (flush == FLUSH_IGNORE)
+		msm_hs_start_rx_locked(uport);
+	if (flush == FLUSH_STOP)
+		msm_uport->rx.flush = FLUSH_SHUTDOWN;
+	if (flush >= FLUSH_DATA_INVALID)
+		goto out;
+
+	rx_count = msm_hs_read(uport, UARTDM_RX_TOTAL_SNAP_ADDR);
+
+	if (0 != (uport->read_status_mask & CREAD)) {
+		retval = tty_insert_flip_string(tty, msm_uport->rx.buffer,
+						rx_count);
+		BUG_ON(retval != rx_count);
+	}
+
+	msm_hs_start_rx_locked(uport);
+
+out:
+	clk_disable(msm_uport->clk);
+
+	spin_unlock_irqrestore(&uport->lock, flags);
+
+	if (flush < FLUSH_DATA_INVALID)
+		queue_work(msm_hs_workqueue, &msm_uport->rx.tty_work);
+}
+
+static void msm_hs_tty_flip_buffer_work(struct work_struct *work)
+{
+	struct msm_hs_port *msm_uport =
+			container_of(work, struct msm_hs_port, rx.tty_work);
+	struct tty_struct *tty = msm_uport->uport.state->port.tty;
+
+	tty_flip_buffer_push(tty);
+}
+
+/*
+ *  Standard API, Current states of modem control inputs
+ *
+ * Since CTS can be handled entirely by HARDWARE we always
+ * indicate clear to send and count on the TX FIFO to block when
+ * it fills up.
+ *
+ * - TIOCM_DCD
+ * - TIOCM_CTS
+ * - TIOCM_DSR
+ * - TIOCM_RI
+ *  (Unsupported) DCD and DSR will return them high. RI will return low.
+ */
+static unsigned int msm_hs_get_mctrl_locked(struct uart_port *uport)
+{
+	return TIOCM_DSR | TIOCM_CAR | TIOCM_CTS;
+}
+
+/*
+ * True enables UART auto RFR, which indicates we are ready for data if the RX
+ * buffer is not full. False disables auto RFR, and deasserts RFR to indicate
+ * we are not ready for data. Must be called with UART clock on.
+ */
+static void set_rfr_locked(struct uart_port *uport, int auto_rfr)
+{
+	unsigned int data;
+
+	data = msm_hs_read(uport, UARTDM_MR1_ADDR);
+
+	if (auto_rfr) {
+		/* enable auto ready-for-receiving */
+		data |= UARTDM_MR1_RX_RDY_CTL_BMSK;
+		msm_hs_write(uport, UARTDM_MR1_ADDR, data);
+	} else {
+		/* disable auto ready-for-receiving */
+		data &= ~UARTDM_MR1_RX_RDY_CTL_BMSK;
+		msm_hs_write(uport, UARTDM_MR1_ADDR, data);
+		/* RFR is active low, set high */
+		msm_hs_write(uport, UARTDM_CR_ADDR, RFR_HIGH);
+	}
+}
+
+/*
+ *  Standard API, used to set or clear RFR
+ */
+static void msm_hs_set_mctrl_locked(struct uart_port *uport,
+				    unsigned int mctrl)
+{
+	unsigned int auto_rfr;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	clk_enable(msm_uport->clk);
+
+	auto_rfr = TIOCM_RTS & mctrl ? 1 : 0;
+	set_rfr_locked(uport, auto_rfr);
+
+	clk_disable(msm_uport->clk);
+}
+
+/* Standard API, Enable modem status (CTS) interrupt  */
+static void msm_hs_enable_ms_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	clk_enable(msm_uport->clk);
+
+	/* Enable DELTA_CTS Interrupt */
+	msm_uport->imr_reg |= UARTDM_ISR_DELTA_CTS_BMSK;
+	msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+
+	clk_disable(msm_uport->clk);
+
+}
+
+/*
+ *  Standard API, Break Signal
+ *
+ * Control the transmission of a break signal. ctl eq 0 => break
+ * signal terminate ctl ne 0 => start break signal
+ */
+static void msm_hs_break_ctl(struct uart_port *uport, int ctl)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	clk_enable(msm_uport->clk);
+	msm_hs_write(uport, UARTDM_CR_ADDR, ctl ? START_BREAK : STOP_BREAK);
+	clk_disable(msm_uport->clk);
+}
+
+static void msm_hs_config_port(struct uart_port *uport, int cfg_flags)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&uport->lock, flags);
+	if (cfg_flags & UART_CONFIG_TYPE) {
+		uport->type = PORT_MSM;
+		msm_hs_request_port(uport);
+	}
+	spin_unlock_irqrestore(&uport->lock, flags);
+}
+
+/*  Handle CTS changes (Called from interrupt handler) */
+static void msm_hs_handle_delta_cts(struct uart_port *uport)
+{
+	unsigned long flags;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	spin_lock_irqsave(&uport->lock, flags);
+	clk_enable(msm_uport->clk);
+
+	/* clear interrupt */
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_CTS);
+	uport->icount.cts++;
+
+	clk_disable(msm_uport->clk);
+	spin_unlock_irqrestore(&uport->lock, flags);
+
+	/* clear the IOCTL TIOCMIWAIT if called */
+	wake_up_interruptible(&uport->state->port.delta_msr_wait);
+}
+
+/* check if the TX path is flushed, and if so clock off
+ * returns 0 did not clock off, need to retry (still sending final byte)
+ *        -1 did not clock off, do not retry
+ *         1 if we clocked off
+ */
+static int msm_hs_check_clock_off_locked(struct uart_port *uport)
+{
+	unsigned long sr_status;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+	struct circ_buf *tx_buf = &uport->state->xmit;
+
+	/* Cancel if tx tty buffer is not empty, dma is in flight,
+	 * or tx fifo is not empty, or rx fifo is not empty */
+	if (msm_uport->clk_state != MSM_HS_CLK_REQUEST_OFF ||
+	    !uart_circ_empty(tx_buf) || msm_uport->tx.dma_in_flight ||
+	    (msm_uport->imr_reg & UARTDM_ISR_TXLEV_BMSK) ||
+	    !(msm_uport->imr_reg & UARTDM_ISR_RXLEV_BMSK))  {
+		return -1;
+	}
+
+	/* Make sure the uart is finished with the last byte */
+	sr_status = msm_hs_read(uport, UARTDM_SR_ADDR);
+	if (!(sr_status & UARTDM_SR_TXEMT_BMSK))
+		return 0;  /* retry */
+
+	/* Make sure forced RXSTALE flush complete */
+	switch (msm_uport->clk_req_off_state) {
+	case CLK_REQ_OFF_START:
+		msm_uport->clk_req_off_state = CLK_REQ_OFF_RXSTALE_ISSUED;
+		msm_hs_write(uport, UARTDM_CR_ADDR, FORCE_STALE_EVENT);
+		return 0;  /* RXSTALE flush not complete - retry */
+	case CLK_REQ_OFF_RXSTALE_ISSUED:
+	case CLK_REQ_OFF_FLUSH_ISSUED:
+		return 0;  /* RXSTALE flush not complete - retry */
+	case CLK_REQ_OFF_RXSTALE_FLUSHED:
+		break;  /* continue */
+	}
+
+	if (msm_uport->rx.flush != FLUSH_SHUTDOWN) {
+		if (msm_uport->rx.flush == FLUSH_NONE)
+			msm_hs_stop_rx_locked(uport);
+		return 0;  /* come back later to really clock off */
+	}
+
+	/* we really want to clock off */
+	clk_disable(msm_uport->clk);
+	msm_uport->clk_state = MSM_HS_CLK_OFF;
+
+	if (use_low_power_rx_wakeup(msm_uport)) {
+		msm_uport->rx_wakeup.ignore = 1;
+		enable_irq(msm_uport->rx_wakeup.irq);
+	}
+	return 1;
+}
+
+static enum hrtimer_restart msm_hs_clk_off_retry(struct hrtimer *timer)
+{
+	unsigned long flags;
+	int ret = HRTIMER_NORESTART;
+	struct msm_hs_port *msm_uport = container_of(timer, struct msm_hs_port,
+						     clk_off_timer);
+	struct uart_port *uport = &msm_uport->uport;
+
+	spin_lock_irqsave(&uport->lock, flags);
+
+	if (!msm_hs_check_clock_off_locked(uport)) {
+		hrtimer_forward_now(timer, msm_uport->clk_off_delay);
+		ret = HRTIMER_RESTART;
+	}
+
+	spin_unlock_irqrestore(&uport->lock, flags);
+
+	return ret;
+}
+
+static irqreturn_t msm_hs_isr(int irq, void *dev)
+{
+	unsigned long flags;
+	unsigned long isr_status;
+	struct msm_hs_port *msm_uport = dev;
+	struct uart_port *uport = &msm_uport->uport;
+	struct circ_buf *tx_buf = &uport->state->xmit;
+	struct msm_hs_tx *tx = &msm_uport->tx;
+	struct msm_hs_rx *rx = &msm_uport->rx;
+
+	spin_lock_irqsave(&uport->lock, flags);
+
+	isr_status = msm_hs_read(uport, UARTDM_MISR_ADDR);
+
+	/* Uart RX starting */
+	if (isr_status & UARTDM_ISR_RXLEV_BMSK) {
+		msm_uport->imr_reg &= ~UARTDM_ISR_RXLEV_BMSK;
+		msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+	}
+	/* Stale rx interrupt */
+	if (isr_status & UARTDM_ISR_RXSTALE_BMSK) {
+		msm_hs_write(uport, UARTDM_CR_ADDR, STALE_EVENT_DISABLE);
+		msm_hs_write(uport, UARTDM_CR_ADDR, RESET_STALE_INT);
+
+		if (msm_uport->clk_req_off_state == CLK_REQ_OFF_RXSTALE_ISSUED)
+			msm_uport->clk_req_off_state =
+					CLK_REQ_OFF_FLUSH_ISSUED;
+		if (rx->flush == FLUSH_NONE) {
+			rx->flush = FLUSH_DATA_READY;
+			msm_dmov_stop_cmd(msm_uport->dma_rx_channel, NULL, 1);
+		}
+	}
+	/* tx ready interrupt */
+	if (isr_status & UARTDM_ISR_TX_READY_BMSK) {
+		/* Clear  TX Ready */
+		msm_hs_write(uport, UARTDM_CR_ADDR, CLEAR_TX_READY);
+
+		if (msm_uport->clk_state == MSM_HS_CLK_REQUEST_OFF) {
+			msm_uport->imr_reg |= UARTDM_ISR_TXLEV_BMSK;
+			msm_hs_write(uport, UARTDM_IMR_ADDR,
+				     msm_uport->imr_reg);
+		}
+
+		/* Complete DMA TX transactions and submit new transactions */
+		tx_buf->tail = (tx_buf->tail + tx->tx_count) & ~UART_XMIT_SIZE;
+
+		tx->dma_in_flight = 0;
+
+		uport->icount.tx += tx->tx_count;
+		if (tx->tx_ready_int_en)
+			msm_hs_submit_tx_locked(uport);
+
+		if (uart_circ_chars_pending(tx_buf) < WAKEUP_CHARS)
+			uart_write_wakeup(uport);
+	}
+	if (isr_status & UARTDM_ISR_TXLEV_BMSK) {
+		/* TX FIFO is empty */
+		msm_uport->imr_reg &= ~UARTDM_ISR_TXLEV_BMSK;
+		msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+		if (!msm_hs_check_clock_off_locked(uport))
+			hrtimer_start(&msm_uport->clk_off_timer,
+				      msm_uport->clk_off_delay,
+				      HRTIMER_MODE_REL);
+	}
+
+	/* Change in CTS interrupt */
+	if (isr_status & UARTDM_ISR_DELTA_CTS_BMSK)
+		msm_hs_handle_delta_cts(uport);
+
+	spin_unlock_irqrestore(&uport->lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+void msm_hs_request_clock_off_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	if (msm_uport->clk_state == MSM_HS_CLK_ON) {
+		msm_uport->clk_state = MSM_HS_CLK_REQUEST_OFF;
+		msm_uport->clk_req_off_state = CLK_REQ_OFF_START;
+		if (!use_low_power_rx_wakeup(msm_uport))
+			set_rfr_locked(uport, 0);
+		msm_uport->imr_reg |= UARTDM_ISR_TXLEV_BMSK;
+		msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+	}
+}
+
+/**
+ * msm_hs_request_clock_off - request to (i.e. asynchronously) turn off uart
+ * clock once pending TX is flushed and Rx DMA command is terminated.
+ * @uport: uart_port structure for the device instance.
+ *
+ * This functions puts the device into a partially active low power mode. It
+ * waits to complete all pending tx transactions, flushes ongoing Rx DMA
+ * command and terminates UART side Rx transaction, puts UART HW in non DMA
+ * mode and then clocks off the device. A client calls this when no UART
+ * data is expected. msm_request_clock_on() must be called before any further
+ * UART can be sent or received.
+ */
+void msm_hs_request_clock_off(struct uart_port *uport)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&uport->lock, flags);
+	msm_hs_request_clock_off_locked(uport);
+	spin_unlock_irqrestore(&uport->lock, flags);
+}
+
+void msm_hs_request_clock_on_locked(struct uart_port *uport)
+{
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+	unsigned int data;
+
+	switch (msm_uport->clk_state) {
+	case MSM_HS_CLK_OFF:
+		clk_enable(msm_uport->clk);
+		disable_irq_nosync(msm_uport->rx_wakeup.irq);
+		/* fall-through */
+	case MSM_HS_CLK_REQUEST_OFF:
+		if (msm_uport->rx.flush == FLUSH_STOP ||
+		    msm_uport->rx.flush == FLUSH_SHUTDOWN) {
+			msm_hs_write(uport, UARTDM_CR_ADDR, RESET_RX);
+			data = msm_hs_read(uport, UARTDM_DMEN_ADDR);
+			data |= UARTDM_RX_DM_EN_BMSK;
+			msm_hs_write(uport, UARTDM_DMEN_ADDR, data);
+		}
+		hrtimer_try_to_cancel(&msm_uport->clk_off_timer);
+		if (msm_uport->rx.flush == FLUSH_SHUTDOWN)
+			msm_hs_start_rx_locked(uport);
+		if (!use_low_power_rx_wakeup(msm_uport))
+			set_rfr_locked(uport, 1);
+		if (msm_uport->rx.flush == FLUSH_STOP)
+			msm_uport->rx.flush = FLUSH_IGNORE;
+		msm_uport->clk_state = MSM_HS_CLK_ON;
+		break;
+	case MSM_HS_CLK_ON:
+		break;
+	case MSM_HS_CLK_PORT_OFF:
+		break;
+	}
+}
+
+/**
+ * msm_hs_request_clock_on - Switch the device from partially active low
+ * power mode to fully active (i.e. clock on) mode.
+ * @uport: uart_port structure for the device.
+ *
+ * This function switches on the input clock, puts UART HW into DMA mode
+ * and enqueues an Rx DMA command if the device was in partially active
+ * mode. It has no effect if called with the device in inactive state.
+ */
+void msm_hs_request_clock_on(struct uart_port *uport)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&uport->lock, flags);
+	msm_hs_request_clock_on_locked(uport);
+	spin_unlock_irqrestore(&uport->lock, flags);
+}
+
+static irqreturn_t msm_hs_rx_wakeup_isr(int irq, void *dev)
+{
+	unsigned int wakeup = 0;
+	unsigned long flags;
+	struct msm_hs_port *msm_uport = dev;
+	struct uart_port *uport = &msm_uport->uport;
+	struct tty_struct *tty = NULL;
+
+	spin_lock_irqsave(&uport->lock, flags);
+	if (msm_uport->clk_state == MSM_HS_CLK_OFF) {
+		/* ignore the first irq - it is a pending irq that occured
+		 * before enable_irq() */
+		if (msm_uport->rx_wakeup.ignore)
+			msm_uport->rx_wakeup.ignore = 0;
+		else
+			wakeup = 1;
+	}
+
+	if (wakeup) {
+		/* the uart was clocked off during an rx, wake up and
+		 * optionally inject char into tty rx */
+		msm_hs_request_clock_on_locked(uport);
+		if (msm_uport->rx_wakeup.inject_rx) {
+			tty = uport->state->port.tty;
+			tty_insert_flip_char(tty,
+					     msm_uport->rx_wakeup.rx_to_inject,
+					     TTY_NORMAL);
+			queue_work(msm_hs_workqueue, &msm_uport->rx.tty_work);
+		}
+	}
+
+	spin_unlock_irqrestore(&uport->lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static const char *msm_hs_type(struct uart_port *port)
+{
+	return (port->type == PORT_MSM) ? "MSM_HS_UART" : NULL;
+}
+
+/* Called when port is opened */
+static int msm_hs_startup(struct uart_port *uport)
+{
+	int ret;
+	int rfr_level;
+	unsigned long flags;
+	unsigned int data;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+	struct circ_buf *tx_buf = &uport->state->xmit;
+	struct msm_hs_tx *tx = &msm_uport->tx;
+	struct msm_hs_rx *rx = &msm_uport->rx;
+
+	rfr_level = uport->fifosize;
+	if (rfr_level > 16)
+		rfr_level -= 16;
+
+	tx->dma_base = dma_map_single(uport->dev, tx_buf->buf, UART_XMIT_SIZE,
+				      DMA_TO_DEVICE);
+
+	/* do not let tty layer execute RX in global workqueue, use a
+	 * dedicated workqueue managed by this driver */
+	uport->state->port.tty->low_latency = 1;
+
+	/* turn on uart clk */
+	ret = msm_hs_init_clk_locked(uport);
+	if (unlikely(ret)) {
+		printk(KERN_ERR "Turning uartclk failed!\n");
+		goto err_msm_hs_init_clk;
+	}
+
+	/* Set auto RFR Level */
+	data = msm_hs_read(uport, UARTDM_MR1_ADDR);
+	data &= ~UARTDM_MR1_AUTO_RFR_LEVEL1_BMSK;
+	data &= ~UARTDM_MR1_AUTO_RFR_LEVEL0_BMSK;
+	data |= (UARTDM_MR1_AUTO_RFR_LEVEL1_BMSK & (rfr_level << 2));
+	data |= (UARTDM_MR1_AUTO_RFR_LEVEL0_BMSK & rfr_level);
+	msm_hs_write(uport, UARTDM_MR1_ADDR, data);
+
+	/* Make sure RXSTALE count is non-zero */
+	data = msm_hs_read(uport, UARTDM_IPR_ADDR);
+	if (!data) {
+		data |= 0x1f & UARTDM_IPR_STALE_LSB_BMSK;
+		msm_hs_write(uport, UARTDM_IPR_ADDR, data);
+	}
+
+	/* Enable Data Mover Mode */
+	data = UARTDM_TX_DM_EN_BMSK | UARTDM_RX_DM_EN_BMSK;
+	msm_hs_write(uport, UARTDM_DMEN_ADDR, data);
+
+	/* Reset TX */
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_TX);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_RX);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_ERROR_STATUS);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_BREAK_INT);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_STALE_INT);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RESET_CTS);
+	msm_hs_write(uport, UARTDM_CR_ADDR, RFR_LOW);
+	/* Turn on Uart Receiver */
+	msm_hs_write(uport, UARTDM_CR_ADDR, UARTDM_CR_RX_EN_BMSK);
+
+	/* Turn on Uart Transmitter */
+	msm_hs_write(uport, UARTDM_CR_ADDR, UARTDM_CR_TX_EN_BMSK);
+
+	/* Initialize the tx */
+	tx->tx_ready_int_en = 0;
+	tx->dma_in_flight = 0;
+
+	tx->xfer.complete_func = msm_hs_dmov_tx_callback;
+	tx->xfer.execute_func = NULL;
+
+	tx->command_ptr->cmd = CMD_LC |
+	    CMD_DST_CRCI(msm_uport->dma_tx_crci) | CMD_MODE_BOX;
+
+	tx->command_ptr->src_dst_len = (MSM_UARTDM_BURST_SIZE << 16)
+					   | (MSM_UARTDM_BURST_SIZE);
+
+	tx->command_ptr->row_offset = (MSM_UARTDM_BURST_SIZE << 16);
+
+	tx->command_ptr->dst_row_addr =
+	    msm_uport->uport.mapbase + UARTDM_TF_ADDR;
+
+
+	/* Turn on Uart Receive */
+	rx->xfer.complete_func = msm_hs_dmov_rx_callback;
+	rx->xfer.execute_func = NULL;
+
+	rx->command_ptr->cmd = CMD_LC |
+	    CMD_SRC_CRCI(msm_uport->dma_rx_crci) | CMD_MODE_BOX;
+
+	rx->command_ptr->src_dst_len = (MSM_UARTDM_BURST_SIZE << 16)
+					   | (MSM_UARTDM_BURST_SIZE);
+	rx->command_ptr->row_offset =  MSM_UARTDM_BURST_SIZE;
+	rx->command_ptr->src_row_addr = uport->mapbase + UARTDM_RF_ADDR;
+
+
+	msm_uport->imr_reg |= UARTDM_ISR_RXSTALE_BMSK;
+	/* Enable reading the current CTS, no harm even if CTS is ignored */
+	msm_uport->imr_reg |= UARTDM_ISR_CURRENT_CTS_BMSK;
+
+	msm_hs_write(uport, UARTDM_TFWR_ADDR, 0);  /* TXLEV on empty TX fifo */
+
+
+	ret = request_irq(uport->irq, msm_hs_isr, IRQF_TRIGGER_HIGH,
+			  "msm_hs_uart", msm_uport);
+	if (unlikely(ret)) {
+		printk(KERN_ERR "Request msm_hs_uart IRQ failed!\n");
+		goto err_request_irq;
+	}
+	if (use_low_power_rx_wakeup(msm_uport)) {
+		ret = request_irq(msm_uport->rx_wakeup.irq,
+				  msm_hs_rx_wakeup_isr,
+				  IRQF_TRIGGER_FALLING,
+				  "msm_hs_rx_wakeup", msm_uport);
+		if (unlikely(ret)) {
+			printk(KERN_ERR "Request msm_hs_rx_wakeup IRQ failed!\n");
+			free_irq(uport->irq, msm_uport);
+			goto err_request_irq;
+		}
+		disable_irq(msm_uport->rx_wakeup.irq);
+	}
+
+	spin_lock_irqsave(&uport->lock, flags);
+
+	msm_hs_write(uport, UARTDM_RFWR_ADDR, 0);
+	msm_hs_start_rx_locked(uport);
+
+	spin_unlock_irqrestore(&uport->lock, flags);
+	ret = pm_runtime_set_active(uport->dev);
+	if (ret)
+		dev_err(uport->dev, "set active error:%d\n", ret);
+	pm_runtime_enable(uport->dev);
+
+	return 0;
+
+err_request_irq:
+err_msm_hs_init_clk:
+	dma_unmap_single(uport->dev, tx->dma_base,
+				UART_XMIT_SIZE, DMA_TO_DEVICE);
+	return ret;
+}
+
+/* Initialize tx and rx data structures */
+static int __devinit uartdm_init_port(struct uart_port *uport)
+{
+	int ret = 0;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+	struct msm_hs_tx *tx = &msm_uport->tx;
+	struct msm_hs_rx *rx = &msm_uport->rx;
+
+	/* Allocate the command pointer. Needs to be 64 bit aligned */
+	tx->command_ptr = kmalloc(sizeof(dmov_box), GFP_KERNEL | __GFP_DMA);
+	if (!tx->command_ptr)
+		return -ENOMEM;
+
+	tx->command_ptr_ptr = kmalloc(sizeof(u32 *), GFP_KERNEL | __GFP_DMA);
+	if (!tx->command_ptr_ptr) {
+		ret = -ENOMEM;
+		goto err_tx_command_ptr_ptr;
+	}
+
+	tx->mapped_cmd_ptr = dma_map_single(uport->dev, tx->command_ptr,
+					    sizeof(dmov_box), DMA_TO_DEVICE);
+	tx->mapped_cmd_ptr_ptr = dma_map_single(uport->dev,
+						tx->command_ptr_ptr,
+						sizeof(u32 *), DMA_TO_DEVICE);
+	tx->xfer.cmdptr = DMOV_CMD_ADDR(tx->mapped_cmd_ptr_ptr);
+
+	init_waitqueue_head(&rx->wait);
+
+	rx->pool = dma_pool_create("rx_buffer_pool", uport->dev,
+				   UARTDM_RX_BUF_SIZE, 16, 0);
+	if (!rx->pool) {
+		pr_err("%s(): cannot allocate rx_buffer_pool", __func__);
+		ret = -ENOMEM;
+		goto err_dma_pool_create;
+	}
+
+	rx->buffer = dma_pool_alloc(rx->pool, GFP_KERNEL, &rx->rbuffer);
+	if (!rx->buffer) {
+		pr_err("%s(): cannot allocate rx->buffer", __func__);
+		ret = -ENOMEM;
+		goto err_dma_pool_alloc;
+	}
+
+	/* Allocate the command pointer. Needs to be 64 bit aligned */
+	rx->command_ptr = kmalloc(sizeof(dmov_box), GFP_KERNEL | __GFP_DMA);
+	if (!rx->command_ptr) {
+		pr_err("%s(): cannot allocate rx->command_ptr", __func__);
+		ret = -ENOMEM;
+		goto err_rx_command_ptr;
+	}
+
+	rx->command_ptr_ptr = kmalloc(sizeof(u32 *), GFP_KERNEL | __GFP_DMA);
+	if (!rx->command_ptr_ptr) {
+		pr_err("%s(): cannot allocate rx->command_ptr_ptr", __func__);
+		ret = -ENOMEM;
+		goto err_rx_command_ptr_ptr;
+	}
+
+	rx->command_ptr->num_rows = ((UARTDM_RX_BUF_SIZE >> 4) << 16) |
+					 (UARTDM_RX_BUF_SIZE >> 4);
+
+	rx->command_ptr->dst_row_addr = rx->rbuffer;
+
+	rx->mapped_cmd_ptr = dma_map_single(uport->dev, rx->command_ptr,
+					    sizeof(dmov_box), DMA_TO_DEVICE);
+
+	*rx->command_ptr_ptr = CMD_PTR_LP | DMOV_CMD_ADDR(rx->mapped_cmd_ptr);
+
+	rx->cmdptr_dmaaddr = dma_map_single(uport->dev, rx->command_ptr_ptr,
+					    sizeof(u32 *), DMA_TO_DEVICE);
+	rx->xfer.cmdptr = DMOV_CMD_ADDR(rx->cmdptr_dmaaddr);
+
+	INIT_WORK(&rx->tty_work, msm_hs_tty_flip_buffer_work);
+
+	return ret;
+
+err_rx_command_ptr_ptr:
+	kfree(rx->command_ptr);
+err_rx_command_ptr:
+	dma_pool_free(msm_uport->rx.pool, msm_uport->rx.buffer,
+						msm_uport->rx.rbuffer);
+err_dma_pool_alloc:
+	dma_pool_destroy(msm_uport->rx.pool);
+err_dma_pool_create:
+	dma_unmap_single(uport->dev, msm_uport->tx.mapped_cmd_ptr_ptr,
+				sizeof(u32 *), DMA_TO_DEVICE);
+	dma_unmap_single(uport->dev, msm_uport->tx.mapped_cmd_ptr,
+				sizeof(dmov_box), DMA_TO_DEVICE);
+	kfree(msm_uport->tx.command_ptr_ptr);
+err_tx_command_ptr_ptr:
+	kfree(msm_uport->tx.command_ptr);
+	return ret;
+}
+
+static int __devinit msm_hs_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct uart_port *uport;
+	struct msm_hs_port *msm_uport;
+	struct resource *resource;
+	const struct msm_serial_hs_platform_data *pdata =
+						pdev->dev.platform_data;
+
+	if (pdev->id < 0 || pdev->id >= UARTDM_NR) {
+		printk(KERN_ERR "Invalid plaform device ID = %d\n", pdev->id);
+		return -EINVAL;
+	}
+
+	msm_uport = &q_uart_port[pdev->id];
+	uport = &msm_uport->uport;
+
+	uport->dev = &pdev->dev;
+
+	resource = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (unlikely(!resource))
+		return -ENXIO;
+
+	uport->mapbase = resource->start;
+	uport->irq = platform_get_irq(pdev, 0);
+	if (unlikely(uport->irq < 0))
+		return -ENXIO;
+
+	if (unlikely(set_irq_wake(uport->irq, 1)))
+		return -ENXIO;
+
+	if (pdata == NULL || pdata->rx_wakeup_irq < 0)
+		msm_uport->rx_wakeup.irq = -1;
+	else {
+		msm_uport->rx_wakeup.irq = pdata->rx_wakeup_irq;
+		msm_uport->rx_wakeup.ignore = 1;
+		msm_uport->rx_wakeup.inject_rx = pdata->inject_rx_on_wakeup;
+		msm_uport->rx_wakeup.rx_to_inject = pdata->rx_to_inject;
+
+		if (unlikely(msm_uport->rx_wakeup.irq < 0))
+			return -ENXIO;
+
+		if (unlikely(set_irq_wake(msm_uport->rx_wakeup.irq, 1)))
+			return -ENXIO;
+	}
+
+	if (pdata == NULL)
+		msm_uport->exit_lpm_cb = NULL;
+	else
+		msm_uport->exit_lpm_cb = pdata->exit_lpm_cb;
+
+	resource = platform_get_resource_byname(pdev, IORESOURCE_DMA,
+						"uartdm_channels");
+	if (unlikely(!resource))
+		return -ENXIO;
+
+	msm_uport->dma_tx_channel = resource->start;
+	msm_uport->dma_rx_channel = resource->end;
+
+	resource = platform_get_resource_byname(pdev, IORESOURCE_DMA,
+						"uartdm_crci");
+	if (unlikely(!resource))
+		return -ENXIO;
+
+	msm_uport->dma_tx_crci = resource->start;
+	msm_uport->dma_rx_crci = resource->end;
+
+	uport->iotype = UPIO_MEM;
+	uport->fifosize = UART_FIFOSIZE;
+	uport->ops = &msm_hs_ops;
+	uport->flags = UPF_BOOT_AUTOCONF;
+	uport->uartclk = UARTCLK;
+	msm_uport->imr_reg = 0x0;
+	msm_uport->clk = clk_get(&pdev->dev, "uartdm_clk");
+	if (IS_ERR(msm_uport->clk))
+		return PTR_ERR(msm_uport->clk);
+
+	ret = uartdm_init_port(uport);
+	if (unlikely(ret))
+		return ret;
+
+	msm_uport->clk_state = MSM_HS_CLK_PORT_OFF;
+	hrtimer_init(&msm_uport->clk_off_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	msm_uport->clk_off_timer.function = msm_hs_clk_off_retry;
+	msm_uport->clk_off_delay = ktime_set(0, 1000000);  /* 1ms */
+
+	uport->line = pdev->id;
+	return uart_add_one_port(&msm_hs_driver, uport);
+}
+
+static int __init msm_serial_hs_init(void)
+{
+	int ret, i;
+
+	/* Init all UARTS as non-configured */
+	for (i = 0; i < UARTDM_NR; i++)
+		q_uart_port[i].uport.type = PORT_UNKNOWN;
+
+	msm_hs_workqueue = create_singlethread_workqueue("msm_serial_hs");
+	if (unlikely(!msm_hs_workqueue))
+		return -ENOMEM;
+
+	ret = uart_register_driver(&msm_hs_driver);
+	if (unlikely(ret)) {
+		printk(KERN_ERR "%s failed to load\n", __func__);
+		goto err_uart_register_driver;
+	}
+
+	ret = platform_driver_register(&msm_serial_hs_platform_driver);
+	if (ret) {
+		printk(KERN_ERR "%s failed to load\n", __func__);
+		goto err_platform_driver_register;
+	}
+
+	return ret;
+
+err_platform_driver_register:
+	uart_unregister_driver(&msm_hs_driver);
+err_uart_register_driver:
+	destroy_workqueue(msm_hs_workqueue);
+	return ret;
+}
+module_init(msm_serial_hs_init);
+
+/*
+ *  Called by the upper layer when port is closed.
+ *     - Disables the port
+ *     - Unhook the ISR
+ */
+static void msm_hs_shutdown(struct uart_port *uport)
+{
+	unsigned long flags;
+	struct msm_hs_port *msm_uport = UARTDM_TO_MSM(uport);
+
+	BUG_ON(msm_uport->rx.flush < FLUSH_STOP);
+
+	spin_lock_irqsave(&uport->lock, flags);
+	clk_enable(msm_uport->clk);
+
+	/* Disable the transmitter */
+	msm_hs_write(uport, UARTDM_CR_ADDR, UARTDM_CR_TX_DISABLE_BMSK);
+	/* Disable the receiver */
+	msm_hs_write(uport, UARTDM_CR_ADDR, UARTDM_CR_RX_DISABLE_BMSK);
+
+	pm_runtime_disable(uport->dev);
+	pm_runtime_set_suspended(uport->dev);
+
+	/* Free the interrupt */
+	free_irq(uport->irq, msm_uport);
+	if (use_low_power_rx_wakeup(msm_uport))
+		free_irq(msm_uport->rx_wakeup.irq, msm_uport);
+
+	msm_uport->imr_reg = 0;
+	msm_hs_write(uport, UARTDM_IMR_ADDR, msm_uport->imr_reg);
+
+	wait_event(msm_uport->rx.wait, msm_uport->rx.flush == FLUSH_SHUTDOWN);
+
+	clk_disable(msm_uport->clk);  /* to balance local clk_enable() */
+	if (msm_uport->clk_state != MSM_HS_CLK_OFF)
+		clk_disable(msm_uport->clk);  /* to balance clk_state */
+	msm_uport->clk_state = MSM_HS_CLK_PORT_OFF;
+
+	dma_unmap_single(uport->dev, msm_uport->tx.dma_base,
+			 UART_XMIT_SIZE, DMA_TO_DEVICE);
+
+	spin_unlock_irqrestore(&uport->lock, flags);
+
+	if (cancel_work_sync(&msm_uport->rx.tty_work))
+		msm_hs_tty_flip_buffer_work(&msm_uport->rx.tty_work);
+}
+
+static void __exit msm_serial_hs_exit(void)
+{
+	flush_workqueue(msm_hs_workqueue);
+	destroy_workqueue(msm_hs_workqueue);
+	platform_driver_unregister(&msm_serial_hs_platform_driver);
+	uart_unregister_driver(&msm_hs_driver);
+}
+module_exit(msm_serial_hs_exit);
+
+#ifdef CONFIG_PM_RUNTIME
+static int msm_hs_runtime_idle(struct device *dev)
+{
+	/*
+	 * returning success from idle results in runtime suspend to be
+	 * called
+	 */
+	return 0;
+}
+
+static int msm_hs_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = container_of(dev, struct
+						    platform_device, dev);
+	struct msm_hs_port *msm_uport = &q_uart_port[pdev->id];
+
+	msm_hs_request_clock_on(&msm_uport->uport);
+	return 0;
+}
+
+static int msm_hs_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = container_of(dev, struct
+						    platform_device, dev);
+	struct msm_hs_port *msm_uport = &q_uart_port[pdev->id];
+
+	msm_hs_request_clock_off(&msm_uport->uport);
+	return 0;
+}
+#else
+#define msm_hs_runtime_idle NULL
+#define msm_hs_runtime_resume NULL
+#define msm_hs_runtime_suspend NULL
+#endif
+
+static const struct dev_pm_ops msm_hs_dev_pm_ops = {
+	.runtime_suspend = msm_hs_runtime_suspend,
+	.runtime_resume  = msm_hs_runtime_resume,
+	.runtime_idle    = msm_hs_runtime_idle,
+};
+
+static struct platform_driver msm_serial_hs_platform_driver = {
+	.probe = msm_hs_probe,
+	.remove = __devexit_p(msm_hs_remove),
+	.driver = {
+		.name = "msm_serial_hs",
+		.owner = THIS_MODULE,
+		.pm   = &msm_hs_dev_pm_ops,
+	},
+};
+
+static struct uart_driver msm_hs_driver = {
+	.owner = THIS_MODULE,
+	.driver_name = "msm_serial_hs",
+	.dev_name = "ttyHS",
+	.nr = UARTDM_NR,
+	.cons = 0,
+};
+
+static struct uart_ops msm_hs_ops = {
+	.tx_empty = msm_hs_tx_empty,
+	.set_mctrl = msm_hs_set_mctrl_locked,
+	.get_mctrl = msm_hs_get_mctrl_locked,
+	.stop_tx = msm_hs_stop_tx_locked,
+	.start_tx = msm_hs_start_tx_locked,
+	.stop_rx = msm_hs_stop_rx_locked,
+	.enable_ms = msm_hs_enable_ms_locked,
+	.break_ctl = msm_hs_break_ctl,
+	.startup = msm_hs_startup,
+	.shutdown = msm_hs_shutdown,
+	.set_termios = msm_hs_set_termios,
+	.pm = msm_hs_pm,
+	.type = msm_hs_type,
+	.config_port = msm_hs_config_port,
+	.release_port = msm_hs_release_port,
+	.request_port = msm_hs_request_port,
+};
+
+MODULE_DESCRIPTION("High Speed UART Driver for the MSM chipset");
+MODULE_VERSION("1.2");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/platform_data/msm_serial_hs.h b/include/linux/platform_data/msm_serial_hs.h
new file mode 100644
index 000000000000..98a2046f8b31
--- /dev/null
+++ b/include/linux/platform_data/msm_serial_hs.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (C) 2008 Google, Inc.
+ * Author: Nick Pelly <npelly@google.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_ARCH_MSM_SERIAL_HS_H
+#define __ASM_ARCH_MSM_SERIAL_HS_H
+
+#include <linux/serial_core.h>
+
+/* API to request the uart clock off or on for low power management
+ * Clients should call request_clock_off() when no uart data is expected,
+ * and must call request_clock_on() before any further uart data can be
+ * received. */
+extern void msm_hs_request_clock_off(struct uart_port *uport);
+extern void msm_hs_request_clock_on(struct uart_port *uport);
+
+/**
+ * struct msm_serial_hs_platform_data
+ * @rx_wakeup_irq: Rx activity irq
+ * @rx_to_inject: extra character to be inserted to Rx tty on wakeup
+ * @inject_rx: 1 = insert rx_to_inject. 0 = do not insert extra character
+ * @exit_lpm_cb: function called before every Tx transaction
+ *
+ * This is an optional structure required for UART Rx GPIO IRQ based
+ * wakeup from low power state. UART wakeup can be triggered by RX activity
+ * (using a wakeup GPIO on the UART RX pin). This should only be used if
+ * there is not a wakeup GPIO on the UART CTS, and the first RX byte is
+ * known (eg., with the Bluetooth Texas Instruments HCILL protocol),
+ * since the first RX byte will always be lost. RTS will be asserted even
+ * while the UART is clocked off in this mode of operation.
+ */
+struct msm_serial_hs_platform_data {
+	int rx_wakeup_irq;
+	unsigned char inject_rx_on_wakeup;
+	char rx_to_inject;
+	void (*exit_lpm_cb)(struct uart_port *);
+};
+
+#endif
-- 
cgit v1.2.3


From 9b37596a2e860404503a3f2a6513db60c296bfdc Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Mon, 7 Mar 2011 11:11:52 -0500
Subject: USB: move usbcore away from hcd->state

The hcd->state variable is a disaster.  It's not clearly owned by
either usbcore or the host controller drivers, and they both change it
from time to time, potentially stepping on each other's toes.  It's
not protected by any locks.  And there's no mechanism to prevent it
from going through an invalid transition.

This patch (as1451) takes a first step toward fixing these problems.
As it turns out, usbcore uses hcd->state for essentially only two
things: checking whether the controller's root hub is running and
checking whether the controller has died.  Therefore the patch adds
two new atomic bitflags to the hcd structure, to store these pieces of
information.  The new flags are used only by usbcore, and a private
spinlock prevents invalid combinations (a dead controller's root hub
cannot be running).

The patch does not change the places where usbcore sets hcd->state,
since HCDs may depend on them.  Furthermore, there is one place in
usb_hcd_irq() where usbcore still must use hcd->state: An HCD's
interrupt handler can implicitly indicate that the controller died by
setting hcd->state to HC_STATE_HALT.  Nevertheless, the new code is a
big improvement over the current code.

The patch makes one other change.  The hcd_bus_suspend() and
hcd_bus_resume() routines now check first whether the host controller
has died; if it has then they return immediately without calling the
HCD's bus_suspend or bus_resume methods.

This fixes the major problem reported in Bugzilla #29902: The system
fails to suspend after a host controller dies during system resume.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Alex Terekhov <a.terekhov@gmail.com>
CC: <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/core/hcd-pci.c | 13 +++++------
 drivers/usb/core/hcd.c     | 55 ++++++++++++++++++++++++++++++++++------------
 include/linux/usb/hcd.h    |  4 ++++
 3 files changed, 51 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index f71e8e307e0f..d37088591d9a 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -363,8 +363,7 @@ static int check_root_hub_suspended(struct device *dev)
 	struct pci_dev		*pci_dev = to_pci_dev(dev);
 	struct usb_hcd		*hcd = pci_get_drvdata(pci_dev);
 
-	if (!(hcd->state == HC_STATE_SUSPENDED ||
-			hcd->state == HC_STATE_HALT)) {
+	if (HCD_RH_RUNNING(hcd)) {
 		dev_warn(dev, "Root hub is not suspended\n");
 		return -EBUSY;
 	}
@@ -386,7 +385,7 @@ static int suspend_common(struct device *dev, bool do_wakeup)
 	if (retval)
 		return retval;
 
-	if (hcd->driver->pci_suspend) {
+	if (hcd->driver->pci_suspend && !HCD_DEAD(hcd)) {
 		/* Optimization: Don't suspend if a root-hub wakeup is
 		 * pending and it would cause the HCD to wake up anyway.
 		 */
@@ -427,7 +426,7 @@ static int resume_common(struct device *dev, int event)
 	struct usb_hcd		*hcd = pci_get_drvdata(pci_dev);
 	int			retval;
 
-	if (hcd->state != HC_STATE_SUSPENDED) {
+	if (HCD_RH_RUNNING(hcd)) {
 		dev_dbg(dev, "can't resume, not suspended!\n");
 		return 0;
 	}
@@ -442,7 +441,7 @@ static int resume_common(struct device *dev, int event)
 
 	clear_bit(HCD_FLAG_SAW_IRQ, &hcd->flags);
 
-	if (hcd->driver->pci_resume) {
+	if (hcd->driver->pci_resume && !HCD_DEAD(hcd)) {
 		if (event != PM_EVENT_AUTO_RESUME)
 			wait_for_companions(pci_dev, hcd);
 
@@ -475,10 +474,10 @@ static int hcd_pci_suspend_noirq(struct device *dev)
 
 	pci_save_state(pci_dev);
 
-	/* If the root hub is HALTed rather than SUSPENDed,
+	/* If the root hub is dead rather than suspended,
 	 * disallow remote wakeup.
 	 */
-	if (hcd->state == HC_STATE_HALT)
+	if (HCD_DEAD(hcd))
 		device_set_wakeup_enable(dev, 0);
 	dev_dbg(dev, "wakeup: %d\n", device_may_wakeup(dev));
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 24765fd6cf12..e7d0c4571bbe 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -983,7 +983,7 @@ static int register_root_hub(struct usb_hcd *hcd)
 		spin_unlock_irq (&hcd_root_hub_lock);
 
 		/* Did the HC die before the root hub was registered? */
-		if (hcd->state == HC_STATE_HALT)
+		if (HCD_DEAD(hcd) || hcd->state == HC_STATE_HALT)
 			usb_hc_died (hcd);	/* This time clean up */
 	}
 
@@ -1089,13 +1089,10 @@ int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb)
 	 * Check the host controller's state and add the URB to the
 	 * endpoint's queue.
 	 */
-	switch (hcd->state) {
-	case HC_STATE_RUNNING:
-	case HC_STATE_RESUMING:
+	if (HCD_RH_RUNNING(hcd)) {
 		urb->unlinked = 0;
 		list_add_tail(&urb->urb_list, &urb->ep->urb_list);
-		break;
-	default:
+	} else {
 		rc = -ESHUTDOWN;
 		goto done;
 	}
@@ -1931,7 +1928,7 @@ int usb_hcd_get_frame_number (struct usb_device *udev)
 {
 	struct usb_hcd	*hcd = bus_to_hcd(udev->bus);
 
-	if (!HC_IS_RUNNING (hcd->state))
+	if (!HCD_RH_RUNNING(hcd))
 		return -ESHUTDOWN;
 	return hcd->driver->get_frame_number (hcd);
 }
@@ -1948,9 +1945,15 @@ int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg)
 
 	dev_dbg(&rhdev->dev, "bus %s%s\n",
 			(msg.event & PM_EVENT_AUTO ? "auto-" : ""), "suspend");
+	if (HCD_DEAD(hcd)) {
+		dev_dbg(&rhdev->dev, "skipped %s of dead bus\n", "suspend");
+		return 0;
+	}
+
 	if (!hcd->driver->bus_suspend) {
 		status = -ENOENT;
 	} else {
+		clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
 		hcd->state = HC_STATE_QUIESCING;
 		status = hcd->driver->bus_suspend(hcd);
 	}
@@ -1958,7 +1961,12 @@ int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg)
 		usb_set_device_state(rhdev, USB_STATE_SUSPENDED);
 		hcd->state = HC_STATE_SUSPENDED;
 	} else {
-		hcd->state = old_state;
+		spin_lock_irq(&hcd_root_hub_lock);
+		if (!HCD_DEAD(hcd)) {
+			set_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
+			hcd->state = old_state;
+		}
+		spin_unlock_irq(&hcd_root_hub_lock);
 		dev_dbg(&rhdev->dev, "bus %s fail, err %d\n",
 				"suspend", status);
 	}
@@ -1973,9 +1981,13 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 
 	dev_dbg(&rhdev->dev, "usb %s%s\n",
 			(msg.event & PM_EVENT_AUTO ? "auto-" : ""), "resume");
+	if (HCD_DEAD(hcd)) {
+		dev_dbg(&rhdev->dev, "skipped %s of dead bus\n", "resume");
+		return 0;
+	}
 	if (!hcd->driver->bus_resume)
 		return -ENOENT;
-	if (hcd->state == HC_STATE_RUNNING)
+	if (HCD_RH_RUNNING(hcd))
 		return 0;
 
 	hcd->state = HC_STATE_RESUMING;
@@ -1984,10 +1996,15 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 	if (status == 0) {
 		/* TRSMRCY = 10 msec */
 		msleep(10);
-		usb_set_device_state(rhdev, rhdev->actconfig
-				? USB_STATE_CONFIGURED
-				: USB_STATE_ADDRESS);
-		hcd->state = HC_STATE_RUNNING;
+		spin_lock_irq(&hcd_root_hub_lock);
+		if (!HCD_DEAD(hcd)) {
+			usb_set_device_state(rhdev, rhdev->actconfig
+					? USB_STATE_CONFIGURED
+					: USB_STATE_ADDRESS);
+			set_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
+			hcd->state = HC_STATE_RUNNING;
+		}
+		spin_unlock_irq(&hcd_root_hub_lock);
 	} else {
 		hcd->state = old_state;
 		dev_dbg(&rhdev->dev, "bus %s fail, err %d\n",
@@ -2098,7 +2115,7 @@ irqreturn_t usb_hcd_irq (int irq, void *__hcd)
 	 */
 	local_irq_save(flags);
 
-	if (unlikely(hcd->state == HC_STATE_HALT || !HCD_HW_ACCESSIBLE(hcd))) {
+	if (unlikely(HCD_DEAD(hcd) || !HCD_HW_ACCESSIBLE(hcd))) {
 		rc = IRQ_NONE;
 	} else if (hcd->driver->irq(hcd) == IRQ_NONE) {
 		rc = IRQ_NONE;
@@ -2132,6 +2149,8 @@ void usb_hc_died (struct usb_hcd *hcd)
 	dev_err (hcd->self.controller, "HC died; cleaning up\n");
 
 	spin_lock_irqsave (&hcd_root_hub_lock, flags);
+	clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
+	set_bit(HCD_FLAG_DEAD, &hcd->flags);
 	if (hcd->rh_registered) {
 		clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 
@@ -2274,6 +2293,12 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	 */
 	device_init_wakeup(&rhdev->dev, 1);
 
+	/* HCD_FLAG_RH_RUNNING doesn't matter until the root hub is
+	 * registered.  But since the controller can die at any time,
+	 * let's initialize the flag before touching the hardware.
+	 */
+	set_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
+
 	/* "reset" is misnamed; its role is now one-time init. the controller
 	 * should already have been reset (and boot firmware kicked off etc).
 	 */
@@ -2341,6 +2366,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	return retval;
 
 error_create_attr_group:
+	clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
 	if (HC_IS_RUNNING(hcd->state))
 		hcd->state = HC_STATE_QUIESCING;
 	spin_lock_irq(&hcd_root_hub_lock);
@@ -2393,6 +2419,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	usb_get_dev(rhdev);
 	sysfs_remove_group(&rhdev->dev.kobj, &usb_bus_attr_group);
 
+	clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
 	if (HC_IS_RUNNING (hcd->state))
 		hcd->state = HC_STATE_QUIESCING;
 
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 9cfba4f2457b..8b65068c6af9 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -99,6 +99,8 @@ struct usb_hcd {
 #define HCD_FLAG_POLL_RH		2	/* poll for rh status? */
 #define HCD_FLAG_POLL_PENDING		3	/* status has changed? */
 #define HCD_FLAG_WAKEUP_PENDING		4	/* root hub is resuming? */
+#define HCD_FLAG_RH_RUNNING		5	/* root hub is running? */
+#define HCD_FLAG_DEAD			6	/* controller has died? */
 
 	/* The flags can be tested using these macros; they are likely to
 	 * be slightly faster than test_bit().
@@ -108,6 +110,8 @@ struct usb_hcd {
 #define HCD_POLL_RH(hcd)	((hcd)->flags & (1U << HCD_FLAG_POLL_RH))
 #define HCD_POLL_PENDING(hcd)	((hcd)->flags & (1U << HCD_FLAG_POLL_PENDING))
 #define HCD_WAKEUP_PENDING(hcd)	((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING))
+#define HCD_RH_RUNNING(hcd)	((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING))
+#define HCD_DEAD(hcd)		((hcd)->flags & (1U << HCD_FLAG_DEAD))
 
 	/* Flags that get set only during HCD registration or removal. */
 	unsigned		rh_registered:1;/* is root hub registered? */
-- 
cgit v1.2.3


From dfb2130c453c2c6d36b5e0f39eca289cbdbb631d Mon Sep 17 00:00:00 2001
From: Pavankumar Kondeti <pkondeti@codeaurora.org>
Date: Fri, 4 Mar 2011 22:45:02 +0530
Subject: USB: Rename "msm72k_otg.c" to "msm_otg.c"

This driver is used across all MSM SoCs.  Hence give a generic name.
All Functions and strutures are also using "msm_otg" as prefix.

Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/gadget/Kconfig    |    2 +-
 drivers/usb/host/Kconfig      |    2 +-
 drivers/usb/otg/Kconfig       |    2 +-
 drivers/usb/otg/Makefile      |    2 +-
 drivers/usb/otg/msm72k_otg.c  | 1124 -----------------------------------------
 drivers/usb/otg/msm_otg.c     | 1124 +++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/msm_hsusb.h |    2 +-
 7 files changed, 1129 insertions(+), 1129 deletions(-)
 delete mode 100644 drivers/usb/otg/msm72k_otg.c
 create mode 100644 drivers/usb/otg/msm_otg.c

(limited to 'include')

diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 99ed91c7cdc6..bfde50e20b30 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -552,7 +552,7 @@ config USB_GADGET_CI13XXX_MSM
 	boolean "MIPS USB CI13xxx for MSM"
 	depends on ARCH_MSM
 	select USB_GADGET_DUALSPEED
-	select USB_MSM_OTG_72K
+	select USB_MSM_OTG
 	help
 	  MSM SoC has chipidea USB controller.  This driver uses
 	  ci13xxx_udc core.
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 9116d30bcdac..b5a908eacb82 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -156,7 +156,7 @@ config USB_EHCI_MSM
 	bool "Support for MSM on-chip EHCI USB controller"
 	depends on USB_EHCI_HCD && ARCH_MSM
 	select USB_EHCI_ROOT_HUB_TT
-	select USB_MSM_OTG_72K
+	select USB_MSM_OTG
 	---help---
 	  Enables support for the USB Host controller present on the
 	  Qualcomm chipsets. Root Hub has inbuilt TT.
diff --git a/drivers/usb/otg/Kconfig b/drivers/usb/otg/Kconfig
index 9ffc8237fb4b..ceb24fee2eac 100644
--- a/drivers/usb/otg/Kconfig
+++ b/drivers/usb/otg/Kconfig
@@ -93,7 +93,7 @@ config USB_LANGWELL_OTG
 	  To compile this driver as a module, choose M here: the
 	  module will be called langwell_otg.
 
-config USB_MSM_OTG_72K
+config USB_MSM_OTG
 	tristate "OTG support for Qualcomm on-chip USB controller"
 	depends on (USB || USB_GADGET) && ARCH_MSM
 	select USB_OTG_UTILS
diff --git a/drivers/usb/otg/Makefile b/drivers/usb/otg/Makefile
index a520e715cfd6..e516894260bf 100644
--- a/drivers/usb/otg/Makefile
+++ b/drivers/usb/otg/Makefile
@@ -16,5 +16,5 @@ obj-$(CONFIG_TWL6030_USB)	+= twl6030-usb.o
 obj-$(CONFIG_USB_LANGWELL_OTG)	+= langwell_otg.o
 obj-$(CONFIG_NOP_USB_XCEIV)	+= nop-usb-xceiv.o
 obj-$(CONFIG_USB_ULPI)		+= ulpi.o
-obj-$(CONFIG_USB_MSM_OTG_72K)	+= msm72k_otg.o
+obj-$(CONFIG_USB_MSM_OTG)	+= msm_otg.o
 obj-$(CONFIG_AB8500_USB)	+= ab8500-usb.o
diff --git a/drivers/usb/otg/msm72k_otg.c b/drivers/usb/otg/msm72k_otg.c
deleted file mode 100644
index 296598628b85..000000000000
--- a/drivers/usb/otg/msm72k_otg.c
+++ /dev/null
@@ -1,1124 +0,0 @@
-/* Copyright (c) 2009-2010, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- *
- */
-
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/err.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/ioport.h>
-#include <linux/uaccess.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include <linux/pm_runtime.h>
-
-#include <linux/usb.h>
-#include <linux/usb/otg.h>
-#include <linux/usb/ulpi.h>
-#include <linux/usb/gadget.h>
-#include <linux/usb/hcd.h>
-#include <linux/usb/msm_hsusb.h>
-#include <linux/usb/msm_hsusb_hw.h>
-
-#include <mach/clk.h>
-
-#define MSM_USB_BASE	(motg->regs)
-#define DRIVER_NAME	"msm_otg"
-
-#define ULPI_IO_TIMEOUT_USEC	(10 * 1000)
-static int ulpi_read(struct otg_transceiver *otg, u32 reg)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-	int cnt = 0;
-
-	/* initiate read operation */
-	writel(ULPI_RUN | ULPI_READ | ULPI_ADDR(reg),
-	       USB_ULPI_VIEWPORT);
-
-	/* wait for completion */
-	while (cnt < ULPI_IO_TIMEOUT_USEC) {
-		if (!(readl(USB_ULPI_VIEWPORT) & ULPI_RUN))
-			break;
-		udelay(1);
-		cnt++;
-	}
-
-	if (cnt >= ULPI_IO_TIMEOUT_USEC) {
-		dev_err(otg->dev, "ulpi_read: timeout %08x\n",
-			readl(USB_ULPI_VIEWPORT));
-		return -ETIMEDOUT;
-	}
-	return ULPI_DATA_READ(readl(USB_ULPI_VIEWPORT));
-}
-
-static int ulpi_write(struct otg_transceiver *otg, u32 val, u32 reg)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-	int cnt = 0;
-
-	/* initiate write operation */
-	writel(ULPI_RUN | ULPI_WRITE |
-	       ULPI_ADDR(reg) | ULPI_DATA(val),
-	       USB_ULPI_VIEWPORT);
-
-	/* wait for completion */
-	while (cnt < ULPI_IO_TIMEOUT_USEC) {
-		if (!(readl(USB_ULPI_VIEWPORT) & ULPI_RUN))
-			break;
-		udelay(1);
-		cnt++;
-	}
-
-	if (cnt >= ULPI_IO_TIMEOUT_USEC) {
-		dev_err(otg->dev, "ulpi_write: timeout\n");
-		return -ETIMEDOUT;
-	}
-	return 0;
-}
-
-static struct otg_io_access_ops msm_otg_io_ops = {
-	.read = ulpi_read,
-	.write = ulpi_write,
-};
-
-static void ulpi_init(struct msm_otg *motg)
-{
-	struct msm_otg_platform_data *pdata = motg->pdata;
-	int *seq = pdata->phy_init_seq;
-
-	if (!seq)
-		return;
-
-	while (seq[0] >= 0) {
-		dev_vdbg(motg->otg.dev, "ulpi: write 0x%02x to 0x%02x\n",
-				seq[0], seq[1]);
-		ulpi_write(&motg->otg, seq[0], seq[1]);
-		seq += 2;
-	}
-}
-
-static int msm_otg_link_clk_reset(struct msm_otg *motg, bool assert)
-{
-	int ret;
-
-	if (assert) {
-		ret = clk_reset(motg->clk, CLK_RESET_ASSERT);
-		if (ret)
-			dev_err(motg->otg.dev, "usb hs_clk assert failed\n");
-	} else {
-		ret = clk_reset(motg->clk, CLK_RESET_DEASSERT);
-		if (ret)
-			dev_err(motg->otg.dev, "usb hs_clk deassert failed\n");
-	}
-	return ret;
-}
-
-static int msm_otg_phy_clk_reset(struct msm_otg *motg)
-{
-	int ret;
-
-	ret = clk_reset(motg->phy_reset_clk, CLK_RESET_ASSERT);
-	if (ret) {
-		dev_err(motg->otg.dev, "usb phy clk assert failed\n");
-		return ret;
-	}
-	usleep_range(10000, 12000);
-	ret = clk_reset(motg->phy_reset_clk, CLK_RESET_DEASSERT);
-	if (ret)
-		dev_err(motg->otg.dev, "usb phy clk deassert failed\n");
-	return ret;
-}
-
-static int msm_otg_phy_reset(struct msm_otg *motg)
-{
-	u32 val;
-	int ret;
-	int retries;
-
-	ret = msm_otg_link_clk_reset(motg, 1);
-	if (ret)
-		return ret;
-	ret = msm_otg_phy_clk_reset(motg);
-	if (ret)
-		return ret;
-	ret = msm_otg_link_clk_reset(motg, 0);
-	if (ret)
-		return ret;
-
-	val = readl(USB_PORTSC) & ~PORTSC_PTS_MASK;
-	writel(val | PORTSC_PTS_ULPI, USB_PORTSC);
-
-	for (retries = 3; retries > 0; retries--) {
-		ret = ulpi_write(&motg->otg, ULPI_FUNC_CTRL_SUSPENDM,
-				ULPI_CLR(ULPI_FUNC_CTRL));
-		if (!ret)
-			break;
-		ret = msm_otg_phy_clk_reset(motg);
-		if (ret)
-			return ret;
-	}
-	if (!retries)
-		return -ETIMEDOUT;
-
-	/* This reset calibrates the phy, if the above write succeeded */
-	ret = msm_otg_phy_clk_reset(motg);
-	if (ret)
-		return ret;
-
-	for (retries = 3; retries > 0; retries--) {
-		ret = ulpi_read(&motg->otg, ULPI_DEBUG);
-		if (ret != -ETIMEDOUT)
-			break;
-		ret = msm_otg_phy_clk_reset(motg);
-		if (ret)
-			return ret;
-	}
-	if (!retries)
-		return -ETIMEDOUT;
-
-	dev_info(motg->otg.dev, "phy_reset: success\n");
-	return 0;
-}
-
-#define LINK_RESET_TIMEOUT_USEC		(250 * 1000)
-static int msm_otg_reset(struct otg_transceiver *otg)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-	struct msm_otg_platform_data *pdata = motg->pdata;
-	int cnt = 0;
-	int ret;
-	u32 val = 0;
-	u32 ulpi_val = 0;
-
-	ret = msm_otg_phy_reset(motg);
-	if (ret) {
-		dev_err(otg->dev, "phy_reset failed\n");
-		return ret;
-	}
-
-	ulpi_init(motg);
-
-	writel(USBCMD_RESET, USB_USBCMD);
-	while (cnt < LINK_RESET_TIMEOUT_USEC) {
-		if (!(readl(USB_USBCMD) & USBCMD_RESET))
-			break;
-		udelay(1);
-		cnt++;
-	}
-	if (cnt >= LINK_RESET_TIMEOUT_USEC)
-		return -ETIMEDOUT;
-
-	/* select ULPI phy */
-	writel(0x80000000, USB_PORTSC);
-
-	msleep(100);
-
-	writel(0x0, USB_AHBBURST);
-	writel(0x00, USB_AHBMODE);
-
-	if (pdata->otg_control == OTG_PHY_CONTROL) {
-		val = readl(USB_OTGSC);
-		if (pdata->mode == USB_OTG) {
-			ulpi_val = ULPI_INT_IDGRD | ULPI_INT_SESS_VALID;
-			val |= OTGSC_IDIE | OTGSC_BSVIE;
-		} else if (pdata->mode == USB_PERIPHERAL) {
-			ulpi_val = ULPI_INT_SESS_VALID;
-			val |= OTGSC_BSVIE;
-		}
-		writel(val, USB_OTGSC);
-		ulpi_write(otg, ulpi_val, ULPI_USB_INT_EN_RISE);
-		ulpi_write(otg, ulpi_val, ULPI_USB_INT_EN_FALL);
-	}
-
-	return 0;
-}
-
-#define PHY_SUSPEND_TIMEOUT_USEC	(500 * 1000)
-#define PHY_RESUME_TIMEOUT_USEC	(100 * 1000)
-
-#ifdef CONFIG_PM_SLEEP
-static int msm_otg_suspend(struct msm_otg *motg)
-{
-	struct otg_transceiver *otg = &motg->otg;
-	struct usb_bus *bus = otg->host;
-	struct msm_otg_platform_data *pdata = motg->pdata;
-	int cnt = 0;
-
-	if (atomic_read(&motg->in_lpm))
-		return 0;
-
-	disable_irq(motg->irq);
-	/*
-	 * Interrupt Latch Register auto-clear feature is not present
-	 * in all PHY versions. Latch register is clear on read type.
-	 * Clear latch register to avoid spurious wakeup from
-	 * low power mode (LPM).
-	 */
-	ulpi_read(otg, 0x14);
-
-	/*
-	 * PHY comparators are disabled when PHY enters into low power
-	 * mode (LPM). Keep PHY comparators ON in LPM only when we expect
-	 * VBUS/Id notifications from USB PHY. Otherwise turn off USB
-	 * PHY comparators. This save significant amount of power.
-	 */
-	if (pdata->otg_control == OTG_PHY_CONTROL)
-		ulpi_write(otg, 0x01, 0x30);
-
-	/*
-	 * PLL is not turned off when PHY enters into low power mode (LPM).
-	 * Disable PLL for maximum power savings.
-	 */
-	ulpi_write(otg, 0x08, 0x09);
-
-	/*
-	 * PHY may take some time or even fail to enter into low power
-	 * mode (LPM). Hence poll for 500 msec and reset the PHY and link
-	 * in failure case.
-	 */
-	writel(readl(USB_PORTSC) | PORTSC_PHCD, USB_PORTSC);
-	while (cnt < PHY_SUSPEND_TIMEOUT_USEC) {
-		if (readl(USB_PORTSC) & PORTSC_PHCD)
-			break;
-		udelay(1);
-		cnt++;
-	}
-
-	if (cnt >= PHY_SUSPEND_TIMEOUT_USEC) {
-		dev_err(otg->dev, "Unable to suspend PHY\n");
-		msm_otg_reset(otg);
-		enable_irq(motg->irq);
-		return -ETIMEDOUT;
-	}
-
-	/*
-	 * PHY has capability to generate interrupt asynchronously in low
-	 * power mode (LPM). This interrupt is level triggered. So USB IRQ
-	 * line must be disabled till async interrupt enable bit is cleared
-	 * in USBCMD register. Assert STP (ULPI interface STOP signal) to
-	 * block data communication from PHY.
-	 */
-	writel(readl(USB_USBCMD) | ASYNC_INTR_CTRL | ULPI_STP_CTRL, USB_USBCMD);
-
-	clk_disable(motg->pclk);
-	clk_disable(motg->clk);
-	if (motg->core_clk)
-		clk_disable(motg->core_clk);
-
-	if (device_may_wakeup(otg->dev))
-		enable_irq_wake(motg->irq);
-	if (bus)
-		clear_bit(HCD_FLAG_HW_ACCESSIBLE, &(bus_to_hcd(bus))->flags);
-
-	atomic_set(&motg->in_lpm, 1);
-	enable_irq(motg->irq);
-
-	dev_info(otg->dev, "USB in low power mode\n");
-
-	return 0;
-}
-
-static int msm_otg_resume(struct msm_otg *motg)
-{
-	struct otg_transceiver *otg = &motg->otg;
-	struct usb_bus *bus = otg->host;
-	int cnt = 0;
-	unsigned temp;
-
-	if (!atomic_read(&motg->in_lpm))
-		return 0;
-
-	clk_enable(motg->pclk);
-	clk_enable(motg->clk);
-	if (motg->core_clk)
-		clk_enable(motg->core_clk);
-
-	temp = readl(USB_USBCMD);
-	temp &= ~ASYNC_INTR_CTRL;
-	temp &= ~ULPI_STP_CTRL;
-	writel(temp, USB_USBCMD);
-
-	/*
-	 * PHY comes out of low power mode (LPM) in case of wakeup
-	 * from asynchronous interrupt.
-	 */
-	if (!(readl(USB_PORTSC) & PORTSC_PHCD))
-		goto skip_phy_resume;
-
-	writel(readl(USB_PORTSC) & ~PORTSC_PHCD, USB_PORTSC);
-	while (cnt < PHY_RESUME_TIMEOUT_USEC) {
-		if (!(readl(USB_PORTSC) & PORTSC_PHCD))
-			break;
-		udelay(1);
-		cnt++;
-	}
-
-	if (cnt >= PHY_RESUME_TIMEOUT_USEC) {
-		/*
-		 * This is a fatal error. Reset the link and
-		 * PHY. USB state can not be restored. Re-insertion
-		 * of USB cable is the only way to get USB working.
-		 */
-		dev_err(otg->dev, "Unable to resume USB."
-				"Re-plugin the cable\n");
-		msm_otg_reset(otg);
-	}
-
-skip_phy_resume:
-	if (device_may_wakeup(otg->dev))
-		disable_irq_wake(motg->irq);
-	if (bus)
-		set_bit(HCD_FLAG_HW_ACCESSIBLE, &(bus_to_hcd(bus))->flags);
-
-	if (motg->async_int) {
-		motg->async_int = 0;
-		pm_runtime_put(otg->dev);
-		enable_irq(motg->irq);
-	}
-
-	atomic_set(&motg->in_lpm, 0);
-
-	dev_info(otg->dev, "USB exited from low power mode\n");
-
-	return 0;
-}
-#endif
-
-static void msm_otg_start_host(struct otg_transceiver *otg, int on)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-	struct msm_otg_platform_data *pdata = motg->pdata;
-	struct usb_hcd *hcd;
-
-	if (!otg->host)
-		return;
-
-	hcd = bus_to_hcd(otg->host);
-
-	if (on) {
-		dev_dbg(otg->dev, "host on\n");
-
-		if (pdata->vbus_power)
-			pdata->vbus_power(1);
-		/*
-		 * Some boards have a switch cotrolled by gpio
-		 * to enable/disable internal HUB. Enable internal
-		 * HUB before kicking the host.
-		 */
-		if (pdata->setup_gpio)
-			pdata->setup_gpio(OTG_STATE_A_HOST);
-#ifdef CONFIG_USB
-		usb_add_hcd(hcd, hcd->irq, IRQF_SHARED);
-#endif
-	} else {
-		dev_dbg(otg->dev, "host off\n");
-
-#ifdef CONFIG_USB
-		usb_remove_hcd(hcd);
-#endif
-		if (pdata->setup_gpio)
-			pdata->setup_gpio(OTG_STATE_UNDEFINED);
-		if (pdata->vbus_power)
-			pdata->vbus_power(0);
-	}
-}
-
-static int msm_otg_set_host(struct otg_transceiver *otg, struct usb_bus *host)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-	struct usb_hcd *hcd;
-
-	/*
-	 * Fail host registration if this board can support
-	 * only peripheral configuration.
-	 */
-	if (motg->pdata->mode == USB_PERIPHERAL) {
-		dev_info(otg->dev, "Host mode is not supported\n");
-		return -ENODEV;
-	}
-
-	if (!host) {
-		if (otg->state == OTG_STATE_A_HOST) {
-			pm_runtime_get_sync(otg->dev);
-			msm_otg_start_host(otg, 0);
-			otg->host = NULL;
-			otg->state = OTG_STATE_UNDEFINED;
-			schedule_work(&motg->sm_work);
-		} else {
-			otg->host = NULL;
-		}
-
-		return 0;
-	}
-
-	hcd = bus_to_hcd(host);
-	hcd->power_budget = motg->pdata->power_budget;
-
-	otg->host = host;
-	dev_dbg(otg->dev, "host driver registered w/ tranceiver\n");
-
-	/*
-	 * Kick the state machine work, if peripheral is not supported
-	 * or peripheral is already registered with us.
-	 */
-	if (motg->pdata->mode == USB_HOST || otg->gadget) {
-		pm_runtime_get_sync(otg->dev);
-		schedule_work(&motg->sm_work);
-	}
-
-	return 0;
-}
-
-static void msm_otg_start_peripheral(struct otg_transceiver *otg, int on)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-	struct msm_otg_platform_data *pdata = motg->pdata;
-
-	if (!otg->gadget)
-		return;
-
-	if (on) {
-		dev_dbg(otg->dev, "gadget on\n");
-		/*
-		 * Some boards have a switch cotrolled by gpio
-		 * to enable/disable internal HUB. Disable internal
-		 * HUB before kicking the gadget.
-		 */
-		if (pdata->setup_gpio)
-			pdata->setup_gpio(OTG_STATE_B_PERIPHERAL);
-		usb_gadget_vbus_connect(otg->gadget);
-	} else {
-		dev_dbg(otg->dev, "gadget off\n");
-		usb_gadget_vbus_disconnect(otg->gadget);
-		if (pdata->setup_gpio)
-			pdata->setup_gpio(OTG_STATE_UNDEFINED);
-	}
-
-}
-
-static int msm_otg_set_peripheral(struct otg_transceiver *otg,
-			struct usb_gadget *gadget)
-{
-	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
-
-	/*
-	 * Fail peripheral registration if this board can support
-	 * only host configuration.
-	 */
-	if (motg->pdata->mode == USB_HOST) {
-		dev_info(otg->dev, "Peripheral mode is not supported\n");
-		return -ENODEV;
-	}
-
-	if (!gadget) {
-		if (otg->state == OTG_STATE_B_PERIPHERAL) {
-			pm_runtime_get_sync(otg->dev);
-			msm_otg_start_peripheral(otg, 0);
-			otg->gadget = NULL;
-			otg->state = OTG_STATE_UNDEFINED;
-			schedule_work(&motg->sm_work);
-		} else {
-			otg->gadget = NULL;
-		}
-
-		return 0;
-	}
-	otg->gadget = gadget;
-	dev_dbg(otg->dev, "peripheral driver registered w/ tranceiver\n");
-
-	/*
-	 * Kick the state machine work, if host is not supported
-	 * or host is already registered with us.
-	 */
-	if (motg->pdata->mode == USB_PERIPHERAL || otg->host) {
-		pm_runtime_get_sync(otg->dev);
-		schedule_work(&motg->sm_work);
-	}
-
-	return 0;
-}
-
-/*
- * We support OTG, Peripheral only and Host only configurations. In case
- * of OTG, mode switch (host-->peripheral/peripheral-->host) can happen
- * via Id pin status or user request (debugfs). Id/BSV interrupts are not
- * enabled when switch is controlled by user and default mode is supplied
- * by board file, which can be changed by userspace later.
- */
-static void msm_otg_init_sm(struct msm_otg *motg)
-{
-	struct msm_otg_platform_data *pdata = motg->pdata;
-	u32 otgsc = readl(USB_OTGSC);
-
-	switch (pdata->mode) {
-	case USB_OTG:
-		if (pdata->otg_control == OTG_PHY_CONTROL) {
-			if (otgsc & OTGSC_ID)
-				set_bit(ID, &motg->inputs);
-			else
-				clear_bit(ID, &motg->inputs);
-
-			if (otgsc & OTGSC_BSV)
-				set_bit(B_SESS_VLD, &motg->inputs);
-			else
-				clear_bit(B_SESS_VLD, &motg->inputs);
-		} else if (pdata->otg_control == OTG_USER_CONTROL) {
-			if (pdata->default_mode == USB_HOST) {
-				clear_bit(ID, &motg->inputs);
-			} else if (pdata->default_mode == USB_PERIPHERAL) {
-				set_bit(ID, &motg->inputs);
-				set_bit(B_SESS_VLD, &motg->inputs);
-			} else {
-				set_bit(ID, &motg->inputs);
-				clear_bit(B_SESS_VLD, &motg->inputs);
-			}
-		}
-		break;
-	case USB_HOST:
-		clear_bit(ID, &motg->inputs);
-		break;
-	case USB_PERIPHERAL:
-		set_bit(ID, &motg->inputs);
-		if (otgsc & OTGSC_BSV)
-			set_bit(B_SESS_VLD, &motg->inputs);
-		else
-			clear_bit(B_SESS_VLD, &motg->inputs);
-		break;
-	default:
-		break;
-	}
-}
-
-static void msm_otg_sm_work(struct work_struct *w)
-{
-	struct msm_otg *motg = container_of(w, struct msm_otg, sm_work);
-	struct otg_transceiver *otg = &motg->otg;
-
-	switch (otg->state) {
-	case OTG_STATE_UNDEFINED:
-		dev_dbg(otg->dev, "OTG_STATE_UNDEFINED state\n");
-		msm_otg_reset(otg);
-		msm_otg_init_sm(motg);
-		otg->state = OTG_STATE_B_IDLE;
-		/* FALL THROUGH */
-	case OTG_STATE_B_IDLE:
-		dev_dbg(otg->dev, "OTG_STATE_B_IDLE state\n");
-		if (!test_bit(ID, &motg->inputs) && otg->host) {
-			/* disable BSV bit */
-			writel(readl(USB_OTGSC) & ~OTGSC_BSVIE, USB_OTGSC);
-			msm_otg_start_host(otg, 1);
-			otg->state = OTG_STATE_A_HOST;
-		} else if (test_bit(B_SESS_VLD, &motg->inputs) && otg->gadget) {
-			msm_otg_start_peripheral(otg, 1);
-			otg->state = OTG_STATE_B_PERIPHERAL;
-		}
-		pm_runtime_put_sync(otg->dev);
-		break;
-	case OTG_STATE_B_PERIPHERAL:
-		dev_dbg(otg->dev, "OTG_STATE_B_PERIPHERAL state\n");
-		if (!test_bit(B_SESS_VLD, &motg->inputs) ||
-				!test_bit(ID, &motg->inputs)) {
-			msm_otg_start_peripheral(otg, 0);
-			otg->state = OTG_STATE_B_IDLE;
-			msm_otg_reset(otg);
-			schedule_work(w);
-		}
-		break;
-	case OTG_STATE_A_HOST:
-		dev_dbg(otg->dev, "OTG_STATE_A_HOST state\n");
-		if (test_bit(ID, &motg->inputs)) {
-			msm_otg_start_host(otg, 0);
-			otg->state = OTG_STATE_B_IDLE;
-			msm_otg_reset(otg);
-			schedule_work(w);
-		}
-		break;
-	default:
-		break;
-	}
-}
-
-static irqreturn_t msm_otg_irq(int irq, void *data)
-{
-	struct msm_otg *motg = data;
-	struct otg_transceiver *otg = &motg->otg;
-	u32 otgsc = 0;
-
-	if (atomic_read(&motg->in_lpm)) {
-		disable_irq_nosync(irq);
-		motg->async_int = 1;
-		pm_runtime_get(otg->dev);
-		return IRQ_HANDLED;
-	}
-
-	otgsc = readl(USB_OTGSC);
-	if (!(otgsc & (OTGSC_IDIS | OTGSC_BSVIS)))
-		return IRQ_NONE;
-
-	if ((otgsc & OTGSC_IDIS) && (otgsc & OTGSC_IDIE)) {
-		if (otgsc & OTGSC_ID)
-			set_bit(ID, &motg->inputs);
-		else
-			clear_bit(ID, &motg->inputs);
-		dev_dbg(otg->dev, "ID set/clear\n");
-		pm_runtime_get_noresume(otg->dev);
-	} else if ((otgsc & OTGSC_BSVIS) && (otgsc & OTGSC_BSVIE)) {
-		if (otgsc & OTGSC_BSV)
-			set_bit(B_SESS_VLD, &motg->inputs);
-		else
-			clear_bit(B_SESS_VLD, &motg->inputs);
-		dev_dbg(otg->dev, "BSV set/clear\n");
-		pm_runtime_get_noresume(otg->dev);
-	}
-
-	writel(otgsc, USB_OTGSC);
-	schedule_work(&motg->sm_work);
-	return IRQ_HANDLED;
-}
-
-static int msm_otg_mode_show(struct seq_file *s, void *unused)
-{
-	struct msm_otg *motg = s->private;
-	struct otg_transceiver *otg = &motg->otg;
-
-	switch (otg->state) {
-	case OTG_STATE_A_HOST:
-		seq_printf(s, "host\n");
-		break;
-	case OTG_STATE_B_PERIPHERAL:
-		seq_printf(s, "peripheral\n");
-		break;
-	default:
-		seq_printf(s, "none\n");
-		break;
-	}
-
-	return 0;
-}
-
-static int msm_otg_mode_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, msm_otg_mode_show, inode->i_private);
-}
-
-static ssize_t msm_otg_mode_write(struct file *file, const char __user *ubuf,
-				size_t count, loff_t *ppos)
-{
-	struct seq_file *s = file->private_data;
-	struct msm_otg *motg = s->private;
-	char buf[16];
-	struct otg_transceiver *otg = &motg->otg;
-	int status = count;
-	enum usb_mode_type req_mode;
-
-	memset(buf, 0x00, sizeof(buf));
-
-	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) {
-		status = -EFAULT;
-		goto out;
-	}
-
-	if (!strncmp(buf, "host", 4)) {
-		req_mode = USB_HOST;
-	} else if (!strncmp(buf, "peripheral", 10)) {
-		req_mode = USB_PERIPHERAL;
-	} else if (!strncmp(buf, "none", 4)) {
-		req_mode = USB_NONE;
-	} else {
-		status = -EINVAL;
-		goto out;
-	}
-
-	switch (req_mode) {
-	case USB_NONE:
-		switch (otg->state) {
-		case OTG_STATE_A_HOST:
-		case OTG_STATE_B_PERIPHERAL:
-			set_bit(ID, &motg->inputs);
-			clear_bit(B_SESS_VLD, &motg->inputs);
-			break;
-		default:
-			goto out;
-		}
-		break;
-	case USB_PERIPHERAL:
-		switch (otg->state) {
-		case OTG_STATE_B_IDLE:
-		case OTG_STATE_A_HOST:
-			set_bit(ID, &motg->inputs);
-			set_bit(B_SESS_VLD, &motg->inputs);
-			break;
-		default:
-			goto out;
-		}
-		break;
-	case USB_HOST:
-		switch (otg->state) {
-		case OTG_STATE_B_IDLE:
-		case OTG_STATE_B_PERIPHERAL:
-			clear_bit(ID, &motg->inputs);
-			break;
-		default:
-			goto out;
-		}
-		break;
-	default:
-		goto out;
-	}
-
-	pm_runtime_get_sync(otg->dev);
-	schedule_work(&motg->sm_work);
-out:
-	return status;
-}
-
-const struct file_operations msm_otg_mode_fops = {
-	.open = msm_otg_mode_open,
-	.read = seq_read,
-	.write = msm_otg_mode_write,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static struct dentry *msm_otg_dbg_root;
-static struct dentry *msm_otg_dbg_mode;
-
-static int msm_otg_debugfs_init(struct msm_otg *motg)
-{
-	msm_otg_dbg_root = debugfs_create_dir("msm_otg", NULL);
-
-	if (!msm_otg_dbg_root || IS_ERR(msm_otg_dbg_root))
-		return -ENODEV;
-
-	msm_otg_dbg_mode = debugfs_create_file("mode", S_IRUGO | S_IWUSR,
-				msm_otg_dbg_root, motg, &msm_otg_mode_fops);
-	if (!msm_otg_dbg_mode) {
-		debugfs_remove(msm_otg_dbg_root);
-		msm_otg_dbg_root = NULL;
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-static void msm_otg_debugfs_cleanup(void)
-{
-	debugfs_remove(msm_otg_dbg_mode);
-	debugfs_remove(msm_otg_dbg_root);
-}
-
-static int __init msm_otg_probe(struct platform_device *pdev)
-{
-	int ret = 0;
-	struct resource *res;
-	struct msm_otg *motg;
-	struct otg_transceiver *otg;
-
-	dev_info(&pdev->dev, "msm_otg probe\n");
-	if (!pdev->dev.platform_data) {
-		dev_err(&pdev->dev, "No platform data given. Bailing out\n");
-		return -ENODEV;
-	}
-
-	motg = kzalloc(sizeof(struct msm_otg), GFP_KERNEL);
-	if (!motg) {
-		dev_err(&pdev->dev, "unable to allocate msm_otg\n");
-		return -ENOMEM;
-	}
-
-	motg->pdata = pdev->dev.platform_data;
-	otg = &motg->otg;
-	otg->dev = &pdev->dev;
-
-	motg->phy_reset_clk = clk_get(&pdev->dev, "usb_phy_clk");
-	if (IS_ERR(motg->phy_reset_clk)) {
-		dev_err(&pdev->dev, "failed to get usb_phy_clk\n");
-		ret = PTR_ERR(motg->phy_reset_clk);
-		goto free_motg;
-	}
-
-	motg->clk = clk_get(&pdev->dev, "usb_hs_clk");
-	if (IS_ERR(motg->clk)) {
-		dev_err(&pdev->dev, "failed to get usb_hs_clk\n");
-		ret = PTR_ERR(motg->clk);
-		goto put_phy_reset_clk;
-	}
-
-	motg->pclk = clk_get(&pdev->dev, "usb_hs_pclk");
-	if (IS_ERR(motg->pclk)) {
-		dev_err(&pdev->dev, "failed to get usb_hs_pclk\n");
-		ret = PTR_ERR(motg->pclk);
-		goto put_clk;
-	}
-
-	/*
-	 * USB core clock is not present on all MSM chips. This
-	 * clock is introduced to remove the dependency on AXI
-	 * bus frequency.
-	 */
-	motg->core_clk = clk_get(&pdev->dev, "usb_hs_core_clk");
-	if (IS_ERR(motg->core_clk))
-		motg->core_clk = NULL;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "failed to get platform resource mem\n");
-		ret = -ENODEV;
-		goto put_core_clk;
-	}
-
-	motg->regs = ioremap(res->start, resource_size(res));
-	if (!motg->regs) {
-		dev_err(&pdev->dev, "ioremap failed\n");
-		ret = -ENOMEM;
-		goto put_core_clk;
-	}
-	dev_info(&pdev->dev, "OTG regs = %p\n", motg->regs);
-
-	motg->irq = platform_get_irq(pdev, 0);
-	if (!motg->irq) {
-		dev_err(&pdev->dev, "platform_get_irq failed\n");
-		ret = -ENODEV;
-		goto free_regs;
-	}
-
-	clk_enable(motg->clk);
-	clk_enable(motg->pclk);
-	if (motg->core_clk)
-		clk_enable(motg->core_clk);
-
-	writel(0, USB_USBINTR);
-	writel(0, USB_OTGSC);
-
-	INIT_WORK(&motg->sm_work, msm_otg_sm_work);
-	ret = request_irq(motg->irq, msm_otg_irq, IRQF_SHARED,
-					"msm_otg", motg);
-	if (ret) {
-		dev_err(&pdev->dev, "request irq failed\n");
-		goto disable_clks;
-	}
-
-	otg->init = msm_otg_reset;
-	otg->set_host = msm_otg_set_host;
-	otg->set_peripheral = msm_otg_set_peripheral;
-
-	otg->io_ops = &msm_otg_io_ops;
-
-	ret = otg_set_transceiver(&motg->otg);
-	if (ret) {
-		dev_err(&pdev->dev, "otg_set_transceiver failed\n");
-		goto free_irq;
-	}
-
-	platform_set_drvdata(pdev, motg);
-	device_init_wakeup(&pdev->dev, 1);
-
-	if (motg->pdata->mode == USB_OTG &&
-			motg->pdata->otg_control == OTG_USER_CONTROL) {
-		ret = msm_otg_debugfs_init(motg);
-		if (ret)
-			dev_dbg(&pdev->dev, "mode debugfs file is"
-					"not available\n");
-	}
-
-	pm_runtime_set_active(&pdev->dev);
-	pm_runtime_enable(&pdev->dev);
-
-	return 0;
-free_irq:
-	free_irq(motg->irq, motg);
-disable_clks:
-	clk_disable(motg->pclk);
-	clk_disable(motg->clk);
-free_regs:
-	iounmap(motg->regs);
-put_core_clk:
-	if (motg->core_clk)
-		clk_put(motg->core_clk);
-	clk_put(motg->pclk);
-put_clk:
-	clk_put(motg->clk);
-put_phy_reset_clk:
-	clk_put(motg->phy_reset_clk);
-free_motg:
-	kfree(motg);
-	return ret;
-}
-
-static int __devexit msm_otg_remove(struct platform_device *pdev)
-{
-	struct msm_otg *motg = platform_get_drvdata(pdev);
-	struct otg_transceiver *otg = &motg->otg;
-	int cnt = 0;
-
-	if (otg->host || otg->gadget)
-		return -EBUSY;
-
-	msm_otg_debugfs_cleanup();
-	cancel_work_sync(&motg->sm_work);
-
-	pm_runtime_resume(&pdev->dev);
-
-	device_init_wakeup(&pdev->dev, 0);
-	pm_runtime_disable(&pdev->dev);
-
-	otg_set_transceiver(NULL);
-	free_irq(motg->irq, motg);
-
-	/*
-	 * Put PHY in low power mode.
-	 */
-	ulpi_read(otg, 0x14);
-	ulpi_write(otg, 0x08, 0x09);
-
-	writel(readl(USB_PORTSC) | PORTSC_PHCD, USB_PORTSC);
-	while (cnt < PHY_SUSPEND_TIMEOUT_USEC) {
-		if (readl(USB_PORTSC) & PORTSC_PHCD)
-			break;
-		udelay(1);
-		cnt++;
-	}
-	if (cnt >= PHY_SUSPEND_TIMEOUT_USEC)
-		dev_err(otg->dev, "Unable to suspend PHY\n");
-
-	clk_disable(motg->pclk);
-	clk_disable(motg->clk);
-	if (motg->core_clk)
-		clk_disable(motg->core_clk);
-
-	iounmap(motg->regs);
-	pm_runtime_set_suspended(&pdev->dev);
-
-	clk_put(motg->phy_reset_clk);
-	clk_put(motg->pclk);
-	clk_put(motg->clk);
-	if (motg->core_clk)
-		clk_put(motg->core_clk);
-
-	kfree(motg);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_RUNTIME
-static int msm_otg_runtime_idle(struct device *dev)
-{
-	struct msm_otg *motg = dev_get_drvdata(dev);
-	struct otg_transceiver *otg = &motg->otg;
-
-	dev_dbg(dev, "OTG runtime idle\n");
-
-	/*
-	 * It is observed some times that a spurious interrupt
-	 * comes when PHY is put into LPM immediately after PHY reset.
-	 * This 1 sec delay also prevents entering into LPM immediately
-	 * after asynchronous interrupt.
-	 */
-	if (otg->state != OTG_STATE_UNDEFINED)
-		pm_schedule_suspend(dev, 1000);
-
-	return -EAGAIN;
-}
-
-static int msm_otg_runtime_suspend(struct device *dev)
-{
-	struct msm_otg *motg = dev_get_drvdata(dev);
-
-	dev_dbg(dev, "OTG runtime suspend\n");
-	return msm_otg_suspend(motg);
-}
-
-static int msm_otg_runtime_resume(struct device *dev)
-{
-	struct msm_otg *motg = dev_get_drvdata(dev);
-
-	dev_dbg(dev, "OTG runtime resume\n");
-	return msm_otg_resume(motg);
-}
-#endif
-
-#ifdef CONFIG_PM_SLEEP
-static int msm_otg_pm_suspend(struct device *dev)
-{
-	struct msm_otg *motg = dev_get_drvdata(dev);
-
-	dev_dbg(dev, "OTG PM suspend\n");
-	return msm_otg_suspend(motg);
-}
-
-static int msm_otg_pm_resume(struct device *dev)
-{
-	struct msm_otg *motg = dev_get_drvdata(dev);
-	int ret;
-
-	dev_dbg(dev, "OTG PM resume\n");
-
-	ret = msm_otg_resume(motg);
-	if (ret)
-		return ret;
-
-	/*
-	 * Runtime PM Documentation recommends bringing the
-	 * device to full powered state upon resume.
-	 */
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
-
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static const struct dev_pm_ops msm_otg_dev_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(msm_otg_pm_suspend, msm_otg_pm_resume)
-	SET_RUNTIME_PM_OPS(msm_otg_runtime_suspend, msm_otg_runtime_resume,
-				msm_otg_runtime_idle)
-};
-#endif
-
-static struct platform_driver msm_otg_driver = {
-	.remove = __devexit_p(msm_otg_remove),
-	.driver = {
-		.name = DRIVER_NAME,
-		.owner = THIS_MODULE,
-#ifdef CONFIG_PM
-		.pm = &msm_otg_dev_pm_ops,
-#endif
-	},
-};
-
-static int __init msm_otg_init(void)
-{
-	return platform_driver_probe(&msm_otg_driver, msm_otg_probe);
-}
-
-static void __exit msm_otg_exit(void)
-{
-	platform_driver_unregister(&msm_otg_driver);
-}
-
-module_init(msm_otg_init);
-module_exit(msm_otg_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("MSM USB transceiver driver");
diff --git a/drivers/usb/otg/msm_otg.c b/drivers/usb/otg/msm_otg.c
new file mode 100644
index 000000000000..296598628b85
--- /dev/null
+++ b/drivers/usb/otg/msm_otg.c
@@ -0,0 +1,1124 @@
+/* Copyright (c) 2009-2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/pm_runtime.h>
+
+#include <linux/usb.h>
+#include <linux/usb/otg.h>
+#include <linux/usb/ulpi.h>
+#include <linux/usb/gadget.h>
+#include <linux/usb/hcd.h>
+#include <linux/usb/msm_hsusb.h>
+#include <linux/usb/msm_hsusb_hw.h>
+
+#include <mach/clk.h>
+
+#define MSM_USB_BASE	(motg->regs)
+#define DRIVER_NAME	"msm_otg"
+
+#define ULPI_IO_TIMEOUT_USEC	(10 * 1000)
+static int ulpi_read(struct otg_transceiver *otg, u32 reg)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+	int cnt = 0;
+
+	/* initiate read operation */
+	writel(ULPI_RUN | ULPI_READ | ULPI_ADDR(reg),
+	       USB_ULPI_VIEWPORT);
+
+	/* wait for completion */
+	while (cnt < ULPI_IO_TIMEOUT_USEC) {
+		if (!(readl(USB_ULPI_VIEWPORT) & ULPI_RUN))
+			break;
+		udelay(1);
+		cnt++;
+	}
+
+	if (cnt >= ULPI_IO_TIMEOUT_USEC) {
+		dev_err(otg->dev, "ulpi_read: timeout %08x\n",
+			readl(USB_ULPI_VIEWPORT));
+		return -ETIMEDOUT;
+	}
+	return ULPI_DATA_READ(readl(USB_ULPI_VIEWPORT));
+}
+
+static int ulpi_write(struct otg_transceiver *otg, u32 val, u32 reg)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+	int cnt = 0;
+
+	/* initiate write operation */
+	writel(ULPI_RUN | ULPI_WRITE |
+	       ULPI_ADDR(reg) | ULPI_DATA(val),
+	       USB_ULPI_VIEWPORT);
+
+	/* wait for completion */
+	while (cnt < ULPI_IO_TIMEOUT_USEC) {
+		if (!(readl(USB_ULPI_VIEWPORT) & ULPI_RUN))
+			break;
+		udelay(1);
+		cnt++;
+	}
+
+	if (cnt >= ULPI_IO_TIMEOUT_USEC) {
+		dev_err(otg->dev, "ulpi_write: timeout\n");
+		return -ETIMEDOUT;
+	}
+	return 0;
+}
+
+static struct otg_io_access_ops msm_otg_io_ops = {
+	.read = ulpi_read,
+	.write = ulpi_write,
+};
+
+static void ulpi_init(struct msm_otg *motg)
+{
+	struct msm_otg_platform_data *pdata = motg->pdata;
+	int *seq = pdata->phy_init_seq;
+
+	if (!seq)
+		return;
+
+	while (seq[0] >= 0) {
+		dev_vdbg(motg->otg.dev, "ulpi: write 0x%02x to 0x%02x\n",
+				seq[0], seq[1]);
+		ulpi_write(&motg->otg, seq[0], seq[1]);
+		seq += 2;
+	}
+}
+
+static int msm_otg_link_clk_reset(struct msm_otg *motg, bool assert)
+{
+	int ret;
+
+	if (assert) {
+		ret = clk_reset(motg->clk, CLK_RESET_ASSERT);
+		if (ret)
+			dev_err(motg->otg.dev, "usb hs_clk assert failed\n");
+	} else {
+		ret = clk_reset(motg->clk, CLK_RESET_DEASSERT);
+		if (ret)
+			dev_err(motg->otg.dev, "usb hs_clk deassert failed\n");
+	}
+	return ret;
+}
+
+static int msm_otg_phy_clk_reset(struct msm_otg *motg)
+{
+	int ret;
+
+	ret = clk_reset(motg->phy_reset_clk, CLK_RESET_ASSERT);
+	if (ret) {
+		dev_err(motg->otg.dev, "usb phy clk assert failed\n");
+		return ret;
+	}
+	usleep_range(10000, 12000);
+	ret = clk_reset(motg->phy_reset_clk, CLK_RESET_DEASSERT);
+	if (ret)
+		dev_err(motg->otg.dev, "usb phy clk deassert failed\n");
+	return ret;
+}
+
+static int msm_otg_phy_reset(struct msm_otg *motg)
+{
+	u32 val;
+	int ret;
+	int retries;
+
+	ret = msm_otg_link_clk_reset(motg, 1);
+	if (ret)
+		return ret;
+	ret = msm_otg_phy_clk_reset(motg);
+	if (ret)
+		return ret;
+	ret = msm_otg_link_clk_reset(motg, 0);
+	if (ret)
+		return ret;
+
+	val = readl(USB_PORTSC) & ~PORTSC_PTS_MASK;
+	writel(val | PORTSC_PTS_ULPI, USB_PORTSC);
+
+	for (retries = 3; retries > 0; retries--) {
+		ret = ulpi_write(&motg->otg, ULPI_FUNC_CTRL_SUSPENDM,
+				ULPI_CLR(ULPI_FUNC_CTRL));
+		if (!ret)
+			break;
+		ret = msm_otg_phy_clk_reset(motg);
+		if (ret)
+			return ret;
+	}
+	if (!retries)
+		return -ETIMEDOUT;
+
+	/* This reset calibrates the phy, if the above write succeeded */
+	ret = msm_otg_phy_clk_reset(motg);
+	if (ret)
+		return ret;
+
+	for (retries = 3; retries > 0; retries--) {
+		ret = ulpi_read(&motg->otg, ULPI_DEBUG);
+		if (ret != -ETIMEDOUT)
+			break;
+		ret = msm_otg_phy_clk_reset(motg);
+		if (ret)
+			return ret;
+	}
+	if (!retries)
+		return -ETIMEDOUT;
+
+	dev_info(motg->otg.dev, "phy_reset: success\n");
+	return 0;
+}
+
+#define LINK_RESET_TIMEOUT_USEC		(250 * 1000)
+static int msm_otg_reset(struct otg_transceiver *otg)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+	struct msm_otg_platform_data *pdata = motg->pdata;
+	int cnt = 0;
+	int ret;
+	u32 val = 0;
+	u32 ulpi_val = 0;
+
+	ret = msm_otg_phy_reset(motg);
+	if (ret) {
+		dev_err(otg->dev, "phy_reset failed\n");
+		return ret;
+	}
+
+	ulpi_init(motg);
+
+	writel(USBCMD_RESET, USB_USBCMD);
+	while (cnt < LINK_RESET_TIMEOUT_USEC) {
+		if (!(readl(USB_USBCMD) & USBCMD_RESET))
+			break;
+		udelay(1);
+		cnt++;
+	}
+	if (cnt >= LINK_RESET_TIMEOUT_USEC)
+		return -ETIMEDOUT;
+
+	/* select ULPI phy */
+	writel(0x80000000, USB_PORTSC);
+
+	msleep(100);
+
+	writel(0x0, USB_AHBBURST);
+	writel(0x00, USB_AHBMODE);
+
+	if (pdata->otg_control == OTG_PHY_CONTROL) {
+		val = readl(USB_OTGSC);
+		if (pdata->mode == USB_OTG) {
+			ulpi_val = ULPI_INT_IDGRD | ULPI_INT_SESS_VALID;
+			val |= OTGSC_IDIE | OTGSC_BSVIE;
+		} else if (pdata->mode == USB_PERIPHERAL) {
+			ulpi_val = ULPI_INT_SESS_VALID;
+			val |= OTGSC_BSVIE;
+		}
+		writel(val, USB_OTGSC);
+		ulpi_write(otg, ulpi_val, ULPI_USB_INT_EN_RISE);
+		ulpi_write(otg, ulpi_val, ULPI_USB_INT_EN_FALL);
+	}
+
+	return 0;
+}
+
+#define PHY_SUSPEND_TIMEOUT_USEC	(500 * 1000)
+#define PHY_RESUME_TIMEOUT_USEC	(100 * 1000)
+
+#ifdef CONFIG_PM_SLEEP
+static int msm_otg_suspend(struct msm_otg *motg)
+{
+	struct otg_transceiver *otg = &motg->otg;
+	struct usb_bus *bus = otg->host;
+	struct msm_otg_platform_data *pdata = motg->pdata;
+	int cnt = 0;
+
+	if (atomic_read(&motg->in_lpm))
+		return 0;
+
+	disable_irq(motg->irq);
+	/*
+	 * Interrupt Latch Register auto-clear feature is not present
+	 * in all PHY versions. Latch register is clear on read type.
+	 * Clear latch register to avoid spurious wakeup from
+	 * low power mode (LPM).
+	 */
+	ulpi_read(otg, 0x14);
+
+	/*
+	 * PHY comparators are disabled when PHY enters into low power
+	 * mode (LPM). Keep PHY comparators ON in LPM only when we expect
+	 * VBUS/Id notifications from USB PHY. Otherwise turn off USB
+	 * PHY comparators. This save significant amount of power.
+	 */
+	if (pdata->otg_control == OTG_PHY_CONTROL)
+		ulpi_write(otg, 0x01, 0x30);
+
+	/*
+	 * PLL is not turned off when PHY enters into low power mode (LPM).
+	 * Disable PLL for maximum power savings.
+	 */
+	ulpi_write(otg, 0x08, 0x09);
+
+	/*
+	 * PHY may take some time or even fail to enter into low power
+	 * mode (LPM). Hence poll for 500 msec and reset the PHY and link
+	 * in failure case.
+	 */
+	writel(readl(USB_PORTSC) | PORTSC_PHCD, USB_PORTSC);
+	while (cnt < PHY_SUSPEND_TIMEOUT_USEC) {
+		if (readl(USB_PORTSC) & PORTSC_PHCD)
+			break;
+		udelay(1);
+		cnt++;
+	}
+
+	if (cnt >= PHY_SUSPEND_TIMEOUT_USEC) {
+		dev_err(otg->dev, "Unable to suspend PHY\n");
+		msm_otg_reset(otg);
+		enable_irq(motg->irq);
+		return -ETIMEDOUT;
+	}
+
+	/*
+	 * PHY has capability to generate interrupt asynchronously in low
+	 * power mode (LPM). This interrupt is level triggered. So USB IRQ
+	 * line must be disabled till async interrupt enable bit is cleared
+	 * in USBCMD register. Assert STP (ULPI interface STOP signal) to
+	 * block data communication from PHY.
+	 */
+	writel(readl(USB_USBCMD) | ASYNC_INTR_CTRL | ULPI_STP_CTRL, USB_USBCMD);
+
+	clk_disable(motg->pclk);
+	clk_disable(motg->clk);
+	if (motg->core_clk)
+		clk_disable(motg->core_clk);
+
+	if (device_may_wakeup(otg->dev))
+		enable_irq_wake(motg->irq);
+	if (bus)
+		clear_bit(HCD_FLAG_HW_ACCESSIBLE, &(bus_to_hcd(bus))->flags);
+
+	atomic_set(&motg->in_lpm, 1);
+	enable_irq(motg->irq);
+
+	dev_info(otg->dev, "USB in low power mode\n");
+
+	return 0;
+}
+
+static int msm_otg_resume(struct msm_otg *motg)
+{
+	struct otg_transceiver *otg = &motg->otg;
+	struct usb_bus *bus = otg->host;
+	int cnt = 0;
+	unsigned temp;
+
+	if (!atomic_read(&motg->in_lpm))
+		return 0;
+
+	clk_enable(motg->pclk);
+	clk_enable(motg->clk);
+	if (motg->core_clk)
+		clk_enable(motg->core_clk);
+
+	temp = readl(USB_USBCMD);
+	temp &= ~ASYNC_INTR_CTRL;
+	temp &= ~ULPI_STP_CTRL;
+	writel(temp, USB_USBCMD);
+
+	/*
+	 * PHY comes out of low power mode (LPM) in case of wakeup
+	 * from asynchronous interrupt.
+	 */
+	if (!(readl(USB_PORTSC) & PORTSC_PHCD))
+		goto skip_phy_resume;
+
+	writel(readl(USB_PORTSC) & ~PORTSC_PHCD, USB_PORTSC);
+	while (cnt < PHY_RESUME_TIMEOUT_USEC) {
+		if (!(readl(USB_PORTSC) & PORTSC_PHCD))
+			break;
+		udelay(1);
+		cnt++;
+	}
+
+	if (cnt >= PHY_RESUME_TIMEOUT_USEC) {
+		/*
+		 * This is a fatal error. Reset the link and
+		 * PHY. USB state can not be restored. Re-insertion
+		 * of USB cable is the only way to get USB working.
+		 */
+		dev_err(otg->dev, "Unable to resume USB."
+				"Re-plugin the cable\n");
+		msm_otg_reset(otg);
+	}
+
+skip_phy_resume:
+	if (device_may_wakeup(otg->dev))
+		disable_irq_wake(motg->irq);
+	if (bus)
+		set_bit(HCD_FLAG_HW_ACCESSIBLE, &(bus_to_hcd(bus))->flags);
+
+	if (motg->async_int) {
+		motg->async_int = 0;
+		pm_runtime_put(otg->dev);
+		enable_irq(motg->irq);
+	}
+
+	atomic_set(&motg->in_lpm, 0);
+
+	dev_info(otg->dev, "USB exited from low power mode\n");
+
+	return 0;
+}
+#endif
+
+static void msm_otg_start_host(struct otg_transceiver *otg, int on)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+	struct msm_otg_platform_data *pdata = motg->pdata;
+	struct usb_hcd *hcd;
+
+	if (!otg->host)
+		return;
+
+	hcd = bus_to_hcd(otg->host);
+
+	if (on) {
+		dev_dbg(otg->dev, "host on\n");
+
+		if (pdata->vbus_power)
+			pdata->vbus_power(1);
+		/*
+		 * Some boards have a switch cotrolled by gpio
+		 * to enable/disable internal HUB. Enable internal
+		 * HUB before kicking the host.
+		 */
+		if (pdata->setup_gpio)
+			pdata->setup_gpio(OTG_STATE_A_HOST);
+#ifdef CONFIG_USB
+		usb_add_hcd(hcd, hcd->irq, IRQF_SHARED);
+#endif
+	} else {
+		dev_dbg(otg->dev, "host off\n");
+
+#ifdef CONFIG_USB
+		usb_remove_hcd(hcd);
+#endif
+		if (pdata->setup_gpio)
+			pdata->setup_gpio(OTG_STATE_UNDEFINED);
+		if (pdata->vbus_power)
+			pdata->vbus_power(0);
+	}
+}
+
+static int msm_otg_set_host(struct otg_transceiver *otg, struct usb_bus *host)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+	struct usb_hcd *hcd;
+
+	/*
+	 * Fail host registration if this board can support
+	 * only peripheral configuration.
+	 */
+	if (motg->pdata->mode == USB_PERIPHERAL) {
+		dev_info(otg->dev, "Host mode is not supported\n");
+		return -ENODEV;
+	}
+
+	if (!host) {
+		if (otg->state == OTG_STATE_A_HOST) {
+			pm_runtime_get_sync(otg->dev);
+			msm_otg_start_host(otg, 0);
+			otg->host = NULL;
+			otg->state = OTG_STATE_UNDEFINED;
+			schedule_work(&motg->sm_work);
+		} else {
+			otg->host = NULL;
+		}
+
+		return 0;
+	}
+
+	hcd = bus_to_hcd(host);
+	hcd->power_budget = motg->pdata->power_budget;
+
+	otg->host = host;
+	dev_dbg(otg->dev, "host driver registered w/ tranceiver\n");
+
+	/*
+	 * Kick the state machine work, if peripheral is not supported
+	 * or peripheral is already registered with us.
+	 */
+	if (motg->pdata->mode == USB_HOST || otg->gadget) {
+		pm_runtime_get_sync(otg->dev);
+		schedule_work(&motg->sm_work);
+	}
+
+	return 0;
+}
+
+static void msm_otg_start_peripheral(struct otg_transceiver *otg, int on)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+	struct msm_otg_platform_data *pdata = motg->pdata;
+
+	if (!otg->gadget)
+		return;
+
+	if (on) {
+		dev_dbg(otg->dev, "gadget on\n");
+		/*
+		 * Some boards have a switch cotrolled by gpio
+		 * to enable/disable internal HUB. Disable internal
+		 * HUB before kicking the gadget.
+		 */
+		if (pdata->setup_gpio)
+			pdata->setup_gpio(OTG_STATE_B_PERIPHERAL);
+		usb_gadget_vbus_connect(otg->gadget);
+	} else {
+		dev_dbg(otg->dev, "gadget off\n");
+		usb_gadget_vbus_disconnect(otg->gadget);
+		if (pdata->setup_gpio)
+			pdata->setup_gpio(OTG_STATE_UNDEFINED);
+	}
+
+}
+
+static int msm_otg_set_peripheral(struct otg_transceiver *otg,
+			struct usb_gadget *gadget)
+{
+	struct msm_otg *motg = container_of(otg, struct msm_otg, otg);
+
+	/*
+	 * Fail peripheral registration if this board can support
+	 * only host configuration.
+	 */
+	if (motg->pdata->mode == USB_HOST) {
+		dev_info(otg->dev, "Peripheral mode is not supported\n");
+		return -ENODEV;
+	}
+
+	if (!gadget) {
+		if (otg->state == OTG_STATE_B_PERIPHERAL) {
+			pm_runtime_get_sync(otg->dev);
+			msm_otg_start_peripheral(otg, 0);
+			otg->gadget = NULL;
+			otg->state = OTG_STATE_UNDEFINED;
+			schedule_work(&motg->sm_work);
+		} else {
+			otg->gadget = NULL;
+		}
+
+		return 0;
+	}
+	otg->gadget = gadget;
+	dev_dbg(otg->dev, "peripheral driver registered w/ tranceiver\n");
+
+	/*
+	 * Kick the state machine work, if host is not supported
+	 * or host is already registered with us.
+	 */
+	if (motg->pdata->mode == USB_PERIPHERAL || otg->host) {
+		pm_runtime_get_sync(otg->dev);
+		schedule_work(&motg->sm_work);
+	}
+
+	return 0;
+}
+
+/*
+ * We support OTG, Peripheral only and Host only configurations. In case
+ * of OTG, mode switch (host-->peripheral/peripheral-->host) can happen
+ * via Id pin status or user request (debugfs). Id/BSV interrupts are not
+ * enabled when switch is controlled by user and default mode is supplied
+ * by board file, which can be changed by userspace later.
+ */
+static void msm_otg_init_sm(struct msm_otg *motg)
+{
+	struct msm_otg_platform_data *pdata = motg->pdata;
+	u32 otgsc = readl(USB_OTGSC);
+
+	switch (pdata->mode) {
+	case USB_OTG:
+		if (pdata->otg_control == OTG_PHY_CONTROL) {
+			if (otgsc & OTGSC_ID)
+				set_bit(ID, &motg->inputs);
+			else
+				clear_bit(ID, &motg->inputs);
+
+			if (otgsc & OTGSC_BSV)
+				set_bit(B_SESS_VLD, &motg->inputs);
+			else
+				clear_bit(B_SESS_VLD, &motg->inputs);
+		} else if (pdata->otg_control == OTG_USER_CONTROL) {
+			if (pdata->default_mode == USB_HOST) {
+				clear_bit(ID, &motg->inputs);
+			} else if (pdata->default_mode == USB_PERIPHERAL) {
+				set_bit(ID, &motg->inputs);
+				set_bit(B_SESS_VLD, &motg->inputs);
+			} else {
+				set_bit(ID, &motg->inputs);
+				clear_bit(B_SESS_VLD, &motg->inputs);
+			}
+		}
+		break;
+	case USB_HOST:
+		clear_bit(ID, &motg->inputs);
+		break;
+	case USB_PERIPHERAL:
+		set_bit(ID, &motg->inputs);
+		if (otgsc & OTGSC_BSV)
+			set_bit(B_SESS_VLD, &motg->inputs);
+		else
+			clear_bit(B_SESS_VLD, &motg->inputs);
+		break;
+	default:
+		break;
+	}
+}
+
+static void msm_otg_sm_work(struct work_struct *w)
+{
+	struct msm_otg *motg = container_of(w, struct msm_otg, sm_work);
+	struct otg_transceiver *otg = &motg->otg;
+
+	switch (otg->state) {
+	case OTG_STATE_UNDEFINED:
+		dev_dbg(otg->dev, "OTG_STATE_UNDEFINED state\n");
+		msm_otg_reset(otg);
+		msm_otg_init_sm(motg);
+		otg->state = OTG_STATE_B_IDLE;
+		/* FALL THROUGH */
+	case OTG_STATE_B_IDLE:
+		dev_dbg(otg->dev, "OTG_STATE_B_IDLE state\n");
+		if (!test_bit(ID, &motg->inputs) && otg->host) {
+			/* disable BSV bit */
+			writel(readl(USB_OTGSC) & ~OTGSC_BSVIE, USB_OTGSC);
+			msm_otg_start_host(otg, 1);
+			otg->state = OTG_STATE_A_HOST;
+		} else if (test_bit(B_SESS_VLD, &motg->inputs) && otg->gadget) {
+			msm_otg_start_peripheral(otg, 1);
+			otg->state = OTG_STATE_B_PERIPHERAL;
+		}
+		pm_runtime_put_sync(otg->dev);
+		break;
+	case OTG_STATE_B_PERIPHERAL:
+		dev_dbg(otg->dev, "OTG_STATE_B_PERIPHERAL state\n");
+		if (!test_bit(B_SESS_VLD, &motg->inputs) ||
+				!test_bit(ID, &motg->inputs)) {
+			msm_otg_start_peripheral(otg, 0);
+			otg->state = OTG_STATE_B_IDLE;
+			msm_otg_reset(otg);
+			schedule_work(w);
+		}
+		break;
+	case OTG_STATE_A_HOST:
+		dev_dbg(otg->dev, "OTG_STATE_A_HOST state\n");
+		if (test_bit(ID, &motg->inputs)) {
+			msm_otg_start_host(otg, 0);
+			otg->state = OTG_STATE_B_IDLE;
+			msm_otg_reset(otg);
+			schedule_work(w);
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static irqreturn_t msm_otg_irq(int irq, void *data)
+{
+	struct msm_otg *motg = data;
+	struct otg_transceiver *otg = &motg->otg;
+	u32 otgsc = 0;
+
+	if (atomic_read(&motg->in_lpm)) {
+		disable_irq_nosync(irq);
+		motg->async_int = 1;
+		pm_runtime_get(otg->dev);
+		return IRQ_HANDLED;
+	}
+
+	otgsc = readl(USB_OTGSC);
+	if (!(otgsc & (OTGSC_IDIS | OTGSC_BSVIS)))
+		return IRQ_NONE;
+
+	if ((otgsc & OTGSC_IDIS) && (otgsc & OTGSC_IDIE)) {
+		if (otgsc & OTGSC_ID)
+			set_bit(ID, &motg->inputs);
+		else
+			clear_bit(ID, &motg->inputs);
+		dev_dbg(otg->dev, "ID set/clear\n");
+		pm_runtime_get_noresume(otg->dev);
+	} else if ((otgsc & OTGSC_BSVIS) && (otgsc & OTGSC_BSVIE)) {
+		if (otgsc & OTGSC_BSV)
+			set_bit(B_SESS_VLD, &motg->inputs);
+		else
+			clear_bit(B_SESS_VLD, &motg->inputs);
+		dev_dbg(otg->dev, "BSV set/clear\n");
+		pm_runtime_get_noresume(otg->dev);
+	}
+
+	writel(otgsc, USB_OTGSC);
+	schedule_work(&motg->sm_work);
+	return IRQ_HANDLED;
+}
+
+static int msm_otg_mode_show(struct seq_file *s, void *unused)
+{
+	struct msm_otg *motg = s->private;
+	struct otg_transceiver *otg = &motg->otg;
+
+	switch (otg->state) {
+	case OTG_STATE_A_HOST:
+		seq_printf(s, "host\n");
+		break;
+	case OTG_STATE_B_PERIPHERAL:
+		seq_printf(s, "peripheral\n");
+		break;
+	default:
+		seq_printf(s, "none\n");
+		break;
+	}
+
+	return 0;
+}
+
+static int msm_otg_mode_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, msm_otg_mode_show, inode->i_private);
+}
+
+static ssize_t msm_otg_mode_write(struct file *file, const char __user *ubuf,
+				size_t count, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct msm_otg *motg = s->private;
+	char buf[16];
+	struct otg_transceiver *otg = &motg->otg;
+	int status = count;
+	enum usb_mode_type req_mode;
+
+	memset(buf, 0x00, sizeof(buf));
+
+	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) {
+		status = -EFAULT;
+		goto out;
+	}
+
+	if (!strncmp(buf, "host", 4)) {
+		req_mode = USB_HOST;
+	} else if (!strncmp(buf, "peripheral", 10)) {
+		req_mode = USB_PERIPHERAL;
+	} else if (!strncmp(buf, "none", 4)) {
+		req_mode = USB_NONE;
+	} else {
+		status = -EINVAL;
+		goto out;
+	}
+
+	switch (req_mode) {
+	case USB_NONE:
+		switch (otg->state) {
+		case OTG_STATE_A_HOST:
+		case OTG_STATE_B_PERIPHERAL:
+			set_bit(ID, &motg->inputs);
+			clear_bit(B_SESS_VLD, &motg->inputs);
+			break;
+		default:
+			goto out;
+		}
+		break;
+	case USB_PERIPHERAL:
+		switch (otg->state) {
+		case OTG_STATE_B_IDLE:
+		case OTG_STATE_A_HOST:
+			set_bit(ID, &motg->inputs);
+			set_bit(B_SESS_VLD, &motg->inputs);
+			break;
+		default:
+			goto out;
+		}
+		break;
+	case USB_HOST:
+		switch (otg->state) {
+		case OTG_STATE_B_IDLE:
+		case OTG_STATE_B_PERIPHERAL:
+			clear_bit(ID, &motg->inputs);
+			break;
+		default:
+			goto out;
+		}
+		break;
+	default:
+		goto out;
+	}
+
+	pm_runtime_get_sync(otg->dev);
+	schedule_work(&motg->sm_work);
+out:
+	return status;
+}
+
+const struct file_operations msm_otg_mode_fops = {
+	.open = msm_otg_mode_open,
+	.read = seq_read,
+	.write = msm_otg_mode_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static struct dentry *msm_otg_dbg_root;
+static struct dentry *msm_otg_dbg_mode;
+
+static int msm_otg_debugfs_init(struct msm_otg *motg)
+{
+	msm_otg_dbg_root = debugfs_create_dir("msm_otg", NULL);
+
+	if (!msm_otg_dbg_root || IS_ERR(msm_otg_dbg_root))
+		return -ENODEV;
+
+	msm_otg_dbg_mode = debugfs_create_file("mode", S_IRUGO | S_IWUSR,
+				msm_otg_dbg_root, motg, &msm_otg_mode_fops);
+	if (!msm_otg_dbg_mode) {
+		debugfs_remove(msm_otg_dbg_root);
+		msm_otg_dbg_root = NULL;
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void msm_otg_debugfs_cleanup(void)
+{
+	debugfs_remove(msm_otg_dbg_mode);
+	debugfs_remove(msm_otg_dbg_root);
+}
+
+static int __init msm_otg_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	struct resource *res;
+	struct msm_otg *motg;
+	struct otg_transceiver *otg;
+
+	dev_info(&pdev->dev, "msm_otg probe\n");
+	if (!pdev->dev.platform_data) {
+		dev_err(&pdev->dev, "No platform data given. Bailing out\n");
+		return -ENODEV;
+	}
+
+	motg = kzalloc(sizeof(struct msm_otg), GFP_KERNEL);
+	if (!motg) {
+		dev_err(&pdev->dev, "unable to allocate msm_otg\n");
+		return -ENOMEM;
+	}
+
+	motg->pdata = pdev->dev.platform_data;
+	otg = &motg->otg;
+	otg->dev = &pdev->dev;
+
+	motg->phy_reset_clk = clk_get(&pdev->dev, "usb_phy_clk");
+	if (IS_ERR(motg->phy_reset_clk)) {
+		dev_err(&pdev->dev, "failed to get usb_phy_clk\n");
+		ret = PTR_ERR(motg->phy_reset_clk);
+		goto free_motg;
+	}
+
+	motg->clk = clk_get(&pdev->dev, "usb_hs_clk");
+	if (IS_ERR(motg->clk)) {
+		dev_err(&pdev->dev, "failed to get usb_hs_clk\n");
+		ret = PTR_ERR(motg->clk);
+		goto put_phy_reset_clk;
+	}
+
+	motg->pclk = clk_get(&pdev->dev, "usb_hs_pclk");
+	if (IS_ERR(motg->pclk)) {
+		dev_err(&pdev->dev, "failed to get usb_hs_pclk\n");
+		ret = PTR_ERR(motg->pclk);
+		goto put_clk;
+	}
+
+	/*
+	 * USB core clock is not present on all MSM chips. This
+	 * clock is introduced to remove the dependency on AXI
+	 * bus frequency.
+	 */
+	motg->core_clk = clk_get(&pdev->dev, "usb_hs_core_clk");
+	if (IS_ERR(motg->core_clk))
+		motg->core_clk = NULL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "failed to get platform resource mem\n");
+		ret = -ENODEV;
+		goto put_core_clk;
+	}
+
+	motg->regs = ioremap(res->start, resource_size(res));
+	if (!motg->regs) {
+		dev_err(&pdev->dev, "ioremap failed\n");
+		ret = -ENOMEM;
+		goto put_core_clk;
+	}
+	dev_info(&pdev->dev, "OTG regs = %p\n", motg->regs);
+
+	motg->irq = platform_get_irq(pdev, 0);
+	if (!motg->irq) {
+		dev_err(&pdev->dev, "platform_get_irq failed\n");
+		ret = -ENODEV;
+		goto free_regs;
+	}
+
+	clk_enable(motg->clk);
+	clk_enable(motg->pclk);
+	if (motg->core_clk)
+		clk_enable(motg->core_clk);
+
+	writel(0, USB_USBINTR);
+	writel(0, USB_OTGSC);
+
+	INIT_WORK(&motg->sm_work, msm_otg_sm_work);
+	ret = request_irq(motg->irq, msm_otg_irq, IRQF_SHARED,
+					"msm_otg", motg);
+	if (ret) {
+		dev_err(&pdev->dev, "request irq failed\n");
+		goto disable_clks;
+	}
+
+	otg->init = msm_otg_reset;
+	otg->set_host = msm_otg_set_host;
+	otg->set_peripheral = msm_otg_set_peripheral;
+
+	otg->io_ops = &msm_otg_io_ops;
+
+	ret = otg_set_transceiver(&motg->otg);
+	if (ret) {
+		dev_err(&pdev->dev, "otg_set_transceiver failed\n");
+		goto free_irq;
+	}
+
+	platform_set_drvdata(pdev, motg);
+	device_init_wakeup(&pdev->dev, 1);
+
+	if (motg->pdata->mode == USB_OTG &&
+			motg->pdata->otg_control == OTG_USER_CONTROL) {
+		ret = msm_otg_debugfs_init(motg);
+		if (ret)
+			dev_dbg(&pdev->dev, "mode debugfs file is"
+					"not available\n");
+	}
+
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	return 0;
+free_irq:
+	free_irq(motg->irq, motg);
+disable_clks:
+	clk_disable(motg->pclk);
+	clk_disable(motg->clk);
+free_regs:
+	iounmap(motg->regs);
+put_core_clk:
+	if (motg->core_clk)
+		clk_put(motg->core_clk);
+	clk_put(motg->pclk);
+put_clk:
+	clk_put(motg->clk);
+put_phy_reset_clk:
+	clk_put(motg->phy_reset_clk);
+free_motg:
+	kfree(motg);
+	return ret;
+}
+
+static int __devexit msm_otg_remove(struct platform_device *pdev)
+{
+	struct msm_otg *motg = platform_get_drvdata(pdev);
+	struct otg_transceiver *otg = &motg->otg;
+	int cnt = 0;
+
+	if (otg->host || otg->gadget)
+		return -EBUSY;
+
+	msm_otg_debugfs_cleanup();
+	cancel_work_sync(&motg->sm_work);
+
+	pm_runtime_resume(&pdev->dev);
+
+	device_init_wakeup(&pdev->dev, 0);
+	pm_runtime_disable(&pdev->dev);
+
+	otg_set_transceiver(NULL);
+	free_irq(motg->irq, motg);
+
+	/*
+	 * Put PHY in low power mode.
+	 */
+	ulpi_read(otg, 0x14);
+	ulpi_write(otg, 0x08, 0x09);
+
+	writel(readl(USB_PORTSC) | PORTSC_PHCD, USB_PORTSC);
+	while (cnt < PHY_SUSPEND_TIMEOUT_USEC) {
+		if (readl(USB_PORTSC) & PORTSC_PHCD)
+			break;
+		udelay(1);
+		cnt++;
+	}
+	if (cnt >= PHY_SUSPEND_TIMEOUT_USEC)
+		dev_err(otg->dev, "Unable to suspend PHY\n");
+
+	clk_disable(motg->pclk);
+	clk_disable(motg->clk);
+	if (motg->core_clk)
+		clk_disable(motg->core_clk);
+
+	iounmap(motg->regs);
+	pm_runtime_set_suspended(&pdev->dev);
+
+	clk_put(motg->phy_reset_clk);
+	clk_put(motg->pclk);
+	clk_put(motg->clk);
+	if (motg->core_clk)
+		clk_put(motg->core_clk);
+
+	kfree(motg);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_RUNTIME
+static int msm_otg_runtime_idle(struct device *dev)
+{
+	struct msm_otg *motg = dev_get_drvdata(dev);
+	struct otg_transceiver *otg = &motg->otg;
+
+	dev_dbg(dev, "OTG runtime idle\n");
+
+	/*
+	 * It is observed some times that a spurious interrupt
+	 * comes when PHY is put into LPM immediately after PHY reset.
+	 * This 1 sec delay also prevents entering into LPM immediately
+	 * after asynchronous interrupt.
+	 */
+	if (otg->state != OTG_STATE_UNDEFINED)
+		pm_schedule_suspend(dev, 1000);
+
+	return -EAGAIN;
+}
+
+static int msm_otg_runtime_suspend(struct device *dev)
+{
+	struct msm_otg *motg = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "OTG runtime suspend\n");
+	return msm_otg_suspend(motg);
+}
+
+static int msm_otg_runtime_resume(struct device *dev)
+{
+	struct msm_otg *motg = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "OTG runtime resume\n");
+	return msm_otg_resume(motg);
+}
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+static int msm_otg_pm_suspend(struct device *dev)
+{
+	struct msm_otg *motg = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "OTG PM suspend\n");
+	return msm_otg_suspend(motg);
+}
+
+static int msm_otg_pm_resume(struct device *dev)
+{
+	struct msm_otg *motg = dev_get_drvdata(dev);
+	int ret;
+
+	dev_dbg(dev, "OTG PM resume\n");
+
+	ret = msm_otg_resume(motg);
+	if (ret)
+		return ret;
+
+	/*
+	 * Runtime PM Documentation recommends bringing the
+	 * device to full powered state upon resume.
+	 */
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PM
+static const struct dev_pm_ops msm_otg_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(msm_otg_pm_suspend, msm_otg_pm_resume)
+	SET_RUNTIME_PM_OPS(msm_otg_runtime_suspend, msm_otg_runtime_resume,
+				msm_otg_runtime_idle)
+};
+#endif
+
+static struct platform_driver msm_otg_driver = {
+	.remove = __devexit_p(msm_otg_remove),
+	.driver = {
+		.name = DRIVER_NAME,
+		.owner = THIS_MODULE,
+#ifdef CONFIG_PM
+		.pm = &msm_otg_dev_pm_ops,
+#endif
+	},
+};
+
+static int __init msm_otg_init(void)
+{
+	return platform_driver_probe(&msm_otg_driver, msm_otg_probe);
+}
+
+static void __exit msm_otg_exit(void)
+{
+	platform_driver_unregister(&msm_otg_driver);
+}
+
+module_init(msm_otg_init);
+module_exit(msm_otg_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MSM USB transceiver driver");
diff --git a/include/linux/usb/msm_hsusb.h b/include/linux/usb/msm_hsusb.h
index 3675e03b1539..3657403eac18 100644
--- a/include/linux/usb/msm_hsusb.h
+++ b/include/linux/usb/msm_hsusb.h
@@ -55,7 +55,7 @@ enum otg_control_type {
 
 /**
  * struct msm_otg_platform_data - platform device data
- *              for msm72k_otg driver.
+ *              for msm_otg driver.
  * @phy_init_seq: PHY configuration sequence. val, reg pairs
  *              terminated by -1.
  * @vbus_power: VBUS power on/off routine.
-- 
cgit v1.2.3


From 256ee435b9a9ee9cca69602fe8046b27ca99fbee Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 1 Mar 2011 07:06:12 +0000
Subject: netdevice: Convert printk to pr_info in netif_tx_stop_queue

This allows any caller to be prefaced by any specific
pr_fmt to better identify which device driver is using
this function inappropriately.

Add terminating newline.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8be4056ad251..71563e7b2bfb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1765,8 +1765,7 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev)
 static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
 {
 	if (WARN_ON(!dev_queue)) {
-		printk(KERN_INFO "netif_stop_queue() cannot be called before "
-		       "register_netdev()");
+		pr_info("netif_stop_queue() cannot be called before register_netdev()\n");
 		return;
 	}
 	set_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
-- 
cgit v1.2.3


From f1a304e7941cc76353363a139cbb6a4b1ca7c737 Mon Sep 17 00:00:00 2001
From: Pratheesh Gangadhar <pratheesh@ti.com>
Date: Sat, 5 Mar 2011 04:30:17 +0530
Subject: UIO: add PRUSS UIO driver support

This patch implements PRUSS (Programmable Real-time Unit Sub System)
UIO driver which exports SOC resources associated with PRUSS like
I/O, memories and IRQs to user space. PRUSS is dual 32-bit RISC
processors which is efficient in performing embedded tasks that
require manipulation of packed memory mapped data structures and
handling system events that have tight real time constraints. This
driver is currently supported on Texas Instruments DA850, AM18xx and
OMAP-L138 devices.
For example, PRUSS runs firmware for real-time critical industrial
communication data link layer and communicates with application stack
running in user space via shared memory and IRQs.

Signed-off-by: Pratheesh Gangadhar <pratheesh@ti.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hans J. Koch <hjk@hansjkoch.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/uio/Kconfig                     |  17 +++
 drivers/uio/Makefile                    |   1 +
 drivers/uio/uio_pruss.c                 | 247 ++++++++++++++++++++++++++++++++
 include/linux/platform_data/uio_pruss.h |  25 ++++
 4 files changed, 290 insertions(+)
 create mode 100644 drivers/uio/uio_pruss.c
 create mode 100644 include/linux/platform_data/uio_pruss.h

(limited to 'include')

diff --git a/drivers/uio/Kconfig b/drivers/uio/Kconfig
index bb440792a1b7..6f3ea9bbc818 100644
--- a/drivers/uio/Kconfig
+++ b/drivers/uio/Kconfig
@@ -94,4 +94,21 @@ config UIO_NETX
 	  To compile this driver as a module, choose M here; the module
 	  will be called uio_netx.
 
+config UIO_PRUSS
+	tristate "Texas Instruments PRUSS driver"
+	depends on ARCH_DAVINCI_DA850
+	help
+	  PRUSS driver for OMAPL138/DA850/AM18XX devices
+	  PRUSS driver requires user space components, examples and user space
+	  driver is available from below SVN repo - you may use anonymous login
+
+	  https://gforge.ti.com/gf/project/pru_sw/
+
+	  More info on API is available at below wiki
+
+	  http://processors.wiki.ti.com/index.php/PRU_Linux_Application_Loader
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called uio_pruss.
+
 endif
diff --git a/drivers/uio/Makefile b/drivers/uio/Makefile
index 18fd818c5b97..d4dd9a5552f8 100644
--- a/drivers/uio/Makefile
+++ b/drivers/uio/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_UIO_AEC)	+= uio_aec.o
 obj-$(CONFIG_UIO_SERCOS3)	+= uio_sercos3.o
 obj-$(CONFIG_UIO_PCI_GENERIC)	+= uio_pci_generic.o
 obj-$(CONFIG_UIO_NETX)	+= uio_netx.o
+obj-$(CONFIG_UIO_PRUSS)         += uio_pruss.o
diff --git a/drivers/uio/uio_pruss.c b/drivers/uio/uio_pruss.c
new file mode 100644
index 000000000000..daf6e77de2b1
--- /dev/null
+++ b/drivers/uio/uio_pruss.c
@@ -0,0 +1,247 @@
+/*
+ * Programmable Real-Time Unit Sub System (PRUSS) UIO driver (uio_pruss)
+ *
+ * This driver exports PRUSS host event out interrupts and PRUSS, L3 RAM,
+ * and DDR RAM to user space for applications interacting with PRUSS firmware
+ *
+ * Copyright (C) 2010-11 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/platform_device.h>
+#include <linux/uio_driver.h>
+#include <linux/platform_data/uio_pruss.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+#include <mach/sram.h>
+
+#define DRV_NAME "pruss_uio"
+#define DRV_VERSION "1.0"
+
+static int sram_pool_sz = SZ_16K;
+module_param(sram_pool_sz, int, 0);
+MODULE_PARM_DESC(sram_pool_sz, "sram pool size to allocate ");
+
+static int extram_pool_sz = SZ_256K;
+module_param(extram_pool_sz, int, 0);
+MODULE_PARM_DESC(extram_pool_sz, "external ram pool size to allocate");
+
+/*
+ * Host event IRQ numbers from PRUSS - PRUSS can generate upto 8 interrupt
+ * events to AINTC of ARM host processor - which can be used for IPC b/w PRUSS
+ * firmware and user space application, async notification from PRU firmware
+ * to user space application
+ * 3	PRU_EVTOUT0
+ * 4	PRU_EVTOUT1
+ * 5	PRU_EVTOUT2
+ * 6	PRU_EVTOUT3
+ * 7	PRU_EVTOUT4
+ * 8	PRU_EVTOUT5
+ * 9	PRU_EVTOUT6
+ * 10	PRU_EVTOUT7
+*/
+#define MAX_PRUSS_EVT	8
+
+#define PINTC_HIDISR	0x0038
+#define PINTC_HIPIR	0x0900
+#define HIPIR_NOPEND	0x80000000
+#define PINTC_HIER	0x1500
+
+struct uio_pruss_dev {
+	struct uio_info *info;
+	struct clk *pruss_clk;
+	dma_addr_t sram_paddr;
+	dma_addr_t ddr_paddr;
+	void __iomem *prussio_vaddr;
+	void *sram_vaddr;
+	void *ddr_vaddr;
+	unsigned int hostirq_start;
+	unsigned int pintc_base;
+};
+
+static irqreturn_t pruss_handler(int irq, struct uio_info *info)
+{
+	struct uio_pruss_dev *gdev = info->priv;
+	int intr_bit = (irq - gdev->hostirq_start + 2);
+	int val, intr_mask = (1 << intr_bit);
+	void __iomem *base = gdev->prussio_vaddr + gdev->pintc_base;
+	void __iomem *intren_reg = base + PINTC_HIER;
+	void __iomem *intrdis_reg = base + PINTC_HIDISR;
+	void __iomem *intrstat_reg = base + PINTC_HIPIR + (intr_bit << 2);
+
+	val = ioread32(intren_reg);
+	/* Is interrupt enabled and active ? */
+	if (!(val & intr_mask) && (ioread32(intrstat_reg) & HIPIR_NOPEND))
+		return IRQ_NONE;
+	/* Disable interrupt */
+	iowrite32(intr_bit, intrdis_reg);
+	return IRQ_HANDLED;
+}
+
+static void pruss_cleanup(struct platform_device *dev,
+			struct uio_pruss_dev *gdev)
+{
+	int cnt;
+	struct uio_info *p = gdev->info;
+
+	for (cnt = 0; cnt < MAX_PRUSS_EVT; cnt++, p++) {
+		uio_unregister_device(p);
+		kfree(p->name);
+	}
+	iounmap(gdev->prussio_vaddr);
+	if (gdev->ddr_vaddr) {
+		dma_free_coherent(&dev->dev, extram_pool_sz, gdev->ddr_vaddr,
+			gdev->ddr_paddr);
+	}
+	if (gdev->sram_vaddr)
+		sram_free(gdev->sram_vaddr, sram_pool_sz);
+	kfree(gdev->info);
+	clk_put(gdev->pruss_clk);
+	kfree(gdev);
+}
+
+static int __devinit pruss_probe(struct platform_device *dev)
+{
+	struct uio_info *p;
+	struct uio_pruss_dev *gdev;
+	struct resource *regs_prussio;
+	int ret = -ENODEV, cnt = 0, len;
+	struct uio_pruss_pdata *pdata = dev->dev.platform_data;
+
+	gdev = kzalloc(sizeof(struct uio_pruss_dev), GFP_KERNEL);
+	if (!gdev)
+		return -ENOMEM;
+
+	gdev->info = kzalloc(sizeof(*p) * MAX_PRUSS_EVT, GFP_KERNEL);
+	if (!gdev->info) {
+		kfree(gdev);
+		return -ENOMEM;
+	}
+	/* Power on PRU in case its not done as part of boot-loader */
+	gdev->pruss_clk = clk_get(&dev->dev, "pruss");
+	if (IS_ERR(gdev->pruss_clk)) {
+		dev_err(&dev->dev, "Failed to get clock\n");
+		kfree(gdev->info);
+		kfree(gdev);
+		ret = PTR_ERR(gdev->pruss_clk);
+		return ret;
+	} else {
+		clk_enable(gdev->pruss_clk);
+	}
+
+	regs_prussio = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!regs_prussio) {
+		dev_err(&dev->dev, "No PRUSS I/O resource specified\n");
+		goto out_free;
+	}
+
+	if (!regs_prussio->start) {
+		dev_err(&dev->dev, "Invalid memory resource\n");
+		goto out_free;
+	}
+
+	gdev->sram_vaddr = sram_alloc(sram_pool_sz, &(gdev->sram_paddr));
+	if (!gdev->sram_vaddr) {
+		dev_err(&dev->dev, "Could not allocate SRAM pool\n");
+		goto out_free;
+	}
+
+	gdev->ddr_vaddr = dma_alloc_coherent(&dev->dev, extram_pool_sz,
+				&(gdev->ddr_paddr), GFP_KERNEL | GFP_DMA);
+	if (!gdev->ddr_vaddr) {
+		dev_err(&dev->dev, "Could not allocate external memory\n");
+		goto out_free;
+	}
+
+	len = resource_size(regs_prussio);
+	gdev->prussio_vaddr = ioremap(regs_prussio->start, len);
+	if (!gdev->prussio_vaddr) {
+		dev_err(&dev->dev, "Can't remap PRUSS I/O  address range\n");
+		goto out_free;
+	}
+
+	gdev->pintc_base = pdata->pintc_base;
+	gdev->hostirq_start = platform_get_irq(dev, 0);
+
+	for (cnt = 0, p = gdev->info; cnt < MAX_PRUSS_EVT; cnt++, p++) {
+		p->mem[0].addr = regs_prussio->start;
+		p->mem[0].size = resource_size(regs_prussio);
+		p->mem[0].memtype = UIO_MEM_PHYS;
+
+		p->mem[1].addr = gdev->sram_paddr;
+		p->mem[1].size = sram_pool_sz;
+		p->mem[1].memtype = UIO_MEM_PHYS;
+
+		p->mem[2].addr = gdev->ddr_paddr;
+		p->mem[2].size = extram_pool_sz;
+		p->mem[2].memtype = UIO_MEM_PHYS;
+
+		p->name = kasprintf(GFP_KERNEL, "pruss_evt%d", cnt);
+		p->version = DRV_VERSION;
+
+		/* Register PRUSS IRQ lines */
+		p->irq = gdev->hostirq_start + cnt;
+		p->handler = pruss_handler;
+		p->priv = gdev;
+
+		ret = uio_register_device(&dev->dev, p);
+		if (ret < 0)
+			goto out_free;
+	}
+
+	platform_set_drvdata(dev, gdev);
+	return 0;
+
+out_free:
+	pruss_cleanup(dev, gdev);
+	return ret;
+}
+
+static int __devexit pruss_remove(struct platform_device *dev)
+{
+	struct uio_pruss_dev *gdev = platform_get_drvdata(dev);
+
+	pruss_cleanup(dev, gdev);
+	platform_set_drvdata(dev, NULL);
+	return 0;
+}
+
+static struct platform_driver pruss_driver = {
+	.probe = pruss_probe,
+	.remove = __devexit_p(pruss_remove),
+	.driver = {
+		   .name = DRV_NAME,
+		   .owner = THIS_MODULE,
+		   },
+};
+
+static int __init pruss_init_module(void)
+{
+	return platform_driver_register(&pruss_driver);
+}
+
+module_init(pruss_init_module);
+
+static void __exit pruss_exit_module(void)
+{
+	platform_driver_unregister(&pruss_driver);
+}
+
+module_exit(pruss_exit_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+MODULE_AUTHOR("Amit Chatterjee <amit.chatterjee@ti.com>");
+MODULE_AUTHOR("Pratheesh Gangadhar <pratheesh@ti.com>");
diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h
new file mode 100644
index 000000000000..f39140aabc6f
--- /dev/null
+++ b/include/linux/platform_data/uio_pruss.h
@@ -0,0 +1,25 @@
+/*
+ * include/linux/platform_data/uio_pruss.h
+ *
+ * Platform data for uio_pruss driver
+ *
+ * Copyright (C) 2010-11 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UIO_PRUSS_H_
+#define _UIO_PRUSS_H_
+
+/* To configure the PRUSS INTC base offset for UIO driver */
+struct uio_pruss_pdata {
+	u32	pintc_base;
+};
+#endif /* _UIO_PRUSS_H_ */
-- 
cgit v1.2.3


From 633e804e89464d3875e59de1959a53f9041d3094 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Mar 2011 15:05:51 +0000
Subject: KEYS: Add an RCU payload dereference macro

Add an RCU payload dereference macro as this seems to be a common piece of code
amongst key types that use RCU referenced payloads.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 include/linux/key.h          | 4 ++++
 security/keys/encrypted.c    | 3 +--
 security/keys/trusted.c      | 3 +--
 security/keys/user_defined.c | 3 +--
 4 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/key.h b/include/linux/key.h
index 3db0adce1fda..a6b1edcffc34 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -275,6 +275,10 @@ static inline key_serial_t key_serial(struct key *key)
 	return key ? key->serial : 0;
 }
 
+#define rcu_dereference_key(KEY)					\
+	(rcu_dereference_protected((KEY)->payload.rcudata,		\
+				   rwsem_is_locked(&((struct key *)(KEY))->sem)))
+
 #ifdef CONFIG_SYSCTL
 extern ctl_table key_sysctls[];
 #endif
diff --git a/security/keys/encrypted.c b/security/keys/encrypted.c
index 9e7e4ce3fae8..69907a58a683 100644
--- a/security/keys/encrypted.c
+++ b/security/keys/encrypted.c
@@ -765,8 +765,7 @@ static long encrypted_read(const struct key *key, char __user *buffer,
 	size_t asciiblob_len;
 	int ret;
 
-	epayload = rcu_dereference_protected(key->payload.data,
-				  rwsem_is_locked(&((struct key *)key)->sem));
+	epayload = rcu_dereference_key(key);
 
 	/* returns the hex encoded iv, encrypted-data, and hmac as ascii */
 	asciiblob_len = epayload->datablob_len + ivsize + 1
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 83fc92e297cd..c99b9368368c 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1076,8 +1076,7 @@ static long trusted_read(const struct key *key, char __user *buffer,
 	char *bufp;
 	int i;
 
-	p = rcu_dereference_protected(key->payload.data,
-			rwsem_is_locked(&((struct key *)key)->sem));
+	p = rcu_dereference_key(key);
 	if (!p)
 		return -EINVAL;
 	if (!buffer || buflen <= 0)
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 02807fb16340..c6ca8662a468 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -184,8 +184,7 @@ long user_read(const struct key *key, char __user *buffer, size_t buflen)
 	struct user_key_payload *upayload;
 	long ret;
 
-	upayload = rcu_dereference_protected(
-		key->payload.data, rwsem_is_locked(&((struct key *)key)->sem));
+	upayload = rcu_dereference_key(key);
 	ret = upayload->datalen;
 
 	/* we can return the data as is */
-- 
cgit v1.2.3


From b9fffa3877a3ebbe0a5ad5a247358e2f7df15b24 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Mar 2011 15:05:59 +0000
Subject: KEYS: Add a key type op to permit the key description to be vetted

Add a key type operation to permit the key type to vet the description of a new
key that key_alloc() is about to allocate.  The operation may reject the
description if it wishes with an error of its choosing.  If it does this, the
key will not be allocated.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 Documentation/keys.txt   |  7 +++++++
 include/linux/key-type.h |  3 +++
 net/rxrpc/ar-key.c       | 19 +++++++++++++++++++
 security/keys/key.c      |  8 ++++++++
 4 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index e4dbbdb1bd96..cf68d1fed95d 100644
--- a/Documentation/keys.txt
+++ b/Documentation/keys.txt
@@ -1062,6 +1062,13 @@ The structure has a number of fields, some of which are mandatory:
      viable.
 
 
+ (*) int (*vet_description)(const char *description);
+
+     This optional method is called to vet a key description.  If the key type
+     doesn't approve of the key description, it may return an error, otherwise
+     it should return 0.
+
+
  (*) int (*instantiate)(struct key *key, const void *data, size_t datalen);
 
      This method is called to attach a payload to a key during construction.
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 65833d4d5998..fc8525e838b7 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -41,6 +41,9 @@ struct key_type {
 	 */
 	size_t def_datalen;
 
+	/* vet a description */
+	int (*vet_description)(const char *description);
+
 	/* instantiate a key of this type
 	 * - this method should call key_payload_reserve() to determine if the
 	 *   user's quota will hold the payload
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index d763793d39de..43ea7de2fc8e 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -25,6 +25,7 @@
 #include <keys/user-type.h>
 #include "ar-internal.h"
 
+static int rxrpc_vet_description_s(const char *);
 static int rxrpc_instantiate(struct key *, const void *, size_t);
 static int rxrpc_instantiate_s(struct key *, const void *, size_t);
 static void rxrpc_destroy(struct key *);
@@ -52,12 +53,30 @@ EXPORT_SYMBOL(key_type_rxrpc);
  */
 struct key_type key_type_rxrpc_s = {
 	.name		= "rxrpc_s",
+	.vet_description = rxrpc_vet_description_s,
 	.instantiate	= rxrpc_instantiate_s,
 	.match		= user_match,
 	.destroy	= rxrpc_destroy_s,
 	.describe	= rxrpc_describe,
 };
 
+/*
+ * Vet the description for an RxRPC server key
+ */
+static int rxrpc_vet_description_s(const char *desc)
+{
+	unsigned long num;
+	char *p;
+
+	num = simple_strtoul(desc, &p, 10);
+	if (*p != ':' || num > 65535)
+		return -EINVAL;
+	num = simple_strtoul(p + 1, &p, 10);
+	if (*p || num < 1 || num > 255)
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * parse an RxKAD type XDR format token
  * - the caller guarantees we have at least 4 words
diff --git a/security/keys/key.c b/security/keys/key.c
index 1c2d43dc5107..8e315ef2e88e 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -249,6 +249,14 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	if (!desc || !*desc)
 		goto error;
 
+	if (type->vet_description) {
+		ret = type->vet_description(desc);
+		if (ret < 0) {
+			key = ERR_PTR(ret);
+			goto error;
+		}
+	}
+
 	desclen = strlen(desc) + 1;
 	quotalen = desclen + type->def_datalen;
 
-- 
cgit v1.2.3


From fdd1b94581782a2ddf9124414e5b7a5f48ce2f9c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Mar 2011 15:06:09 +0000
Subject: KEYS: Add a new keyctl op to reject a key with a specified error code

Add a new keyctl op to reject a key with a specified error code.  This works
much the same as negating a key, and so keyctl_negate_key() is made a special
case of keyctl_reject_key().  The difference is that keyctl_negate_key()
selects ENOKEY as the error to be reported.

Typically the key would be rejected with EKEYEXPIRED, EKEYREVOKED or
EKEYREJECTED, but this is not mandatory.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 Documentation/keys-request-key.txt |  9 +++++----
 Documentation/keys.txt             | 10 ++++++++--
 include/linux/key-type.h           | 11 ++++++++++-
 include/linux/key.h                |  1 +
 include/linux/keyctl.h             |  1 +
 security/keys/compat.c             |  3 +++
 security/keys/internal.h           |  1 +
 security/keys/key.c                | 19 ++++++++++--------
 security/keys/keyctl.c             | 40 ++++++++++++++++++++++++++++++++++++--
 security/keys/keyring.c            |  4 ++--
 security/keys/request_key.c        |  2 +-
 11 files changed, 81 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/Documentation/keys-request-key.txt b/Documentation/keys-request-key.txt
index 09b55e461740..69686ad12c66 100644
--- a/Documentation/keys-request-key.txt
+++ b/Documentation/keys-request-key.txt
@@ -127,14 +127,15 @@ This is because process A's keyrings can't simply be attached to
 of them, and (b) it requires the same UID/GID/Groups all the way through.
 
 
-======================
-NEGATIVE INSTANTIATION
-======================
+====================================
+NEGATIVE INSTANTIATION AND REJECTION
+====================================
 
 Rather than instantiating a key, it is possible for the possessor of an
 authorisation key to negatively instantiate a key that's under construction.
 This is a short duration placeholder that causes any attempt at re-requesting
-the key whilst it exists to fail with error ENOKEY.
+the key whilst it exists to fail with error ENOKEY if negated or the specified
+error if rejected.
 
 This is provided to prevent excessive repeated spawning of /sbin/request-key
 processes for a key that will never be obtainable.
diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index cf68d1fed95d..a6a97fdfaddd 100644
--- a/Documentation/keys.txt
+++ b/Documentation/keys.txt
@@ -657,6 +657,8 @@ The keyctl syscall functions are:
 
 	long keyctl(KEYCTL_NEGATE, key_serial_t key,
 		    unsigned timeout, key_serial_t keyring);
+	long keyctl(KEYCTL_REJECT, key_serial_t key,
+		    unsigned timeout, unsigned error, key_serial_t keyring);
 
      If the kernel calls back to userspace to complete the instantiation of a
      key, userspace should use this call mark the key as negative before the
@@ -669,6 +671,10 @@ The keyctl syscall functions are:
      that keyring, however all the constraints applying in KEYCTL_LINK apply in
      this case too.
 
+     If the key is rejected, future searches for it will return the specified
+     error code until the rejected key expires.  Negating the key is the same
+     as rejecting the key with ENOKEY as the error code.
+
 
  (*) Set the default request-key destination keyring.
 
@@ -1240,8 +1246,8 @@ example, the KDE desktop manager).
 The program (or whatever it calls) should finish construction of the key by
 calling KEYCTL_INSTANTIATE, which also permits it to cache the key in one of
 the keyrings (probably the session ring) before returning. Alternatively, the
-key can be marked as negative with KEYCTL_NEGATE; this also permits the key to
-be cached in one of the keyrings.
+key can be marked as negative with KEYCTL_NEGATE or KEYCTL_REJECT; this also
+permits the key to be cached in one of the keyrings.
 
 If it returns with the key remaining in the unconstructed state, the key will
 be marked as being negative, it will be added to the session keyring, and an
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index fc8525e838b7..9efd081bb31e 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -105,11 +105,20 @@ extern int key_instantiate_and_link(struct key *key,
 				    size_t datalen,
 				    struct key *keyring,
 				    struct key *instkey);
-extern int key_negate_and_link(struct key *key,
+extern int key_reject_and_link(struct key *key,
 			       unsigned timeout,
+			       unsigned error,
 			       struct key *keyring,
 			       struct key *instkey);
 extern void complete_request_key(struct key_construction *cons, int error);
 
+static inline int key_negate_and_link(struct key *key,
+				      unsigned timeout,
+				      struct key *keyring,
+				      struct key *instkey)
+{
+	return key_reject_and_link(key, timeout, ENOKEY, keyring, instkey);
+}
+
 #endif /* CONFIG_KEYS */
 #endif /* _LINUX_KEY_TYPE_H */
diff --git a/include/linux/key.h b/include/linux/key.h
index a6b1edcffc34..b2bb01719561 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -170,6 +170,7 @@ struct key {
 		struct list_head	link;
 		unsigned long		x[2];
 		void			*p[2];
+		int			reject_error;
 	} type_data;
 
 	/* key data
diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h
index bd383f1944fb..7022974def0c 100644
--- a/include/linux/keyctl.h
+++ b/include/linux/keyctl.h
@@ -53,5 +53,6 @@
 #define KEYCTL_ASSUME_AUTHORITY		16	/* assume request_key() authorisation */
 #define KEYCTL_GET_SECURITY		17	/* get key security label */
 #define KEYCTL_SESSION_TO_PARENT	18	/* apply session keyring to parent process */
+#define KEYCTL_REJECT			19	/* reject a partially constructed key */
 
 #endif /*  _LINUX_KEYCTL_H */
diff --git a/security/keys/compat.c b/security/keys/compat.c
index 07a5f35e3970..17c99d0149ec 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -85,6 +85,9 @@ asmlinkage long compat_sys_keyctl(u32 option,
 	case KEYCTL_SESSION_TO_PARENT:
 		return keyctl_session_to_parent();
 
+	case KEYCTL_REJECT:
+		return keyctl_reject_key(arg2, arg3, arg4, arg5);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index a52aa7c88b41..286c0959ee51 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -214,6 +214,7 @@ extern long keyctl_assume_authority(key_serial_t);
 extern long keyctl_get_security(key_serial_t keyid, char __user *buffer,
 				size_t buflen);
 extern long keyctl_session_to_parent(void);
+extern long keyctl_reject_key(key_serial_t, unsigned, unsigned, key_serial_t);
 
 /*
  * Debugging key validation
diff --git a/security/keys/key.c b/security/keys/key.c
index 8e315ef2e88e..f7f9d93f08d9 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -511,26 +511,29 @@ int key_instantiate_and_link(struct key *key,
 EXPORT_SYMBOL(key_instantiate_and_link);
 
 /**
- * key_negate_and_link - Negatively instantiate a key and link it into the keyring.
+ * key_reject_and_link - Negatively instantiate a key and link it into the keyring.
  * @key: The key to instantiate.
  * @timeout: The timeout on the negative key.
+ * @error: The error to return when the key is hit.
  * @keyring: Keyring to create a link in on success (or NULL).
  * @authkey: The authorisation token permitting instantiation.
  *
  * Negatively instantiate a key that's in the uninstantiated state and, if
- * successful, set its timeout and link it in to the destination keyring if one
- * is supplied.  The key and any links to the key will be automatically garbage
- * collected after the timeout expires.
+ * successful, set its timeout and stored error and link it in to the
+ * destination keyring if one is supplied.  The key and any links to the key
+ * will be automatically garbage collected after the timeout expires.
  *
  * Negative keys are used to rate limit repeated request_key() calls by causing
- * them to return -ENOKEY until the negative key expires.
+ * them to return the stored error code (typically ENOKEY) until the negative
+ * key expires.
  *
  * If successful, 0 is returned, the authorisation token is revoked and anyone
  * waiting for the key is woken up.  If the key was already instantiated,
  * -EBUSY will be returned.
  */
-int key_negate_and_link(struct key *key,
+int key_reject_and_link(struct key *key,
 			unsigned timeout,
+			unsigned error,
 			struct key *keyring,
 			struct key *authkey)
 {
@@ -556,6 +559,7 @@ int key_negate_and_link(struct key *key,
 		atomic_inc(&key->user->nikeys);
 		set_bit(KEY_FLAG_NEGATIVE, &key->flags);
 		set_bit(KEY_FLAG_INSTANTIATED, &key->flags);
+		key->type_data.reject_error = -error;
 		now = current_kernel_time();
 		key->expiry = now.tv_sec + timeout;
 		key_schedule_gc(key->expiry + key_gc_delay);
@@ -585,8 +589,7 @@ int key_negate_and_link(struct key *key,
 
 	return ret == 0 ? link_ret : ret;
 }
-
-EXPORT_SYMBOL(key_negate_and_link);
+EXPORT_SYMBOL(key_reject_and_link);
 
 /*
  * Garbage collect keys in process context so that we don't have to disable
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 31a0fd8189f1..0d7b1946ff94 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1012,13 +1012,43 @@ error:
  * If successful, 0 will be returned.
  */
 long keyctl_negate_key(key_serial_t id, unsigned timeout, key_serial_t ringid)
+{
+	return keyctl_reject_key(id, timeout, ENOKEY, ringid);
+}
+
+/*
+ * Negatively instantiate the key with the given timeout (in seconds) and error
+ * code and link the key into the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * The key and any links to the key will be automatically garbage collected
+ * after the timeout expires.
+ *
+ * Negative keys are used to rate limit repeated request_key() calls by causing
+ * them to return the specified error code until the negative key expires.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error,
+		       key_serial_t ringid)
 {
 	const struct cred *cred = current_cred();
 	struct request_key_auth *rka;
 	struct key *instkey, *dest_keyring;
 	long ret;
 
-	kenter("%d,%u,%d", id, timeout, ringid);
+	kenter("%d,%u,%u,%d", id, timeout, error, ringid);
+
+	/* must be a valid error code and mustn't be a kernel special */
+	if (error <= 0 ||
+	    error >= MAX_ERRNO ||
+	    error == ERESTARTSYS ||
+	    error == ERESTARTNOINTR ||
+	    error == ERESTARTNOHAND ||
+	    error == ERESTART_RESTARTBLOCK)
+		return -EINVAL;
 
 	/* the appropriate instantiation authorisation key must have been
 	 * assumed before calling this */
@@ -1038,7 +1068,7 @@ long keyctl_negate_key(key_serial_t id, unsigned timeout, key_serial_t ringid)
 		goto error;
 
 	/* instantiate the key and link it into a keyring */
-	ret = key_negate_and_link(rka->target_key, timeout,
+	ret = key_reject_and_link(rka->target_key, timeout, error,
 				  dest_keyring, instkey);
 
 	key_put(dest_keyring);
@@ -1492,6 +1522,12 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case KEYCTL_SESSION_TO_PARENT:
 		return keyctl_session_to_parent();
 
+	case KEYCTL_REJECT:
+		return keyctl_reject_key((key_serial_t) arg2,
+					 (unsigned) arg3,
+					 (unsigned) arg4,
+					 (key_serial_t) arg5);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 5620f084dede..cdd2f3f88c88 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -352,7 +352,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 			goto error_2;
 		if (key->expiry && now.tv_sec >= key->expiry)
 			goto error_2;
-		key_ref = ERR_PTR(-ENOKEY);
+		key_ref = ERR_PTR(key->type_data.reject_error);
 		if (kflags & (1 << KEY_FLAG_NEGATIVE))
 			goto error_2;
 		goto found;
@@ -401,7 +401,7 @@ descend:
 
 		/* we set a different error code if we pass a negative key */
 		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
-			err = -ENOKEY;
+			err = key->type_data.reject_error;
 			continue;
 		}
 
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index a3dc0d460def..df3c0417ee40 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -585,7 +585,7 @@ int wait_for_key_construction(struct key *key, bool intr)
 	if (ret < 0)
 		return ret;
 	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
-		return -ENOKEY;
+		return key->type_data.reject_error;
 	return key_validate(key);
 }
 EXPORT_SYMBOL(wait_for_key_construction);
-- 
cgit v1.2.3


From ee009e4a0d4555ed522a631bae9896399674f064 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Mar 2011 15:06:20 +0000
Subject: KEYS: Add an iovec version of KEYCTL_INSTANTIATE

Add a keyctl op (KEYCTL_INSTANTIATE_IOV) that is like KEYCTL_INSTANTIATE, but
takes an iovec array and concatenates the data in-kernel into one buffer.
Since the KEYCTL_INSTANTIATE copies the data anyway, this isn't too much of a
problem.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 Documentation/keys.txt   |  15 +++++--
 arch/x86/Kconfig         |   5 +++
 include/linux/keyctl.h   |   1 +
 security/keys/compat.c   |  47 +++++++++++++++++++++
 security/keys/internal.h |   7 ++++
 security/keys/keyctl.c   | 103 +++++++++++++++++++++++++++++++++++++++++++----
 6 files changed, 167 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index a6a97fdfaddd..6523a9e6f293 100644
--- a/Documentation/keys.txt
+++ b/Documentation/keys.txt
@@ -637,6 +637,9 @@ The keyctl syscall functions are:
 	long keyctl(KEYCTL_INSTANTIATE, key_serial_t key,
 		    const void *payload, size_t plen,
 		    key_serial_t keyring);
+	long keyctl(KEYCTL_INSTANTIATE_IOV, key_serial_t key,
+		    const struct iovec *payload_iov, unsigned ioc,
+		    key_serial_t keyring);
 
      If the kernel calls back to userspace to complete the instantiation of a
      key, userspace should use this call to supply data for the key before the
@@ -652,6 +655,9 @@ The keyctl syscall functions are:
 
      The payload and plen arguments describe the payload data as for add_key().
 
+     The payload_iov and ioc arguments describe the payload data in an iovec
+     array instead of a single buffer.
+
 
  (*) Negatively instantiate a partially constructed key.
 
@@ -1244,10 +1250,11 @@ hand the request off to (perhaps a path held in placed in another key by, for
 example, the KDE desktop manager).
 
 The program (or whatever it calls) should finish construction of the key by
-calling KEYCTL_INSTANTIATE, which also permits it to cache the key in one of
-the keyrings (probably the session ring) before returning. Alternatively, the
-key can be marked as negative with KEYCTL_NEGATE or KEYCTL_REJECT; this also
-permits the key to be cached in one of the keyrings.
+calling KEYCTL_INSTANTIATE or KEYCTL_INSTANTIATE_IOV, which also permits it to
+cache the key in one of the keyrings (probably the session ring) before
+returning.  Alternatively, the key can be marked as negative with KEYCTL_NEGATE
+or KEYCTL_REJECT; this also permits the key to be cached in one of the
+keyrings.
 
 If it returns with the key remaining in the unconstructed state, the key will
 be marked as being negative, it will be added to the session keyring, and an
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d5ed94d30aad..b46b75bef496 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2138,6 +2138,11 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
+config KEYS_COMPAT
+	bool
+	depends on COMPAT && KEYS
+	default y
+
 endmenu
 
 
diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h
index 7022974def0c..9b0b865ce622 100644
--- a/include/linux/keyctl.h
+++ b/include/linux/keyctl.h
@@ -54,5 +54,6 @@
 #define KEYCTL_GET_SECURITY		17	/* get key security label */
 #define KEYCTL_SESSION_TO_PARENT	18	/* apply session keyring to parent process */
 #define KEYCTL_REJECT			19	/* reject a partially constructed key */
+#define KEYCTL_INSTANTIATE_IOV		20	/* instantiate a partially constructed key */
 
 #endif /*  _LINUX_KEYCTL_H */
diff --git a/security/keys/compat.c b/security/keys/compat.c
index 17c99d0149ec..338b510e9027 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -12,8 +12,51 @@
 #include <linux/syscalls.h>
 #include <linux/keyctl.h>
 #include <linux/compat.h>
+#include <linux/slab.h>
 #include "internal.h"
 
+/*
+ * Instantiate a key with the specified compatibility multipart payload and
+ * link the key into the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+long compat_keyctl_instantiate_key_iov(
+	key_serial_t id,
+	const struct compat_iovec __user *_payload_iov,
+	unsigned ioc,
+	key_serial_t ringid)
+{
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	long ret;
+
+	if (_payload_iov == 0 || ioc == 0)
+		goto no_payload;
+
+	ret = compat_rw_copy_check_uvector(WRITE, _payload_iov, ioc,
+					   ARRAY_SIZE(iovstack),
+					   iovstack, &iov);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		goto no_payload_free;
+
+	ret = keyctl_instantiate_key_common(id, iov, ioc, ret, ringid);
+
+	if (iov != iovstack)
+		kfree(iov);
+	return ret;
+
+no_payload_free:
+	if (iov != iovstack)
+		kfree(iov);
+no_payload:
+	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
+}
+
 /*
  * The key control system call, 32-bit compatibility version for 64-bit archs
  *
@@ -88,6 +131,10 @@ asmlinkage long compat_sys_keyctl(u32 option,
 	case KEYCTL_REJECT:
 		return keyctl_reject_key(arg2, arg3, arg4, arg5);
 
+	case KEYCTL_INSTANTIATE_IOV:
+		return compat_keyctl_instantiate_key_iov(
+			arg2, compat_ptr(arg3), arg4, arg5);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 286c0959ee51..07a025f81902 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -215,6 +215,13 @@ extern long keyctl_get_security(key_serial_t keyid, char __user *buffer,
 				size_t buflen);
 extern long keyctl_session_to_parent(void);
 extern long keyctl_reject_key(key_serial_t, unsigned, unsigned, key_serial_t);
+extern long keyctl_instantiate_key_iov(key_serial_t,
+				       const struct iovec __user *,
+				       unsigned, key_serial_t);
+
+extern long keyctl_instantiate_key_common(key_serial_t,
+					  const struct iovec __user *,
+					  unsigned, size_t, key_serial_t);
 
 /*
  * Debugging key validation
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 0d7b1946ff94..427fddcaeb19 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -912,6 +912,21 @@ static int keyctl_change_reqkey_auth(struct key *key)
 	return commit_creds(new);
 }
 
+/*
+ * Copy the iovec data from userspace
+ */
+static long copy_from_user_iovec(void *buffer, const struct iovec *iov,
+				 unsigned ioc)
+{
+	for (; ioc > 0; ioc--) {
+		if (copy_from_user(buffer, iov->iov_base, iov->iov_len) != 0)
+			return -EFAULT;
+		buffer += iov->iov_len;
+		iov++;
+	}
+	return 0;
+}
+
 /*
  * Instantiate a key with the specified payload and link the key into the
  * destination keyring if one is given.
@@ -921,10 +936,11 @@ static int keyctl_change_reqkey_auth(struct key *key)
  *
  * If successful, 0 will be returned.
  */
-long keyctl_instantiate_key(key_serial_t id,
-			    const void __user *_payload,
-			    size_t plen,
-			    key_serial_t ringid)
+long keyctl_instantiate_key_common(key_serial_t id,
+				   const struct iovec *payload_iov,
+				   unsigned ioc,
+				   size_t plen,
+				   key_serial_t ringid)
 {
 	const struct cred *cred = current_cred();
 	struct request_key_auth *rka;
@@ -953,7 +969,7 @@ long keyctl_instantiate_key(key_serial_t id,
 	/* pull the payload in if one was supplied */
 	payload = NULL;
 
-	if (_payload) {
+	if (payload_iov) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
 		if (!payload) {
@@ -965,8 +981,8 @@ long keyctl_instantiate_key(key_serial_t id,
 				goto error;
 		}
 
-		ret = -EFAULT;
-		if (copy_from_user(payload, _payload, plen) != 0)
+		ret = copy_from_user_iovec(payload, payload_iov, ioc);
+		if (ret < 0)
 			goto error2;
 	}
 
@@ -996,6 +1012,72 @@ error:
 	return ret;
 }
 
+/*
+ * Instantiate a key with the specified payload and link the key into the
+ * destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_instantiate_key(key_serial_t id,
+			    const void __user *_payload,
+			    size_t plen,
+			    key_serial_t ringid)
+{
+	if (_payload && plen) {
+		struct iovec iov[1] = {
+			[0].iov_base = (void __user *)_payload,
+			[0].iov_len  = plen
+		};
+
+		return keyctl_instantiate_key_common(id, iov, 1, plen, ringid);
+	}
+
+	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
+}
+
+/*
+ * Instantiate a key with the specified multipart payload and link the key into
+ * the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_instantiate_key_iov(key_serial_t id,
+				const struct iovec __user *_payload_iov,
+				unsigned ioc,
+				key_serial_t ringid)
+{
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	long ret;
+
+	if (_payload_iov == 0 || ioc == 0)
+		goto no_payload;
+
+	ret = rw_copy_check_uvector(WRITE, _payload_iov, ioc,
+				    ARRAY_SIZE(iovstack), iovstack, &iov);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		goto no_payload_free;
+
+	ret = keyctl_instantiate_key_common(id, iov, ioc, ret, ringid);
+
+	if (iov != iovstack)
+		kfree(iov);
+	return ret;
+
+no_payload_free:
+	if (iov != iovstack)
+		kfree(iov);
+no_payload:
+	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
+}
+
 /*
  * Negatively instantiate the key with the given timeout (in seconds) and link
  * the key into the destination keyring if one is given.
@@ -1528,6 +1610,13 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
 					 (unsigned) arg4,
 					 (key_serial_t) arg5);
 
+	case KEYCTL_INSTANTIATE_IOV:
+		return keyctl_instantiate_key_iov(
+			(key_serial_t) arg2,
+			(const struct iovec __user *) arg3,
+			(unsigned) arg4,
+			(key_serial_t) arg5);
+
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 6247e086188dd2ba5bfd64f9a876fe42b0cf39fb Mon Sep 17 00:00:00 2001
From: Yi Zou <yi.zou@intel.com>
Date: Tue, 1 Feb 2011 07:22:06 +0000
Subject: net: add ndo_fcoe_ddp_target() to support FCoE DDP in target mode

The Fiber Channel over Ethernet (FCoE) Direct Data Placement (DDP) can also be
used for FCoE target, where the DDP used for read I/O on an initiator can be
used on an FCoE target to speed up the write I/O to the target from the initiator.
The added ndo_fcoe_ddp_target() works in the similar way as the existing
ndo_fcoe_ddp_setup() to allow the underlying hardware set up the DDP context
accordingly when it gets called from the FCoE target implementation on top
the existing Open-FCoE fcoe/libfc protocol stack so without losing the ability
to provide DDP for read I/O as an initiator, it can also provide DDP offload
to the write I/O coming from the initiator as a target.

Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/netdevice.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 71563e7b2bfb..6bd5d460b7c1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -871,6 +871,10 @@ struct net_device_ops {
 						      unsigned int sgc);
 	int			(*ndo_fcoe_ddp_done)(struct net_device *dev,
 						     u16 xid);
+	int			(*ndo_fcoe_ddp_target)(struct net_device *dev,
+						       u16 xid,
+						       struct scatterlist *sgl,
+						       unsigned int sgc);
 #define NETDEV_FCOE_WWNN 0
 #define NETDEV_FCOE_WWPN 1
 	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
-- 
cgit v1.2.3


From 1fc050a13473348f5c439de2bb41c8e92dba5588 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 7 Mar 2011 20:54:48 -0800
Subject: ipv4: Cache source address in nexthop entries.

When doing output route lookups, we have to select the source address
if the user has not specified an explicit one.

First, if the route has an explicit preferred source address
specified, then we use that.

Otherwise we search the route's outgoing interface for a suitable
address.

This search can be precomputed and cached at route insertion time.

The only missing part is that we have to refresh this precomputed
value any time addresses are added or removed from the interface, and
this is accomplished by fib_update_nh_saddrs().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  7 +++++--
 net/ipv4/fib_frontend.c  |  2 ++
 net/ipv4/fib_semantics.c | 31 ++++++++++++++++++++++++-------
 3 files changed, 31 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 523a170b0ecb..0e140830b85a 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -60,6 +60,7 @@ struct fib_nh {
 #endif
 	int			nh_oif;
 	__be32			nh_gw;
+	__be32			nh_saddr;
 };
 
 /*
@@ -139,11 +140,13 @@ struct fib_result_nl {
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
-#define FIB_RES_PREFSRC(res)		((res).fi->fib_prefsrc ? : __fib_res_prefsrc(&res))
+#define FIB_RES_SADDR(res)		(FIB_RES_NH(res).nh_saddr)
 #define FIB_RES_GW(res)			(FIB_RES_NH(res).nh_gw)
 #define FIB_RES_DEV(res)		(FIB_RES_NH(res).nh_dev)
 #define FIB_RES_OIF(res)		(FIB_RES_NH(res).nh_oif)
 
+#define FIB_RES_PREFSRC(res)		((res).fi->fib_prefsrc ? : FIB_RES_SADDR(res))
+
 struct fib_table {
 	struct hlist_node tb_hlist;
 	u32		tb_id;
@@ -224,8 +227,8 @@ extern void fib_select_default(struct fib_result *res);
 extern int ip_fib_check_default(__be32 gw, struct net_device *dev);
 extern int fib_sync_down_dev(struct net_device *dev, int force);
 extern int fib_sync_down_addr(struct net *net, __be32 local);
+extern void fib_update_nh_saddrs(struct net_device *dev);
 extern int fib_sync_up(struct net_device *dev);
-extern __be32  __fib_res_prefsrc(struct fib_result *res);
 extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res);
 
 /* Exported by fib_trie.c */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ad0778a3fa53..1d2233cd99e6 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -890,10 +890,12 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		fib_sync_up(dev);
 #endif
+		fib_update_nh_saddrs(dev);
 		rt_cache_flush(dev_net(dev), -1);
 		break;
 	case NETDEV_DOWN:
 		fib_del_ifaddr(ifa);
+		fib_update_nh_saddrs(dev);
 		if (ifa->ifa_dev->ifa_list == NULL) {
 			/* Last address was deleted from this interface.
 			 * Disable IP.
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 6349a21692ec..952c737f2a27 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -853,6 +853,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 				goto err_inval;
 	}
 
+	change_nexthops(fi) {
+		nexthop_nh->nh_saddr = inet_select_addr(nexthop_nh->nh_dev,
+							nexthop_nh->nh_gw,
+							nexthop_nh->nh_scope);
+	} endfor_nexthops(fi)
+
 link_it:
 	ofi = fib_find_info(fi);
 	if (ofi) {
@@ -898,13 +904,6 @@ failure:
 	return ERR_PTR(err);
 }
 
-/* Find appropriate source address to this destination */
-
-__be32 __fib_res_prefsrc(struct fib_result *res)
-{
-	return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope);
-}
-
 int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 		  u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
 		  struct fib_info *fi, unsigned int flags)
@@ -1128,6 +1127,24 @@ out:
 	return;
 }
 
+void fib_update_nh_saddrs(struct net_device *dev)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct fib_nh *nh;
+	unsigned int hash;
+
+	hash = fib_devindex_hashfn(dev->ifindex);
+	head = &fib_info_devhash[hash];
+	hlist_for_each_entry(nh, node, head, nh_hash) {
+		if (nh->nh_dev != dev)
+			continue;
+		nh->nh_saddr = inet_select_addr(nh->nh_dev,
+						nh->nh_gw,
+						nh->nh_scope);
+	}
+}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 /*
-- 
cgit v1.2.3


From dfef6dcd35cb4a251f6322ca9b2c06f0bb1aa1f4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 8 Mar 2011 01:25:28 -0500
Subject: unfuck proc_sysctl ->d_compare()

a) struct inode is not going to be freed under ->d_compare();
however, the thing PROC_I(inode)->sysctl points to just might.
Fortunately, it's enough to make freeing that sucker delayed,
provided that we don't step on its ->unregistering, clear
the pointer to it in PROC_I(inode) before dropping the reference
and check if it's NULL in ->d_compare().

b) I'm not sure that we *can* walk into NULL inode here (we recheck
dentry->seq between verifying that it's still hashed / fetching
dentry->d_inode and passing it to ->d_compare() and there's no
negative hashed dentries in /proc/sys/*), but if we can walk into
that, we really should not have ->d_compare() return 0 on it!
Said that, I really suspect that this check can be simply killed.
Nick?

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/inode.c        |  8 ++++++--
 fs/proc/proc_sysctl.c  |  7 +++++--
 include/linux/sysctl.h | 14 ++++++++++----
 kernel/sysctl.c        | 15 ++++++++++-----
 4 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 176ce4cda68a..d6a7ca1fdac5 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -27,6 +27,7 @@
 static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
+	struct ctl_table_header *head;
 
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
@@ -38,8 +39,11 @@ static void proc_evict_inode(struct inode *inode)
 	de = PROC_I(inode)->pde;
 	if (de)
 		pde_put(de);
-	if (PROC_I(inode)->sysctl)
-		sysctl_head_put(PROC_I(inode)->sysctl);
+	head = PROC_I(inode)->sysctl;
+	if (head) {
+		rcu_assign_pointer(PROC_I(inode)->sysctl, NULL);
+		sysctl_head_put(head);
+	}
 }
 
 struct vfsmount *proc_mnt;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 09a1f92a34ef..8eb2522111c5 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -408,15 +408,18 @@ static int proc_sys_compare(const struct dentry *parent,
 		const struct dentry *dentry, const struct inode *inode,
 		unsigned int len, const char *str, const struct qstr *name)
 {
+	struct ctl_table_header *head;
 	/* Although proc doesn't have negative dentries, rcu-walk means
 	 * that inode here can be NULL */
+	/* AV: can it, indeed? */
 	if (!inode)
-		return 0;
+		return 1;
 	if (name->len != len)
 		return 1;
 	if (memcmp(name->name, str, len))
 		return 1;
-	return !sysctl_is_seen(PROC_I(inode)->sysctl);
+	head = rcu_dereference(PROC_I(inode)->sysctl);
+	return !head || !sysctl_is_seen(head);
 }
 
 static const struct dentry_operations proc_sys_dentry_operations = {
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 7bb5cb64f3b8..bb7c2b086fa4 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -25,6 +25,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/rcupdate.h>
 
 struct completion;
 
@@ -1037,10 +1038,15 @@ struct ctl_table_root {
    struct ctl_table trees. */
 struct ctl_table_header
 {
-	struct ctl_table *ctl_table;
-	struct list_head ctl_entry;
-	int used;
-	int count;
+	union {
+		struct {
+			struct ctl_table *ctl_table;
+			struct list_head ctl_entry;
+			int used;
+			int count;
+		};
+		struct rcu_head rcu;
+	};
 	struct completion *unregistering;
 	struct ctl_table *ctl_table_arg;
 	struct ctl_table_root *root;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0f1bd83db985..4eed0af5d144 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write,
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
-	.count = 1,
+	{{.count = 1,
 	.ctl_table = root_table,
-	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
+	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
 	.root = &sysctl_table_root,
 	.set = &sysctl_table_root.default_set,
 };
@@ -1567,11 +1567,16 @@ void sysctl_head_get(struct ctl_table_header *head)
 	spin_unlock(&sysctl_lock);
 }
 
+static void free_head(struct rcu_head *rcu)
+{
+	kfree(container_of(rcu, struct ctl_table_header, rcu));
+}
+
 void sysctl_head_put(struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
 	if (!--head->count)
-		kfree(head);
+		call_rcu(&head->rcu, free_head);
 	spin_unlock(&sysctl_lock);
 }
 
@@ -1948,10 +1953,10 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 	start_unregistering(header);
 	if (!--header->parent->count) {
 		WARN_ON(1);
-		kfree(header->parent);
+		call_rcu(&header->parent->rcu, free_head);
 	}
 	if (!--header->count)
-		kfree(header);
+		call_rcu(&header->rcu, free_head);
 	spin_unlock(&sysctl_lock);
 }
 
-- 
cgit v1.2.3


From 997772884036e6e121de39322179989154437d9f Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Mon, 7 Mar 2011 09:58:33 +0100
Subject: debugobjects: Add hint for better object identification

In complex subsystems like mac80211 structures can contain several
timers and work structs, so identifying a specific instance from the
call trace and object type output of debugobjects can be hard.

Allow the subsystems which support debugobjects to provide a hint
function. This function returns a pointer to a kernel address
(preferrably the objects callback function) which is printed along
with the debugobjects type.

Add hint methods for timer_list, work_struct and hrtimer.

[ tglx: Massaged changelog, made it compile ]

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <20110307085809.GA9334@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/debugobjects.h | 5 ++++-
 kernel/hrtimer.c             | 6 ++++++
 kernel/timer.c               | 6 ++++++
 kernel/workqueue.c           | 6 ++++++
 lib/debugobjects.c           | 9 ++++++---
 5 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 597692f1fc8d..65970b811e22 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -34,7 +34,10 @@ struct debug_obj {
 
 /**
  * struct debug_obj_descr - object type specific debug description structure
+ *
  * @name:		name of the object typee
+ * @debug_hint:		function returning address, which have associated
+ *			kernel symbol, to allow identify the object
  * @fixup_init:		fixup function, which is called when the init check
  *			fails
  * @fixup_activate:	fixup function, which is called when the activate check
@@ -46,7 +49,7 @@ struct debug_obj {
  */
 struct debug_obj_descr {
 	const char		*name;
-
+	void *(*debug_hint)	(void *addr);
 	int (*fixup_init)	(void *addr, enum debug_obj_state state);
 	int (*fixup_activate)	(void *addr, enum debug_obj_state state);
 	int (*fixup_destroy)	(void *addr, enum debug_obj_state state);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c048615..e38f5a073d01 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -334,6 +334,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe);
 
 static struct debug_obj_descr hrtimer_debug_descr;
 
+static void *hrtimer_debug_hint(void *addr)
+{
+	return ((struct hrtimer *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -393,6 +398,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr hrtimer_debug_descr = {
 	.name		= "hrtimer",
+	.debug_hint	= hrtimer_debug_hint,
 	.fixup_init	= hrtimer_fixup_init,
 	.fixup_activate	= hrtimer_fixup_activate,
 	.fixup_free	= hrtimer_fixup_free,
diff --git a/kernel/timer.c b/kernel/timer.c
index d6459923d245..33a67925d900 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -404,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {}
 
 static struct debug_obj_descr timer_debug_descr;
 
+static void *timer_debug_hint(void *addr)
+{
+	return ((struct timer_list *) addr)->function;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -477,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr timer_debug_descr = {
 	.name		= "timer_list",
+	.debug_hint	= timer_debug_hint,
 	.fixup_init	= timer_fixup_init,
 	.fixup_activate	= timer_fixup_activate,
 	.fixup_free	= timer_fixup_free,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ee6578b578ad..b5fe4c00eb3c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -316,6 +316,11 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
 
 static struct debug_obj_descr work_debug_descr;
 
+static void *work_debug_hint(void *addr)
+{
+	return ((struct work_struct *) addr)->func;
+}
+
 /*
  * fixup_init is called when:
  * - an active object is initialized
@@ -387,6 +392,7 @@ static int work_fixup_free(void *addr, enum debug_obj_state state)
 
 static struct debug_obj_descr work_debug_descr = {
 	.name		= "work_struct",
+	.debug_hint	= work_debug_hint,
 	.fixup_init	= work_fixup_init,
 	.fixup_activate	= work_fixup_activate,
 	.fixup_free	= work_fixup_free,
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index deebcc57d4e6..9d86e45086f5 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -249,14 +249,17 @@ static struct debug_bucket *get_bucket(unsigned long addr)
 
 static void debug_print_object(struct debug_obj *obj, char *msg)
 {
+	struct debug_obj_descr *descr = obj->descr;
 	static int limit;
 
-	if (limit < 5 && obj->descr != descr_test) {
+	if (limit < 5 && descr != descr_test) {
+		void *hint = descr->debug_hint ?
+			descr->debug_hint(obj->object) : NULL;
 		limit++;
 		WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
-				 "object type: %s\n",
+				 "object type: %s hint: %pS\n",
 			msg, obj_states[obj->state], obj->astate,
-			obj->descr->name);
+			descr->name, hint);
 	}
 	debug_objects_warnings++;
 }
-- 
cgit v1.2.3


From ea7145477a461e09d8d194cac4b996dc4f449107 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Mon, 7 Mar 2011 19:10:39 +0100
Subject: x86: Separate out entry text section

Put x86 entry code into a separate link section: .entry.text.

Separating the entry text section seems to have performance
benefits - caused by more efficient instruction cache usage.

Running hackbench with perf stat --repeat showed that the change
compresses the icache footprint. The icache load miss rate went
down by about 15%:

 before patch:
         19417627  L1-icache-load-misses      ( +-   0.147% )

 after patch:
         16490788  L1-icache-load-misses      ( +-   0.180% )

The motivation of the patch was to fix a particular kprobes
bug that relates to the entry text section, the performance
advantage was discovered accidentally.

Whole perf output follows:

 - results for current tip tree:

  Performance counter stats for './hackbench/hackbench 10' (500 runs):

         19417627  L1-icache-load-misses      ( +-   0.147% )
       2676914223  instructions             #      0.497 IPC     ( +- 0.079% )
       5389516026  cycles                     ( +-   0.144% )

      0.206267711  seconds time elapsed   ( +-   0.138% )

 - results for current tip tree with the patch applied:

  Performance counter stats for './hackbench/hackbench 10' (500 runs):

         16490788  L1-icache-load-misses      ( +-   0.180% )
       2717734941  instructions             #      0.502 IPC     ( +- 0.079% )
       5414756975  cycles                     ( +-   0.148% )

      0.206747566  seconds time elapsed   ( +-   0.137% )

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: masami.hiramatsu.pt@hitachi.com
Cc: ananth@in.ibm.com
Cc: davem@davemloft.net
Cc: 2nddept-manager@sdl.hitachi.co.jp
LKML-Reference: <20110307181039.GB15197@jolsa.redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/ia32/ia32entry.S         | 2 ++
 arch/x86/kernel/entry_32.S        | 6 ++++--
 arch/x86/kernel/entry_64.S        | 6 ++++--
 arch/x86/kernel/vmlinux.lds.S     | 1 +
 include/asm-generic/sections.h    | 1 +
 include/asm-generic/vmlinux.lds.h | 6 ++++++
 6 files changed, 18 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 518bb99c3394..f729b2e9679c 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -25,6 +25,8 @@
 #define sysretl_audit ia32_ret_from_sys_call
 #endif
 
+	.section .entry.text, "ax"
+
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
 
 	.macro IA32_ARG_FIXUP noebp=0
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c8b4efad7ebb..f5accf8eaa78 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -65,6 +65,8 @@
 #define sysexit_audit	syscall_exit_work
 #endif
 
+	.section .entry.text, "ax"
+
 /*
  * We use macros for low-level operations which need to be overridden
  * for paravirtualization.  The following will never clobber any registers:
@@ -788,7 +790,7 @@ ENDPROC(ptregs_clone)
  */
 .section .init.rodata,"a"
 ENTRY(interrupt)
-.text
+.section .entry.text, "ax"
 	.p2align 5
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
@@ -807,7 +809,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .endif
       .previous
 	.long 1b
-      .text
+      .section .entry.text, "ax"
 vector=vector+1
     .endif
   .endr
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index aed1ffbeb0c9..0a0ed794edb2 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -61,6 +61,8 @@
 #define __AUDIT_ARCH_LE	   0x40000000
 
 	.code64
+	.section .entry.text, "ax"
+
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
@@ -744,7 +746,7 @@ END(stub_rt_sigreturn)
  */
 	.section .init.rodata,"a"
 ENTRY(interrupt)
-	.text
+	.section .entry.text
 	.p2align 5
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
@@ -763,7 +765,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .endif
       .previous
 	.quad 1b
-      .text
+      .section .entry.text
 vector=vector+1
     .endif
   .endr
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bf4700755184..6d4341d5c52a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -105,6 +105,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		ENTRY_TEXT
 		IRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index b3bfabc258f3..c1a1216e29ce 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -11,6 +11,7 @@ extern char _sinittext[], _einittext[];
 extern char _end[];
 extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index fe77e3395b40..906c3ceca9a2 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -424,6 +424,12 @@
 		*(.kprobes.text)					\
 		VMLINUX_SYMBOL(__kprobes_text_end) = .;
 
+#define ENTRY_TEXT							\
+		ALIGN_FUNCTION();					\
+		VMLINUX_SYMBOL(__entry_text_start) = .;			\
+		*(.entry.text)						\
+		VMLINUX_SYMBOL(__entry_text_end) = .;
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define IRQENTRY_TEXT							\
 		ALIGN_FUNCTION();					\
-- 
cgit v1.2.3


From a7ac8fc1d8d26c975c460a69aa7b9d5b5d5d29b0 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 8 Mar 2011 11:03:21 -0800
Subject: ipv4: Fix scope value used in route src-address caching.

We have to use cfg->fc_scope not the final nh_scope value.

Reported-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 1 +
 net/ipv4/fib_semantics.c | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 0e140830b85a..3f6c943faedc 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -51,6 +51,7 @@ struct fib_nh {
 	struct fib_info		*nh_parent;
 	unsigned		nh_flags;
 	unsigned char		nh_scope;
+	unsigned char		nh_cfg_scope;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			nh_weight;
 	int			nh_power;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 952c737f2a27..d73d7581b51f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -854,9 +854,10 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	}
 
 	change_nexthops(fi) {
+		nexthop_nh->nh_cfg_scope = cfg->fc_scope;
 		nexthop_nh->nh_saddr = inet_select_addr(nexthop_nh->nh_dev,
 							nexthop_nh->nh_gw,
-							nexthop_nh->nh_scope);
+							nexthop_nh->nh_cfg_scope);
 	} endfor_nexthops(fi)
 
 link_it:
@@ -1141,7 +1142,7 @@ void fib_update_nh_saddrs(struct net_device *dev)
 			continue;
 		nh->nh_saddr = inet_select_addr(nh->nh_dev,
 						nh->nh_gw,
-						nh->nh_scope);
+						nh->nh_cfg_scope);
 	}
 }
 
-- 
cgit v1.2.3


From 51de69523ffe1c17994dc2f260369f29dfdce71c Mon Sep 17 00:00:00 2001
From: Owen Smith <owen.smith@citrix.com>
Date: Wed, 22 Dec 2010 15:05:00 +0000
Subject: xen: Union the blkif_request request specific fields

Prepare for extending the block device ring to allow request
specific fields, by moving the request specific fields for
reads, writes and barrier requests to a union member.

Acked-by: Jens Axboe <jaxboe@fusionio.com>
Signed-off-by: Owen Smith <owen.smith@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/block/xen-blkfront.c     |  8 ++++----
 include/xen/interface/io/blkif.h | 16 +++++++++++-----
 2 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d7aa39e349a6..cc4514c9d8a6 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -281,7 +281,7 @@ static int blkif_queue_request(struct request *req)
 	info->shadow[id].request = req;
 
 	ring_req->id = id;
-	ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
+	ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
 	ring_req->handle = info->handle;
 
 	ring_req->operation = rq_data_dir(req) ?
@@ -317,7 +317,7 @@ static int blkif_queue_request(struct request *req)
 				rq_data_dir(req) );
 
 		info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
-		ring_req->seg[i] =
+		ring_req->u.rw.seg[i] =
 				(struct blkif_request_segment) {
 					.gref       = ref,
 					.first_sect = fsect,
@@ -615,7 +615,7 @@ static void blkif_completion(struct blk_shadow *s)
 {
 	int i;
 	for (i = 0; i < s->req.nr_segments; i++)
-		gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL);
+		gnttab_end_foreign_access(s->req.u.rw.seg[i].gref, 0, 0UL);
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -932,7 +932,7 @@ static int blkif_recover(struct blkfront_info *info)
 		/* Rewrite any grant references invalidated by susp/resume. */
 		for (j = 0; j < req->nr_segments; j++)
 			gnttab_grant_foreign_access_ref(
-				req->seg[j].gref,
+				req->u.rw.seg[j].gref,
 				info->xbdev->otherend_id,
 				pfn_to_mfn(info->shadow[req->id].frame[j]),
 				rq_data_dir(info->shadow[req->id].request));
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index c2d1fa4dc1ee..e4f743cfa151 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -51,11 +51,7 @@ typedef uint64_t blkif_sector_t;
  */
 #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
 
-struct blkif_request {
-	uint8_t        operation;    /* BLKIF_OP_???                         */
-	uint8_t        nr_segments;  /* number of segments                   */
-	blkif_vdev_t   handle;       /* only for read/write requests         */
-	uint64_t       id;           /* private guest value, echoed in resp  */
+struct blkif_request_rw {
 	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
 	struct blkif_request_segment {
 		grant_ref_t gref;        /* reference to I/O buffer frame        */
@@ -65,6 +61,16 @@ struct blkif_request {
 	} seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 };
 
+struct blkif_request {
+	uint8_t        operation;    /* BLKIF_OP_???                         */
+	uint8_t        nr_segments;  /* number of segments                   */
+	blkif_vdev_t   handle;       /* only for read/write requests         */
+	uint64_t       id;           /* private guest value, echoed in resp  */
+	union {
+		struct blkif_request_rw rw;
+	} u;
+};
+
 struct blkif_response {
 	uint64_t        id;              /* copied from request */
 	uint8_t         operation;       /* copied from request */
-- 
cgit v1.2.3


From 750912fa366312e9c5bc83eab352898a26750401 Mon Sep 17 00:00:00 2001
From: David Sharp <dhsharp@google.com>
Date: Wed, 8 Dec 2010 13:46:47 -0800
Subject: tracing: Add an 'overwrite' trace_option.

Add an "overwrite" trace_option for ftrace to control whether the buffer should
be overwritten on overflow or not. The default remains to overwrite old events
when the buffer is full. This patch adds the option to instead discard newest
events when the buffer is full. This is useful to get a snapshot of traces just
after enabling traces. Dropping the current event is also a simpler code path.

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291844807-15481-1-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/trace/ftrace.txt |  5 +++++
 include/linux/ring_buffer.h    |  2 ++
 kernel/trace/ring_buffer.c     | 11 +++++++++++
 kernel/trace/trace.c           | 17 +++++++++++------
 kernel/trace/trace.h           |  1 +
 5 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 67f1cc473257..1ebc24cf9a55 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -454,6 +454,11 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
                    latencies, as described in "Latency
                    trace format".
 
+  overwrite - This controls what happens when the trace buffer is
+              full. If "1" (default), the oldest events are
+              discarded and overwritten. If "0", then the newest
+              events are discarded.
+
 ftrace_enabled
 --------------
 
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8d3a2486544d..ab38ac80b0f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
+
 struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
 						   unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd1c35a4fbcc..269db80a961e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1429,6 +1429,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+	mutex_lock(&buffer->mutex);
+	if (val)
+		buffer->flags |= RB_FL_OVERWRITE;
+	else
+		buffer->flags &= ~RB_FL_OVERWRITE;
+	mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8dc8da6733f9..85e3ee1e474e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,8 +41,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-#define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
@@ -340,7 +338,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
 
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +423,7 @@ static const char *trace_options[] = {
 	"sleep-time",
 	"graph-time",
 	"record-cmd",
+	"overwrite",
 	NULL
 };
 
@@ -2529,6 +2528,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
+
+	if (mask == TRACE_ITER_OVERWRITE)
+		ring_buffer_change_overwrite(global_trace.buffer, enabled);
 }
 
 static ssize_t
@@ -4555,9 +4557,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 __init static int tracer_alloc_buffers(void)
 {
 	int ring_buf_size;
+	enum ring_buffer_flags rb_flags;
 	int i;
 	int ret = -ENOMEM;
 
+
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;
 
@@ -4570,12 +4574,13 @@ __init static int tracer_alloc_buffers(void)
 	else
 		ring_buf_size = 1;
 
+	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
-	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
-						   TRACE_BUFFER_FLAGS);
+	global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
 	if (!global_trace.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
@@ -4585,7 +4590,7 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+	max_tr.buffer = ring_buffer_alloc(1, rb_flags);
 	if (!max_tr.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
 		WARN_ON(1);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 856e73cc1d3f..951d0b7e7062 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -606,6 +606,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_SLEEP_TIME		= 0x40000,
 	TRACE_ITER_GRAPH_TIME		= 0x80000,
 	TRACE_ITER_RECORD_CMD		= 0x100000,
+	TRACE_ITER_OVERWRITE		= 0x200000,
 };
 
 /*
-- 
cgit v1.2.3


From f44f7f96a20af16f6f12e1c995576d6becf5f57b Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 21 Feb 2011 22:58:51 -0800
Subject: RTC: Initialize kernel state from RTC

Mark Brown pointed out a corner case: that RTC alarms should
be allowed to be persistent across reboots if the hardware
supported it.

The rework of the generic layer to virtualize the RTC alarm
virtualized much of the alarm handling, and removed the
code used to read the alarm time from the hardware.

Mark noted if we want the alarm to be persistent across
reboots, we need to re-read the alarm value into the
virtualized generic layer at boot up, so that the generic
layer properly exposes that value.

This patch restores much of the earlier removed
rtc_read_alarm code and wires it in so that we
set the kernel's alarm value to what we find in the
hardware at boot time.

NOTE: Not all hardware supports persistent RTC alarm state across
system reset. rtc-cmos for example will keep the alarm time, but
disables the AIE mode irq. Applications should not expect the RTC
alarm to be valid after a system reset. We will preserve what
we can, to represent the hardware state at boot, but its not
guarenteed.

Further, in the future, with multiplexed RTC alarms, the
soonest alarm to fire may not be the one set via the /dev/rt
ioctls. So an application may set the alarm with RTC_ALM_SET,
but after a reset find that RTC_ALM_READ returns an earlier
time. Again, we preserve what we can, but applications should
not expect the RTC alarm state to persist across a system reset.

Big thanks to Mark for pointing out the issue!
Thanks also to Marcelo for helping think through the solution.

CC: Mark Brown <broonie@opensource.wolfsonmicro.com>
CC: Marcelo Roberto Jimenez <mroberto@cpti.cetuc.puc-rio.br>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alessandro Zummo <a.zummo@towertech.it>
CC: rtc-linux@googlegroups.com
Reported-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/class.c     |   7 ++
 drivers/rtc/interface.c | 180 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/rtc.h     |   1 +
 3 files changed, 188 insertions(+)

(limited to 'include')

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index c404b61386bf..09b4437b3e61 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -117,6 +117,7 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev,
 					struct module *owner)
 {
 	struct rtc_device *rtc;
+	struct rtc_wkalrm alrm;
 	int id, err;
 
 	if (idr_pre_get(&rtc_idr, GFP_KERNEL) == 0) {
@@ -166,6 +167,12 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev,
 	rtc->pie_timer.function = rtc_pie_update_irq;
 	rtc->pie_enabled = 0;
 
+	/* Check to see if there is an ALARM already set in hw */
+	err = __rtc_read_alarm(rtc, &alrm);
+
+	if (!err && !rtc_valid_tm(&alrm.time))
+		rtc_set_alarm(rtc, &alrm);
+
 	strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE);
 	dev_set_name(&rtc->dev, "rtc%d", id);
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index cb2f0728fd70..8ec6b069a7f5 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -116,6 +116,186 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs)
 }
 EXPORT_SYMBOL_GPL(rtc_set_mmss);
 
+static int rtc_read_alarm_internal(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+	int err;
+
+	err = mutex_lock_interruptible(&rtc->ops_lock);
+	if (err)
+		return err;
+
+	if (rtc->ops == NULL)
+		err = -ENODEV;
+	else if (!rtc->ops->read_alarm)
+		err = -EINVAL;
+	else {
+		memset(alarm, 0, sizeof(struct rtc_wkalrm));
+		err = rtc->ops->read_alarm(rtc->dev.parent, alarm);
+	}
+
+	mutex_unlock(&rtc->ops_lock);
+	return err;
+}
+
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+	int err;
+	struct rtc_time before, now;
+	int first_time = 1;
+	unsigned long t_now, t_alm;
+	enum { none, day, month, year } missing = none;
+	unsigned days;
+
+	/* The lower level RTC driver may return -1 in some fields,
+	 * creating invalid alarm->time values, for reasons like:
+	 *
+	 *   - The hardware may not be capable of filling them in;
+	 *     many alarms match only on time-of-day fields, not
+	 *     day/month/year calendar data.
+	 *
+	 *   - Some hardware uses illegal values as "wildcard" match
+	 *     values, which non-Linux firmware (like a BIOS) may try
+	 *     to set up as e.g. "alarm 15 minutes after each hour".
+	 *     Linux uses only oneshot alarms.
+	 *
+	 * When we see that here, we deal with it by using values from
+	 * a current RTC timestamp for any missing (-1) values.  The
+	 * RTC driver prevents "periodic alarm" modes.
+	 *
+	 * But this can be racey, because some fields of the RTC timestamp
+	 * may have wrapped in the interval since we read the RTC alarm,
+	 * which would lead to us inserting inconsistent values in place
+	 * of the -1 fields.
+	 *
+	 * Reading the alarm and timestamp in the reverse sequence
+	 * would have the same race condition, and not solve the issue.
+	 *
+	 * So, we must first read the RTC timestamp,
+	 * then read the RTC alarm value,
+	 * and then read a second RTC timestamp.
+	 *
+	 * If any fields of the second timestamp have changed
+	 * when compared with the first timestamp, then we know
+	 * our timestamp may be inconsistent with that used by
+	 * the low-level rtc_read_alarm_internal() function.
+	 *
+	 * So, when the two timestamps disagree, we just loop and do
+	 * the process again to get a fully consistent set of values.
+	 *
+	 * This could all instead be done in the lower level driver,
+	 * but since more than one lower level RTC implementation needs it,
+	 * then it's probably best best to do it here instead of there..
+	 */
+
+	/* Get the "before" timestamp */
+	err = rtc_read_time(rtc, &before);
+	if (err < 0)
+		return err;
+	do {
+		if (!first_time)
+			memcpy(&before, &now, sizeof(struct rtc_time));
+		first_time = 0;
+
+		/* get the RTC alarm values, which may be incomplete */
+		err = rtc_read_alarm_internal(rtc, alarm);
+		if (err)
+			return err;
+
+		/* full-function RTCs won't have such missing fields */
+		if (rtc_valid_tm(&alarm->time) == 0)
+			return 0;
+
+		/* get the "after" timestamp, to detect wrapped fields */
+		err = rtc_read_time(rtc, &now);
+		if (err < 0)
+			return err;
+
+		/* note that tm_sec is a "don't care" value here: */
+	} while (   before.tm_min   != now.tm_min
+		 || before.tm_hour  != now.tm_hour
+		 || before.tm_mon   != now.tm_mon
+		 || before.tm_year  != now.tm_year);
+
+	/* Fill in the missing alarm fields using the timestamp; we
+	 * know there's at least one since alarm->time is invalid.
+	 */
+	if (alarm->time.tm_sec == -1)
+		alarm->time.tm_sec = now.tm_sec;
+	if (alarm->time.tm_min == -1)
+		alarm->time.tm_min = now.tm_min;
+	if (alarm->time.tm_hour == -1)
+		alarm->time.tm_hour = now.tm_hour;
+
+	/* For simplicity, only support date rollover for now */
+	if (alarm->time.tm_mday == -1) {
+		alarm->time.tm_mday = now.tm_mday;
+		missing = day;
+	}
+	if (alarm->time.tm_mon == -1) {
+		alarm->time.tm_mon = now.tm_mon;
+		if (missing == none)
+			missing = month;
+	}
+	if (alarm->time.tm_year == -1) {
+		alarm->time.tm_year = now.tm_year;
+		if (missing == none)
+			missing = year;
+	}
+
+	/* with luck, no rollover is needed */
+	rtc_tm_to_time(&now, &t_now);
+	rtc_tm_to_time(&alarm->time, &t_alm);
+	if (t_now < t_alm)
+		goto done;
+
+	switch (missing) {
+
+	/* 24 hour rollover ... if it's now 10am Monday, an alarm that
+	 * that will trigger at 5am will do so at 5am Tuesday, which
+	 * could also be in the next month or year.  This is a common
+	 * case, especially for PCs.
+	 */
+	case day:
+		dev_dbg(&rtc->dev, "alarm rollover: %s\n", "day");
+		t_alm += 24 * 60 * 60;
+		rtc_time_to_tm(t_alm, &alarm->time);
+		break;
+
+	/* Month rollover ... if it's the 31th, an alarm on the 3rd will
+	 * be next month.  An alarm matching on the 30th, 29th, or 28th
+	 * may end up in the month after that!  Many newer PCs support
+	 * this type of alarm.
+	 */
+	case month:
+		dev_dbg(&rtc->dev, "alarm rollover: %s\n", "month");
+		do {
+			if (alarm->time.tm_mon < 11)
+				alarm->time.tm_mon++;
+			else {
+				alarm->time.tm_mon = 0;
+				alarm->time.tm_year++;
+			}
+			days = rtc_month_days(alarm->time.tm_mon,
+					alarm->time.tm_year);
+		} while (days < alarm->time.tm_mday);
+		break;
+
+	/* Year rollover ... easy except for leap years! */
+	case year:
+		dev_dbg(&rtc->dev, "alarm rollover: %s\n", "year");
+		do {
+			alarm->time.tm_year++;
+		} while (rtc_valid_tm(&alarm->time) != 0);
+		break;
+
+	default:
+		dev_warn(&rtc->dev, "alarm rollover not handled\n");
+	}
+
+done:
+	return 0;
+}
+
 int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 {
 	int err;
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 89c3e5182991..db3832d5f280 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -227,6 +227,7 @@ extern void rtc_device_unregister(struct rtc_device *rtc);
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs);
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm);
 extern int rtc_read_alarm(struct rtc_device *rtc,
 			struct rtc_wkalrm *alrm);
 extern int rtc_set_alarm(struct rtc_device *rtc,
-- 
cgit v1.2.3


From 80d4bb515b78f38738f3378fd1be6039063ab040 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 3 Feb 2011 11:34:50 -0800
Subject: RTC: Cleanup rtc_class_ops->irq_set_state

With PIE mode interrupts now emulated in generic code via an hrtimer,
no one calls rtc_class_ops->irq_set_state(), so this patch removes it
along with driver implementations.

CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alessandro Zummo <a.zummo@towertech.it>
CC: Marcelo Roberto Jimenez <mroberto@cpti.cetuc.puc-rio.br>
CC: rtc-linux@googlegroups.com
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/rtc-cmos.c    | 20 --------------------
 drivers/rtc/rtc-davinci.c | 34 ----------------------------------
 drivers/rtc/rtc-mrst.c    | 20 --------------------
 drivers/rtc/rtc-pl031.c   | 34 ----------------------------------
 drivers/rtc/rtc-pxa.c     | 13 -------------
 drivers/rtc/rtc-rx8025.c  | 25 -------------------------
 drivers/rtc/rtc-s3c.c     | 32 --------------------------------
 drivers/rtc/rtc-sa1100.c  | 18 ------------------
 drivers/rtc/rtc-sh.c      |  1 -
 drivers/rtc/rtc-vr41xx.c  | 11 -----------
 include/linux/rtc.h       |  1 -
 11 files changed, 209 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index c7ff8df347e7..de632e793d46 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -400,25 +400,6 @@ static int cmos_irq_set_freq(struct device *dev, int freq)
 	return 0;
 }
 
-static int cmos_irq_set_state(struct device *dev, int enabled)
-{
-	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
-	unsigned long	flags;
-
-	if (!is_valid_irq(cmos->irq))
-		return -ENXIO;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	if (enabled)
-		cmos_irq_enable(cmos, RTC_PIE);
-	else
-		cmos_irq_disable(cmos, RTC_PIE);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return 0;
-}
-
 static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -502,7 +483,6 @@ static const struct rtc_class_ops cmos_rtc_ops = {
 	.set_alarm		= cmos_set_alarm,
 	.proc			= cmos_procfs,
 	.irq_set_freq		= cmos_irq_set_freq,
-	.irq_set_state		= cmos_irq_set_state,
 	.alarm_irq_enable	= cmos_alarm_irq_enable,
 	.update_irq_enable	= cmos_update_irq_enable,
 };
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index 34647fc1ee98..92da73d40e13 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -473,39 +473,6 @@ static int davinci_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 	return 0;
 }
 
-static int davinci_rtc_irq_set_state(struct device *dev, int enabled)
-{
-	struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
-	unsigned long flags;
-	u8 rtc_ctrl;
-
-	spin_lock_irqsave(&davinci_rtc_lock, flags);
-
-	rtc_ctrl = rtcss_read(davinci_rtc, PRTCSS_RTC_CTRL);
-
-	if (enabled) {
-		while (rtcss_read(davinci_rtc, PRTCSS_RTC_CTRL)
-		       & PRTCSS_RTC_CTRL_WDTBUS)
-			cpu_relax();
-
-		rtc_ctrl |= PRTCSS_RTC_CTRL_TE;
-		rtcss_write(davinci_rtc, rtc_ctrl, PRTCSS_RTC_CTRL);
-
-		rtcss_write(davinci_rtc, 0x0, PRTCSS_RTC_CLKC_CNT);
-
-		rtc_ctrl |= PRTCSS_RTC_CTRL_TIEN |
-			    PRTCSS_RTC_CTRL_TMMD |
-			    PRTCSS_RTC_CTRL_TMRFLG;
-	} else
-		rtc_ctrl &= ~PRTCSS_RTC_CTRL_TIEN;
-
-	rtcss_write(davinci_rtc, rtc_ctrl, PRTCSS_RTC_CTRL);
-
-	spin_unlock_irqrestore(&davinci_rtc_lock, flags);
-
-	return 0;
-}
-
 static int davinci_rtc_irq_set_freq(struct device *dev, int freq)
 {
 	struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
@@ -529,7 +496,6 @@ static struct rtc_class_ops davinci_rtc_ops = {
 	.alarm_irq_enable	= davinci_rtc_alarm_irq_enable,
 	.read_alarm		= davinci_rtc_read_alarm,
 	.set_alarm		= davinci_rtc_set_alarm,
-	.irq_set_state		= davinci_rtc_irq_set_state,
 	.irq_set_freq		= davinci_rtc_irq_set_freq,
 };
 
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index 1db62db8469d..4db96fa306fc 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -236,25 +236,6 @@ static int mrst_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
-static int mrst_irq_set_state(struct device *dev, int enabled)
-{
-	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
-	unsigned long	flags;
-
-	if (!mrst->irq)
-		return -ENXIO;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	if (enabled)
-		mrst_irq_enable(mrst, RTC_PIE);
-	else
-		mrst_irq_disable(mrst, RTC_PIE);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return 0;
-}
-
 /* Currently, the vRTC doesn't support UIE ON/OFF */
 static int mrst_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
@@ -301,7 +282,6 @@ static const struct rtc_class_ops mrst_rtc_ops = {
 	.read_alarm	= mrst_read_alarm,
 	.set_alarm	= mrst_set_alarm,
 	.proc		= mrst_procfs,
-	.irq_set_state	= mrst_irq_set_state,
 	.alarm_irq_enable = mrst_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index b7a6690e5b35..0e7c15b24c1c 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -293,38 +293,6 @@ static int pl031_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	return ret;
 }
 
-/* Periodic interrupt is only available in ST variants. */
-static int pl031_irq_set_state(struct device *dev, int enabled)
-{
-	struct pl031_local *ldata = dev_get_drvdata(dev);
-
-	if (enabled == 1) {
-		/* Clear any pending timer interrupt. */
-		writel(RTC_BIT_PI, ldata->base + RTC_ICR);
-
-		writel(readl(ldata->base + RTC_IMSC) | RTC_BIT_PI,
-			ldata->base + RTC_IMSC);
-
-		/* Now start the timer */
-		writel(readl(ldata->base + RTC_TCR) | RTC_TCR_EN,
-			ldata->base + RTC_TCR);
-
-	} else {
-		writel(readl(ldata->base + RTC_IMSC) & (~RTC_BIT_PI),
-			ldata->base + RTC_IMSC);
-
-		/* Also stop the timer */
-		writel(readl(ldata->base + RTC_TCR) & (~RTC_TCR_EN),
-			ldata->base + RTC_TCR);
-	}
-	/* Wait at least 1 RTC32 clock cycle to ensure next access
-	 * to RTC_TCR will succeed.
-	 */
-	udelay(40);
-
-	return 0;
-}
-
 static int pl031_irq_set_freq(struct device *dev, int freq)
 {
 	struct pl031_local *ldata = dev_get_drvdata(dev);
@@ -440,7 +408,6 @@ static struct rtc_class_ops stv1_pl031_ops = {
 	.read_alarm = pl031_read_alarm,
 	.set_alarm = pl031_set_alarm,
 	.alarm_irq_enable = pl031_alarm_irq_enable,
-	.irq_set_state = pl031_irq_set_state,
 	.irq_set_freq = pl031_irq_set_freq,
 };
 
@@ -451,7 +418,6 @@ static struct rtc_class_ops stv2_pl031_ops = {
 	.read_alarm = pl031_stv2_read_alarm,
 	.set_alarm = pl031_stv2_set_alarm,
 	.alarm_irq_enable = pl031_alarm_irq_enable,
-	.irq_set_state = pl031_irq_set_state,
 	.irq_set_freq = pl031_irq_set_freq,
 };
 
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index 29e867a1aaa8..b216ae5389c8 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -223,18 +223,6 @@ static int pxa_periodic_irq_set_freq(struct device *dev, int freq)
 	return 0;
 }
 
-static int pxa_periodic_irq_set_state(struct device *dev, int enabled)
-{
-	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-
-	if (enabled)
-		rtsr_set_bits(pxa_rtc, RTSR_PIALE | RTSR_PICE);
-	else
-		rtsr_clear_bits(pxa_rtc, RTSR_PIALE | RTSR_PICE);
-
-	return 0;
-}
-
 static int pxa_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
@@ -348,7 +336,6 @@ static const struct rtc_class_ops pxa_rtc_ops = {
 	.alarm_irq_enable = pxa_alarm_irq_enable,
 	.update_irq_enable = pxa_update_irq_enable,
 	.proc = pxa_rtc_proc,
-	.irq_set_state = pxa_periodic_irq_set_state,
 	.irq_set_freq = pxa_periodic_irq_set_freq,
 };
 
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index af32a62e12a8..fde172fb2abe 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -424,37 +424,12 @@ static int rx8025_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int rx8025_irq_set_state(struct device *dev, int enabled)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct rx8025_data *rx8025 = i2c_get_clientdata(client);
-	int ctrl1;
-	int err;
-
-	if (client->irq <= 0)
-		return -ENXIO;
-
-	ctrl1 = rx8025->ctrl1 & ~RX8025_BIT_CTRL1_CT;
-	if (enabled)
-		ctrl1 |= RX8025_BIT_CTRL1_CT_1HZ;
-	if (ctrl1 != rx8025->ctrl1) {
-		rx8025->ctrl1 = ctrl1;
-		err = rx8025_write_reg(rx8025->client, RX8025_REG_CTRL1,
-				       rx8025->ctrl1);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 static struct rtc_class_ops rx8025_rtc_ops = {
 	.read_time = rx8025_get_time,
 	.set_time = rx8025_set_time,
 	.read_alarm = rx8025_read_alarm,
 	.set_alarm = rx8025_set_alarm,
 	.alarm_irq_enable = rx8025_alarm_irq_enable,
-	.irq_set_state  = rx8025_irq_set_state,
 };
 
 /*
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index b80fa2882408..80fb7e72f9d9 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -93,37 +93,6 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int s3c_rtc_setpie(struct device *dev, int enabled)
-{
-	unsigned int tmp;
-
-	pr_debug("%s: pie=%d\n", __func__, enabled);
-
-	spin_lock_irq(&s3c_rtc_pie_lock);
-
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
-		tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
-		tmp &= ~S3C64XX_RTCCON_TICEN;
-
-		if (enabled)
-			tmp |= S3C64XX_RTCCON_TICEN;
-
-		writew(tmp, s3c_rtc_base + S3C2410_RTCCON);
-	} else {
-		tmp = readb(s3c_rtc_base + S3C2410_TICNT);
-		tmp &= ~S3C2410_TICNT_ENABLE;
-
-		if (enabled)
-			tmp |= S3C2410_TICNT_ENABLE;
-
-		writeb(tmp, s3c_rtc_base + S3C2410_TICNT);
-	}
-
-	spin_unlock_irq(&s3c_rtc_pie_lock);
-
-	return 0;
-}
-
 static int s3c_rtc_setfreq(struct device *dev, int freq)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -380,7 +349,6 @@ static const struct rtc_class_ops s3c_rtcops = {
 	.read_alarm	= s3c_rtc_getalarm,
 	.set_alarm	= s3c_rtc_setalarm,
 	.irq_set_freq	= s3c_rtc_setfreq,
-	.irq_set_state	= s3c_rtc_setpie,
 	.proc		= s3c_rtc_proc,
 	.alarm_irq_enable = s3c_rtc_setaie,
 };
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index 5dfe5ffcb0d3..d47b3fc9830f 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -171,23 +171,6 @@ static int sa1100_irq_set_freq(struct device *dev, int freq)
 
 static int rtc_timer1_count;
 
-static int sa1100_irq_set_state(struct device *dev, int enabled)
-{
-	spin_lock_irq(&sa1100_rtc_lock);
-	if (enabled) {
-		struct rtc_device *rtc = (struct rtc_device *)dev;
-
-		OSMR1 = timer_freq / rtc->irq_freq + OSCR;
-		OIER |= OIER_E1;
-		rtc_timer1_count = 1;
-	} else {
-		OIER &= ~OIER_E1;
-	}
-	spin_unlock_irq(&sa1100_rtc_lock);
-
-	return 0;
-}
-
 static inline int sa1100_timer1_retrigger(struct rtc_device *rtc)
 {
 	unsigned long diff;
@@ -410,7 +393,6 @@ static const struct rtc_class_ops sa1100_rtc_ops = {
 	.set_alarm = sa1100_rtc_set_alarm,
 	.proc = sa1100_rtc_proc,
 	.irq_set_freq = sa1100_irq_set_freq,
-	.irq_set_state = sa1100_irq_set_state,
 	.alarm_irq_enable = sa1100_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index 93314a9e7fa9..ff50a8bc13f6 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -603,7 +603,6 @@ static struct rtc_class_ops sh_rtc_ops = {
 	.set_time	= sh_rtc_set_time,
 	.read_alarm	= sh_rtc_read_alarm,
 	.set_alarm	= sh_rtc_set_alarm,
-	.irq_set_state	= sh_rtc_irq_set_state,
 	.irq_set_freq	= sh_rtc_irq_set_freq,
 	.proc		= sh_rtc_proc,
 	.alarm_irq_enable = sh_rtc_alarm_irq_enable,
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index 769190ac6d11..86f14909f9db 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -227,16 +227,6 @@ static int vr41xx_rtc_irq_set_freq(struct device *dev, int freq)
 	return 0;
 }
 
-static int vr41xx_rtc_irq_set_state(struct device *dev, int enabled)
-{
-	if (enabled)
-		enable_irq(pie_irq);
-	else
-		disable_irq(pie_irq);
-
-	return 0;
-}
-
 static int vr41xx_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -309,7 +299,6 @@ static const struct rtc_class_ops vr41xx_rtc_ops = {
 	.read_alarm	= vr41xx_rtc_read_alarm,
 	.set_alarm	= vr41xx_rtc_set_alarm,
 	.irq_set_freq	= vr41xx_rtc_irq_set_freq,
-	.irq_set_state	= vr41xx_rtc_irq_set_state,
 };
 
 static int __devinit rtc_probe(struct platform_device *pdev)
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index db3832d5f280..0e2063acc260 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -148,7 +148,6 @@ struct rtc_class_ops {
 	int (*set_alarm)(struct device *, struct rtc_wkalrm *);
 	int (*proc)(struct device *, struct seq_file *);
 	int (*set_mmss)(struct device *, unsigned long secs);
-	int (*irq_set_state)(struct device *, int enabled);
 	int (*irq_set_freq)(struct device *, int freq);
 	int (*read_callback)(struct device *, int data);
 	int (*alarm_irq_enable)(struct device *, unsigned int enabled);
-- 
cgit v1.2.3


From 696160fec162601d06940862b5b3aa4460344c1b Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 3 Feb 2011 12:02:07 -0800
Subject: RTC: Cleanup rtc_class_ops->irq_set_freq()

With the generic rtc code now emulating PIE mode irqs via an
hrtimer, no one calls the rtc_class_ops->irq_set_freq call.

This patch removes the hook and deletes the driver functions
if no one else calls them.

CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alessandro Zummo <a.zummo@towertech.it>
CC: Marcelo Roberto Jimenez <mroberto@cpti.cetuc.puc-rio.br>
CC: rtc-linux@googlegroups.com
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/rtc-cmos.c    | 26 --------------------------
 drivers/rtc/rtc-davinci.c | 17 -----------------
 drivers/rtc/rtc-pl031.c   | 21 ---------------------
 drivers/rtc/rtc-pxa.c     | 15 ---------------
 drivers/rtc/rtc-s3c.c     |  1 -
 drivers/rtc/rtc-sa1100.c  |  1 -
 drivers/rtc/rtc-sh.c      |  1 -
 drivers/rtc/rtc-vr41xx.c  | 21 ---------------------
 include/linux/rtc.h       |  2 --
 9 files changed, 105 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index de632e793d46..bdb1f8e2042a 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -375,31 +375,6 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
-static int cmos_irq_set_freq(struct device *dev, int freq)
-{
-	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
-	int		f;
-	unsigned long	flags;
-
-	if (!is_valid_irq(cmos->irq))
-		return -ENXIO;
-
-	if (!is_power_of_2(freq))
-		return -EINVAL;
-	/* 0 = no irqs; 1 = 2^15 Hz ... 15 = 2^0 Hz */
-	f = ffs(freq);
-	if (f-- > 16)
-		return -EINVAL;
-	f = 16 - f;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	hpet_set_periodic_freq(freq);
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ | f, RTC_FREQ_SELECT);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return 0;
-}
-
 static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -482,7 +457,6 @@ static const struct rtc_class_ops cmos_rtc_ops = {
 	.read_alarm		= cmos_read_alarm,
 	.set_alarm		= cmos_set_alarm,
 	.proc			= cmos_procfs,
-	.irq_set_freq		= cmos_irq_set_freq,
 	.alarm_irq_enable	= cmos_alarm_irq_enable,
 	.update_irq_enable	= cmos_update_irq_enable,
 };
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index 92da73d40e13..dfd98a235ad1 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -473,22 +473,6 @@ static int davinci_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 	return 0;
 }
 
-static int davinci_rtc_irq_set_freq(struct device *dev, int freq)
-{
-	struct davinci_rtc *davinci_rtc = dev_get_drvdata(dev);
-	unsigned long flags;
-	u16 tmr_counter = (0x8000 >> (ffs(freq) - 1));
-
-	spin_lock_irqsave(&davinci_rtc_lock, flags);
-
-	rtcss_write(davinci_rtc, tmr_counter & 0xFF, PRTCSS_RTC_TMR0);
-	rtcss_write(davinci_rtc, (tmr_counter & 0xFF00) >> 8, PRTCSS_RTC_TMR1);
-
-	spin_unlock_irqrestore(&davinci_rtc_lock, flags);
-
-	return 0;
-}
-
 static struct rtc_class_ops davinci_rtc_ops = {
 	.ioctl			= davinci_rtc_ioctl,
 	.read_time		= davinci_rtc_read_time,
@@ -496,7 +480,6 @@ static struct rtc_class_ops davinci_rtc_ops = {
 	.alarm_irq_enable	= davinci_rtc_alarm_irq_enable,
 	.read_alarm		= davinci_rtc_read_alarm,
 	.set_alarm		= davinci_rtc_set_alarm,
-	.irq_set_freq		= davinci_rtc_irq_set_freq,
 };
 
 static int __init davinci_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index 0e7c15b24c1c..d829ea63c4fb 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -293,25 +293,6 @@ static int pl031_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	return ret;
 }
 
-static int pl031_irq_set_freq(struct device *dev, int freq)
-{
-	struct pl031_local *ldata = dev_get_drvdata(dev);
-
-	/* Cant set timer if it is already enabled */
-	if (readl(ldata->base + RTC_TCR) & RTC_TCR_EN) {
-		dev_err(dev, "can't change frequency while timer enabled\n");
-		return -EINVAL;
-	}
-
-	/* If self start bit in RTC_TCR is set timer will start here,
-	 * but we never set that bit. Instead we start the timer when
-	 * set_state is called with enabled == 1.
-	 */
-	writel(RTC_TIMER_FREQ / freq, ldata->base + RTC_TLR);
-
-	return 0;
-}
-
 static int pl031_remove(struct amba_device *adev)
 {
 	struct pl031_local *ldata = dev_get_drvdata(&adev->dev);
@@ -408,7 +389,6 @@ static struct rtc_class_ops stv1_pl031_ops = {
 	.read_alarm = pl031_read_alarm,
 	.set_alarm = pl031_set_alarm,
 	.alarm_irq_enable = pl031_alarm_irq_enable,
-	.irq_set_freq = pl031_irq_set_freq,
 };
 
 /* And the second ST derivative */
@@ -418,7 +398,6 @@ static struct rtc_class_ops stv2_pl031_ops = {
 	.read_alarm = pl031_stv2_read_alarm,
 	.set_alarm = pl031_stv2_set_alarm,
 	.alarm_irq_enable = pl031_alarm_irq_enable,
-	.irq_set_freq = pl031_irq_set_freq,
 };
 
 static struct amba_id pl031_ids[] = {
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index b216ae5389c8..a1fdc802598a 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -209,20 +209,6 @@ static void pxa_rtc_release(struct device *dev)
 	free_irq(pxa_rtc->irq_1Hz, dev);
 }
 
-static int pxa_periodic_irq_set_freq(struct device *dev, int freq)
-{
-	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-	int period_ms;
-
-	if (freq < 1 || freq > MAXFREQ_PERIODIC)
-		return -EINVAL;
-
-	period_ms = 1000 / freq;
-	rtc_writel(pxa_rtc, PIAR, period_ms);
-
-	return 0;
-}
-
 static int pxa_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
@@ -336,7 +322,6 @@ static const struct rtc_class_ops pxa_rtc_ops = {
 	.alarm_irq_enable = pxa_alarm_irq_enable,
 	.update_irq_enable = pxa_update_irq_enable,
 	.proc = pxa_rtc_proc,
-	.irq_set_freq = pxa_periodic_irq_set_freq,
 };
 
 static int __init pxa_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 80fb7e72f9d9..714964913e5e 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -348,7 +348,6 @@ static const struct rtc_class_ops s3c_rtcops = {
 	.set_time	= s3c_rtc_settime,
 	.read_alarm	= s3c_rtc_getalarm,
 	.set_alarm	= s3c_rtc_setalarm,
-	.irq_set_freq	= s3c_rtc_setfreq,
 	.proc		= s3c_rtc_proc,
 	.alarm_irq_enable = s3c_rtc_setaie,
 };
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index d47b3fc9830f..d1a2b0bc3b24 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -392,7 +392,6 @@ static const struct rtc_class_ops sa1100_rtc_ops = {
 	.read_alarm = sa1100_rtc_read_alarm,
 	.set_alarm = sa1100_rtc_set_alarm,
 	.proc = sa1100_rtc_proc,
-	.irq_set_freq = sa1100_irq_set_freq,
 	.alarm_irq_enable = sa1100_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index ff50a8bc13f6..148544979a54 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -603,7 +603,6 @@ static struct rtc_class_ops sh_rtc_ops = {
 	.set_time	= sh_rtc_set_time,
 	.read_alarm	= sh_rtc_read_alarm,
 	.set_alarm	= sh_rtc_set_alarm,
-	.irq_set_freq	= sh_rtc_irq_set_freq,
 	.proc		= sh_rtc_proc,
 	.alarm_irq_enable = sh_rtc_alarm_irq_enable,
 };
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index 86f14909f9db..c5698cda366a 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -207,26 +207,6 @@ static int vr41xx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *wkalrm)
 	return 0;
 }
 
-static int vr41xx_rtc_irq_set_freq(struct device *dev, int freq)
-{
-	u64 count;
-
-	if (!is_power_of_2(freq))
-		return -EINVAL;
-	count = RTC_FREQUENCY;
-	do_div(count, freq);
-
-	spin_lock_irq(&rtc_lock);
-
-	periodic_count = count;
-	rtc1_write(RTCL1LREG, periodic_count);
-	rtc1_write(RTCL1HREG, periodic_count >> 16);
-
-	spin_unlock_irq(&rtc_lock);
-
-	return 0;
-}
-
 static int vr41xx_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -298,7 +278,6 @@ static const struct rtc_class_ops vr41xx_rtc_ops = {
 	.set_time	= vr41xx_rtc_set_time,
 	.read_alarm	= vr41xx_rtc_read_alarm,
 	.set_alarm	= vr41xx_rtc_set_alarm,
-	.irq_set_freq	= vr41xx_rtc_irq_set_freq,
 };
 
 static int __devinit rtc_probe(struct platform_device *pdev)
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 0e2063acc260..741a51cc4460 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -133,7 +133,6 @@ extern struct class *rtc_class;
  * The (current) exceptions are mostly filesystem hooks:
  *   - the proc() hook for procfs
  *   - non-ioctl() chardev hooks:  open(), release(), read_callback()
- *   - periodic irq calls:  irq_set_state(), irq_set_freq()
  *
  * REVISIT those periodic irq calls *do* have ops_lock when they're
  * issued through ioctl() ...
@@ -148,7 +147,6 @@ struct rtc_class_ops {
 	int (*set_alarm)(struct device *, struct rtc_wkalrm *);
 	int (*proc)(struct device *, struct seq_file *);
 	int (*set_mmss)(struct device *, unsigned long secs);
-	int (*irq_set_freq)(struct device *, int freq);
 	int (*read_callback)(struct device *, int data);
 	int (*alarm_irq_enable)(struct device *, unsigned int enabled);
 	int (*update_irq_enable)(struct device *, unsigned int enabled);
-- 
cgit v1.2.3


From 51ba60c5bb3b0f71bee26404ddc22d8e4109e88a Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 3 Feb 2011 12:13:50 -0800
Subject: RTC: Cleanup rtc_class_ops->update_irq_enable()

Now that the generic code handles UIE mode irqs via periodic
alarm interrupts, no one calls the
rtc_class_ops->update_irq_enable() method anymore.

This patch removes the driver hooks and implementations of
update_irq_enable if no one else is calling it.

CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alessandro Zummo <a.zummo@towertech.it>
CC: Marcelo Roberto Jimenez <mroberto@cpti.cetuc.puc-rio.br>
CC: rtc-linux@googlegroups.com
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/rtc-cmos.c     | 20 --------------------
 drivers/rtc/rtc-ds1511.c   | 17 -----------------
 drivers/rtc/rtc-ds1553.c   | 17 -----------------
 drivers/rtc/rtc-ds3232.c   | 18 ------------------
 drivers/rtc/rtc-jz4740.c   |  7 -------
 drivers/rtc/rtc-mc13xxx.c  |  7 -------
 drivers/rtc/rtc-mpc5121.c  | 20 --------------------
 drivers/rtc/rtc-mxc.c      |  7 -------
 drivers/rtc/rtc-nuc900.c   | 15 ---------------
 drivers/rtc/rtc-pcap.c     |  6 ------
 drivers/rtc/rtc-pcf50633.c | 22 +---------------------
 drivers/rtc/rtc-pxa.c      | 16 ----------------
 drivers/rtc/rtc-stmp3xxx.c | 15 ---------------
 drivers/rtc/rtc-twl.c      | 13 -------------
 drivers/rtc/rtc-wm831x.c   | 16 ----------------
 drivers/rtc/rtc-wm8350.c   | 21 ---------------------
 include/linux/rtc.h        |  1 -
 17 files changed, 1 insertion(+), 237 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index bdb1f8e2042a..dc2a0ba969ce 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -394,25 +394,6 @@ static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int cmos_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
-	unsigned long	flags;
-
-	if (!is_valid_irq(cmos->irq))
-		return -EINVAL;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	if (enabled)
-		cmos_irq_enable(cmos, RTC_UIE);
-	else
-		cmos_irq_disable(cmos, RTC_UIE);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return 0;
-}
-
 #if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
 
 static int cmos_procfs(struct device *dev, struct seq_file *seq)
@@ -458,7 +439,6 @@ static const struct rtc_class_ops cmos_rtc_ops = {
 	.set_alarm		= cmos_set_alarm,
 	.proc			= cmos_procfs,
 	.alarm_irq_enable	= cmos_alarm_irq_enable,
-	.update_irq_enable	= cmos_update_irq_enable,
 };
 
 /*----------------------------------------------------------------*/
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index 37268e97de49..3fffd708711f 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -397,29 +397,12 @@ static int ds1511_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int ds1511_rtc_update_irq_enable(struct device *dev,
-	unsigned int enabled)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-
-	if (pdata->irq <= 0)
-		return -EINVAL;
-	if (enabled)
-		pdata->irqen |= RTC_UF;
-	else
-		pdata->irqen &= ~RTC_UF;
-	ds1511_rtc_update_alarm(pdata);
-	return 0;
-}
-
 static const struct rtc_class_ops ds1511_rtc_ops = {
 	.read_time		= ds1511_rtc_read_time,
 	.set_time		= ds1511_rtc_set_time,
 	.read_alarm		= ds1511_rtc_read_alarm,
 	.set_alarm		= ds1511_rtc_set_alarm,
 	.alarm_irq_enable	= ds1511_rtc_alarm_irq_enable,
-	.update_irq_enable	= ds1511_rtc_update_irq_enable,
 };
 
  static ssize_t
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index ff432e2ca275..fee41b97c9e8 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -227,29 +227,12 @@ static int ds1553_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int ds1553_rtc_update_irq_enable(struct device *dev,
-	unsigned int enabled)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-
-	if (pdata->irq <= 0)
-		return -EINVAL;
-	if (enabled)
-		pdata->irqen |= RTC_UF;
-	else
-		pdata->irqen &= ~RTC_UF;
-	ds1553_rtc_update_alarm(pdata);
-	return 0;
-}
-
 static const struct rtc_class_ops ds1553_rtc_ops = {
 	.read_time		= ds1553_rtc_read_time,
 	.set_time		= ds1553_rtc_set_time,
 	.read_alarm		= ds1553_rtc_read_alarm,
 	.set_alarm		= ds1553_rtc_set_alarm,
 	.alarm_irq_enable	= ds1553_rtc_alarm_irq_enable,
-	.update_irq_enable	= ds1553_rtc_update_irq_enable,
 };
 
 static ssize_t ds1553_nvram_read(struct file *filp, struct kobject *kobj,
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 950735415a7c..27b7bf672ac6 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -339,23 +339,6 @@ static int ds3232_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int ds3232_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
-
-	if (client->irq <= 0)
-		return -EINVAL;
-
-	if (enabled)
-		ds3232->rtc->irq_data |= RTC_UF;
-	else
-		ds3232->rtc->irq_data &= ~RTC_UF;
-
-	ds3232_update_alarm(client);
-	return 0;
-}
-
 static irqreturn_t ds3232_irq(int irq, void *dev_id)
 {
 	struct i2c_client *client = dev_id;
@@ -406,7 +389,6 @@ static const struct rtc_class_ops ds3232_rtc_ops = {
 	.read_alarm = ds3232_read_alarm,
 	.set_alarm = ds3232_set_alarm,
 	.alarm_irq_enable = ds3232_alarm_irq_enable,
-	.update_irq_enable = ds3232_update_irq_enable,
 };
 
 static int __devinit ds3232_probe(struct i2c_client *client,
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 2e16f72c9056..b6473631d182 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -168,12 +168,6 @@ static int jz4740_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return ret;
 }
 
-static int jz4740_rtc_update_irq_enable(struct device *dev, unsigned int enable)
-{
-	struct jz4740_rtc *rtc = dev_get_drvdata(dev);
-	return jz4740_rtc_ctrl_set_bits(rtc, JZ_RTC_CTRL_1HZ_IRQ, enable);
-}
-
 static int jz4740_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 {
 	struct jz4740_rtc *rtc = dev_get_drvdata(dev);
@@ -185,7 +179,6 @@ static struct rtc_class_ops jz4740_rtc_ops = {
 	.set_mmss	= jz4740_rtc_set_mmss,
 	.read_alarm	= jz4740_rtc_read_alarm,
 	.set_alarm	= jz4740_rtc_set_alarm,
-	.update_irq_enable = jz4740_rtc_update_irq_enable,
 	.alarm_irq_enable = jz4740_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index 5314b153bfba..c42006469559 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -282,12 +282,6 @@ static irqreturn_t mc13xxx_rtc_update_handler(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static int mc13xxx_rtc_update_irq_enable(struct device *dev,
-		unsigned int enabled)
-{
-	return mc13xxx_rtc_irq_enable(dev, enabled, MC13XXX_IRQ_1HZ);
-}
-
 static int mc13xxx_rtc_alarm_irq_enable(struct device *dev,
 		unsigned int enabled)
 {
@@ -300,7 +294,6 @@ static const struct rtc_class_ops mc13xxx_rtc_ops = {
 	.read_alarm = mc13xxx_rtc_read_alarm,
 	.set_alarm = mc13xxx_rtc_set_alarm,
 	.alarm_irq_enable = mc13xxx_rtc_alarm_irq_enable,
-	.update_irq_enable = mc13xxx_rtc_update_irq_enable,
 };
 
 static irqreturn_t mc13xxx_rtc_reset_handler(int irq, void *dev)
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index dfcdf0901d21..b40c1ff1ebc8 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -240,32 +240,12 @@ static int mpc5121_rtc_alarm_irq_enable(struct device *dev,
 	return 0;
 }
 
-static int mpc5121_rtc_update_irq_enable(struct device *dev,
-					 unsigned int enabled)
-{
-	struct mpc5121_rtc_data *rtc = dev_get_drvdata(dev);
-	struct mpc5121_rtc_regs __iomem *regs = rtc->regs;
-	int val;
-
-	val = in_8(&regs->int_enable);
-
-	if (enabled)
-		val = (val & ~0x8) | 0x1;
-	else
-		val &= ~0x1;
-
-	out_8(&regs->int_enable, val);
-
-	return 0;
-}
-
 static const struct rtc_class_ops mpc5121_rtc_ops = {
 	.read_time = mpc5121_rtc_read_time,
 	.set_time = mpc5121_rtc_set_time,
 	.read_alarm = mpc5121_rtc_read_alarm,
 	.set_alarm = mpc5121_rtc_set_alarm,
 	.alarm_irq_enable = mpc5121_rtc_alarm_irq_enable,
-	.update_irq_enable = mpc5121_rtc_update_irq_enable,
 };
 
 static int __devinit mpc5121_rtc_probe(struct platform_device *op,
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index 0b06c1e03fd5..826ab64a8fa9 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -274,12 +274,6 @@ static int mxc_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int mxc_rtc_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	mxc_rtc_irq_enable(dev, RTC_1HZ_BIT, enabled);
-	return 0;
-}
-
 /*
  * This function reads the current RTC time into tm in Gregorian date.
  */
@@ -368,7 +362,6 @@ static struct rtc_class_ops mxc_rtc_ops = {
 	.read_alarm		= mxc_rtc_read_alarm,
 	.set_alarm		= mxc_rtc_set_alarm,
 	.alarm_irq_enable	= mxc_rtc_alarm_irq_enable,
-	.update_irq_enable	= mxc_rtc_update_irq_enable,
 };
 
 static int __init mxc_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-nuc900.c b/drivers/rtc/rtc-nuc900.c
index ddb0857e15a4..781068d62f23 100644
--- a/drivers/rtc/rtc-nuc900.c
+++ b/drivers/rtc/rtc-nuc900.c
@@ -134,20 +134,6 @@ static void nuc900_rtc_bin2bcd(struct device *dev, struct rtc_time *settm,
 	gettm->bcd_hour = bin2bcd(settm->tm_hour) << 16;
 }
 
-static int nuc900_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct nuc900_rtc *rtc = dev_get_drvdata(dev);
-
-	if (enabled)
-		__raw_writel(__raw_readl(rtc->rtc_reg + REG_RTC_RIER)|
-				(TICKINTENB), rtc->rtc_reg + REG_RTC_RIER);
-	else
-		__raw_writel(__raw_readl(rtc->rtc_reg + REG_RTC_RIER)&
-				(~TICKINTENB), rtc->rtc_reg + REG_RTC_RIER);
-
-	return 0;
-}
-
 static int nuc900_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct nuc900_rtc *rtc = dev_get_drvdata(dev);
@@ -234,7 +220,6 @@ static struct rtc_class_ops nuc900_rtc_ops = {
 	.read_alarm = nuc900_rtc_read_alarm,
 	.set_alarm = nuc900_rtc_set_alarm,
 	.alarm_irq_enable = nuc900_alarm_irq_enable,
-	.update_irq_enable = nuc900_update_irq_enable,
 };
 
 static int __devinit nuc900_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-pcap.c b/drivers/rtc/rtc-pcap.c
index 25c0b3fd44f1..a633abc42896 100644
--- a/drivers/rtc/rtc-pcap.c
+++ b/drivers/rtc/rtc-pcap.c
@@ -131,18 +131,12 @@ static int pcap_rtc_alarm_irq_enable(struct device *dev, unsigned int en)
 	return pcap_rtc_irq_enable(dev, PCAP_IRQ_TODA, en);
 }
 
-static int pcap_rtc_update_irq_enable(struct device *dev, unsigned int en)
-{
-	return pcap_rtc_irq_enable(dev, PCAP_IRQ_1HZ, en);
-}
-
 static const struct rtc_class_ops pcap_rtc_ops = {
 	.read_time = pcap_rtc_read_time,
 	.read_alarm = pcap_rtc_read_alarm,
 	.set_alarm = pcap_rtc_set_alarm,
 	.set_mmss = pcap_rtc_set_mmss,
 	.alarm_irq_enable = pcap_rtc_alarm_irq_enable,
-	.update_irq_enable = pcap_rtc_update_irq_enable,
 };
 
 static int __devinit pcap_rtc_probe(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-pcf50633.c b/drivers/rtc/rtc-pcf50633.c
index 16edf94ab42f..f90c574f9d05 100644
--- a/drivers/rtc/rtc-pcf50633.c
+++ b/drivers/rtc/rtc-pcf50633.c
@@ -106,25 +106,6 @@ pcf50633_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int
-pcf50633_rtc_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct pcf50633_rtc *rtc = dev_get_drvdata(dev);
-	int err;
-
-	if (enabled)
-		err = pcf50633_irq_unmask(rtc->pcf, PCF50633_IRQ_SECOND);
-	else
-		err = pcf50633_irq_mask(rtc->pcf, PCF50633_IRQ_SECOND);
-
-	if (err < 0)
-		return err;
-
-	rtc->second_enabled = enabled;
-
-	return 0;
-}
-
 static int pcf50633_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct pcf50633_rtc *rtc;
@@ -262,8 +243,7 @@ static struct rtc_class_ops pcf50633_rtc_ops = {
 	.set_time		= pcf50633_rtc_set_time,
 	.read_alarm		= pcf50633_rtc_read_alarm,
 	.set_alarm		= pcf50633_rtc_set_alarm,
-	.alarm_irq_enable 	= pcf50633_rtc_alarm_irq_enable,
-	.update_irq_enable 	= pcf50633_rtc_update_irq_enable,
+	.alarm_irq_enable	= pcf50633_rtc_alarm_irq_enable,
 };
 
 static void pcf50633_rtc_irq(int irq, void *data)
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index a1fdc802598a..fc9f4991574b 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -224,21 +224,6 @@ static int pxa_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int pxa_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
-
-	spin_lock_irq(&pxa_rtc->lock);
-
-	if (enabled)
-		rtsr_set_bits(pxa_rtc, RTSR_HZE);
-	else
-		rtsr_clear_bits(pxa_rtc, RTSR_HZE);
-
-	spin_unlock_irq(&pxa_rtc->lock);
-	return 0;
-}
-
 static int pxa_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev);
@@ -320,7 +305,6 @@ static const struct rtc_class_ops pxa_rtc_ops = {
 	.read_alarm = pxa_rtc_read_alarm,
 	.set_alarm = pxa_rtc_set_alarm,
 	.alarm_irq_enable = pxa_alarm_irq_enable,
-	.update_irq_enable = pxa_update_irq_enable,
 	.proc = pxa_rtc_proc,
 };
 
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index 7e7d0c806f2d..572e9534b591 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -115,19 +115,6 @@ static int stmp3xxx_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
-static int stmp3xxx_update_irq_enable(struct device *dev, unsigned int enabled)
-{
-	struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
-
-	if (enabled)
-		stmp3xxx_setl(BM_RTC_CTRL_ONEMSEC_IRQ_EN,
-				rtc_data->io + HW_RTC_CTRL);
-	else
-		stmp3xxx_clearl(BM_RTC_CTRL_ONEMSEC_IRQ_EN,
-				rtc_data->io + HW_RTC_CTRL);
-	return 0;
-}
-
 static int stmp3xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
 {
 	struct stmp3xxx_rtc_data *rtc_data = dev_get_drvdata(dev);
@@ -149,8 +136,6 @@ static int stmp3xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 static struct rtc_class_ops stmp3xxx_rtc_ops = {
 	.alarm_irq_enable =
 			  stmp3xxx_alarm_irq_enable,
-	.update_irq_enable =
-			  stmp3xxx_update_irq_enable,
 	.read_time	= stmp3xxx_rtc_gettime,
 	.set_mmss	= stmp3xxx_rtc_set_mmss,
 	.read_alarm	= stmp3xxx_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index ed1b86828124..f9a2799c44d6 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -213,18 +213,6 @@ static int twl_rtc_alarm_irq_enable(struct device *dev, unsigned enabled)
 	return ret;
 }
 
-static int twl_rtc_update_irq_enable(struct device *dev, unsigned enabled)
-{
-	int ret;
-
-	if (enabled)
-		ret = set_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
-	else
-		ret = mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
-
-	return ret;
-}
-
 /*
  * Gets current TWL RTC time and date parameters.
  *
@@ -433,7 +421,6 @@ static struct rtc_class_ops twl_rtc_ops = {
 	.read_alarm	= twl_rtc_read_alarm,
 	.set_alarm	= twl_rtc_set_alarm,
 	.alarm_irq_enable = twl_rtc_alarm_irq_enable,
-	.update_irq_enable = twl_rtc_update_irq_enable,
 };
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c
index 82931dc65c0b..bdc909bd56da 100644
--- a/drivers/rtc/rtc-wm831x.c
+++ b/drivers/rtc/rtc-wm831x.c
@@ -315,21 +315,6 @@ static int wm831x_rtc_alarm_irq_enable(struct device *dev,
 		return wm831x_rtc_stop_alarm(wm831x_rtc);
 }
 
-static int wm831x_rtc_update_irq_enable(struct device *dev,
-					unsigned int enabled)
-{
-	struct wm831x_rtc *wm831x_rtc = dev_get_drvdata(dev);
-	int val;
-
-	if (enabled)
-		val = 1 << WM831X_RTC_PINT_FREQ_SHIFT;
-	else
-		val = 0;
-
-	return wm831x_set_bits(wm831x_rtc->wm831x, WM831X_RTC_CONTROL,
-			       WM831X_RTC_PINT_FREQ_MASK, val);
-}
-
 static irqreturn_t wm831x_alm_irq(int irq, void *data)
 {
 	struct wm831x_rtc *wm831x_rtc = data;
@@ -354,7 +339,6 @@ static const struct rtc_class_ops wm831x_rtc_ops = {
 	.read_alarm = wm831x_rtc_readalarm,
 	.set_alarm = wm831x_rtc_setalarm,
 	.alarm_irq_enable = wm831x_rtc_alarm_irq_enable,
-	.update_irq_enable = wm831x_rtc_update_irq_enable,
 };
 
 #ifdef CONFIG_PM
diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c
index 3d0dc76b38af..66421426e404 100644
--- a/drivers/rtc/rtc-wm8350.c
+++ b/drivers/rtc/rtc-wm8350.c
@@ -302,26 +302,6 @@ static int wm8350_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return ret;
 }
 
-static int wm8350_rtc_update_irq_enable(struct device *dev,
-					unsigned int enabled)
-{
-	struct wm8350 *wm8350 = dev_get_drvdata(dev);
-
-	/* Suppress duplicate changes since genirq nests enable and
-	 * disable calls. */
-	if (enabled == wm8350->rtc.update_enabled)
-		return 0;
-
-	if (enabled)
-		wm8350_unmask_irq(wm8350, WM8350_IRQ_RTC_SEC);
-	else
-		wm8350_mask_irq(wm8350, WM8350_IRQ_RTC_SEC);
-
-	wm8350->rtc.update_enabled = enabled;
-
-	return 0;
-}
-
 static irqreturn_t wm8350_rtc_alarm_handler(int irq, void *data)
 {
 	struct wm8350 *wm8350 = data;
@@ -357,7 +337,6 @@ static const struct rtc_class_ops wm8350_rtc_ops = {
 	.read_alarm = wm8350_rtc_readalarm,
 	.set_alarm = wm8350_rtc_setalarm,
 	.alarm_irq_enable = wm8350_rtc_alarm_irq_enable,
-	.update_irq_enable = wm8350_rtc_update_irq_enable,
 };
 
 #ifdef CONFIG_PM
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 741a51cc4460..2ca7e8a78060 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -149,7 +149,6 @@ struct rtc_class_ops {
 	int (*set_mmss)(struct device *, unsigned long secs);
 	int (*read_callback)(struct device *, int data);
 	int (*alarm_irq_enable)(struct device *, unsigned int enabled);
-	int (*update_irq_enable)(struct device *, unsigned int enabled);
 };
 
 #define RTC_DEVICE_NAME_SIZE 20
-- 
cgit v1.2.3


From f7ae8d59f66154df0424fd94035c89981fed3379 Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Tue, 8 Mar 2011 22:44:10 +0000
Subject: Phonet: allocate sock from accept syscall rather than soft IRQ
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This moves most of the accept logic to process context like other
socket stacks do. Then we can use a few more common socket helpers
and simplify a bit.

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pep.h |   1 -
 net/phonet/pep.c         | 284 +++++++++++++++++++----------------------------
 net/phonet/socket.c      |  10 +-
 3 files changed, 121 insertions(+), 174 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h
index 38eed1be6ffd..b669fe6dbc3b 100644
--- a/include/net/phonet/pep.h
+++ b/include/net/phonet/pep.h
@@ -28,7 +28,6 @@ struct pep_sock {
 
 	/* XXX: union-ify listening vs connected stuff ? */
 	/* Listening socket stuff: */
-	struct hlist_head	ackq;
 	struct hlist_head	hlist;
 
 	/* Connected socket stuff: */
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 610794a416e8..c0fab4cfcef7 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -42,7 +42,7 @@
  * TCP_ESTABLISHED	connected pipe in enabled state
  *
  * pep_sock locking:
- *  - sk_state, ackq, hlist: sock lock needed
+ *  - sk_state, hlist: sock lock needed
  *  - listener: read only
  *  - pipe_handle: read only
  */
@@ -202,11 +202,12 @@ static int pep_accept_conn(struct sock *sk, struct sk_buff *skb)
 				GFP_KERNEL);
 }
 
-static int pep_reject_conn(struct sock *sk, struct sk_buff *skb, u8 code)
+static int pep_reject_conn(struct sock *sk, struct sk_buff *skb, u8 code,
+				gfp_t priority)
 {
 	static const u8 data[4] = { PAD, PAD, PAD, 0 /* sub-blocks */ };
 	WARN_ON(code == PN_PIPE_NO_ERROR);
-	return pep_reply(sk, skb, code, data, sizeof(data), GFP_ATOMIC);
+	return pep_reply(sk, skb, code, data, sizeof(data), priority);
 }
 
 /* Control requests are not sent by the pipe service and have a specific
@@ -365,7 +366,7 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
 
 	switch (hdr->message_id) {
 	case PNS_PEP_CONNECT_REQ:
-		pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE);
+		pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE, GFP_ATOMIC);
 		break;
 
 	case PNS_PEP_DISCONNECT_REQ:
@@ -574,7 +575,6 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 
 	sk->sk_state = TCP_SYN_RECV;
 	sk->sk_backlog_rcv = pipe_do_rcv;
-	sk->sk_destruct = pipe_destruct;
 	pn->rx_credits = 0;
 	sk->sk_state_change(sk);
 
@@ -582,96 +582,6 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 }
 #endif
 
-static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb)
-{
-	struct sock *newsk;
-	struct pep_sock *newpn, *pn = pep_sk(sk);
-	struct pnpipehdr *hdr;
-	struct sockaddr_pn dst, src;
-	u16 peer_type;
-	u8 pipe_handle, enabled, n_sb;
-	u8 aligned = 0;
-
-	if (!pskb_pull(skb, sizeof(*hdr) + 4))
-		return -EINVAL;
-
-	hdr = pnp_hdr(skb);
-	pipe_handle = hdr->pipe_handle;
-	switch (hdr->state_after_connect) {
-	case PN_PIPE_DISABLE:
-		enabled = 0;
-		break;
-	case PN_PIPE_ENABLE:
-		enabled = 1;
-		break;
-	default:
-		pep_reject_conn(sk, skb, PN_PIPE_ERR_INVALID_PARAM);
-		return -EINVAL;
-	}
-	peer_type = hdr->other_pep_type << 8;
-
-	/* Parse sub-blocks (options) */
-	n_sb = hdr->data[4];
-	while (n_sb > 0) {
-		u8 type, buf[1], len = sizeof(buf);
-		const u8 *data = pep_get_sb(skb, &type, &len, buf);
-
-		if (data == NULL)
-			return -EINVAL;
-		switch (type) {
-		case PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE:
-			if (len < 1)
-				return -EINVAL;
-			peer_type = (peer_type & 0xff00) | data[0];
-			break;
-		case PN_PIPE_SB_ALIGNED_DATA:
-			aligned = data[0] != 0;
-			break;
-		}
-		n_sb--;
-	}
-
-	skb = skb_clone(skb, GFP_ATOMIC);
-	if (!skb)
-		return -ENOMEM;
-
-	/* Create a new to-be-accepted sock */
-	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_ATOMIC, sk->sk_prot);
-	if (!newsk) {
-		kfree_skb(skb);
-		return -ENOMEM;
-	}
-	sock_init_data(NULL, newsk);
-	newsk->sk_state = TCP_SYN_RECV;
-	newsk->sk_backlog_rcv = pipe_do_rcv;
-	newsk->sk_protocol = sk->sk_protocol;
-	newsk->sk_destruct = pipe_destruct;
-
-	newpn = pep_sk(newsk);
-	pn_skb_get_dst_sockaddr(skb, &dst);
-	pn_skb_get_src_sockaddr(skb, &src);
-	newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst);
-	newpn->pn_sk.dobject = pn_sockaddr_get_object(&src);
-	newpn->pn_sk.resource = pn_sockaddr_get_resource(&dst);
-	skb_queue_head_init(&newpn->ctrlreq_queue);
-	newpn->pipe_handle = pipe_handle;
-	atomic_set(&newpn->tx_credits, 0);
-	newpn->peer_type = peer_type;
-	newpn->rx_credits = 0;
-	newpn->rx_fc = newpn->tx_fc = PN_LEGACY_FLOW_CONTROL;
-	newpn->init_enable = enabled;
-	newpn->aligned = aligned;
-
-	BUG_ON(!skb_queue_empty(&newsk->sk_receive_queue));
-	skb_queue_head(&newsk->sk_receive_queue, skb);
-	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, 0);
-
-	sk_acceptq_added(sk);
-	sk_add_node(newsk, &pn->ackq);
-	return 0;
-}
-
 /* Listening sock must be locked */
 static struct sock *pep_find_pipe(const struct hlist_head *hlist,
 					const struct sockaddr_pn *dst,
@@ -726,22 +636,18 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb)
 	if (sknode)
 		return sk_receive_skb(sknode, skb, 1);
 
-	/* Look for a pipe handle pending accept */
-	sknode = pep_find_pipe(&pn->ackq, &dst, pipe_handle);
-	if (sknode) {
-		sock_put(sknode);
-		if (net_ratelimit())
-			printk(KERN_WARNING"Phonet unconnected PEP ignored");
-		goto drop;
-	}
-
 	switch (hdr->message_id) {
 	case PNS_PEP_CONNECT_REQ:
-		if (sk->sk_state == TCP_LISTEN && !sk_acceptq_is_full(sk))
-			pep_connreq_rcv(sk, skb);
-		else
-			pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE);
-		break;
+		if (sk->sk_state != TCP_LISTEN || sk_acceptq_is_full(sk)) {
+			pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE,
+					GFP_ATOMIC);
+			break;
+		}
+		skb_queue_head(&sk->sk_receive_queue, skb);
+		sk_acceptq_added(sk);
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_data_ready(sk, 0);
+		return NET_RX_SUCCESS;
 
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNS_PEP_CONNECT_RESP:
@@ -799,24 +705,16 @@ static void pep_sock_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	lock_sock(sk);
-	if (sk->sk_state == TCP_LISTEN) {
-		/* Destroy the listen queue */
-		struct sock *sknode;
-		struct hlist_node *p, *n;
-
-		sk_for_each_safe(sknode, p, n, &pn->ackq)
-			sk_del_node_init(sknode);
-		sk->sk_state = TCP_CLOSE;
-	} else if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED)) {
+	if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED)) {
 #ifndef CONFIG_PHONET_PIPECTRLR
 		/* Forcefully remove dangling Phonet pipe */
 		pipe_do_remove(sk);
 #else
 		/* send pep disconnect request */
 		pipe_handler_request(sk, PNS_PEP_DISCONNECT_REQ, PAD, NULL, 0);
-		sk->sk_state = TCP_CLOSE;
 #endif
 	}
+	sk->sk_state = TCP_CLOSE;
 
 	ifindex = pn->ifindex;
 	pn->ifindex = 0;
@@ -827,69 +725,121 @@ static void pep_sock_close(struct sock *sk, long timeout)
 	sock_put(sk);
 }
 
-static int pep_wait_connreq(struct sock *sk, int noblock)
+static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
 {
-	struct task_struct *tsk = current;
-	struct pep_sock *pn = pep_sk(sk);
-	long timeo = sock_rcvtimeo(sk, noblock);
-
-	for (;;) {
-		DEFINE_WAIT(wait);
+	struct pep_sock *pn = pep_sk(sk), *newpn;
+	struct sock *newsk = NULL;
+	struct sk_buff *skb;
+	struct pnpipehdr *hdr;
+	struct sockaddr_pn dst, src;
+	int err;
+	u16 peer_type;
+	u8 pipe_handle, enabled, n_sb;
+	u8 aligned = 0;
 
-		if (sk->sk_state != TCP_LISTEN)
-			return -EINVAL;
-		if (!hlist_empty(&pn->ackq))
-			break;
-		if (!timeo)
-			return -EWOULDBLOCK;
-		if (signal_pending(tsk))
-			return sock_intr_errno(timeo);
+	skb = skb_recv_datagram(sk, 0, flags & O_NONBLOCK, errp);
+	if (!skb)
+		return NULL;
 
-		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
-						TASK_INTERRUPTIBLE);
-		release_sock(sk);
-		timeo = schedule_timeout(timeo);
-		lock_sock(sk);
-		finish_wait(sk_sleep(sk), &wait);
+	lock_sock(sk);
+	if (sk->sk_state != TCP_LISTEN) {
+		err = -EINVAL;
+		goto drop;
 	}
+	sk_acceptq_removed(sk);
 
-	return 0;
-}
+	err = -EPROTO;
+	if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
+		goto drop;
 
-static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
-{
-	struct pep_sock *pn = pep_sk(sk);
-	struct sock *newsk = NULL;
-	struct sk_buff *oskb;
-	int err;
+	hdr = pnp_hdr(skb);
+	pipe_handle = hdr->pipe_handle;
+	switch (hdr->state_after_connect) {
+	case PN_PIPE_DISABLE:
+		enabled = 0;
+		break;
+	case PN_PIPE_ENABLE:
+		enabled = 1;
+		break;
+	default:
+		pep_reject_conn(sk, skb, PN_PIPE_ERR_INVALID_PARAM,
+				GFP_KERNEL);
+		goto drop;
+	}
+	peer_type = hdr->other_pep_type << 8;
 
-	lock_sock(sk);
-	err = pep_wait_connreq(sk, flags & O_NONBLOCK);
-	if (err)
-		goto out;
+	/* Parse sub-blocks (options) */
+	n_sb = hdr->data[4];
+	while (n_sb > 0) {
+		u8 type, buf[1], len = sizeof(buf);
+		const u8 *data = pep_get_sb(skb, &type, &len, buf);
 
-	newsk = __sk_head(&pn->ackq);
+		if (data == NULL)
+			goto drop;
+		switch (type) {
+		case PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE:
+			if (len < 1)
+				goto drop;
+			peer_type = (peer_type & 0xff00) | data[0];
+			break;
+		case PN_PIPE_SB_ALIGNED_DATA:
+			aligned = data[0] != 0;
+			break;
+		}
+		n_sb--;
+	}
 
-	oskb = skb_dequeue(&newsk->sk_receive_queue);
-	err = pep_accept_conn(newsk, oskb);
-	if (err) {
-		skb_queue_head(&newsk->sk_receive_queue, oskb);
+	/* Check for duplicate pipe handle */
+	newsk = pep_find_pipe(&pn->hlist, &dst, pipe_handle);
+	if (unlikely(newsk)) {
+		__sock_put(newsk);
 		newsk = NULL;
-		goto out;
+		pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE, GFP_KERNEL);
+		goto drop;
+	}
+
+	/* Create a new to-be-accepted sock */
+	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot);
+	if (!newsk) {
+		pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
+		err = -ENOBUFS;
+		goto drop;
 	}
-	kfree_skb(oskb);
 
+	sock_init_data(NULL, newsk);
+	newsk->sk_state = TCP_SYN_RECV;
+	newsk->sk_backlog_rcv = pipe_do_rcv;
+	newsk->sk_protocol = sk->sk_protocol;
+	newsk->sk_destruct = pipe_destruct;
+
+	newpn = pep_sk(newsk);
+	pn_skb_get_dst_sockaddr(skb, &dst);
+	pn_skb_get_src_sockaddr(skb, &src);
+	newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst);
+	newpn->pn_sk.dobject = pn_sockaddr_get_object(&src);
+	newpn->pn_sk.resource = pn_sockaddr_get_resource(&dst);
 	sock_hold(sk);
-	pep_sk(newsk)->listener = sk;
+	newpn->listener = sk;
+	skb_queue_head_init(&newpn->ctrlreq_queue);
+	newpn->pipe_handle = pipe_handle;
+	atomic_set(&newpn->tx_credits, 0);
+	newpn->ifindex = 0;
+	newpn->peer_type = peer_type;
+	newpn->rx_credits = 0;
+	newpn->rx_fc = newpn->tx_fc = PN_LEGACY_FLOW_CONTROL;
+	newpn->init_enable = enabled;
+	newpn->aligned = aligned;
 
-	sock_hold(newsk);
-	sk_del_node_init(newsk);
-	sk_acceptq_removed(sk);
+	err = pep_accept_conn(newsk, skb);
+	if (err) {
+		sock_put(newsk);
+		newsk = NULL;
+		goto drop;
+	}
 	sk_add_node(newsk, &pn->hlist);
-	__sock_put(newsk);
-
-out:
+drop:
 	release_sock(sk);
+	kfree_skb(skb);
 	*errp = err;
 	return newsk;
 }
@@ -937,7 +887,7 @@ static int pep_init(struct sock *sk)
 {
 	struct pep_sock *pn = pep_sk(sk);
 
-	INIT_HLIST_HEAD(&pn->ackq);
+	sk->sk_destruct = pipe_destruct;
 	INIT_HLIST_HEAD(&pn->hlist);
 	skb_queue_head_init(&pn->ctrlreq_queue);
 	pn->pipe_handle = PN_PIPE_INVALID_HANDLE;
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 65a03338769e..1eccfc35bcc0 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -327,6 +327,9 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock,
 	struct sock *newsk;
 	int err;
 
+	if (unlikely(sk->sk_state != TCP_LISTEN))
+		return -EINVAL;
+
 	newsk = sk->sk_prot->accept(sk, flags, &err);
 	if (!newsk)
 		return err;
@@ -363,13 +366,8 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock,
 
 	poll_wait(file, sk_sleep(sk), wait);
 
-	switch (sk->sk_state) {
-	case TCP_LISTEN:
-		return hlist_empty(&pn->ackq) ? 0 : POLLIN;
-	case TCP_CLOSE:
+	if (sk->sk_state == TCP_CLOSE)
 		return POLLERR;
-	}
-
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
 	if (!skb_queue_empty(&pn->ctrlreq_queue))
-- 
cgit v1.2.3


From acaf7df610ff3faf1778ce40d601fc3dd4a41b40 Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Tue, 8 Mar 2011 22:44:11 +0000
Subject: Phonet: provide pipe socket option to retrieve the pipe identifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-space sometimes needs this information. In particular, the GPRS
context or the AT commands pipe setups may use the pipe handle as a
reference.

This removes the settable pipe handle with CONFIG_PHONET_PIPECTRLR.
It did not handle error cases correctly. Furthermore, the kernel
*could* implement a smart scheme for allocating handles (if ever
needed), but userspace really cannot.

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/phonet.txt |  7 ++++---
 include/linux/phonet.h              |  2 +-
 net/phonet/pep.c                    | 15 +++++++--------
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/phonet.txt b/Documentation/networking/phonet.txt
index 24ad2adba6e5..cacac968c1c3 100644
--- a/Documentation/networking/phonet.txt
+++ b/Documentation/networking/phonet.txt
@@ -181,6 +181,10 @@ The pipe protocol provides two socket options at the SOL_PNPIPE level:
     interface index of the network interface created by PNPIPE_ENCAP,
     or zero if encapsulation is off.
 
+  PNPIPE_HANDLE is a read-only integer value. It contains the underlying
+    identifier ("pipe handle") of the pipe. This is only defined for
+    socket descriptors that are already connected or being connected.
+
 
 Phonet Pipe-controller Implementation
 -------------------------------------
@@ -199,9 +203,6 @@ between itself and a remote pipe-end point (e.g. modem).
 
 The implementation adds socket options at SOL_PNPIPE level:
 
- PNPIPE_PIPE_HANDLE
-	It accepts an integer argument for setting value of pipe handle.
-
   PNPIPE_ENABLE accepts one integer value (int). If set to zero, the pipe
     is disabled. If the value is non-zero, the pipe is enabled. If the pipe
     is not (yet) connected, ENOTCONN is error is returned.
diff --git a/include/linux/phonet.h b/include/linux/phonet.h
index 26c8df786918..32a0965da953 100644
--- a/include/linux/phonet.h
+++ b/include/linux/phonet.h
@@ -36,7 +36,7 @@
 /* Socket options for SOL_PNPIPE level */
 #define PNPIPE_ENCAP		1
 #define PNPIPE_IFINDEX		2
-#define PNPIPE_PIPE_HANDLE	3
+#define PNPIPE_HANDLE		3
 #define PNPIPE_ENABLE           4
 /* unused slot */
 
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index c0fab4cfcef7..abfb795af142 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -853,6 +853,7 @@ static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len)
 
 	pn->pn_sk.dobject = pn_sockaddr_get_object(spn);
 	pn->pn_sk.resource = pn_sockaddr_get_resource(spn);
+	pn->pipe_handle = 1; /* anything but INVALID_HANDLE */
 	return pipe_handler_request(sk, PNS_PEP_CONNECT_REQ,
 					PN_PIPE_DISABLE, data, 4);
 }
@@ -909,14 +910,6 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
 
 	lock_sock(sk);
 	switch (optname) {
-#ifdef CONFIG_PHONET_PIPECTRLR
-	case PNPIPE_PIPE_HANDLE:
-		if (val) {
-			pn->pipe_handle = val;
-			break;
-		}
-#endif
-
 	case PNPIPE_ENCAP:
 		if (val && val != PNPIPE_ENCAP_IP) {
 			err = -EINVAL;
@@ -982,6 +975,12 @@ static int pep_getsockopt(struct sock *sk, int level, int optname,
 		val = pn->ifindex;
 		break;
 
+	case PNPIPE_HANDLE:
+		val = pn->pipe_handle;
+		if (val == PN_PIPE_INVALID_HANDLE)
+			return -EINVAL;
+		break;
+
 #ifdef CONFIG_PHONET_PIPECTRLR
 	case PNPIPE_ENABLE:
 		val = sk->sk_state == TCP_ESTABLISHED;
-- 
cgit v1.2.3


From a015f6f49968c330b236ca2f6c2170820414f922 Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Tue, 8 Mar 2011 22:44:13 +0000
Subject: Phonet: kill the ST-Ericsson pipe controller Kconfig
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is now a run-time choice so that a single kernel can support both
old and new generation ISI modems. Support for manually enabling the
pipe flow is removed as it did not work properly, does not fit well
with the socket API, and I am not aware of any use at the moment.

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/phonet.txt | 13 -------------
 include/linux/phonet.h              |  2 --
 net/phonet/Kconfig                  | 12 ------------
 net/phonet/pep.c                    | 25 -------------------------
 4 files changed, 52 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/phonet.txt b/Documentation/networking/phonet.txt
index 3d127791cb06..81003581f47a 100644
--- a/Documentation/networking/phonet.txt
+++ b/Documentation/networking/phonet.txt
@@ -205,19 +205,6 @@ The pipe protocol provides two socket options at the SOL_PNPIPE level:
     socket descriptors that are already connected or being connected.
 
 
-Phonet Pipe-controller Implementation
--------------------------------------
-
-Phonet Pipe-controller is enabled by selecting the CONFIG_PHONET_PIPECTRLR
-Kconfig option.
-
-The implementation adds socket options at SOL_PNPIPE level:
-
-  PNPIPE_ENABLE accepts one integer value (int). If set to zero, the pipe
-    is disabled. If the value is non-zero, the pipe is enabled. If the pipe
-    is not (yet) connected, ENOTCONN is error is returned.
-
-
 Authors
 -------
 
diff --git a/include/linux/phonet.h b/include/linux/phonet.h
index 32a0965da953..6fb13841db45 100644
--- a/include/linux/phonet.h
+++ b/include/linux/phonet.h
@@ -37,8 +37,6 @@
 #define PNPIPE_ENCAP		1
 #define PNPIPE_IFINDEX		2
 #define PNPIPE_HANDLE		3
-#define PNPIPE_ENABLE           4
-/* unused slot */
 
 #define PNADDR_ANY		0
 #define PNADDR_BROADCAST	0xFC
diff --git a/net/phonet/Kconfig b/net/phonet/Kconfig
index 0d9b8a220a78..6ec7d55b1769 100644
--- a/net/phonet/Kconfig
+++ b/net/phonet/Kconfig
@@ -14,15 +14,3 @@ config PHONET
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called phonet. If unsure, say N.
-
-config PHONET_PIPECTRLR
-	bool "Phonet Pipe Controller (EXPERIMENTAL)"
-	depends on PHONET && EXPERIMENTAL
-	default N
-	help
-	  The Pipe Controller implementation in Phonet stack to support Pipe
-	  data with Nokia Slim modems like WG2.5 used on ST-Ericsson U8500
-	  platform.
-
-	  This option is incompatible with older Nokia modems.
-	  Say N here unless you really know what you are doing.
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 671effb4ea15..68e635f11de8 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -167,15 +167,6 @@ static int pipe_handler_send_created_ind(struct sock *sk)
 				data, 4, GFP_ATOMIC);
 }
 
-#ifdef CONFIG_PHONET_PIPECTRLR
-static int pipe_handler_enable_pipe(struct sock *sk, int enable)
-{
-	u8 id = enable ? PNS_PEP_ENABLE_REQ : PNS_PEP_DISABLE_REQ;
-
-	return pipe_handler_request(sk, id, PAD, NULL, 0);
-}
-#endif
-
 static int pep_accept_conn(struct sock *sk, struct sk_buff *skb)
 {
 	static const u8 data[20] = {
@@ -968,16 +959,6 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
 		}
 		goto out_norel;
 
-#ifdef CONFIG_PHONET_PIPECTRLR
-	case PNPIPE_ENABLE:
-		if ((1 << sk->sk_state) & ~(TCPF_SYN_RECV|TCPF_ESTABLISHED)) {
-			err = -ENOTCONN;
-			break;
-		}
-		err = pipe_handler_enable_pipe(sk, val);
-		break;
-#endif
-
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1013,12 +994,6 @@ static int pep_getsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		break;
 
-#ifdef CONFIG_PHONET_PIPECTRLR
-	case PNPIPE_ENABLE:
-		val = sk->sk_state == TCP_ESTABLISHED;
-		break;
-#endif
-
 	default:
 		return -ENOPROTOOPT;
 	}
-- 
cgit v1.2.3


From 80751e2b8ffcbbe065e850d943301aa1ab219599 Mon Sep 17 00:00:00 2001
From: Bing Zhao <bzhao@marvell.com>
Date: Mon, 7 Mar 2011 11:14:23 -0800
Subject: ieee80211: add IEEE80211_COUNTRY_STRING_LEN definition

and make use of it in wireless drivers

Signed-off-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/at76c50x-usb.h        | 2 +-
 drivers/net/wireless/ipw2x00/ipw2200.h     | 2 +-
 drivers/net/wireless/libertas/host.h       | 2 +-
 drivers/net/wireless/wl1251/wl12xx_80211.h | 3 +--
 drivers/net/wireless/wl12xx/wl12xx_80211.h | 3 +--
 include/linux/ieee80211.h                  | 3 +++
 6 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/at76c50x-usb.h b/drivers/net/wireless/at76c50x-usb.h
index 4a37447dfc01..f14a65473fe8 100644
--- a/drivers/net/wireless/at76c50x-usb.h
+++ b/drivers/net/wireless/at76c50x-usb.h
@@ -290,7 +290,7 @@ struct mib_mac_mgmt {
 	u8 res;
 	u8 multi_domain_capability_implemented;
 	u8 multi_domain_capability_enabled;
-	u8 country_string[3];
+	u8 country_string[IEEE80211_COUNTRY_STRING_LEN];
 	u8 reserved[3];
 } __packed;
 
diff --git a/drivers/net/wireless/ipw2x00/ipw2200.h b/drivers/net/wireless/ipw2x00/ipw2200.h
index d7d049c7a4fa..d9e1d9bad581 100644
--- a/drivers/net/wireless/ipw2x00/ipw2200.h
+++ b/drivers/net/wireless/ipw2x00/ipw2200.h
@@ -961,7 +961,7 @@ struct ipw_country_channel_info {
 struct ipw_country_info {
 	u8 id;
 	u8 length;
-	u8 country_str[3];
+	u8 country_str[IEEE80211_COUNTRY_STRING_LEN];
 	struct ipw_country_channel_info groups[7];
 } __packed;
 
diff --git a/drivers/net/wireless/libertas/host.h b/drivers/net/wireless/libertas/host.h
index 5eac1351a021..6cb6935ee4a3 100644
--- a/drivers/net/wireless/libertas/host.h
+++ b/drivers/net/wireless/libertas/host.h
@@ -387,7 +387,7 @@ struct lbs_offset_value {
 struct mrvl_ie_domain_param_set {
 	struct mrvl_ie_header header;
 
-	u8 country_code[3];
+	u8 country_code[IEEE80211_COUNTRY_STRING_LEN];
 	struct ieee80211_country_ie_triplet triplet[MAX_11D_TRIPLETS];
 } __packed;
 
diff --git a/drivers/net/wireless/wl1251/wl12xx_80211.h b/drivers/net/wireless/wl1251/wl12xx_80211.h
index 184628027213..1417b1445c3d 100644
--- a/drivers/net/wireless/wl1251/wl12xx_80211.h
+++ b/drivers/net/wireless/wl1251/wl12xx_80211.h
@@ -54,7 +54,6 @@
 
 /* This really should be 8, but not for our firmware */
 #define MAX_SUPPORTED_RATES 32
-#define COUNTRY_STRING_LEN 3
 #define MAX_COUNTRY_TRIPLETS 32
 
 /* Headers */
@@ -98,7 +97,7 @@ struct country_triplet {
 
 struct wl12xx_ie_country {
 	struct wl12xx_ie_header header;
-	u8 country_string[COUNTRY_STRING_LEN];
+	u8 country_string[IEEE80211_COUNTRY_STRING_LEN];
 	struct country_triplet triplets[MAX_COUNTRY_TRIPLETS];
 } __packed;
 
diff --git a/drivers/net/wireless/wl12xx/wl12xx_80211.h b/drivers/net/wireless/wl12xx/wl12xx_80211.h
index 67dcf8f28cd3..18fe542360f2 100644
--- a/drivers/net/wireless/wl12xx/wl12xx_80211.h
+++ b/drivers/net/wireless/wl12xx/wl12xx_80211.h
@@ -55,7 +55,6 @@
 
 /* This really should be 8, but not for our firmware */
 #define MAX_SUPPORTED_RATES 32
-#define COUNTRY_STRING_LEN 3
 #define MAX_COUNTRY_TRIPLETS 32
 
 /* Headers */
@@ -99,7 +98,7 @@ struct country_triplet {
 
 struct wl12xx_ie_country {
 	struct wl12xx_ie_header header;
-	u8 country_string[COUNTRY_STRING_LEN];
+	u8 country_string[IEEE80211_COUNTRY_STRING_LEN];
 	struct country_triplet triplets[MAX_COUNTRY_TRIPLETS];
 } __packed;
 
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 294169e31364..2d1c6117d92c 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1325,6 +1325,9 @@ enum {
 /* Although the spec says 8 I'm seeing 6 in practice */
 #define IEEE80211_COUNTRY_IE_MIN_LEN	6
 
+/* The Country String field of the element shall be 3 octets in length */
+#define IEEE80211_COUNTRY_STRING_LEN	3
+
 /*
  * For regulatory extension stuff see IEEE 802.11-2007
  * Annex I (page 1141) and Annex J (page 1147). Also
-- 
cgit v1.2.3


From 2f4e1b3970973bbb57cc3a3b9d67e67c1c648c37 Mon Sep 17 00:00:00 2001
From: Mario Schuknecht <m.schuknecht@dresearch.de>
Date: Wed, 9 Mar 2011 14:08:09 -0800
Subject: tcp: ioctl type SIOCOUTQNSD returns amount of data not sent

In contrast to SIOCOUTQ which returns the amount of data sent
but not yet acknowledged plus data not yet sent this patch only
returns the data not sent.

For various methods of live streaming bitrate control it may
be helpful to know how much data are in the tcp outqueue are
not sent yet.

Signed-off-by: Mario Schuknecht <m.schuknecht@dresearch.de>
Signed-off-by: Steffen Sledz <sledz@dresearch.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sockios.h | 4 +++-
 net/ipv4/tcp.c          | 9 +++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sockios.h b/include/linux/sockios.h
index 241f179347d9..7997a506ad41 100644
--- a/include/linux/sockios.h
+++ b/include/linux/sockios.h
@@ -22,7 +22,7 @@
 
 /* Linux-specific socket ioctls */
 #define SIOCINQ		FIONREAD
-#define SIOCOUTQ	TIOCOUTQ
+#define SIOCOUTQ	TIOCOUTQ        /* output queue size (not sent + not acked) */
 
 /* Routing table calls. */
 #define SIOCADDRT	0x890B		/* add routing table entry	*/
@@ -83,6 +83,8 @@
 
 #define SIOCWANDEV	0x894A		/* get/set netdev parameters	*/
 
+#define SIOCOUTQNSD	0x894B		/* output queue size (not sent only) */
+
 /* ARP cache control calls. */
 		    /*  0x8950 - 0x8952  * obsolete calls, don't re-use */
 #define SIOCDARP	0x8953		/* delete ARP table entry	*/
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a17a5a72b98d..b22d45010545 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -505,6 +505,15 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		else
 			answ = tp->write_seq - tp->snd_una;
 		break;
+	case SIOCOUTQNSD:
+		if (sk->sk_state == TCP_LISTEN)
+			return -EINVAL;
+
+		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
+			answ = 0;
+		else
+			answ = tp->write_seq - tp->snd_nxt;
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
-- 
cgit v1.2.3


From 8909c9ad8ff03611c9c96c9a92656213e4bb495b Mon Sep 17 00:00:00 2001
From: Vasiliy Kulikov <segoon@openwall.com>
Date: Wed, 2 Mar 2011 00:33:13 +0300
Subject: net: don't allow CAP_NET_ADMIN to load non-netdev kernel modules

Since a8f80e8ff94ecba629542d9b4b5f5a8ee3eb565c any process with
CAP_NET_ADMIN may load any module from /lib/modules/.  This doesn't mean
that CAP_NET_ADMIN is a superset of CAP_SYS_MODULE as modules are
limited to /lib/modules/**.  However, CAP_NET_ADMIN capability shouldn't
allow anybody load any module not related to networking.

This patch restricts an ability of autoloading modules to netdev modules
with explicit aliases.  This fixes CVE-2011-1019.

Arnd Bergmann suggested to leave untouched the old pre-v2.6.32 behavior
of loading netdev modules by name (without any prefix) for processes
with CAP_SYS_MODULE to maintain the compatibility with network scripts
that use autoloading netdev modules by aliases like "eth0", "wlan0".

Currently there are only three users of the feature in the upstream
kernel: ipip, ip_gre and sit.

    root@albatros:~# capsh --drop=$(seq -s, 0 11),$(seq -s, 13 34) --
    root@albatros:~# grep Cap /proc/$$/status
    CapInh:	0000000000000000
    CapPrm:	fffffff800001000
    CapEff:	fffffff800001000
    CapBnd:	fffffff800001000
    root@albatros:~# modprobe xfs
    FATAL: Error inserting xfs
    (/lib/modules/2.6.38-rc6-00001-g2bf4ca3/kernel/fs/xfs/xfs.ko): Operation not permitted
    root@albatros:~# lsmod | grep xfs
    root@albatros:~# ifconfig xfs
    xfs: error fetching interface information: Device not found
    root@albatros:~# lsmod | grep xfs
    root@albatros:~# lsmod | grep sit
    root@albatros:~# ifconfig sit
    sit: error fetching interface information: Device not found
    root@albatros:~# lsmod | grep sit
    root@albatros:~# ifconfig sit0
    sit0      Link encap:IPv6-in-IPv4
	      NOARP  MTU:1480  Metric:1

    root@albatros:~# lsmod | grep sit
    sit                    10457  0
    tunnel4                 2957  1 sit

For CAP_SYS_MODULE module loading is still relaxed:

    root@albatros:~# grep Cap /proc/$$/status
    CapInh:	0000000000000000
    CapPrm:	ffffffffffffffff
    CapEff:	ffffffffffffffff
    CapBnd:	ffffffffffffffff
    root@albatros:~# ifconfig xfs
    xfs: error fetching interface information: Device not found
    root@albatros:~# lsmod | grep xfs
    xfs                   745319  0

Reference: https://lkml.org/lkml/2011/2/24/203

Signed-off-by: Vasiliy Kulikov <segoon@openwall.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Kees Cook <kees.cook@canonical.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 include/linux/netdevice.h |  3 +++
 net/core/dev.c            | 12 ++++++++++--
 net/ipv4/ip_gre.c         |  2 +-
 net/ipv4/ipip.c           |  2 +-
 net/ipv6/sit.c            |  2 +-
 5 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d971346b0340..71caf7a5e6c6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2392,6 +2392,9 @@ extern int netdev_notice(const struct net_device *dev, const char *format, ...)
 extern int netdev_info(const struct net_device *dev, const char *format, ...)
 	__attribute__ ((format (printf, 2, 3)));
 
+#define MODULE_ALIAS_NETDEV(device) \
+	MODULE_ALIAS("netdev-" device)
+
 #if defined(DEBUG)
 #define netdev_dbg(__dev, format, args...)			\
 	netdev_printk(KERN_DEBUG, __dev, format, ##args)
diff --git a/net/core/dev.c b/net/core/dev.c
index 8ae6631abcc2..6561021d22d1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1114,13 +1114,21 @@ EXPORT_SYMBOL(netdev_bonding_change);
 void dev_load(struct net *net, const char *name)
 {
 	struct net_device *dev;
+	int no_module;
 
 	rcu_read_lock();
 	dev = dev_get_by_name_rcu(net, name);
 	rcu_read_unlock();
 
-	if (!dev && capable(CAP_NET_ADMIN))
-		request_module("%s", name);
+	no_module = !dev;
+	if (no_module && capable(CAP_NET_ADMIN))
+		no_module = request_module("netdev-%s", name);
+	if (no_module && capable(CAP_SYS_MODULE)) {
+		if (!request_module("%s", name))
+			pr_err("Loading kernel module for a network device "
+"with CAP_SYS_MODULE (deprecated).  Use CAP_NET_ADMIN and alias netdev-%s "
+"instead\n", name);
+	}
 }
 EXPORT_SYMBOL(dev_load);
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6613edfac28c..d1d0e2c256fc 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1765,4 +1765,4 @@ module_exit(ipgre_fini);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("gre");
 MODULE_ALIAS_RTNL_LINK("gretap");
-MODULE_ALIAS("gre0");
+MODULE_ALIAS_NETDEV("gre0");
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 988f52fba54a..a5f58e7cbb26 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -913,4 +913,4 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("tunl0");
+MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 8ce38f10a547..d2c16e10f650 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1290,4 +1290,4 @@ static int __init sit_init(void)
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("sit0");
+MODULE_ALIAS_NETDEV("sit0");
-- 
cgit v1.2.3


From 684adca4f84365ca327e06dba696b62de7a79eca Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Thu, 10 Mar 2011 11:14:17 +1100
Subject: sysctl: the include of rcupdate.h is only needed in the kernel

Fixes this build-check error:

  include/linux/sysctl.h:28: included file 'linux/rcupdate.h' is not exported

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sysctl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index bb7c2b086fa4..11684d9e6bd2 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -25,7 +25,6 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
-#include <linux/rcupdate.h>
 
 struct completion;
 
@@ -931,6 +930,7 @@ enum
 
 #ifdef __KERNEL__
 #include <linux/list.h>
+#include <linux/rcupdate.h>
 
 /* For the /proc/sys support */
 struct ctl_table;
-- 
cgit v1.2.3


From d4894f3ea7375dd9492b5d3d2ecb0b6e4bdb604e Mon Sep 17 00:00:00 2001
From: Matt Carlson <mcarlson@broadcom.com>
Date: Wed, 9 Mar 2011 16:58:21 +0000
Subject: tg3: Add code to verify RODATA checksum of VPD

This patch adds code to verify the checksum stored in the "RV" info
keyword of the RODATA VPD section.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tg3.c   | 35 +++++++++++++++++++++++++++++++++++
 include/linux/pci.h |  1 +
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 8f7160812e06..ffb09795101e 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -10499,6 +10499,41 @@ static int tg3_test_nvram(struct tg3 *tp)
 	if (csum != le32_to_cpu(buf[0xfc/4]))
 		goto out;
 
+	for (i = 0; i < TG3_NVM_VPD_LEN; i += 4) {
+		/* The data is in little-endian format in NVRAM.
+		 * Use the big-endian read routines to preserve
+		 * the byte order as it exists in NVRAM.
+		 */
+		if (tg3_nvram_read_be32(tp, TG3_NVM_VPD_OFF + i, &buf[i/4]))
+			goto out;
+	}
+
+	i = pci_vpd_find_tag((u8 *)buf, 0, TG3_NVM_VPD_LEN,
+			     PCI_VPD_LRDT_RO_DATA);
+	if (i > 0) {
+		j = pci_vpd_lrdt_size(&((u8 *)buf)[i]);
+		if (j < 0)
+			goto out;
+
+		if (i + PCI_VPD_LRDT_TAG_SIZE + j > TG3_NVM_VPD_LEN)
+			goto out;
+
+		i += PCI_VPD_LRDT_TAG_SIZE;
+		j = pci_vpd_find_info_keyword((u8 *)buf, i, j,
+					      PCI_VPD_RO_KEYWORD_CHKSUM);
+		if (j > 0) {
+			u8 csum8 = 0;
+
+			j += PCI_VPD_INFO_FLD_HDR_SIZE;
+
+			for (i = 0; i <= j; i++)
+				csum8 += ((u8 *)buf)[i];
+
+			if (csum8)
+				goto out;
+		}
+	}
+
 	err = 0;
 
 out:
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 559d02897075..ff5bccb87136 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1479,6 +1479,7 @@ void pci_request_acs(void);
 #define PCI_VPD_RO_KEYWORD_PARTNO	"PN"
 #define PCI_VPD_RO_KEYWORD_MFR_ID	"MN"
 #define PCI_VPD_RO_KEYWORD_VENDOR0	"V0"
+#define PCI_VPD_RO_KEYWORD_CHKSUM	"RV"
 
 /**
  * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length
-- 
cgit v1.2.3


From e6e1e2593592a8f6f6380496655d8c6f67431266 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 9 Mar 2011 10:41:56 -0500
Subject: tracing: Remove lock_depth from event entry

The lock_depth field in the event headers was added as a temporary
data point for help in removing the BKL. Now that the BKL is pretty
much been removed, we can remove this field.

This in turn changes the header from 12 bytes to 8 bytes,
removing the 4 byte buffer that gcc would insert if the first field
in the data load was 8 bytes in size.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |  1 -
 kernel/trace/trace.c         |  8 +++-----
 kernel/trace/trace_events.c  |  1 -
 kernel/trace/trace_output.c  | 10 ++--------
 4 files changed, 5 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 1a99e7939c2b..22b32af1b5ec 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -37,7 +37,6 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			lock_depth;
 };
 
 #define FTRACE_MAX_EVENT						\
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 85e3ee1e474e..fd6e1b906b3c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1101,7 +1101,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->lock_depth		= (tsk) ? tsk->lock_depth : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1748,10 +1747,9 @@ static void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#                | / _----=> need-resched    \n");
 	seq_puts(m, "#                || / _---=> hardirq/softirq \n");
 	seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-	seq_puts(m, "#                |||| /_--=> lock-depth       \n");
-	seq_puts(m, "#                |||||/     delay             \n");
-	seq_puts(m, "#  cmd     pid   |||||| time  |   caller      \n");
-	seq_puts(m, "#     \\   /      ||||||   \\   |   /           \n");
+	seq_puts(m, "#                |||| /     delay             \n");
+	seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
+	seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5f499e0438a4..e1d579b19834 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, lock_depth);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02272baa2206..151f32e5f2c6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -529,7 +529,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
  * @entry: The trace entry field from the ring buffer
  *
  * Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
  */
 int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
@@ -554,13 +554,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 	else
 		ret = trace_seq_putc(s, '.');
 
-	if (!ret)
-		return 0;
-
-	if (entry->lock_depth < 0)
-		return trace_seq_putc(s, '.');
-
-	return trace_seq_printf(s, "%d", entry->lock_depth);
+	return ret;
 }
 
 static int
-- 
cgit v1.2.3


From b5e3008e489f5a00c6d5db914a4c4338c9ef5e8b Mon Sep 17 00:00:00 2001
From: David Sharp <dhsharp@google.com>
Date: Fri, 3 Dec 2010 16:13:20 -0800
Subject: tracing: Fix event alignment: module:module_request

Acked-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-7-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/module.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c6bae36547e5..21a546d27c0c 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -108,14 +108,14 @@ TRACE_EVENT(module_request,
 	TP_ARGS(name, wait, ip),
 
 	TP_STRUCT__entry(
-		__field(	bool,		wait		)
 		__field(	unsigned long,	ip		)
+		__field(	bool,		wait		)
 		__string(	name,		name		)
 	),
 
 	TP_fast_assign(
-		__entry->wait	= wait;
 		__entry->ip	= ip;
+		__entry->wait	= wait;
 		__assign_str(name, name);
 	),
 
@@ -129,4 +129,3 @@ TRACE_EVENT(module_request,
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
-
-- 
cgit v1.2.3


From ad440ad66f1617194738bf674dfe2d38978ac54d Mon Sep 17 00:00:00 2001
From: David Sharp <dhsharp@google.com>
Date: Fri, 3 Dec 2010 16:13:22 -0800
Subject: tracing: Fix event alignment: mce:mce_record

Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-9-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/mce.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 7eee77895cb3..4cbbcef6baa8 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -17,36 +17,36 @@ TRACE_EVENT(mce_record,
 	TP_STRUCT__entry(
 		__field(	u64,		mcgcap		)
 		__field(	u64,		mcgstatus	)
-		__field(	u8,		bank		)
 		__field(	u64,		status		)
 		__field(	u64,		addr		)
 		__field(	u64,		misc		)
 		__field(	u64,		ip		)
-		__field(	u8,		cs		)
 		__field(	u64,		tsc		)
 		__field(	u64,		walltime	)
 		__field(	u32,		cpu		)
 		__field(	u32,		cpuid		)
 		__field(	u32,		apicid		)
 		__field(	u32,		socketid	)
+		__field(	u8,		cs		)
+		__field(	u8,		bank		)
 		__field(	u8,		cpuvendor	)
 	),
 
 	TP_fast_assign(
 		__entry->mcgcap		= m->mcgcap;
 		__entry->mcgstatus	= m->mcgstatus;
-		__entry->bank		= m->bank;
 		__entry->status		= m->status;
 		__entry->addr		= m->addr;
 		__entry->misc		= m->misc;
 		__entry->ip		= m->ip;
-		__entry->cs		= m->cs;
 		__entry->tsc		= m->tsc;
 		__entry->walltime	= m->time;
 		__entry->cpu		= m->extcpu;
 		__entry->cpuid		= m->cpuid;
 		__entry->apicid		= m->apicid;
 		__entry->socketid	= m->socketid;
+		__entry->cs		= m->cs;
+		__entry->bank		= m->bank;
 		__entry->cpuvendor	= m->cpuvendor;
 	),
 
-- 
cgit v1.2.3


From ca9da2dd63b0b32de1b693953dff66cadeb6400b Mon Sep 17 00:00:00 2001
From: David Sharp <dhsharp@google.com>
Date: Fri, 3 Dec 2010 16:13:23 -0800
Subject: tracing: Fix event alignment: skb:kfree_skb

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David Sharp <dhsharp@google.com>
LKML-Reference: <1291421609-14665-10-git-send-email-dhsharp@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/skb.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index f10293c41b1e..0c68ae22da22 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb,
 
 	TP_STRUCT__entry(
 		__field(	void *,		skbaddr		)
-		__field(	unsigned short,	protocol	)
 		__field(	void *,		location	)
+		__field(	unsigned short,	protocol	)
 	),
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		__entry->protocol = ntohs(skb->protocol);
 		__entry->location = location;
+		__entry->protocol = ntohs(skb->protocol);
 	),
 
 	TP_printk("skbaddr=%p protocol=%u location=%p",
-- 
cgit v1.2.3


From 53370d2e8c0382e3e2aa76def93365ed674e7fc7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Mar 2011 18:26:33 +0100
Subject: hrtimer: Update hrtimer->state documentation

We changed some of the state bits and combinations thereof over time,
but never updated the documentation.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 6bc1804bfbfa..62f500c724f9 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -54,11 +54,13 @@ enum hrtimer_restart {
  * 0x00		inactive
  * 0x01		enqueued into rbtree
  * 0x02		callback function running
+ * 0x04		timer is migrated to another cpu
  *
  * Special cases:
  * 0x03		callback function running and enqueued
  *		(was requeued on another CPU)
- * 0x09		timer was migrated on CPU hotunplug
+ * 0x05		timer was migrated on CPU hotunplug
+ *
  * The "callback function running and enqueued" status is only possible on
  * SMP. It happens for example when a posix timer expired and the callback
  * queued a signal. Between dropping the lock which protects the posix timer
@@ -67,8 +69,11 @@ enum hrtimer_restart {
  * as otherwise the timer could be removed before the softirq code finishes the
  * the handling of the timer.
  *
- * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state to
- * preserve the HRTIMER_STATE_CALLBACK bit in the above scenario.
+ * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state
+ * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This
+ * also affects HRTIMER_STATE_MIGRATE where the preservation is not
+ * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is
+ * enqueued on the new cpu.
  *
  * All state transitions are protected by cpu_base->lock.
  */
@@ -376,8 +381,9 @@ extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
 extern ktime_t hrtimer_get_next_event(void);
 
 /*
- * A timer is active, when it is enqueued into the rbtree or the callback
- * function is running.
+ * A timer is active, when it is enqueued into the rbtree or the
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
  */
 static inline int hrtimer_active(const struct hrtimer *timer)
 {
-- 
cgit v1.2.3


From bb5d079aefa828c292c267ed34ed2282947fa233 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Fri, 18 Feb 2011 16:43:28 +0000
Subject: xen: events: drop XEN_ALLOC_IRQ flag to xen_allocate_pirq_msi

All callers pass this flag so it is pointless.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/xen.c   |  6 +++---
 drivers/xen/events.c | 12 +++++-------
 include/xen/events.h |  5 +----
 3 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 47c4688dcd48..ca5fa09ca56d 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -101,7 +101,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
 		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
 			xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-					"msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ);
+					"msi-x" : "msi", &irq, &pirq, 0);
 			if (irq < 0)
 				goto error;
 			ret = set_irq_msi(irq, msidesc);
@@ -112,7 +112,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			return 0;
 		}
 		xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-				"msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ));
+				"msi-x" : "msi", &irq, &pirq, 1);
 		if (irq < 0 || pirq < 0)
 			goto error;
 		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
@@ -160,7 +160,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		xen_allocate_pirq_msi(
 			(type == PCI_CAP_ID_MSIX) ?
 			"pcifront-msi-x" : "pcifront-msi",
-			&irq, &v[i], XEN_ALLOC_IRQ);
+			&irq, &v[i], 0);
 		if (irq < 0) {
 			ret = -1;
 			goto free;
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index bce303590075..36e9adcdebe9 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -664,17 +664,15 @@ static int find_unbound_pirq(int type)
 	return -1;
 }
 
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc)
+void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_pirq)
 {
 	spin_lock(&irq_mapping_update_lock);
 
-	if (alloc & XEN_ALLOC_IRQ) {
-		*irq = xen_allocate_irq_dynamic();
-		if (*irq == -1)
-			goto out;
-	}
+	*irq = xen_allocate_irq_dynamic();
+	if (*irq == -1)
+		goto out;
 
-	if (alloc & XEN_ALLOC_PIRQ) {
+	if (alloc_pirq) {
 		*pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
 		if (*pirq == -1) {
 			xen_free_irq(*irq);
diff --git a/include/xen/events.h b/include/xen/events.h
index 00f53ddcc062..8d98861e4d92 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -75,10 +75,7 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 
 #ifdef CONFIG_PCI_MSI
-/* Allocate an irq and a pirq to be used with MSIs. */
-#define XEN_ALLOC_PIRQ (1 << 0)
-#define XEN_ALLOC_IRQ  (1 << 1)
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_mask);
+void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_pirq);
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 
-- 
cgit v1.2.3


From 4b41df7f6e0b5684378d9155773c42a4577e8582 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Fri, 18 Feb 2011 16:43:29 +0000
Subject: xen: events: return irq from xen_allocate_pirq_msi

consistent with other similar functions.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/xen.c   | 12 ++++++------
 drivers/xen/events.c | 19 +++++++++++--------
 include/xen/events.h |  2 +-
 3 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index ca5fa09ca56d..6fd695b06faa 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -100,8 +100,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
 			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
 		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
-			xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-					"msi-x" : "msi", &irq, &pirq, 0);
+			irq = xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
+						    "msi-x" : "msi", &pirq, 0);
 			if (irq < 0)
 				goto error;
 			ret = set_irq_msi(irq, msidesc);
@@ -111,8 +111,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 					" pirq=%d\n", irq, pirq);
 			return 0;
 		}
-		xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-				"msi-x" : "msi", &irq, &pirq, 1);
+		irq = xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
+					    "msi-x" : "msi", &pirq, 1);
 		if (irq < 0 || pirq < 0)
 			goto error;
 		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
@@ -157,10 +157,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		goto error;
 	i = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		xen_allocate_pirq_msi(
+		irq = xen_allocate_pirq_msi(
 			(type == PCI_CAP_ID_MSIX) ?
 			"pcifront-msi-x" : "pcifront-msi",
-			&irq, &v[i], 0);
+			&v[i], 0);
 		if (irq < 0) {
 			ret = -1;
 			goto free;
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 36e9adcdebe9..ed3420df0937 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -664,31 +664,34 @@ static int find_unbound_pirq(int type)
 	return -1;
 }
 
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_pirq)
+int xen_allocate_pirq_msi(char *name, int *pirq, int alloc_pirq)
 {
+	int irq;
+
 	spin_lock(&irq_mapping_update_lock);
 
-	*irq = xen_allocate_irq_dynamic();
-	if (*irq == -1)
+	irq = xen_allocate_irq_dynamic();
+	if (irq == -1)
 		goto out;
 
 	if (alloc_pirq) {
 		*pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
 		if (*pirq == -1) {
-			xen_free_irq(*irq);
-			*irq = -1;
+			xen_free_irq(irq);
+			irq = -1;
 			goto out;
 		}
 	}
 
-	set_irq_chip_and_handler_name(*irq, &xen_pirq_chip,
+	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
 				      handle_level_irq, name);
 
-	irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0);
-	pirq_to_irq[*pirq] = *irq;
+	irq_info[irq] = mk_pirq_info(0, *pirq, 0, 0);
+	pirq_to_irq[*pirq] = irq;
 
 out:
 	spin_unlock(&irq_mapping_update_lock);
+	return irq;
 }
 
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
diff --git a/include/xen/events.h b/include/xen/events.h
index 8d98861e4d92..f70536af921c 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -75,7 +75,7 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 
 #ifdef CONFIG_PCI_MSI
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_pirq);
+int xen_allocate_pirq_msi(char *name, int *pirq, int alloc_pirq);
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 
-- 
cgit v1.2.3


From bf480d952bcf25e8ff7e95d2a23964107513ac51 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Fri, 18 Feb 2011 16:43:32 +0000
Subject: xen: events: separate MSI PIRQ allocation from PIRQ binding to IRQ

Split the binding aspect of xen_allocate_pirq_msi out into a new
xen_bind_pirq_to_irq function.

In xen_hvm_setup_msi_irq when allocating a pirq write the MSI message
to signal the PIRQ as soon as the pirq is obtained. There is no way to
free the pirq back so if the subsequent binding to an IRQ fails we
want to ensure that we will reuse the PIRQ next time rather than leak
it.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/xen.c   | 68 ++++++++++++++++++++--------------------------------
 drivers/xen/events.c | 30 +++++++++++------------
 include/xen/events.h |  4 +++-
 3 files changed, 43 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 0d5087eeced8..93e42152d8d0 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -86,7 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 
 static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	int irq, pirq, ret = 0;
+	int irq, pirq;
 	struct msi_desc *msidesc;
 	struct msi_msg msg;
 
@@ -94,39 +94,32 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		__read_msi_msg(msidesc, &msg);
 		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
 			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
-		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
-			irq = xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-						    "msi-x" : "msi", &pirq, 0);
-			if (irq < 0)
+		if (msg.data != XEN_PIRQ_MSI_DATA ||
+		    xen_irq_from_pirq(pirq) < 0) {
+			pirq = xen_allocate_pirq_msi(dev, msidesc);
+			if (pirq < 0)
 				goto error;
-			ret = set_irq_msi(irq, msidesc);
-			if (ret < 0)
-				goto error_while;
-			printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d"
-					" pirq=%d\n", irq, pirq);
-			return 0;
+			xen_msi_compose_msg(dev, pirq, &msg);
+			__write_msi_msg(msidesc, &msg);
+			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
+		} else {
+			dev_dbg(&dev->dev,
+				"xen: msi already bound to pirq=%d\n", pirq);
 		}
-		irq = xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-					    "msi-x" : "msi", &pirq, 1);
-		if (irq < 0 || pirq < 0)
+		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
+					       (type == PCI_CAP_ID_MSIX) ?
+					       "msi-x" : "msi");
+		if (irq < 0)
 			goto error;
-		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
-		xen_msi_compose_msg(dev, pirq, &msg);
-		ret = set_irq_msi(irq, msidesc);
-		if (ret < 0)
-			goto error_while;
-		write_msi_msg(irq, &msg);
+		dev_dbg(&dev->dev,
+			"xen: msi --> pirq=%d --> irq=%d\n", pirq, irq);
 	}
 	return 0;
 
-error_while:
-	unbind_from_irqhandler(irq, NULL);
 error:
-	if (ret == -ENODEV)
-		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
-				" MSI/MSI-X support!\n");
-
-	return ret;
+	dev_err(&dev->dev,
+		"Xen PCI frontend has not registered MSI/MSI-X support!\n");
+	return -ENODEV;
 }
 
 /*
@@ -152,28 +145,19 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		goto error;
 	i = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = xen_allocate_pirq_msi(
-			(type == PCI_CAP_ID_MSIX) ?
-			"pcifront-msi-x" : "pcifront-msi",
-			&v[i], 0);
-		if (irq < 0) {
-			ret = -1;
+		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
+					       (type == PCI_CAP_ID_MSIX) ?
+					       "pcifront-msi-x" :
+					       "pcifront-msi");
+		if (irq < 0)
 			goto free;
-		}
-		ret = set_irq_msi(irq, msidesc);
-		if (ret)
-			goto error_while;
 		i++;
 	}
 	kfree(v);
 	return 0;
 
-error_while:
-	unbind_from_irqhandler(irq, NULL);
 error:
-	if (ret == -ENODEV)
-		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
-			" MSI/MSI-X support!\n");
+	dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
 free:
 	kfree(v);
 	return ret;
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index c21066fc30be..1033f6284f31 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -647,12 +647,12 @@ out:
 #include <linux/msi.h>
 #include "../pci/msi.h"
 
-static int find_unbound_pirq(int type)
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 {
 	int rc;
 	struct physdev_get_free_pirq op_get_free_pirq;
 
-	op_get_free_pirq.type = type;
+	op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
 	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
 
 	WARN_ONCE(rc == -ENOSYS,
@@ -661,9 +661,10 @@ static int find_unbound_pirq(int type)
 	return rc ? -1 : op_get_free_pirq.pirq;
 }
 
-int xen_allocate_pirq_msi(char *name, int *pirq, int alloc_pirq)
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			     int pirq, const char *name)
 {
-	int irq;
+	int irq, ret;
 
 	spin_lock(&irq_mapping_update_lock);
 
@@ -671,24 +672,21 @@ int xen_allocate_pirq_msi(char *name, int *pirq, int alloc_pirq)
 	if (irq == -1)
 		goto out;
 
-	if (alloc_pirq) {
-		*pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
-		if (*pirq == -1) {
-			xen_free_irq(irq);
-			irq = -1;
-			goto out;
-		}
-	}
-
 	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
 				      handle_level_irq, name);
 
-	irq_info[irq] = mk_pirq_info(0, *pirq, 0, 0);
-	pirq_to_irq[*pirq] = irq;
-
+	irq_info[irq] = mk_pirq_info(0, pirq, 0, 0);
+	pirq_to_irq[pirq] = irq;
+	ret = set_irq_msi(irq, msidesc);
+	if (ret < 0)
+		goto error_irq;
 out:
 	spin_unlock(&irq_mapping_update_lock);
 	return irq;
+error_irq:
+	spin_unlock(&irq_mapping_update_lock);
+	xen_free_irq(irq);
+	return -1;
 }
 
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
diff --git a/include/xen/events.h b/include/xen/events.h
index f70536af921c..18bf825bac66 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -75,7 +75,9 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 
 #ifdef CONFIG_PCI_MSI
-int xen_allocate_pirq_msi(char *name, int *pirq, int alloc_pirq);
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			     int pirq, const char *name);
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 
-- 
cgit v1.2.3


From ca1d8fe9521fb67c95cfa736c08f4bbbc282b5bd Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@citrix.com>
Date: Fri, 18 Feb 2011 16:43:36 +0000
Subject: xen: events: use xen_bind_pirq_msi_to_irq from xen_create_msi_irq

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/xen.c   |  4 ++--
 drivers/xen/events.c | 36 +++++++-----------------------------
 include/xen/events.h |  2 +-
 3 files changed, 10 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 15fd981d35f1..ffd8c7a2cdbb 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -106,7 +106,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			dev_dbg(&dev->dev,
 				"xen: msi already bound to pirq=%d\n", pirq);
 		}
-		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
+		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
 					       (type == PCI_CAP_ID_MSIX) ?
 					       "msi-x" : "msi");
 		if (irq < 0)
@@ -145,7 +145,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		goto error;
 	i = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
+		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
 					       (type == PCI_CAP_ID_MSIX) ?
 					       "pcifront-msi-x" :
 					       "pcifront-msi");
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 77ede77a9ee9..34469489087b 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -662,7 +662,7 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 }
 
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-			     int pirq, const char *name)
+			     int pirq, int vector, const char *name)
 {
 	int irq, ret;
 
@@ -675,7 +675,7 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
 				      handle_level_irq, name);
 
-	irq_info[irq] = mk_pirq_info(0, pirq, 0, 0);
+	irq_info[irq] = mk_pirq_info(0, pirq, 0, vector);
 	pirq_to_irq[pirq] = irq;
 	ret = set_irq_msi(irq, msidesc);
 	if (ret < 0)
@@ -691,7 +691,6 @@ error_irq:
 
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
 {
-	int ret, irq = -1;
 	struct physdev_map_pirq map_irq;
 	int rc;
 	int pos;
@@ -719,34 +718,13 @@ int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
 	rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
 	if (rc) {
 		dev_warn(&dev->dev, "xen map irq failed %d\n", rc);
-		goto out;
+		return -1;
 	}
 
-	spin_lock(&irq_mapping_update_lock);
-
-	irq = xen_allocate_irq_dynamic();
-
-	if (irq == -1)
-		goto out;
-
-	irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index);
-	pirq_to_irq[map_irq.pirq] = irq;
-
-	set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
-			handle_level_irq,
-			(type == PCI_CAP_ID_MSIX) ? "msi-x":"msi");
-
-	ret = set_irq_msi(irq, msidesc);
-	if (ret)
-		goto out_irq;
-
-out:
-	spin_unlock(&irq_mapping_update_lock);
-	return irq;
-out_irq:
-	spin_unlock(&irq_mapping_update_lock);
-	xen_free_irq(irq);
-	return -1;
+	return xen_bind_pirq_msi_to_irq(dev, msidesc,
+					map_irq.pirq, map_irq.index,
+					(type == PCI_CAP_ID_MSIX) ?
+					"msi-x" : "msi");
 }
 #endif
 
diff --git a/include/xen/events.h b/include/xen/events.h
index 18bf825bac66..45c08a0d580a 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -77,7 +77,7 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 #ifdef CONFIG_PCI_MSI
 int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-			     int pirq, const char *name);
+			     int pirq, int vector, const char *name);
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 
-- 
cgit v1.2.3


From 71eef7d1e3d9df760897fdd2cad6949a8bcf1620 Mon Sep 17 00:00:00 2001
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Fri, 18 Feb 2011 17:06:55 +0000
Subject: xen: events: remove dom0 specific xen_create_msi_irq

The function name does not distinguish it from xen_allocate_pirq_msi
(which operates on domU and pvhvm domains rather than dom0).

Hoist domain 0 specific functionality up into the only caller leaving
functionality common to all guest types in xen_bind_pirq_msi_to_irq.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/xen.c   | 45 ++++++++++++++++++++++++++++++++++++++++-----
 drivers/xen/events.c | 41 -----------------------------------------
 include/xen/events.h |  1 -
 3 files changed, 40 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index ffd8c7a2cdbb..8c4085a95ef1 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -185,15 +185,50 @@ static void xen_teardown_msi_irq(unsigned int irq)
 #ifdef CONFIG_XEN_DOM0
 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	int irq;
+	int ret = 0;
 	struct msi_desc *msidesc;
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = xen_create_msi_irq(dev, msidesc, type);
-		if (irq < 0)
-			return -1;
+		struct physdev_map_pirq map_irq;
+
+		memset(&map_irq, 0, sizeof(map_irq));
+		map_irq.domid = DOMID_SELF;
+		map_irq.type = MAP_PIRQ_TYPE_MSI;
+		map_irq.index = -1;
+		map_irq.pirq = -1;
+		map_irq.bus = dev->bus->number;
+		map_irq.devfn = dev->devfn;
+
+		if (type == PCI_CAP_ID_MSIX) {
+			int pos;
+			u32 table_offset, bir;
+
+			pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+
+			pci_read_config_dword(dev, pos + PCI_MSIX_TABLE,
+					      &table_offset);
+			bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
+
+			map_irq.table_base = pci_resource_start(dev, bir);
+			map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
+		}
+
+		ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
+		if (ret) {
+			dev_warn(&dev->dev, "xen map irq failed %d\n", ret);
+			goto out;
+		}
+
+		ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
+					       map_irq.pirq, map_irq.index,
+					       (type == PCI_CAP_ID_MSIX) ?
+					       "msi-x" : "msi");
+		if (ret < 0)
+			goto out;
 	}
-	return 0;
+	ret = 0;
+out:
+	return ret;
 }
 #endif
 #endif
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 34469489087b..6befe6227159 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -644,9 +644,6 @@ out:
 }
 
 #ifdef CONFIG_PCI_MSI
-#include <linux/msi.h>
-#include "../pci/msi.h"
-
 int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 {
 	int rc;
@@ -688,44 +685,6 @@ error_irq:
 	xen_free_irq(irq);
 	return -1;
 }
-
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
-{
-	struct physdev_map_pirq map_irq;
-	int rc;
-	int pos;
-	u32 table_offset, bir;
-
-	memset(&map_irq, 0, sizeof(map_irq));
-	map_irq.domid = DOMID_SELF;
-	map_irq.type = MAP_PIRQ_TYPE_MSI;
-	map_irq.index = -1;
-	map_irq.pirq = -1;
-	map_irq.bus = dev->bus->number;
-	map_irq.devfn = dev->devfn;
-
-	if (type == PCI_CAP_ID_MSIX) {
-		pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-
-		pci_read_config_dword(dev, msix_table_offset_reg(pos),
-					&table_offset);
-		bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-
-		map_irq.table_base = pci_resource_start(dev, bir);
-		map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
-	}
-
-	rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
-	if (rc) {
-		dev_warn(&dev->dev, "xen map irq failed %d\n", rc);
-		return -1;
-	}
-
-	return xen_bind_pirq_msi_to_irq(dev, msidesc,
-					map_irq.pirq, map_irq.index,
-					(type == PCI_CAP_ID_MSIX) ?
-					"msi-x" : "msi");
-}
 #endif
 
 int xen_destroy_irq(int irq)
diff --git a/include/xen/events.h b/include/xen/events.h
index 45c08a0d580a..962da2ced5b4 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -78,7 +78,6 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 			     int pirq, int vector, const char *name);
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 
 /* De-allocates the above mentioned physical interrupt. */
-- 
cgit v1.2.3


From bf294b41cefcb22fc3139e0f42c5b3f06728bd5e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Mon, 21 Feb 2011 11:05:41 -0800
Subject: SUNRPC: Close a race in __rpc_wait_for_completion_task()

Although they run as rpciod background tasks, under normal operation
(i.e. no SIGKILL), functions like nfs_sillyrename(), nfs4_proc_unlck()
and nfs4_do_close() want to be fully synchronous. This means that when we
exit, we want all references to the rpc_task to be gone, and we want
any dentry references etc. held by that task to be released.

For this reason these functions call __rpc_wait_for_completion_task(),
followed by rpc_put_task() in the expectation that the latter will be
releasing the last reference to the rpc_task, and thus ensuring that the
callback_ops->rpc_release() has been called synchronously.

This patch fixes a race which exists due to the fact that
rpciod calls rpc_complete_task() (in order to wake up the callers of
__rpc_wait_for_completion_task()) and then subsequently calls
rpc_put_task() without ensuring that these two steps are done atomically.

In order to avoid adding new spin locks, the patch uses the existing
waitqueue spin lock to order the rpc_task reference count releases between
the waiting process and rpciod.
The common case where nobody is waiting for completion is optimised for by
checking if the RPC_TASK_ASYNC flag is cleared and/or if the rpc_task
reference count is 1: in those cases we drop trying to grab the spin lock,
and immediately free up the rpc_task.

Those few processes that need to put the rpc_task from inside an
asynchronous context and that do not care about ordering are given a new
helper: rpc_put_task_async().

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c            |  4 +--
 fs/nfs/unlink.c              |  2 +-
 include/linux/sunrpc/sched.h |  1 +
 kernel/sched.c               |  1 +
 net/sunrpc/sched.c           | 75 +++++++++++++++++++++++++++++++++++---------
 5 files changed, 66 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1ff76acc7e98..d1ed67145cf3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4150,7 +4150,7 @@ static void nfs4_lock_release(void *calldata)
 		task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
 				data->arg.lock_seqid);
 		if (!IS_ERR(task))
-			rpc_put_task(task);
+			rpc_put_task_async(task);
 		dprintk("%s: cancelling lock!\n", __func__);
 	} else
 		nfs_free_seqid(data->arg.lock_seqid);
@@ -5227,7 +5227,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
 	else
-		rpc_put_task(task);
+		rpc_put_task_async(task);
 	dprintk("<-- %s status=%d\n", __func__, ret);
 	return ret;
 }
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index e313a51acdd1..6481d537d69d 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -180,7 +180,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
 	task_setup_data.rpc_client = NFS_CLIENT(dir);
 	task = rpc_run_task(&task_setup_data);
 	if (!IS_ERR(task))
-		rpc_put_task(task);
+		rpc_put_task_async(task);
 	return 1;
 }
 
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 88513fd8e208..d81db8012c63 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -212,6 +212,7 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
 				const struct rpc_call_ops *ops);
 void		rpc_put_task(struct rpc_task *);
+void		rpc_put_task_async(struct rpc_task *);
 void		rpc_exit_task(struct rpc_task *);
 void		rpc_exit(struct rpc_task *, int);
 void		rpc_release_calldata(const struct rpc_call_ops *, void *);
diff --git a/kernel/sched.c b/kernel/sched.c
index 18d38e4ec7ba..42eab5a8437d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4213,6 +4213,7 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
 	__wake_up_common(q, mode, 1, 0, key);
 }
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 243fc09b164e..59e599498e37 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -252,23 +252,37 @@ static void rpc_set_active(struct rpc_task *task)
 
 /*
  * Mark an RPC call as having completed by clearing the 'active' bit
+ * and then waking up all tasks that were sleeping.
  */
-static void rpc_mark_complete_task(struct rpc_task *task)
+static int rpc_complete_task(struct rpc_task *task)
 {
-	smp_mb__before_clear_bit();
+	void *m = &task->tk_runstate;
+	wait_queue_head_t *wq = bit_waitqueue(m, RPC_TASK_ACTIVE);
+	struct wait_bit_key k = __WAIT_BIT_KEY_INITIALIZER(m, RPC_TASK_ACTIVE);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&wq->lock, flags);
 	clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
-	smp_mb__after_clear_bit();
-	wake_up_bit(&task->tk_runstate, RPC_TASK_ACTIVE);
+	ret = atomic_dec_and_test(&task->tk_count);
+	if (waitqueue_active(wq))
+		__wake_up_locked_key(wq, TASK_NORMAL, &k);
+	spin_unlock_irqrestore(&wq->lock, flags);
+	return ret;
 }
 
 /*
  * Allow callers to wait for completion of an RPC call
+ *
+ * Note the use of out_of_line_wait_on_bit() rather than wait_on_bit()
+ * to enforce taking of the wq->lock and hence avoid races with
+ * rpc_complete_task().
  */
 int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *))
 {
 	if (action == NULL)
 		action = rpc_wait_bit_killable;
-	return wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE,
+	return out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE,
 			action, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
@@ -857,34 +871,67 @@ static void rpc_async_release(struct work_struct *work)
 	rpc_free_task(container_of(work, struct rpc_task, u.tk_work));
 }
 
-void rpc_put_task(struct rpc_task *task)
+static void rpc_release_resources_task(struct rpc_task *task)
 {
-	if (!atomic_dec_and_test(&task->tk_count))
-		return;
-	/* Release resources */
 	if (task->tk_rqstp)
 		xprt_release(task);
 	if (task->tk_msg.rpc_cred)
 		put_rpccred(task->tk_msg.rpc_cred);
 	rpc_task_release_client(task);
-	if (task->tk_workqueue != NULL) {
+}
+
+static void rpc_final_put_task(struct rpc_task *task,
+		struct workqueue_struct *q)
+{
+	if (q != NULL) {
 		INIT_WORK(&task->u.tk_work, rpc_async_release);
-		queue_work(task->tk_workqueue, &task->u.tk_work);
+		queue_work(q, &task->u.tk_work);
 	} else
 		rpc_free_task(task);
 }
+
+static void rpc_do_put_task(struct rpc_task *task, struct workqueue_struct *q)
+{
+	if (atomic_dec_and_test(&task->tk_count)) {
+		rpc_release_resources_task(task);
+		rpc_final_put_task(task, q);
+	}
+}
+
+void rpc_put_task(struct rpc_task *task)
+{
+	rpc_do_put_task(task, NULL);
+}
 EXPORT_SYMBOL_GPL(rpc_put_task);
 
+void rpc_put_task_async(struct rpc_task *task)
+{
+	rpc_do_put_task(task, task->tk_workqueue);
+}
+EXPORT_SYMBOL_GPL(rpc_put_task_async);
+
 static void rpc_release_task(struct rpc_task *task)
 {
 	dprintk("RPC: %5u release task\n", task->tk_pid);
 
 	BUG_ON (RPC_IS_QUEUED(task));
 
-	/* Wake up anyone who is waiting for task completion */
-	rpc_mark_complete_task(task);
+	rpc_release_resources_task(task);
 
-	rpc_put_task(task);
+	/*
+	 * Note: at this point we have been removed from rpc_clnt->cl_tasks,
+	 * so it should be safe to use task->tk_count as a test for whether
+	 * or not any other processes still hold references to our rpc_task.
+	 */
+	if (atomic_read(&task->tk_count) != 1 + !RPC_IS_ASYNC(task)) {
+		/* Wake up anyone who may be waiting for task completion */
+		if (!rpc_complete_task(task))
+			return;
+	} else {
+		if (!atomic_dec_and_test(&task->tk_count))
+			return;
+	}
+	rpc_final_put_task(task, task->tk_workqueue);
 }
 
 int rpciod_up(void)
-- 
cgit v1.2.3


From 114f64b5f24abac33a42f4f1856eb3a9766d497e Mon Sep 17 00:00:00 2001
From: Andy Adamson <andros@netapp.com>
Date: Wed, 9 Mar 2011 13:13:45 -0500
Subject: NFSv4: remove duplicate clientid in struct nfs_client

Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4xdr.c          | 4 ++--
 include/linux/nfs_fs_sb.h | 2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4e2c168b6ee9..94d50e86a124 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1660,7 +1660,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 
 	p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12);
 	*p++ = cpu_to_be32(OP_CREATE_SESSION);
-	p = xdr_encode_hyper(p, clp->cl_ex_clid);
+	p = xdr_encode_hyper(p, clp->cl_clientid);
 	*p++ = cpu_to_be32(clp->cl_seqid);			/*Sequence id */
 	*p++ = cpu_to_be32(args->flags);			/*flags */
 
@@ -4694,7 +4694,7 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
-	xdr_decode_hyper(p, &clp->cl_ex_clid);
+	xdr_decode_hyper(p, &clp->cl_clientid);
 	p = xdr_inline_decode(xdr, 12);
 	if (unlikely(!p))
 		goto out_overflow;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b197563913bf..6beb33e834ba 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -71,8 +71,6 @@ struct nfs_client {
 #endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_NFS_V4_1
-	/* clientid returned from EXCHANGE_ID, used by session operations */
-	u64			cl_ex_clid;
 	/* The sequence id to use for the next CREATE_SESSION */
 	u32			cl_seqid;
 	/* The flags used for obtaining the clientid during EXCHANGE_ID */
-- 
cgit v1.2.3


From dbdd9a52e38a4a93adfa4d0278801cce4fad98eb Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 10 Mar 2011 16:34:38 -0800
Subject: ipv4: Remove redundant RCU locking in ip_check_mc().

All callers are under rcu_read_lock() protection already.

Rename to ip_check_mc_rcu() to make it even more clear.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/igmp.h | 2 +-
 net/ipv4/igmp.c      | 5 ++---
 net/ipv4/route.c     | 8 ++++----
 3 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 74cfcff0148b..82de336b8155 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -217,7 +217,7 @@ struct ip_mc_list {
 #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value)
 #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value)
 
-extern int ip_check_mc(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto);
+extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto);
 extern int igmp_rcv(struct sk_buff *);
 extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr);
 extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 44ba9068b72f..12b65ccca8e9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2333,13 +2333,13 @@ void ip_mc_drop_socket(struct sock *sk)
 	rtnl_unlock();
 }
 
-int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto)
+/* called with rcu_read_lock() */
+int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto)
 {
 	struct ip_mc_list *im;
 	struct ip_sf_list *psf;
 	int rv = 0;
 
-	rcu_read_lock();
 	for_each_pmc_rcu(in_dev, im) {
 		if (im->multiaddr == mc_addr)
 			break;
@@ -2361,7 +2361,6 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p
 		} else
 			rv = 1; /* unspecified source; tentatively allow */
 	}
-	rcu_read_unlock();
 	return rv;
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ac32d8f3d68f..f6730d94e307 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2309,8 +2309,8 @@ skip_cache:
 		struct in_device *in_dev = __in_dev_get_rcu(dev);
 
 		if (in_dev) {
-			int our = ip_check_mc(in_dev, daddr, saddr,
-					      ip_hdr(skb)->protocol);
+			int our = ip_check_mc_rcu(in_dev, daddr, saddr,
+						  ip_hdr(skb)->protocol);
 			if (our
 #ifdef CONFIG_IP_MROUTE
 				||
@@ -2368,8 +2368,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		fi = NULL;
 	} else if (type == RTN_MULTICAST) {
 		flags |= RTCF_MULTICAST | RTCF_LOCAL;
-		if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
-				 oldflp->proto))
+		if (!ip_check_mc_rcu(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
+				     oldflp->proto))
 			flags &= ~RTCF_LOCAL;
 		/* If multicast route do not exist use
 		 * default one, but do not gateway in this case.
-- 
cgit v1.2.3


From 1b7fe59322bef9e7a2c05b64a07a66b875299736 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 10 Mar 2011 17:01:16 -0800
Subject: ipv4: Kill flowi arg to fib_select_multipath()

Completely unused.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 2 +-
 net/ipv4/fib_semantics.c | 2 +-
 net/ipv4/route.c         | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 3f6c943faedc..d948e232eb06 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -230,7 +230,7 @@ extern int fib_sync_down_dev(struct net_device *dev, int force);
 extern int fib_sync_down_addr(struct net *net, __be32 local);
 extern void fib_update_nh_saddrs(struct net_device *dev);
 extern int fib_sync_up(struct net_device *dev);
-extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res);
+extern void fib_select_multipath(struct fib_result *res);
 
 /* Exported by fib_trie.c */
 extern void fib_trie_init(void);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d73d7581b51f..b5d523b911e6 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1210,7 +1210,7 @@ int fib_sync_up(struct net_device *dev)
  * The algorithm is suboptimal, but it provides really
  * fair weighted route distribution.
  */
-void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
+void fib_select_multipath(struct fib_result *res)
 {
 	struct fib_info *fi = res->fi;
 	int w;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a7ac90cb151d..9c17e32d5623 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2048,7 +2048,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1)
-		fib_select_multipath(fl, res);
+		fib_select_multipath(res);
 #endif
 
 	/* create a routing cache entry */
@@ -2598,7 +2598,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res.fi->fib_nhs > 1 && fl.oif == 0)
-		fib_select_multipath(&fl, &res);
+		fib_select_multipath(&res);
 	else
 #endif
 	if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
-- 
cgit v1.2.3


From e9bce845c0cee1a492e5cee6a827ae71140fe8b3 Mon Sep 17 00:00:00 2001
From: Yi Zou <yi.zou@intel.com>
Date: Wed, 9 Mar 2011 08:48:03 +0000
Subject: net: add proper documentation for previously added net_device_ops for
 FCoE

Add proper documentation for previously added net_device_ops ops for FCoE.

Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/netdevice.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7a071535c4c0..604dbf5051d3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -777,6 +777,42 @@ struct netdev_tc_txq {
  * 	queues stopped. This allows the netdevice to perform queue management
  * 	safely.
  *
+ *	Fiber Channel over Ethernet (FCoE) offload functions.
+ * int (*ndo_fcoe_enable)(struct net_device *dev);
+ *	Called when the FCoE protocol stack wants to start using LLD for FCoE
+ *	so the underlying device can perform whatever needed configuration or
+ *	initialization to support acceleration of FCoE traffic.
+ *
+ * int (*ndo_fcoe_disable)(struct net_device *dev);
+ *	Called when the FCoE protocol stack wants to stop using LLD for FCoE
+ *	so the underlying device can perform whatever needed clean-ups to
+ *	stop supporting acceleration of FCoE traffic.
+ *
+ * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid,
+ *			     struct scatterlist *sgl, unsigned int sgc);
+ *	Called when the FCoE Initiator wants to initialize an I/O that
+ *	is a possible candidate for Direct Data Placement (DDP). The LLD can
+ *	perform necessary setup and returns 1 to indicate the device is set up
+ *	successfully to perform DDP on this I/O, otherwise this returns 0.
+ *
+ * int (*ndo_fcoe_ddp_done)(struct net_device *dev,  u16 xid);
+ *	Called when the FCoE Initiator/Target is done with the DDPed I/O as
+ *	indicated by the FC exchange id 'xid', so the underlying device can
+ *	clean up and reuse resources for later DDP requests.
+ *
+ * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid,
+ *			      struct scatterlist *sgl, unsigned int sgc);
+ *	Called when the FCoE Target wants to initialize an I/O that
+ *	is a possible candidate for Direct Data Placement (DDP). The LLD can
+ *	perform necessary setup and returns 1 to indicate the device is set up
+ *	successfully to perform DDP on this I/O, otherwise this returns 0.
+ *
+ * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type);
+ *	Called when the underlying device wants to override default World Wide
+ *	Name (WWN) generation mechanism in FCoE protocol stack to pass its own
+ *	World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE
+ *	protocol stack to use.
+ *
  *	RFS acceleration.
  * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
  *			    u16 rxq_index, u32 flow_id);
-- 
cgit v1.2.3


From 37a9d912b24f96a0591773e6e6c3642991ae5a70 Mon Sep 17 00:00:00 2001
From: Michel Lespinasse <walken@google.com>
Date: Thu, 10 Mar 2011 18:48:51 -0800
Subject: futex: Sanitize cmpxchg_futex_value_locked API

The cmpxchg_futex_value_locked API was funny in that it returned either
the original, user-exposed futex value OR an error code such as -EFAULT.
This was confusing at best, and could be a source of livelocks in places
that retry the cmpxchg_futex_value_locked after trying to fix the issue
by running fault_in_user_writeable().

This change makes the cmpxchg_futex_value_locked API more similar to the
get_futex_value_locked one, returning an error code and updating the
original value through a reference argument.

Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>  [tile]
Acked-by: Tony Luck <tony.luck@intel.com>  [ia64]
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Michal Simek <monstr@monstr.eu>  [microblaze]
Acked-by: David Howells <dhowells@redhat.com> [frv]
Cc: Darren Hart <darren@dvhart.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <20110311024851.GC26122@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/alpha/include/asm/futex.h      | 22 +++++++++---------
 arch/arm/include/asm/futex.h        | 18 ++++++++-------
 arch/frv/include/asm/futex.h        |  3 ++-
 arch/ia64/include/asm/futex.h       |  9 +++++---
 arch/microblaze/include/asm/futex.h | 24 +++++++++++---------
 arch/mips/include/asm/futex.h       | 32 +++++++++++++-------------
 arch/parisc/include/asm/futex.h     | 18 +++++++--------
 arch/powerpc/include/asm/futex.h    | 20 +++++++++--------
 arch/s390/include/asm/futex.h       |  4 ++--
 arch/s390/include/asm/uaccess.h     |  2 +-
 arch/s390/lib/uaccess.h             |  4 ++--
 arch/s390/lib/uaccess_pt.c          | 13 ++++++-----
 arch/s390/lib/uaccess_std.c         |  6 +++--
 arch/sh/include/asm/futex-irq.h     |  9 ++++----
 arch/sh/include/asm/futex.h         |  5 +++--
 arch/sparc/include/asm/futex_64.h   | 16 ++++++++-----
 arch/tile/include/asm/futex.h       |  7 +++---
 arch/x86/include/asm/futex.h        | 16 +++++++------
 include/asm-generic/futex.h         |  3 ++-
 kernel/futex.c                      | 45 +++++++++++++------------------------
 20 files changed, 144 insertions(+), 132 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index 945de222ab91..c4e5c2850cce 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -81,21 +81,22 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
-	int prev, cmp;
+	int ret = 0, prev, cmp;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
 	__asm__ __volatile__ (
 		__ASM_SMP_MB
-	"1:	ldl_l	%0,0(%2)\n"
-	"	cmpeq	%0,%3,%1\n"
-	"	beq	%1,3f\n"
-	"	mov	%4,%1\n"
-	"2:	stl_c	%1,0(%2)\n"
-	"	beq	%1,4f\n"
+	"1:	ldl_l	%1,0(%3)\n"
+	"	cmpeq	%1,%4,%2\n"
+	"	beq	%2,3f\n"
+	"	mov	%5,%2\n"
+	"2:	stl_c	%2,0(%3)\n"
+	"	beq	%2,4f\n"
 	"3:	.subsection 2\n"
 	"4:	br	1b\n"
 	"	.previous\n"
@@ -105,11 +106,12 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	"	.long	2b-.\n"
 	"	lda	$31,3b-2b(%0)\n"
 	"	.previous\n"
-	:	"=&r"(prev), "=&r"(cmp)
+	:	"+r"(ret), "=&r"(prev), "=&r"(cmp)
 	:	"r"(uaddr), "r"((long)oldval), "r"(newval)
 	:	"memory");
 
-	return prev;
+	*uval = prev;
+	return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 7133a8620830..d20b78fce758 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -88,9 +88,10 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
-	int val;
+	int ret = 0, val;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
@@ -99,24 +100,25 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	 * call sites. */
 
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	" T(ldr) "	%0, [%3]\n"
-	"	teq	%0, %1\n"
+	"1:	" T(ldr) "	%1, [%4]\n"
+	"	teq	%1, %2\n"
 	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	" T(streq) "	%2, [%3]\n"
+	"2:	" T(streq) "	%3, [%4]\n"
 	"3:\n"
 	"	.pushsection __ex_table,\"a\"\n"
 	"	.align	3\n"
 	"	.long	1b, 4f, 2b, 4f\n"
 	"	.popsection\n"
 	"	.pushsection .fixup,\"ax\"\n"
-	"4:	mov	%0, %4\n"
+	"4:	mov	%0, %5\n"
 	"	b	3b\n"
 	"	.popsection"
-	: "=&r" (val)
+	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
 
-	return val;
+	*uval = val;
+	return ret;
 }
 
 #endif /* !SMP */
diff --git a/arch/frv/include/asm/futex.h b/arch/frv/include/asm/futex.h
index 08b3d1da3583..0548f8e4d11e 100644
--- a/arch/frv/include/asm/futex.h
+++ b/arch/frv/include/asm/futex.h
@@ -10,7 +10,8 @@
 extern int futex_atomic_op_inuser(int encoded_op, int __user *uaddr);
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
 	return -ENOSYS;
 }
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index c7f0f062239c..b0728404dad0 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -100,23 +100,26 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
 	{
-		register unsigned long r8 __asm ("r8");
+		register unsigned long r8 __asm ("r8") = 0;
+		unsigned long prev;
 		__asm__ __volatile__(
 			"	mf;;					\n"
 			"	mov ar.ccv=%3;;				\n"
 			"[1:]	cmpxchg4.acq %0=[%1],%2,ar.ccv		\n"
 			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
 			"[2:]"
-			: "=r" (r8)
+			: "=r" (prev)
 			: "r" (uaddr), "r" (newval),
 			  "rO" ((long) (unsigned) oldval)
 			: "memory");
+		*uval = prev;
 		return r8;
 	}
 }
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index ad3fd61b2fe7..fa019ed65dfb 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -94,31 +94,33 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
-	int prev, cmp;
+	int ret = 0, prev, cmp;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	__asm__ __volatile__ ("1:	lwx	%0, %2, r0;		\
-					cmp	%1, %0, %3;		\
-					beqi	%1, 3f;			\
-				2:	swx	%4, %2, r0;		\
-					addic	%1, r0, 0;		\
-					bnei	%1, 1b;			\
+	__asm__ __volatile__ ("1:	lwx	%1, %3, r0;		\
+					cmp	%2, %1, %4;		\
+					beqi	%2, 3f;			\
+				2:	swx	%5, %3, r0;		\
+					addic	%2, r0, 0;		\
+					bnei	%2, 1b;			\
 				3:					\
 				.section .fixup,\"ax\";			\
 				4:	brid	3b;			\
-					addik	%0, r0, %5;		\
+					addik	%0, r0, %6;		\
 				.previous;				\
 				.section __ex_table,\"a\";		\
 				.word	1b,4b,2b,4b;			\
 				.previous;"				\
-		: "=&r" (prev), "=&r"(cmp)				\
+		: "+r" (ret), "=&r" (prev), "=&r"(cmp)	\
 		: "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT));
 
-	return prev;
+	*uval = prev;
+	return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index b9cce90346cf..692a24bd83b7 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -132,9 +132,10 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
-	int retval;
+	int ret = 0, val;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
@@ -145,25 +146,25 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		"	.set	push					\n"
 		"	.set	noat					\n"
 		"	.set	mips3					\n"
-		"1:	ll	%0, %2					\n"
-		"	bne	%0, %z3, 3f				\n"
+		"1:	ll	%1, %3					\n"
+		"	bne	%1, %z4, 3f				\n"
 		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
+		"	move	$1, %z5					\n"
 		"	.set	mips3					\n"
-		"2:	sc	$1, %1					\n"
+		"2:	sc	$1, %2					\n"
 		"	beqzl	$1, 1b					\n"
 		__WEAK_LLSC_MB
 		"3:							\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
-		"4:	li	%0, %5					\n"
+		"4:	li	%0, %6					\n"
 		"	j	3b					\n"
 		"	.previous					\n"
 		"	.section __ex_table,\"a\"			\n"
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "=&r" (retval), "=R" (*uaddr)
+		: "+r" (ret), "=&r" (val), "=R" (*uaddr)
 		: "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
@@ -172,31 +173,32 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 		"	.set	push					\n"
 		"	.set	noat					\n"
 		"	.set	mips3					\n"
-		"1:	ll	%0, %2					\n"
-		"	bne	%0, %z3, 3f				\n"
+		"1:	ll	%1, %3					\n"
+		"	bne	%1, %z4, 3f				\n"
 		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
+		"	move	$1, %z5					\n"
 		"	.set	mips3					\n"
-		"2:	sc	$1, %1					\n"
+		"2:	sc	$1, %2					\n"
 		"	beqz	$1, 1b					\n"
 		__WEAK_LLSC_MB
 		"3:							\n"
 		"	.set	pop					\n"
 		"	.section .fixup,\"ax\"				\n"
-		"4:	li	%0, %5					\n"
+		"4:	li	%0, %6					\n"
 		"	j	3b					\n"
 		"	.previous					\n"
 		"	.section __ex_table,\"a\"			\n"
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "=&r" (retval), "=R" (*uaddr)
+		: "+r" (ret), "=&r" (val), "=R" (*uaddr)
 		: "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT)
 		: "memory");
 	} else
 		return -ENOSYS;
 
-	return retval;
+	*uval = val;
+	return ret;
 }
 
 #endif
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 0c705c3a55ef..4c6d8672325b 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -51,10 +51,10 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 
 /* Non-atomic version */
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
-	int err = 0;
-	int uval;
+	int val;
 
 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
@@ -65,12 +65,12 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	err = get_user(uval, uaddr);
-	if (err) return -EFAULT;
-	if (uval == oldval)
-		err = put_user(newval, uaddr);
-	if (err) return -EFAULT;
-	return uval;
+	if (get_user(val, uaddr))
+		return -EFAULT;
+	if (val == oldval && put_user(newval, uaddr))
+		return -EFAULT;
+	*uval = val;
+	return 0;
 }
 
 #endif /*__KERNEL__*/
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 7c589ef81fb0..631e8da60064 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -82,35 +82,37 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
-	int prev;
+	int ret = 0, prev;
 
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
         __asm__ __volatile__ (
         PPC_RELEASE_BARRIER
-"1:     lwarx   %0,0,%2         # futex_atomic_cmpxchg_inatomic\n\
-        cmpw    0,%0,%3\n\
+"1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
+        cmpw    0,%1,%4\n\
         bne-    3f\n"
-        PPC405_ERR77(0,%2)
-"2:     stwcx.  %4,0,%2\n\
+        PPC405_ERR77(0,%3)
+"2:     stwcx.  %5,0,%3\n\
         bne-    1b\n"
         PPC_ACQUIRE_BARRIER
 "3:	.section .fixup,\"ax\"\n\
-4:	li	%0,%5\n\
+4:	li	%0,%6\n\
 	b	3b\n\
 	.previous\n\
 	.section __ex_table,\"a\"\n\
 	.align 3\n\
 	" PPC_LONG "1b,4b,2b,4b\n\
 	.previous" \
-        : "=&r" (prev), "+m" (*uaddr)
+        : "+r" (ret), "=&r" (prev), "+m" (*uaddr)
         : "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT)
         : "cc", "memory");
 
-        return prev;
+	*uval = prev;
+        return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 5c5d02de49e9..27ac515ef59c 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -39,13 +39,13 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr,
+static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
 						int oldval, int newval)
 {
 	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	return uaccess.futex_atomic_cmpxchg(uaddr, oldval, newval);
+	return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index d6b1ed0ec52b..549adf6a9b8b 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -84,7 +84,7 @@ struct uaccess_ops {
 	size_t (*strnlen_user)(size_t, const char __user *);
 	size_t (*strncpy_from_user)(size_t, const char __user *, char *);
 	int (*futex_atomic_op)(int op, int __user *, int oparg, int *old);
-	int (*futex_atomic_cmpxchg)(int __user *, int old, int new);
+	int (*futex_atomic_cmpxchg)(int *, int __user *, int old, int new);
 };
 
 extern struct uaccess_ops uaccess;
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
index 126011df14f1..89a80674e44b 100644
--- a/arch/s390/lib/uaccess.h
+++ b/arch/s390/lib/uaccess.h
@@ -12,12 +12,12 @@ extern size_t copy_from_user_std(size_t, const void __user *, void *);
 extern size_t copy_to_user_std(size_t, void __user *, const void *);
 extern size_t strnlen_user_std(size_t, const char __user *);
 extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
-extern int futex_atomic_cmpxchg_std(int __user *, int, int);
+extern int futex_atomic_cmpxchg_std(int *, int __user *, int, int);
 extern int futex_atomic_op_std(int, int __user *, int, int *);
 
 extern size_t copy_from_user_pt(size_t, const void __user *, void *);
 extern size_t copy_to_user_pt(size_t, void __user *, const void *);
 extern int futex_atomic_op_pt(int, int __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(int __user *, int, int);
+extern int futex_atomic_cmpxchg_pt(int *, int __user *, int, int);
 
 #endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 404f2de296dc..b3cebcd52f5c 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -354,26 +354,29 @@ int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-static int __futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+static int __futex_atomic_cmpxchg_pt(int *uval, int __user *uaddr,
+				     int oldval, int newval)
 {
 	int ret;
 
 	asm volatile("0: cs   %1,%4,0(%5)\n"
-		     "1: lr   %0,%1\n"
+		     "1: la   %0,0\n"
 		     "2:\n"
 		     EX_TABLE(0b,2b) EX_TABLE(1b,2b)
 		     : "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		     : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		     : "cc", "memory" );
+	*uval = oldval;
 	return ret;
 }
 
-int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_pt(int *uval, int __user *uaddr,
+			    int oldval, int newval)
 {
 	int ret;
 
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+		return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
 	spin_lock(&current->mm->page_table_lock);
 	uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr);
 	if (!uaddr) {
@@ -382,7 +385,7 @@ int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
 	}
 	get_page(virt_to_page(uaddr));
 	spin_unlock(&current->mm->page_table_lock);
-	ret = __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+	ret = __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
 	put_page(virt_to_page(uaddr));
 	return ret;
 }
diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c
index a6c4f7ed24a4..1d6643c0b95f 100644
--- a/arch/s390/lib/uaccess_std.c
+++ b/arch/s390/lib/uaccess_std.c
@@ -287,19 +287,21 @@ int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_cmpxchg_std(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_std(int *uval, int __user *uaddr,
+			     int oldval, int newval)
 {
 	int ret;
 
 	asm volatile(
 		"   sacf 256\n"
 		"0: cs   %1,%4,0(%5)\n"
-		"1: lr   %0,%1\n"
+		"1: la   %0,0\n"
 		"2: sacf 0\n"
 		EX_TABLE(0b,2b) EX_TABLE(1b,2b)
 		: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		: "cc", "memory" );
+	*uval = oldval;
 	return ret;
 }
 
diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h
index a9f16a7f9aea..7b701cbd1e84 100644
--- a/arch/sh/include/asm/futex-irq.h
+++ b/arch/sh/include/asm/futex-irq.h
@@ -88,7 +88,8 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr,
+static inline int atomic_futex_op_cmpxchg_inatomic(int *uval,
+						   int __user *uaddr,
 						   int oldval, int newval)
 {
 	unsigned long flags;
@@ -102,10 +103,8 @@ static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr,
 
 	local_irq_restore(flags);
 
-	if (ret)
-		return ret;
-
-	return prev;
+	*uval = prev;
+	return ret;
 }
 
 #endif /* __ASM_SH_FUTEX_IRQ_H */
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
index 68256ec5fa35..a8a5125dc9b4 100644
--- a/arch/sh/include/asm/futex.h
+++ b/arch/sh/include/asm/futex.h
@@ -65,12 +65,13 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	return atomic_futex_op_cmpxchg_inatomic(uaddr, oldval, newval);
+	return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h
index 47f95839dc69..e0862200d6a1 100644
--- a/arch/sparc/include/asm/futex_64.h
+++ b/arch/sparc/include/asm/futex_64.h
@@ -85,26 +85,30 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
+	int ret = 0;
+
 	__asm__ __volatile__(
-	"\n1:	casa	[%3] %%asi, %2, %0\n"
+	"\n1:	casa	[%4] %%asi, %3, %1\n"
 	"2:\n"
 	"	.section .fixup,#alloc,#execinstr\n"
 	"	.align	4\n"
 	"3:	sethi	%%hi(2b), %0\n"
 	"	jmpl	%0 + %%lo(2b), %%g0\n"
-	"	 mov	%4, %0\n"
+	"	mov	%5, %0\n"
 	"	.previous\n"
 	"	.section __ex_table,\"a\"\n"
 	"	.align	4\n"
 	"	.word	1b, 3b\n"
 	"	.previous\n"
-	: "=r" (newval)
-	: "0" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT)
+	: "+r" (ret), "=r" (newval)
+	: "1" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT)
 	: "memory");
 
-	return newval;
+	*uval = newval;
+	return ret;
 }
 
 #endif /* !(_SPARC64_FUTEX_H) */
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index fe0d10dcae57..664b20aa2584 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -119,8 +119,8 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
-						int newval)
+static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+						int oldval, int newval)
 {
 	struct __get_user asm_ret;
 
@@ -128,7 +128,8 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
 		return -EFAULT;
 
 	asm_ret = futex_cmpxchg(uaddr, oldval, newval);
-	return asm_ret.err ? asm_ret.err : asm_ret.val;
+	*uval = asm_ret.val;
+	return asm_ret.err;
 }
 
 #ifndef __tilegx__
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 1f11ce44e956..884c0b5676f4 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -109,9 +109,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
-						int newval)
+static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+						int oldval, int newval)
 {
+	int ret = 0;
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
 	/* Real i386 machines have no cmpxchg instruction */
@@ -122,18 +123,19 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
+	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
 		     "2:\t.section .fixup, \"ax\"\n"
-		     "3:\tmov     %2, %0\n"
+		     "3:\tmov     %3, %0\n"
 		     "\tjmp     2b\n"
 		     "\t.previous\n"
 		     _ASM_EXTABLE(1b, 3b)
-		     : "=a" (oldval), "+m" (*uaddr)
-		     : "i" (-EFAULT), "r" (newval), "0" (oldval)
+		     : "+r" (ret), "=a" (oldval), "+m" (*uaddr)
+		     : "i" (-EFAULT), "r" (newval), "1" (oldval)
 		     : "memory"
 	);
 
-	return oldval;
+	*uval = oldval;
+	return ret;
 }
 
 #endif
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 3c2344f48136..132bf5227b44 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -48,7 +48,8 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
+			      int oldval, int newval)
 {
 	return -ENOSYS;
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 773815465bac..237f14bfc022 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -381,15 +381,16 @@ static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
 	return NULL;
 }
 
-static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
+static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
+				      u32 uval, u32 newval)
 {
-	u32 curval;
+	int ret;
 
 	pagefault_disable();
-	curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
 	pagefault_enable();
 
-	return curval;
+	return ret;
 }
 
 static int get_futex_value_locked(u32 *dest, u32 __user *from)
@@ -688,9 +689,7 @@ retry:
 	if (set_waiters)
 		newval |= FUTEX_WAITERS;
 
-	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
-	if (unlikely(curval == -EFAULT))
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
 		return -EFAULT;
 
 	/*
@@ -728,9 +727,7 @@ retry:
 		lock_taken = 1;
 	}
 
-	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-	if (unlikely(curval == -EFAULT))
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 	if (unlikely(curval != uval))
 		goto retry;
@@ -843,9 +840,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 
 		newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-		if (curval == -EFAULT)
+		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
 			ret = -EFAULT;
 		else if (curval != uval)
 			ret = -EINVAL;
@@ -880,10 +875,8 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
 	 * There is no waiter, so we unlock the futex. The owner died
 	 * bit has not to be preserved here. We are the owner:
 	 */
-	oldval = cmpxchg_futex_value_locked(uaddr, uval, 0);
-
-	if (oldval == -EFAULT)
-		return oldval;
+	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
+		return -EFAULT;
 	if (oldval != uval)
 		return -EAGAIN;
 
@@ -1578,9 +1571,7 @@ retry:
 	while (1) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-		if (curval == -EFAULT)
+		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
 			goto handle_fault;
 		if (curval == uval)
 			break;
@@ -2073,11 +2064,8 @@ retry:
 	 * again. If it succeeds then we can return without waking
 	 * anyone else up:
 	 */
-	if (!(uval & FUTEX_OWNER_DIED))
-		uval = cmpxchg_futex_value_locked(uaddr, vpid, 0);
-
-
-	if (unlikely(uval == -EFAULT))
+	if (!(uval & FUTEX_OWNER_DIED) &&
+	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
 		goto pi_faulted;
 	/*
 	 * Rare case: we managed to release the lock atomically,
@@ -2464,9 +2452,7 @@ retry:
 		 * userspace.
 		 */
 		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
-
-		if (nval == -EFAULT)
+		if (futex_atomic_cmpxchg_inatomic(&nval, uaddr, uval, mval))
 			return -1;
 
 		if (nval != uval)
@@ -2679,8 +2665,7 @@ static int __init futex_init(void)
 	 * implementation, the non-functional ones will return
 	 * -ENOSYS.
 	 */
-	curval = cmpxchg_futex_value_locked(NULL, 0, 0);
-	if (curval == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
 	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
-- 
cgit v1.2.3


From 8d7718aa082aaf30a0b4989e1f04858952f941bc Mon Sep 17 00:00:00 2001
From: Michel Lespinasse <walken@google.com>
Date: Thu, 10 Mar 2011 18:50:58 -0800
Subject: futex: Sanitize futex ops argument types

Change futex_atomic_op_inuser and futex_atomic_cmpxchg_inatomic
prototypes to use u32 types for the futex as this is the data type the
futex core code uses all over the place.

Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Darren Hart <darren@dvhart.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <20110311025058.GD26122@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/alpha/include/asm/futex.h      | 13 +++++++------
 arch/arm/include/asm/futex.h        | 13 +++++++------
 arch/frv/include/asm/futex.h        |  6 +++---
 arch/frv/kernel/futex.c             | 14 +++++++-------
 arch/ia64/include/asm/futex.h       | 10 +++++-----
 arch/microblaze/include/asm/futex.h | 13 +++++++------
 arch/mips/include/asm/futex.h       | 13 +++++++------
 arch/parisc/include/asm/futex.h     | 12 ++++++------
 arch/powerpc/include/asm/futex.h    | 13 +++++++------
 arch/s390/include/asm/futex.h       | 10 +++++-----
 arch/s390/include/asm/uaccess.h     |  4 ++--
 arch/s390/lib/uaccess.h             |  8 ++++----
 arch/s390/lib/uaccess_pt.c          | 12 ++++++------
 arch/s390/lib/uaccess_std.c         |  6 +++---
 arch/sh/include/asm/futex-irq.h     | 19 ++++++++++---------
 arch/sh/include/asm/futex.h         | 10 +++++-----
 arch/sparc/include/asm/futex_64.h   |  8 ++++----
 arch/tile/include/asm/futex.h       | 24 ++++++++++++------------
 arch/x86/include/asm/futex.h        | 10 +++++-----
 include/asm-generic/futex.h         |  8 ++++----
 20 files changed, 116 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index c4e5c2850cce..e8a761aee088 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -29,7 +29,7 @@
 	:	"r" (uaddr), "r"(oparg)				\
 	:	"memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -39,7 +39,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -81,12 +81,13 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int ret = 0, prev, cmp;
+	int ret = 0, cmp;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	__asm__ __volatile__ (
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index d20b78fce758..0e29d8e6a5c2 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -35,7 +35,7 @@
 	: "cc", "memory")
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -46,7 +46,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();	/* implies preempt_disable() */
@@ -88,12 +88,13 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int ret = 0, val;
+	int ret = 0;
+	u32 val;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	/* Note that preemption is disabled by futex_atomic_cmpxchg_inatomic
diff --git a/arch/frv/include/asm/futex.h b/arch/frv/include/asm/futex.h
index 0548f8e4d11e..4bea27f50a7a 100644
--- a/arch/frv/include/asm/futex.h
+++ b/arch/frv/include/asm/futex.h
@@ -7,11 +7,11 @@
 #include <asm/errno.h>
 #include <asm/uaccess.h>
 
-extern int futex_atomic_op_inuser(int encoded_op, int __user *uaddr);
+extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr);
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
 	return -ENOSYS;
 }
diff --git a/arch/frv/kernel/futex.c b/arch/frv/kernel/futex.c
index 14f64b054c7e..d155ca9e5098 100644
--- a/arch/frv/kernel/futex.c
+++ b/arch/frv/kernel/futex.c
@@ -18,7 +18,7 @@
  * the various futex operations; MMU fault checking is ignored under no-MMU
  * conditions
  */
-static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -50,7 +50,7 @@ static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_o
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -83,7 +83,7 @@ static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_o
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -116,7 +116,7 @@ static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_ol
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -149,7 +149,7 @@ static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_o
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_oldval)
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, int *_oldval)
 {
 	int oldval, ret;
 
@@ -186,7 +186,7 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_o
 /*
  * do the futex operations
  */
-int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -197,7 +197,7 @@ int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index b0728404dad0..8428525ddb22 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -46,7 +46,7 @@ do {									\
 } while (0)
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -56,7 +56,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -100,10 +100,10 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	{
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index fa019ed65dfb..b0526d2716fa 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -29,7 +29,7 @@
 })
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -39,7 +39,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -94,12 +94,13 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int ret = 0, prev, cmp;
+	int ret = 0, cmp;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	__asm__ __volatile__ ("1:	lwx	%1, %3, r0;		\
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index 692a24bd83b7..6ebf1734b411 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -75,7 +75,7 @@
 }
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -85,7 +85,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -132,12 +132,13 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int ret = 0, val;
+	int ret = 0;
+	u32 val;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	if (cpu_has_llsc && R10000_LLSC_WAR) {
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 4c6d8672325b..67a33cc27ef2 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -8,7 +8,7 @@
 #include <asm/errno.h>
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -18,7 +18,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -51,10 +51,10 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 
 /* Non-atomic version */
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int val;
+	u32 val;
 
 	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
 	 * our gateway page, and causes no end of trouble...
@@ -62,7 +62,7 @@ futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
 	if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
 		return -EFAULT;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	if (get_user(val, uaddr))
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 631e8da60064..c94e4a3fe2ef 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -30,7 +30,7 @@
 	: "b" (uaddr), "i" (-EFAULT), "r" (oparg) \
 	: "cr0", "memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -40,7 +40,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -82,12 +82,13 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int ret = 0, prev;
+	int ret = 0;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
         __asm__ __volatile__ (
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 27ac515ef59c..81cf36b691f1 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -7,7 +7,7 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -18,7 +18,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -39,10 +39,10 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-						int oldval, int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 549adf6a9b8b..2d9ea11f919a 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -83,8 +83,8 @@ struct uaccess_ops {
 	size_t (*clear_user)(size_t, void __user *);
 	size_t (*strnlen_user)(size_t, const char __user *);
 	size_t (*strncpy_from_user)(size_t, const char __user *, char *);
-	int (*futex_atomic_op)(int op, int __user *, int oparg, int *old);
-	int (*futex_atomic_cmpxchg)(int *, int __user *, int old, int new);
+	int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
+	int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
 };
 
 extern struct uaccess_ops uaccess;
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
index 89a80674e44b..1d2536cb630b 100644
--- a/arch/s390/lib/uaccess.h
+++ b/arch/s390/lib/uaccess.h
@@ -12,12 +12,12 @@ extern size_t copy_from_user_std(size_t, const void __user *, void *);
 extern size_t copy_to_user_std(size_t, void __user *, const void *);
 extern size_t strnlen_user_std(size_t, const char __user *);
 extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
-extern int futex_atomic_cmpxchg_std(int *, int __user *, int, int);
-extern int futex_atomic_op_std(int, int __user *, int, int *);
+extern int futex_atomic_cmpxchg_std(u32 *, u32 __user *, u32, u32);
+extern int futex_atomic_op_std(int, u32 __user *, int, int *);
 
 extern size_t copy_from_user_pt(size_t, const void __user *, void *);
 extern size_t copy_to_user_pt(size_t, void __user *, const void *);
-extern int futex_atomic_op_pt(int, int __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(int *, int __user *, int, int);
+extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
+extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
 
 #endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index b3cebcd52f5c..74833831417f 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -302,7 +302,7 @@ fault:
 		     : "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		       "m" (*uaddr) : "cc" );
 
-static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int oldval = 0, newval, ret;
 
@@ -335,7 +335,7 @@ static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int ret;
 
@@ -354,8 +354,8 @@ int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-static int __futex_atomic_cmpxchg_pt(int *uval, int __user *uaddr,
-				     int oldval, int newval)
+static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+				     u32 oldval, u32 newval)
 {
 	int ret;
 
@@ -370,8 +370,8 @@ static int __futex_atomic_cmpxchg_pt(int *uval, int __user *uaddr,
 	return ret;
 }
 
-int futex_atomic_cmpxchg_pt(int *uval, int __user *uaddr,
-			    int oldval, int newval)
+int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+			    u32 oldval, u32 newval)
 {
 	int ret;
 
diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c
index 1d6643c0b95f..bb1a7eed42ce 100644
--- a/arch/s390/lib/uaccess_std.c
+++ b/arch/s390/lib/uaccess_std.c
@@ -255,7 +255,7 @@ size_t strncpy_from_user_std(size_t size, const char __user *src, char *dst)
 		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		  "m" (*uaddr) : "cc");
 
-int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_std(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int oldval = 0, newval, ret;
 
@@ -287,8 +287,8 @@ int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_cmpxchg_std(int *uval, int __user *uaddr,
-			     int oldval, int newval)
+int futex_atomic_cmpxchg_std(u32 *uval, u32 __user *uaddr,
+			     u32 oldval, u32 newval)
 {
 	int ret;
 
diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h
index 7b701cbd1e84..6cb9f193a95e 100644
--- a/arch/sh/include/asm/futex-irq.h
+++ b/arch/sh/include/asm/futex-irq.h
@@ -3,7 +3,7 @@
 
 #include <asm/system.h>
 
-static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -20,7 +20,7 @@ static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -37,7 +37,7 @@ static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr,
 					  int *oldval)
 {
 	unsigned long flags;
@@ -54,7 +54,7 @@ static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -71,7 +71,7 @@ static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr,
+static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr,
 					   int *oldval)
 {
 	unsigned long flags;
@@ -88,12 +88,13 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr,
 	return ret;
 }
 
-static inline int atomic_futex_op_cmpxchg_inatomic(int *uval,
-						   int __user *uaddr,
-						   int oldval, int newval)
+static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval,
+						   u32 __user *uaddr,
+						   u32 oldval, u32 newval)
 {
 	unsigned long flags;
-	int ret, prev = 0;
+	int ret;
+	u32 prev = 0;
 
 	local_irq_save(flags);
 
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
index a8a5125dc9b4..7be39a646fbd 100644
--- a/arch/sh/include/asm/futex.h
+++ b/arch/sh/include/asm/futex.h
@@ -10,7 +10,7 @@
 /* XXX: UP variants, fix for SH-4A and SMP.. */
 #include <asm/futex-irq.h>
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -21,7 +21,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -65,10 +65,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval);
diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h
index e0862200d6a1..444e7bea23bc 100644
--- a/arch/sparc/include/asm/futex_64.h
+++ b/arch/sparc/include/asm/futex_64.h
@@ -30,7 +30,7 @@
 	: "r" (uaddr), "r" (oparg), "i" (-EFAULT)	\
 	: "memory")
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -38,7 +38,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret, tem;
 
-	if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(int))))
+	if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
 		return -EFAULT;
 	if (unlikely((((unsigned long) uaddr) & 0x3UL)))
 		return -EINVAL;
@@ -85,8 +85,8 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
 	int ret = 0;
 
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index 664b20aa2584..d03ec124a598 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -29,16 +29,16 @@
 #include <linux/uaccess.h>
 #include <linux/errno.h>
 
-extern struct __get_user futex_set(int __user *v, int i);
-extern struct __get_user futex_add(int __user *v, int n);
-extern struct __get_user futex_or(int __user *v, int n);
-extern struct __get_user futex_andn(int __user *v, int n);
-extern struct __get_user futex_cmpxchg(int __user *v, int o, int n);
+extern struct __get_user futex_set(u32 __user *v, int i);
+extern struct __get_user futex_add(u32 __user *v, int n);
+extern struct __get_user futex_or(u32 __user *v, int n);
+extern struct __get_user futex_andn(u32 __user *v, int n);
+extern struct __get_user futex_cmpxchg(u32 __user *v, int o, int n);
 
 #ifndef __tilegx__
-extern struct __get_user futex_xor(int __user *v, int n);
+extern struct __get_user futex_xor(u32 __user *v, int n);
 #else
-static inline struct __get_user futex_xor(int __user *uaddr, int n)
+static inline struct __get_user futex_xor(u32 __user *uaddr, int n)
 {
 	struct __get_user asm_ret = __get_user_4(uaddr);
 	if (!asm_ret.err) {
@@ -53,7 +53,7 @@ static inline struct __get_user futex_xor(int __user *uaddr, int n)
 }
 #endif
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -65,7 +65,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -119,12 +119,12 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-						int oldval, int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
 	struct __get_user asm_ret;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	asm_ret = futex_cmpxchg(uaddr, oldval, newval);
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 884c0b5676f4..d09bb03653f0 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -37,7 +37,7 @@
 		       "+m" (*uaddr), "=&r" (tem)		\
 		     : "r" (oparg), "i" (-EFAULT), "1" (0))
 
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -48,7 +48,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
@@ -109,8 +109,8 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-						int oldval, int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
 	int ret = 0;
 
@@ -120,7 +120,7 @@ static inline int futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
 		return -ENOSYS;
 #endif
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 132bf5227b44..01f227e14254 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -6,7 +6,7 @@
 #include <asm/errno.h>
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -16,7 +16,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -48,8 +48,8 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int *uval, int __user *uaddr,
-			      int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
 	return -ENOSYS;
 }
-- 
cgit v1.2.3


From d9936bb3952a08d701f7b03f8f62d158f94d8085 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 11 Mar 2011 14:15:35 +0100
Subject: genirq: Add desc->irq_data accessor

We have accessors for all fields in irq_data based on irq_desc, but
not for irq_data itself.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irqdesc.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 9eb9cd313052..00218371518b 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -109,6 +109,11 @@ static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
+static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
+{
+	return &desc->irq_data;
+}
+
 static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc)
 {
 	return desc->irq_data.chip;
-- 
cgit v1.2.3


From 3677713b799155c96637cdef3fa025e42f3fcf48 Mon Sep 17 00:00:00 2001
From: "John W. Linville" <linville@tuxdriver.com>
Date: Mon, 7 Mar 2011 16:17:59 -0500
Subject: wireless: add support for ethtool_ops->{get,set}_ringparam

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/cfg80211.h |  8 ++++++++
 net/wireless/ethtool.c | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1ac5786da14b..60f7876b6da8 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1197,6 +1197,10 @@ struct cfg80211_pmksa {
  *	(also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX).
  *
  * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant).
+ *
+ * @set_ringparam: Set tx and rx ring sizes.
+ *
+ * @get_ringparam: Get tx and rx ring current and maximum sizes.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy);
@@ -1364,6 +1368,10 @@ struct cfg80211_ops {
 
 	int	(*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant);
 	int	(*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant);
+
+	int	(*set_ringparam)(struct wiphy *wiphy, u32 tx, u32 rx);
+	void	(*get_ringparam)(struct wiphy *wiphy,
+				 u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max);
 };
 
 /*
diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c
index ca4c825be93d..9bde4d1d3e9b 100644
--- a/net/wireless/ethtool.c
+++ b/net/wireless/ethtool.c
@@ -1,5 +1,6 @@
 #include <linux/utsname.h>
 #include <net/cfg80211.h>
+#include "core.h"
 #include "ethtool.h"
 
 static void cfg80211_get_drvinfo(struct net_device *dev,
@@ -37,9 +38,41 @@ static void cfg80211_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	regs->len = 0;
 }
 
+static void cfg80211_get_ringparam(struct net_device *dev,
+				   struct ethtool_ringparam *rp)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+
+	memset(rp, 0, sizeof(*rp));
+
+	if (rdev->ops->get_ringparam)
+		rdev->ops->get_ringparam(wdev->wiphy,
+					 &rp->tx_pending, &rp->tx_max_pending,
+					 &rp->rx_pending, &rp->rx_max_pending);
+}
+
+static int cfg80211_set_ringparam(struct net_device *dev,
+				  struct ethtool_ringparam *rp)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+
+	if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0)
+		return -EINVAL;
+
+	if (rdev->ops->set_ringparam)
+		return rdev->ops->set_ringparam(wdev->wiphy,
+						rp->tx_pending, rp->rx_pending);
+
+	return -ENOTSUPP;
+}
+
 const struct ethtool_ops cfg80211_ethtool_ops = {
 	.get_drvinfo = cfg80211_get_drvinfo,
 	.get_regs_len = cfg80211_get_regs_len,
 	.get_regs = cfg80211_get_regs,
 	.get_link = ethtool_op_get_link,
+	.get_ringparam = cfg80211_get_ringparam,
+	.set_ringparam = cfg80211_set_ringparam,
 };
-- 
cgit v1.2.3


From bf6a9b8336ba12672755c2ae898b0abe42c7a5ac Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Tue, 21 Dec 2010 17:55:14 +0800
Subject: plist: Shrink struct plist_head

struct plist_head is used in struct task_struct as well as struct
rtmutex. If we can make it smaller, it will also make these structures
smaller as well.

The field prio_list in struct plist_head is seldom used and we can get
its information from the plist_nodes. Removing this field will decrease
the size of plist_head by half.

Signed-off-by:  Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4D107982.9090700@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/plist.h | 47 ++++++++++++++++++++++----------------------
 lib/plist.c           | 54 +++++++++++++++++++++++++++++++++------------------
 2 files changed, 59 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/linux/plist.h b/include/linux/plist.h
index 7254eda078e5..c9b9f322c8d8 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -31,15 +31,17 @@
  *
  * Simple ASCII art explanation:
  *
- * |HEAD          |
- * |              |
- * |prio_list.prev|<------------------------------------|
- * |prio_list.next|<->|pl|<->|pl|<--------------->|pl|<-|
- * |10            |   |10|   |21|   |21|   |21|   |40|   (prio)
- * |              |   |  |   |  |   |  |   |  |   |  |
- * |              |   |  |   |  |   |  |   |  |   |  |
- * |node_list.next|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
- * |node_list.prev|<------------------------------------|
+ * pl:prio_list (only for plist_node)
+ * nl:node_list
+ *   HEAD|             NODE(S)
+ *       |
+ *       ||------------------------------------|
+ *       ||->|pl|<->|pl|<--------------->|pl|<-|
+ *       |   |10|   |21|   |21|   |21|   |40|   (prio)
+ *       |   |  |   |  |   |  |   |  |   |  |
+ *       |   |  |   |  |   |  |   |  |   |  |
+ * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
+ * |-------------------------------------------|
  *
  * The nodes on the prio_list list are sorted by priority to simplify
  * the insertion of new nodes. There are no nodes with duplicate
@@ -78,7 +80,6 @@
 #include <linux/spinlock_types.h>
 
 struct plist_head {
-	struct list_head prio_list;
 	struct list_head node_list;
 #ifdef CONFIG_DEBUG_PI_LIST
 	raw_spinlock_t *rawlock;
@@ -88,7 +89,8 @@ struct plist_head {
 
 struct plist_node {
 	int			prio;
-	struct plist_head	plist;
+	struct list_head	prio_list;
+	struct list_head	node_list;
 };
 
 #ifdef CONFIG_DEBUG_PI_LIST
@@ -100,7 +102,6 @@ struct plist_node {
 #endif
 
 #define _PLIST_HEAD_INIT(head)				\
-	.prio_list = LIST_HEAD_INIT((head).prio_list),	\
 	.node_list = LIST_HEAD_INIT((head).node_list)
 
 /**
@@ -133,7 +134,8 @@ struct plist_node {
 #define PLIST_NODE_INIT(node, __prio)			\
 {							\
 	.prio  = (__prio),				\
-	.plist = { _PLIST_HEAD_INIT((node).plist) },	\
+	.prio_list = LIST_HEAD_INIT((node).prio_list),	\
+	.node_list = LIST_HEAD_INIT((node).node_list),	\
 }
 
 /**
@@ -144,7 +146,6 @@ struct plist_node {
 static inline void
 plist_head_init(struct plist_head *head, spinlock_t *lock)
 {
-	INIT_LIST_HEAD(&head->prio_list);
 	INIT_LIST_HEAD(&head->node_list);
 #ifdef CONFIG_DEBUG_PI_LIST
 	head->spinlock = lock;
@@ -160,7 +161,6 @@ plist_head_init(struct plist_head *head, spinlock_t *lock)
 static inline void
 plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
 {
-	INIT_LIST_HEAD(&head->prio_list);
 	INIT_LIST_HEAD(&head->node_list);
 #ifdef CONFIG_DEBUG_PI_LIST
 	head->rawlock = lock;
@@ -176,7 +176,8 @@ plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
 static inline void plist_node_init(struct plist_node *node, int prio)
 {
 	node->prio = prio;
-	plist_head_init(&node->plist, NULL);
+	INIT_LIST_HEAD(&node->prio_list);
+	INIT_LIST_HEAD(&node->node_list);
 }
 
 extern void plist_add(struct plist_node *node, struct plist_head *head);
@@ -188,7 +189,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * @head:	the head for your list
  */
 #define plist_for_each(pos, head)	\
-	 list_for_each_entry(pos, &(head)->node_list, plist.node_list)
+	 list_for_each_entry(pos, &(head)->node_list, node_list)
 
 /**
  * plist_for_each_safe - iterate safely over a plist of given type
@@ -199,7 +200,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * Iterate over a plist of given type, safe against removal of list entry.
  */
 #define plist_for_each_safe(pos, n, head)	\
-	 list_for_each_entry_safe(pos, n, &(head)->node_list, plist.node_list)
+	 list_for_each_entry_safe(pos, n, &(head)->node_list, node_list)
 
 /**
  * plist_for_each_entry	- iterate over list of given type
@@ -208,7 +209,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * @mem:	the name of the list_struct within the struct
  */
 #define plist_for_each_entry(pos, head, mem)	\
-	 list_for_each_entry(pos, &(head)->node_list, mem.plist.node_list)
+	 list_for_each_entry(pos, &(head)->node_list, mem.node_list)
 
 /**
  * plist_for_each_entry_safe - iterate safely over list of given type
@@ -220,7 +221,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
  * Iterate over list of given type, safe against removal of list entry.
  */
 #define plist_for_each_entry_safe(pos, n, head, m)	\
-	list_for_each_entry_safe(pos, n, &(head)->node_list, m.plist.node_list)
+	list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list)
 
 /**
  * plist_head_empty - return !0 if a plist_head is empty
@@ -237,7 +238,7 @@ static inline int plist_head_empty(const struct plist_head *head)
  */
 static inline int plist_node_empty(const struct plist_node *node)
 {
-	return plist_head_empty(&node->plist);
+	return list_empty(&node->node_list);
 }
 
 /* All functions below assume the plist_head is not empty. */
@@ -285,7 +286,7 @@ static inline int plist_node_empty(const struct plist_node *node)
 static inline struct plist_node *plist_first(const struct plist_head *head)
 {
 	return list_entry(head->node_list.next,
-			  struct plist_node, plist.node_list);
+			  struct plist_node, node_list);
 }
 
 /**
@@ -297,7 +298,7 @@ static inline struct plist_node *plist_first(const struct plist_head *head)
 static inline struct plist_node *plist_last(const struct plist_head *head)
 {
 	return list_entry(head->node_list.prev,
-			  struct plist_node, plist.node_list);
+			  struct plist_node, node_list);
 }
 
 #endif
diff --git a/lib/plist.c b/lib/plist.c
index 1471988d9190..8c614d0e6c35 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -59,7 +59,8 @@ static void plist_check_head(struct plist_head *head)
 		WARN_ON_SMP(!raw_spin_is_locked(head->rawlock));
 	if (head->spinlock)
 		WARN_ON_SMP(!spin_is_locked(head->spinlock));
-	plist_check_list(&head->prio_list);
+	if (!plist_head_empty(head))
+		plist_check_list(&plist_first(head)->prio_list);
 	plist_check_list(&head->node_list);
 }
 
@@ -75,25 +76,33 @@ static void plist_check_head(struct plist_head *head)
  */
 void plist_add(struct plist_node *node, struct plist_head *head)
 {
-	struct plist_node *iter;
+	struct plist_node *first, *iter, *prev = NULL;
+	struct list_head *node_next = &head->node_list;
 
 	plist_check_head(head);
 	WARN_ON(!plist_node_empty(node));
+	WARN_ON(!list_empty(&node->prio_list));
 
-	list_for_each_entry(iter, &head->prio_list, plist.prio_list) {
-		if (node->prio < iter->prio)
-			goto lt_prio;
-		else if (node->prio == iter->prio) {
-			iter = list_entry(iter->plist.prio_list.next,
-					struct plist_node, plist.prio_list);
-			goto eq_prio;
+	if (plist_head_empty(head))
+		goto ins_node;
+
+	first = iter = plist_first(head);
+
+	do {
+		if (node->prio < iter->prio) {
+			node_next = &iter->node_list;
+			break;
 		}
-	}
 
-lt_prio:
-	list_add_tail(&node->plist.prio_list, &iter->plist.prio_list);
-eq_prio:
-	list_add_tail(&node->plist.node_list, &iter->plist.node_list);
+		prev = iter;
+		iter = list_entry(iter->prio_list.next,
+				struct plist_node, prio_list);
+	} while (iter != first);
+
+	if (!prev || prev->prio != node->prio)
+		list_add_tail(&node->prio_list, &iter->prio_list);
+ins_node:
+	list_add_tail(&node->node_list, node_next);
 
 	plist_check_head(head);
 }
@@ -108,14 +117,21 @@ void plist_del(struct plist_node *node, struct plist_head *head)
 {
 	plist_check_head(head);
 
-	if (!list_empty(&node->plist.prio_list)) {
-		struct plist_node *next = plist_first(&node->plist);
+	if (!list_empty(&node->prio_list)) {
+		if (node->node_list.next != &head->node_list) {
+			struct plist_node *next;
+
+			next = list_entry(node->node_list.next,
+					struct plist_node, node_list);
 
-		list_move_tail(&next->plist.prio_list, &node->plist.prio_list);
-		list_del_init(&node->plist.prio_list);
+			/* add the next plist_node into prio_list */
+			if (list_empty(&next->prio_list))
+				list_add(&next->prio_list, &node->prio_list);
+		}
+		list_del_init(&node->prio_list);
 	}
 
-	list_del_init(&node->plist.node_list);
+	list_del_init(&node->node_list);
 
 	plist_check_head(head);
 }
-- 
cgit v1.2.3


From 0400a6b0cb756f976bae32ae8db47bfa9853897c Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Wed, 9 Mar 2011 16:00:53 -0500
Subject: NFSv4/4.1: Fix nfs4_schedule_state_recovery abuses

nfs4_schedule_state_recovery() should only be used when we need to force
the state manager to check the lease. If we just want to start the
state manager in order to handle a state recovery situation, we should be
using nfs4_schedule_state_manager().

This patch fixes the abuses of nfs4_schedule_state_recovery() by replacing
its use with a set of helper functions that do the right thing.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4_fs.h          |  8 +++++++-
 fs/nfs/nfs4proc.c         | 45 +++++++++++++++++++++++----------------------
 fs/nfs/nfs4state.c        | 25 +++++++++++++++++++------
 include/linux/nfs_fs_sb.h |  8 +++-----
 4 files changed, 52 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 7a7474073148..54ff900cb8f0 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -298,6 +298,11 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
 #if defined(CONFIG_NFS_V4_1)
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+extern void nfs4_schedule_session_recovery(struct nfs4_session *);
+#else
+static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
@@ -307,8 +312,9 @@ extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct path *, struct nfs4_state *, fmode_t);
 extern void nfs4_close_sync(struct path *, struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
-extern void nfs4_schedule_state_recovery(struct nfs_client *);
+extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
+extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
 extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
 extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0a13ae720dd0..411dc80d0656 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -257,12 +257,13 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 		case -NFS4ERR_OPENMODE:
 			if (state == NULL)
 				break;
-			nfs4_state_mark_reclaim_nograce(clp, state);
-			goto do_state_recovery;
+			nfs4_schedule_stateid_recovery(server, state);
+			goto wait_on_recovery;
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
-			goto do_state_recovery;
+			nfs4_schedule_lease_recovery(clp);
+			goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -273,7 +274,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 		case -NFS4ERR_SEQ_MISORDERED:
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
-			nfs4_schedule_state_recovery(clp);
+			nfs4_schedule_session_recovery(clp->cl_session);
 			exception->retry = 1;
 			break;
 #endif /* defined(CONFIG_NFS_V4_1) */
@@ -296,8 +297,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 	}
 	/* We failed to handle the error */
 	return nfs4_map_errors(ret);
-do_state_recovery:
-	nfs4_schedule_state_recovery(clp);
+wait_on_recovery:
 	ret = nfs4_wait_clnt_recover(clp);
 	if (ret == 0)
 		exception->retry = 1;
@@ -1256,14 +1256,13 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 			case -NFS4ERR_BAD_HIGH_SLOT:
 			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 			case -NFS4ERR_DEADSESSION:
-				nfs4_schedule_state_recovery(
-					server->nfs_client);
+				nfs4_schedule_session_recovery(server->nfs_client->cl_session);
 				goto out;
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
 				/* Don't recall a delegation if it was lost */
-				nfs4_schedule_state_recovery(server->nfs_client);
+				nfs4_schedule_lease_recovery(server->nfs_client);
 				goto out;
 			case -ERESTARTSYS:
 				/*
@@ -1272,7 +1271,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 				 */
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_BAD_STATEID:
-				nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+				nfs4_schedule_stateid_recovery(server, state);
 			case -EKEYEXPIRED:
 				/*
 				 * User RPCSEC_GSS context has expired.
@@ -1588,7 +1587,7 @@ static int nfs4_recover_expired_lease(struct nfs_server *server)
 		if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
 		    !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
 			break;
-		nfs4_schedule_state_recovery(clp);
+		nfs4_schedule_state_manager(clp);
 		ret = -EIO;
 	}
 	return ret;
@@ -3179,7 +3178,7 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata)
 	if (task->tk_status < 0) {
 		/* Unless we're shutting down, schedule state recovery! */
 		if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) != 0)
-			nfs4_schedule_state_recovery(clp);
+			nfs4_schedule_lease_recovery(clp);
 		return;
 	}
 	do_renew_lease(clp, timestamp);
@@ -3504,12 +3503,13 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_OPENMODE:
 			if (state == NULL)
 				break;
-			nfs4_state_mark_reclaim_nograce(clp, state);
-			goto do_state_recovery;
+			nfs4_schedule_stateid_recovery(server, state);
+			goto wait_on_recovery;
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_EXPIRED:
-			goto do_state_recovery;
+			nfs4_schedule_lease_recovery(clp);
+			goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -3520,7 +3520,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_SEQ_MISORDERED:
 			dprintk("%s ERROR %d, Reset session\n", __func__,
 				task->tk_status);
-			nfs4_schedule_state_recovery(clp);
+			nfs4_schedule_session_recovery(clp->cl_session);
 			task->tk_status = 0;
 			return -EAGAIN;
 #endif /* CONFIG_NFS_V4_1 */
@@ -3537,9 +3537,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 	}
 	task->tk_status = nfs4_map_errors(task->tk_status);
 	return 0;
-do_state_recovery:
+wait_on_recovery:
 	rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
-	nfs4_schedule_state_recovery(clp);
 	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
 		rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
 	task->tk_status = 0;
@@ -4406,12 +4405,14 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 			case -NFS4ERR_EXPIRED:
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_STALE_STATEID:
+				nfs4_schedule_lease_recovery(server->nfs_client);
+				goto out;
 			case -NFS4ERR_BADSESSION:
 			case -NFS4ERR_BADSLOT:
 			case -NFS4ERR_BAD_HIGH_SLOT:
 			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 			case -NFS4ERR_DEADSESSION:
-				nfs4_schedule_state_recovery(server->nfs_client);
+				nfs4_schedule_session_recovery(server->nfs_client->cl_session);
 				goto out;
 			case -ERESTARTSYS:
 				/*
@@ -4421,7 +4422,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_BAD_STATEID:
 			case -NFS4ERR_OPENMODE:
-				nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+				nfs4_schedule_stateid_recovery(server, state);
 				err = 0;
 				goto out;
 			case -EKEYEXPIRED:
@@ -5150,7 +5151,7 @@ static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		return -EAGAIN;
 	default:
-		nfs4_schedule_state_recovery(clp);
+		nfs4_schedule_lease_recovery(clp);
 	}
 	return 0;
 }
@@ -5291,7 +5292,7 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		return -EAGAIN;
 	default:
-		nfs4_schedule_state_recovery(clp);
+		nfs4_schedule_lease_recovery(clp);
 	}
 	return 0;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e6742b57a04c..47c8dcdada8a 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1007,9 +1007,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 }
 
 /*
- * Schedule a state recovery attempt
+ * Schedule a lease recovery attempt
  */
-void nfs4_schedule_state_recovery(struct nfs_client *clp)
+void nfs4_schedule_lease_recovery(struct nfs_client *clp)
 {
 	if (!clp)
 		return;
@@ -1041,6 +1041,14 @@ int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *s
 	return 1;
 }
 
+void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state)
+{
+	struct nfs_client *clp = server->nfs_client;
+
+	nfs4_state_mark_reclaim_nograce(clp, state);
+	nfs4_schedule_state_manager(clp);
+}
+
 static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
 {
 	struct inode *inode = state->inode;
@@ -1436,10 +1444,15 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 }
 
 #ifdef CONFIG_NFS_V4_1
+void nfs4_schedule_session_recovery(struct nfs4_session *session)
+{
+	nfs4_schedule_lease_recovery(session->clp);
+}
+
 void nfs41_handle_recall_slot(struct nfs_client *clp)
 {
 	set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
-	nfs4_schedule_state_recovery(clp);
+	nfs4_schedule_state_manager(clp);
 }
 
 static void nfs4_reset_all_state(struct nfs_client *clp)
@@ -1447,7 +1460,7 @@ static void nfs4_reset_all_state(struct nfs_client *clp)
 	if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
 		clp->cl_boot_time = CURRENT_TIME;
 		nfs4_state_start_reclaim_nograce(clp);
-		nfs4_schedule_state_recovery(clp);
+		nfs4_schedule_state_manager(clp);
 	}
 }
 
@@ -1455,7 +1468,7 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp)
 {
 	if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
 		nfs4_state_start_reclaim_reboot(clp);
-		nfs4_schedule_state_recovery(clp);
+		nfs4_schedule_state_manager(clp);
 	}
 }
 
@@ -1475,7 +1488,7 @@ static void nfs41_handle_cb_path_down(struct nfs_client *clp)
 {
 	nfs_expire_all_delegations(clp);
 	if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
-		nfs4_schedule_state_recovery(clp);
+		nfs4_schedule_state_manager(clp);
 }
 
 void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 6beb33e834ba..3e112de12d8d 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -68,9 +68,7 @@ struct nfs_client {
 	unsigned char		cl_id_uniquifier;
 	u32			cl_cb_ident;	/* v4.0 callback identifier */
 	const struct nfs4_minor_version_ops *cl_mvops;
-#endif /* CONFIG_NFS_V4 */
 
-#ifdef CONFIG_NFS_V4_1
 	/* The sequence id to use for the next CREATE_SESSION */
 	u32			cl_seqid;
 	/* The flags used for obtaining the clientid during EXCHANGE_ID */
@@ -78,7 +76,7 @@ struct nfs_client {
 	struct nfs4_session	*cl_session; 	/* sharred session */
 	struct list_head	cl_layouts;
 	struct pnfs_deviceid_cache *cl_devid_cache; /* pNFS deviceid cache */
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_NFS_FSCACHE
 	struct fscache_cookie	*fscache;	/* client index cache cookie */
@@ -183,7 +181,7 @@ struct nfs_server {
 /* maximum number of slots to use */
 #define NFS4_MAX_SLOT_TABLE RPC_MAX_SLOT_TABLE
 
-#if defined(CONFIG_NFS_V4_1)
+#if defined(CONFIG_NFS_V4)
 
 /* Sessions */
 #define SLOT_TABLE_SZ (NFS4_MAX_SLOT_TABLE/(8*sizeof(long)))
@@ -223,5 +221,5 @@ struct nfs4_session {
 	struct nfs_client		*clp;
 };
 
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_NFS_V4 */
 #endif
-- 
cgit v1.2.3


From 38c091590f6ed78fcaf114c14ce133e5b3f717e6 Mon Sep 17 00:00:00 2001
From: "John W. Linville" <linville@tuxdriver.com>
Date: Mon, 7 Mar 2011 16:19:18 -0500
Subject: mac80211: implement support for cfg80211_ops->{get,set}_ringparam

Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/mac80211.h      |  7 ++++++
 net/mac80211/cfg.c          | 17 +++++++++++++++
 net/mac80211/driver-ops.h   | 26 +++++++++++++++++++++++
 net/mac80211/driver-trace.h | 52 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 102 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 2b072fa99399..8650e7bf2ed0 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1804,6 +1804,10 @@ enum ieee80211_ampdu_mlme_action {
  *	return value is 1, then the @remain_on_channel will be used with a
  *	regular transmission (if supported.)
  * @offchannel_tx_cancel_wait: cancel wait associated with offchannel TX
+ *
+ * @set_ringparam: Set tx and rx ring sizes.
+ *
+ * @get_ringparam: Get tx and rx ring current and maximum sizes.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb);
@@ -1888,6 +1892,9 @@ struct ieee80211_ops {
 			     enum nl80211_channel_type channel_type,
 			     unsigned int wait);
 	int (*offchannel_tx_cancel_wait)(struct ieee80211_hw *hw);
+	int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx);
+	void (*get_ringparam)(struct ieee80211_hw *hw,
+			      u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max);
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 11866b42f1ed..334213571ad0 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2012,6 +2012,21 @@ static int ieee80211_get_antenna(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant)
 	return drv_get_antenna(local, tx_ant, rx_ant);
 }
 
+static int ieee80211_set_ringparam(struct wiphy *wiphy, u32 tx, u32 rx)
+{
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+
+	return drv_set_ringparam(local, tx, rx);
+}
+
+static void ieee80211_get_ringparam(struct wiphy *wiphy,
+				    u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max)
+{
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+
+	drv_get_ringparam(local, tx, tx_max, rx, rx_max);
+}
+
 struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -2069,4 +2084,6 @@ struct cfg80211_ops mac80211_config_ops = {
 	.mgmt_frame_register = ieee80211_mgmt_frame_register,
 	.set_antenna = ieee80211_set_antenna,
 	.get_antenna = ieee80211_get_antenna,
+	.set_ringparam = ieee80211_set_ringparam,
+	.get_ringparam = ieee80211_get_ringparam,
 };
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 3729296f6f95..9c0d62bb0ea3 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -526,4 +526,30 @@ static inline int drv_offchannel_tx_cancel_wait(struct ieee80211_local *local)
 	return ret;
 }
 
+static inline int drv_set_ringparam(struct ieee80211_local *local,
+				    u32 tx, u32 rx)
+{
+	int ret = -ENOTSUPP;
+
+	might_sleep();
+
+	trace_drv_set_ringparam(local, tx, rx);
+	if (local->ops->set_ringparam)
+		ret = local->ops->set_ringparam(&local->hw, tx, rx);
+	trace_drv_return_int(local, ret);
+
+	return ret;
+}
+
+static inline void drv_get_ringparam(struct ieee80211_local *local,
+				     u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max)
+{
+	might_sleep();
+
+	trace_drv_get_ringparam(local, tx, tx_max, rx, rx_max);
+	if (local->ops->get_ringparam)
+		local->ops->get_ringparam(&local->hw, tx, tx_max, rx, rx_max);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h
index 520fe2444893..45aab80738e2 100644
--- a/net/mac80211/driver-trace.h
+++ b/net/mac80211/driver-trace.h
@@ -912,6 +912,58 @@ TRACE_EVENT(drv_offchannel_tx,
 	)
 );
 
+TRACE_EVENT(drv_set_ringparam,
+	TP_PROTO(struct ieee80211_local *local, u32 tx, u32 rx),
+
+	TP_ARGS(local, tx, rx),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(u32, tx)
+		__field(u32, rx)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->tx = tx;
+		__entry->rx = rx;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT " tx:%d rx %d",
+		LOCAL_PR_ARG, __entry->tx, __entry->rx
+	)
+);
+
+TRACE_EVENT(drv_get_ringparam,
+	TP_PROTO(struct ieee80211_local *local, u32 *tx, u32 *tx_max,
+		 u32 *rx, u32 *rx_max),
+
+	TP_ARGS(local, tx, tx_max, rx, rx_max),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(u32, tx)
+		__field(u32, tx_max)
+		__field(u32, rx)
+		__field(u32, rx_max)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->tx = *tx;
+		__entry->tx_max = *tx_max;
+		__entry->rx = *rx;
+		__entry->rx_max = *rx_max;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT " tx:%d tx_max %d rx %d rx_max %d",
+		LOCAL_PR_ARG,
+		__entry->tx, __entry->tx_max, __entry->rx, __entry->rx_max
+	)
+);
+
 DEFINE_EVENT(local_only_evt, drv_offchannel_tx_cancel_wait,
 	TP_PROTO(struct ieee80211_local *local),
 	TP_ARGS(local)
-- 
cgit v1.2.3


From ee398ba97dd76ed53bed548dec648d918af4004c Mon Sep 17 00:00:00 2001
From: Benoit Goby <benoit@android.com>
Date: Wed, 9 Mar 2011 16:28:54 -0800
Subject: usb: otg: Add ulpi viewport access ops

Add generic access ops for controllers with a ulpi viewport register
(e.g. Chipidea/ARC based controllers).

Signed-off-by: Benoit Goby <benoit@android.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/otg/Kconfig         |  7 ++++
 drivers/usb/otg/Makefile        |  1 +
 drivers/usb/otg/ulpi_viewport.c | 80 +++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/ulpi.h        |  5 +++
 4 files changed, 93 insertions(+)
 create mode 100644 drivers/usb/otg/ulpi_viewport.c

(limited to 'include')

diff --git a/drivers/usb/otg/Kconfig b/drivers/usb/otg/Kconfig
index ceb24fee2eac..daf3e5f1a0e7 100644
--- a/drivers/usb/otg/Kconfig
+++ b/drivers/usb/otg/Kconfig
@@ -49,6 +49,13 @@ config USB_ULPI
 	  Enable this to support ULPI connected USB OTG transceivers which
 	  are likely found on embedded boards.
 
+config USB_ULPI_VIEWPORT
+	bool
+	depends on USB_ULPI
+	help
+	  Provides read/write operations to the ULPI phy register set for
+	  controllers with a viewport register (e.g. Chipidea/ARC controllers).
+
 config TWL4030_USB
 	tristate "TWL4030 USB Transceiver Driver"
 	depends on TWL4030_CORE && REGULATOR_TWL4030
diff --git a/drivers/usb/otg/Makefile b/drivers/usb/otg/Makefile
index e516894260bf..e22d917de017 100644
--- a/drivers/usb/otg/Makefile
+++ b/drivers/usb/otg/Makefile
@@ -16,5 +16,6 @@ obj-$(CONFIG_TWL6030_USB)	+= twl6030-usb.o
 obj-$(CONFIG_USB_LANGWELL_OTG)	+= langwell_otg.o
 obj-$(CONFIG_NOP_USB_XCEIV)	+= nop-usb-xceiv.o
 obj-$(CONFIG_USB_ULPI)		+= ulpi.o
+obj-$(CONFIG_USB_ULPI_VIEWPORT)	+= ulpi_viewport.o
 obj-$(CONFIG_USB_MSM_OTG)	+= msm_otg.o
 obj-$(CONFIG_AB8500_USB)	+= ab8500-usb.o
diff --git a/drivers/usb/otg/ulpi_viewport.c b/drivers/usb/otg/ulpi_viewport.c
new file mode 100644
index 000000000000..e9a37f90994f
--- /dev/null
+++ b/drivers/usb/otg/ulpi_viewport.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/usb.h>
+#include <linux/io.h>
+#include <linux/usb/otg.h>
+#include <linux/usb/ulpi.h>
+
+#define ULPI_VIEW_WAKEUP	(1 << 31)
+#define ULPI_VIEW_RUN		(1 << 30)
+#define ULPI_VIEW_WRITE		(1 << 29)
+#define ULPI_VIEW_READ		(0 << 29)
+#define ULPI_VIEW_ADDR(x)	(((x) & 0xff) << 16)
+#define ULPI_VIEW_DATA_READ(x)	(((x) >> 8) & 0xff)
+#define ULPI_VIEW_DATA_WRITE(x)	((x) & 0xff)
+
+static int ulpi_viewport_wait(void __iomem *view, u32 mask)
+{
+	unsigned long usec = 2000;
+
+	while (usec--) {
+		if (!(readl(view) & mask))
+			return 0;
+
+		udelay(1);
+	};
+
+	return -ETIMEDOUT;
+}
+
+static int ulpi_viewport_read(struct otg_transceiver *otg, u32 reg)
+{
+	int ret;
+	void __iomem *view = otg->io_priv;
+
+	writel(ULPI_VIEW_WAKEUP | ULPI_VIEW_WRITE, view);
+	ret = ulpi_viewport_wait(view, ULPI_VIEW_WAKEUP);
+	if (ret)
+		return ret;
+
+	writel(ULPI_VIEW_RUN | ULPI_VIEW_READ | ULPI_VIEW_ADDR(reg), view);
+	ret = ulpi_viewport_wait(view, ULPI_VIEW_RUN);
+	if (ret)
+		return ret;
+
+	return ULPI_VIEW_DATA_READ(readl(view));
+}
+
+static int ulpi_viewport_write(struct otg_transceiver *otg, u32 val, u32 reg)
+{
+	int ret;
+	void __iomem *view = otg->io_priv;
+
+	writel(ULPI_VIEW_WAKEUP | ULPI_VIEW_WRITE, view);
+	ret = ulpi_viewport_wait(view, ULPI_VIEW_WAKEUP);
+	if (ret)
+		return ret;
+
+	writel(ULPI_VIEW_RUN | ULPI_VIEW_WRITE | ULPI_VIEW_DATA_WRITE(val) |
+						 ULPI_VIEW_ADDR(reg), view);
+
+	return ulpi_viewport_wait(view, ULPI_VIEW_RUN);
+}
+
+struct otg_io_access_ops ulpi_viewport_access_ops = {
+	.read	= ulpi_viewport_read,
+	.write	= ulpi_viewport_write,
+};
diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h
index 82b1507f4735..9595796d62ed 100644
--- a/include/linux/usb/ulpi.h
+++ b/include/linux/usb/ulpi.h
@@ -184,4 +184,9 @@
 struct otg_transceiver *otg_ulpi_create(struct otg_io_access_ops *ops,
 					unsigned int flags);
 
+#ifdef CONFIG_USB_ULPI_VIEWPORT
+/* access ops for controllers with a viewport register */
+extern struct otg_io_access_ops ulpi_viewport_access_ops;
+#endif
+
 #endif /* __LINUX_USB_ULPI_H */
-- 
cgit v1.2.3


From 79ad3b5add4a683af02d1b51ccb699d1b01f1fbf Mon Sep 17 00:00:00 2001
From: Benoit Goby <benoit@android.com>
Date: Wed, 9 Mar 2011 16:28:56 -0800
Subject: usb: host: Add EHCI driver for NVIDIA Tegra SoCs

The Tegra 2 SoC has 3 EHCI compatible USB controllers. This patch adds
the necessary glue to allow the ehci-hcd driver to work on Tegra 2
SoCs.

The platform data is used to configure board-specific phy settings and
to configure the operating mode, as one of the ports may be used as a otg
port. For additional power saving, the driver supports powering down the
phy on bus suspend when it is used, for example, to connect an internal
device that use an out-of-band remote wakeup mechanism (e.g. a gpio).

Signed-off-by: Benoit Goby <benoit@android.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/host/Kconfig                |   8 +
 drivers/usb/host/ehci-hcd.c             |   5 +
 drivers/usb/host/ehci-tegra.c           | 625 ++++++++++++++++++++++++++++++++
 include/linux/platform_data/tegra_usb.h |  31 ++
 include/linux/usb/ehci_def.h            |   4 +-
 5 files changed, 672 insertions(+), 1 deletion(-)
 create mode 100644 drivers/usb/host/ehci-tegra.c
 create mode 100644 include/linux/platform_data/tegra_usb.h

(limited to 'include')

diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index b5a908eacb82..9483acdf2e9e 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -165,6 +165,14 @@ config USB_EHCI_MSM
 	  This driver is not supported on boards like trout which
 	  has an external PHY.
 
+config USB_EHCI_TEGRA
+       boolean "NVIDIA Tegra HCD support"
+       depends on USB_EHCI_HCD && ARCH_TEGRA
+       select USB_EHCI_ROOT_HUB_TT
+       help
+         This driver enables support for the internal USB Host Controllers
+         found in NVIDIA Tegra SoCs. The controllers are EHCI compliant.
+
 config USB_EHCI_HCD_PPC_OF
 	bool "EHCI support for PPC USB controller on OF platform bus"
 	depends on USB_EHCI_HCD && PPC_OF
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index cfeb24b3ee09..d30c4e08c137 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -1260,6 +1260,11 @@ MODULE_LICENSE ("GPL");
 #define	PLATFORM_DRIVER		ehci_hcd_msp_driver
 #endif
 
+#ifdef CONFIG_USB_EHCI_TEGRA
+#include "ehci-tegra.c"
+#define PLATFORM_DRIVER		tegra_ehci_driver
+#endif
+
 #if !defined(PCI_DRIVER) && !defined(PLATFORM_DRIVER) && \
     !defined(PS3_SYSTEM_BUS_DRIVER) && !defined(OF_PLATFORM_DRIVER) && \
     !defined(XILINX_OF_PLATFORM_DRIVER)
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
new file mode 100644
index 000000000000..6202102a6d75
--- /dev/null
+++ b/drivers/usb/host/ehci-tegra.c
@@ -0,0 +1,625 @@
+/*
+ * EHCI-compliant USB host controller driver for NVIDIA Tegra SoCs
+ *
+ * Copyright (C) 2010 Google, Inc.
+ * Copyright (C) 2009 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/tegra_usb.h>
+#include <linux/irq.h>
+#include <linux/usb/otg.h>
+#include <mach/usb_phy.h>
+
+struct tegra_ehci_hcd {
+	struct ehci_hcd *ehci;
+	struct tegra_usb_phy *phy;
+	struct clk *clk;
+	struct clk *emc_clk;
+	struct otg_transceiver *transceiver;
+	int host_resumed;
+	int bus_suspended;
+	int port_resuming;
+	int power_down_on_bus_suspend;
+	enum tegra_usb_phy_port_speed port_speed;
+};
+
+static void tegra_ehci_power_up(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+
+	clk_enable(tegra->emc_clk);
+	clk_enable(tegra->clk);
+	tegra_usb_phy_power_on(tegra->phy);
+	tegra->host_resumed = 1;
+}
+
+static void tegra_ehci_power_down(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+
+	tegra->host_resumed = 0;
+	tegra_usb_phy_power_off(tegra->phy);
+	clk_disable(tegra->clk);
+	clk_disable(tegra->emc_clk);
+}
+
+static int tegra_ehci_hub_control(
+	struct usb_hcd	*hcd,
+	u16		typeReq,
+	u16		wValue,
+	u16		wIndex,
+	char		*buf,
+	u16		wLength
+)
+{
+	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+	u32 __iomem	*status_reg;
+	u32		temp;
+	unsigned long	flags;
+	int		retval = 0;
+
+	status_reg = &ehci->regs->port_status[(wIndex & 0xff) - 1];
+
+	spin_lock_irqsave(&ehci->lock, flags);
+
+	/*
+	 * In ehci_hub_control() for USB_PORT_FEAT_ENABLE clears the other bits
+	 * that are write on clear, by writing back the register read value, so
+	 * USB_PORT_FEAT_ENABLE is handled by masking the set on clear bits
+	 */
+	if (typeReq == ClearPortFeature && wValue == USB_PORT_FEAT_ENABLE) {
+		temp = ehci_readl(ehci, status_reg) & ~PORT_RWC_BITS;
+		ehci_writel(ehci, temp & ~PORT_PE, status_reg);
+		goto done;
+	}
+
+	else if (typeReq == GetPortStatus) {
+		temp = ehci_readl(ehci, status_reg);
+		if (tegra->port_resuming && !(temp & PORT_SUSPEND)) {
+			/* Resume completed, re-enable disconnect detection */
+			tegra->port_resuming = 0;
+			tegra_usb_phy_postresume(tegra->phy);
+		}
+	}
+
+	else if (typeReq == SetPortFeature && wValue == USB_PORT_FEAT_SUSPEND) {
+		temp = ehci_readl(ehci, status_reg);
+		if ((temp & PORT_PE) == 0 || (temp & PORT_RESET) != 0) {
+			retval = -EPIPE;
+			goto done;
+		}
+
+		temp &= ~PORT_WKCONN_E;
+		temp |= PORT_WKDISC_E | PORT_WKOC_E;
+		ehci_writel(ehci, temp | PORT_SUSPEND, status_reg);
+
+		/*
+		 * If a transaction is in progress, there may be a delay in
+		 * suspending the port. Poll until the port is suspended.
+		 */
+		if (handshake(ehci, status_reg, PORT_SUSPEND,
+						PORT_SUSPEND, 5000))
+			pr_err("%s: timeout waiting for SUSPEND\n", __func__);
+
+		set_bit((wIndex & 0xff) - 1, &ehci->suspended_ports);
+		goto done;
+	}
+
+	/*
+	 * Tegra host controller will time the resume operation to clear the bit
+	 * when the port control state switches to HS or FS Idle. This behavior
+	 * is different from EHCI where the host controller driver is required
+	 * to set this bit to a zero after the resume duration is timed in the
+	 * driver.
+	 */
+	else if (typeReq == ClearPortFeature &&
+					wValue == USB_PORT_FEAT_SUSPEND) {
+		temp = ehci_readl(ehci, status_reg);
+		if ((temp & PORT_RESET) || !(temp & PORT_PE)) {
+			retval = -EPIPE;
+			goto done;
+		}
+
+		if (!(temp & PORT_SUSPEND))
+			goto done;
+
+		/* Disable disconnect detection during port resume */
+		tegra_usb_phy_preresume(tegra->phy);
+
+		ehci->reset_done[wIndex-1] = jiffies + msecs_to_jiffies(25);
+
+		temp &= ~(PORT_RWC_BITS | PORT_WAKE_BITS);
+		/* start resume signalling */
+		ehci_writel(ehci, temp | PORT_RESUME, status_reg);
+
+		spin_unlock_irqrestore(&ehci->lock, flags);
+		msleep(20);
+		spin_lock_irqsave(&ehci->lock, flags);
+
+		/* Poll until the controller clears RESUME and SUSPEND */
+		if (handshake(ehci, status_reg, PORT_RESUME, 0, 2000))
+			pr_err("%s: timeout waiting for RESUME\n", __func__);
+		if (handshake(ehci, status_reg, PORT_SUSPEND, 0, 2000))
+			pr_err("%s: timeout waiting for SUSPEND\n", __func__);
+
+		ehci->reset_done[wIndex-1] = 0;
+
+		tegra->port_resuming = 1;
+		goto done;
+	}
+
+	spin_unlock_irqrestore(&ehci->lock, flags);
+
+	/* Handle the hub control events here */
+	return ehci_hub_control(hcd, typeReq, wValue, wIndex, buf, wLength);
+done:
+	spin_unlock_irqrestore(&ehci->lock, flags);
+	return retval;
+}
+
+static void tegra_ehci_restart(struct usb_hcd *hcd)
+{
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+
+	ehci_reset(ehci);
+
+	/* setup the frame list and Async q heads */
+	ehci_writel(ehci, ehci->periodic_dma, &ehci->regs->frame_list);
+	ehci_writel(ehci, (u32)ehci->async->qh_dma, &ehci->regs->async_next);
+	/* setup the command register and set the controller in RUN mode */
+	ehci->command &= ~(CMD_LRESET|CMD_IAAD|CMD_PSE|CMD_ASE|CMD_RESET);
+	ehci->command |= CMD_RUN;
+	ehci_writel(ehci, ehci->command, &ehci->regs->command);
+
+	down_write(&ehci_cf_port_reset_rwsem);
+	ehci_writel(ehci, FLAG_CF, &ehci->regs->configured_flag);
+	/* flush posted writes */
+	ehci_readl(ehci, &ehci->regs->command);
+	up_write(&ehci_cf_port_reset_rwsem);
+}
+
+static int tegra_usb_suspend(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+	struct ehci_regs __iomem *hw = tegra->ehci->regs;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tegra->ehci->lock, flags);
+
+	tegra->port_speed = (readl(&hw->port_status[0]) >> 26) & 0x3;
+	ehci_halt(tegra->ehci);
+	clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+
+	spin_unlock_irqrestore(&tegra->ehci->lock, flags);
+
+	tegra_ehci_power_down(hcd);
+	return 0;
+}
+
+static int tegra_usb_resume(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
+	struct ehci_regs __iomem *hw = ehci->regs;
+	unsigned long val;
+
+	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+	tegra_ehci_power_up(hcd);
+
+	if (tegra->port_speed > TEGRA_USB_PHY_PORT_SPEED_HIGH) {
+		/* Wait for the phy to detect new devices
+		 * before we restart the controller */
+		msleep(10);
+		goto restart;
+	}
+
+	/* Force the phy to keep data lines in suspend state */
+	tegra_ehci_phy_restore_start(tegra->phy, tegra->port_speed);
+
+	/* Enable host mode */
+	tdi_reset(ehci);
+
+	/* Enable Port Power */
+	val = readl(&hw->port_status[0]);
+	val |= PORT_POWER;
+	writel(val, &hw->port_status[0]);
+	udelay(10);
+
+	/* Check if the phy resume from LP0. When the phy resume from LP0
+	 * USB register will be reset. */
+	if (!readl(&hw->async_next)) {
+		/* Program the field PTC based on the saved speed mode */
+		val = readl(&hw->port_status[0]);
+		val &= ~PORT_TEST(~0);
+		if (tegra->port_speed == TEGRA_USB_PHY_PORT_SPEED_HIGH)
+			val |= PORT_TEST_FORCE;
+		else if (tegra->port_speed == TEGRA_USB_PHY_PORT_SPEED_FULL)
+			val |= PORT_TEST(6);
+		else if (tegra->port_speed == TEGRA_USB_PHY_PORT_SPEED_LOW)
+			val |= PORT_TEST(7);
+		writel(val, &hw->port_status[0]);
+		udelay(10);
+
+		/* Disable test mode by setting PTC field to NORMAL_OP */
+		val = readl(&hw->port_status[0]);
+		val &= ~PORT_TEST(~0);
+		writel(val, &hw->port_status[0]);
+		udelay(10);
+	}
+
+	/* Poll until CCS is enabled */
+	if (handshake(ehci, &hw->port_status[0], PORT_CONNECT,
+						 PORT_CONNECT, 2000)) {
+		pr_err("%s: timeout waiting for PORT_CONNECT\n", __func__);
+		goto restart;
+	}
+
+	/* Poll until PE is enabled */
+	if (handshake(ehci, &hw->port_status[0], PORT_PE,
+						 PORT_PE, 2000)) {
+		pr_err("%s: timeout waiting for USB_PORTSC1_PE\n", __func__);
+		goto restart;
+	}
+
+	/* Clear the PCI status, to avoid an interrupt taken upon resume */
+	val = readl(&hw->status);
+	val |= STS_PCD;
+	writel(val, &hw->status);
+
+	/* Put controller in suspend mode by writing 1 to SUSP bit of PORTSC */
+	val = readl(&hw->port_status[0]);
+	if ((val & PORT_POWER) && (val & PORT_PE)) {
+		val |= PORT_SUSPEND;
+		writel(val, &hw->port_status[0]);
+
+		/* Wait until port suspend completes */
+		if (handshake(ehci, &hw->port_status[0], PORT_SUSPEND,
+							 PORT_SUSPEND, 1000)) {
+			pr_err("%s: timeout waiting for PORT_SUSPEND\n",
+								__func__);
+			goto restart;
+		}
+	}
+
+	tegra_ehci_phy_restore_end(tegra->phy);
+	return 0;
+
+restart:
+	if (tegra->port_speed <= TEGRA_USB_PHY_PORT_SPEED_HIGH)
+		tegra_ehci_phy_restore_end(tegra->phy);
+
+	tegra_ehci_restart(hcd);
+	return 0;
+}
+
+static void tegra_ehci_shutdown(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+
+	/* ehci_shutdown touches the USB controller registers, make sure
+	 * controller has clocks to it */
+	if (!tegra->host_resumed)
+		tegra_ehci_power_up(hcd);
+
+	ehci_shutdown(hcd);
+}
+
+static int tegra_ehci_setup(struct usb_hcd *hcd)
+{
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+	int retval;
+
+	/* EHCI registers start at offset 0x100 */
+	ehci->caps = hcd->regs + 0x100;
+	ehci->regs = hcd->regs + 0x100 +
+		HC_LENGTH(readl(&ehci->caps->hc_capbase));
+
+	dbg_hcs_params(ehci, "reset");
+	dbg_hcc_params(ehci, "reset");
+
+	/* cache this readonly data; minimize chip reads */
+	ehci->hcs_params = readl(&ehci->caps->hcs_params);
+
+	/* switch to host mode */
+	hcd->has_tt = 1;
+	ehci_reset(ehci);
+
+	retval = ehci_halt(ehci);
+	if (retval)
+		return retval;
+
+	/* data structure init */
+	retval = ehci_init(hcd);
+	if (retval)
+		return retval;
+
+	ehci->sbrn = 0x20;
+
+	ehci_port_power(ehci, 1);
+	return retval;
+}
+
+#ifdef CONFIG_PM
+static int tegra_ehci_bus_suspend(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+	int error_status = 0;
+
+	error_status = ehci_bus_suspend(hcd);
+	if (!error_status && tegra->power_down_on_bus_suspend) {
+		tegra_usb_suspend(hcd);
+		tegra->bus_suspended = 1;
+	}
+
+	return error_status;
+}
+
+static int tegra_ehci_bus_resume(struct usb_hcd *hcd)
+{
+	struct tegra_ehci_hcd *tegra = dev_get_drvdata(hcd->self.controller);
+
+	if (tegra->bus_suspended && tegra->power_down_on_bus_suspend) {
+		tegra_usb_resume(hcd);
+		tegra->bus_suspended = 0;
+	}
+
+	tegra_usb_phy_preresume(tegra->phy);
+	tegra->port_resuming = 1;
+	return ehci_bus_resume(hcd);
+}
+#endif
+
+static const struct hc_driver tegra_ehci_hc_driver = {
+	.description		= hcd_name,
+	.product_desc		= "Tegra EHCI Host Controller",
+	.hcd_priv_size		= sizeof(struct ehci_hcd),
+
+	.flags			= HCD_USB2 | HCD_MEMORY,
+
+	.reset			= tegra_ehci_setup,
+	.irq			= ehci_irq,
+
+	.start			= ehci_run,
+	.stop			= ehci_stop,
+	.shutdown		= tegra_ehci_shutdown,
+	.urb_enqueue		= ehci_urb_enqueue,
+	.urb_dequeue		= ehci_urb_dequeue,
+	.endpoint_disable	= ehci_endpoint_disable,
+	.endpoint_reset		= ehci_endpoint_reset,
+	.get_frame_number	= ehci_get_frame,
+	.hub_status_data	= ehci_hub_status_data,
+	.hub_control		= tegra_ehci_hub_control,
+	.clear_tt_buffer_complete = ehci_clear_tt_buffer_complete,
+#ifdef CONFIG_PM
+	.bus_suspend		= tegra_ehci_bus_suspend,
+	.bus_resume		= tegra_ehci_bus_resume,
+#endif
+	.relinquish_port	= ehci_relinquish_port,
+	.port_handed_over	= ehci_port_handed_over,
+};
+
+static int tegra_ehci_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct usb_hcd *hcd;
+	struct tegra_ehci_hcd *tegra;
+	struct tegra_ehci_platform_data *pdata;
+	int err = 0;
+	int irq;
+	int instance = pdev->id;
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		dev_err(&pdev->dev, "Platform data missing\n");
+		return -EINVAL;
+	}
+
+	tegra = kzalloc(sizeof(struct tegra_ehci_hcd), GFP_KERNEL);
+	if (!tegra)
+		return -ENOMEM;
+
+	hcd = usb_create_hcd(&tegra_ehci_hc_driver, &pdev->dev,
+					dev_name(&pdev->dev));
+	if (!hcd) {
+		dev_err(&pdev->dev, "Unable to create HCD\n");
+		err = -ENOMEM;
+		goto fail_hcd;
+	}
+
+	platform_set_drvdata(pdev, tegra);
+
+	tegra->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(tegra->clk)) {
+		dev_err(&pdev->dev, "Can't get ehci clock\n");
+		err = PTR_ERR(tegra->clk);
+		goto fail_clk;
+	}
+
+	err = clk_enable(tegra->clk);
+	if (err)
+		goto fail_clken;
+
+	tegra->emc_clk = clk_get(&pdev->dev, "emc");
+	if (IS_ERR(tegra->emc_clk)) {
+		dev_err(&pdev->dev, "Can't get emc clock\n");
+		err = PTR_ERR(tegra->emc_clk);
+		goto fail_emc_clk;
+	}
+
+	clk_enable(tegra->emc_clk);
+	clk_set_rate(tegra->emc_clk, 400000000);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "Failed to get I/O memory\n");
+		err = -ENXIO;
+		goto fail_io;
+	}
+	hcd->rsrc_start = res->start;
+	hcd->rsrc_len = resource_size(res);
+	hcd->regs = ioremap(res->start, resource_size(res));
+	if (!hcd->regs) {
+		dev_err(&pdev->dev, "Failed to remap I/O memory\n");
+		err = -ENOMEM;
+		goto fail_io;
+	}
+
+	tegra->phy = tegra_usb_phy_open(instance, hcd->regs, pdata->phy_config,
+						TEGRA_USB_PHY_MODE_HOST);
+	if (IS_ERR(tegra->phy)) {
+		dev_err(&pdev->dev, "Failed to open USB phy\n");
+		err = -ENXIO;
+		goto fail_phy;
+	}
+
+	err = tegra_usb_phy_power_on(tegra->phy);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to power on the phy\n");
+		goto fail;
+	}
+
+	tegra->host_resumed = 1;
+	tegra->power_down_on_bus_suspend = pdata->power_down_on_bus_suspend;
+	tegra->ehci = hcd_to_ehci(hcd);
+
+	irq = platform_get_irq(pdev, 0);
+	if (!irq) {
+		dev_err(&pdev->dev, "Failed to get IRQ\n");
+		err = -ENODEV;
+		goto fail;
+	}
+	set_irq_flags(irq, IRQF_VALID);
+
+#ifdef CONFIG_USB_OTG_UTILS
+	if (pdata->operating_mode == TEGRA_USB_OTG) {
+		tegra->transceiver = otg_get_transceiver();
+		if (tegra->transceiver)
+			otg_set_host(tegra->transceiver, &hcd->self);
+	}
+#endif
+
+	err = usb_add_hcd(hcd, irq, IRQF_DISABLED | IRQF_SHARED);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to add USB HCD\n");
+		goto fail;
+	}
+
+	return err;
+
+fail:
+#ifdef CONFIG_USB_OTG_UTILS
+	if (tegra->transceiver) {
+		otg_set_host(tegra->transceiver, NULL);
+		otg_put_transceiver(tegra->transceiver);
+	}
+#endif
+	tegra_usb_phy_close(tegra->phy);
+fail_phy:
+	iounmap(hcd->regs);
+fail_io:
+	clk_disable(tegra->emc_clk);
+	clk_put(tegra->emc_clk);
+fail_emc_clk:
+	clk_disable(tegra->clk);
+fail_clken:
+	clk_put(tegra->clk);
+fail_clk:
+	usb_put_hcd(hcd);
+fail_hcd:
+	kfree(tegra);
+	return err;
+}
+
+#ifdef CONFIG_PM
+static int tegra_ehci_resume(struct platform_device *pdev)
+{
+	struct tegra_ehci_hcd *tegra = platform_get_drvdata(pdev);
+	struct usb_hcd *hcd = ehci_to_hcd(tegra->ehci);
+
+	if (tegra->bus_suspended)
+		return 0;
+
+	return tegra_usb_resume(hcd);
+}
+
+static int tegra_ehci_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct tegra_ehci_hcd *tegra = platform_get_drvdata(pdev);
+	struct usb_hcd *hcd = ehci_to_hcd(tegra->ehci);
+
+	if (tegra->bus_suspended)
+		return 0;
+
+	if (time_before(jiffies, tegra->ehci->next_statechange))
+		msleep(10);
+
+	return tegra_usb_suspend(hcd);
+}
+#endif
+
+static int tegra_ehci_remove(struct platform_device *pdev)
+{
+	struct tegra_ehci_hcd *tegra = platform_get_drvdata(pdev);
+	struct usb_hcd *hcd = ehci_to_hcd(tegra->ehci);
+
+	if (tegra == NULL || hcd == NULL)
+		return -EINVAL;
+
+#ifdef CONFIG_USB_OTG_UTILS
+	if (tegra->transceiver) {
+		otg_set_host(tegra->transceiver, NULL);
+		otg_put_transceiver(tegra->transceiver);
+	}
+#endif
+
+	usb_remove_hcd(hcd);
+	usb_put_hcd(hcd);
+
+	tegra_usb_phy_close(tegra->phy);
+	iounmap(hcd->regs);
+
+	clk_disable(tegra->clk);
+	clk_put(tegra->clk);
+
+	clk_disable(tegra->emc_clk);
+	clk_put(tegra->emc_clk);
+
+	kfree(tegra);
+	return 0;
+}
+
+static void tegra_ehci_hcd_shutdown(struct platform_device *pdev)
+{
+	struct tegra_ehci_hcd *tegra = platform_get_drvdata(pdev);
+	struct usb_hcd *hcd = ehci_to_hcd(tegra->ehci);
+
+	if (hcd->driver->shutdown)
+		hcd->driver->shutdown(hcd);
+}
+
+static struct platform_driver tegra_ehci_driver = {
+	.probe		= tegra_ehci_probe,
+	.remove		= tegra_ehci_remove,
+#ifdef CONFIG_PM
+	.suspend	= tegra_ehci_suspend,
+	.resume		= tegra_ehci_resume,
+#endif
+	.shutdown	= tegra_ehci_hcd_shutdown,
+	.driver		= {
+		.name	= "tegra-ehci",
+	}
+};
diff --git a/include/linux/platform_data/tegra_usb.h b/include/linux/platform_data/tegra_usb.h
new file mode 100644
index 000000000000..6bca5b569acb
--- /dev/null
+++ b/include/linux/platform_data/tegra_usb.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2010 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _TEGRA_USB_H_
+#define _TEGRA_USB_H_
+
+enum tegra_usb_operating_modes {
+	TEGRA_USB_DEVICE,
+	TEGRA_USB_HOST,
+	TEGRA_USB_OTG,
+};
+
+struct tegra_ehci_platform_data {
+	enum tegra_usb_operating_modes operating_mode;
+	/* power down the phy on bus suspend */
+	int power_down_on_bus_suspend;
+	void *phy_config;
+};
+
+#endif /* _TEGRA_USB_H_ */
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index 2e262cb15425..656380245198 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -127,7 +127,9 @@ struct ehci_regs {
 #define PORT_WKDISC_E	(1<<21)		/* wake on disconnect (enable) */
 #define PORT_WKCONN_E	(1<<20)		/* wake on connect (enable) */
 /* 19:16 for port testing */
-#define PORT_TEST_PKT	(0x4<<16)	/* Port Test Control - packet test */
+#define PORT_TEST(x)	(((x)&0xf)<<16)	/* Port Test Control */
+#define PORT_TEST_PKT	PORT_TEST(0x4)	/* Port Test Control - packet test */
+#define PORT_TEST_FORCE	PORT_TEST(0x5)	/* Port Test Control - force enable */
 #define PORT_LED_OFF	(0<<14)
 #define PORT_LED_AMBER	(1<<14)
 #define PORT_LED_GREEN	(2<<14)
-- 
cgit v1.2.3


From d209a699a0b975ad47f399d70ddc3791f1b84496 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 11 Mar 2011 21:22:14 +0100
Subject: genirq: Add chip flag to force mask on suspend

On suspend we disable all interrupts in the core code, but this does
not mask the interrupt line in the default implementation as we use a
lazy disable approach. That means we mark the interrupt disabled, but
leave the hardware unmasked. That's an optimization because we avoid
the hardware access for the common case where no interrupt happens
after we marked it disabled. If an interrupt happens, then the
interrupt flow handler masks the line at the hardware level and marks
it pending.

Suspend makes use of this delayed disable as it "disables" all
interrupts when preparing the suspend transition. Right before the
system goes into hardware suspend state it checks whether one of the
interrupts which is marked as a wakeup interrupt came in after
disabling it.

Most interrupt chips have a separate register which selects the
interrupts which can wake up the system from suspend, so we don't have
to mask any on the non wakeup interrupts.

But now we have to deal with brilliant designed hardware which lacks
such a wakeup configuration facility. For such hardware it's necessary
to mask all non wakeup interrupts before going into suspend in order
to avoid the wakeup from random interrupts.

Rather than working around this in the affected interrupt chip
implementations we can solve this elegant in the core code itself.

Add a flag IRQCHIP_MASK_ON_SUSPEND which can be set by the irq chip
implementation to indicate, that the interrupts which are not selected
as wakeup sources must be masked in the suspend path. Mask them in the
loop which checks the wakeup interrupts pending flag.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Abhijeet Dharmapurikar <adharmap@codeaurora.org>
LKML-Reference: <alpine.LFD.2.00.1103112112310.2787@localhost6.localdomain6>
---
 include/linux/irq.h |  2 ++
 kernel/irq/pm.c     | 22 ++++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index ff62d0145b8f..1d3577f30d45 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -330,10 +330,12 @@ struct irq_chip {
  *
  * IRQCHIP_SET_TYPE_MASKED:	Mask before calling chip.irq_set_type()
  * IRQCHIP_EOI_IF_HANDLED:	Only issue irq_eoi() when irq was handled
+ * IRQCHIP_MASK_ON_SUSPEND:	Mask non wake irqs in the suspend path
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
 	IRQCHIP_EOI_IF_HANDLED		= (1 <<  1),
+	IRQCHIP_MASK_ON_SUSPEND		= (1 <<  2),
 };
 
 /* This include will go away once we isolated irq_desc usage to core code */
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 1329f0eff49e..f76fc00c9877 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -68,10 +68,24 @@ int check_wakeup_irqs(void)
 	struct irq_desc *desc;
 	int irq;
 
-	for_each_irq_desc(irq, desc)
-		if (irqd_is_wakeup_set(&desc->irq_data) &&
-		    (desc->istate & IRQS_PENDING))
-			return -EBUSY;
+	for_each_irq_desc(irq, desc) {
+		if (irqd_is_wakeup_set(&desc->irq_data)) {
+			if (desc->istate & IRQS_PENDING)
+				return -EBUSY;
+			continue;
+		}
+		/*
+		 * Check the non wakeup interrupts whether they need
+		 * to be masked before finally going into suspend
+		 * state. That's for hardware which has no wakeup
+		 * source configuration facility. The chip
+		 * implementation indicates that with
+		 * IRQCHIP_MASK_ON_SUSPEND.
+		 */
+		if (desc->istate & IRQS_SUSPENDED &&
+		    irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+			mask_irq(desc);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 78fbfd8a653ca972afe479517a40661bfff6d8c3 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 00:00:52 -0500
Subject: ipv4: Create and use route lookup helpers.

The idea here is this minimizes the number of places one has to edit
in order to make changes to how flows are defined and used.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c        |  8 +-----
 drivers/infiniband/hw/cxgb3/iwch_cm.c | 21 +++------------
 drivers/infiniband/hw/cxgb4/cm.c      | 21 +++------------
 drivers/infiniband/hw/nes/nes_cm.c    |  5 +---
 drivers/net/bonding/bond_main.c       | 12 +++------
 drivers/net/cnic.c                    | 16 ++++--------
 drivers/net/pptp.c                    | 45 +++++++++++++-------------------
 drivers/scsi/cxgbi/libcxgbi.c         | 20 +++-----------
 include/net/route.h                   | 48 ++++++++++++++++++++++++++++++++++
 net/atm/clip.c                        |  4 +--
 net/bridge/br_netfilter.c             |  7 ++---
 net/ipv4/af_inet.c                    | 20 +++-----------
 net/ipv4/arp.c                        | 12 +++------
 net/ipv4/igmp.c                       | 34 +++++++++++-------------
 net/ipv4/ip_gre.c                     | 49 ++++++++++++-----------------------
 net/ipv4/ip_output.c                  | 33 ++++++++++-------------
 net/ipv4/ipip.c                       | 36 ++++++++++---------------
 net/ipv4/ipmr.c                       | 24 +++++++----------
 net/ipv6/ip6_tunnel.c                 | 19 +++++++-------
 net/ipv6/sit.c                        | 31 ++++++++++------------
 net/l2tp/l2tp_ip.c                    | 30 ++++++++-------------
 net/netfilter/ipvs/ip_vs_xmit.c       | 14 ++--------
 net/rxrpc/ar-peer.c                   | 23 +++-------------
 23 files changed, 206 insertions(+), 326 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 2d749937a969..1742f72fbd57 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -183,17 +183,11 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 {
 	__be32 src_ip = src_in->sin_addr.s_addr;
 	__be32 dst_ip = dst_in->sin_addr.s_addr;
-	struct flowi fl;
 	struct rtable *rt;
 	struct neighbour *neigh;
 	int ret;
 
-	memset(&fl, 0, sizeof fl);
-	fl.nl_u.ip4_u.daddr = dst_ip;
-	fl.nl_u.ip4_u.saddr = src_ip;
-	fl.oif = addr->bound_dev_if;
-
-	rt = ip_route_output_key(&init_net, &fl);
+	rt = ip_route_output(&init_net, dst_ip, src_ip, 0, addr->bound_dev_if);
 	if (IS_ERR(rt)) {
 		ret = PTR_ERR(rt);
 		goto out;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index e0ccbc53fbcc..3216bcad7e82 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -338,23 +338,10 @@ static struct rtable *find_route(struct t3cdev *dev, __be32 local_ip,
 				 __be16 peer_port, u8 tos)
 {
 	struct rtable *rt;
-	struct flowi fl = {
-		.oif = 0,
-		.nl_u = {
-			 .ip4_u = {
-				   .daddr = peer_ip,
-				   .saddr = local_ip,
-				   .tos = tos}
-			 },
-		.proto = IPPROTO_TCP,
-		.uli_u = {
-			  .ports = {
-				    .sport = local_port,
-				    .dport = peer_port}
-			  }
-	};
-
-	rt = ip_route_output_flow(&init_net, &fl, NULL);
+
+	rt = ip_route_output_ports(&init_net, NULL, peer_ip, local_ip,
+				   peer_port, local_port, IPPROTO_TCP,
+				   tos, 0);
 	if (IS_ERR(rt))
 		return NULL;
 	return rt;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 77b0eef2aad9..97a876a0f20b 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -315,23 +315,10 @@ static struct rtable *find_route(struct c4iw_dev *dev, __be32 local_ip,
 				 __be16 peer_port, u8 tos)
 {
 	struct rtable *rt;
-	struct flowi fl = {
-		.oif = 0,
-		.nl_u = {
-			 .ip4_u = {
-				   .daddr = peer_ip,
-				   .saddr = local_ip,
-				   .tos = tos}
-			 },
-		.proto = IPPROTO_TCP,
-		.uli_u = {
-			  .ports = {
-				    .sport = local_port,
-				    .dport = peer_port}
-			  }
-	};
-
-	rt = ip_route_output_flow(&init_net, &fl, NULL);
+
+	rt = ip_route_output_ports(&init_net, NULL, peer_ip, local_ip,
+				   peer_port, local_port, IPPROTO_TCP,
+				   tos, 0);
 	if (IS_ERR(rt))
 		return NULL;
 	return rt;
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index e81599cb1fe6..ef3291551bc6 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1104,15 +1104,12 @@ static inline int mini_cm_accelerated(struct nes_cm_core *cm_core,
 static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpindex)
 {
 	struct rtable *rt;
-	struct flowi fl;
 	struct neighbour *neigh;
 	int rc = arpindex;
 	struct net_device *netdev;
 	struct nes_adapter *nesadapter = nesvnic->nesdev->nesadapter;
 
-	memset(&fl, 0, sizeof fl);
-	fl.nl_u.ip4_u.daddr = htonl(dst_ip);
-	rt = ip_route_output_key(&init_net, &fl);
+	rt = ip_route_output(&init_net, htonl(dst_ip), 0, 0, 0);
 	if (IS_ERR(rt)) {
 		printk(KERN_ERR "%s: ip_route_output_key failed for 0x%08X\n",
 				__func__, dst_ip);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 68a5ce0a649f..3ad4f501949e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2676,7 +2676,6 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 	__be32 *targets = bond->params.arp_targets;
 	struct vlan_entry *vlan;
 	struct net_device *vlan_dev;
-	struct flowi fl;
 	struct rtable *rt;
 
 	for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
@@ -2695,15 +2694,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		 * determine which VLAN interface would be used, so we
 		 * can tag the ARP with the proper VLAN tag.
 		 */
-		memset(&fl, 0, sizeof(fl));
-		fl.fl4_dst = targets[i];
-		fl.fl4_tos = RTO_ONLINK;
-
-		rt = ip_route_output_key(dev_net(bond->dev), &fl);
+		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
+				     RTO_ONLINK, 0);
 		if (IS_ERR(rt)) {
 			if (net_ratelimit()) {
 				pr_warning("%s: no route to arp_ip_target %pI4\n",
-					   bond->dev->name, &fl.fl4_dst);
+					   bond->dev->name, &targets[i]);
 			}
 			continue;
 		}
@@ -2739,7 +2735,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 
 		if (net_ratelimit()) {
 			pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
-				   bond->dev->name, &fl.fl4_dst,
+				   bond->dev->name, &targets[i],
 				   rt->dst.dev ? rt->dst.dev->name : "NULL");
 		}
 		ip_rt_put(rt);
diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c
index 271a1f00c224..65832951fe07 100644
--- a/drivers/net/cnic.c
+++ b/drivers/net/cnic.c
@@ -3407,20 +3407,14 @@ static int cnic_get_v4_route(struct sockaddr_in *dst_addr,
 			     struct dst_entry **dst)
 {
 #if defined(CONFIG_INET)
-	struct flowi fl;
-	int err;
 	struct rtable *rt;
 
-	memset(&fl, 0, sizeof(fl));
-	fl.nl_u.ip4_u.daddr = dst_addr->sin_addr.s_addr;
-
-	rt = ip_route_output_key(&init_net, &fl);
-	err = 0;
-	if (!IS_ERR(rt))
+	rt = ip_route_output(&init_net, dst_addr->sin_addr.s_addr, 0, 0, 0);
+	if (!IS_ERR(rt)) {
 		*dst = &rt->dst;
-	else
-		err = PTR_ERR(rt);
-	return err;
+		return 0;
+	}
+	return PTR_ERR(rt);
 #else
 	return -ENETUNREACH;
 #endif
diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c
index 1af549c89d51..51dfcf8023c7 100644
--- a/drivers/net/pptp.c
+++ b/drivers/net/pptp.c
@@ -189,18 +189,14 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	if (sk_pppox(po)->sk_state & PPPOX_DEAD)
 		goto tx_error;
 
-	{
-		struct flowi fl = { .oif = 0,
-			.nl_u = {
-				.ip4_u = {
-					.daddr = opt->dst_addr.sin_addr.s_addr,
-					.saddr = opt->src_addr.sin_addr.s_addr,
-					.tos = RT_TOS(0) } },
-			.proto = IPPROTO_GRE };
-		rt = ip_route_output_key(&init_net, &fl);
-		if (IS_ERR(rt))
-			goto tx_error;
-	}
+	rt = ip_route_output_ports(&init_net, NULL,
+				   opt->dst_addr.sin_addr.s_addr,
+				   opt->src_addr.sin_addr.s_addr,
+				   0, 0, IPPROTO_GRE,
+				   RT_TOS(0), 0);
+	if (IS_ERR(rt))
+		goto tx_error;
+
 	tdev = rt->dst.dev;
 
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph) + sizeof(*hdr) + 2;
@@ -467,22 +463,17 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.private = sk;
 	po->chan.ops = &pptp_chan_ops;
 
-	{
-		struct flowi fl = {
-			.nl_u = {
-				.ip4_u = {
-					.daddr = opt->dst_addr.sin_addr.s_addr,
-					.saddr = opt->src_addr.sin_addr.s_addr,
-					.tos = RT_CONN_FLAGS(sk) } },
-			.proto = IPPROTO_GRE };
-		security_sk_classify_flow(sk, &fl);
-		rt = ip_route_output_key(&init_net, &fl);
-		if (IS_ERR(rt)) {
-			error = -EHOSTUNREACH;
-			goto end;
-		}
-		sk_setup_caps(sk, &rt->dst);
+	rt = ip_route_output_ports(&init_net, sk,
+				   opt->dst_addr.sin_addr.s_addr,
+				   opt->src_addr.sin_addr.s_addr,
+				   0, 0,
+				   IPPROTO_GRE, RT_CONN_FLAGS(sk), 0);
+	if (IS_ERR(rt)) {
+		error = -EHOSTUNREACH;
+		goto end;
 	}
+	sk_setup_caps(sk, &rt->dst);
+
 	po->chan.mtu = dst_mtu(&rt->dst);
 	if (!po->chan.mtu)
 		po->chan.mtu = PPP_MTU;
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 889199aa1f5b..a24dff9f9163 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -451,26 +451,12 @@ static struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *cdev)
 }
 
 static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
-					__be16 sport, __be16 dport, u8 tos)
+				      __be16 sport, __be16 dport, u8 tos)
 {
 	struct rtable *rt;
-	struct flowi fl = {
-		.oif = 0,
-		.nl_u = {
-			.ip4_u = {
-				.daddr = daddr,
-				.saddr = saddr,
-				.tos = tos }
-			},
-		.proto = IPPROTO_TCP,
-		.uli_u = {
-			.ports = {
-				.sport = sport,
-				.dport = dport }
-			}
-	};
 
-	rt = ip_route_output_flow(&init_net, &fl, NULL);
+	rt = ip_route_output_ports(&init_net, NULL, daddr, saddr,
+				   dport, sport, IPPROTO_TCP, tos, 0);
 	if (IS_ERR(rt))
 		return NULL;
 
diff --git a/include/net/route.h b/include/net/route.h
index 9257f5f17337..f140f4130fea 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -132,6 +132,54 @@ static inline struct rtable *ip_route_output_key(struct net *net, struct flowi *
 	return ip_route_output_flow(net, flp, NULL);
 }
 
+static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
+					     __be32 saddr, u8 tos, int oif)
+{
+	struct flowi fl = {
+		.oif = oif,
+		.fl4_dst = daddr,
+		.fl4_src = saddr,
+		.fl4_tos = tos,
+	};
+	return ip_route_output_key(net, &fl);
+}
+
+static inline struct rtable *ip_route_output_ports(struct net *net, struct sock *sk,
+						   __be32 daddr, __be32 saddr,
+						   __be16 dport, __be16 sport,
+						   __u8 proto, __u8 tos, int oif)
+{
+	struct flowi fl = {
+		.oif = oif,
+		.flags = sk ? inet_sk_flowi_flags(sk) : 0,
+		.mark = sk ? sk->sk_mark : 0,
+		.fl4_dst = daddr,
+		.fl4_src = saddr,
+		.fl4_tos = tos,
+		.proto = proto,
+		.fl_ip_dport = dport,
+		.fl_ip_sport = sport,
+	};
+	if (sk)
+		security_sk_classify_flow(sk, &fl);
+	return ip_route_output_flow(net, &fl, sk);
+}
+
+static inline struct rtable *ip_route_output_gre(struct net *net,
+						 __be32 daddr, __be32 saddr,
+						 __be32 gre_key, __u8 tos, int oif)
+{
+	struct flowi fl = {
+		.oif = oif,
+		.fl4_dst = daddr,
+		.fl4_src = saddr,
+		.fl4_tos = tos,
+		.proto = IPPROTO_GRE,
+		.fl_gre_key = gre_key,
+	};
+	return ip_route_output_key(net, &fl);
+}
+
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin, bool noref);
 
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 810a1294eddb..1d4be60e1390 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -502,8 +502,6 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 	struct atmarp_entry *entry;
 	int error;
 	struct clip_vcc *clip_vcc;
-	struct flowi fl = { .fl4_dst = ip,
-			    .fl4_tos = 1 };
 	struct rtable *rt;
 
 	if (vcc->push != clip_push) {
@@ -520,7 +518,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 		unlink_clip_vcc(clip_vcc);
 		return 0;
 	}
-	rt = ip_route_output_key(&init_net, &fl);
+	rt = ip_route_output(&init_net, ip, 0, 1, 0);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 	neigh = __neigh_lookup(&clip_tbl, &ip, rt->dst.dev, 1);
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 45b57b173f70..f97af5590ba1 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -412,10 +412,6 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 	if (dnat_took_place(skb)) {
 		if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
-			struct flowi fl = {
-				.fl4_dst = iph->daddr,
-				.fl4_tos = RT_TOS(iph->tos),
-			};
 			struct in_device *in_dev = __in_dev_get_rcu(dev);
 
 			/* If err equals -EHOSTUNREACH the error is due to a
@@ -428,7 +424,8 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 			if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
 				goto free_skb;
 
-			rt = ip_route_output_key(dev_net(dev), &fl);
+			rt = ip_route_output(dev_net(dev), iph->daddr, 0,
+					     RT_TOS(iph->tos), 0);
 			if (!IS_ERR(rt)) {
 				/* - Bridged-and-DNAT'ed traffic doesn't
 				 *   require ip_forwarding. */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 35a502055018..807d83c02ef6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1157,22 +1157,10 @@ int inet_sk_rebuild_header(struct sock *sk)
 	daddr = inet->inet_daddr;
 	if (inet->opt && inet->opt->srr)
 		daddr = inet->opt->faddr;
-	{
-	struct flowi fl = {
-		.oif = sk->sk_bound_dev_if,
-		.mark = sk->sk_mark,
-		.fl4_dst = daddr,
-		.fl4_src = inet->inet_saddr,
-		.fl4_tos = RT_CONN_FLAGS(sk),
-		.proto = sk->sk_protocol,
-		.flags = inet_sk_flowi_flags(sk),
-		.fl_ip_sport = inet->inet_sport,
-		.fl_ip_dport = inet->inet_dport,
-	};
-
-	security_sk_classify_flow(sk, &fl);
-	rt = ip_route_output_flow(sock_net(sk), &fl, sk);
-	}
+	rt = ip_route_output_ports(sock_net(sk), sk, daddr, inet->inet_saddr,
+				   inet->inet_dport, inet->inet_sport,
+				   sk->sk_protocol, RT_CONN_FLAGS(sk),
+				   sk->sk_bound_dev_if);
 	if (!IS_ERR(rt)) {
 		err = 0;
 		sk_setup_caps(sk, &rt->dst);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index fa9988da1da4..090d273d7865 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -433,14 +433,12 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
 
 static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 {
-	struct flowi fl = { .fl4_dst = sip,
-			    .fl4_src = tip };
 	struct rtable *rt;
 	int flag = 0;
 	/*unsigned long now; */
 	struct net *net = dev_net(dev);
 
-	rt = ip_route_output_key(net, &fl);
+	rt = ip_route_output(net, sip, tip, 0, 0);
 	if (IS_ERR(rt))
 		return 1;
 	if (rt->dst.dev != dev) {
@@ -1062,9 +1060,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 	if (r->arp_flags & ATF_PERM)
 		r->arp_flags |= ATF_COM;
 	if (dev == NULL) {
-		struct flowi fl = { .fl4_dst = ip,
-				    .fl4_tos = RTO_ONLINK };
-		struct rtable *rt = ip_route_output_key(net, &fl);
+		struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
 
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
@@ -1185,9 +1181,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
 
 	ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
 	if (dev == NULL) {
-		struct flowi fl = { .fl4_dst = ip,
-				    .fl4_tos = RTO_ONLINK };
-		struct rtable *rt = ip_route_output_key(net, &fl);
+		struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 		dev = rt->dst.dev;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 12b65ccca8e9..1fd3d9ce8398 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -321,15 +321,12 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	}
 	igmp_skb_size(skb) = size;
 
-	{
-		struct flowi fl = { .oif = dev->ifindex,
-				    .fl4_dst = IGMPV3_ALL_MCR,
-				    .proto = IPPROTO_IGMP };
-		rt = ip_route_output_key(net, &fl);
-		if (IS_ERR(rt)) {
-			kfree_skb(skb);
-			return NULL;
-		}
+	rt = ip_route_output_ports(net, NULL, IGMPV3_ALL_MCR, 0,
+				   0, 0,
+				   IPPROTO_IGMP, 0, dev->ifindex);
+	if (IS_ERR(rt)) {
+		kfree_skb(skb);
+		return NULL;
 	}
 	if (rt->rt_src == 0) {
 		kfree_skb(skb);
@@ -667,14 +664,12 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	else
 		dst = group;
 
-	{
-		struct flowi fl = { .oif = dev->ifindex,
-				    .fl4_dst = dst,
-				    .proto = IPPROTO_IGMP };
-		rt = ip_route_output_key(net, &fl);
-		if (IS_ERR(rt))
-			return -1;
-	}
+	rt = ip_route_output_ports(net, NULL, dst, 0,
+				   0, 0,
+				   IPPROTO_IGMP, 0, dev->ifindex);
+	if (IS_ERR(rt))
+		return -1;
+
 	if (rt->rt_src == 0) {
 		ip_rt_put(rt);
 		return -1;
@@ -1441,7 +1436,6 @@ void ip_mc_destroy_dev(struct in_device *in_dev)
 /* RTNL is locked */
 static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
 {
-	struct flowi fl = { .fl4_dst = imr->imr_multiaddr.s_addr };
 	struct net_device *dev = NULL;
 	struct in_device *idev = NULL;
 
@@ -1456,7 +1450,9 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
 	}
 
 	if (!dev) {
-		struct rtable *rt = ip_route_output_key(net, &fl);
+		struct rtable *rt = ip_route_output(net,
+						    imr->imr_multiaddr.s_addr,
+						    0, 0, 0);
 		if (!IS_ERR(rt)) {
 			dev = rt->dst.dev;
 			ip_rt_put(rt);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 71465955520b..da5941f18c3c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -769,20 +769,12 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			tos = ipv6_get_dsfield((struct ipv6hdr *)old_iph);
 	}
 
-	{
-		struct flowi fl = {
-			.oif = tunnel->parms.link,
-			.fl4_dst = dst,
-			.fl4_src = tiph->saddr,
-			.fl4_tos = RT_TOS(tos),
-			.proto = IPPROTO_GRE,
-			.fl_gre_key = tunnel->parms.o_key
-		};
-		rt = ip_route_output_key(dev_net(dev), &fl);
-		if (IS_ERR(rt)) {
-			dev->stats.tx_carrier_errors++;
-			goto tx_error;
-		}
+	rt = ip_route_output_gre(dev_net(dev), dst, tiph->saddr,
+				 tunnel->parms.o_key, RT_TOS(tos),
+				 tunnel->parms.link);
+	if (IS_ERR(rt)) {
+		dev->stats.tx_carrier_errors++;
+		goto tx_error;
 	}
 	tdev = rt->dst.dev;
 
@@ -946,15 +938,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
 	/* Guess output device to choose reasonable mtu and needed_headroom */
 
 	if (iph->daddr) {
-		struct flowi fl = {
-			.oif = tunnel->parms.link,
-			.fl4_dst = iph->daddr,
-			.fl4_src = iph->saddr,
-			.fl4_tos = RT_TOS(iph->tos),
-			.proto = IPPROTO_GRE,
-			.fl_gre_key = tunnel->parms.o_key
-		};
-		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
+		struct rtable *rt = ip_route_output_gre(dev_net(dev),
+							iph->daddr, iph->saddr,
+							tunnel->parms.o_key,
+							RT_TOS(iph->tos),
+							tunnel->parms.link);
 
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
@@ -1208,15 +1196,12 @@ static int ipgre_open(struct net_device *dev)
 	struct ip_tunnel *t = netdev_priv(dev);
 
 	if (ipv4_is_multicast(t->parms.iph.daddr)) {
-		struct flowi fl = {
-			.oif = t->parms.link,
-			.fl4_dst = t->parms.iph.daddr,
-			.fl4_src = t->parms.iph.saddr,
-			.fl4_tos = RT_TOS(t->parms.iph.tos),
-			.proto = IPPROTO_GRE,
-			.fl_gre_key = t->parms.o_key
-		};
-		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
+		struct rtable *rt = ip_route_output_gre(dev_net(dev),
+							t->parms.iph.daddr,
+							t->parms.iph.saddr,
+							t->parms.o_key,
+							RT_TOS(t->parms.iph.tos),
+							t->parms.link);
 
 		if (IS_ERR(rt))
 			return -EADDRNOTAVAIL;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 171f483b21d5..916152dbdce4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -339,26 +339,19 @@ int ip_queue_xmit(struct sk_buff *skb)
 		if(opt && opt->srr)
 			daddr = opt->faddr;
 
-		{
-			struct flowi fl = { .oif = sk->sk_bound_dev_if,
-					    .mark = sk->sk_mark,
-					    .fl4_dst = daddr,
-					    .fl4_src = inet->inet_saddr,
-					    .fl4_tos = RT_CONN_FLAGS(sk),
-					    .proto = sk->sk_protocol,
-					    .flags = inet_sk_flowi_flags(sk),
-					    .fl_ip_sport = inet->inet_sport,
-					    .fl_ip_dport = inet->inet_dport };
-
-			/* If this fails, retransmit mechanism of transport layer will
-			 * keep trying until route appears or the connection times
-			 * itself out.
-			 */
-			security_sk_classify_flow(sk, &fl);
-			rt = ip_route_output_flow(sock_net(sk), &fl, sk);
-			if (IS_ERR(rt))
-				goto no_route;
-		}
+		/* If this fails, retransmit mechanism of transport layer will
+		 * keep trying until route appears or the connection times
+		 * itself out.
+		 */
+		rt = ip_route_output_ports(sock_net(sk), sk,
+					   daddr, inet->inet_saddr,
+					   inet->inet_dport,
+					   inet->inet_sport,
+					   sk->sk_protocol,
+					   RT_CONN_FLAGS(sk),
+					   sk->sk_bound_dev_if);
+		if (IS_ERR(rt))
+			goto no_route;
 		sk_setup_caps(sk, &rt->dst);
 	}
 	skb_dst_set_noref(skb, &rt->dst);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 65008f45addc..bfc17c5914e7 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -460,20 +460,14 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto tx_error_icmp;
 	}
 
-	{
-		struct flowi fl = {
-			.oif = tunnel->parms.link,
-			.fl4_dst = dst,
-			.fl4_src= tiph->saddr,
-			.fl4_tos = RT_TOS(tos),
-			.proto = IPPROTO_IPIP
-		};
-
-		rt = ip_route_output_key(dev_net(dev), &fl);
-		if (IS_ERR(rt)) {
-			dev->stats.tx_carrier_errors++;
-			goto tx_error_icmp;
-		}
+	rt = ip_route_output_ports(dev_net(dev), NULL,
+				   dst, tiph->saddr,
+				   0, 0,
+				   IPPROTO_IPIP, RT_TOS(tos),
+				   tunnel->parms.link);
+	if (IS_ERR(rt)) {
+		dev->stats.tx_carrier_errors++;
+		goto tx_error_icmp;
 	}
 	tdev = rt->dst.dev;
 
@@ -584,14 +578,12 @@ static void ipip_tunnel_bind_dev(struct net_device *dev)
 	iph = &tunnel->parms.iph;
 
 	if (iph->daddr) {
-		struct flowi fl = {
-			.oif = tunnel->parms.link,
-			.fl4_dst = iph->daddr,
-			.fl4_src = iph->saddr,
-			.fl4_tos = RT_TOS(iph->tos),
-			.proto = IPPROTO_IPIP
-		};
-		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
+		struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL,
+							  iph->daddr, iph->saddr,
+							  0, 0,
+							  IPPROTO_IPIP,
+							  RT_TOS(iph->tos),
+							  tunnel->parms.link);
 
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 74909bac8817..594a3004367b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1611,25 +1611,19 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 #endif
 
 	if (vif->flags & VIFF_TUNNEL) {
-		struct flowi fl = {
-			.oif = vif->link,
-			.fl4_dst = vif->remote,
-			.fl4_src = vif->local,
-			.fl4_tos = RT_TOS(iph->tos),
-			.proto = IPPROTO_IPIP
-		};
-		rt = ip_route_output_key(net, &fl);
+		rt = ip_route_output_ports(net, NULL,
+					   vif->remote, vif->local,
+					   0, 0,
+					   IPPROTO_IPIP,
+					   RT_TOS(iph->tos), vif->link);
 		if (IS_ERR(rt))
 			goto out_free;
 		encap = sizeof(struct iphdr);
 	} else {
-		struct flowi fl = {
-			.oif = vif->link,
-			.fl4_dst = iph->daddr,
-			.fl4_tos = RT_TOS(iph->tos),
-			.proto = IPPROTO_IPIP
-		};
-		rt = ip_route_output_key(net, &fl);
+		rt = ip_route_output_ports(net, NULL, iph->daddr, 0,
+					   0, 0,
+					   IPPROTO_IPIP,
+					   RT_TOS(iph->tos), vif->link);
 		if (IS_ERR(rt))
 			goto out_free;
 	}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ea8d5e8128a9..f199b8486120 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -536,7 +536,6 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	int err;
 	struct sk_buff *skb2;
 	struct iphdr *eiph;
-	struct flowi fl;
 	struct rtable *rt;
 
 	err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
@@ -578,11 +577,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	eiph = ip_hdr(skb2);
 
 	/* Try to guess incoming interface */
-	memset(&fl, 0, sizeof(fl));
-	fl.fl4_dst = eiph->saddr;
-	fl.fl4_tos = RT_TOS(eiph->tos);
-	fl.proto = IPPROTO_IPIP;
-	rt = ip_route_output_key(dev_net(skb->dev), &fl);
+	rt = ip_route_output_ports(dev_net(skb->dev), NULL,
+				   eiph->saddr, 0,
+				   0, 0,
+				   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
 	if (IS_ERR(rt))
 		goto out;
 
@@ -592,10 +590,11 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (rt->rt_flags & RTCF_LOCAL) {
 		ip_rt_put(rt);
 		rt = NULL;
-		fl.fl4_dst = eiph->daddr;
-		fl.fl4_src = eiph->saddr;
-		fl.fl4_tos = eiph->tos;
-		rt = ip_route_output_key(dev_net(skb->dev), &fl);
+		rt = ip_route_output_ports(dev_net(skb->dev), NULL,
+					   eiph->daddr, eiph->saddr,
+					   0, 0,
+					   IPPROTO_IPIP,
+					   RT_TOS(eiph->tos), 0);
 		if (IS_ERR(rt) ||
 		    rt->dst.dev->type != ARPHRD_TUNNEL) {
 			if (!IS_ERR(rt))
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3534ceaa4fba..43b33373adb2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -732,17 +732,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		dst = addr6->s6_addr32[3];
 	}
 
-	{
-		struct flowi fl = { .fl4_dst = dst,
-				    .fl4_src = tiph->saddr,
-				    .fl4_tos = RT_TOS(tos),
-				    .oif = tunnel->parms.link,
-				    .proto = IPPROTO_IPV6 };
-		rt = ip_route_output_key(dev_net(dev), &fl);
-		if (IS_ERR(rt)) {
-			dev->stats.tx_carrier_errors++;
-			goto tx_error_icmp;
-		}
+	rt = ip_route_output_ports(dev_net(dev), NULL,
+				   dst, tiph->saddr,
+				   0, 0,
+				   IPPROTO_IPV6, RT_TOS(tos),
+				   tunnel->parms.link);
+	if (IS_ERR(rt)) {
+		dev->stats.tx_carrier_errors++;
+		goto tx_error_icmp;
 	}
 	if (rt->rt_type != RTN_UNICAST) {
 		ip_rt_put(rt);
@@ -858,12 +855,12 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	iph = &tunnel->parms.iph;
 
 	if (iph->daddr) {
-		struct flowi fl = { .fl4_dst = iph->daddr,
-				    .fl4_src = iph->saddr,
-				    .fl4_tos = RT_TOS(iph->tos),
-				    .oif = tunnel->parms.link,
-				    .proto = IPPROTO_IPV6 };
-		struct rtable *rt = ip_route_output_key(dev_net(dev), &fl);
+		struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL,
+							  iph->daddr, iph->saddr,
+							  0, 0,
+							  IPPROTO_IPV6,
+							  RT_TOS(iph->tos),
+							  tunnel->parms.link);
 
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 2a698ff89db6..fce9bd3bd3fe 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -475,25 +475,17 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		if (opt && opt->srr)
 			daddr = opt->faddr;
 
-		{
-			struct flowi fl = { .oif = sk->sk_bound_dev_if,
-					    .fl4_dst = daddr,
-					    .fl4_src = inet->inet_saddr,
-					    .fl4_tos = RT_CONN_FLAGS(sk),
-					    .proto = sk->sk_protocol,
-					    .flags = inet_sk_flowi_flags(sk),
-					    .fl_ip_sport = inet->inet_sport,
-					    .fl_ip_dport = inet->inet_dport };
-
-			/* If this fails, retransmit mechanism of transport layer will
-			 * keep trying until route appears or the connection times
-			 * itself out.
-			 */
-			security_sk_classify_flow(sk, &fl);
-			rt = ip_route_output_flow(sock_net(sk), &fl, sk);
-			if (IS_ERR(rt))
-				goto no_route;
-		}
+		/* If this fails, retransmit mechanism of transport layer will
+		 * keep trying until route appears or the connection times
+		 * itself out.
+		 */
+		rt = ip_route_output_ports(sock_net(sk), sk,
+					   daddr, inet->inet_saddr,
+					   inet->inet_dport, inet->inet_sport,
+					   sk->sk_protocol, RT_CONN_FLAGS(sk),
+					   sk->sk_bound_dev_if);
+		if (IS_ERR(rt))
+			goto no_route;
 		sk_setup_caps(sk, &rt->dst);
 	}
 	skb_dst_set(skb, dst_clone(&rt->dst));
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 878f6dd9dbad..faf381d9da7c 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -98,12 +98,7 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		spin_lock(&dest->dst_lock);
 		if (!(rt = (struct rtable *)
 		      __ip_vs_dst_check(dest, rtos))) {
-			struct flowi fl = {
-				.fl4_dst = dest->addr.ip,
-				.fl4_tos = rtos,
-			};
-
-			rt = ip_route_output_key(net, &fl);
+			rt = ip_route_output(net, dest->addr.ip, 0, rtos, 0);
 			if (IS_ERR(rt)) {
 				spin_unlock(&dest->dst_lock);
 				IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
@@ -117,12 +112,7 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		}
 		spin_unlock(&dest->dst_lock);
 	} else {
-		struct flowi fl = {
-			.fl4_dst = daddr,
-			.fl4_tos = rtos,
-		};
-
-		rt = ip_route_output_key(net, &fl);
+		rt = ip_route_output(net, daddr, 0, rtos, 0);
 		if (IS_ERR(rt)) {
 			IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
 				     &daddr);
diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c
index 3620c569275f..55b93dc60d0c 100644
--- a/net/rxrpc/ar-peer.c
+++ b/net/rxrpc/ar-peer.c
@@ -36,28 +36,13 @@ static void rxrpc_destroy_peer(struct work_struct *work);
 static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
 {
 	struct rtable *rt;
-	struct flowi fl;
 
 	peer->if_mtu = 1500;
 
-	memset(&fl, 0, sizeof(fl));
-
-	switch (peer->srx.transport.family) {
-	case AF_INET:
-		fl.oif = 0;
-		fl.proto = IPPROTO_UDP,
-		fl.fl4_dst = peer->srx.transport.sin.sin_addr.s_addr;
-		fl.fl4_src = 0;
-		fl.fl4_tos = 0;
-		/* assume AFS.CM talking to AFS.FS */
-		fl.fl_ip_sport = htons(7001);
-		fl.fl_ip_dport = htons(7000);
-		break;
-	default:
-		BUG();
-	}
-
-	rt = ip_route_output_key(&init_net, &fl);
+	rt = ip_route_output_ports(&init_net, NULL,
+				   peer->srx.transport.sin.sin_addr.s_addr, 0,
+				   htons(7000), htons(7001),
+				   IPPROTO_UDP, 0, 0);
 	if (IS_ERR(rt)) {
 		_leave(" [route err %ld]", PTR_ERR(rt));
 		return;
-- 
cgit v1.2.3


From fbef0a40919a80eb8a02fe9d3b96dfdcdebf4317 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 11 Mar 2011 15:55:37 -0500
Subject: net: Remove unnecessary padding in struct flowi

Move tos, scope, proto, and flags to the beginning of
the structure.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index fd0413873b8e..a661fd6f76ba 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -14,13 +14,19 @@ struct flowi {
 	int	oif;
 	int	iif;
 	__u32	mark;
+	__u8	tos;
+	__u8	scope;
+	__u8	proto;
+	__u8	flags;
+#define FLOWI_FLAG_ANYSRC		0x01
+#define FLOWI_FLAG_PRECOW_METRICS	0x02
+#define FLOWI_FLAG_CAN_SLEEP		0x04
+	__u32	secid;
 
 	union {
 		struct {
 			__be32			daddr;
 			__be32			saddr;
-			__u8			tos;
-			__u8			scope;
 		} ip4_u;
 		
 		struct {
@@ -43,14 +49,9 @@ struct flowi {
 #define fl6_flowlabel	nl_u.ip6_u.flowlabel
 #define fl4_dst		nl_u.ip4_u.daddr
 #define fl4_src		nl_u.ip4_u.saddr
-#define fl4_tos		nl_u.ip4_u.tos
-#define fl4_scope	nl_u.ip4_u.scope
+#define fl4_tos		tos
+#define fl4_scope	scope
 
-	__u8	proto;
-	__u8	flags;
-#define FLOWI_FLAG_ANYSRC		0x01
-#define FLOWI_FLAG_PRECOW_METRICS	0x02
-#define FLOWI_FLAG_CAN_SLEEP		0x04
 	union {
 		struct {
 			__be16	sport;
@@ -81,7 +82,6 @@ struct flowi {
 #define fl_ipsec_spi	uli_u.spi
 #define fl_mh_type	uli_u.mht.type
 #define fl_gre_key	uli_u.gre_key
-	__u32           secid;	/* used by xfrm; see secid.txt */
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 #define FLOW_DIR_IN	0
-- 
cgit v1.2.3


From 1d28f42c1bd4bb2363d88df74d0128b4da135b4a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 00:29:39 -0500
Subject: net: Put flowi_* prefix on AF independent members of struct flowi

I intend to turn struct flowi into a union of AF specific flowi
structs.  There will be a common structure that each variant includes
first, much like struct sock_common.

This is the first step to move in that direction.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c   |  2 +-
 drivers/net/cnic.c               |  2 +-
 include/net/dn_route.h           |  4 +-
 include/net/flow.h               | 22 ++++-----
 include/net/route.h              | 36 +++++++--------
 include/net/xfrm.h               |  4 +-
 net/core/fib_rules.c             |  6 +--
 net/dccp/ipv4.c                  | 17 +++----
 net/dccp/ipv6.c                  | 20 ++++-----
 net/decnet/af_decnet.c           |  4 +-
 net/decnet/dn_fib.c              |  4 +-
 net/decnet/dn_nsp_out.c          |  4 +-
 net/decnet/dn_route.c            | 96 +++++++++++++++++++++-------------------
 net/ipv4/fib_frontend.c          | 12 ++---
 net/ipv4/fib_semantics.c         |  2 +-
 net/ipv4/fib_trie.c              |  2 +-
 net/ipv4/icmp.c                  | 12 ++---
 net/ipv4/inet_connection_sock.c  | 22 ++++-----
 net/ipv4/ip_output.c             | 18 ++++----
 net/ipv4/ipmr.c                  | 12 ++---
 net/ipv4/netfilter.c             |  6 +--
 net/ipv4/raw.c                   | 10 ++---
 net/ipv4/route.c                 | 72 +++++++++++++++---------------
 net/ipv4/syncookies.c            | 20 +++++----
 net/ipv4/udp.c                   | 21 ++++-----
 net/ipv4/xfrm4_policy.c          | 10 ++---
 net/ipv4/xfrm4_state.c           |  4 +-
 net/ipv6/af_inet6.c              |  6 +--
 net/ipv6/datagram.c              | 20 ++++-----
 net/ipv6/icmp.c                  | 24 +++++-----
 net/ipv6/inet6_connection_sock.c | 12 ++---
 net/ipv6/ip6_flowlabel.c         |  2 +-
 net/ipv6/ip6_output.c            | 10 ++---
 net/ipv6/ip6_tunnel.c            |  8 ++--
 net/ipv6/ip6mr.c                 | 22 ++++-----
 net/ipv6/ipv6_sockglue.c         |  4 +-
 net/ipv6/mip6.c                  |  6 +--
 net/ipv6/netfilter.c             |  4 +-
 net/ipv6/netfilter/ip6t_REJECT.c |  2 +-
 net/ipv6/raw.c                   | 20 ++++-----
 net/ipv6/route.c                 | 20 ++++-----
 net/ipv6/syncookies.c            |  6 +--
 net/ipv6/tcp_ipv6.c              | 22 ++++-----
 net/ipv6/udp.c                   | 20 ++++-----
 net/ipv6/xfrm6_policy.c          | 10 ++---
 net/ipv6/xfrm6_state.c           |  4 +-
 net/netfilter/ipvs/ip_vs_ctl.c   |  2 +-
 net/netfilter/ipvs/ip_vs_xmit.c  |  2 +-
 net/netfilter/xt_TEE.c           |  4 +-
 net/sctp/ipv6.c                  |  8 ++--
 net/sctp/protocol.c              |  4 +-
 net/xfrm/xfrm_policy.c           | 18 ++++----
 net/xfrm/xfrm_state.c            |  2 +-
 security/security.c              |  4 +-
 security/selinux/hooks.c         |  2 +-
 security/selinux/xfrm.c          |  4 +-
 56 files changed, 365 insertions(+), 351 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 1742f72fbd57..3c2b309ab891 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -239,7 +239,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 	memset(&fl, 0, sizeof fl);
 	ipv6_addr_copy(&fl.fl6_dst, &dst_in->sin6_addr);
 	ipv6_addr_copy(&fl.fl6_src, &src_in->sin6_addr);
-	fl.oif = addr->bound_dev_if;
+	fl.flowi_oif = addr->bound_dev_if;
 
 	dst = ip6_route_output(&init_net, NULL, &fl);
 	if ((ret = dst->error))
diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c
index 65832951fe07..c8922f69705e 100644
--- a/drivers/net/cnic.c
+++ b/drivers/net/cnic.c
@@ -3429,7 +3429,7 @@ static int cnic_get_v6_route(struct sockaddr_in6 *dst_addr,
 	memset(&fl, 0, sizeof(fl));
 	ipv6_addr_copy(&fl.fl6_dst, &dst_addr->sin6_addr);
 	if (ipv6_addr_type(&fl.fl6_dst) & IPV6_ADDR_LINKLOCAL)
-		fl.oif = dst_addr->sin6_scope_id;
+		fl.flowi_oif = dst_addr->sin6_scope_id;
 
 	*dst = ip6_route_output(&init_net, NULL, &fl);
 	if (*dst)
diff --git a/include/net/dn_route.h b/include/net/dn_route.h
index 9b185df265fb..1f59005e4979 100644
--- a/include/net/dn_route.h
+++ b/include/net/dn_route.h
@@ -82,12 +82,12 @@ struct dn_route {
 
 static inline bool dn_is_input_route(struct dn_route *rt)
 {
-	return rt->fl.iif != 0;
+	return rt->fl.flowi_iif != 0;
 }
 
 static inline bool dn_is_output_route(struct dn_route *rt)
 {
-	return rt->fl.iif == 0;
+	return rt->fl.flowi_iif == 0;
 }
 
 extern void dn_route_init(void);
diff --git a/include/net/flow.h b/include/net/flow.h
index a661fd6f76ba..8c4dbd078490 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -11,17 +11,17 @@
 #include <asm/atomic.h>
 
 struct flowi {
-	int	oif;
-	int	iif;
-	__u32	mark;
-	__u8	tos;
-	__u8	scope;
-	__u8	proto;
-	__u8	flags;
+	int	flowi_oif;
+	int	flowi_iif;
+	__u32	flowi_mark;
+	__u8	flowi_tos;
+	__u8	flowi_scope;
+	__u8	flowi_proto;
+	__u8	flowi_flags;
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_PRECOW_METRICS	0x02
 #define FLOWI_FLAG_CAN_SLEEP		0x04
-	__u32	secid;
+	__u32	flowi_secid;
 
 	union {
 		struct {
@@ -49,8 +49,8 @@ struct flowi {
 #define fl6_flowlabel	nl_u.ip6_u.flowlabel
 #define fl4_dst		nl_u.ip4_u.daddr
 #define fl4_src		nl_u.ip4_u.saddr
-#define fl4_tos		tos
-#define fl4_scope	scope
+#define fl4_tos		flowi_tos
+#define fl4_scope	flowi_scope
 
 	union {
 		struct {
@@ -116,7 +116,7 @@ extern atomic_t flow_cache_genid;
 static inline int flow_cache_uli_match(const struct flowi *fl1,
 				       const struct flowi *fl2)
 {
-	return (fl1->proto == fl2->proto &&
+	return (fl1->flowi_proto == fl2->flowi_proto &&
 		!memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u)));
 }
 
diff --git a/include/net/route.h b/include/net/route.h
index f140f4130fea..3d814f84abd0 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -136,7 +136,7 @@ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
 					     __be32 saddr, u8 tos, int oif)
 {
 	struct flowi fl = {
-		.oif = oif,
+		.flowi_oif = oif,
 		.fl4_dst = daddr,
 		.fl4_src = saddr,
 		.fl4_tos = tos,
@@ -150,13 +150,13 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct sock
 						   __u8 proto, __u8 tos, int oif)
 {
 	struct flowi fl = {
-		.oif = oif,
-		.flags = sk ? inet_sk_flowi_flags(sk) : 0,
-		.mark = sk ? sk->sk_mark : 0,
+		.flowi_oif = oif,
+		.flowi_flags = sk ? inet_sk_flowi_flags(sk) : 0,
+		.flowi_mark = sk ? sk->sk_mark : 0,
 		.fl4_dst = daddr,
 		.fl4_src = saddr,
 		.fl4_tos = tos,
-		.proto = proto,
+		.flowi_proto = proto,
 		.fl_ip_dport = dport,
 		.fl_ip_sport = sport,
 	};
@@ -170,11 +170,11 @@ static inline struct rtable *ip_route_output_gre(struct net *net,
 						 __be32 gre_key, __u8 tos, int oif)
 {
 	struct flowi fl = {
-		.oif = oif,
+		.flowi_oif = oif,
 		.fl4_dst = daddr,
 		.fl4_src = saddr,
 		.fl4_tos = tos,
-		.proto = IPPROTO_GRE,
+		.flowi_proto = IPPROTO_GRE,
 		.fl_gre_key = gre_key,
 	};
 	return ip_route_output_key(net, &fl);
@@ -228,23 +228,23 @@ static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos,
 					      __be16 sport, __be16 dport,
 					      struct sock *sk, bool can_sleep)
 {
-	struct flowi fl = { .oif = oif,
-			    .mark = sk->sk_mark,
+	struct flowi fl = { .flowi_oif = oif,
+			    .flowi_mark = sk->sk_mark,
 			    .fl4_dst = dst,
 			    .fl4_src = src,
 			    .fl4_tos = tos,
-			    .proto = protocol,
+			    .flowi_proto = protocol,
 			    .fl_ip_sport = sport,
 			    .fl_ip_dport = dport };
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
 
 	if (inet_sk(sk)->transparent)
-		fl.flags |= FLOWI_FLAG_ANYSRC;
+		fl.flowi_flags |= FLOWI_FLAG_ANYSRC;
 	if (protocol == IPPROTO_TCP)
-		fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
+		fl.flowi_flags |= FLOWI_FLAG_PRECOW_METRICS;
 	if (can_sleep)
-		fl.flags |= FLOWI_FLAG_CAN_SLEEP;
+		fl.flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	if (!dst || !src) {
 		rt = __ip_route_output_key(net, &fl);
@@ -264,19 +264,19 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 					       __be16 dport, struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
-		struct flowi fl = { .oif = rt->rt_oif,
-				    .mark = rt->rt_mark,
+		struct flowi fl = { .flowi_oif = rt->rt_oif,
+				    .flowi_mark = rt->rt_mark,
 				    .fl4_dst = rt->rt_key_dst,
 				    .fl4_src = rt->rt_key_src,
 				    .fl4_tos = rt->rt_tos,
-				    .proto = protocol,
+				    .flowi_proto = protocol,
 				    .fl_ip_sport = sport,
 				    .fl_ip_dport = dport };
 
 		if (inet_sk(sk)->transparent)
-			fl.flags |= FLOWI_FLAG_ANYSRC;
+			fl.flowi_flags |= FLOWI_FLAG_ANYSRC;
 		if (protocol == IPPROTO_TCP)
-			fl.flags |= FLOWI_FLAG_PRECOW_METRICS;
+			fl.flowi_flags |= FLOWI_FLAG_PRECOW_METRICS;
 		ip_rt_put(rt);
 		security_sk_classify_flow(sk, &fl);
 		return ip_route_output_flow(sock_net(sk), &fl, sk);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index d5dcf3974636..d5a12d10a0d4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -803,7 +803,7 @@ static __inline__
 __be16 xfrm_flowi_sport(const struct flowi *fl)
 {
 	__be16 port;
-	switch(fl->proto) {
+	switch(fl->flowi_proto) {
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
 	case IPPROTO_UDPLITE:
@@ -830,7 +830,7 @@ static __inline__
 __be16 xfrm_flowi_dport(const struct flowi *fl)
 {
 	__be16 port;
-	switch(fl->proto) {
+	switch(fl->flowi_proto) {
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
 	case IPPROTO_UDPLITE:
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index a20e5d3bbfa0..8248ebb5891d 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -181,13 +181,13 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 {
 	int ret = 0;
 
-	if (rule->iifindex && (rule->iifindex != fl->iif))
+	if (rule->iifindex && (rule->iifindex != fl->flowi_iif))
 		goto out;
 
-	if (rule->oifindex && (rule->oifindex != fl->oif))
+	if (rule->oifindex && (rule->oifindex != fl->flowi_oif))
 		goto out;
 
-	if ((rule->mark ^ fl->mark) & rule->mark_mask)
+	if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
 		goto out;
 
 	ret = ops->match(rule, fl, flags);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 7882377bc62e..09a09911c5ea 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -465,14 +465,15 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 					   struct sk_buff *skb)
 {
 	struct rtable *rt;
-	struct flowi fl = { .oif = skb_rtable(skb)->rt_iif,
-			    .fl4_dst = ip_hdr(skb)->saddr,
-			    .fl4_src = ip_hdr(skb)->daddr,
-			    .fl4_tos = RT_CONN_FLAGS(sk),
-			    .proto = sk->sk_protocol,
-			    .fl_ip_sport = dccp_hdr(skb)->dccph_dport,
-			    .fl_ip_dport = dccp_hdr(skb)->dccph_sport
-			  };
+	struct flowi fl = {
+		.flowi_oif = skb_rtable(skb)->rt_iif,
+		.fl4_dst = ip_hdr(skb)->saddr,
+		.fl4_src = ip_hdr(skb)->daddr,
+		.fl4_tos = RT_CONN_FLAGS(sk),
+		.flowi_proto = sk->sk_protocol,
+		.fl_ip_sport = dccp_hdr(skb)->dccph_dport,
+		.fl_ip_dport = dccp_hdr(skb)->dccph_sport,
+	};
 
 	security_skb_classify_flow(skb, &fl);
 	rt = ip_route_output_flow(net, &fl, sk);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5efc57f5e605..5209ee7a3dc2 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -154,10 +154,10 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			   for now.
 			 */
 			memset(&fl, 0, sizeof(fl));
-			fl.proto = IPPROTO_DCCP;
+			fl.flowi_proto = IPPROTO_DCCP;
 			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-			fl.oif = sk->sk_bound_dev_if;
+			fl.flowi_oif = sk->sk_bound_dev_if;
 			fl.fl_ip_dport = inet->inet_dport;
 			fl.fl_ip_sport = inet->inet_sport;
 			security_sk_classify_flow(sk, &fl);
@@ -248,11 +248,11 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 	struct dst_entry *dst;
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = IPPROTO_DCCP;
+	fl.flowi_proto = IPPROTO_DCCP;
 	ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
 	ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
 	fl.fl6_flowlabel = 0;
-	fl.oif = ireq6->iif;
+	fl.flowi_oif = ireq6->iif;
 	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
 	fl.fl_ip_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
@@ -321,8 +321,8 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 	ipv6_addr_copy(&fl.fl6_dst, &rxip6h->saddr);
 	ipv6_addr_copy(&fl.fl6_src, &rxip6h->daddr);
 
-	fl.proto = IPPROTO_DCCP;
-	fl.oif = inet6_iif(rxskb);
+	fl.flowi_proto = IPPROTO_DCCP;
+	fl.flowi_oif = inet6_iif(rxskb);
 	fl.fl_ip_dport = dccp_hdr(skb)->dccph_dport;
 	fl.fl_ip_sport = dccp_hdr(skb)->dccph_sport;
 	security_skb_classify_flow(rxskb, &fl);
@@ -530,11 +530,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		struct flowi fl;
 
 		memset(&fl, 0, sizeof(fl));
-		fl.proto = IPPROTO_DCCP;
+		fl.flowi_proto = IPPROTO_DCCP;
 		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
 		final_p = fl6_update_dst(&fl, opt, &final);
 		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
-		fl.oif = sk->sk_bound_dev_if;
+		fl.flowi_oif = sk->sk_bound_dev_if;
 		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
 		fl.fl_ip_sport = inet_rsk(req)->loc_port;
 		security_sk_classify_flow(sk, &fl);
@@ -953,10 +953,10 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (!ipv6_addr_any(&np->rcv_saddr))
 		saddr = &np->rcv_saddr;
 
-	fl.proto = IPPROTO_DCCP;
+	fl.flowi_proto = IPPROTO_DCCP;
 	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 	ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr);
-	fl.oif = sk->sk_bound_dev_if;
+	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.fl_ip_dport = usin->sin6_port;
 	fl.fl_ip_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, &fl);
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 2af15b15d1fa..aafd15a01575 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -948,11 +948,11 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen,
 
 	err = -EHOSTUNREACH;
 	memset(&fl, 0, sizeof(fl));
-	fl.oif = sk->sk_bound_dev_if;
+	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.fld_dst = dn_saddr2dn(&scp->peer);
 	fl.fld_src = dn_saddr2dn(&scp->addr);
 	dn_sk_ports_copy(&fl, scp);
-	fl.proto = DNPROTO_NSP;
+	fl.flowi_proto = DNPROTO_NSP;
 	if (dn_route_output_sock(&sk->sk_dst_cache, &fl, sk, flags) < 0)
 		goto out;
 	sk->sk_route_caps = sk->sk_dst_cache->dev->features;
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 0ef0a81bcd72..4dfffa0b67a8 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -223,7 +223,7 @@ static int dn_fib_check_nh(const struct rtmsg *r, struct dn_fib_info *fi, struct
 
 		memset(&fl, 0, sizeof(fl));
 		fl.fld_dst = nh->nh_gw;
-		fl.oif = nh->nh_oif;
+		fl.flowi_oif = nh->nh_oif;
 		fl.fld_scope = r->rtm_scope + 1;
 
 		if (fl.fld_scope < RT_SCOPE_LINK)
@@ -424,7 +424,7 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowi *
 				for_nexthops(fi) {
 					if (nh->nh_flags & RTNH_F_DEAD)
 						continue;
-					if (!fl->oif || fl->oif == nh->nh_oif)
+					if (!fl->flowi_oif || fl->flowi_oif == nh->nh_oif)
 						break;
 				}
 				if (nhsel < fi->fib_nhs) {
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index 2ef115277bea..b3d66742a01f 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -92,11 +92,11 @@ try_again:
 	}
 
 	memset(&fl, 0, sizeof(fl));
-	fl.oif = sk->sk_bound_dev_if;
+	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.fld_src = dn_saddr2dn(&scp->addr);
 	fl.fld_dst = dn_saddr2dn(&scp->peer);
 	dn_sk_ports_copy(&fl, scp);
-	fl.proto = DNPROTO_NSP;
+	fl.flowi_proto = DNPROTO_NSP;
 	if (dn_route_output_sock(&sk->sk_dst_cache, &fl, sk, 0) == 0) {
 		dst = sk_dst_get(sk);
 		sk->sk_route_caps = dst->dev->features;
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 484fdbf92bd8..d74d34b93f80 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -286,10 +286,10 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
 {
 	return ((fl1->fld_dst ^ fl2->fld_dst) |
 		(fl1->fld_src ^ fl2->fld_src) |
-		(fl1->mark ^ fl2->mark) |
+		(fl1->flowi_mark ^ fl2->flowi_mark) |
 		(fl1->fld_scope ^ fl2->fld_scope) |
-		(fl1->oif ^ fl2->oif) |
-		(fl1->iif ^ fl2->iif)) == 0;
+		(fl1->flowi_oif ^ fl2->flowi_oif) |
+		(fl1->flowi_iif ^ fl2->flowi_iif)) == 0;
 }
 
 static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp)
@@ -905,12 +905,14 @@ static inline __le16 dn_fib_rules_map_destination(__le16 daddr, struct dn_fib_re
 
 static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *oldflp, int try_hard)
 {
-	struct flowi fl = { .fld_dst = oldflp->fld_dst,
-			    .fld_src = oldflp->fld_src,
-			    .fld_scope = RT_SCOPE_UNIVERSE,
-			    .mark = oldflp->mark,
-			    .iif = init_net.loopback_dev->ifindex,
-			    .oif = oldflp->oif };
+	struct flowi fl = {
+		.fld_dst = oldflp->fld_dst,
+		.fld_src = oldflp->fld_src,
+		.fld_scope = RT_SCOPE_UNIVERSE,
+		.flowi_mark = oldflp->flowi_mark,
+		.flowi_iif = init_net.loopback_dev->ifindex,
+		.flowi_oif = oldflp->flowi_oif,
+	};
 	struct dn_route *rt = NULL;
 	struct net_device *dev_out = NULL, *dev;
 	struct neighbour *neigh = NULL;
@@ -926,11 +928,11 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old
 		       "dn_route_output_slow: dst=%04x src=%04x mark=%d"
 		       " iif=%d oif=%d\n", le16_to_cpu(oldflp->fld_dst),
 		       le16_to_cpu(oldflp->fld_src),
-		       oldflp->mark, init_net.loopback_dev->ifindex, oldflp->oif);
+		       oldflp->flowi_mark, init_net.loopback_dev->ifindex, oldflp->flowi_oif);
 
 	/* If we have an output interface, verify its a DECnet device */
-	if (oldflp->oif) {
-		dev_out = dev_get_by_index(&init_net, oldflp->oif);
+	if (oldflp->flowi_oif) {
+		dev_out = dev_get_by_index(&init_net, oldflp->flowi_oif);
 		err = -ENODEV;
 		if (dev_out && dev_out->dn_ptr == NULL) {
 			dev_put(dev_out);
@@ -988,7 +990,7 @@ source_ok:
 			if (!fl.fld_dst)
 				goto out;
 		}
-		fl.oif = init_net.loopback_dev->ifindex;
+		fl.flowi_oif = init_net.loopback_dev->ifindex;
 		res.type = RTN_LOCAL;
 		goto make_route;
 	}
@@ -998,7 +1000,7 @@ source_ok:
 		       "dn_route_output_slow: initial checks complete."
 		       " dst=%o4x src=%04x oif=%d try_hard=%d\n",
 		       le16_to_cpu(fl.fld_dst), le16_to_cpu(fl.fld_src),
-		       fl.oif, try_hard);
+		       fl.flowi_oif, try_hard);
 
 	/*
 	 * N.B. If the kernel is compiled without router support then
@@ -1023,8 +1025,8 @@ source_ok:
 		if (!try_hard) {
 			neigh = neigh_lookup_nodev(&dn_neigh_table, &init_net, &fl.fld_dst);
 			if (neigh) {
-				if ((oldflp->oif &&
-				    (neigh->dev->ifindex != oldflp->oif)) ||
+				if ((oldflp->flowi_oif &&
+				    (neigh->dev->ifindex != oldflp->flowi_oif)) ||
 				    (oldflp->fld_src &&
 				    (!dn_dev_islocal(neigh->dev,
 						      oldflp->fld_src)))) {
@@ -1078,7 +1080,7 @@ select_source:
 			if (fl.fld_src == 0 && res.type != RTN_LOCAL)
 				goto e_addr;
 		}
-		fl.oif = dev_out->ifindex;
+		fl.flowi_oif = dev_out->ifindex;
 		goto make_route;
 	}
 	free_res = 1;
@@ -1093,14 +1095,14 @@ select_source:
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
-		fl.oif = dev_out->ifindex;
+		fl.flowi_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
 		res.fi = NULL;
 		goto make_route;
 	}
 
-	if (res.fi->fib_nhs > 1 && fl.oif == 0)
+	if (res.fi->fib_nhs > 1 && fl.flowi_oif == 0)
 		dn_fib_select_multipath(&fl, &res);
 
 	/*
@@ -1115,7 +1117,7 @@ select_source:
 		dev_put(dev_out);
 	dev_out = DN_FIB_RES_DEV(res);
 	dev_hold(dev_out);
-	fl.oif = dev_out->ifindex;
+	fl.flowi_oif = dev_out->ifindex;
 	gateway = DN_FIB_RES_GW(res);
 
 make_route:
@@ -1131,9 +1133,9 @@ make_route:
 
 	rt->fl.fld_src    = oldflp->fld_src;
 	rt->fl.fld_dst    = oldflp->fld_dst;
-	rt->fl.oif        = oldflp->oif;
-	rt->fl.iif        = 0;
-	rt->fl.mark       = oldflp->mark;
+	rt->fl.flowi_oif     = oldflp->flowi_oif;
+	rt->fl.flowi_iif     = 0;
+	rt->fl.flowi_mark    = oldflp->flowi_mark;
 
 	rt->rt_saddr      = fl.fld_src;
 	rt->rt_daddr      = fl.fld_dst;
@@ -1201,9 +1203,9 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *fl
 			rt = rcu_dereference_bh(rt->dst.dn_next)) {
 			if ((flp->fld_dst == rt->fl.fld_dst) &&
 			    (flp->fld_src == rt->fl.fld_src) &&
-			    (flp->mark == rt->fl.mark) &&
+			    (flp->flowi_mark == rt->fl.flowi_mark) &&
 			    dn_is_output_route(rt) &&
-			    (rt->fl.oif == flp->oif)) {
+			    (rt->fl.flowi_oif == flp->flowi_oif)) {
 				dst_use(&rt->dst, jiffies);
 				rcu_read_unlock_bh();
 				*pprt = &rt->dst;
@@ -1221,7 +1223,7 @@ static int dn_route_output_key(struct dst_entry **pprt, struct flowi *flp, int f
 	int err;
 
 	err = __dn_route_output_key(pprt, flp, flags);
-	if (err == 0 && flp->proto) {
+	if (err == 0 && flp->flowi_proto) {
 		*pprt = xfrm_lookup(&init_net, *pprt, flp, NULL, 0);
 		if (IS_ERR(*pprt)) {
 			err = PTR_ERR(*pprt);
@@ -1236,9 +1238,9 @@ int dn_route_output_sock(struct dst_entry **pprt, struct flowi *fl, struct sock
 	int err;
 
 	err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD);
-	if (err == 0 && fl->proto) {
+	if (err == 0 && fl->flowi_proto) {
 		if (!(flags & MSG_DONTWAIT))
-			fl->flags |= FLOWI_FLAG_CAN_SLEEP;
+			fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
 		*pprt = xfrm_lookup(&init_net, *pprt, fl, sk, 0);
 		if (IS_ERR(*pprt)) {
 			err = PTR_ERR(*pprt);
@@ -1260,11 +1262,13 @@ static int dn_route_input_slow(struct sk_buff *skb)
 	int flags = 0;
 	__le16 gateway = 0;
 	__le16 local_src = 0;
-	struct flowi fl = { .fld_dst = cb->dst,
-			    .fld_src = cb->src,
-			    .fld_scope = RT_SCOPE_UNIVERSE,
-			    .mark = skb->mark,
-			    .iif = skb->dev->ifindex };
+	struct flowi fl = {
+		.fld_dst = cb->dst,
+		.fld_src = cb->src,
+		.fld_scope = RT_SCOPE_UNIVERSE,
+		.flowi_mark = skb->mark,
+		.flowi_iif = skb->dev->ifindex,
+	};
 	struct dn_fib_res res = { .fi = NULL, .type = RTN_UNREACHABLE };
 	int err = -EINVAL;
 	int free_res = 0;
@@ -1343,7 +1347,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
 		if (dn_db->parms.forwarding == 0)
 			goto e_inval;
 
-		if (res.fi->fib_nhs > 1 && fl.oif == 0)
+		if (res.fi->fib_nhs > 1 && fl.flowi_oif == 0)
 			dn_fib_select_multipath(&fl, &res);
 
 		/*
@@ -1408,9 +1412,9 @@ make_route:
 
 	rt->fl.fld_src    = cb->src;
 	rt->fl.fld_dst    = cb->dst;
-	rt->fl.oif        = 0;
-	rt->fl.iif        = in_dev->ifindex;
-	rt->fl.mark       = fl.mark;
+	rt->fl.flowi_oif     = 0;
+	rt->fl.flowi_iif     = in_dev->ifindex;
+	rt->fl.flowi_mark    = fl.flowi_mark;
 
 	rt->dst.flags = DST_HOST;
 	rt->dst.neighbour = neigh;
@@ -1482,9 +1486,9 @@ static int dn_route_input(struct sk_buff *skb)
 	    rt = rcu_dereference(rt->dst.dn_next)) {
 		if ((rt->fl.fld_src == cb->src) &&
 		    (rt->fl.fld_dst == cb->dst) &&
-		    (rt->fl.oif == 0) &&
-		    (rt->fl.mark == skb->mark) &&
-		    (rt->fl.iif == cb->iif)) {
+		    (rt->fl.flowi_oif == 0) &&
+		    (rt->fl.flowi_mark == skb->mark) &&
+		    (rt->fl.flowi_iif == cb->iif)) {
 			dst_use(&rt->dst, jiffies);
 			rcu_read_unlock();
 			skb_dst_set(skb, (struct dst_entry *)rt);
@@ -1541,7 +1545,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 			       rt->dst.error) < 0)
 		goto rtattr_failure;
 	if (dn_is_input_route(rt))
-		RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.iif);
+		RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.flowi_iif);
 
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	return skb->len;
@@ -1570,7 +1574,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 		return -EINVAL;
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = DNPROTO_NSP;
+	fl.flowi_proto = DNPROTO_NSP;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb == NULL)
@@ -1583,11 +1587,11 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 	if (rta[RTA_DST-1])
 		memcpy(&fl.fld_dst, RTA_DATA(rta[RTA_DST-1]), 2);
 	if (rta[RTA_IIF-1])
-		memcpy(&fl.iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));
+		memcpy(&fl.flowi_iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));
 
-	if (fl.iif) {
+	if (fl.flowi_iif) {
 		struct net_device *dev;
-		if ((dev = dev_get_by_index(&init_net, fl.iif)) == NULL) {
+		if ((dev = dev_get_by_index(&init_net, fl.flowi_iif)) == NULL) {
 			kfree_skb(skb);
 			return -ENODEV;
 		}
@@ -1611,7 +1615,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 		int oif = 0;
 		if (rta[RTA_OIF - 1])
 			memcpy(&oif, RTA_DATA(rta[RTA_OIF - 1]), sizeof(int));
-		fl.oif = oif;
+		fl.flowi_oif = oif;
 		err = dn_route_output_key((struct dst_entry **)&rt, &fl, 0);
 	}
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index fe10bcd0f307..76105284a81c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -200,9 +200,9 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 	int ret;
 	struct net *net;
 
-	fl.oif = 0;
-	fl.iif = oif;
-	fl.mark = mark;
+	fl.flowi_oif = 0;
+	fl.flowi_iif = oif;
+	fl.flowi_mark = mark;
 	fl.fl4_dst = src;
 	fl.fl4_src = dst;
 	fl.fl4_tos = tos;
@@ -215,7 +215,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 		rpf = IN_DEV_RPFILTER(in_dev);
 		accept_local = IN_DEV_ACCEPT_LOCAL(in_dev);
 		if (mark && !IN_DEV_SRC_VMARK(in_dev))
-			fl.mark = 0;
+			fl.flowi_mark = 0;
 	}
 
 	if (in_dev == NULL)
@@ -253,7 +253,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 		goto last_resort;
 	if (rpf == 1)
 		goto e_rpf;
-	fl.oif = dev->ifindex;
+	fl.flowi_oif = dev->ifindex;
 
 	ret = 0;
 	if (fib_lookup(net, &fl, &res) == 0) {
@@ -797,7 +797,7 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
 
 	struct fib_result       res;
 	struct flowi            fl = {
-		.mark = frn->fl_mark,
+		.flowi_mark = frn->fl_mark,
 		.fl4_dst = frn->fl_addr,
 		.fl4_tos = frn->fl_tos,
 		.fl4_scope = frn->fl_scope,
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b5d523b911e6..79179ade5294 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -563,7 +563,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			struct flowi fl = {
 				.fl4_dst = nh->nh_gw,
 				.fl4_scope = cfg->fc_scope + 1,
-				.oif = nh->nh_oif,
+				.flowi_oif = nh->nh_oif,
 			};
 
 			/* It is not necessary, but requires a bit of thinking */
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index a4109a544778..d5ff80ef001a 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1379,7 +1379,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
 				if (nh->nh_flags & RTNH_F_DEAD)
 					continue;
-				if (flp->oif && flp->oif != nh->nh_oif)
+				if (flp->flowi_oif && flp->flowi_oif != nh->nh_oif)
 					continue;
 
 #ifdef CONFIG_IP_FIB_TRIE_STATS
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 1771ce662548..3fde7f23c70b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,10 +353,12 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 			daddr = icmp_param->replyopts.faddr;
 	}
 	{
-		struct flowi fl = { .fl4_dst= daddr,
-				    .fl4_src = rt->rt_spec_dst,
-				    .fl4_tos = RT_TOS(ip_hdr(skb)->tos),
-				    .proto = IPPROTO_ICMP };
+		struct flowi fl = {
+			.fl4_dst = daddr,
+			.fl4_src = rt->rt_spec_dst,
+			.fl4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi_proto = IPPROTO_ICMP,
+		};
 		security_skb_classify_flow(skb, &fl);
 		rt = ip_route_output_key(net, &fl);
 		if (IS_ERR(rt))
@@ -381,7 +383,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 			    param->replyopts.faddr : iph->saddr),
 		.fl4_src = saddr,
 		.fl4_tos = RT_TOS(tos),
-		.proto = IPPROTO_ICMP,
+		.flowi_proto = IPPROTO_ICMP,
 		.fl_icmp_type = type,
 		.fl_icmp_code = code,
 	};
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e4e301a61c5b..97081702dffd 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -356,16 +356,18 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct rtable *rt;
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct ip_options *opt = inet_rsk(req)->opt;
-	struct flowi fl = { .oif = sk->sk_bound_dev_if,
-			    .mark = sk->sk_mark,
-			    .fl4_dst = ((opt && opt->srr) ?
-					  opt->faddr : ireq->rmt_addr),
-			    .fl4_src = ireq->loc_addr,
-			    .fl4_tos = RT_CONN_FLAGS(sk),
-			    .proto = sk->sk_protocol,
-			    .flags = inet_sk_flowi_flags(sk),
-			    .fl_ip_sport = inet_sk(sk)->inet_sport,
-			    .fl_ip_dport = ireq->rmt_port };
+	struct flowi fl = {
+		.flowi_oif = sk->sk_bound_dev_if,
+		.flowi_mark = sk->sk_mark,
+		.fl4_dst = ((opt && opt->srr) ?
+			    opt->faddr : ireq->rmt_addr),
+		.fl4_src = ireq->loc_addr,
+		.fl4_tos = RT_CONN_FLAGS(sk),
+		.flowi_proto = sk->sk_protocol,
+		.flowi_flags = inet_sk_flowi_flags(sk),
+		.fl_ip_sport = inet_sk(sk)->inet_sport,
+		.fl_ip_dport = ireq->rmt_port,
+	};
 	struct net *net = sock_net(sk);
 
 	security_req_classify_flow(req, &fl);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 916152dbdce4..e35ca40df03b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1474,14 +1474,16 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 	}
 
 	{
-		struct flowi fl = { .oif = arg->bound_dev_if,
-				    .fl4_dst = daddr,
-				    .fl4_src = rt->rt_spec_dst,
-				    .fl4_tos = RT_TOS(ip_hdr(skb)->tos),
-				    .fl_ip_sport = tcp_hdr(skb)->dest,
-				    .fl_ip_dport = tcp_hdr(skb)->source,
-				    .proto = sk->sk_protocol,
-				    .flags = ip_reply_arg_flowi_flags(arg) };
+		struct flowi fl = {
+			.flowi_oif = arg->bound_dev_if,
+			.fl4_dst = daddr,
+			.fl4_src = rt->rt_spec_dst,
+			.fl4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.fl_ip_sport = tcp_hdr(skb)->dest,
+			.fl_ip_dport = tcp_hdr(skb)->source,
+			.flowi_proto = sk->sk_protocol,
+			.flowi_flags = ip_reply_arg_flowi_flags(arg),
+		};
 		security_skb_classify_flow(skb, &fl);
 		rt = ip_route_output_key(sock_net(sk), &fl);
 		if (IS_ERR(rt))
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 594a3004367b..3b72b0a26d7e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -436,9 +436,9 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net *net = dev_net(dev);
 	struct mr_table *mrt;
 	struct flowi fl = {
-		.oif		= dev->ifindex,
-		.iif		= skb->skb_iif,
-		.mark		= skb->mark,
+		.flowi_oif	= dev->ifindex,
+		.flowi_iif	= skb->skb_iif,
+		.flowi_mark	= skb->mark,
 	};
 	int err;
 
@@ -1793,9 +1793,9 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct rtable *rt)
 		.fl4_dst = rt->rt_key_dst,
 		.fl4_src = rt->rt_key_src,
 		.fl4_tos = rt->rt_tos,
-		.oif = rt->rt_oif,
-		.iif = rt->rt_iif,
-		.mark = rt->rt_mark,
+		.flowi_oif = rt->rt_oif,
+		.flowi_iif = rt->rt_iif,
+		.flowi_mark = rt->rt_mark,
 	};
 	struct mr_table *mrt;
 	int err;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 67bf709180de..6f40ba511c6b 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -35,9 +35,9 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 		if (type == RTN_LOCAL)
 			fl.fl4_src = iph->saddr;
 		fl.fl4_tos = RT_TOS(iph->tos);
-		fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
-		fl.mark = skb->mark;
-		fl.flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+		fl.flowi_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+		fl.flowi_mark = skb->mark;
+		fl.flowi_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
 		rt = ip_route_output_key(net, &fl);
 		if (IS_ERR(rt))
 			return -1;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 467d570d087a..b42b7cd56c03 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -418,7 +418,7 @@ static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 		if (!iov)
 			continue;
 
-		switch (fl->proto) {
+		switch (fl->flowi_proto) {
 		case IPPROTO_ICMP:
 			/* check if one-byte field is readable or not. */
 			if (iov->iov_base && iov->iov_len < 1)
@@ -548,14 +548,14 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	}
 
 	{
-		struct flowi fl = { .oif = ipc.oif,
-				    .mark = sk->sk_mark,
+		struct flowi fl = { .flowi_oif = ipc.oif,
+				    .flowi_mark = sk->sk_mark,
 				    .fl4_dst = daddr,
 				    .fl4_src = saddr,
 				    .fl4_tos = tos,
-				    .proto = inet->hdrincl ? IPPROTO_RAW :
+				    .flowi_proto = inet->hdrincl ? IPPROTO_RAW :
 							     sk->sk_protocol,
-				    .flags = FLOWI_FLAG_CAN_SLEEP,
+				    .flowi_flags = FLOWI_FLAG_CAN_SLEEP,
 		};
 		if (!inet->hdrincl) {
 			err = raw_probe_proto_opt(&fl, msg);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9c17e32d5623..c9aa4f9effe2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1701,9 +1701,9 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 			.fl4_dst = rt->rt_key_dst,
 			.fl4_src = rt->rt_key_src,
 			.fl4_tos = rt->rt_tos,
-			.oif = rt->rt_oif,
-			.iif = rt->rt_iif,
-			.mark = rt->rt_mark,
+			.flowi_oif = rt->rt_oif,
+			.flowi_iif = rt->rt_iif,
+			.flowi_mark = rt->rt_mark,
 		};
 
 		rcu_read_lock();
@@ -1766,7 +1766,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi *oldflp,
 	/* If a peer entry exists for this destination, we must hook
 	 * it up in order to get at cached metrics.
 	 */
-	if (oldflp && (oldflp->flags & FLOWI_FLAG_PRECOW_METRICS))
+	if (oldflp && (oldflp->flowi_flags & FLOWI_FLAG_PRECOW_METRICS))
 		create = 1;
 
 	rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
@@ -2057,9 +2057,9 @@ static int ip_mkroute_input(struct sk_buff *skb,
 		return err;
 
 	/* put it into the cache */
-	hash = rt_hash(daddr, saddr, fl->iif,
+	hash = rt_hash(daddr, saddr, fl->flowi_iif,
 		       rt_genid(dev_net(rth->dst.dev)));
-	rth = rt_intern_hash(hash, rth, skb, fl->iif);
+	rth = rt_intern_hash(hash, rth, skb, fl->flowi_iif);
 	if (IS_ERR(rth))
 		return PTR_ERR(rth);
 	return 0;
@@ -2118,9 +2118,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	/*
 	 *	Now we are ready to route packet.
 	 */
-	fl.oif = 0;
-	fl.iif = dev->ifindex;
-	fl.mark = skb->mark;
+	fl.flowi_oif = 0;
+	fl.flowi_iif = dev->ifindex;
+	fl.flowi_mark = skb->mark;
 	fl.fl4_dst = daddr;
 	fl.fl4_src = saddr;
 	fl.fl4_tos = tos;
@@ -2205,8 +2205,8 @@ local_input:
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
 	rth->rt_type	= res.type;
-	hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
-	rth = rt_intern_hash(hash, rth, skb, fl.iif);
+	hash = rt_hash(daddr, saddr, fl.flowi_iif, rt_genid(net));
+	rth = rt_intern_hash(hash, rth, skb, fl.flowi_iif);
 	err = 0;
 	if (IS_ERR(rth))
 		err = PTR_ERR(rth);
@@ -2369,7 +2369,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	} else if (type == RTN_MULTICAST) {
 		flags |= RTCF_MULTICAST | RTCF_LOCAL;
 		if (!ip_check_mc_rcu(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
-				     oldflp->proto))
+				     oldflp->flowi_proto))
 			flags &= ~RTCF_LOCAL;
 		/* If multicast route do not exist use
 		 * default one, but do not gateway in this case.
@@ -2387,8 +2387,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_key_dst	= oldflp->fl4_dst;
 	rth->rt_tos	= tos;
 	rth->rt_key_src	= oldflp->fl4_src;
-	rth->rt_oif	= oldflp->oif;
-	rth->rt_mark    = oldflp->mark;
+	rth->rt_oif	= oldflp->flowi_oif;
+	rth->rt_mark    = oldflp->flowi_mark;
 	rth->rt_dst	= fl->fl4_dst;
 	rth->rt_src	= fl->fl4_src;
 	rth->rt_iif	= 0;
@@ -2452,9 +2452,9 @@ static struct rtable *ip_route_output_slow(struct net *net,
 	res.r		= NULL;
 #endif
 
-	fl.oif = oldflp->oif;
-	fl.iif = net->loopback_dev->ifindex;
-	fl.mark = oldflp->mark;
+	fl.flowi_oif = oldflp->flowi_oif;
+	fl.flowi_iif = net->loopback_dev->ifindex;
+	fl.flowi_mark = oldflp->flowi_mark;
 	fl.fl4_dst = oldflp->fl4_dst;
 	fl.fl4_src = oldflp->fl4_src;
 	fl.fl4_tos = tos & IPTOS_RT_MASK;
@@ -2477,7 +2477,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
 		      of another iface. --ANK
 		 */
 
-		if (oldflp->oif == 0 &&
+		if (oldflp->flowi_oif == 0 &&
 		    (ipv4_is_multicast(oldflp->fl4_dst) ||
 		     ipv4_is_lbcast(oldflp->fl4_dst))) {
 			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
@@ -2500,11 +2500,11 @@ static struct rtable *ip_route_output_slow(struct net *net,
 			   Luckily, this hack is good workaround.
 			 */
 
-			fl.oif = dev_out->ifindex;
+			fl.flowi_oif = dev_out->ifindex;
 			goto make_route;
 		}
 
-		if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) {
+		if (!(oldflp->flowi_flags & FLOWI_FLAG_ANYSRC)) {
 			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
 			if (!__ip_dev_find(net, oldflp->fl4_src, false))
 				goto out;
@@ -2512,8 +2512,8 @@ static struct rtable *ip_route_output_slow(struct net *net,
 	}
 
 
-	if (oldflp->oif) {
-		dev_out = dev_get_by_index_rcu(net, oldflp->oif);
+	if (oldflp->flowi_oif) {
+		dev_out = dev_get_by_index_rcu(net, oldflp->flowi_oif);
 		rth = ERR_PTR(-ENODEV);
 		if (dev_out == NULL)
 			goto out;
@@ -2545,7 +2545,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
 		if (!fl.fl4_dst)
 			fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK);
 		dev_out = net->loopback_dev;
-		fl.oif = net->loopback_dev->ifindex;
+		fl.flowi_oif = net->loopback_dev->ifindex;
 		res.type = RTN_LOCAL;
 		flags |= RTCF_LOCAL;
 		goto make_route;
@@ -2553,7 +2553,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
 
 	if (fib_lookup(net, &fl, &res)) {
 		res.fi = NULL;
-		if (oldflp->oif) {
+		if (oldflp->flowi_oif) {
 			/* Apparently, routing tables are wrong. Assume,
 			   that the destination is on link.
 
@@ -2590,25 +2590,25 @@ static struct rtable *ip_route_output_slow(struct net *net,
 				fl.fl4_src = fl.fl4_dst;
 		}
 		dev_out = net->loopback_dev;
-		fl.oif = dev_out->ifindex;
+		fl.flowi_oif = dev_out->ifindex;
 		res.fi = NULL;
 		flags |= RTCF_LOCAL;
 		goto make_route;
 	}
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res.fi->fib_nhs > 1 && fl.oif == 0)
+	if (res.fi->fib_nhs > 1 && fl.flowi_oif == 0)
 		fib_select_multipath(&res);
 	else
 #endif
-	if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
+	if (!res.prefixlen && res.type == RTN_UNICAST && !fl.flowi_oif)
 		fib_select_default(&res);
 
 	if (!fl.fl4_src)
 		fl.fl4_src = FIB_RES_PREFSRC(res);
 
 	dev_out = FIB_RES_DEV(res);
-	fl.oif = dev_out->ifindex;
+	fl.flowi_oif = dev_out->ifindex;
 
 
 make_route:
@@ -2616,9 +2616,9 @@ make_route:
 	if (!IS_ERR(rth)) {
 		unsigned int hash;
 
-		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
+		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->flowi_oif,
 			       rt_genid(dev_net(dev_out)));
-		rth = rt_intern_hash(hash, rth, NULL, oldflp->oif);
+		rth = rt_intern_hash(hash, rth, NULL, oldflp->flowi_oif);
 	}
 
 out:
@@ -2634,7 +2634,7 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
 	if (!rt_caching(net))
 		goto slow_output;
 
-	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
+	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->flowi_oif, rt_genid(net));
 
 	rcu_read_lock_bh();
 	for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
@@ -2642,8 +2642,8 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
 		if (rth->rt_key_dst == flp->fl4_dst &&
 		    rth->rt_key_src == flp->fl4_src &&
 		    rt_is_output_route(rth) &&
-		    rth->rt_oif == flp->oif &&
-		    rth->rt_mark == flp->mark &&
+		    rth->rt_oif == flp->flowi_oif &&
+		    rth->rt_mark == flp->flowi_mark &&
 		    !((rth->rt_tos ^ flp->fl4_tos) &
 			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
@@ -2741,7 +2741,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi *flp,
 	if (IS_ERR(rt))
 		return rt;
 
-	if (flp->proto) {
+	if (flp->flowi_proto) {
 		if (!flp->fl4_src)
 			flp->fl4_src = rt->rt_src;
 		if (!flp->fl4_dst)
@@ -2917,8 +2917,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 			.fl4_dst = dst,
 			.fl4_src = src,
 			.fl4_tos = rtm->rtm_tos,
-			.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
-			.mark = mark,
+			.flowi_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
+			.flowi_mark = mark,
 		};
 		rt = ip_route_output_key(net, &fl);
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 0ad6ddf638a7..98d47dc60c89 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -345,15 +345,17 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * no easy way to do this.
 	 */
 	{
-		struct flowi fl = { .mark = sk->sk_mark,
-				    .fl4_dst = ((opt && opt->srr) ?
-						opt->faddr : ireq->rmt_addr),
-				    .fl4_src = ireq->loc_addr,
-				    .fl4_tos = RT_CONN_FLAGS(sk),
-				    .proto = IPPROTO_TCP,
-				    .flags = inet_sk_flowi_flags(sk),
-				    .fl_ip_sport = th->dest,
-				    .fl_ip_dport = th->source };
+		struct flowi fl = {
+			.flowi_mark = sk->sk_mark,
+			.fl4_dst = ((opt && opt->srr) ?
+				    opt->faddr : ireq->rmt_addr),
+			.fl4_src = ireq->loc_addr,
+			.fl4_tos = RT_CONN_FLAGS(sk),
+			.flowi_proto = IPPROTO_TCP,
+			.flowi_flags = inet_sk_flowi_flags(sk),
+			.fl_ip_sport = th->dest,
+			.fl_ip_dport = th->source,
+		};
 		security_req_classify_flow(req, &fl);
 		rt = ip_route_output_key(sock_net(sk), &fl);
 		if (IS_ERR(rt)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c9a73e5b26a3..e10f62e6c07c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -908,16 +908,17 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		rt = (struct rtable *)sk_dst_check(sk, 0);
 
 	if (rt == NULL) {
-		struct flowi fl = { .oif = ipc.oif,
-				    .mark = sk->sk_mark,
-				    .fl4_dst = faddr,
-				    .fl4_src = saddr,
-				    .fl4_tos = tos,
-				    .proto = sk->sk_protocol,
-				    .flags = (inet_sk_flowi_flags(sk) |
-					      FLOWI_FLAG_CAN_SLEEP),
-				    .fl_ip_sport = inet->inet_sport,
-				    .fl_ip_dport = dport
+		struct flowi fl = {
+			.flowi_oif = ipc.oif,
+			.flowi_mark = sk->sk_mark,
+			.fl4_dst = faddr,
+			.fl4_src = saddr,
+			.fl4_tos = tos,
+			.flowi_proto = sk->sk_protocol,
+			.flowi_flags = (inet_sk_flowi_flags(sk) |
+				     FLOWI_FLAG_CAN_SLEEP),
+			.fl_ip_sport = inet->inet_sport,
+			.fl_ip_dport = dport,
 		};
 		struct net *net = sock_net(sk);
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index c70c42e7e77b..4294f121a749 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -73,9 +73,9 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	rt->rt_key_dst = fl->fl4_dst;
 	rt->rt_key_src = fl->fl4_src;
 	rt->rt_tos = fl->fl4_tos;
-	rt->rt_iif = fl->iif;
-	rt->rt_oif = fl->oif;
-	rt->rt_mark = fl->mark;
+	rt->rt_iif = fl->flowi_iif;
+	rt->rt_oif = fl->flowi_oif;
+	rt->rt_mark = fl->flowi_mark;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);
@@ -104,7 +104,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
 
 	memset(fl, 0, sizeof(struct flowi));
-	fl->mark = skb->mark;
+	fl->flowi_mark = skb->mark;
 
 	if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) {
 		switch (iph->protocol) {
@@ -173,7 +173,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			break;
 		}
 	}
-	fl->proto = iph->protocol;
+	fl->flowi_proto = iph->protocol;
 	fl->fl4_dst = reverse ? iph->saddr : iph->daddr;
 	fl->fl4_src = reverse ? iph->daddr : iph->saddr;
 	fl->fl4_tos = iph->tos;
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 983eff248988..d2314348dd2a 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -32,8 +32,8 @@ __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 	sel->family = AF_INET;
 	sel->prefixlen_d = 32;
 	sel->prefixlen_s = 32;
-	sel->proto = fl->proto;
-	sel->ifindex = fl->oif;
+	sel->proto = fl->flowi_proto;
+	sel->ifindex = fl->flowi_oif;
 }
 
 static void
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a88b2e9d25f1..35b0be0463f9 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -655,12 +655,12 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		struct flowi fl;
 
 		memset(&fl, 0, sizeof(fl));
-		fl.proto = sk->sk_protocol;
+		fl.flowi_proto = sk->sk_protocol;
 		ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
 		fl.fl6_flowlabel = np->flow_label;
-		fl.oif = sk->sk_bound_dev_if;
-		fl.mark = sk->sk_mark;
+		fl.flowi_oif = sk->sk_bound_dev_if;
+		fl.flowi_mark = sk->sk_mark;
 		fl.fl_ip_dport = inet->inet_dport;
 		fl.fl_ip_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, &fl);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index be3a781c0085..6c24b26f67ec 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -146,16 +146,16 @@ ipv4_connected:
 	 *	destination cache for it.
 	 */
 
-	fl.proto = sk->sk_protocol;
+	fl.flowi_proto = sk->sk_protocol;
 	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-	fl.oif = sk->sk_bound_dev_if;
-	fl.mark = sk->sk_mark;
+	fl.flowi_oif = sk->sk_bound_dev_if;
+	fl.flowi_mark = sk->sk_mark;
 	fl.fl_ip_dport = inet->inet_dport;
 	fl.fl_ip_sport = inet->inet_sport;
 
-	if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST))
-		fl.oif = np->mcast_oif;
+	if (!fl.flowi_oif && (addr_type&IPV6_ADDR_MULTICAST))
+		fl.flowi_oif = np->mcast_oif;
 
 	security_sk_classify_flow(sk, &fl);
 
@@ -299,7 +299,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
 	mtu_info->ip6m_addr.sin6_family = AF_INET6;
 	mtu_info->ip6m_addr.sin6_port = 0;
 	mtu_info->ip6m_addr.sin6_flowinfo = 0;
-	mtu_info->ip6m_addr.sin6_scope_id = fl->oif;
+	mtu_info->ip6m_addr.sin6_scope_id = fl->flowi_oif;
 	ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
 
 	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
@@ -629,16 +629,16 @@ int datagram_send_ctl(struct net *net,
 			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
 
 			if (src_info->ipi6_ifindex) {
-				if (fl->oif && src_info->ipi6_ifindex != fl->oif)
+				if (fl->flowi_oif && src_info->ipi6_ifindex != fl->flowi_oif)
 					return -EINVAL;
-				fl->oif = src_info->ipi6_ifindex;
+				fl->flowi_oif = src_info->ipi6_ifindex;
 			}
 
 			addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
 
 			rcu_read_lock();
-			if (fl->oif) {
-				dev = dev_get_by_index_rcu(net, fl->oif);
+			if (fl->flowi_oif) {
+				dev = dev_get_by_index_rcu(net, fl->flowi_oif);
 				if (!dev) {
 					rcu_read_unlock();
 					return -ENODEV;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 55665956b3a8..9e123e08b9b7 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -235,7 +235,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct
 					sizeof(struct icmp6hdr), skb->csum);
 		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
 						      &fl->fl6_dst,
-						      len, fl->proto,
+						      len, fl->flowi_proto,
 						      skb->csum);
 	} else {
 		__wsum tmp_csum = 0;
@@ -248,7 +248,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct
 					sizeof(struct icmp6hdr), tmp_csum);
 		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
 						      &fl->fl6_dst,
-						      len, fl->proto,
+						      len, fl->flowi_proto,
 						      tmp_csum);
 	}
 	ip6_push_pending_frames(sk);
@@ -443,11 +443,11 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	mip6_addr_swap(skb);
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = IPPROTO_ICMPV6;
+	fl.flowi_proto = IPPROTO_ICMPV6;
 	ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
 	if (saddr)
 		ipv6_addr_copy(&fl.fl6_src, saddr);
-	fl.oif = iif;
+	fl.flowi_oif = iif;
 	fl.fl_icmp_type = type;
 	fl.fl_icmp_code = code;
 	security_skb_classify_flow(skb, &fl);
@@ -465,8 +465,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	tmp_hdr.icmp6_cksum = 0;
 	tmp_hdr.icmp6_pointer = htonl(info);
 
-	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
-		fl.oif = np->mcast_oif;
+	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst))
+		fl.flowi_oif = np->mcast_oif;
 
 	dst = icmpv6_route_lookup(net, skb, sk, &fl);
 	if (IS_ERR(dst))
@@ -539,11 +539,11 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = IPPROTO_ICMPV6;
+	fl.flowi_proto = IPPROTO_ICMPV6;
 	ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr);
 	if (saddr)
 		ipv6_addr_copy(&fl.fl6_src, saddr);
-	fl.oif = skb->dev->ifindex;
+	fl.flowi_oif = skb->dev->ifindex;
 	fl.fl_icmp_type = ICMPV6_ECHO_REPLY;
 	security_skb_classify_flow(skb, &fl);
 
@@ -552,8 +552,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		return;
 	np = inet6_sk(sk);
 
-	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
-		fl.oif = np->mcast_oif;
+	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst))
+		fl.flowi_oif = np->mcast_oif;
 
 	err = ip6_dst_lookup(sk, &dst, &fl);
 	if (err)
@@ -793,10 +793,10 @@ void icmpv6_flow_init(struct sock *sk, struct flowi *fl,
 	memset(fl, 0, sizeof(*fl));
 	ipv6_addr_copy(&fl->fl6_src, saddr);
 	ipv6_addr_copy(&fl->fl6_dst, daddr);
-	fl->proto	 	= IPPROTO_ICMPV6;
+	fl->flowi_proto	 	= IPPROTO_ICMPV6;
 	fl->fl_icmp_type	= type;
 	fl->fl_icmp_code	= 0;
-	fl->oif			= oif;
+	fl->flowi_oif		= oif;
 	security_sk_classify_flow(sk, fl);
 }
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index d687e1397333..673f9bf28958 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -64,12 +64,12 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	struct flowi fl;
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = IPPROTO_TCP;
+	fl.flowi_proto = IPPROTO_TCP;
 	ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
 	final_p = fl6_update_dst(&fl, np->opt, &final);
 	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
-	fl.oif = sk->sk_bound_dev_if;
-	fl.mark = sk->sk_mark;
+	fl.flowi_oif = sk->sk_bound_dev_if;
+	fl.flowi_mark = sk->sk_mark;
 	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
 	fl.fl_ip_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
@@ -213,13 +213,13 @@ int inet6_csk_xmit(struct sk_buff *skb)
 	struct in6_addr *final_p, final;
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = sk->sk_protocol;
+	fl.flowi_proto = sk->sk_protocol;
 	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
 	fl.fl6_flowlabel = np->flow_label;
 	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
-	fl.oif = sk->sk_bound_dev_if;
-	fl.mark = sk->sk_mark;
+	fl.flowi_oif = sk->sk_bound_dev_if;
+	fl.flowi_mark = sk->sk_mark;
 	fl.fl_ip_sport = inet->inet_sport;
 	fl.fl_ip_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, &fl);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 13654686aeab..c8fa470b174b 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -358,7 +358,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
 
 		msg.msg_controllen = olen;
 		msg.msg_control = (void*)(fl->opt+1);
-		flowi.oif = 0;
+		flowi.flowi_oif = 0;
 
 		err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk,
 					&junk, &junk);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index adaffaf84555..3d0f2ac868a7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -182,7 +182,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	struct in6_addr *first_hop = &fl->fl6_dst;
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr;
-	u8  proto = fl->proto;
+	u8  proto = fl->flowi_proto;
 	int seg_len = skb->len;
 	int hlimit = -1;
 	int tclass = 0;
@@ -908,7 +908,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 #ifdef CONFIG_IPV6_SUBTREES
 	    ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) ||
 #endif
-	    (fl->oif && fl->oif != dst->dev->ifindex)) {
+	    (fl->flowi_oif && fl->flowi_oif != dst->dev->ifindex)) {
 		dst_release(dst);
 		dst = NULL;
 	}
@@ -1026,7 +1026,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
 	if (can_sleep)
-		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
+		fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
 }
@@ -1062,7 +1062,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
 	if (final_dst)
 		ipv6_addr_copy(&fl->fl6_dst, final_dst);
 	if (can_sleep)
-		fl->flags |= FLOWI_FLAG_CAN_SLEEP;
+		fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
 }
@@ -1517,7 +1517,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	struct ipv6_txoptions *opt = np->cork.opt;
 	struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
 	struct flowi *fl = &inet->cork.fl;
-	unsigned char proto = fl->proto;
+	unsigned char proto = fl->flowi_proto;
 	int err = 0;
 
 	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f199b8486120..c3fc824c24d9 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -963,7 +963,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 
 	skb->transport_header = skb->network_header;
 
-	proto = fl->proto;
+	proto = fl->flowi_proto;
 	if (encap_limit >= 0) {
 		init_tel_txopt(&opt, encap_limit);
 		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
@@ -1020,7 +1020,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl, &t->fl, sizeof (fl));
-	fl.proto = IPPROTO_IPIP;
+	fl.flowi_proto = IPPROTO_IPIP;
 
 	dsfield = ipv4_get_dsfield(iph);
 
@@ -1070,7 +1070,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl, &t->fl, sizeof (fl));
-	fl.proto = IPPROTO_IPV6;
+	fl.flowi_proto = IPPROTO_IPV6;
 
 	dsfield = ipv6_get_dsfield(ipv6h);
 	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
@@ -1149,7 +1149,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 	/* Set up flowi template */
 	ipv6_addr_copy(&fl->fl6_src, &p->laddr);
 	ipv6_addr_copy(&fl->fl6_dst, &p->raddr);
-	fl->oif = p->link;
+	fl->flowi_oif = p->link;
 	fl->fl6_flowlabel = 0;
 
 	if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 618f67ccda31..61a8be3ac4e4 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -618,8 +618,8 @@ static int pim6_rcv(struct sk_buff *skb)
 	struct net *net = dev_net(skb->dev);
 	struct mr6_table *mrt;
 	struct flowi fl = {
-		.iif	= skb->dev->ifindex,
-		.mark	= skb->mark,
+		.flowi_iif	= skb->dev->ifindex,
+		.flowi_mark = skb->mark,
 	};
 	int reg_vif_num;
 
@@ -688,9 +688,9 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	struct net *net = dev_net(dev);
 	struct mr6_table *mrt;
 	struct flowi fl = {
-		.oif		= dev->ifindex,
-		.iif		= skb->skb_iif,
-		.mark		= skb->mark,
+		.flowi_oif		= dev->ifindex,
+		.flowi_iif		= skb->skb_iif,
+		.flowi_mark	= skb->mark,
 	};
 	int err;
 
@@ -1548,9 +1548,9 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
 {
 	struct mr6_table *mrt;
 	struct flowi fl = {
-		.iif	= skb->skb_iif,
-		.oif	= skb->dev->ifindex,
-		.mark	= skb->mark,
+		.flowi_iif	= skb->skb_iif,
+		.flowi_oif	= skb->dev->ifindex,
+		.flowi_mark= skb->mark,
 	};
 
 	if (ip6mr_fib_lookup(net, &fl, &mrt) < 0)
@@ -1916,7 +1916,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
 	ipv6h = ipv6_hdr(skb);
 
 	fl = (struct flowi) {
-		.oif = vif->link,
+		.flowi_oif = vif->link,
 		.fl6_dst = ipv6h->daddr,
 	};
 
@@ -2044,8 +2044,8 @@ int ip6_mr_input(struct sk_buff *skb)
 	struct net *net = dev_net(skb->dev);
 	struct mr6_table *mrt;
 	struct flowi fl = {
-		.iif	= skb->dev->ifindex,
-		.mark	= skb->mark,
+		.flowi_iif	= skb->dev->ifindex,
+		.flowi_mark= skb->mark,
 	};
 	int err;
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d1770e061c08..1448c507fdff 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -448,8 +448,8 @@ sticky_done:
 		int junk;
 
 		fl.fl6_flowlabel = 0;
-		fl.oif = sk->sk_bound_dev_if;
-		fl.mark = sk->sk_mark;
+		fl.flowi_oif = sk->sk_bound_dev_if;
+		fl.flowi_mark = sk->sk_mark;
 
 		if (optlen == 0)
 			goto update;
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index f3e3ca938a54..e2f852cd0f4e 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -214,7 +214,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	struct timeval stamp;
 	int err = 0;
 
-	if (unlikely(fl->proto == IPPROTO_MH &&
+	if (unlikely(fl->flowi_proto == IPPROTO_MH &&
 		     fl->fl_mh_type <= IP6_MH_TYPE_MAX))
 		goto out;
 
@@ -240,14 +240,14 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	       sizeof(sel.saddr));
 	sel.prefixlen_s = 128;
 	sel.family = AF_INET6;
-	sel.proto = fl->proto;
+	sel.proto = fl->flowi_proto;
 	sel.dport = xfrm_flowi_dport(fl);
 	if (sel.dport)
 		sel.dport_mask = htons(~0);
 	sel.sport = xfrm_flowi_sport(fl);
 	if (sel.sport)
 		sel.sport_mask = htons(~0);
-	sel.ifindex = fl->oif;
+	sel.ifindex = fl->flowi_oif;
 
 	err = km_report(net, IPPROTO_DSTOPTS, &sel,
 			(hao ? (xfrm_address_t *)&hao->addr : NULL));
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 8d74116ae27d..d282c62bc6f4 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -16,8 +16,8 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct dst_entry *dst;
 	struct flowi fl = {
-		.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
-		.mark = skb->mark,
+		.flowi_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
+		.flowi_mark = skb->mark,
 		.fl6_dst = iph->daddr,
 		.fl6_src = iph->saddr,
 	};
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 91f6a61cefab..fd3938803eb3 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -90,7 +90,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	}
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = IPPROTO_TCP;
+	fl.flowi_proto = IPPROTO_TCP;
 	ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr);
 	ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr);
 	fl.fl_ip_sport = otcph.dest;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index dc29b07caf42..323ad44ff775 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -588,9 +588,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
 
 	csum = csum_ipv6_magic(&fl->fl6_src,
 				   &fl->fl6_dst,
-				   total_len, fl->proto, tmp_csum);
+				   total_len, fl->flowi_proto, tmp_csum);
 
-	if (csum == 0 && fl->proto == IPPROTO_UDP)
+	if (csum == 0 && fl->flowi_proto == IPPROTO_UDP)
 		csum = CSUM_MANGLED_0;
 
 	if (skb_store_bits(skb, offset, &csum, 2))
@@ -679,7 +679,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 		if (!iov)
 			continue;
 
-		switch (fl->proto) {
+		switch (fl->flowi_proto) {
 		case IPPROTO_ICMPV6:
 			/* check if one-byte field is readable or not. */
 			if (iov->iov_base && iov->iov_len < 1)
@@ -758,7 +758,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	 */
 	memset(&fl, 0, sizeof(fl));
 
-	fl.mark = sk->sk_mark;
+	fl.flowi_mark = sk->sk_mark;
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
@@ -800,7 +800,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
 		    ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
-			fl.oif = sin6->sin6_scope_id;
+			fl.flowi_oif = sin6->sin6_scope_id;
 	} else {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
@@ -810,8 +810,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		fl.fl6_flowlabel = np->flow_label;
 	}
 
-	if (fl.oif == 0)
-		fl.oif = sk->sk_bound_dev_if;
+	if (fl.flowi_oif == 0)
+		fl.flowi_oif = sk->sk_bound_dev_if;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
@@ -838,7 +838,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
 
-	fl.proto = proto;
+	fl.flowi_proto = proto;
 	err = rawv6_probe_proto_opt(&fl, msg);
 	if (err)
 		goto out;
@@ -852,8 +852,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 	final_p = fl6_update_dst(&fl, opt, &final);
 
-	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
-		fl.oif = np->mcast_oif;
+	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst))
+		fl.flowi_oif = np->mcast_oif;
 	security_sk_classify_flow(sk, &fl);
 
 	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 001276055a6b..c3b20d63921f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -608,7 +608,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
 restart:
 	rt = fn->leaf;
-	rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags);
+	rt = rt6_device_match(net, rt, &fl->fl6_src, fl->flowi_oif, flags);
 	BACKTRACK(net, &fl->fl6_src);
 out:
 	dst_use(&rt->dst, jiffies);
@@ -621,7 +621,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif, int strict)
 {
 	struct flowi fl = {
-		.oif = oif,
+		.flowi_oif = oif,
 		.fl6_dst = *daddr,
 	};
 	struct dst_entry *dst;
@@ -825,7 +825,7 @@ out2:
 static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
 					    struct flowi *fl, int flags)
 {
-	return ip6_pol_route(net, table, fl->iif, fl, flags);
+	return ip6_pol_route(net, table, fl->flowi_iif, fl, flags);
 }
 
 void ip6_route_input(struct sk_buff *skb)
@@ -834,12 +834,12 @@ void ip6_route_input(struct sk_buff *skb)
 	struct net *net = dev_net(skb->dev);
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct flowi fl = {
-		.iif = skb->dev->ifindex,
+		.flowi_iif = skb->dev->ifindex,
 		.fl6_dst = iph->daddr,
 		.fl6_src = iph->saddr,
 		.fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
-		.mark = skb->mark,
-		.proto = iph->nexthdr,
+		.flowi_mark = skb->mark,
+		.flowi_proto = iph->nexthdr,
 	};
 
 	if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
@@ -851,7 +851,7 @@ void ip6_route_input(struct sk_buff *skb)
 static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
 					     struct flowi *fl, int flags)
 {
-	return ip6_pol_route(net, table, fl->oif, fl, flags);
+	return ip6_pol_route(net, table, fl->flowi_oif, fl, flags);
 }
 
 struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
@@ -1484,7 +1484,7 @@ restart:
 			continue;
 		if (!(rt->rt6i_flags & RTF_GATEWAY))
 			continue;
-		if (fl->oif != rt->rt6i_dev->ifindex)
+		if (fl->flowi_oif != rt->rt6i_dev->ifindex)
 			continue;
 		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
 			continue;
@@ -1511,7 +1511,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
 	struct net *net = dev_net(dev);
 	struct ip6rd_flowi rdfl = {
 		.fl = {
-			.oif = dev->ifindex,
+			.flowi_oif = dev->ifindex,
 			.fl6_dst = *dest,
 			.fl6_src = *src,
 		},
@@ -2413,7 +2413,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 		iif = nla_get_u32(tb[RTA_IIF]);
 
 	if (tb[RTA_OIF])
-		fl.oif = nla_get_u32(tb[RTA_OIF]);
+		fl.flowi_oif = nla_get_u32(tb[RTA_OIF]);
 
 	if (iif) {
 		struct net_device *dev;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 0b4cf350631b..ca5255c08371 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -234,12 +234,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		struct in6_addr *final_p, final;
 		struct flowi fl;
 		memset(&fl, 0, sizeof(fl));
-		fl.proto = IPPROTO_TCP;
+		fl.flowi_proto = IPPROTO_TCP;
 		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
 		final_p = fl6_update_dst(&fl, np->opt, &final);
 		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
-		fl.oif = sk->sk_bound_dev_if;
-		fl.mark = sk->sk_mark;
+		fl.flowi_oif = sk->sk_bound_dev_if;
+		fl.flowi_mark = sk->sk_mark;
 		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
 		fl.fl_ip_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, &fl);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e59a31c48baf..a3d1229b4004 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -242,12 +242,12 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (!ipv6_addr_any(&np->rcv_saddr))
 		saddr = &np->rcv_saddr;
 
-	fl.proto = IPPROTO_TCP;
+	fl.flowi_proto = IPPROTO_TCP;
 	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 	ipv6_addr_copy(&fl.fl6_src,
 		       (saddr ? saddr : &np->saddr));
-	fl.oif = sk->sk_bound_dev_if;
-	fl.mark = sk->sk_mark;
+	fl.flowi_oif = sk->sk_bound_dev_if;
+	fl.flowi_mark = sk->sk_mark;
 	fl.fl_ip_dport = usin->sin6_port;
 	fl.fl_ip_sport = inet->inet_sport;
 
@@ -396,11 +396,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			   for now.
 			 */
 			memset(&fl, 0, sizeof(fl));
-			fl.proto = IPPROTO_TCP;
+			fl.flowi_proto = IPPROTO_TCP;
 			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-			fl.oif = sk->sk_bound_dev_if;
-			fl.mark = sk->sk_mark;
+			fl.flowi_oif = sk->sk_bound_dev_if;
+			fl.flowi_mark = sk->sk_mark;
 			fl.fl_ip_dport = inet->inet_dport;
 			fl.fl_ip_sport = inet->inet_sport;
 			security_skb_classify_flow(skb, &fl);
@@ -487,12 +487,12 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	int err;
 
 	memset(&fl, 0, sizeof(fl));
-	fl.proto = IPPROTO_TCP;
+	fl.flowi_proto = IPPROTO_TCP;
 	ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
 	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
 	fl.fl6_flowlabel = 0;
-	fl.oif = treq->iif;
-	fl.mark = sk->sk_mark;
+	fl.flowi_oif = treq->iif;
+	fl.flowi_mark = sk->sk_mark;
 	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
 	fl.fl_ip_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
@@ -1055,8 +1055,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	__tcp_v6_send_check(buff, &fl.fl6_src, &fl.fl6_dst);
 
-	fl.proto = IPPROTO_TCP;
-	fl.oif = inet6_iif(skb);
+	fl.flowi_proto = IPPROTO_TCP;
+	fl.flowi_oif = inet6_iif(skb);
 	fl.fl_ip_dport = t1->dest;
 	fl.fl_ip_sport = t1->source;
 	security_skb_classify_flow(skb, &fl);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d86d7f67a597..91f8047463ec 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -915,7 +915,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 
 	/* add protocol-dependent pseudo-header */
 	uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst,
-				    up->len, fl->proto, csum   );
+				    up->len, fl->flowi_proto, csum);
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
@@ -1060,7 +1060,7 @@ do_udp_sendmsg:
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
 		    ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
-			fl.oif = sin6->sin6_scope_id;
+			fl.flowi_oif = sin6->sin6_scope_id;
 	} else {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
@@ -1071,13 +1071,13 @@ do_udp_sendmsg:
 		connected = 1;
 	}
 
-	if (!fl.oif)
-		fl.oif = sk->sk_bound_dev_if;
+	if (!fl.flowi_oif)
+		fl.flowi_oif = sk->sk_bound_dev_if;
 
-	if (!fl.oif)
-		fl.oif = np->sticky_pktinfo.ipi6_ifindex;
+	if (!fl.flowi_oif)
+		fl.flowi_oif = np->sticky_pktinfo.ipi6_ifindex;
 
-	fl.mark = sk->sk_mark;
+	fl.flowi_mark = sk->sk_mark;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
@@ -1105,7 +1105,7 @@ do_udp_sendmsg:
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
 
-	fl.proto = sk->sk_protocol;
+	fl.flowi_proto = sk->sk_protocol;
 	if (!ipv6_addr_any(daddr))
 		ipv6_addr_copy(&fl.fl6_dst, daddr);
 	else
@@ -1118,8 +1118,8 @@ do_udp_sendmsg:
 	if (final_p)
 		connected = 0;
 
-	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) {
-		fl.oif = np->mcast_oif;
+	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst)) {
+		fl.flowi_oif = np->mcast_oif;
 		connected = 0;
 	}
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 48ce496802fd..d62496c1a6f9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -128,7 +128,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 	u8 nexthdr = nh[IP6CB(skb)->nhoff];
 
 	memset(fl, 0, sizeof(struct flowi));
-	fl->mark = skb->mark;
+	fl->flowi_mark = skb->mark;
 
 	ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr);
 	ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr);
@@ -161,7 +161,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 				fl->fl_ip_sport = ports[!!reverse];
 				fl->fl_ip_dport = ports[!reverse];
 			}
-			fl->proto = nexthdr;
+			fl->flowi_proto = nexthdr;
 			return;
 
 		case IPPROTO_ICMPV6:
@@ -171,7 +171,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 				fl->fl_icmp_type = icmp[0];
 				fl->fl_icmp_code = icmp[1];
 			}
-			fl->proto = nexthdr;
+			fl->flowi_proto = nexthdr;
 			return;
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
@@ -182,7 +182,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 
 				fl->fl_mh_type = mh->ip6mh_type;
 			}
-			fl->proto = nexthdr;
+			fl->flowi_proto = nexthdr;
 			return;
 #endif
 
@@ -192,7 +192,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 		case IPPROTO_COMP:
 		default:
 			fl->fl_ipsec_spi = 0;
-			fl->proto = nexthdr;
+			fl->flowi_proto = nexthdr;
 			return;
 		}
 	}
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index a02598e0079a..805d0e14c331 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -33,8 +33,8 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 	sel->family = AF_INET6;
 	sel->prefixlen_d = 128;
 	sel->prefixlen_s = 128;
-	sel->proto = fl->proto;
-	sel->ifindex = fl->oif;
+	sel->proto = fl->flowi_proto;
+	sel->ifindex = fl->flowi_oif;
 }
 
 static void
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d69ec26b6bd4..d07a32aa07b6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -76,7 +76,7 @@ static int __ip_vs_addr_is_local_v6(struct net *net,
 {
 	struct rt6_info *rt;
 	struct flowi fl = {
-		.oif = 0,
+		.flowi_oif = 0,
 		.fl6_dst = *addr,
 		.fl6_src = { .s6_addr32 = {0, 0, 0, 0} },
 	};
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index faf381d9da7c..cc8071f68903 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -169,7 +169,7 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 			.fl4_dst = iph->daddr,
 			.fl4_src = iph->saddr,
 			.fl4_tos = RT_TOS(iph->tos),
-			.mark = skb->mark,
+			.flowi_mark = skb->mark,
 		};
 
 		rt = ip_route_output_key(net, &fl);
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 624725b5286f..cb14ae2de15d 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -68,7 +68,7 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	if (info->priv) {
 		if (info->priv->oif == -1)
 			return false;
-		fl.oif = info->priv->oif;
+		fl.flowi_oif = info->priv->oif;
 	}
 	fl.fl4_dst = info->gw.ip;
 	fl.fl4_tos = RT_TOS(iph->tos);
@@ -149,7 +149,7 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	if (info->priv) {
 		if (info->priv->oif == -1)
 			return false;
-		fl.oif = info->priv->oif;
+		fl.flowi_oif = info->priv->oif;
 	}
 	fl.fl6_dst = info->gw.in6;
 	fl.fl6_flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 95e0c8eda1a0..831627156884 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -205,7 +205,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 
 	memset(&fl, 0, sizeof(fl));
 
-	fl.proto = sk->sk_protocol;
+	fl.flowi_proto = sk->sk_protocol;
 
 	/* Fill in the dest address from the route entry passed with the skb
 	 * and the source address from the transport.
@@ -216,9 +216,9 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	fl.fl6_flowlabel = np->flow_label;
 	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
 	if (ipv6_addr_type(&fl.fl6_src) & IPV6_ADDR_LINKLOCAL)
-		fl.oif = transport->saddr.v6.sin6_scope_id;
+		fl.flowi_oif = transport->saddr.v6.sin6_scope_id;
 	else
-		fl.oif = sk->sk_bound_dev_if;
+		fl.flowi_oif = sk->sk_bound_dev_if;
 
 	if (np->opt && np->opt->srcrt) {
 		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
@@ -250,7 +250,7 @@ static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc,
 	memset(&fl, 0, sizeof(fl));
 	ipv6_addr_copy(&fl.fl6_dst, &daddr->v6.sin6_addr);
 	if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
-		fl.oif = daddr->v6.sin6_scope_id;
+		fl.flowi_oif = daddr->v6.sin6_scope_id;
 
 
 	SCTP_DEBUG_PRINTK("%s: DST=%pI6 ", __func__, &fl.fl6_dst);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 4e55e6c49ec9..832665ac2100 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -477,10 +477,10 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 	memset(&fl, 0x0, sizeof(struct flowi));
 	fl.fl4_dst  = daddr->v4.sin_addr.s_addr;
 	fl.fl_ip_dport = daddr->v4.sin_port;
-	fl.proto = IPPROTO_SCTP;
+	fl.flowi_proto = IPPROTO_SCTP;
 	if (asoc) {
 		fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk);
-		fl.oif = asoc->base.sk->sk_bound_dev_if;
+		fl.flowi_oif = asoc->base.sk->sk_bound_dev_if;
 		fl.fl_ip_sport = htons(asoc->base.bind_addr.port);
 	}
 	if (saddr) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 9e4aacda26cc..dd6243f9d933 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -63,8 +63,8 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
 		!((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) &&
 		!((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) &&
-		(fl->proto == sel->proto || !sel->proto) &&
-		(fl->oif == sel->ifindex || !sel->ifindex);
+		(fl->flowi_proto == sel->proto || !sel->proto) &&
+		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
 }
 
 static inline int
@@ -74,8 +74,8 @@ __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
 		!((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) &&
 		!((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) &&
-		(fl->proto == sel->proto || !sel->proto) &&
-		(fl->oif == sel->ifindex || !sel->ifindex);
+		(fl->flowi_proto == sel->proto || !sel->proto) &&
+		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
 }
 
 int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
@@ -876,13 +876,13 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 	int match, ret = -ESRCH;
 
 	if (pol->family != family ||
-	    (fl->mark & pol->mark.m) != pol->mark.v ||
+	    (fl->flowi_mark & pol->mark.m) != pol->mark.v ||
 	    pol->type != type)
 		return ret;
 
 	match = xfrm_selector_match(sel, fl, family);
 	if (match)
-		ret = security_xfrm_policy_lookup(pol->security, fl->secid,
+		ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid,
 						  dir);
 
 	return ret;
@@ -1012,7 +1012,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
 				goto out;
 			}
 			err = security_xfrm_policy_lookup(pol->security,
-						      fl->secid,
+						      fl->flowi_secid,
 						      policy_to_flow_dir(dir));
 			if (!err)
 				xfrm_pol_hold(pol);
@@ -1848,7 +1848,7 @@ restart:
 
 			return make_blackhole(net, family, dst_orig);
 		}
-		if (fl->flags & FLOWI_FLAG_CAN_SLEEP) {
+		if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) {
 			DECLARE_WAITQUEUE(wait, current);
 
 			add_wait_queue(&net->xfrm.km_waitq, &wait);
@@ -1990,7 +1990,7 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 		return -EAFNOSUPPORT;
 
 	afinfo->decode_session(skb, fl, reverse);
-	err = security_xfrm_decode_session(skb, &fl->secid);
+	err = security_xfrm_decode_session(skb, &fl->flowi_secid);
 	xfrm_policy_put_afinfo(afinfo);
 	return err;
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 81221d9cbf06..cd6be49f2ae8 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -859,7 +859,7 @@ found:
 		xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
 		memcpy(&x->mark, &pol->mark, sizeof(x->mark));
 
-		error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid);
+		error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid);
 		if (error) {
 			x->km.state = XFRM_STATE_DEAD;
 			to_put = x;
diff --git a/security/security.c b/security/security.c
index 8ef1f7dff277..bae843c8a13e 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1100,7 +1100,7 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk)
 
 void security_sk_classify_flow(struct sock *sk, struct flowi *fl)
 {
-	security_ops->sk_getsecid(sk, &fl->secid);
+	security_ops->sk_getsecid(sk, &fl->flowi_secid);
 }
 EXPORT_SYMBOL(security_sk_classify_flow);
 
@@ -1246,7 +1246,7 @@ int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid)
 
 void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl)
 {
-	int rc = security_ops->xfrm_decode_session(skb, &fl->secid, 0);
+	int rc = security_ops->xfrm_decode_session(skb, &fl->flowi_secid, 0);
 
 	BUG_ON(rc);
 }
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index cef42f5d69a2..c178494850a9 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4306,7 +4306,7 @@ static void selinux_secmark_refcount_dec(void)
 static void selinux_req_classify_flow(const struct request_sock *req,
 				      struct flowi *fl)
 {
-	fl->secid = req->secid;
+	fl->flowi_secid = req->secid;
 }
 
 static int selinux_tun_dev_create(void)
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index c43ab542246c..510ec2cf6c23 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -135,10 +135,10 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *
 
 	state_sid = x->security->ctx_sid;
 
-	if (fl->secid != state_sid)
+	if (fl->flowi_secid != state_sid)
 		return 0;
 
-	rc = avc_has_perm(fl->secid, state_sid, SECCLASS_ASSOCIATION,
+	rc = avc_has_perm(fl->flowi_secid, state_sid, SECCLASS_ASSOCIATION,
 			  ASSOCIATION__SENDTO,
 			  NULL)? 0:1;
 
-- 
cgit v1.2.3


From 806566cc78390b1565ded91712cd28619cea5f57 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 11 Mar 2011 18:22:00 -0500
Subject: net: Create struct flowi_common

Pull out the AF independent members of struct flowi into a
new struct flowi_common

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 8c4dbd078490..775968716b47 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -10,18 +10,30 @@
 #include <linux/in6.h>
 #include <asm/atomic.h>
 
-struct flowi {
-	int	flowi_oif;
-	int	flowi_iif;
-	__u32	flowi_mark;
-	__u8	flowi_tos;
-	__u8	flowi_scope;
-	__u8	flowi_proto;
-	__u8	flowi_flags;
+struct flowi_common {
+	int	flowic_oif;
+	int	flowic_iif;
+	__u32	flowic_mark;
+	__u8	flowic_tos;
+	__u8	flowic_scope;
+	__u8	flowic_proto;
+	__u8	flowic_flags;
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_PRECOW_METRICS	0x02
 #define FLOWI_FLAG_CAN_SLEEP		0x04
-	__u32	flowi_secid;
+	__u32	flowic_secid;
+};
+
+struct flowi {
+	struct flowi_common	__fl_common;
+#define flowi_oif		__fl_common.flowic_oif
+#define flowi_iif		__fl_common.flowic_iif
+#define flowi_mark		__fl_common.flowic_mark
+#define flowi_tos		__fl_common.flowic_tos
+#define flowi_scope		__fl_common.flowic_scope
+#define flowi_proto		__fl_common.flowic_proto
+#define flowi_flags		__fl_common.flowic_flags
+#define flowi_secid		__fl_common.flowic_secid
 
 	union {
 		struct {
-- 
cgit v1.2.3


From 08704bcbf022786532b5f188935ab6619906049f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 11 Mar 2011 18:36:42 -0500
Subject: net: Create union flowi_uli

This will be used when we have seperate flowi types.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 48 +++++++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 775968716b47..541ac13f245a 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -24,6 +24,30 @@ struct flowi_common {
 	__u32	flowic_secid;
 };
 
+union flowi_uli {
+	struct {
+		__be16	sport;
+		__be16	dport;
+	} ports;
+
+	struct {
+		__u8	type;
+		__u8	code;
+	} icmpt;
+
+	struct {
+		__le16	sport;
+		__le16	dport;
+	} dnports;
+
+	__be32		spi;
+	__be32		gre_key;
+
+	struct {
+		__u8	type;
+	} mht;
+};
+
 struct flowi {
 	struct flowi_common	__fl_common;
 #define flowi_oif		__fl_common.flowic_oif
@@ -64,29 +88,7 @@ struct flowi {
 #define fl4_tos		flowi_tos
 #define fl4_scope	flowi_scope
 
-	union {
-		struct {
-			__be16	sport;
-			__be16	dport;
-		} ports;
-
-		struct {
-			__u8	type;
-			__u8	code;
-		} icmpt;
-
-		struct {
-			__le16	sport;
-			__le16	dport;
-		} dnports;
-
-		__be32		spi;
-		__be32		gre_key;
-
-		struct {
-			__u8	type;
-		} mht;
-	} uli_u;
+	union flowi_uli uli_u;
 #define fl_ip_sport	uli_u.ports.sport
 #define fl_ip_dport	uli_u.ports.dport
 #define fl_icmp_type	uli_u.icmpt.type
-- 
cgit v1.2.3


From 6281dcc94a96bd73017b2baa8fa83925405109ef Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 00:43:55 -0500
Subject: net: Make flowi ports AF dependent.

Create two sets of port member accessors, one set prefixed by fl4_*
and the other prefixed by fl6_*

This will let us to create AF optimal flow instances.

It will work because every context in which we access the ports,
we have to be fully aware of which AF the flowi is anyways.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h                     | 21 +++++++++++------
 include/net/route.h                    | 43 ++++++++++++++++++----------------
 include/net/xfrm.h                     | 18 +++++++-------
 net/dccp/ipv4.c                        |  4 ++--
 net/dccp/ipv6.c                        | 20 ++++++++--------
 net/ipv4/icmp.c                        |  4 ++--
 net/ipv4/inet_connection_sock.c        |  4 ++--
 net/ipv4/ip_output.c                   |  4 ++--
 net/ipv4/netfilter/nf_nat_standalone.c |  4 ++--
 net/ipv4/raw.c                         |  4 ++--
 net/ipv4/syncookies.c                  |  4 ++--
 net/ipv4/udp.c                         | 10 ++++----
 net/ipv4/xfrm4_policy.c                | 18 +++++++-------
 net/ipv4/xfrm4_state.c                 |  4 ++--
 net/ipv6/af_inet6.c                    |  4 ++--
 net/ipv6/datagram.c                    |  6 ++---
 net/ipv6/icmp.c                        | 10 ++++----
 net/ipv6/inet6_connection_sock.c       |  8 +++----
 net/ipv6/mip6.c                        |  6 ++---
 net/ipv6/netfilter/ip6t_REJECT.c       |  4 ++--
 net/ipv6/raw.c                         |  6 ++---
 net/ipv6/syncookies.c                  |  4 ++--
 net/ipv6/tcp_ipv6.c                    | 16 ++++++-------
 net/ipv6/udp.c                         | 10 ++++----
 net/ipv6/xfrm6_policy.c                | 12 +++++-----
 net/ipv6/xfrm6_state.c                 |  4 ++--
 net/sctp/protocol.c                    |  8 +++----
 net/xfrm/xfrm_policy.c                 |  8 +++----
 28 files changed, 139 insertions(+), 129 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 541ac13f245a..f19f41d7dafc 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -89,13 +89,20 @@ struct flowi {
 #define fl4_scope	flowi_scope
 
 	union flowi_uli uli_u;
-#define fl_ip_sport	uli_u.ports.sport
-#define fl_ip_dport	uli_u.ports.dport
-#define fl_icmp_type	uli_u.icmpt.type
-#define fl_icmp_code	uli_u.icmpt.code
-#define fl_ipsec_spi	uli_u.spi
-#define fl_mh_type	uli_u.mht.type
-#define fl_gre_key	uli_u.gre_key
+#define fl4_sport	uli_u.ports.sport
+#define fl4_dport	uli_u.ports.dport
+#define fl4_icmp_type	uli_u.icmpt.type
+#define fl4_icmp_code	uli_u.icmpt.code
+#define fl4_ipsec_spi	uli_u.spi
+#define fl4_mh_type	uli_u.mht.type
+#define fl4_gre_key	uli_u.gre_key
+#define fl6_sport	uli_u.ports.sport
+#define fl6_dport	uli_u.ports.dport
+#define fl6_icmp_type	uli_u.icmpt.type
+#define fl6_icmp_code	uli_u.icmpt.code
+#define fl6_ipsec_spi	uli_u.spi
+#define fl6_mh_type	uli_u.mht.type
+#define fl6_gre_key	uli_u.gre_key
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 #define FLOW_DIR_IN	0
diff --git a/include/net/route.h b/include/net/route.h
index 3d814f84abd0..4c207f9fe0cb 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -157,8 +157,8 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct sock
 		.fl4_src = saddr,
 		.fl4_tos = tos,
 		.flowi_proto = proto,
-		.fl_ip_dport = dport,
-		.fl_ip_sport = sport,
+		.fl4_dport = dport,
+		.fl4_sport = sport,
 	};
 	if (sk)
 		security_sk_classify_flow(sk, &fl);
@@ -175,7 +175,7 @@ static inline struct rtable *ip_route_output_gre(struct net *net,
 		.fl4_src = saddr,
 		.fl4_tos = tos,
 		.flowi_proto = IPPROTO_GRE,
-		.fl_gre_key = gre_key,
+		.fl4_gre_key = gre_key,
 	};
 	return ip_route_output_key(net, &fl);
 }
@@ -228,14 +228,16 @@ static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos,
 					      __be16 sport, __be16 dport,
 					      struct sock *sk, bool can_sleep)
 {
-	struct flowi fl = { .flowi_oif = oif,
-			    .flowi_mark = sk->sk_mark,
-			    .fl4_dst = dst,
-			    .fl4_src = src,
-			    .fl4_tos = tos,
-			    .flowi_proto = protocol,
-			    .fl_ip_sport = sport,
-			    .fl_ip_dport = dport };
+	struct flowi fl = {
+		.flowi_oif = oif,
+		.flowi_mark = sk->sk_mark,
+		.fl4_dst = dst,
+		.fl4_src = src,
+		.fl4_tos = tos,
+		.flowi_proto = protocol,
+		.fl4_sport = sport,
+		.fl4_dport = dport,
+	};
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
 
@@ -264,15 +266,16 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 					       __be16 dport, struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
-		struct flowi fl = { .flowi_oif = rt->rt_oif,
-				    .flowi_mark = rt->rt_mark,
-				    .fl4_dst = rt->rt_key_dst,
-				    .fl4_src = rt->rt_key_src,
-				    .fl4_tos = rt->rt_tos,
-				    .flowi_proto = protocol,
-				    .fl_ip_sport = sport,
-				    .fl_ip_dport = dport };
-
+		struct flowi fl = {
+			.flowi_oif = rt->rt_oif,
+			.flowi_mark = rt->rt_mark,
+			.fl4_dst = rt->rt_key_dst,
+			.fl4_src = rt->rt_key_src,
+			.fl4_tos = rt->rt_tos,
+			.flowi_proto = protocol,
+			.fl4_sport = sport,
+			.fl4_dport = dport
+		};
 		if (inet_sk(sk)->transparent)
 			fl.flowi_flags |= FLOWI_FLAG_ANYSRC;
 		if (protocol == IPPROTO_TCP)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index d5a12d10a0d4..aa860add570b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -800,7 +800,7 @@ static inline bool addr_match(const void *token1, const void *token2,
 }
 
 static __inline__
-__be16 xfrm_flowi_sport(const struct flowi *fl)
+__be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli)
 {
 	__be16 port;
 	switch(fl->flowi_proto) {
@@ -808,17 +808,17 @@ __be16 xfrm_flowi_sport(const struct flowi *fl)
 	case IPPROTO_UDP:
 	case IPPROTO_UDPLITE:
 	case IPPROTO_SCTP:
-		port = fl->fl_ip_sport;
+		port = uli->ports.sport;
 		break;
 	case IPPROTO_ICMP:
 	case IPPROTO_ICMPV6:
-		port = htons(fl->fl_icmp_type);
+		port = htons(uli->icmpt.type);
 		break;
 	case IPPROTO_MH:
-		port = htons(fl->fl_mh_type);
+		port = htons(uli->mht.type);
 		break;
 	case IPPROTO_GRE:
-		port = htons(ntohl(fl->fl_gre_key) >> 16);
+		port = htons(ntohl(uli->gre_key) >> 16);
 		break;
 	default:
 		port = 0;	/*XXX*/
@@ -827,7 +827,7 @@ __be16 xfrm_flowi_sport(const struct flowi *fl)
 }
 
 static __inline__
-__be16 xfrm_flowi_dport(const struct flowi *fl)
+__be16 xfrm_flowi_dport(const struct flowi *fl, const union flowi_uli *uli)
 {
 	__be16 port;
 	switch(fl->flowi_proto) {
@@ -835,14 +835,14 @@ __be16 xfrm_flowi_dport(const struct flowi *fl)
 	case IPPROTO_UDP:
 	case IPPROTO_UDPLITE:
 	case IPPROTO_SCTP:
-		port = fl->fl_ip_dport;
+		port = uli->ports.dport;
 		break;
 	case IPPROTO_ICMP:
 	case IPPROTO_ICMPV6:
-		port = htons(fl->fl_icmp_code);
+		port = htons(uli->icmpt.code);
 		break;
 	case IPPROTO_GRE:
-		port = htons(ntohl(fl->fl_gre_key) & 0xffff);
+		port = htons(ntohl(uli->gre_key) & 0xffff);
 		break;
 	default:
 		port = 0;	/*XXX*/
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 09a09911c5ea..d934b2040230 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -471,8 +471,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 		.fl4_src = ip_hdr(skb)->daddr,
 		.fl4_tos = RT_CONN_FLAGS(sk),
 		.flowi_proto = sk->sk_protocol,
-		.fl_ip_sport = dccp_hdr(skb)->dccph_dport,
-		.fl_ip_dport = dccp_hdr(skb)->dccph_sport,
+		.fl4_sport = dccp_hdr(skb)->dccph_dport,
+		.fl4_dport = dccp_hdr(skb)->dccph_sport,
 	};
 
 	security_skb_classify_flow(skb, &fl);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5209ee7a3dc2..2b351c6da49a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -158,8 +158,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
 			fl.flowi_oif = sk->sk_bound_dev_if;
-			fl.fl_ip_dport = inet->inet_dport;
-			fl.fl_ip_sport = inet->inet_sport;
+			fl.fl6_dport = inet->inet_dport;
+			fl.fl6_sport = inet->inet_sport;
 			security_sk_classify_flow(sk, &fl);
 
 			dst = ip6_dst_lookup_flow(sk, &fl, NULL, false);
@@ -253,8 +253,8 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 	ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
 	fl.fl6_flowlabel = 0;
 	fl.flowi_oif = ireq6->iif;
-	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
-	fl.fl_ip_sport = inet_rsk(req)->loc_port;
+	fl.fl6_dport = inet_rsk(req)->rmt_port;
+	fl.fl6_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
 
 	opt = np->opt;
@@ -323,8 +323,8 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 
 	fl.flowi_proto = IPPROTO_DCCP;
 	fl.flowi_oif = inet6_iif(rxskb);
-	fl.fl_ip_dport = dccp_hdr(skb)->dccph_dport;
-	fl.fl_ip_sport = dccp_hdr(skb)->dccph_sport;
+	fl.fl6_dport = dccp_hdr(skb)->dccph_dport;
+	fl.fl6_sport = dccp_hdr(skb)->dccph_sport;
 	security_skb_classify_flow(rxskb, &fl);
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
@@ -535,8 +535,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		final_p = fl6_update_dst(&fl, opt, &final);
 		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
 		fl.flowi_oif = sk->sk_bound_dev_if;
-		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
-		fl.fl_ip_sport = inet_rsk(req)->loc_port;
+		fl.fl6_dport = inet_rsk(req)->rmt_port;
+		fl.fl6_sport = inet_rsk(req)->loc_port;
 		security_sk_classify_flow(sk, &fl);
 
 		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
@@ -957,8 +957,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
 	ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr);
 	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.fl_ip_dport = usin->sin6_port;
-	fl.fl_ip_sport = inet->inet_sport;
+	fl.fl6_dport = usin->sin6_port;
+	fl.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, &fl);
 
 	final_p = fl6_update_dst(&fl, np->opt, &final);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 3fde7f23c70b..8d091954625b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -384,8 +384,8 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 		.fl4_src = saddr,
 		.fl4_tos = RT_TOS(tos),
 		.flowi_proto = IPPROTO_ICMP,
-		.fl_icmp_type = type,
-		.fl_icmp_code = code,
+		.fl4_icmp_type = type,
+		.fl4_icmp_code = code,
 	};
 	struct rtable *rt, *rt2;
 	int err;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 97081702dffd..10a8e9523578 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -365,8 +365,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 		.fl4_tos = RT_CONN_FLAGS(sk),
 		.flowi_proto = sk->sk_protocol,
 		.flowi_flags = inet_sk_flowi_flags(sk),
-		.fl_ip_sport = inet_sk(sk)->inet_sport,
-		.fl_ip_dport = ireq->rmt_port,
+		.fl4_sport = inet_sk(sk)->inet_sport,
+		.fl4_dport = ireq->rmt_port,
 	};
 	struct net *net = sock_net(sk);
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e35ca40df03b..67e5f7130322 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1479,8 +1479,8 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 			.fl4_dst = daddr,
 			.fl4_src = rt->rt_spec_dst,
 			.fl4_tos = RT_TOS(ip_hdr(skb)->tos),
-			.fl_ip_sport = tcp_hdr(skb)->dest,
-			.fl_ip_dport = tcp_hdr(skb)->source,
+			.fl4_sport = tcp_hdr(skb)->dest,
+			.fl4_dport = tcp_hdr(skb)->source,
 			.flowi_proto = sk->sk_protocol,
 			.flowi_flags = ip_reply_arg_flowi_flags(arg),
 		};
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 95481fee8bdb..1f3c695a47c8 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -55,7 +55,7 @@ static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 		    t->dst.protonum == IPPROTO_UDPLITE ||
 		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
-			fl->fl_ip_dport = t->dst.u.tcp.port;
+			fl->fl4_dport = t->dst.u.tcp.port;
 	}
 
 	statusbit ^= IPS_NAT_MASK;
@@ -67,7 +67,7 @@ static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 		    t->dst.protonum == IPPROTO_UDPLITE ||
 		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
-			fl->fl_ip_sport = t->src.u.tcp.port;
+			fl->fl4_sport = t->src.u.tcp.port;
 	}
 }
 #endif
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b42b7cd56c03..333b826c1871 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -433,8 +433,8 @@ static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 				code = iov->iov_base;
 
 			if (type && code) {
-				if (get_user(fl->fl_icmp_type, type) ||
-				    get_user(fl->fl_icmp_code, code))
+				if (get_user(fl->fl4_icmp_type, type) ||
+				    get_user(fl->fl4_icmp_code, code))
 					return -EFAULT;
 				probed = 1;
 			}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 98d47dc60c89..d90529d45ee6 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -353,8 +353,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			.fl4_tos = RT_CONN_FLAGS(sk),
 			.flowi_proto = IPPROTO_TCP,
 			.flowi_flags = inet_sk_flowi_flags(sk),
-			.fl_ip_sport = th->dest,
-			.fl_ip_dport = th->source,
+			.fl4_sport = th->dest,
+			.fl4_dport = th->source,
 		};
 		security_req_classify_flow(req, &fl);
 		rt = ip_route_output_key(sock_net(sk), &fl);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e10f62e6c07c..116e4a8bfb73 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -778,7 +778,7 @@ static int udp_push_pending_frames(struct sock *sk)
 	if (!skb)
 		goto out;
 
-	err = udp_send_skb(skb, fl->fl4_dst, fl->fl_ip_dport);
+	err = udp_send_skb(skb, fl->fl4_dst, fl->fl4_dport);
 
 out:
 	up->len = 0;
@@ -917,8 +917,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			.flowi_proto = sk->sk_protocol,
 			.flowi_flags = (inet_sk_flowi_flags(sk) |
 				     FLOWI_FLAG_CAN_SLEEP),
-			.fl_ip_sport = inet->inet_sport,
-			.fl_ip_dport = dport,
+			.fl4_sport = inet->inet_sport,
+			.fl4_dport = dport,
 		};
 		struct net *net = sock_net(sk);
 
@@ -973,9 +973,9 @@ back_from_confirm:
 	 *	Now cork the socket to pend data.
 	 */
 	inet->cork.fl.fl4_dst = daddr;
-	inet->cork.fl.fl_ip_dport = dport;
+	inet->cork.fl.fl4_dport = dport;
 	inet->cork.fl.fl4_src = saddr;
-	inet->cork.fl.fl_ip_sport = inet->inet_sport;
+	inet->cork.fl.fl4_sport = inet->inet_sport;
 	up->pending = AF_INET;
 
 do_append_data:
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 4294f121a749..b7b0921b425d 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -117,8 +117,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ports = (__be16 *)xprth;
 
-				fl->fl_ip_sport = ports[!!reverse];
-				fl->fl_ip_dport = ports[!reverse];
+				fl->fl4_sport = ports[!!reverse];
+				fl->fl4_dport = ports[!reverse];
 			}
 			break;
 
@@ -126,8 +126,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
 				u8 *icmp = xprth;
 
-				fl->fl_icmp_type = icmp[0];
-				fl->fl_icmp_code = icmp[1];
+				fl->fl4_icmp_type = icmp[0];
+				fl->fl4_icmp_code = icmp[1];
 			}
 			break;
 
@@ -135,7 +135,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be32 *ehdr = (__be32 *)xprth;
 
-				fl->fl_ipsec_spi = ehdr[0];
+				fl->fl4_ipsec_spi = ehdr[0];
 			}
 			break;
 
@@ -143,7 +143,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
 				__be32 *ah_hdr = (__be32*)xprth;
 
-				fl->fl_ipsec_spi = ah_hdr[1];
+				fl->fl4_ipsec_spi = ah_hdr[1];
 			}
 			break;
 
@@ -151,7 +151,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ipcomp_hdr = (__be16 *)xprth;
 
-				fl->fl_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
+				fl->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
 			}
 			break;
 
@@ -163,13 +163,13 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 				if (greflags[0] & GRE_KEY) {
 					if (greflags[0] & GRE_CSUM)
 						gre_hdr++;
-					fl->fl_gre_key = gre_hdr[1];
+					fl->fl4_gre_key = gre_hdr[1];
 				}
 			}
 			break;
 
 		default:
-			fl->fl_ipsec_spi = 0;
+			fl->fl4_ipsec_spi = 0;
 			break;
 		}
 	}
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index d2314348dd2a..663b5501abcd 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -25,9 +25,9 @@ __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 {
 	sel->daddr.a4 = fl->fl4_dst;
 	sel->saddr.a4 = fl->fl4_src;
-	sel->dport = xfrm_flowi_dport(fl);
+	sel->dport = xfrm_flowi_dport(fl, &fl->uli_u);
 	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl);
+	sel->sport = xfrm_flowi_sport(fl, &fl->uli_u);
 	sel->sport_mask = htons(0xffff);
 	sel->family = AF_INET;
 	sel->prefixlen_d = 32;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 35b0be0463f9..923febea8989 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -661,8 +661,8 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl.fl6_flowlabel = np->flow_label;
 		fl.flowi_oif = sk->sk_bound_dev_if;
 		fl.flowi_mark = sk->sk_mark;
-		fl.fl_ip_dport = inet->inet_dport;
-		fl.fl_ip_sport = inet->inet_sport;
+		fl.fl6_dport = inet->inet_dport;
+		fl.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, &fl);
 
 		final_p = fl6_update_dst(&fl, np->opt, &final);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 6c24b26f67ec..07e03e68243b 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -151,8 +151,8 @@ ipv4_connected:
 	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
 	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.flowi_mark = sk->sk_mark;
-	fl.fl_ip_dport = inet->inet_dport;
-	fl.fl_ip_sport = inet->inet_sport;
+	fl.fl6_dport = inet->inet_dport;
+	fl.fl6_sport = inet->inet_sport;
 
 	if (!fl.flowi_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl.flowi_oif = np->mcast_oif;
@@ -261,7 +261,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
 	serr->ee.ee_info = info;
 	serr->ee.ee_data = 0;
 	serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb);
-	serr->port = fl->fl_ip_dport;
+	serr->port = fl->fl6_dport;
 
 	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
 	skb_reset_transport_header(skb);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 9e123e08b9b7..52ff7aa1f9fc 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -448,8 +448,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	if (saddr)
 		ipv6_addr_copy(&fl.fl6_src, saddr);
 	fl.flowi_oif = iif;
-	fl.fl_icmp_type = type;
-	fl.fl_icmp_code = code;
+	fl.fl6_icmp_type = type;
+	fl.fl6_icmp_code = code;
 	security_skb_classify_flow(skb, &fl);
 
 	sk = icmpv6_xmit_lock(net);
@@ -544,7 +544,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (saddr)
 		ipv6_addr_copy(&fl.fl6_src, saddr);
 	fl.flowi_oif = skb->dev->ifindex;
-	fl.fl_icmp_type = ICMPV6_ECHO_REPLY;
+	fl.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	security_skb_classify_flow(skb, &fl);
 
 	sk = icmpv6_xmit_lock(net);
@@ -794,8 +794,8 @@ void icmpv6_flow_init(struct sock *sk, struct flowi *fl,
 	ipv6_addr_copy(&fl->fl6_src, saddr);
 	ipv6_addr_copy(&fl->fl6_dst, daddr);
 	fl->flowi_proto	 	= IPPROTO_ICMPV6;
-	fl->fl_icmp_type	= type;
-	fl->fl_icmp_code	= 0;
+	fl->fl6_icmp_type	= type;
+	fl->fl6_icmp_code	= 0;
 	fl->flowi_oif		= oif;
 	security_sk_classify_flow(sk, fl);
 }
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 673f9bf28958..1b06a24019c6 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -70,8 +70,8 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
 	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.flowi_mark = sk->sk_mark;
-	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
-	fl.fl_ip_sport = inet_rsk(req)->loc_port;
+	fl.fl6_dport = inet_rsk(req)->rmt_port;
+	fl.fl6_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
 
 	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
@@ -220,8 +220,8 @@ int inet6_csk_xmit(struct sk_buff *skb)
 	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
 	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.flowi_mark = sk->sk_mark;
-	fl.fl_ip_sport = inet->inet_sport;
-	fl.fl_ip_dport = inet->inet_dport;
+	fl.fl6_sport = inet->inet_sport;
+	fl.fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, &fl);
 
 	final_p = fl6_update_dst(&fl, np->opt, &final);
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index e2f852cd0f4e..5038e6b2b55b 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -215,7 +215,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	int err = 0;
 
 	if (unlikely(fl->flowi_proto == IPPROTO_MH &&
-		     fl->fl_mh_type <= IP6_MH_TYPE_MAX))
+		     fl->fl6_mh_type <= IP6_MH_TYPE_MAX))
 		goto out;
 
 	if (likely(opt->dsthao)) {
@@ -241,10 +241,10 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	sel.prefixlen_s = 128;
 	sel.family = AF_INET6;
 	sel.proto = fl->flowi_proto;
-	sel.dport = xfrm_flowi_dport(fl);
+	sel.dport = xfrm_flowi_dport(fl, &fl->uli_u);
 	if (sel.dport)
 		sel.dport_mask = htons(~0);
-	sel.sport = xfrm_flowi_sport(fl);
+	sel.sport = xfrm_flowi_sport(fl, &fl->uli_u);
 	if (sel.sport)
 		sel.sport_mask = htons(~0);
 	sel.ifindex = fl->flowi_oif;
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index fd3938803eb3..d1e905b7f563 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -93,8 +93,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	fl.flowi_proto = IPPROTO_TCP;
 	ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr);
 	ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr);
-	fl.fl_ip_sport = otcph.dest;
-	fl.fl_ip_dport = otcph.source;
+	fl.fl6_sport = otcph.dest;
+	fl.fl6_dport = otcph.source;
 	security_skb_classify_flow(oldskb, &fl);
 	dst = ip6_route_output(net, NULL, &fl);
 	if (dst == NULL || dst->error) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 323ad44ff775..d061465d6827 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -694,8 +694,8 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 				code = iov->iov_base;
 
 			if (type && code) {
-				if (get_user(fl->fl_icmp_type, type) ||
-				    get_user(fl->fl_icmp_code, code))
+				if (get_user(fl->fl6_icmp_type, type) ||
+				    get_user(fl->fl6_icmp_code, code))
 					return -EFAULT;
 				probed = 1;
 			}
@@ -706,7 +706,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 			/* check if type field is readable or not. */
 			if (iov->iov_len > 2 - len) {
 				u8 __user *p = iov->iov_base;
-				if (get_user(fl->fl_mh_type, &p[2 - len]))
+				if (get_user(fl->fl6_mh_type, &p[2 - len]))
 					return -EFAULT;
 				probed = 1;
 			} else
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index ca5255c08371..5b9eded1432c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -240,8 +240,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
 		fl.flowi_oif = sk->sk_bound_dev_if;
 		fl.flowi_mark = sk->sk_mark;
-		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
-		fl.fl_ip_sport = inet_sk(sk)->inet_sport;
+		fl.fl6_dport = inet_rsk(req)->rmt_port;
+		fl.fl6_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, &fl);
 
 		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a3d1229b4004..c531ad5fbccc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -248,8 +248,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		       (saddr ? saddr : &np->saddr));
 	fl.flowi_oif = sk->sk_bound_dev_if;
 	fl.flowi_mark = sk->sk_mark;
-	fl.fl_ip_dport = usin->sin6_port;
-	fl.fl_ip_sport = inet->inet_sport;
+	fl.fl6_dport = usin->sin6_port;
+	fl.fl6_sport = inet->inet_sport;
 
 	final_p = fl6_update_dst(&fl, np->opt, &final);
 
@@ -401,8 +401,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
 			fl.flowi_oif = sk->sk_bound_dev_if;
 			fl.flowi_mark = sk->sk_mark;
-			fl.fl_ip_dport = inet->inet_dport;
-			fl.fl_ip_sport = inet->inet_sport;
+			fl.fl6_dport = inet->inet_dport;
+			fl.fl6_sport = inet->inet_sport;
 			security_skb_classify_flow(skb, &fl);
 
 			dst = ip6_dst_lookup_flow(sk, &fl, NULL, false);
@@ -493,8 +493,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	fl.fl6_flowlabel = 0;
 	fl.flowi_oif = treq->iif;
 	fl.flowi_mark = sk->sk_mark;
-	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
-	fl.fl_ip_sport = inet_rsk(req)->loc_port;
+	fl.fl6_dport = inet_rsk(req)->rmt_port;
+	fl.fl6_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, &fl);
 
 	opt = np->opt;
@@ -1057,8 +1057,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	fl.flowi_proto = IPPROTO_TCP;
 	fl.flowi_oif = inet6_iif(skb);
-	fl.fl_ip_dport = t1->dest;
-	fl.fl_ip_sport = t1->source;
+	fl.fl6_dport = t1->dest;
+	fl.fl6_sport = t1->source;
 	security_skb_classify_flow(skb, &fl);
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 91f8047463ec..dad035fb0afd 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -899,8 +899,8 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	 * Create a UDP header
 	 */
 	uh = udp_hdr(skb);
-	uh->source = fl->fl_ip_sport;
-	uh->dest = fl->fl_ip_dport;
+	uh->source = fl->fl6_sport;
+	uh->dest = fl->fl6_dport;
 	uh->len = htons(up->len);
 	uh->check = 0;
 
@@ -1036,7 +1036,7 @@ do_udp_sendmsg:
 		if (sin6->sin6_port == 0)
 			return -EINVAL;
 
-		fl.fl_ip_dport = sin6->sin6_port;
+		fl.fl6_dport = sin6->sin6_port;
 		daddr = &sin6->sin6_addr;
 
 		if (np->sndflow) {
@@ -1065,7 +1065,7 @@ do_udp_sendmsg:
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
-		fl.fl_ip_dport = inet->inet_dport;
+		fl.fl6_dport = inet->inet_dport;
 		daddr = &np->daddr;
 		fl.fl6_flowlabel = np->flow_label;
 		connected = 1;
@@ -1112,7 +1112,7 @@ do_udp_sendmsg:
 		fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
 	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
 		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-	fl.fl_ip_sport = inet->inet_sport;
+	fl.fl6_sport = inet->inet_sport;
 
 	final_p = fl6_update_dst(&fl, opt, &final);
 	if (final_p)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index d62496c1a6f9..213c7594144b 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -158,8 +158,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
 				__be16 *ports = (__be16 *)exthdr;
 
-				fl->fl_ip_sport = ports[!!reverse];
-				fl->fl_ip_dport = ports[!reverse];
+				fl->fl6_sport = ports[!!reverse];
+				fl->fl6_dport = ports[!reverse];
 			}
 			fl->flowi_proto = nexthdr;
 			return;
@@ -168,8 +168,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
 				u8 *icmp = (u8 *)exthdr;
 
-				fl->fl_icmp_type = icmp[0];
-				fl->fl_icmp_code = icmp[1];
+				fl->fl6_icmp_type = icmp[0];
+				fl->fl6_icmp_code = icmp[1];
 			}
 			fl->flowi_proto = nexthdr;
 			return;
@@ -180,7 +180,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 				struct ip6_mh *mh;
 				mh = (struct ip6_mh *)exthdr;
 
-				fl->fl_mh_type = mh->ip6mh_type;
+				fl->fl6_mh_type = mh->ip6mh_type;
 			}
 			fl->flowi_proto = nexthdr;
 			return;
@@ -191,7 +191,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 		case IPPROTO_ESP:
 		case IPPROTO_COMP:
 		default:
-			fl->fl_ipsec_spi = 0;
+			fl->fl6_ipsec_spi = 0;
 			fl->flowi_proto = nexthdr;
 			return;
 		}
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 805d0e14c331..71277ce78590 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -26,9 +26,9 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 	 * to current session. */
 	ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
 	ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
-	sel->dport = xfrm_flowi_dport(fl);
+	sel->dport = xfrm_flowi_dport(fl, &fl->uli_u);
 	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl);
+	sel->sport = xfrm_flowi_sport(fl, &fl->uli_u);
 	sel->sport_mask = htons(0xffff);
 	sel->family = AF_INET6;
 	sel->prefixlen_d = 128;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 832665ac2100..b6fa2940e30b 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -476,16 +476,16 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 
 	memset(&fl, 0x0, sizeof(struct flowi));
 	fl.fl4_dst  = daddr->v4.sin_addr.s_addr;
-	fl.fl_ip_dport = daddr->v4.sin_port;
+	fl.fl4_dport = daddr->v4.sin_port;
 	fl.flowi_proto = IPPROTO_SCTP;
 	if (asoc) {
 		fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk);
 		fl.flowi_oif = asoc->base.sk->sk_bound_dev_if;
-		fl.fl_ip_sport = htons(asoc->base.bind_addr.port);
+		fl.fl4_sport = htons(asoc->base.bind_addr.port);
 	}
 	if (saddr) {
 		fl.fl4_src = saddr->v4.sin_addr.s_addr;
-		fl.fl_ip_sport = saddr->v4.sin_port;
+		fl.fl4_sport = saddr->v4.sin_port;
 	}
 
 	SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ",
@@ -534,7 +534,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 		if ((laddr->state == SCTP_ADDR_SRC) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
 			fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
-			fl.fl_ip_sport = laddr->a.v4.sin_port;
+			fl.fl4_sport = laddr->a.v4.sin_port;
 			rt = ip_route_output_key(&init_net, &fl);
 			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dd6243f9d933..d54b6e7165c6 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -61,8 +61,8 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
-		!((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) &&
-		!((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) &&
+		!((xfrm_flowi_dport(fl, &fl->uli_u) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl->uli_u) ^ sel->sport) & sel->sport_mask) &&
 		(fl->flowi_proto == sel->proto || !sel->proto) &&
 		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
 }
@@ -72,8 +72,8 @@ __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
-		!((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) &&
-		!((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) &&
+		!((xfrm_flowi_dport(fl, &fl->uli_u) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl->uli_u) ^ sel->sport) & sel->sport_mask) &&
 		(fl->flowi_proto == sel->proto || !sel->proto) &&
 		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
 }
-- 
cgit v1.2.3


From 56bb8059e1a8bf291054c26367564dc302f6fd8f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 00:44:35 -0500
Subject: net: Break struct flowi out into AF specific instances.

Now we have struct flowi4, flowi6, and flowidn for each address
family.  And struct flowi is just a union of them all.

It might have been troublesome to convert flow_cache_uli_match() but
as it turns out this function is completely unused and therefore can
be simply removed.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dn.h       |   4 +-
 include/net/flow.h     | 114 ++++++++++++++++++++++++-------------------------
 net/ipv4/xfrm4_state.c |   4 +-
 net/ipv6/mip6.c        |   4 +-
 net/ipv6/xfrm6_state.c |   4 +-
 net/xfrm/xfrm_policy.c |   8 ++--
 6 files changed, 69 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/include/net/dn.h b/include/net/dn.h
index a514a3cf4573..558dc7f93fb3 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -194,8 +194,8 @@ static inline void dn_dn2eth(unsigned char *ethaddr, __le16 addr)
 
 static inline void dn_sk_ports_copy(struct flowi *fl, struct dn_scp *scp)
 {
-	fl->uli_u.dnports.sport = scp->addrloc;
-	fl->uli_u.dnports.dport = scp->addrrem;
+	fl->u.dn.uli.ports.sport = scp->addrloc;
+	fl->u.dn.uli.ports.dport = scp->addrrem;
 }
 
 extern unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu);
diff --git a/include/net/flow.h b/include/net/flow.h
index f19f41d7dafc..931169095cc9 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -48,61 +48,68 @@ union flowi_uli {
 	} mht;
 };
 
-struct flowi {
+struct flowi4 {
+	struct flowi_common	__fl_common;
+	__be32			daddr;
+	__be32			saddr;
+	union flowi_uli		uli;
+};
+
+struct flowi6 {
 	struct flowi_common	__fl_common;
-#define flowi_oif		__fl_common.flowic_oif
-#define flowi_iif		__fl_common.flowic_iif
-#define flowi_mark		__fl_common.flowic_mark
-#define flowi_tos		__fl_common.flowic_tos
-#define flowi_scope		__fl_common.flowic_scope
-#define flowi_proto		__fl_common.flowic_proto
-#define flowi_flags		__fl_common.flowic_flags
-#define flowi_secid		__fl_common.flowic_secid
+	struct in6_addr		daddr;
+	struct in6_addr		saddr;
+	__be32			flowlabel;
+	union flowi_uli		uli;
+};
 
+struct flowidn {
+	struct flowi_common	__fl_common;
+	__le16			daddr;
+	__le16			saddr;
+	union flowi_uli		uli;
+};
+
+struct flowi {
 	union {
-		struct {
-			__be32			daddr;
-			__be32			saddr;
-		} ip4_u;
-		
-		struct {
-			struct in6_addr		daddr;
-			struct in6_addr		saddr;
-			__be32			flowlabel;
-		} ip6_u;
-
-		struct {
-			__le16			daddr;
-			__le16			saddr;
-			__u8			scope;
-		} dn_u;
-	} nl_u;
-#define fld_dst		nl_u.dn_u.daddr
-#define fld_src		nl_u.dn_u.saddr
-#define fld_scope	nl_u.dn_u.scope
-#define fl6_dst		nl_u.ip6_u.daddr
-#define fl6_src		nl_u.ip6_u.saddr
-#define fl6_flowlabel	nl_u.ip6_u.flowlabel
-#define fl4_dst		nl_u.ip4_u.daddr
-#define fl4_src		nl_u.ip4_u.saddr
+		struct flowi_common	__fl_common;
+		struct flowi4		ip4;
+		struct flowi6		ip6;
+		struct flowidn		dn;
+	} u;
+#define flowi_oif	u.__fl_common.flowic_oif
+#define flowi_iif	u.__fl_common.flowic_iif
+#define flowi_mark	u.__fl_common.flowic_mark
+#define flowi_tos	u.__fl_common.flowic_tos
+#define flowi_scope	u.__fl_common.flowic_scope
+#define flowi_proto	u.__fl_common.flowic_proto
+#define flowi_flags	u.__fl_common.flowic_flags
+#define flowi_secid	u.__fl_common.flowic_secid
 #define fl4_tos		flowi_tos
 #define fl4_scope	flowi_scope
-
-	union flowi_uli uli_u;
-#define fl4_sport	uli_u.ports.sport
-#define fl4_dport	uli_u.ports.dport
-#define fl4_icmp_type	uli_u.icmpt.type
-#define fl4_icmp_code	uli_u.icmpt.code
-#define fl4_ipsec_spi	uli_u.spi
-#define fl4_mh_type	uli_u.mht.type
-#define fl4_gre_key	uli_u.gre_key
-#define fl6_sport	uli_u.ports.sport
-#define fl6_dport	uli_u.ports.dport
-#define fl6_icmp_type	uli_u.icmpt.type
-#define fl6_icmp_code	uli_u.icmpt.code
-#define fl6_ipsec_spi	uli_u.spi
-#define fl6_mh_type	uli_u.mht.type
-#define fl6_gre_key	uli_u.gre_key
+#define fld_scope	flowi_scope
+
+#define fld_dst		u.dn.daddr
+#define fld_src		u.dn.saddr
+#define fl6_dst		u.ip6.daddr
+#define fl6_src		u.ip6.saddr
+#define fl6_flowlabel	u.ip6.flowlabel
+#define fl4_dst		u.ip4.daddr
+#define fl4_src		u.ip4.saddr
+#define fl4_sport	u.ip4.uli.ports.sport
+#define fl4_dport	u.ip4.uli.ports.dport
+#define fl4_icmp_type	u.ip4.uli.icmpt.type
+#define fl4_icmp_code	u.ip4.uli.icmpt.code
+#define fl4_ipsec_spi	u.ip4.uli.spi
+#define fl4_mh_type	u.ip4.uli.mht.type
+#define fl4_gre_key	u.ip4.uli.gre_key
+#define fl6_sport	u.ip6.uli.ports.sport
+#define fl6_dport	u.ip6.uli.ports.dport
+#define fl6_icmp_type	u.ip6.uli.icmpt.type
+#define fl6_icmp_code	u.ip6.uli.icmpt.code
+#define fl6_ipsec_spi	u.ip6.uli.spi
+#define fl6_mh_type	u.ip6.uli.mht.type
+#define fl6_gre_key	u.ip6.uli.gre_key
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 #define FLOW_DIR_IN	0
@@ -134,11 +141,4 @@ extern struct flow_cache_object *flow_cache_lookup(
 extern void flow_cache_flush(void);
 extern atomic_t flow_cache_genid;
 
-static inline int flow_cache_uli_match(const struct flowi *fl1,
-				       const struct flowi *fl2)
-{
-	return (fl1->flowi_proto == fl2->flowi_proto &&
-		!memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u)));
-}
-
 #endif
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 663b5501abcd..d8d541954532 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -25,9 +25,9 @@ __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 {
 	sel->daddr.a4 = fl->fl4_dst;
 	sel->saddr.a4 = fl->fl4_src;
-	sel->dport = xfrm_flowi_dport(fl, &fl->uli_u);
+	sel->dport = xfrm_flowi_dport(fl, &fl->u.ip4.uli);
 	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl, &fl->uli_u);
+	sel->sport = xfrm_flowi_sport(fl, &fl->u.ip4.uli);
 	sel->sport_mask = htons(0xffff);
 	sel->family = AF_INET;
 	sel->prefixlen_d = 32;
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 5038e6b2b55b..e1767aec3334 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -241,10 +241,10 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	sel.prefixlen_s = 128;
 	sel.family = AF_INET6;
 	sel.proto = fl->flowi_proto;
-	sel.dport = xfrm_flowi_dport(fl, &fl->uli_u);
+	sel.dport = xfrm_flowi_dport(fl, &fl->u.ip6.uli);
 	if (sel.dport)
 		sel.dport_mask = htons(~0);
-	sel.sport = xfrm_flowi_sport(fl, &fl->uli_u);
+	sel.sport = xfrm_flowi_sport(fl, &fl->u.ip6.uli);
 	if (sel.sport)
 		sel.sport_mask = htons(~0);
 	sel.ifindex = fl->flowi_oif;
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 71277ce78590..b456533a652d 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -26,9 +26,9 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 	 * to current session. */
 	ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
 	ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
-	sel->dport = xfrm_flowi_dport(fl, &fl->uli_u);
+	sel->dport = xfrm_flowi_dport(fl, &fl->u.ip6.uli);
 	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl, &fl->uli_u);
+	sel->sport = xfrm_flowi_sport(fl, &fl->u.ip6.uli);
 	sel->sport_mask = htons(0xffff);
 	sel->family = AF_INET6;
 	sel->prefixlen_d = 128;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d54b6e7165c6..2ecd18a106cf 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -61,8 +61,8 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
-		!((xfrm_flowi_dport(fl, &fl->uli_u) ^ sel->dport) & sel->dport_mask) &&
-		!((xfrm_flowi_sport(fl, &fl->uli_u) ^ sel->sport) & sel->sport_mask) &&
+		!((xfrm_flowi_dport(fl, &fl->u.ip4.uli) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl->u.ip4.uli) ^ sel->sport) & sel->sport_mask) &&
 		(fl->flowi_proto == sel->proto || !sel->proto) &&
 		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
 }
@@ -72,8 +72,8 @@ __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	return  addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) &&
 		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
-		!((xfrm_flowi_dport(fl, &fl->uli_u) ^ sel->dport) & sel->dport_mask) &&
-		!((xfrm_flowi_sport(fl, &fl->uli_u) ^ sel->sport) & sel->sport_mask) &&
+		!((xfrm_flowi_dport(fl, &fl->u.ip6.uli) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl->u.ip6.uli) ^ sel->sport) & sel->sport_mask) &&
 		(fl->flowi_proto == sel->proto || !sel->proto) &&
 		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
 }
-- 
cgit v1.2.3


From 59b1a94c9a034e63a5e030a5154be1d4d84677d9 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 11 Mar 2011 19:23:02 -0500
Subject: net: Add flowiX_to_flowi() shorthands.

This is just a shorthand which will help in passing around AF
specific flow structures as generic ones.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 931169095cc9..8139257ee11e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -112,6 +112,21 @@ struct flowi {
 #define fl6_gre_key	u.ip6.uli.gre_key
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
+static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
+{
+	return container_of(fl4, struct flowi, u.ip4);
+}
+
+static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6)
+{
+	return container_of(fl6, struct flowi, u.ip6);
+}
+
+static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
+{
+	return container_of(fldn, struct flowi, u.dn);
+}
+
 #define FLOW_DIR_IN	0
 #define FLOW_DIR_OUT	1
 #define FLOW_DIR_FWD	2
-- 
cgit v1.2.3


From 22bd5b9b13f2931ac80949f8bfbc40e8cab05be7 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 11 Mar 2011 19:54:08 -0500
Subject: ipv4: Pass ipv4 flow objects into fib_lookup() paths.

To start doing these conversions, we need to add some temporary
flow4_* macros which will eventually go away when all the protocol
code paths are changed to work on AF specific flowi objects.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h       |  8 ++++++++
 include/net/ip_fib.h     |  6 +++---
 net/ipv4/fib_frontend.c  |  8 ++++----
 net/ipv4/fib_rules.c     |  6 +++---
 net/ipv4/fib_semantics.c |  2 +-
 net/ipv4/fib_trie.c      | 12 ++++++------
 net/ipv4/route.c         |  6 +++---
 7 files changed, 28 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 8139257ee11e..3e4630ebde32 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -50,6 +50,14 @@ union flowi_uli {
 
 struct flowi4 {
 	struct flowi_common	__fl_common;
+#define flowi4_oif		__fl_common.flowic_oif
+#define flowi4_iif		__fl_common.flowic_iif
+#define flowi4_mark		__fl_common.flowic_mark
+#define flowi4_tos		__fl_common.flowic_tos
+#define flowi4_scope		__fl_common.flowic_scope
+#define flowi4_proto		__fl_common.flowic_proto
+#define flowi4_flags		__fl_common.flowic_flags
+#define flowi4_secid		__fl_common.flowic_secid
 	__be32			daddr;
 	__be32			saddr;
 	union flowi_uli		uli;
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index d948e232eb06..a1a858035913 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -155,7 +155,7 @@ struct fib_table {
 	unsigned char	tb_data[0];
 };
 
-extern int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
+extern int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 			    struct fib_result *res, int fib_flags);
 extern int fib_table_insert(struct fib_table *, struct fib_config *);
 extern int fib_table_delete(struct fib_table *, struct fib_config *);
@@ -186,7 +186,7 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id)
 	return fib_get_table(net, id);
 }
 
-static inline int fib_lookup(struct net *net, const struct flowi *flp,
+static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 			     struct fib_result *res)
 {
 	struct fib_table *table;
@@ -209,7 +209,7 @@ extern void __net_exit fib4_rules_exit(struct net *net);
 extern u32 fib_rules_tclass(const struct fib_result *res);
 #endif
 
-extern int fib_lookup(struct net *n, struct flowi *flp, struct fib_result *res);
+extern int fib_lookup(struct net *n, struct flowi4 *flp, struct fib_result *res);
 
 extern struct fib_table *fib_new_table(struct net *net, u32 id);
 extern struct fib_table *fib_get_table(struct net *net, u32 id);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 76105284a81c..48125d559f17 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -158,7 +158,7 @@ static inline unsigned __inet_dev_addr_type(struct net *net,
 	if (local_table) {
 		ret = RTN_UNICAST;
 		rcu_read_lock();
-		if (!fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) {
+		if (!fib_table_lookup(local_table, &fl.u.ip4, &res, FIB_LOOKUP_NOREF)) {
 			if (!dev || dev == res.fi->fib_dev)
 				ret = res.type;
 		}
@@ -222,7 +222,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 		goto e_inval;
 
 	net = dev_net(dev);
-	if (fib_lookup(net, &fl, &res))
+	if (fib_lookup(net, &fl.u.ip4, &res))
 		goto last_resort;
 	if (res.type != RTN_UNICAST) {
 		if (res.type != RTN_LOCAL || !accept_local)
@@ -256,7 +256,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
 	fl.flowi_oif = dev->ifindex;
 
 	ret = 0;
-	if (fib_lookup(net, &fl, &res) == 0) {
+	if (fib_lookup(net, &fl.u.ip4, &res) == 0) {
 		if (res.type == RTN_UNICAST) {
 			*spec_dst = FIB_RES_PREFSRC(res);
 			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
@@ -813,7 +813,7 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
 
 		frn->tb_id = tb->tb_id;
 		rcu_read_lock();
-		frn->err = fib_table_lookup(tb, &fl, &res, FIB_LOOKUP_NOREF);
+		frn->err = fib_table_lookup(tb, &fl.u.ip4, &res, FIB_LOOKUP_NOREF);
 
 		if (!frn->err) {
 			frn->prefixlen = res.prefixlen;
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 3018efbaea77..0c63c4ab0936 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -53,7 +53,7 @@ u32 fib_rules_tclass(const struct fib_result *res)
 }
 #endif
 
-int fib_lookup(struct net *net, struct flowi *flp, struct fib_result *res)
+int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
 {
 	struct fib_lookup_arg arg = {
 		.result = res,
@@ -61,7 +61,7 @@ int fib_lookup(struct net *net, struct flowi *flp, struct fib_result *res)
 	};
 	int err;
 
-	err = fib_rules_lookup(net->ipv4.rules_ops, flp, 0, &arg);
+	err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg);
 	res->r = arg.rule;
 
 	return err;
@@ -95,7 +95,7 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
 	if (!tbl)
 		goto errout;
 
-	err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result, arg->flags);
+	err = fib_table_lookup(tbl, &flp->u.ip4, (struct fib_result *) arg->result, arg->flags);
 	if (err > 0)
 		err = -EAGAIN;
 errout:
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 79179ade5294..a721013fdf46 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -569,7 +569,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 			/* It is not necessary, but requires a bit of thinking */
 			if (fl.fl4_scope < RT_SCOPE_LINK)
 				fl.fl4_scope = RT_SCOPE_LINK;
-			err = fib_lookup(net, &fl, &res);
+			err = fib_lookup(net, &fl.u.ip4, &res);
 			if (err) {
 				rcu_read_unlock();
 				return err;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index d5ff80ef001a..3d28a35c2e1a 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1341,7 +1341,7 @@ err:
 
 /* should be called with rcu_read_lock */
 static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
-		      t_key key,  const struct flowi *flp,
+		      t_key key,  const struct flowi4 *flp,
 		      struct fib_result *res, int fib_flags)
 {
 	struct leaf_info *li;
@@ -1360,9 +1360,9 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 			struct fib_info *fi = fa->fa_info;
 			int nhsel, err;
 
-			if (fa->fa_tos && fa->fa_tos != flp->fl4_tos)
+			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 				continue;
-			if (fa->fa_scope < flp->fl4_scope)
+			if (fa->fa_scope < flp->flowi4_scope)
 				continue;
 			fib_alias_accessed(fa);
 			err = fib_props[fa->fa_type].error;
@@ -1379,7 +1379,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
 				if (nh->nh_flags & RTNH_F_DEAD)
 					continue;
-				if (flp->flowi_oif && flp->flowi_oif != nh->nh_oif)
+				if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
 					continue;
 
 #ifdef CONFIG_IP_FIB_TRIE_STATS
@@ -1406,7 +1406,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 	return 1;
 }
 
-int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
+int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags)
 {
 	struct trie *t = (struct trie *) tb->tb_data;
@@ -1414,7 +1414,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
 	struct rt_trie_node *n;
 	struct tnode *pn;
 	unsigned int pos, bits;
-	t_key key = ntohl(flp->fl4_dst);
+	t_key key = ntohl(flp->daddr);
 	unsigned int chopped_off;
 	t_key cindex = 0;
 	unsigned int current_prefix_length = KEYLENGTH;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c9aa4f9effe2..027b4cc0f4a0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1707,7 +1707,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 		};
 
 		rcu_read_lock();
-		if (fib_lookup(dev_net(rt->dst.dev), &fl, &res) == 0)
+		if (fib_lookup(dev_net(rt->dst.dev), &fl.u.ip4, &res) == 0)
 			src = FIB_RES_PREFSRC(res);
 		else
 			src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
@@ -2125,7 +2125,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl.fl4_src = saddr;
 	fl.fl4_tos = tos;
 	fl.fl4_scope = RT_SCOPE_UNIVERSE;
-	err = fib_lookup(net, &fl, &res);
+	err = fib_lookup(net, &fl.u.ip4, &res);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
 			goto e_hostunreach;
@@ -2551,7 +2551,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
 		goto make_route;
 	}
 
-	if (fib_lookup(net, &fl, &res)) {
+	if (fib_lookup(net, &fl.u.ip4, &res)) {
 		res.fi = NULL;
 		if (oldflp->flowi_oif) {
 			/* Apparently, routing tables are wrong. Assume,
-- 
cgit v1.2.3


From 9d6ec938019c6b16cb9ec96598ebe8f20de435fe Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 01:12:47 -0500
Subject: ipv4: Use flowi4 in public route lookup interfaces.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h             | 118 ++++++++++++++++++++--------------------
 net/dccp/ipv4.c                 |  20 +++----
 net/ipv4/icmp.c                 |  59 ++++++++++----------
 net/ipv4/inet_connection_sock.c |  26 ++++-----
 net/ipv4/ip_output.c            |  22 ++++----
 net/ipv4/netfilter.c            |  26 ++++-----
 net/ipv4/raw.c                  |  32 ++++++-----
 net/ipv4/route.c                |  36 ++++++------
 net/ipv4/syncookies.c           |  24 ++++----
 net/ipv4/udp.c                  |  26 ++++-----
 net/ipv4/xfrm4_policy.c         |  10 ++--
 net/netfilter/ipvs/ip_vs_xmit.c |  12 ++--
 net/netfilter/xt_TEE.c          |  14 ++---
 net/sctp/protocol.c             |  30 +++++-----
 14 files changed, 231 insertions(+), 224 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index 4c207f9fe0cb..80b0353f4f41 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -122,12 +122,12 @@ extern void		ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
 				       __be32 src, struct net_device *dev);
 extern void		rt_cache_flush(struct net *net, int how);
 extern void		rt_cache_flush_batch(struct net *net);
-extern struct rtable *__ip_route_output_key(struct net *, const struct flowi *flp);
-extern struct rtable *ip_route_output_flow(struct net *, struct flowi *flp,
+extern struct rtable *__ip_route_output_key(struct net *, const struct flowi4 *flp);
+extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
 					   struct sock *sk);
 extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
 
-static inline struct rtable *ip_route_output_key(struct net *net, struct flowi *flp)
+static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp)
 {
 	return ip_route_output_flow(net, flp, NULL);
 }
@@ -135,13 +135,13 @@ static inline struct rtable *ip_route_output_key(struct net *net, struct flowi *
 static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
 					     __be32 saddr, u8 tos, int oif)
 {
-	struct flowi fl = {
-		.flowi_oif = oif,
-		.fl4_dst = daddr,
-		.fl4_src = saddr,
-		.fl4_tos = tos,
+	struct flowi4 fl4 = {
+		.flowi4_oif = oif,
+		.daddr = daddr,
+		.saddr = saddr,
+		.flowi4_tos = tos,
 	};
-	return ip_route_output_key(net, &fl);
+	return ip_route_output_key(net, &fl4);
 }
 
 static inline struct rtable *ip_route_output_ports(struct net *net, struct sock *sk,
@@ -149,35 +149,35 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct sock
 						   __be16 dport, __be16 sport,
 						   __u8 proto, __u8 tos, int oif)
 {
-	struct flowi fl = {
-		.flowi_oif = oif,
-		.flowi_flags = sk ? inet_sk_flowi_flags(sk) : 0,
-		.flowi_mark = sk ? sk->sk_mark : 0,
-		.fl4_dst = daddr,
-		.fl4_src = saddr,
-		.fl4_tos = tos,
-		.flowi_proto = proto,
-		.fl4_dport = dport,
-		.fl4_sport = sport,
+	struct flowi4 fl4 = {
+		.flowi4_oif = oif,
+		.flowi4_flags = sk ? inet_sk_flowi_flags(sk) : 0,
+		.flowi4_mark = sk ? sk->sk_mark : 0,
+		.daddr = daddr,
+		.saddr = saddr,
+		.flowi4_tos = tos,
+		.flowi4_proto = proto,
+		.uli.ports.dport = dport,
+		.uli.ports.sport = sport,
 	};
 	if (sk)
-		security_sk_classify_flow(sk, &fl);
-	return ip_route_output_flow(net, &fl, sk);
+		security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	return ip_route_output_flow(net, &fl4, sk);
 }
 
 static inline struct rtable *ip_route_output_gre(struct net *net,
 						 __be32 daddr, __be32 saddr,
 						 __be32 gre_key, __u8 tos, int oif)
 {
-	struct flowi fl = {
-		.flowi_oif = oif,
-		.fl4_dst = daddr,
-		.fl4_src = saddr,
-		.fl4_tos = tos,
-		.flowi_proto = IPPROTO_GRE,
-		.fl4_gre_key = gre_key,
+	struct flowi4 fl4 = {
+		.flowi4_oif = oif,
+		.daddr = daddr,
+		.saddr = saddr,
+		.flowi4_tos = tos,
+		.flowi4_proto = IPPROTO_GRE,
+		.uli.gre_key = gre_key,
 	};
-	return ip_route_output_key(net, &fl);
+	return ip_route_output_key(net, &fl4);
 }
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
@@ -228,36 +228,36 @@ static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos,
 					      __be16 sport, __be16 dport,
 					      struct sock *sk, bool can_sleep)
 {
-	struct flowi fl = {
-		.flowi_oif = oif,
-		.flowi_mark = sk->sk_mark,
-		.fl4_dst = dst,
-		.fl4_src = src,
-		.fl4_tos = tos,
-		.flowi_proto = protocol,
-		.fl4_sport = sport,
-		.fl4_dport = dport,
+	struct flowi4 fl4 = {
+		.flowi4_oif = oif,
+		.flowi4_mark = sk->sk_mark,
+		.daddr = dst,
+		.saddr = src,
+		.flowi4_tos = tos,
+		.flowi4_proto = protocol,
+		.uli.ports.sport = sport,
+		.uli.ports.dport = dport,
 	};
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
 
 	if (inet_sk(sk)->transparent)
-		fl.flowi_flags |= FLOWI_FLAG_ANYSRC;
+		fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
 	if (protocol == IPPROTO_TCP)
-		fl.flowi_flags |= FLOWI_FLAG_PRECOW_METRICS;
+		fl4.flowi4_flags |= FLOWI_FLAG_PRECOW_METRICS;
 	if (can_sleep)
-		fl.flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
+		fl4.flowi4_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	if (!dst || !src) {
-		rt = __ip_route_output_key(net, &fl);
+		rt = __ip_route_output_key(net, &fl4);
 		if (IS_ERR(rt))
 			return rt;
-		fl.fl4_dst = rt->rt_dst;
-		fl.fl4_src = rt->rt_src;
+		fl4.daddr = rt->rt_dst;
+		fl4.saddr = rt->rt_src;
 		ip_rt_put(rt);
 	}
-	security_sk_classify_flow(sk, &fl);
-	return ip_route_output_flow(net, &fl, sk);
+	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	return ip_route_output_flow(net, &fl4, sk);
 }
 
 static inline struct rtable *ip_route_newports(struct rtable *rt,
@@ -266,23 +266,23 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 					       __be16 dport, struct sock *sk)
 {
 	if (sport != orig_sport || dport != orig_dport) {
-		struct flowi fl = {
-			.flowi_oif = rt->rt_oif,
-			.flowi_mark = rt->rt_mark,
-			.fl4_dst = rt->rt_key_dst,
-			.fl4_src = rt->rt_key_src,
-			.fl4_tos = rt->rt_tos,
-			.flowi_proto = protocol,
-			.fl4_sport = sport,
-			.fl4_dport = dport
+		struct flowi4 fl4 = {
+			.flowi4_oif = rt->rt_oif,
+			.flowi4_mark = rt->rt_mark,
+			.daddr = rt->rt_key_dst,
+			.saddr = rt->rt_key_src,
+			.flowi4_tos = rt->rt_tos,
+			.flowi4_proto = protocol,
+			.uli.ports.sport = sport,
+			.uli.ports.dport = dport
 		};
 		if (inet_sk(sk)->transparent)
-			fl.flowi_flags |= FLOWI_FLAG_ANYSRC;
+			fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
 		if (protocol == IPPROTO_TCP)
-			fl.flowi_flags |= FLOWI_FLAG_PRECOW_METRICS;
+			fl4.flowi4_flags |= FLOWI_FLAG_PRECOW_METRICS;
 		ip_rt_put(rt);
-		security_sk_classify_flow(sk, &fl);
-		return ip_route_output_flow(sock_net(sk), &fl, sk);
+		security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+		return ip_route_output_flow(sock_net(sk), &fl4, sk);
 	}
 	return rt;
 }
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d934b2040230..be984706126b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -465,18 +465,18 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 					   struct sk_buff *skb)
 {
 	struct rtable *rt;
-	struct flowi fl = {
-		.flowi_oif = skb_rtable(skb)->rt_iif,
-		.fl4_dst = ip_hdr(skb)->saddr,
-		.fl4_src = ip_hdr(skb)->daddr,
-		.fl4_tos = RT_CONN_FLAGS(sk),
-		.flowi_proto = sk->sk_protocol,
-		.fl4_sport = dccp_hdr(skb)->dccph_dport,
-		.fl4_dport = dccp_hdr(skb)->dccph_sport,
+	struct flowi4 fl4 = {
+		.flowi4_oif = skb_rtable(skb)->rt_iif,
+		.daddr = ip_hdr(skb)->saddr,
+		.saddr = ip_hdr(skb)->daddr,
+		.flowi4_tos = RT_CONN_FLAGS(sk),
+		.flowi4_proto = sk->sk_protocol,
+		.uli.ports.sport = dccp_hdr(skb)->dccph_dport,
+		.uli.ports.dport = dccp_hdr(skb)->dccph_sport,
 	};
 
-	security_skb_classify_flow(skb, &fl);
-	rt = ip_route_output_flow(net, &fl, sk);
+	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
 		return NULL;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8d091954625b..8eca3c28cbc3 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,14 +353,14 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 			daddr = icmp_param->replyopts.faddr;
 	}
 	{
-		struct flowi fl = {
-			.fl4_dst = daddr,
-			.fl4_src = rt->rt_spec_dst,
-			.fl4_tos = RT_TOS(ip_hdr(skb)->tos),
-			.flowi_proto = IPPROTO_ICMP,
+		struct flowi4 fl4 = {
+			.daddr = daddr,
+			.saddr = rt->rt_spec_dst,
+			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi4_proto = IPPROTO_ICMP,
 		};
-		security_skb_classify_flow(skb, &fl);
-		rt = ip_route_output_key(net, &fl);
+		security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+		rt = ip_route_output_key(net, &fl4);
 		if (IS_ERR(rt))
 			goto out_unlock;
 	}
@@ -378,30 +378,31 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 					int type, int code,
 					struct icmp_bxm *param)
 {
-	struct flowi fl = {
-		.fl4_dst = (param->replyopts.srr ?
-			    param->replyopts.faddr : iph->saddr),
-		.fl4_src = saddr,
-		.fl4_tos = RT_TOS(tos),
-		.flowi_proto = IPPROTO_ICMP,
-		.fl4_icmp_type = type,
-		.fl4_icmp_code = code,
+	struct flowi4 fl4 = {
+		.daddr = (param->replyopts.srr ?
+			  param->replyopts.faddr : iph->saddr),
+		.saddr = saddr,
+		.flowi4_tos = RT_TOS(tos),
+		.flowi4_proto = IPPROTO_ICMP,
+		.uli.icmpt.type = type,
+		.uli.icmpt.code = code,
 	};
 	struct rtable *rt, *rt2;
 	int err;
 
-	security_skb_classify_flow(skb_in, &fl);
-	rt = __ip_route_output_key(net, &fl);
+	security_skb_classify_flow(skb_in, flowi4_to_flowi(&fl4));
+	rt = __ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		return rt;
 
 	/* No need to clone since we're just using its address. */
 	rt2 = rt;
 
-	if (!fl.fl4_src)
-		fl.fl4_src = rt->rt_src;
+	if (!fl4.saddr)
+		fl4.saddr = rt->rt_src;
 
-	rt = (struct rtable *) xfrm_lookup(net, &rt->dst, &fl, NULL, 0);
+	rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
+					   flowi4_to_flowi(&fl4), NULL, 0);
 	if (!IS_ERR(rt)) {
 		if (rt != rt2)
 			return rt;
@@ -410,27 +411,27 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 	} else
 		return rt;
 
-	err = xfrm_decode_session_reverse(skb_in, &fl, AF_INET);
+	err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4), AF_INET);
 	if (err)
 		goto relookup_failed;
 
-	if (inet_addr_type(net, fl.fl4_src) == RTN_LOCAL) {
-		rt2 = __ip_route_output_key(net, &fl);
+	if (inet_addr_type(net, fl4.saddr) == RTN_LOCAL) {
+		rt2 = __ip_route_output_key(net, &fl4);
 		if (IS_ERR(rt2))
 			err = PTR_ERR(rt2);
 	} else {
-		struct flowi fl2 = {};
+		struct flowi4 fl4_2 = {};
 		unsigned long orefdst;
 
-		fl2.fl4_dst = fl.fl4_src;
-		rt2 = ip_route_output_key(net, &fl2);
+		fl4_2.daddr = fl4.saddr;
+		rt2 = ip_route_output_key(net, &fl4_2);
 		if (IS_ERR(rt2)) {
 			err = PTR_ERR(rt2);
 			goto relookup_failed;
 		}
 		/* Ugh! */
 		orefdst = skb_in->_skb_refdst; /* save old refdst */
-		err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src,
+		err = ip_route_input(skb_in, fl4.daddr, fl4.saddr,
 				     RT_TOS(tos), rt2->dst.dev);
 
 		dst_release(&rt2->dst);
@@ -441,7 +442,9 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 	if (err)
 		goto relookup_failed;
 
-	rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, &fl, NULL, XFRM_LOOKUP_ICMP);
+	rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst,
+					    flowi4_to_flowi(&fl4), NULL,
+					    XFRM_LOOKUP_ICMP);
 	if (!IS_ERR(rt2)) {
 		dst_release(&rt->dst);
 		rt = rt2;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 10a8e9523578..beecc1272169 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -356,22 +356,22 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct rtable *rt;
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct ip_options *opt = inet_rsk(req)->opt;
-	struct flowi fl = {
-		.flowi_oif = sk->sk_bound_dev_if,
-		.flowi_mark = sk->sk_mark,
-		.fl4_dst = ((opt && opt->srr) ?
-			    opt->faddr : ireq->rmt_addr),
-		.fl4_src = ireq->loc_addr,
-		.fl4_tos = RT_CONN_FLAGS(sk),
-		.flowi_proto = sk->sk_protocol,
-		.flowi_flags = inet_sk_flowi_flags(sk),
-		.fl4_sport = inet_sk(sk)->inet_sport,
-		.fl4_dport = ireq->rmt_port,
+	struct flowi4 fl4 = {
+		.flowi4_oif = sk->sk_bound_dev_if,
+		.flowi4_mark = sk->sk_mark,
+		.daddr = ((opt && opt->srr) ?
+			  opt->faddr : ireq->rmt_addr),
+		.saddr = ireq->loc_addr,
+		.flowi4_tos = RT_CONN_FLAGS(sk),
+		.flowi4_proto = sk->sk_protocol,
+		.flowi4_flags = inet_sk_flowi_flags(sk),
+		.uli.ports.sport = inet_sk(sk)->inet_sport,
+		.uli.ports.dport = ireq->rmt_port,
 	};
 	struct net *net = sock_net(sk);
 
-	security_req_classify_flow(req, &fl);
-	rt = ip_route_output_flow(net, &fl, sk);
+	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
 	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 67e5f7130322..2b9cc40397ee 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1474,18 +1474,18 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 	}
 
 	{
-		struct flowi fl = {
-			.flowi_oif = arg->bound_dev_if,
-			.fl4_dst = daddr,
-			.fl4_src = rt->rt_spec_dst,
-			.fl4_tos = RT_TOS(ip_hdr(skb)->tos),
-			.fl4_sport = tcp_hdr(skb)->dest,
-			.fl4_dport = tcp_hdr(skb)->source,
-			.flowi_proto = sk->sk_protocol,
-			.flowi_flags = ip_reply_arg_flowi_flags(arg),
+		struct flowi4 fl4 = {
+			.flowi4_oif = arg->bound_dev_if,
+			.daddr = daddr,
+			.saddr = rt->rt_spec_dst,
+			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.uli.ports.sport = tcp_hdr(skb)->dest,
+			.uli.ports.dport = tcp_hdr(skb)->source,
+			.flowi4_proto = sk->sk_protocol,
+			.flowi4_flags = ip_reply_arg_flowi_flags(arg),
 		};
-		security_skb_classify_flow(skb, &fl);
-		rt = ip_route_output_key(sock_net(sk), &fl);
+		security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+		rt = ip_route_output_key(sock_net(sk), &fl4);
 		if (IS_ERR(rt))
 			return;
 	}
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 6f40ba511c6b..f3c0b549b8e1 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -16,7 +16,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
-	struct flowi fl = {};
+	struct flowi4 fl4 = {};
 	unsigned long orefdst;
 	unsigned int hh_len;
 	unsigned int type;
@@ -31,14 +31,14 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	 * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
 	 */
 	if (addr_type == RTN_LOCAL) {
-		fl.fl4_dst = iph->daddr;
+		fl4.daddr = iph->daddr;
 		if (type == RTN_LOCAL)
-			fl.fl4_src = iph->saddr;
-		fl.fl4_tos = RT_TOS(iph->tos);
-		fl.flowi_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
-		fl.flowi_mark = skb->mark;
-		fl.flowi_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
-		rt = ip_route_output_key(net, &fl);
+			fl4.saddr = iph->saddr;
+		fl4.flowi4_tos = RT_TOS(iph->tos);
+		fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+		fl4.flowi4_mark = skb->mark;
+		fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+		rt = ip_route_output_key(net, &fl4);
 		if (IS_ERR(rt))
 			return -1;
 
@@ -48,8 +48,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	} else {
 		/* non-local src, find valid iif to satisfy
 		 * rp-filter when calling ip_route_input. */
-		fl.fl4_dst = iph->saddr;
-		rt = ip_route_output_key(net, &fl);
+		fl4.daddr = iph->saddr;
+		rt = ip_route_output_key(net, &fl4);
 		if (IS_ERR(rt))
 			return -1;
 
@@ -68,10 +68,10 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 
 #ifdef CONFIG_XFRM
 	if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
-	    xfrm_decode_session(skb, &fl, AF_INET) == 0) {
+	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
 		struct dst_entry *dst = skb_dst(skb);
 		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
+		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
 		if (IS_ERR(dst))
 			return -1;
 		skb_dst_set(skb, dst);
@@ -223,7 +223,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
 
 static int nf_ip_route(struct dst_entry **dst, struct flowi *fl)
 {
-	struct rtable *rt = ip_route_output_key(&init_net, fl);
+	struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 	*dst = &rt->dst;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 333b826c1871..452e178d962d 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -402,7 +402,7 @@ error:
 	return err;
 }
 
-static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+static int raw_probe_proto_opt(struct flowi4 *fl4, struct msghdr *msg)
 {
 	struct iovec *iov;
 	u8 __user *type = NULL;
@@ -418,7 +418,7 @@ static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 		if (!iov)
 			continue;
 
-		switch (fl->flowi_proto) {
+		switch (fl4->flowi4_proto) {
 		case IPPROTO_ICMP:
 			/* check if one-byte field is readable or not. */
 			if (iov->iov_base && iov->iov_len < 1)
@@ -433,8 +433,8 @@ static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 				code = iov->iov_base;
 
 			if (type && code) {
-				if (get_user(fl->fl4_icmp_type, type) ||
-				    get_user(fl->fl4_icmp_code, code))
+				if (get_user(fl4->uli.icmpt.type, type) ||
+				    get_user(fl4->uli.icmpt.code, code))
 					return -EFAULT;
 				probed = 1;
 			}
@@ -548,23 +548,25 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	}
 
 	{
-		struct flowi fl = { .flowi_oif = ipc.oif,
-				    .flowi_mark = sk->sk_mark,
-				    .fl4_dst = daddr,
-				    .fl4_src = saddr,
-				    .fl4_tos = tos,
-				    .flowi_proto = inet->hdrincl ? IPPROTO_RAW :
-							     sk->sk_protocol,
-				    .flowi_flags = FLOWI_FLAG_CAN_SLEEP,
+		struct flowi4 fl4 = {
+			.flowi4_oif = ipc.oif,
+			.flowi4_mark = sk->sk_mark,
+			.daddr = daddr,
+			.saddr = saddr,
+			.flowi4_tos = tos,
+			.flowi4_proto = (inet->hdrincl ?
+					 IPPROTO_RAW :
+					 sk->sk_protocol),
+			.flowi4_flags = FLOWI_FLAG_CAN_SLEEP,
 		};
 		if (!inet->hdrincl) {
-			err = raw_probe_proto_opt(&fl, msg);
+			err = raw_probe_proto_opt(&fl4, msg);
 			if (err)
 				goto done;
 		}
 
-		security_sk_classify_flow(sk, &fl);
-		rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+		security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt)) {
 			err = PTR_ERR(rt);
 			goto done;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9e938f95cea8..5655095a89e0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2626,7 +2626,7 @@ out:
 	return rth;
 }
 
-struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
+struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *flp4)
 {
 	struct rtable *rth;
 	unsigned int hash;
@@ -2634,17 +2634,17 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
 	if (!rt_caching(net))
 		goto slow_output;
 
-	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->flowi_oif, rt_genid(net));
+	hash = rt_hash(flp4->daddr, flp4->saddr, flp4->flowi4_oif, rt_genid(net));
 
 	rcu_read_lock_bh();
 	for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
 		rth = rcu_dereference_bh(rth->dst.rt_next)) {
-		if (rth->rt_key_dst == flp->fl4_dst &&
-		    rth->rt_key_src == flp->fl4_src &&
+		if (rth->rt_key_dst == flp4->daddr &&
+		    rth->rt_key_src == flp4->saddr &&
 		    rt_is_output_route(rth) &&
-		    rth->rt_oif == flp->flowi_oif &&
-		    rth->rt_mark == flp->flowi_mark &&
-		    !((rth->rt_tos ^ flp->fl4_tos) &
+		    rth->rt_oif == flp4->flowi4_oif &&
+		    rth->rt_mark == flp4->flowi4_mark &&
+		    !((rth->rt_tos ^ flp4->flowi4_tos) &
 			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
@@ -2658,7 +2658,7 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
 	rcu_read_unlock_bh();
 
 slow_output:
-	return ip_route_output_slow(net, &flp->u.ip4);
+	return ip_route_output_slow(net, flp4);
 }
 EXPORT_SYMBOL_GPL(__ip_route_output_key);
 
@@ -2733,20 +2733,22 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 	return rt ? &rt->dst : ERR_PTR(-ENOMEM);
 }
 
-struct rtable *ip_route_output_flow(struct net *net, struct flowi *flp,
+struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 				    struct sock *sk)
 {
-	struct rtable *rt = __ip_route_output_key(net, flp);
+	struct rtable *rt = __ip_route_output_key(net, flp4);
 
 	if (IS_ERR(rt))
 		return rt;
 
-	if (flp->flowi_proto) {
-		if (!flp->fl4_src)
-			flp->fl4_src = rt->rt_src;
-		if (!flp->fl4_dst)
-			flp->fl4_dst = rt->rt_dst;
-		rt = (struct rtable *) xfrm_lookup(net, &rt->dst, flp, sk, 0);
+	if (flp4->flowi4_proto) {
+		if (!flp4->saddr)
+			flp4->saddr = rt->rt_src;
+		if (!flp4->daddr)
+			flp4->daddr = rt->rt_dst;
+		rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
+						   flowi4_to_flowi(flp4),
+						   sk, 0);
 	}
 
 	return rt;
@@ -2920,7 +2922,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 			.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
 			.flowi4_mark = mark,
 		};
-		rt = ip_route_output_key(net, flowi4_to_flowi(&fl4));
+		rt = ip_route_output_key(net, &fl4);
 
 		err = 0;
 		if (IS_ERR(rt))
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index d90529d45ee6..e3b5b754311c 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -345,19 +345,19 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * no easy way to do this.
 	 */
 	{
-		struct flowi fl = {
-			.flowi_mark = sk->sk_mark,
-			.fl4_dst = ((opt && opt->srr) ?
-				    opt->faddr : ireq->rmt_addr),
-			.fl4_src = ireq->loc_addr,
-			.fl4_tos = RT_CONN_FLAGS(sk),
-			.flowi_proto = IPPROTO_TCP,
-			.flowi_flags = inet_sk_flowi_flags(sk),
-			.fl4_sport = th->dest,
-			.fl4_dport = th->source,
+		struct flowi4 fl4 = {
+			.flowi4_mark = sk->sk_mark,
+			.daddr = ((opt && opt->srr) ?
+				  opt->faddr : ireq->rmt_addr),
+			.saddr = ireq->loc_addr,
+			.flowi4_tos = RT_CONN_FLAGS(sk),
+			.flowi4_proto = IPPROTO_TCP,
+			.flowi4_flags = inet_sk_flowi_flags(sk),
+			.uli.ports.sport = th->dest,
+			.uli.ports.dport = th->source,
 		};
-		security_req_classify_flow(req, &fl);
-		rt = ip_route_output_key(sock_net(sk), &fl);
+		security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+		rt = ip_route_output_key(sock_net(sk), &fl4);
 		if (IS_ERR(rt)) {
 			reqsk_free(req);
 			goto out;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 116e4a8bfb73..25c080798bd0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -908,22 +908,22 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		rt = (struct rtable *)sk_dst_check(sk, 0);
 
 	if (rt == NULL) {
-		struct flowi fl = {
-			.flowi_oif = ipc.oif,
-			.flowi_mark = sk->sk_mark,
-			.fl4_dst = faddr,
-			.fl4_src = saddr,
-			.fl4_tos = tos,
-			.flowi_proto = sk->sk_protocol,
-			.flowi_flags = (inet_sk_flowi_flags(sk) |
-				     FLOWI_FLAG_CAN_SLEEP),
-			.fl4_sport = inet->inet_sport,
-			.fl4_dport = dport,
+		struct flowi4 fl4 = {
+			.flowi4_oif = ipc.oif,
+			.flowi4_mark = sk->sk_mark,
+			.daddr = faddr,
+			.saddr = saddr,
+			.flowi4_tos = tos,
+			.flowi4_proto = sk->sk_protocol,
+			.flowi4_flags = (inet_sk_flowi_flags(sk) |
+					 FLOWI_FLAG_CAN_SLEEP),
+			.uli.ports.sport = inet->inet_sport,
+			.uli.ports.dport = dport,
 		};
 		struct net *net = sock_net(sk);
 
-		security_sk_classify_flow(sk, &fl);
-		rt = ip_route_output_flow(net, &fl, sk);
+		security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+		rt = ip_route_output_flow(net, &fl4, sk);
 		if (IS_ERR(rt)) {
 			err = PTR_ERR(rt);
 			rt = NULL;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index b7b0921b425d..b111f468fa29 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -22,16 +22,16 @@ static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
 					  const xfrm_address_t *saddr,
 					  const xfrm_address_t *daddr)
 {
-	struct flowi fl = {
-		.fl4_dst = daddr->a4,
-		.fl4_tos = tos,
+	struct flowi4 fl4 = {
+		.daddr = daddr->a4,
+		.flowi4_tos = tos,
 	};
 	struct rtable *rt;
 
 	if (saddr)
-		fl.fl4_src = saddr->a4;
+		fl4.saddr = saddr->a4;
 
-	rt = __ip_route_output_key(net, &fl);
+	rt = __ip_route_output_key(net, &fl4);
 	if (!IS_ERR(rt))
 		return &rt->dst;
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index cc8071f68903..7dc00e313611 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -165,14 +165,14 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 			return 0;
 		refdst_drop(orefdst);
 	} else {
-		struct flowi fl = {
-			.fl4_dst = iph->daddr,
-			.fl4_src = iph->saddr,
-			.fl4_tos = RT_TOS(iph->tos),
-			.flowi_mark = skb->mark,
+		struct flowi4 fl4 = {
+			.daddr = iph->daddr,
+			.saddr = iph->saddr,
+			.flowi4_tos = RT_TOS(iph->tos),
+			.flowi4_mark = skb->mark,
 		};
 
-		rt = ip_route_output_key(net, &fl);
+		rt = ip_route_output_key(net, &fl4);
 		if (IS_ERR(rt))
 			return 0;
 		if (!(rt->rt_flags & RTCF_LOCAL)) {
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index cb14ae2de15d..d8c00f9342ae 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -62,18 +62,18 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct net *net = pick_net(skb);
 	struct rtable *rt;
-	struct flowi fl;
+	struct flowi4 fl4;
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl4, 0, sizeof(fl4));
 	if (info->priv) {
 		if (info->priv->oif == -1)
 			return false;
-		fl.flowi_oif = info->priv->oif;
+		fl4.flowi4_oif = info->priv->oif;
 	}
-	fl.fl4_dst = info->gw.ip;
-	fl.fl4_tos = RT_TOS(iph->tos);
-	fl.fl4_scope = RT_SCOPE_UNIVERSE;
-	rt = ip_route_output_key(net, &fl);
+	fl4.daddr = info->gw.ip;
+	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		return false;
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index b6fa2940e30b..31c04568b23c 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -468,30 +468,30 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 					 union sctp_addr *saddr)
 {
 	struct rtable *rt;
-	struct flowi fl;
+	struct flowi4 fl4;
 	struct sctp_bind_addr *bp;
 	struct sctp_sockaddr_entry *laddr;
 	struct dst_entry *dst = NULL;
 	union sctp_addr dst_saddr;
 
-	memset(&fl, 0x0, sizeof(struct flowi));
-	fl.fl4_dst  = daddr->v4.sin_addr.s_addr;
-	fl.fl4_dport = daddr->v4.sin_port;
-	fl.flowi_proto = IPPROTO_SCTP;
+	memset(&fl4, 0x0, sizeof(struct flowi4));
+	fl4.daddr  = daddr->v4.sin_addr.s_addr;
+	fl4.uli.ports.dport = daddr->v4.sin_port;
+	fl4.flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
-		fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk);
-		fl.flowi_oif = asoc->base.sk->sk_bound_dev_if;
-		fl.fl4_sport = htons(asoc->base.bind_addr.port);
+		fl4.flowi4_tos = RT_CONN_FLAGS(asoc->base.sk);
+		fl4.flowi4_oif = asoc->base.sk->sk_bound_dev_if;
+		fl4.uli.ports.sport = htons(asoc->base.bind_addr.port);
 	}
 	if (saddr) {
-		fl.fl4_src = saddr->v4.sin_addr.s_addr;
-		fl.fl4_sport = saddr->v4.sin_port;
+		fl4.saddr = saddr->v4.sin_addr.s_addr;
+		fl4.uli.ports.sport = saddr->v4.sin_port;
 	}
 
 	SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ",
-			  __func__, &fl.fl4_dst, &fl.fl4_src);
+			  __func__, &fl4.daddr, &fl4.saddr);
 
-	rt = ip_route_output_key(&init_net, &fl);
+	rt = ip_route_output_key(&init_net, &fl4);
 	if (!IS_ERR(rt))
 		dst = &rt->dst;
 
@@ -533,9 +533,9 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 			continue;
 		if ((laddr->state == SCTP_ADDR_SRC) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
-			fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
-			fl.fl4_sport = laddr->a.v4.sin_port;
-			rt = ip_route_output_key(&init_net, &fl);
+			fl4.saddr = laddr->a.v4.sin_addr.s_addr;
+			fl4.uli.ports.sport = laddr->a.v4.sin_port;
+			rt = ip_route_output_key(&init_net, &fl4);
 			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
 				goto out_unlock;
-- 
cgit v1.2.3


From 2032656e76b5355151effdff14de4a1a58643915 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 02:30:50 -0500
Subject: net: Add flowi6_* member helper macros.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 3e4630ebde32..8d5b402d600a 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -65,6 +65,14 @@ struct flowi4 {
 
 struct flowi6 {
 	struct flowi_common	__fl_common;
+#define flowi6_oif		__fl_common.flowic_oif
+#define flowi6_iif		__fl_common.flowic_iif
+#define flowi6_mark		__fl_common.flowic_mark
+#define flowi6_tos		__fl_common.flowic_tos
+#define flowi6_scope		__fl_common.flowic_scope
+#define flowi6_proto		__fl_common.flowic_proto
+#define flowi6_flags		__fl_common.flowic_flags
+#define flowi6_secid		__fl_common.flowic_secid
 	struct in6_addr		daddr;
 	struct in6_addr		saddr;
 	__be32			flowlabel;
-- 
cgit v1.2.3


From 7e1dc7b6f709dfc1a9ab4b320dbe723f45992693 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 02:42:11 -0500
Subject: net: Use flowi4 and flowi6 in xfrm layer.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h      | 24 ++++++++++++------------
 net/ipv4/xfrm4_policy.c | 46 ++++++++++++++++++++++++----------------------
 net/ipv4/xfrm4_state.c  | 14 ++++++++------
 net/ipv6/xfrm6_policy.c | 39 +++++++++++++++++++++------------------
 net/ipv6/xfrm6_state.c  | 14 ++++++++------
 net/xfrm/xfrm_policy.c  | 28 ++++++++++++++++------------
 6 files changed, 89 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index aa860add570b..8f8bd82606bf 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1142,9 +1142,9 @@ xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family)
 {
 	switch (family){
 	case AF_INET:
-		return (xfrm_address_t *)&fl->fl4_dst;
+		return (xfrm_address_t *)&fl->u.ip4.daddr;
 	case AF_INET6:
-		return (xfrm_address_t *)&fl->fl6_dst;
+		return (xfrm_address_t *)&fl->u.ip6.daddr;
 	}
 	return NULL;
 }
@@ -1154,9 +1154,9 @@ xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family)
 {
 	switch (family){
 	case AF_INET:
-		return (xfrm_address_t *)&fl->fl4_src;
+		return (xfrm_address_t *)&fl->u.ip4.saddr;
 	case AF_INET6:
-		return (xfrm_address_t *)&fl->fl6_src;
+		return (xfrm_address_t *)&fl->u.ip6.saddr;
 	}
 	return NULL;
 }
@@ -1168,12 +1168,12 @@ void xfrm_flowi_addr_get(const struct flowi *fl,
 {
 	switch(family) {
 	case AF_INET:
-		memcpy(&saddr->a4, &fl->fl4_src, sizeof(saddr->a4));
-		memcpy(&daddr->a4, &fl->fl4_dst, sizeof(daddr->a4));
+		memcpy(&saddr->a4, &fl->u.ip4.saddr, sizeof(saddr->a4));
+		memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4));
 		break;
 	case AF_INET6:
-		ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->fl6_src);
-		ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->fl6_dst);
+		ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->u.ip6.saddr);
+		ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->u.ip6.daddr);
 		break;
 	}
 }
@@ -1221,12 +1221,12 @@ xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl,
 	switch (family) {
 	case AF_INET:
 		return __xfrm4_state_addr_check(x,
-						(const xfrm_address_t *)&fl->fl4_dst,
-						(const xfrm_address_t *)&fl->fl4_src);
+						(const xfrm_address_t *)&fl->u.ip4.daddr,
+						(const xfrm_address_t *)&fl->u.ip4.saddr);
 	case AF_INET6:
 		return __xfrm6_state_addr_check(x,
-						(const xfrm_address_t *)&fl->fl6_dst,
-						(const xfrm_address_t *)&fl->fl6_src);
+						(const xfrm_address_t *)&fl->u.ip6.daddr,
+						(const xfrm_address_t *)&fl->u.ip6.saddr);
 	}
 	return 0;
 }
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index b111f468fa29..30b312c577bc 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -56,7 +56,7 @@ static int xfrm4_get_saddr(struct net *net,
 
 static int xfrm4_get_tos(const struct flowi *fl)
 {
-	return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */
+	return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; /* Strip ECN bits */
 }
 
 static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
@@ -69,13 +69,14 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 			  const struct flowi *fl)
 {
 	struct rtable *rt = (struct rtable *)xdst->route;
+	const struct flowi4 *fl4 = &fl->u.ip4;
 
-	rt->rt_key_dst = fl->fl4_dst;
-	rt->rt_key_src = fl->fl4_src;
-	rt->rt_tos = fl->fl4_tos;
-	rt->rt_iif = fl->flowi_iif;
-	rt->rt_oif = fl->flowi_oif;
-	rt->rt_mark = fl->flowi_mark;
+	rt->rt_key_dst = fl4->daddr;
+	rt->rt_key_src = fl4->saddr;
+	rt->rt_tos = fl4->flowi4_tos;
+	rt->rt_iif = fl4->flowi4_iif;
+	rt->rt_oif = fl4->flowi4_oif;
+	rt->rt_mark = fl4->flowi4_mark;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);
@@ -102,9 +103,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
 	struct iphdr *iph = ip_hdr(skb);
 	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+	struct flowi4 *fl4 = &fl->u.ip4;
 
-	memset(fl, 0, sizeof(struct flowi));
-	fl->flowi_mark = skb->mark;
+	memset(fl4, 0, sizeof(struct flowi4));
+	fl4->flowi4_mark = skb->mark;
 
 	if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) {
 		switch (iph->protocol) {
@@ -117,8 +119,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ports = (__be16 *)xprth;
 
-				fl->fl4_sport = ports[!!reverse];
-				fl->fl4_dport = ports[!reverse];
+				fl4->uli.ports.sport = ports[!!reverse];
+				fl4->uli.ports.dport = ports[!reverse];
 			}
 			break;
 
@@ -126,8 +128,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
 				u8 *icmp = xprth;
 
-				fl->fl4_icmp_type = icmp[0];
-				fl->fl4_icmp_code = icmp[1];
+				fl4->uli.icmpt.type = icmp[0];
+				fl4->uli.icmpt.code = icmp[1];
 			}
 			break;
 
@@ -135,7 +137,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be32 *ehdr = (__be32 *)xprth;
 
-				fl->fl4_ipsec_spi = ehdr[0];
+				fl4->uli.spi = ehdr[0];
 			}
 			break;
 
@@ -143,7 +145,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
 				__be32 *ah_hdr = (__be32*)xprth;
 
-				fl->fl4_ipsec_spi = ah_hdr[1];
+				fl4->uli.spi = ah_hdr[1];
 			}
 			break;
 
@@ -151,7 +153,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ipcomp_hdr = (__be16 *)xprth;
 
-				fl->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
+				fl4->uli.spi = htonl(ntohs(ipcomp_hdr[1]));
 			}
 			break;
 
@@ -163,20 +165,20 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 				if (greflags[0] & GRE_KEY) {
 					if (greflags[0] & GRE_CSUM)
 						gre_hdr++;
-					fl->fl4_gre_key = gre_hdr[1];
+					fl4->uli.gre_key = gre_hdr[1];
 				}
 			}
 			break;
 
 		default:
-			fl->fl4_ipsec_spi = 0;
+			fl4->uli.spi = 0;
 			break;
 		}
 	}
-	fl->flowi_proto = iph->protocol;
-	fl->fl4_dst = reverse ? iph->saddr : iph->daddr;
-	fl->fl4_src = reverse ? iph->daddr : iph->saddr;
-	fl->fl4_tos = iph->tos;
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
 }
 
 static inline int xfrm4_garbage_collect(struct dst_ops *ops)
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index d8d541954532..1717c64628d1 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -23,17 +23,19 @@ static int xfrm4_init_flags(struct xfrm_state *x)
 static void
 __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 {
-	sel->daddr.a4 = fl->fl4_dst;
-	sel->saddr.a4 = fl->fl4_src;
-	sel->dport = xfrm_flowi_dport(fl, &fl->u.ip4.uli);
+	const struct flowi4 *fl4 = &fl->u.ip4;
+
+	sel->daddr.a4 = fl4->daddr;
+	sel->saddr.a4 = fl4->saddr;
+	sel->dport = xfrm_flowi_dport(fl, &fl4->uli);
 	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl, &fl->u.ip4.uli);
+	sel->sport = xfrm_flowi_sport(fl, &fl4->uli);
 	sel->sport_mask = htons(0xffff);
 	sel->family = AF_INET;
 	sel->prefixlen_d = 32;
 	sel->prefixlen_s = 32;
-	sel->proto = fl->flowi_proto;
-	sel->ifindex = fl->flowi_oif;
+	sel->proto = fl4->flowi4_proto;
+	sel->ifindex = fl4->flowi4_oif;
 }
 
 static void
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 213c7594144b..254aa6d79506 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -30,15 +30,17 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
 					  const xfrm_address_t *saddr,
 					  const xfrm_address_t *daddr)
 {
-	struct flowi fl = {};
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int err;
 
-	memcpy(&fl.fl6_dst, daddr, sizeof(fl.fl6_dst));
+	memset(&fl6, 0, sizeof(fl6));
+	memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
 	if (saddr)
-		memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src));
+		memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
 
-	dst = ip6_route_output(net, NULL, &fl);
+	dst = ip6_route_output(net, NULL,
+			       flowi6_to_flowi(&fl6));
 
 	err = dst->error;
 	if (dst->error) {
@@ -120,6 +122,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 static inline void
 _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
+	struct flowi6 *fl6 = &fl->u.ip6;
 	int onlyproto = 0;
 	u16 offset = skb_network_header_len(skb);
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -127,11 +130,11 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 	const unsigned char *nh = skb_network_header(skb);
 	u8 nexthdr = nh[IP6CB(skb)->nhoff];
 
-	memset(fl, 0, sizeof(struct flowi));
-	fl->flowi_mark = skb->mark;
+	memset(fl6, 0, sizeof(struct flowi6));
+	fl6->flowi6_mark = skb->mark;
 
-	ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr);
-	ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr);
+	ipv6_addr_copy(&fl6->daddr, reverse ? &hdr->saddr : &hdr->daddr);
+	ipv6_addr_copy(&fl6->saddr, reverse ? &hdr->daddr : &hdr->saddr);
 
 	while (nh + offset + 1 < skb->data ||
 	       pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
@@ -158,20 +161,20 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
 				__be16 *ports = (__be16 *)exthdr;
 
-				fl->fl6_sport = ports[!!reverse];
-				fl->fl6_dport = ports[!reverse];
+				fl6->uli.ports.sport = ports[!!reverse];
+				fl6->uli.ports.dport = ports[!reverse];
 			}
-			fl->flowi_proto = nexthdr;
+			fl6->flowi6_proto = nexthdr;
 			return;
 
 		case IPPROTO_ICMPV6:
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
 				u8 *icmp = (u8 *)exthdr;
 
-				fl->fl6_icmp_type = icmp[0];
-				fl->fl6_icmp_code = icmp[1];
+				fl6->uli.icmpt.type = icmp[0];
+				fl6->uli.icmpt.code = icmp[1];
 			}
-			fl->flowi_proto = nexthdr;
+			fl6->flowi6_proto = nexthdr;
 			return;
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
@@ -180,9 +183,9 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 				struct ip6_mh *mh;
 				mh = (struct ip6_mh *)exthdr;
 
-				fl->fl6_mh_type = mh->ip6mh_type;
+				fl6->uli.mht.type = mh->ip6mh_type;
 			}
-			fl->flowi_proto = nexthdr;
+			fl6->flowi6_proto = nexthdr;
 			return;
 #endif
 
@@ -191,8 +194,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 		case IPPROTO_ESP:
 		case IPPROTO_COMP:
 		default:
-			fl->fl6_ipsec_spi = 0;
-			fl->flowi_proto = nexthdr;
+			fl6->uli.spi = 0;
+			fl6->flowi6_proto = nexthdr;
 			return;
 		}
 	}
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index b456533a652d..afe941e9415c 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -22,19 +22,21 @@
 static void
 __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 {
+	const struct flowi6 *fl6 = &fl->u.ip6;
+
 	/* Initialize temporary selector matching only
 	 * to current session. */
-	ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
-	ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
-	sel->dport = xfrm_flowi_dport(fl, &fl->u.ip6.uli);
+	ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl6->daddr);
+	ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl6->saddr);
+	sel->dport = xfrm_flowi_dport(fl, &fl6->uli);
 	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl, &fl->u.ip6.uli);
+	sel->sport = xfrm_flowi_sport(fl, &fl6->uli);
 	sel->sport_mask = htons(0xffff);
 	sel->family = AF_INET6;
 	sel->prefixlen_d = 128;
 	sel->prefixlen_s = 128;
-	sel->proto = fl->flowi_proto;
-	sel->ifindex = fl->flowi_oif;
+	sel->proto = fl6->flowi6_proto;
+	sel->ifindex = fl6->flowi6_oif;
 }
 
 static void
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 2ecd18a106cf..1ba0258b49c7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -59,23 +59,27 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 static inline int
 __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
-	return  addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) &&
-		addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) &&
-		!((xfrm_flowi_dport(fl, &fl->u.ip4.uli) ^ sel->dport) & sel->dport_mask) &&
-		!((xfrm_flowi_sport(fl, &fl->u.ip4.uli) ^ sel->sport) & sel->sport_mask) &&
-		(fl->flowi_proto == sel->proto || !sel->proto) &&
-		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
+	const struct flowi4 *fl4 = &fl->u.ip4;
+
+	return  addr_match(&fl4->daddr, &sel->daddr, sel->prefixlen_d) &&
+		addr_match(&fl4->saddr, &sel->saddr, sel->prefixlen_s) &&
+		!((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
+		(fl4->flowi4_proto == sel->proto || !sel->proto) &&
+		(fl4->flowi4_oif == sel->ifindex || !sel->ifindex);
 }
 
 static inline int
 __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
-	return  addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) &&
-		addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) &&
-		!((xfrm_flowi_dport(fl, &fl->u.ip6.uli) ^ sel->dport) & sel->dport_mask) &&
-		!((xfrm_flowi_sport(fl, &fl->u.ip6.uli) ^ sel->sport) & sel->sport_mask) &&
-		(fl->flowi_proto == sel->proto || !sel->proto) &&
-		(fl->flowi_oif == sel->ifindex || !sel->ifindex);
+	const struct flowi6 *fl6 = &fl->u.ip6;
+
+	return  addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) &&
+		addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) &&
+		!((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) &&
+		!((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) &&
+		(fl6->flowi6_proto == sel->proto || !sel->proto) &&
+		(fl6->flowi6_oif == sel->ifindex || !sel->ifindex);
 }
 
 int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
-- 
cgit v1.2.3


From 9cce96df5b76691712dba22e83ff5efe900361e1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 03:00:33 -0500
Subject: net: Put fl4_* macros to struct flowi4 and use them again.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h                     | 18 +++++++-----------
 include/net/route.h                    | 14 +++++++-------
 net/dccp/ipv4.c                        |  4 ++--
 net/ipv4/icmp.c                        |  4 ++--
 net/ipv4/inet_connection_sock.c        |  4 ++--
 net/ipv4/ip_output.c                   |  4 ++--
 net/ipv4/netfilter/nf_nat_standalone.c |  4 ++--
 net/ipv4/raw.c                         |  4 ++--
 net/ipv4/syncookies.c                  |  4 ++--
 net/ipv4/udp.c                         | 10 +++++-----
 net/ipv4/xfrm4_policy.c                | 18 +++++++++---------
 net/sctp/protocol.c                    |  8 ++++----
 12 files changed, 46 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 8d5b402d600a..44bd37628f55 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -61,6 +61,13 @@ struct flowi4 {
 	__be32			daddr;
 	__be32			saddr;
 	union flowi_uli		uli;
+#define fl4_sport		uli.ports.sport
+#define fl4_dport		uli.ports.dport
+#define fl4_icmp_type		uli.icmpt.type
+#define fl4_icmp_code		uli.icmpt.code
+#define fl4_ipsec_spi		uli.spi
+#define fl4_mh_type		uli.mht.type
+#define fl4_gre_key		uli.gre_key
 };
 
 struct flowi6 {
@@ -101,8 +108,6 @@ struct flowi {
 #define flowi_proto	u.__fl_common.flowic_proto
 #define flowi_flags	u.__fl_common.flowic_flags
 #define flowi_secid	u.__fl_common.flowic_secid
-#define fl4_tos		flowi_tos
-#define fl4_scope	flowi_scope
 #define fld_scope	flowi_scope
 
 #define fld_dst		u.dn.daddr
@@ -110,15 +115,6 @@ struct flowi {
 #define fl6_dst		u.ip6.daddr
 #define fl6_src		u.ip6.saddr
 #define fl6_flowlabel	u.ip6.flowlabel
-#define fl4_dst		u.ip4.daddr
-#define fl4_src		u.ip4.saddr
-#define fl4_sport	u.ip4.uli.ports.sport
-#define fl4_dport	u.ip4.uli.ports.dport
-#define fl4_icmp_type	u.ip4.uli.icmpt.type
-#define fl4_icmp_code	u.ip4.uli.icmpt.code
-#define fl4_ipsec_spi	u.ip4.uli.spi
-#define fl4_mh_type	u.ip4.uli.mht.type
-#define fl4_gre_key	u.ip4.uli.gre_key
 #define fl6_sport	u.ip6.uli.ports.sport
 #define fl6_dport	u.ip6.uli.ports.dport
 #define fl6_icmp_type	u.ip6.uli.icmpt.type
diff --git a/include/net/route.h b/include/net/route.h
index 80b0353f4f41..30d6cae3841a 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -157,8 +157,8 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct sock
 		.saddr = saddr,
 		.flowi4_tos = tos,
 		.flowi4_proto = proto,
-		.uli.ports.dport = dport,
-		.uli.ports.sport = sport,
+		.fl4_dport = dport,
+		.fl4_sport = sport,
 	};
 	if (sk)
 		security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
@@ -175,7 +175,7 @@ static inline struct rtable *ip_route_output_gre(struct net *net,
 		.saddr = saddr,
 		.flowi4_tos = tos,
 		.flowi4_proto = IPPROTO_GRE,
-		.uli.gre_key = gre_key,
+		.fl4_gre_key = gre_key,
 	};
 	return ip_route_output_key(net, &fl4);
 }
@@ -235,8 +235,8 @@ static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos,
 		.saddr = src,
 		.flowi4_tos = tos,
 		.flowi4_proto = protocol,
-		.uli.ports.sport = sport,
-		.uli.ports.dport = dport,
+		.fl4_sport = sport,
+		.fl4_dport = dport,
 	};
 	struct net *net = sock_net(sk);
 	struct rtable *rt;
@@ -273,8 +273,8 @@ static inline struct rtable *ip_route_newports(struct rtable *rt,
 			.saddr = rt->rt_key_src,
 			.flowi4_tos = rt->rt_tos,
 			.flowi4_proto = protocol,
-			.uli.ports.sport = sport,
-			.uli.ports.dport = dport
+			.fl4_sport = sport,
+			.fl4_dport = dport
 		};
 		if (inet_sk(sk)->transparent)
 			fl4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index be984706126b..ae451c6d83ba 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -471,8 +471,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 		.saddr = ip_hdr(skb)->daddr,
 		.flowi4_tos = RT_CONN_FLAGS(sk),
 		.flowi4_proto = sk->sk_protocol,
-		.uli.ports.sport = dccp_hdr(skb)->dccph_dport,
-		.uli.ports.dport = dccp_hdr(skb)->dccph_sport,
+		.fl4_sport = dccp_hdr(skb)->dccph_dport,
+		.fl4_dport = dccp_hdr(skb)->dccph_sport,
 	};
 
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8eca3c28cbc3..a91dc1611081 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -384,8 +384,8 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 		.saddr = saddr,
 		.flowi4_tos = RT_TOS(tos),
 		.flowi4_proto = IPPROTO_ICMP,
-		.uli.icmpt.type = type,
-		.uli.icmpt.code = code,
+		.fl4_icmp_type = type,
+		.fl4_icmp_code = code,
 	};
 	struct rtable *rt, *rt2;
 	int err;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index beecc1272169..6c0b7f4a3d7d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -365,8 +365,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 		.flowi4_tos = RT_CONN_FLAGS(sk),
 		.flowi4_proto = sk->sk_protocol,
 		.flowi4_flags = inet_sk_flowi_flags(sk),
-		.uli.ports.sport = inet_sk(sk)->inet_sport,
-		.uli.ports.dport = ireq->rmt_port,
+		.fl4_sport = inet_sk(sk)->inet_sport,
+		.fl4_dport = ireq->rmt_port,
 	};
 	struct net *net = sock_net(sk);
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 2b9cc40397ee..67f241b97649 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1479,8 +1479,8 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 			.daddr = daddr,
 			.saddr = rt->rt_spec_dst,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
-			.uli.ports.sport = tcp_hdr(skb)->dest,
-			.uli.ports.dport = tcp_hdr(skb)->source,
+			.fl4_sport = tcp_hdr(skb)->dest,
+			.fl4_dport = tcp_hdr(skb)->source,
 			.flowi4_proto = sk->sk_protocol,
 			.flowi4_flags = ip_reply_arg_flowi_flags(arg),
 		};
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 963320b295e2..7317bdf1d457 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -56,7 +56,7 @@ static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 		    t->dst.protonum == IPPROTO_UDPLITE ||
 		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
-			fl4->uli.ports.dport = t->dst.u.tcp.port;
+			fl4->fl4_dport = t->dst.u.tcp.port;
 	}
 
 	statusbit ^= IPS_NAT_MASK;
@@ -68,7 +68,7 @@ static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
 		    t->dst.protonum == IPPROTO_UDPLITE ||
 		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
-			fl4->uli.ports.sport = t->src.u.tcp.port;
+			fl4->fl4_sport = t->src.u.tcp.port;
 	}
 }
 #endif
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 452e178d962d..e837ffd3edc3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -433,8 +433,8 @@ static int raw_probe_proto_opt(struct flowi4 *fl4, struct msghdr *msg)
 				code = iov->iov_base;
 
 			if (type && code) {
-				if (get_user(fl4->uli.icmpt.type, type) ||
-				    get_user(fl4->uli.icmpt.code, code))
+				if (get_user(fl4->fl4_icmp_type, type) ||
+				    get_user(fl4->fl4_icmp_code, code))
 					return -EFAULT;
 				probed = 1;
 			}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e3b5b754311c..8b44c6d2a79b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -353,8 +353,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			.flowi4_tos = RT_CONN_FLAGS(sk),
 			.flowi4_proto = IPPROTO_TCP,
 			.flowi4_flags = inet_sk_flowi_flags(sk),
-			.uli.ports.sport = th->dest,
-			.uli.ports.dport = th->source,
+			.fl4_sport = th->dest,
+			.fl4_dport = th->source,
 		};
 		security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 		rt = ip_route_output_key(sock_net(sk), &fl4);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 91cba3ca37c4..588f47af5faf 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -778,7 +778,7 @@ static int udp_push_pending_frames(struct sock *sk)
 	if (!skb)
 		goto out;
 
-	err = udp_send_skb(skb, fl4->daddr, fl4->uli.ports.dport);
+	err = udp_send_skb(skb, fl4->daddr, fl4->fl4_dport);
 
 out:
 	up->len = 0;
@@ -918,8 +918,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			.flowi4_proto = sk->sk_protocol,
 			.flowi4_flags = (inet_sk_flowi_flags(sk) |
 					 FLOWI_FLAG_CAN_SLEEP),
-			.uli.ports.sport = inet->inet_sport,
-			.uli.ports.dport = dport,
+			.fl4_sport = inet->inet_sport,
+			.fl4_dport = dport,
 		};
 		struct net *net = sock_net(sk);
 
@@ -976,8 +976,8 @@ back_from_confirm:
 	fl4 = &inet->cork.fl.u.ip4;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
-	fl4->uli.ports.dport = dport;
-	fl4->uli.ports.sport = inet->inet_sport;
+	fl4->fl4_dport = dport;
+	fl4->fl4_sport = inet->inet_sport;
 	up->pending = AF_INET;
 
 do_append_data:
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 30b312c577bc..13e0e7f659ff 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -119,8 +119,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ports = (__be16 *)xprth;
 
-				fl4->uli.ports.sport = ports[!!reverse];
-				fl4->uli.ports.dport = ports[!reverse];
+				fl4->fl4_sport = ports[!!reverse];
+				fl4->fl4_dport = ports[!reverse];
 			}
 			break;
 
@@ -128,8 +128,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
 				u8 *icmp = xprth;
 
-				fl4->uli.icmpt.type = icmp[0];
-				fl4->uli.icmpt.code = icmp[1];
+				fl4->fl4_icmp_type = icmp[0];
+				fl4->fl4_icmp_code = icmp[1];
 			}
 			break;
 
@@ -137,7 +137,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be32 *ehdr = (__be32 *)xprth;
 
-				fl4->uli.spi = ehdr[0];
+				fl4->fl4_ipsec_spi = ehdr[0];
 			}
 			break;
 
@@ -145,7 +145,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
 				__be32 *ah_hdr = (__be32*)xprth;
 
-				fl4->uli.spi = ah_hdr[1];
+				fl4->fl4_ipsec_spi = ah_hdr[1];
 			}
 			break;
 
@@ -153,7 +153,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ipcomp_hdr = (__be16 *)xprth;
 
-				fl4->uli.spi = htonl(ntohs(ipcomp_hdr[1]));
+				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
 			}
 			break;
 
@@ -165,13 +165,13 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 				if (greflags[0] & GRE_KEY) {
 					if (greflags[0] & GRE_CSUM)
 						gre_hdr++;
-					fl4->uli.gre_key = gre_hdr[1];
+					fl4->fl4_gre_key = gre_hdr[1];
 				}
 			}
 			break;
 
 		default:
-			fl4->uli.spi = 0;
+			fl4->fl4_ipsec_spi = 0;
 			break;
 		}
 	}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 31c04568b23c..152976ec0b74 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -476,16 +476,16 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 
 	memset(&fl4, 0x0, sizeof(struct flowi4));
 	fl4.daddr  = daddr->v4.sin_addr.s_addr;
-	fl4.uli.ports.dport = daddr->v4.sin_port;
+	fl4.fl4_dport = daddr->v4.sin_port;
 	fl4.flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
 		fl4.flowi4_tos = RT_CONN_FLAGS(asoc->base.sk);
 		fl4.flowi4_oif = asoc->base.sk->sk_bound_dev_if;
-		fl4.uli.ports.sport = htons(asoc->base.bind_addr.port);
+		fl4.fl4_sport = htons(asoc->base.bind_addr.port);
 	}
 	if (saddr) {
 		fl4.saddr = saddr->v4.sin_addr.s_addr;
-		fl4.uli.ports.sport = saddr->v4.sin_port;
+		fl4.fl4_sport = saddr->v4.sin_port;
 	}
 
 	SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ",
@@ -534,7 +534,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
 		if ((laddr->state == SCTP_ADDR_SRC) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
 			fl4.saddr = laddr->a.v4.sin_addr.s_addr;
-			fl4.uli.ports.sport = laddr->a.v4.sin_port;
+			fl4.fl4_sport = laddr->a.v4.sin_port;
 			rt = ip_route_output_key(&init_net, &fl4);
 			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
-- 
cgit v1.2.3


From 4c9483b2fb5d2548c3cc1fe03cdd4484ceeb5d1c Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 16:22:43 -0500
Subject: ipv6: Convert to use flowi6 where applicable.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c   |  18 +++---
 drivers/net/cnic.c               |  12 ++--
 include/linux/icmpv6.h           |   4 +-
 include/net/ip6_fib.h            |   4 +-
 include/net/ip6_route.h          |   2 +-
 include/net/ipv6.h               |  16 ++---
 include/net/transp_v6.h          |   4 +-
 net/dccp/ipv6.c                  | 132 +++++++++++++++++++--------------------
 net/ipv6/af_inet6.c              |  32 +++++-----
 net/ipv6/datagram.c              |  75 +++++++++++-----------
 net/ipv6/exthdrs.c               |  12 ++--
 net/ipv6/fib6_rules.c            |  19 +++---
 net/ipv6/icmp.c                  | 110 ++++++++++++++++----------------
 net/ipv6/inet6_connection_sock.c |  60 +++++++++---------
 net/ipv6/ip6_fib.c               |   4 +-
 net/ipv6/ip6_flowlabel.c         |   6 +-
 net/ipv6/ip6_output.c            |  90 +++++++++++++-------------
 net/ipv6/ip6_tunnel.c            |  50 +++++++--------
 net/ipv6/ip6mr.c                 |  53 ++++++++--------
 net/ipv6/ipv6_sockglue.c         |  10 +--
 net/ipv6/mcast.c                 |  12 ++--
 net/ipv6/mip6.c                  |  13 ++--
 net/ipv6/ndisc.c                 |  14 ++---
 net/ipv6/netfilter.c             |  18 +++---
 net/ipv6/netfilter/ip6t_REJECT.c |  20 +++---
 net/ipv6/raw.c                   |  79 ++++++++++++-----------
 net/ipv6/route.c                 |  96 ++++++++++++++--------------
 net/ipv6/syncookies.c            |  26 ++++----
 net/ipv6/tcp_ipv6.c              | 114 ++++++++++++++++-----------------
 net/ipv6/udp.c                   |  76 +++++++++++-----------
 net/ipv6/xfrm6_policy.c          |   3 +-
 net/netfilter/ipvs/ip_vs_ctl.c   |  10 ++-
 net/netfilter/ipvs/ip_vs_xmit.c  |  14 ++---
 net/netfilter/xt_TEE.c           |  12 ++--
 net/sctp/ipv6.c                  |  42 ++++++-------
 35 files changed, 632 insertions(+), 630 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 3c2b309ab891..e0ef5fdc361e 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -231,28 +231,28 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 			 struct sockaddr_in6 *dst_in,
 			 struct rdma_dev_addr *addr)
 {
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct neighbour *neigh;
 	struct dst_entry *dst;
 	int ret;
 
-	memset(&fl, 0, sizeof fl);
-	ipv6_addr_copy(&fl.fl6_dst, &dst_in->sin6_addr);
-	ipv6_addr_copy(&fl.fl6_src, &src_in->sin6_addr);
-	fl.flowi_oif = addr->bound_dev_if;
+	memset(&fl6, 0, sizeof fl6);
+	ipv6_addr_copy(&fl6.daddr, &dst_in->sin6_addr);
+	ipv6_addr_copy(&fl6.saddr, &src_in->sin6_addr);
+	fl6.flowi6_oif = addr->bound_dev_if;
 
-	dst = ip6_route_output(&init_net, NULL, &fl);
+	dst = ip6_route_output(&init_net, NULL, &fl6);
 	if ((ret = dst->error))
 		goto put;
 
-	if (ipv6_addr_any(&fl.fl6_src)) {
+	if (ipv6_addr_any(&fl6.saddr)) {
 		ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev,
-					 &fl.fl6_dst, 0, &fl.fl6_src);
+					 &fl6.daddr, 0, &fl6.saddr);
 		if (ret)
 			goto put;
 
 		src_in->sin6_family = AF_INET6;
-		ipv6_addr_copy(&src_in->sin6_addr, &fl.fl6_src);
+		ipv6_addr_copy(&src_in->sin6_addr, &fl6.saddr);
 	}
 
 	if (dst->dev->flags & IFF_LOOPBACK) {
diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c
index c8922f69705e..8cca60e43444 100644
--- a/drivers/net/cnic.c
+++ b/drivers/net/cnic.c
@@ -3424,14 +3424,14 @@ static int cnic_get_v6_route(struct sockaddr_in6 *dst_addr,
 			     struct dst_entry **dst)
 {
 #if defined(CONFIG_IPV6) || (defined(CONFIG_IPV6_MODULE) && defined(MODULE))
-	struct flowi fl;
+	struct flowi6 fl6;
 
-	memset(&fl, 0, sizeof(fl));
-	ipv6_addr_copy(&fl.fl6_dst, &dst_addr->sin6_addr);
-	if (ipv6_addr_type(&fl.fl6_dst) & IPV6_ADDR_LINKLOCAL)
-		fl.flowi_oif = dst_addr->sin6_scope_id;
+	memset(&fl6, 0, sizeof(fl6));
+	ipv6_addr_copy(&fl6.daddr, &dst_addr->sin6_addr);
+	if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
+		fl6.flowi6_oif = dst_addr->sin6_scope_id;
 
-	*dst = ip6_route_output(&init_net, NULL, &fl);
+	*dst = ip6_route_output(&init_net, NULL, &fl6);
 	if (*dst)
 		return 0;
 #endif
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 4c4c74ec5987..ba45e6bc0764 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -183,10 +183,10 @@ extern void				icmpv6_cleanup(void);
 extern void				icmpv6_param_prob(struct sk_buff *skb,
 							  u8 code, int pos);
 
-struct flowi;
+struct flowi6;
 struct in6_addr;
 extern void				icmpv6_flow_init(struct sock *sk,
-							 struct flowi *fl,
+							 struct flowi6 *fl6,
 							 u8 type,
 							 const struct in6_addr *saddr,
 							 const struct in6_addr *daddr,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 46a6e8ae232c..bc3cde0a810c 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -183,7 +183,7 @@ struct fib6_table {
 
 typedef struct rt6_info *(*pol_lookup_t)(struct net *,
 					 struct fib6_table *,
-					 struct flowi *, int);
+					 struct flowi6 *, int);
 
 /*
  *	exported functions
@@ -192,7 +192,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *,
 extern struct fib6_table        *fib6_get_table(struct net *net, u32 id);
 extern struct fib6_table        *fib6_new_table(struct net *net, u32 id);
 extern struct dst_entry         *fib6_rule_lookup(struct net *net,
-						  struct flowi *fl, int flags,
+						  struct flowi6 *fl6, int flags,
 						  pol_lookup_t lookup);
 
 extern struct fib6_node		*fib6_lookup(struct fib6_node *root,
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 8552f0a2e854..642a80bb42cf 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -71,7 +71,7 @@ extern void			ip6_route_input(struct sk_buff *skb);
 
 extern struct dst_entry *	ip6_route_output(struct net *net,
 						 struct sock *sk,
-						 struct flowi *fl);
+						 struct flowi6 *fl6);
 
 extern int			ip6_route_init(void);
 extern void			ip6_route_cleanup(void);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4635a5c80967..34200f9e6805 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -492,7 +492,7 @@ extern int			ip6_rcv_finish(struct sk_buff *skb);
  */
 extern int			ip6_xmit(struct sock *sk,
 					 struct sk_buff *skb,
-					 struct flowi *fl,
+					 struct flowi6 *fl6,
 					 struct ipv6_txoptions *opt);
 
 extern int			ip6_nd_hdr(struct sock *sk,
@@ -512,7 +512,7 @@ extern int			ip6_append_data(struct sock *sk,
 		      				int hlimit,
 		      				int tclass,
 						struct ipv6_txoptions *opt,
-						struct flowi *fl,
+						struct flowi6 *fl6,
 						struct rt6_info *rt,
 						unsigned int flags,
 						int dontfrag);
@@ -523,13 +523,13 @@ extern void			ip6_flush_pending_frames(struct sock *sk);
 
 extern int			ip6_dst_lookup(struct sock *sk,
 					       struct dst_entry **dst,
-					       struct flowi *fl);
+					       struct flowi6 *fl6);
 extern struct dst_entry *	ip6_dst_lookup_flow(struct sock *sk,
-						    struct flowi *fl,
+						    struct flowi6 *fl6,
 						    const struct in6_addr *final_dst,
 						    bool can_sleep);
 extern struct dst_entry *	ip6_sk_dst_lookup_flow(struct sock *sk,
-						       struct flowi *fl,
+						       struct flowi6 *fl6,
 						       const struct in6_addr *final_dst,
 						       bool can_sleep);
 extern struct dst_entry *	ip6_blackhole_route(struct net *net,
@@ -566,7 +566,7 @@ extern int 			ipv6_ext_hdr(u8 nexthdr);
 
 extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type);
 
-extern struct in6_addr *fl6_update_dst(struct flowi *fl,
+extern struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
 				       const struct ipv6_txoptions *opt,
 				       struct in6_addr *orig);
 
@@ -600,8 +600,8 @@ extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
 extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
 extern void			ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 						u32 info, u8 *payload);
-extern void			ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info);
-extern void			ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu);
+extern void			ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
+extern void			ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
 
 extern int inet6_release(struct socket *sock);
 extern int inet6_bind(struct socket *sock, struct sockaddr *uaddr, 
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index 42a0eb68b7b6..eeb077dd735f 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -14,7 +14,7 @@ extern struct proto udpv6_prot;
 extern struct proto udplitev6_prot;
 extern struct proto tcpv6_prot;
 
-struct flowi;
+struct flowi6;
 
 /* extention headers */
 extern int				ipv6_exthdrs_init(void);
@@ -42,7 +42,7 @@ extern int			datagram_recv_ctl(struct sock *sk,
 
 extern int			datagram_send_ctl(struct net *net,
 						  struct msghdr *msg,
-						  struct flowi *fl,
+						  struct flowi6 *fl6,
 						  struct ipv6_txoptions *opt,
 						  int *hlimit, int *tclass,
 						  int *dontfrag);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 2b351c6da49a..8d26c122de64 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -147,22 +147,22 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		dst = __sk_dst_check(sk, np->dst_cookie);
 		if (dst == NULL) {
 			struct inet_sock *inet = inet_sk(sk);
-			struct flowi fl;
+			struct flowi6 fl6;
 
 			/* BUGGG_FUTURE: Again, it is not clear how
 			   to handle rthdr case. Ignore this complexity
 			   for now.
 			 */
-			memset(&fl, 0, sizeof(fl));
-			fl.flowi_proto = IPPROTO_DCCP;
-			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-			fl.flowi_oif = sk->sk_bound_dev_if;
-			fl.fl6_dport = inet->inet_dport;
-			fl.fl6_sport = inet->inet_sport;
-			security_sk_classify_flow(sk, &fl);
-
-			dst = ip6_dst_lookup_flow(sk, &fl, NULL, false);
+			memset(&fl6, 0, sizeof(fl6));
+			fl6.flowi6_proto = IPPROTO_DCCP;
+			ipv6_addr_copy(&fl6.daddr, &np->daddr);
+			ipv6_addr_copy(&fl6.saddr, &np->saddr);
+			fl6.flowi6_oif = sk->sk_bound_dev_if;
+			fl6.uli.ports.dport = inet->inet_dport;
+			fl6.uli.ports.sport = inet->inet_sport;
+			security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
 			if (IS_ERR(dst)) {
 				sk->sk_err_soft = -PTR_ERR(dst);
 				goto out;
@@ -243,25 +243,25 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 	struct sk_buff *skb;
 	struct ipv6_txoptions *opt = NULL;
 	struct in6_addr *final_p, final;
-	struct flowi fl;
+	struct flowi6 fl6;
 	int err = -1;
 	struct dst_entry *dst;
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = IPPROTO_DCCP;
-	ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
-	ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
-	fl.fl6_flowlabel = 0;
-	fl.flowi_oif = ireq6->iif;
-	fl.fl6_dport = inet_rsk(req)->rmt_port;
-	fl.fl6_sport = inet_rsk(req)->loc_port;
-	security_req_classify_flow(req, &fl);
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_DCCP;
+	ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+	ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+	fl6.flowlabel = 0;
+	fl6.flowi6_oif = ireq6->iif;
+	fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
+	fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 	opt = np->opt;
 
-	final_p = fl6_update_dst(&fl, opt, &final);
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
@@ -275,8 +275,8 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 		dh->dccph_checksum = dccp_v6_csum_finish(skb,
 							 &ireq6->loc_addr,
 							 &ireq6->rmt_addr);
-		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
-		err = ip6_xmit(sk, skb, &fl, opt);
+		ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+		err = ip6_xmit(sk, skb, &fl6, opt);
 		err = net_xmit_eval(err);
 	}
 
@@ -298,7 +298,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 {
 	struct ipv6hdr *rxip6h;
 	struct sk_buff *skb;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct net *net = dev_net(skb_dst(rxskb)->dev);
 	struct sock *ctl_sk = net->dccp.v6_ctl_sk;
 	struct dst_entry *dst;
@@ -317,21 +317,21 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 	dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr,
 							    &rxip6h->daddr);
 
-	memset(&fl, 0, sizeof(fl));
-	ipv6_addr_copy(&fl.fl6_dst, &rxip6h->saddr);
-	ipv6_addr_copy(&fl.fl6_src, &rxip6h->daddr);
+	memset(&fl6, 0, sizeof(fl6));
+	ipv6_addr_copy(&fl6.daddr, &rxip6h->saddr);
+	ipv6_addr_copy(&fl6.saddr, &rxip6h->daddr);
 
-	fl.flowi_proto = IPPROTO_DCCP;
-	fl.flowi_oif = inet6_iif(rxskb);
-	fl.fl6_dport = dccp_hdr(skb)->dccph_dport;
-	fl.fl6_sport = dccp_hdr(skb)->dccph_sport;
-	security_skb_classify_flow(rxskb, &fl);
+	fl6.flowi6_proto = IPPROTO_DCCP;
+	fl6.flowi6_oif = inet6_iif(rxskb);
+	fl6.uli.ports.dport = dccp_hdr(skb)->dccph_dport;
+	fl6.uli.ports.sport = dccp_hdr(skb)->dccph_sport;
+	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl, NULL, false);
+	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(skb, dst);
-		ip6_xmit(ctl_sk, skb, &fl, NULL);
+		ip6_xmit(ctl_sk, skb, &fl6, NULL);
 		DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
 		DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
 		return;
@@ -527,19 +527,19 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	if (dst == NULL) {
 		struct in6_addr *final_p, final;
-		struct flowi fl;
-
-		memset(&fl, 0, sizeof(fl));
-		fl.flowi_proto = IPPROTO_DCCP;
-		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
-		final_p = fl6_update_dst(&fl, opt, &final);
-		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
-		fl.flowi_oif = sk->sk_bound_dev_if;
-		fl.fl6_dport = inet_rsk(req)->rmt_port;
-		fl.fl6_sport = inet_rsk(req)->loc_port;
-		security_sk_classify_flow(sk, &fl);
-
-		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		struct flowi6 fl6;
+
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_DCCP;
+		ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+		final_p = fl6_update_dst(&fl6, opt, &final);
+		ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
+		fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
+		fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 		if (IS_ERR(dst))
 			goto out;
 	}
@@ -859,7 +859,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
 	int err;
@@ -872,14 +872,14 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (usin->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 
 	if (np->sndflow) {
-		fl.fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
-		IP6_ECN_flow_init(fl.fl6_flowlabel);
-		if (fl.fl6_flowlabel & IPV6_FLOWLABEL_MASK) {
+		fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
+		IP6_ECN_flow_init(fl6.flowlabel);
+		if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
 			struct ip6_flowlabel *flowlabel;
-			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
 			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
@@ -916,7 +916,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	}
 
 	ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
-	np->flow_label = fl.fl6_flowlabel;
+	np->flow_label = fl6.flowlabel;
 
 	/*
 	 * DCCP over IPv4
@@ -953,24 +953,24 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (!ipv6_addr_any(&np->rcv_saddr))
 		saddr = &np->rcv_saddr;
 
-	fl.flowi_proto = IPPROTO_DCCP;
-	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-	ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr);
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.fl6_dport = usin->sin6_port;
-	fl.fl6_sport = inet->inet_sport;
-	security_sk_classify_flow(sk, &fl);
+	fl6.flowi6_proto = IPPROTO_DCCP;
+	ipv6_addr_copy(&fl6.daddr, &np->daddr);
+	ipv6_addr_copy(&fl6.saddr, saddr ? saddr : &np->saddr);
+	fl6.flowi6_oif = sk->sk_bound_dev_if;
+	fl6.uli.ports.dport = usin->sin6_port;
+	fl6.uli.ports.sport = inet->inet_sport;
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl, np->opt, &final);
+	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
 	}
 
 	if (saddr == NULL) {
-		saddr = &fl.fl6_src;
+		saddr = &fl6.saddr;
 		ipv6_addr_copy(&np->rcv_saddr, saddr);
 	}
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 923febea8989..689eea6553fd 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -652,22 +652,22 @@ int inet6_sk_rebuild_header(struct sock *sk)
 	if (dst == NULL) {
 		struct inet_sock *inet = inet_sk(sk);
 		struct in6_addr *final_p, final;
-		struct flowi fl;
-
-		memset(&fl, 0, sizeof(fl));
-		fl.flowi_proto = sk->sk_protocol;
-		ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-		fl.fl6_flowlabel = np->flow_label;
-		fl.flowi_oif = sk->sk_bound_dev_if;
-		fl.flowi_mark = sk->sk_mark;
-		fl.fl6_dport = inet->inet_dport;
-		fl.fl6_sport = inet->inet_sport;
-		security_sk_classify_flow(sk, &fl);
-
-		final_p = fl6_update_dst(&fl, np->opt, &final);
-
-		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		struct flowi6 fl6;
+
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_proto = sk->sk_protocol;
+		ipv6_addr_copy(&fl6.daddr, &np->daddr);
+		ipv6_addr_copy(&fl6.saddr, &np->saddr);
+		fl6.flowlabel = np->flow_label;
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
+		fl6.flowi6_mark = sk->sk_mark;
+		fl6.uli.ports.dport = inet->inet_dport;
+		fl6.uli.ports.sport = inet->inet_sport;
+		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+		final_p = fl6_update_dst(&fl6, np->opt, &final);
+
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 		if (IS_ERR(dst)) {
 			sk->sk_route_caps = 0;
 			sk->sk_err_soft = -PTR_ERR(dst);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 07e03e68243b..04ae676d14ee 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,7 +40,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct ipv6_pinfo      	*np = inet6_sk(sk);
 	struct in6_addr		*daddr, *final_p, final;
 	struct dst_entry	*dst;
-	struct flowi		fl;
+	struct flowi6		fl6;
 	struct ip6_flowlabel	*flowlabel = NULL;
 	struct ipv6_txoptions   *opt;
 	int			addr_type;
@@ -59,11 +59,11 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (usin->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 	if (np->sndflow) {
-		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
-			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+		fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
+			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
 			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
@@ -137,7 +137,7 @@ ipv4_connected:
 	}
 
 	ipv6_addr_copy(&np->daddr, daddr);
-	np->flow_label = fl.fl6_flowlabel;
+	np->flow_label = fl6.flowlabel;
 
 	inet->inet_dport = usin->sin6_port;
 
@@ -146,23 +146,23 @@ ipv4_connected:
 	 *	destination cache for it.
 	 */
 
-	fl.flowi_proto = sk->sk_protocol;
-	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.flowi_mark = sk->sk_mark;
-	fl.fl6_dport = inet->inet_dport;
-	fl.fl6_sport = inet->inet_sport;
+	fl6.flowi6_proto = sk->sk_protocol;
+	ipv6_addr_copy(&fl6.daddr, &np->daddr);
+	ipv6_addr_copy(&fl6.saddr, &np->saddr);
+	fl6.flowi6_oif = sk->sk_bound_dev_if;
+	fl6.flowi6_mark = sk->sk_mark;
+	fl6.uli.ports.dport = inet->inet_dport;
+	fl6.uli.ports.sport = inet->inet_sport;
 
-	if (!fl.flowi_oif && (addr_type&IPV6_ADDR_MULTICAST))
-		fl.flowi_oif = np->mcast_oif;
+	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
+		fl6.flowi6_oif = np->mcast_oif;
 
-	security_sk_classify_flow(sk, &fl);
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 	opt = flowlabel ? flowlabel->opt : np->opt;
-	final_p = fl6_update_dst(&fl, opt, &final);
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
 	err = 0;
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -172,20 +172,20 @@ ipv4_connected:
 	/* source address lookup done in ip6_dst_lookup */
 
 	if (ipv6_addr_any(&np->saddr))
-		ipv6_addr_copy(&np->saddr, &fl.fl6_src);
+		ipv6_addr_copy(&np->saddr, &fl6.saddr);
 
 	if (ipv6_addr_any(&np->rcv_saddr)) {
-		ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
+		ipv6_addr_copy(&np->rcv_saddr, &fl6.saddr);
 		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 		if (sk->sk_prot->rehash)
 			sk->sk_prot->rehash(sk);
 	}
 
 	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
+		      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
 		      &np->daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
-		      ipv6_addr_equal(&fl.fl6_src, &np->saddr) ?
+		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
 		      &np->saddr :
 #endif
 		      NULL);
@@ -231,7 +231,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 		kfree_skb(skb);
 }
 
-void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
+void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
@@ -250,7 +250,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
 	skb_put(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
-	ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+	ipv6_addr_copy(&iph->daddr, &fl6->daddr);
 
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
@@ -261,7 +261,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
 	serr->ee.ee_info = info;
 	serr->ee.ee_data = 0;
 	serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb);
-	serr->port = fl->fl6_dport;
+	serr->port = fl6->uli.ports.dport;
 
 	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
 	skb_reset_transport_header(skb);
@@ -270,7 +270,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
 		kfree_skb(skb);
 }
 
-void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
+void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6hdr *iph;
@@ -287,7 +287,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
 	skb_put(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
-	ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+	ipv6_addr_copy(&iph->daddr, &fl6->daddr);
 
 	mtu_info = IP6CBMTU(skb);
 	if (!mtu_info) {
@@ -299,7 +299,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
 	mtu_info->ip6m_addr.sin6_family = AF_INET6;
 	mtu_info->ip6m_addr.sin6_port = 0;
 	mtu_info->ip6m_addr.sin6_flowinfo = 0;
-	mtu_info->ip6m_addr.sin6_scope_id = fl->flowi_oif;
+	mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif;
 	ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
 
 	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
@@ -593,7 +593,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 }
 
 int datagram_send_ctl(struct net *net,
-		      struct msghdr *msg, struct flowi *fl,
+		      struct msghdr *msg, struct flowi6 *fl6,
 		      struct ipv6_txoptions *opt,
 		      int *hlimit, int *tclass, int *dontfrag)
 {
@@ -629,16 +629,17 @@ int datagram_send_ctl(struct net *net,
 			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
 
 			if (src_info->ipi6_ifindex) {
-				if (fl->flowi_oif && src_info->ipi6_ifindex != fl->flowi_oif)
+				if (fl6->flowi6_oif &&
+				    src_info->ipi6_ifindex != fl6->flowi6_oif)
 					return -EINVAL;
-				fl->flowi_oif = src_info->ipi6_ifindex;
+				fl6->flowi6_oif = src_info->ipi6_ifindex;
 			}
 
 			addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
 
 			rcu_read_lock();
-			if (fl->flowi_oif) {
-				dev = dev_get_by_index_rcu(net, fl->flowi_oif);
+			if (fl6->flowi6_oif) {
+				dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
 				if (!dev) {
 					rcu_read_unlock();
 					return -ENODEV;
@@ -654,7 +655,7 @@ int datagram_send_ctl(struct net *net,
 						   strict ? dev : NULL, 0))
 					err = -EINVAL;
 				else
-					ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr);
+					ipv6_addr_copy(&fl6->saddr, &src_info->ipi6_addr);
 			}
 
 			rcu_read_unlock();
@@ -671,13 +672,13 @@ int datagram_send_ctl(struct net *net,
 				goto exit_f;
 			}
 
-			if (fl->fl6_flowlabel&IPV6_FLOWINFO_MASK) {
-				if ((fl->fl6_flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) {
+			if (fl6->flowlabel&IPV6_FLOWINFO_MASK) {
+				if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) {
 					err = -EINVAL;
 					goto exit_f;
 				}
 			}
-			fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg);
+			fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg);
 			break;
 
 		case IPV6_2292HOPOPTS:
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 262f105d23b9..79a485e8a700 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -876,22 +876,22 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
  * fl6_update_dst - update flowi destination address with info given
  *                  by srcrt option, if any.
  *
- * @fl: flowi for which fl6_dst is to be updated
+ * @fl6: flowi6 for which daddr is to be updated
  * @opt: struct ipv6_txoptions in which to look for srcrt opt
- * @orig: copy of original fl6_dst address if modified
+ * @orig: copy of original daddr address if modified
  *
  * Returns NULL if no txoptions or no srcrt, otherwise returns orig
- * and initial value of fl->fl6_dst set in orig
+ * and initial value of fl6->daddr set in orig
  */
-struct in6_addr *fl6_update_dst(struct flowi *fl,
+struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
 				const struct ipv6_txoptions *opt,
 				struct in6_addr *orig)
 {
 	if (!opt || !opt->srcrt)
 		return NULL;
 
-	ipv6_addr_copy(orig, &fl->fl6_dst);
-	ipv6_addr_copy(&fl->fl6_dst, ((struct rt0_hdr *)opt->srcrt)->addr);
+	ipv6_addr_copy(orig, &fl6->daddr);
+	ipv6_addr_copy(&fl6->daddr, ((struct rt0_hdr *)opt->srcrt)->addr);
 	return orig;
 }
 
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index d829874d8946..34d244df907d 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -29,7 +29,7 @@ struct fib6_rule
 	u8			tclass;
 };
 
-struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
 	struct fib_lookup_arg arg = {
@@ -37,7 +37,8 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
 		.flags = FIB_LOOKUP_NOREF,
 	};
 
-	fib_rules_lookup(net->ipv6.fib6_rules_ops, fl, flags, &arg);
+	fib_rules_lookup(net->ipv6.fib6_rules_ops,
+			 flowi6_to_flowi(fl6), flags, &arg);
 
 	if (arg.result)
 		return arg.result;
@@ -49,6 +50,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			    int flags, struct fib_lookup_arg *arg)
 {
+	struct flowi6 *flp6 = &flp->u.ip6;
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
 	struct net *net = rule->fr_net;
@@ -71,7 +73,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 	table = fib6_get_table(net, rule->table);
 	if (table)
-		rt = lookup(net, table, flp, flags);
+		rt = lookup(net, table, flp6, flags);
 
 	if (rt != net->ipv6.ip6_null_entry) {
 		struct fib6_rule *r = (struct fib6_rule *)rule;
@@ -86,14 +88,14 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 			if (ipv6_dev_get_saddr(net,
 					       ip6_dst_idev(&rt->dst)->dev,
-					       &flp->fl6_dst,
+					       &flp6->daddr,
 					       rt6_flags2srcprefs(flags),
 					       &saddr))
 				goto again;
 			if (!ipv6_prefix_equal(&saddr, &r->src.addr,
 					       r->src.plen))
 				goto again;
-			ipv6_addr_copy(&flp->fl6_src, &saddr);
+			ipv6_addr_copy(&flp6->saddr, &saddr);
 		}
 		goto out;
 	}
@@ -113,9 +115,10 @@ out:
 static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 {
 	struct fib6_rule *r = (struct fib6_rule *) rule;
+	struct flowi6 *fl6 = &fl->u.ip6;
 
 	if (r->dst.plen &&
-	    !ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen))
+	    !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen))
 		return 0;
 
 	/*
@@ -125,14 +128,14 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 	 */
 	if (r->src.plen) {
 		if (flags & RT6_LOOKUP_F_HAS_SADDR) {
-			if (!ipv6_prefix_equal(&fl->fl6_src, &r->src.addr,
+			if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr,
 					       r->src.plen))
 				return 0;
 		} else if (!(r->common.flags & FIB_RULE_FIND_SADDR))
 			return 0;
 	}
 
-	if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff))
+	if (r->tclass && r->tclass != ((ntohl(fl6->flowlabel) >> 20) & 0xff))
 		return 0;
 
 	return 1;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 52ff7aa1f9fc..f7b9041f7845 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -158,7 +158,7 @@ static int is_ineligible(struct sk_buff *skb)
  * Check the ICMP output rate limit
  */
 static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
-				      struct flowi *fl)
+				      struct flowi6 *fl6)
 {
 	struct dst_entry *dst;
 	struct net *net = sock_net(sk);
@@ -177,7 +177,7 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	 * XXX: perhaps the expire for routing entries cloned by
 	 * this lookup should be more aggressive (not longer than timeout).
 	 */
-	dst = ip6_route_output(net, sk, fl);
+	dst = ip6_route_output(net, sk, fl6);
 	if (dst->error) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst),
 			      IPSTATS_MIB_OUTNOROUTES);
@@ -217,7 +217,7 @@ static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset)
 	return (*op & 0xC0) == 0x80;
 }
 
-static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6hdr *thdr, int len)
+static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len)
 {
 	struct sk_buff *skb;
 	struct icmp6hdr *icmp6h;
@@ -233,9 +233,9 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct
 	if (skb_queue_len(&sk->sk_write_queue) == 1) {
 		skb->csum = csum_partial(icmp6h,
 					sizeof(struct icmp6hdr), skb->csum);
-		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
-						      &fl->fl6_dst,
-						      len, fl->flowi_proto,
+		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
+						      &fl6->daddr,
+						      len, fl6->flowi6_proto,
 						      skb->csum);
 	} else {
 		__wsum tmp_csum = 0;
@@ -246,9 +246,9 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct
 
 		tmp_csum = csum_partial(icmp6h,
 					sizeof(struct icmp6hdr), tmp_csum);
-		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
-						      &fl->fl6_dst,
-						      len, fl->flowi_proto,
+		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
+						      &fl6->daddr,
+						      len, fl6->flowi6_proto,
 						      tmp_csum);
 	}
 	ip6_push_pending_frames(sk);
@@ -301,13 +301,13 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {}
 #endif
 
 static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
-					     struct sock *sk, struct flowi *fl)
+					     struct sock *sk, struct flowi6 *fl6)
 {
 	struct dst_entry *dst, *dst2;
-	struct flowi fl2;
+	struct flowi6 fl2;
 	int err;
 
-	err = ip6_dst_lookup(sk, &dst, fl);
+	err = ip6_dst_lookup(sk, &dst, fl6);
 	if (err)
 		return ERR_PTR(err);
 
@@ -324,7 +324,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *sk
 	/* No need to clone since we're just using its address. */
 	dst2 = dst;
 
-	dst = xfrm_lookup(net, dst, fl, sk, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0);
 	if (!IS_ERR(dst)) {
 		if (dst != dst2)
 			return dst;
@@ -335,7 +335,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *sk
 			return dst;
 	}
 
-	err = xfrm_decode_session_reverse(skb, &fl2, AF_INET6);
+	err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
 	if (err)
 		goto relookup_failed;
 
@@ -343,7 +343,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *sk
 	if (err)
 		goto relookup_failed;
 
-	dst2 = xfrm_lookup(net, dst2, &fl2, sk, XFRM_LOOKUP_ICMP);
+	dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP);
 	if (!IS_ERR(dst2)) {
 		dst_release(dst);
 		dst = dst2;
@@ -375,7 +375,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	struct in6_addr *saddr = NULL;
 	struct dst_entry *dst;
 	struct icmp6hdr tmp_hdr;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct icmpv6_msg msg;
 	int iif = 0;
 	int addr_type = 0;
@@ -442,22 +442,22 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 
 	mip6_addr_swap(skb);
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = IPPROTO_ICMPV6;
-	ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_ICMPV6;
+	ipv6_addr_copy(&fl6.daddr, &hdr->saddr);
 	if (saddr)
-		ipv6_addr_copy(&fl.fl6_src, saddr);
-	fl.flowi_oif = iif;
-	fl.fl6_icmp_type = type;
-	fl.fl6_icmp_code = code;
-	security_skb_classify_flow(skb, &fl);
+		ipv6_addr_copy(&fl6.saddr, saddr);
+	fl6.flowi6_oif = iif;
+	fl6.uli.icmpt.type = type;
+	fl6.uli.icmpt.code = code;
+	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
 	if (sk == NULL)
 		return;
 	np = inet6_sk(sk);
 
-	if (!icmpv6_xrlim_allow(sk, type, &fl))
+	if (!icmpv6_xrlim_allow(sk, type, &fl6))
 		goto out;
 
 	tmp_hdr.icmp6_type = type;
@@ -465,14 +465,14 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	tmp_hdr.icmp6_cksum = 0;
 	tmp_hdr.icmp6_pointer = htonl(info);
 
-	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst))
-		fl.flowi_oif = np->mcast_oif;
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+		fl6.flowi6_oif = np->mcast_oif;
 
-	dst = icmpv6_route_lookup(net, skb, sk, &fl);
+	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
 	if (IS_ERR(dst))
 		goto out;
 
-	if (ipv6_addr_is_multicast(&fl.fl6_dst))
+	if (ipv6_addr_is_multicast(&fl6.daddr))
 		hlimit = np->mcast_hops;
 	else
 		hlimit = np->hop_limit;
@@ -495,14 +495,14 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
 			      len + sizeof(struct icmp6hdr),
 			      sizeof(struct icmp6hdr), hlimit,
-			      np->tclass, NULL, &fl, (struct rt6_info*)dst,
+			      np->tclass, NULL, &fl6, (struct rt6_info*)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
 		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 		goto out_put;
 	}
-	err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, len + sizeof(struct icmp6hdr));
+	err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr));
 
 out_put:
 	if (likely(idev != NULL))
@@ -524,7 +524,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct in6_addr *saddr = NULL;
 	struct icmp6hdr *icmph = icmp6_hdr(skb);
 	struct icmp6hdr tmp_hdr;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct icmpv6_msg msg;
 	struct dst_entry *dst;
 	int err = 0;
@@ -538,31 +538,31 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
 	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = IPPROTO_ICMPV6;
-	ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr);
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_ICMPV6;
+	ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr);
 	if (saddr)
-		ipv6_addr_copy(&fl.fl6_src, saddr);
-	fl.flowi_oif = skb->dev->ifindex;
-	fl.fl6_icmp_type = ICMPV6_ECHO_REPLY;
-	security_skb_classify_flow(skb, &fl);
+		ipv6_addr_copy(&fl6.saddr, saddr);
+	fl6.flowi6_oif = skb->dev->ifindex;
+	fl6.uli.icmpt.type = ICMPV6_ECHO_REPLY;
+	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
 	if (sk == NULL)
 		return;
 	np = inet6_sk(sk);
 
-	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst))
-		fl.flowi_oif = np->mcast_oif;
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+		fl6.flowi6_oif = np->mcast_oif;
 
-	err = ip6_dst_lookup(sk, &dst, &fl);
+	err = ip6_dst_lookup(sk, &dst, &fl6);
 	if (err)
 		goto out;
-	dst = xfrm_lookup(net, dst, &fl, sk, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
 	if (IS_ERR(dst))
 		goto out;
 
-	if (ipv6_addr_is_multicast(&fl.fl6_dst))
+	if (ipv6_addr_is_multicast(&fl6.daddr))
 		hlimit = np->mcast_hops;
 	else
 		hlimit = np->hop_limit;
@@ -576,7 +576,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	msg.type = ICMPV6_ECHO_REPLY;
 
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
-				sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl,
+				sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6,
 				(struct rt6_info*)dst, MSG_DONTWAIT,
 				np->dontfrag);
 
@@ -585,7 +585,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		ip6_flush_pending_frames(sk);
 		goto out_put;
 	}
-	err = icmpv6_push_pending_frames(sk, &fl, &tmp_hdr, skb->len + sizeof(struct icmp6hdr));
+	err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr));
 
 out_put:
 	if (likely(idev != NULL))
@@ -784,20 +784,20 @@ drop_no_count:
 	return 0;
 }
 
-void icmpv6_flow_init(struct sock *sk, struct flowi *fl,
+void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
 		      u8 type,
 		      const struct in6_addr *saddr,
 		      const struct in6_addr *daddr,
 		      int oif)
 {
-	memset(fl, 0, sizeof(*fl));
-	ipv6_addr_copy(&fl->fl6_src, saddr);
-	ipv6_addr_copy(&fl->fl6_dst, daddr);
-	fl->flowi_proto	 	= IPPROTO_ICMPV6;
-	fl->fl6_icmp_type	= type;
-	fl->fl6_icmp_code	= 0;
-	fl->flowi_oif		= oif;
-	security_sk_classify_flow(sk, fl);
+	memset(fl6, 0, sizeof(*fl6));
+	ipv6_addr_copy(&fl6->saddr, saddr);
+	ipv6_addr_copy(&fl6->daddr, daddr);
+	fl6->flowi6_proto 	= IPPROTO_ICMPV6;
+	fl6->uli.icmpt.type	= type;
+	fl6->uli.icmpt.code	= 0;
+	fl6->flowi6_oif		= oif;
+	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 }
 
 /*
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 1b06a24019c6..27d669160ba6 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -61,20 +61,20 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *final_p, final;
 	struct dst_entry *dst;
-	struct flowi fl;
-
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
-	final_p = fl6_update_dst(&fl, np->opt, &final);
-	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.flowi_mark = sk->sk_mark;
-	fl.fl6_dport = inet_rsk(req)->rmt_port;
-	fl.fl6_sport = inet_rsk(req)->loc_port;
-	security_req_classify_flow(req, &fl);
-
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+	struct flowi6 fl6;
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
+	fl6.flowi6_oif = sk->sk_bound_dev_if;
+	fl6.flowi6_mark = sk->sk_mark;
+	fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
+	fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 	if (IS_ERR(dst))
 		return NULL;
 
@@ -208,28 +208,28 @@ int inet6_csk_xmit(struct sk_buff *skb)
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	struct in6_addr *final_p, final;
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = sk->sk_protocol;
-	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-	fl.fl6_flowlabel = np->flow_label;
-	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.flowi_mark = sk->sk_mark;
-	fl.fl6_sport = inet->inet_sport;
-	fl.fl6_dport = inet->inet_dport;
-	security_sk_classify_flow(sk, &fl);
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = sk->sk_protocol;
+	ipv6_addr_copy(&fl6.daddr, &np->daddr);
+	ipv6_addr_copy(&fl6.saddr, &np->saddr);
+	fl6.flowlabel = np->flow_label;
+	IP6_ECN_flow_xmit(sk, fl6.flowlabel);
+	fl6.flowi6_oif = sk->sk_bound_dev_if;
+	fl6.flowi6_mark = sk->sk_mark;
+	fl6.uli.ports.sport = inet->inet_sport;
+	fl6.uli.ports.dport = inet->inet_dport;
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl, np->opt, &final);
+	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 
 	if (dst == NULL) {
-		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 
 		if (IS_ERR(dst)) {
 			sk->sk_err_soft = -PTR_ERR(dst);
@@ -244,9 +244,9 @@ int inet6_csk_xmit(struct sk_buff *skb)
 	skb_dst_set(skb, dst_clone(dst));
 
 	/* Restore final destination back after routing done */
-	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
+	ipv6_addr_copy(&fl6.daddr, &np->daddr);
 
-	return ip6_xmit(sk, skb, &fl, np->opt);
+	return ip6_xmit(sk, skb, &fl6, np->opt);
 }
 
 EXPORT_SYMBOL_GPL(inet6_csk_xmit);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index de382114609b..7548905e79e1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -260,10 +260,10 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id)
 	  return net->ipv6.fib6_main_tbl;
 }
 
-struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
-	return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags);
+	return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
 }
 
 static void __net_init fib6_tables_init(struct net *net)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index c8fa470b174b..f3caf1b8d572 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -342,7 +342,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
 
 	if (olen > 0) {
 		struct msghdr msg;
-		struct flowi flowi;
+		struct flowi6 flowi6;
 		int junk;
 
 		err = -ENOMEM;
@@ -358,9 +358,9 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
 
 		msg.msg_controllen = olen;
 		msg.msg_control = (void*)(fl->opt+1);
-		flowi.flowi_oif = 0;
+		memset(&flowi6, 0, sizeof(flowi6));
 
-		err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk,
+		err = datagram_send_ctl(net, &msg, &flowi6, fl->opt, &junk,
 					&junk, &junk);
 		if (err)
 			goto done;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3d0f2ac868a7..18208876aa8a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -174,15 +174,15 @@ int ip6_output(struct sk_buff *skb)
  *	xmit an sk_buff (used by TCP, SCTP and DCCP)
  */
 
-int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	     struct ipv6_txoptions *opt)
 {
 	struct net *net = sock_net(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct in6_addr *first_hop = &fl->fl6_dst;
+	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr;
-	u8  proto = fl->flowi_proto;
+	u8  proto = fl6->flowi6_proto;
 	int seg_len = skb->len;
 	int hlimit = -1;
 	int tclass = 0;
@@ -230,13 +230,13 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 
-	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;
+	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel;
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
 	hdr->hop_limit = hlimit;
 
-	ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
+	ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
 	ipv6_addr_copy(&hdr->daddr, first_hop);
 
 	skb->priority = sk->sk_priority;
@@ -879,7 +879,7 @@ static inline int ip6_rt_check(struct rt6key *rt_key,
 
 static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 					  struct dst_entry *dst,
-					  struct flowi *fl)
+					  struct flowi6 *fl6)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct rt6_info *rt = (struct rt6_info *)dst;
@@ -904,11 +904,11 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 	 *    sockets.
 	 * 2. oif also should be the same.
 	 */
-	if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) ||
+	if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) ||
 #ifdef CONFIG_IPV6_SUBTREES
-	    ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) ||
+	    ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
 #endif
-	    (fl->flowi_oif && fl->flowi_oif != dst->dev->ifindex)) {
+	    (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
 		dst_release(dst);
 		dst = NULL;
 	}
@@ -918,22 +918,22 @@ out:
 }
 
 static int ip6_dst_lookup_tail(struct sock *sk,
-			       struct dst_entry **dst, struct flowi *fl)
+			       struct dst_entry **dst, struct flowi6 *fl6)
 {
 	int err;
 	struct net *net = sock_net(sk);
 
 	if (*dst == NULL)
-		*dst = ip6_route_output(net, sk, fl);
+		*dst = ip6_route_output(net, sk, fl6);
 
 	if ((err = (*dst)->error))
 		goto out_err_release;
 
-	if (ipv6_addr_any(&fl->fl6_src)) {
+	if (ipv6_addr_any(&fl6->saddr)) {
 		err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev,
-					 &fl->fl6_dst,
+					 &fl6->daddr,
 					 sk ? inet6_sk(sk)->srcprefs : 0,
-					 &fl->fl6_src);
+					 &fl6->saddr);
 		if (err)
 			goto out_err_release;
 	}
@@ -949,10 +949,10 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	 */
 	if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
 		struct inet6_ifaddr *ifp;
-		struct flowi fl_gw;
+		struct flowi6 fl_gw6;
 		int redirect;
 
-		ifp = ipv6_get_ifaddr(net, &fl->fl6_src,
+		ifp = ipv6_get_ifaddr(net, &fl6->saddr,
 				      (*dst)->dev, 1);
 
 		redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
@@ -965,9 +965,9 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 			 * default router instead
 			 */
 			dst_release(*dst);
-			memcpy(&fl_gw, fl, sizeof(struct flowi));
-			memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
-			*dst = ip6_route_output(net, sk, &fl_gw);
+			memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
+			memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
+			*dst = ip6_route_output(net, sk, &fl_gw6);
 			if ((err = (*dst)->error))
 				goto out_err_release;
 		}
@@ -988,23 +988,23 @@ out_err_release:
  *	ip6_dst_lookup - perform route lookup on flow
  *	@sk: socket which provides route info
  *	@dst: pointer to dst_entry * for result
- *	@fl: flow to lookup
+ *	@fl6: flow to lookup
  *
  *	This function performs a route lookup on the given flow.
  *
  *	It returns zero on success, or a standard errno code on error.
  */
-int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
+int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6)
 {
 	*dst = NULL;
-	return ip6_dst_lookup_tail(sk, dst, fl);
+	return ip6_dst_lookup_tail(sk, dst, fl6);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup);
 
 /**
  *	ip6_dst_lookup_flow - perform route lookup on flow with ipsec
  *	@sk: socket which provides route info
- *	@fl: flow to lookup
+ *	@fl6: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
  *	@can_sleep: we are in a sleepable context
  *
@@ -1013,29 +1013,29 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	It returns a valid dst pointer on success, or a pointer encoded
  *	error code.
  */
-struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi *fl,
+struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst,
 				      bool can_sleep)
 {
 	struct dst_entry *dst = NULL;
 	int err;
 
-	err = ip6_dst_lookup_tail(sk, &dst, fl);
+	err = ip6_dst_lookup_tail(sk, &dst, fl6);
 	if (err)
 		return ERR_PTR(err);
 	if (final_dst)
-		ipv6_addr_copy(&fl->fl6_dst, final_dst);
+		ipv6_addr_copy(&fl6->daddr, final_dst);
 	if (can_sleep)
-		fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
+		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
-	return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
+	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
 
 /**
  *	ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow
  *	@sk: socket which provides the dst cache and route info
- *	@fl: flow to lookup
+ *	@fl6: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
  *	@can_sleep: we are in a sleepable context
  *
@@ -1047,24 +1047,24 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *	It returns a valid dst pointer on success, or a pointer encoded
  *	error code.
  */
-struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi *fl,
+struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst,
 					 bool can_sleep)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
 	int err;
 
-	dst = ip6_sk_dst_check(sk, dst, fl);
+	dst = ip6_sk_dst_check(sk, dst, fl6);
 
-	err = ip6_dst_lookup_tail(sk, &dst, fl);
+	err = ip6_dst_lookup_tail(sk, &dst, fl6);
 	if (err)
 		return ERR_PTR(err);
 	if (final_dst)
-		ipv6_addr_copy(&fl->fl6_dst, final_dst);
+		ipv6_addr_copy(&fl6->daddr, final_dst);
 	if (can_sleep)
-		fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
+		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
-	return xfrm_lookup(sock_net(sk), dst, fl, sk, 0);
+	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
@@ -1145,7 +1145,7 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
 int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	int offset, int len, int odd, struct sk_buff *skb),
 	void *from, int length, int transhdrlen,
-	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
+	int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
 	struct rt6_info *rt, unsigned int flags, int dontfrag)
 {
 	struct inet_sock *inet = inet_sk(sk);
@@ -1203,7 +1203,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		}
 		dst_hold(&rt->dst);
 		inet->cork.dst = &rt->dst;
-		inet->cork.fl = *fl;
+		inet->cork.fl.u.ip6 = *fl6;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
 		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
@@ -1224,7 +1224,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		transhdrlen += exthdrlen;
 	} else {
 		rt = (struct rt6_info *)inet->cork.dst;
-		fl = &inet->cork.fl;
+		fl6 = &inet->cork.fl.u.ip6;
 		opt = np->cork.opt;
 		transhdrlen = 0;
 		exthdrlen = 0;
@@ -1239,7 +1239,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
 		if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
-			ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
+			ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
 			return -EMSGSIZE;
 		}
 	}
@@ -1271,7 +1271,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	if (length > mtu) {
 		int proto = sk->sk_protocol;
 		if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
-			ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
+			ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
 			return -EMSGSIZE;
 		}
 
@@ -1516,8 +1516,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	struct ipv6hdr *hdr;
 	struct ipv6_txoptions *opt = np->cork.opt;
 	struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
-	struct flowi *fl = &inet->cork.fl;
-	unsigned char proto = fl->flowi_proto;
+	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+	unsigned char proto = fl6->flowi6_proto;
 	int err = 0;
 
 	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
@@ -1542,7 +1542,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (np->pmtudisc < IPV6_PMTUDISC_DO)
 		skb->local_df = 1;
 
-	ipv6_addr_copy(final_dst, &fl->fl6_dst);
+	ipv6_addr_copy(final_dst, &fl6->daddr);
 	__skb_pull(skb, skb_network_header_len(skb));
 	if (opt && opt->opt_flen)
 		ipv6_push_frag_opts(skb, opt, &proto);
@@ -1553,12 +1553,12 @@ int ip6_push_pending_frames(struct sock *sk)
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	*(__be32*)hdr = fl->fl6_flowlabel |
+	*(__be32*)hdr = fl6->flowlabel |
 		     htonl(0x60000000 | ((int)np->cork.tclass << 20));
 
 	hdr->hop_limit = np->cork.hop_limit;
 	hdr->nexthdr = proto;
-	ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
+	ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
 	ipv6_addr_copy(&hdr->daddr, final_dst);
 
 	skb->priority = sk->sk_priority;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index c3fc824c24d9..c1b1bd312df2 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -884,7 +884,7 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
 static int ip6_tnl_xmit2(struct sk_buff *skb,
 			 struct net_device *dev,
 			 __u8 dsfield,
-			 struct flowi *fl,
+			 struct flowi6 *fl6,
 			 int encap_limit,
 			 __u32 *pmtu)
 {
@@ -904,11 +904,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	if ((dst = ip6_tnl_dst_check(t)) != NULL)
 		dst_hold(dst);
 	else {
-		dst = ip6_route_output(net, NULL, fl);
+		dst = ip6_route_output(net, NULL, fl6);
 
 		if (dst->error)
 			goto tx_err_link_failure;
-		dst = xfrm_lookup(net, dst, fl, NULL, 0);
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0);
 		if (IS_ERR(dst)) {
 			err = PTR_ERR(dst);
 			dst = NULL;
@@ -963,7 +963,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 
 	skb->transport_header = skb->network_header;
 
-	proto = fl->flowi_proto;
+	proto = fl6->flowi6_proto;
 	if (encap_limit >= 0) {
 		init_tel_txopt(&opt, encap_limit);
 		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
@@ -971,13 +971,13 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
-	*(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000);
+	*(__be32*)ipv6h = fl6->flowlabel | htonl(0x60000000);
 	dsfield = INET_ECN_encapsulate(0, dsfield);
 	ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
 	ipv6h->hop_limit = t->parms.hop_limit;
 	ipv6h->nexthdr = proto;
-	ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src);
-	ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst);
+	ipv6_addr_copy(&ipv6h->saddr, &fl6->saddr);
+	ipv6_addr_copy(&ipv6h->daddr, &fl6->daddr);
 	nf_reset(skb);
 	pkt_len = skb->len;
 	err = ip6_local_out(skb);
@@ -1007,7 +1007,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct iphdr  *iph = ip_hdr(skb);
 	int encap_limit = -1;
-	struct flowi fl;
+	struct flowi6 fl6;
 	__u8 dsfield;
 	__u32 mtu;
 	int err;
@@ -1019,16 +1019,16 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
-	memcpy(&fl, &t->fl, sizeof (fl));
-	fl.flowi_proto = IPPROTO_IPIP;
+	memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
+	fl6.flowi6_proto = IPPROTO_IPIP;
 
 	dsfield = ipv4_get_dsfield(iph);
 
 	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
-		fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
+		fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
 					  & IPV6_TCLASS_MASK;
 
-	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
+	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu);
 	if (err != 0) {
 		/* XXX: send ICMP error even if DF is not set. */
 		if (err == -EMSGSIZE)
@@ -1047,7 +1047,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	int encap_limit = -1;
 	__u16 offset;
-	struct flowi fl;
+	struct flowi6 fl6;
 	__u8 dsfield;
 	__u32 mtu;
 	int err;
@@ -1069,16 +1069,16 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
-	memcpy(&fl, &t->fl, sizeof (fl));
-	fl.flowi_proto = IPPROTO_IPV6;
+	memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
+	fl6.flowi6_proto = IPPROTO_IPV6;
 
 	dsfield = ipv6_get_dsfield(ipv6h);
 	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
-		fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
+		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
 	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL))
-		fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
+		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
 
-	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
+	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu);
 	if (err != 0) {
 		if (err == -EMSGSIZE)
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -1141,21 +1141,21 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 {
 	struct net_device *dev = t->dev;
 	struct ip6_tnl_parm *p = &t->parms;
-	struct flowi *fl = &t->fl;
+	struct flowi6 *fl6 = &t->fl.u.ip6;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
 	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
 
 	/* Set up flowi template */
-	ipv6_addr_copy(&fl->fl6_src, &p->laddr);
-	ipv6_addr_copy(&fl->fl6_dst, &p->raddr);
-	fl->flowi_oif = p->link;
-	fl->fl6_flowlabel = 0;
+	ipv6_addr_copy(&fl6->saddr, &p->laddr);
+	ipv6_addr_copy(&fl6->daddr, &p->raddr);
+	fl6->flowi6_oif = p->link;
+	fl6->flowlabel = 0;
 
 	if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
-		fl->fl6_flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
+		fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
 	if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL))
-		fl->fl6_flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo;
+		fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo;
 
 	ip6_tnl_set_cap(t);
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 61a8be3ac4e4..7ff0343e05c7 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -135,14 +135,15 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 	return NULL;
 }
 
-static int ip6mr_fib_lookup(struct net *net, struct flowi *flp,
+static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr6_table **mrt)
 {
 	struct ip6mr_result res;
 	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
 
-	err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flp, 0, &arg);
+	err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
+			       flowi6_to_flowi(flp6), 0, &arg);
 	if (err < 0)
 		return err;
 	*mrt = res.mrt;
@@ -270,7 +271,7 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 	return net->ipv6.mrt6;
 }
 
-static int ip6mr_fib_lookup(struct net *net, struct flowi *flp,
+static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr6_table **mrt)
 {
 	*mrt = net->ipv6.mrt6;
@@ -617,9 +618,9 @@ static int pim6_rcv(struct sk_buff *skb)
 	struct net_device  *reg_dev = NULL;
 	struct net *net = dev_net(skb->dev);
 	struct mr6_table *mrt;
-	struct flowi fl = {
-		.flowi_iif	= skb->dev->ifindex,
-		.flowi_mark = skb->mark,
+	struct flowi6 fl6 = {
+		.flowi6_iif	= skb->dev->ifindex,
+		.flowi6_mark	= skb->mark,
 	};
 	int reg_vif_num;
 
@@ -644,7 +645,7 @@ static int pim6_rcv(struct sk_buff *skb)
 	    ntohs(encap->payload_len) + sizeof(*pim) > skb->len)
 		goto drop;
 
-	if (ip6mr_fib_lookup(net, &fl, &mrt) < 0)
+	if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
 		goto drop;
 	reg_vif_num = mrt->mroute_reg_vif_num;
 
@@ -687,14 +688,14 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 {
 	struct net *net = dev_net(dev);
 	struct mr6_table *mrt;
-	struct flowi fl = {
-		.flowi_oif		= dev->ifindex,
-		.flowi_iif		= skb->skb_iif,
-		.flowi_mark	= skb->mark,
+	struct flowi6 fl6 = {
+		.flowi6_oif	= dev->ifindex,
+		.flowi6_iif	= skb->skb_iif,
+		.flowi6_mark	= skb->mark,
 	};
 	int err;
 
-	err = ip6mr_fib_lookup(net, &fl, &mrt);
+	err = ip6mr_fib_lookup(net, &fl6, &mrt);
 	if (err < 0)
 		return err;
 
@@ -1547,13 +1548,13 @@ int ip6mr_sk_done(struct sock *sk)
 struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
 {
 	struct mr6_table *mrt;
-	struct flowi fl = {
-		.flowi_iif	= skb->skb_iif,
-		.flowi_oif	= skb->dev->ifindex,
-		.flowi_mark= skb->mark,
+	struct flowi6 fl6 = {
+		.flowi6_iif	= skb->skb_iif,
+		.flowi6_oif	= skb->dev->ifindex,
+		.flowi6_mark	= skb->mark,
 	};
 
-	if (ip6mr_fib_lookup(net, &fl, &mrt) < 0)
+	if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
 		return NULL;
 
 	return mrt->mroute6_sk;
@@ -1897,7 +1898,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
 	struct mif_device *vif = &mrt->vif6_table[vifi];
 	struct net_device *dev;
 	struct dst_entry *dst;
-	struct flowi fl;
+	struct flowi6 fl6;
 
 	if (vif->dev == NULL)
 		goto out_free;
@@ -1915,12 +1916,12 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
 
 	ipv6h = ipv6_hdr(skb);
 
-	fl = (struct flowi) {
-		.flowi_oif = vif->link,
-		.fl6_dst = ipv6h->daddr,
+	fl6 = (struct flowi6) {
+		.flowi6_oif = vif->link,
+		.daddr = ipv6h->daddr,
 	};
 
-	dst = ip6_route_output(net, NULL, &fl);
+	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst)
 		goto out_free;
 
@@ -2043,13 +2044,13 @@ int ip6_mr_input(struct sk_buff *skb)
 	struct mfc6_cache *cache;
 	struct net *net = dev_net(skb->dev);
 	struct mr6_table *mrt;
-	struct flowi fl = {
-		.flowi_iif	= skb->dev->ifindex,
-		.flowi_mark= skb->mark,
+	struct flowi6 fl6 = {
+		.flowi6_iif	= skb->dev->ifindex,
+		.flowi6_mark	= skb->mark,
 	};
 	int err;
 
-	err = ip6mr_fib_lookup(net, &fl, &mrt);
+	err = ip6mr_fib_lookup(net, &fl6, &mrt);
 	if (err < 0)
 		return err;
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 1448c507fdff..9cb191ecaba8 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -444,12 +444,12 @@ sticky_done:
 	{
 		struct ipv6_txoptions *opt = NULL;
 		struct msghdr msg;
-		struct flowi fl;
+		struct flowi6 fl6;
 		int junk;
 
-		fl.fl6_flowlabel = 0;
-		fl.flowi_oif = sk->sk_bound_dev_if;
-		fl.flowi_mark = sk->sk_mark;
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
+		fl6.flowi6_mark = sk->sk_mark;
 
 		if (optlen == 0)
 			goto update;
@@ -475,7 +475,7 @@ sticky_done:
 		msg.msg_controllen = optlen;
 		msg.msg_control = (void*)(opt+1);
 
-		retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk,
+		retv = datagram_send_ctl(net, &msg, &fl6, opt, &junk, &junk,
 					 &junk);
 		if (retv)
 			goto done;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index f2c9b6930ffc..76b893771e6e 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1396,7 +1396,7 @@ static void mld_sendpack(struct sk_buff *skb)
 	struct inet6_dev *idev;
 	struct net *net = dev_net(skb->dev);
 	int err;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 
 	rcu_read_lock();
@@ -1419,11 +1419,11 @@ static void mld_sendpack(struct sk_buff *skb)
 		goto err_out;
 	}
 
-	icmpv6_flow_init(net->ipv6.igmp_sk, &fl, ICMPV6_MLD2_REPORT,
+	icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT,
 			 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
 			 skb->dev->ifindex);
 
-	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 	err = 0;
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -1731,7 +1731,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 	u8 ra[8] = { IPPROTO_ICMPV6, 0,
 		     IPV6_TLV_ROUTERALERT, 2, 0, 0,
 		     IPV6_TLV_PADN, 0 };
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 
 	if (type == ICMPV6_MGM_REDUCTION)
@@ -1791,11 +1791,11 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 		goto err_out;
 	}
 
-	icmpv6_flow_init(sk, &fl, type,
+	icmpv6_flow_init(sk, &fl6, type,
 			 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
 			 skb->dev->ifindex);
 
-	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto err_out;
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index e1767aec3334..6a137355311c 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -208,14 +208,15 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 {
 	struct net *net = xs_net(x);
 	struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb;
+	const struct flowi6 *fl6 = &fl->u.ip6;
 	struct ipv6_destopt_hao *hao = NULL;
 	struct xfrm_selector sel;
 	int offset;
 	struct timeval stamp;
 	int err = 0;
 
-	if (unlikely(fl->flowi_proto == IPPROTO_MH &&
-		     fl->fl6_mh_type <= IP6_MH_TYPE_MAX))
+	if (unlikely(fl6->flowi6_proto == IPPROTO_MH &&
+		     fl6->uli.mht.type <= IP6_MH_TYPE_MAX))
 		goto out;
 
 	if (likely(opt->dsthao)) {
@@ -240,14 +241,14 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	       sizeof(sel.saddr));
 	sel.prefixlen_s = 128;
 	sel.family = AF_INET6;
-	sel.proto = fl->flowi_proto;
-	sel.dport = xfrm_flowi_dport(fl, &fl->u.ip6.uli);
+	sel.proto = fl6->flowi6_proto;
+	sel.dport = xfrm_flowi_dport(fl, &fl6->uli);
 	if (sel.dport)
 		sel.dport_mask = htons(~0);
-	sel.sport = xfrm_flowi_sport(fl, &fl->u.ip6.uli);
+	sel.sport = xfrm_flowi_sport(fl, &fl6->uli);
 	if (sel.sport)
 		sel.sport_mask = htons(~0);
-	sel.ifindex = fl->flowi_oif;
+	sel.ifindex = fl6->flowi6_oif;
 
 	err = km_report(net, IPPROTO_DSTOPTS, &sel,
 			(hao ? (xfrm_address_t *)&hao->addr : NULL));
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 9360d3be94f0..0e49c9db3c98 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -511,7 +511,7 @@ void ndisc_send_skb(struct sk_buff *skb,
 		    const struct in6_addr *saddr,
 		    struct icmp6hdr *icmp6h)
 {
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	struct net *net = dev_net(dev);
 	struct sock *sk = net->ipv6.ndisc_sk;
@@ -521,7 +521,7 @@ void ndisc_send_skb(struct sk_buff *skb,
 
 	type = icmp6h->icmp6_type;
 
-	icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex);
+	icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex);
 
 	dst = icmp6_dst_alloc(dev, neigh, daddr);
 	if (!dst) {
@@ -529,7 +529,7 @@ void ndisc_send_skb(struct sk_buff *skb,
 		return;
 	}
 
-	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 	if (IS_ERR(dst)) {
 		kfree_skb(skb);
 		return;
@@ -1515,7 +1515,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	struct rt6_info *rt;
 	struct dst_entry *dst;
 	struct inet6_dev *idev;
-	struct flowi fl;
+	struct flowi6 fl6;
 	u8 *opt;
 	int rd_len;
 	int err;
@@ -1535,14 +1535,14 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 		return;
 	}
 
-	icmpv6_flow_init(sk, &fl, NDISC_REDIRECT,
+	icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT,
 			 &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex);
 
-	dst = ip6_route_output(net, NULL, &fl);
+	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst == NULL)
 		return;
 
-	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 	if (IS_ERR(dst))
 		return;
 
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d282c62bc6f4..39aaca2b4fd2 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -15,14 +15,14 @@ int ip6_route_me_harder(struct sk_buff *skb)
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct dst_entry *dst;
-	struct flowi fl = {
-		.flowi_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
-		.flowi_mark = skb->mark,
-		.fl6_dst = iph->daddr,
-		.fl6_src = iph->saddr,
+	struct flowi6 fl6 = {
+		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
+		.flowi6_mark = skb->mark,
+		.daddr = iph->daddr,
+		.saddr = iph->saddr,
 	};
 
-	dst = ip6_route_output(net, skb->sk, &fl);
+	dst = ip6_route_output(net, skb->sk, &fl6);
 	if (dst->error) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
@@ -37,9 +37,9 @@ int ip6_route_me_harder(struct sk_buff *skb)
 
 #ifdef CONFIG_XFRM
 	if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
+	    xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
 		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
 		if (IS_ERR(dst))
 			return -1;
 		skb_dst_set(skb, dst);
@@ -92,7 +92,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 
 static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl)
 {
-	*dst = ip6_route_output(&init_net, NULL, fl);
+	*dst = ip6_route_output(&init_net, NULL, &fl->u.ip6);
 	return (*dst)->error;
 }
 
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index d1e905b7f563..df05511dea33 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -47,7 +47,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	struct ipv6hdr *ip6h;
 	struct dst_entry *dst = NULL;
 	u8 proto;
-	struct flowi fl;
+	struct flowi6 fl6;
 
 	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
 	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
@@ -89,19 +89,19 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 		return;
 	}
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr);
-	ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr);
-	fl.fl6_sport = otcph.dest;
-	fl.fl6_dport = otcph.source;
-	security_skb_classify_flow(oldskb, &fl);
-	dst = ip6_route_output(net, NULL, &fl);
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	ipv6_addr_copy(&fl6.saddr, &oip6h->daddr);
+	ipv6_addr_copy(&fl6.daddr, &oip6h->saddr);
+	fl6.uli.ports.sport = otcph.dest;
+	fl6.uli.ports.dport = otcph.source;
+	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst == NULL || dst->error) {
 		dst_release(dst);
 		return;
 	}
-	dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 	if (IS_ERR(dst))
 		return;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index d061465d6827..259f1b231038 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -524,7 +524,7 @@ csum_copy_err:
 	goto out;
 }
 
-static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
+static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 				     struct raw6_sock *rp)
 {
 	struct sk_buff *skb;
@@ -586,11 +586,10 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
 	if (unlikely(csum))
 		tmp_csum = csum_sub(tmp_csum, csum_unfold(csum));
 
-	csum = csum_ipv6_magic(&fl->fl6_src,
-				   &fl->fl6_dst,
-				   total_len, fl->flowi_proto, tmp_csum);
+	csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
+			       total_len, fl6->flowi6_proto, tmp_csum);
 
-	if (csum == 0 && fl->flowi_proto == IPPROTO_UDP)
+	if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP)
 		csum = CSUM_MANGLED_0;
 
 	if (skb_store_bits(skb, offset, &csum, 2))
@@ -603,7 +602,7 @@ out:
 }
 
 static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
-			struct flowi *fl, struct dst_entry **dstp,
+			struct flowi6 *fl6, struct dst_entry **dstp,
 			unsigned int flags)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -613,7 +612,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	struct rt6_info *rt = (struct rt6_info *)*dstp;
 
 	if (length > rt->dst.dev->mtu) {
-		ipv6_local_error(sk, EMSGSIZE, fl, rt->dst.dev->mtu);
+		ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
 	if (flags&MSG_PROBE)
@@ -662,7 +661,7 @@ error:
 	return err;
 }
 
-static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
 {
 	struct iovec *iov;
 	u8 __user *type = NULL;
@@ -679,7 +678,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 		if (!iov)
 			continue;
 
-		switch (fl->flowi_proto) {
+		switch (fl6->flowi6_proto) {
 		case IPPROTO_ICMPV6:
 			/* check if one-byte field is readable or not. */
 			if (iov->iov_base && iov->iov_len < 1)
@@ -694,8 +693,8 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 				code = iov->iov_base;
 
 			if (type && code) {
-				if (get_user(fl->fl6_icmp_type, type) ||
-				    get_user(fl->fl6_icmp_code, code))
+				if (get_user(fl6->uli.icmpt.type, type) ||
+				    get_user(fl6->uli.icmpt.code, code))
 					return -EFAULT;
 				probed = 1;
 			}
@@ -706,7 +705,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 			/* check if type field is readable or not. */
 			if (iov->iov_len > 2 - len) {
 				u8 __user *p = iov->iov_base;
-				if (get_user(fl->fl6_mh_type, &p[2 - len]))
+				if (get_user(fl6->uli.mht.type, &p[2 - len]))
 					return -EFAULT;
 				probed = 1;
 			} else
@@ -735,7 +734,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
-	struct flowi fl;
+	struct flowi6 fl6;
 	int addr_len = msg->msg_namelen;
 	int hlimit = -1;
 	int tclass = -1;
@@ -756,9 +755,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	/*
 	 *	Get and verify the address.
 	 */
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 
-	fl.flowi_mark = sk->sk_mark;
+	fl6.flowi6_mark = sk->sk_mark;
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
@@ -780,9 +779,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 		daddr = &sin6->sin6_addr;
 		if (np->sndflow) {
-			fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-			if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
-				flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+			fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+			if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
+				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 				if (flowlabel == NULL)
 					return -EINVAL;
 				daddr = &flowlabel->dst;
@@ -800,32 +799,32 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
 		    ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
-			fl.flowi_oif = sin6->sin6_scope_id;
+			fl6.flowi6_oif = sin6->sin6_scope_id;
 	} else {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
 		proto = inet->inet_num;
 		daddr = &np->daddr;
-		fl.fl6_flowlabel = np->flow_label;
+		fl6.flowlabel = np->flow_label;
 	}
 
-	if (fl.flowi_oif == 0)
-		fl.flowi_oif = sk->sk_bound_dev_if;
+	if (fl6.flowi6_oif == 0)
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+		err = datagram_send_ctl(sock_net(sk), msg, &fl6, opt, &hlimit,
 					&tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
 		}
-		if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
-			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+		if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
+			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
 		}
@@ -838,31 +837,31 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
 
-	fl.flowi_proto = proto;
-	err = rawv6_probe_proto_opt(&fl, msg);
+	fl6.flowi6_proto = proto;
+	err = rawv6_probe_proto_opt(&fl6, msg);
 	if (err)
 		goto out;
 
 	if (!ipv6_addr_any(daddr))
-		ipv6_addr_copy(&fl.fl6_dst, daddr);
+		ipv6_addr_copy(&fl6.daddr, daddr);
 	else
-		fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
-	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
-		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
+		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
+	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
+		ipv6_addr_copy(&fl6.saddr, &np->saddr);
 
-	final_p = fl6_update_dst(&fl, opt, &final);
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst))
-		fl.flowi_oif = np->mcast_oif;
-	security_sk_classify_flow(sk, &fl);
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+		fl6.flowi6_oif = np->mcast_oif;
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
 	}
 	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl.fl6_dst))
+		if (ipv6_addr_is_multicast(&fl6.daddr))
 			hlimit = np->mcast_hops;
 		else
 			hlimit = np->hop_limit;
@@ -881,17 +880,17 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 back_from_confirm:
 	if (inet->hdrincl)
-		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl, &dst, msg->msg_flags);
+		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags);
 	else {
 		lock_sock(sk);
 		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
-			len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
+			len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst,
 			msg->msg_flags, dontfrag);
 
 		if (err)
 			ip6_flush_pending_frames(sk);
 		else if (!(msg->msg_flags & MSG_MORE))
-			err = rawv6_push_pending_frames(sk, &fl, rp);
+			err = rawv6_push_pending_frames(sk, &fl6, rp);
 		release_sock(sk);
 	}
 done:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c3b20d63921f..6814c8722fa7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -599,17 +599,17 @@ do { \
 
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
-					     struct flowi *fl, int flags)
+					     struct flowi6 *fl6, int flags)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt;
 
 	read_lock_bh(&table->tb6_lock);
-	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	rt = fn->leaf;
-	rt = rt6_device_match(net, rt, &fl->fl6_src, fl->flowi_oif, flags);
-	BACKTRACK(net, &fl->fl6_src);
+	rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
+	BACKTRACK(net, &fl6->saddr);
 out:
 	dst_use(&rt->dst, jiffies);
 	read_unlock_bh(&table->tb6_lock);
@@ -620,19 +620,19 @@ out:
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif, int strict)
 {
-	struct flowi fl = {
-		.flowi_oif = oif,
-		.fl6_dst = *daddr,
+	struct flowi6 fl6 = {
+		.flowi6_oif = oif,
+		.daddr = *daddr,
 	};
 	struct dst_entry *dst;
 	int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
 
 	if (saddr) {
-		memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
+		memcpy(&fl6.saddr, saddr, sizeof(*saddr));
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 	}
 
-	dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_lookup);
+	dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup);
 	if (dst->error == 0)
 		return (struct rt6_info *) dst;
 
@@ -753,7 +753,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d
 }
 
 static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
-				      struct flowi *fl, int flags)
+				      struct flowi6 *fl6, int flags)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt, *nrt;
@@ -768,12 +768,12 @@ relookup:
 	read_lock_bh(&table->tb6_lock);
 
 restart_2:
-	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 
 restart:
 	rt = rt6_select(fn, oif, strict | reachable);
 
-	BACKTRACK(net, &fl->fl6_src);
+	BACKTRACK(net, &fl6->saddr);
 	if (rt == net->ipv6.ip6_null_entry ||
 	    rt->rt6i_flags & RTF_CACHE)
 		goto out;
@@ -782,9 +782,9 @@ restart:
 	read_unlock_bh(&table->tb6_lock);
 
 	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
-		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
+		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
-		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
+		nrt = rt6_alloc_clone(rt, &fl6->daddr);
 	else
 		goto out2;
 
@@ -823,9 +823,9 @@ out2:
 }
 
 static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
-					    struct flowi *fl, int flags)
+					    struct flowi6 *fl6, int flags)
 {
-	return ip6_pol_route(net, table, fl->flowi_iif, fl, flags);
+	return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
 }
 
 void ip6_route_input(struct sk_buff *skb)
@@ -833,41 +833,41 @@ void ip6_route_input(struct sk_buff *skb)
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct net *net = dev_net(skb->dev);
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
-	struct flowi fl = {
-		.flowi_iif = skb->dev->ifindex,
-		.fl6_dst = iph->daddr,
-		.fl6_src = iph->saddr,
-		.fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
-		.flowi_mark = skb->mark,
-		.flowi_proto = iph->nexthdr,
+	struct flowi6 fl6 = {
+		.flowi6_iif = skb->dev->ifindex,
+		.daddr = iph->daddr,
+		.saddr = iph->saddr,
+		.flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
+		.flowi6_mark = skb->mark,
+		.flowi6_proto = iph->nexthdr,
 	};
 
 	if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input));
+	skb_dst_set(skb, fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_input));
 }
 
 static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
-					     struct flowi *fl, int flags)
+					     struct flowi6 *fl6, int flags)
 {
-	return ip6_pol_route(net, table, fl->flowi_oif, fl, flags);
+	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
 struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
-				    struct flowi *fl)
+				    struct flowi6 *fl6)
 {
 	int flags = 0;
 
-	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl->fl6_dst))
+	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	if (!ipv6_addr_any(&fl->fl6_src))
+	if (!ipv6_addr_any(&fl6->saddr))
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 	else if (sk)
 		flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
 
-	return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
+	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
 }
 
 EXPORT_SYMBOL(ip6_route_output);
@@ -1444,16 +1444,16 @@ static int ip6_route_del(struct fib6_config *cfg)
  *	Handle redirects
  */
 struct ip6rd_flowi {
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct in6_addr gateway;
 };
 
 static struct rt6_info *__ip6_route_redirect(struct net *net,
 					     struct fib6_table *table,
-					     struct flowi *fl,
+					     struct flowi6 *fl6,
 					     int flags)
 {
-	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl;
+	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
 	struct rt6_info *rt;
 	struct fib6_node *fn;
 
@@ -1469,7 +1469,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	 */
 
 	read_lock_bh(&table->tb6_lock);
-	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
 		/*
@@ -1484,7 +1484,7 @@ restart:
 			continue;
 		if (!(rt->rt6i_flags & RTF_GATEWAY))
 			continue;
-		if (fl->flowi_oif != rt->rt6i_dev->ifindex)
+		if (fl6->flowi6_oif != rt->rt6i_dev->ifindex)
 			continue;
 		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
 			continue;
@@ -1493,7 +1493,7 @@ restart:
 
 	if (!rt)
 		rt = net->ipv6.ip6_null_entry;
-	BACKTRACK(net, &fl->fl6_src);
+	BACKTRACK(net, &fl6->saddr);
 out:
 	dst_hold(&rt->dst);
 
@@ -1510,10 +1510,10 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct net *net = dev_net(dev);
 	struct ip6rd_flowi rdfl = {
-		.fl = {
-			.flowi_oif = dev->ifindex,
-			.fl6_dst = *dest,
-			.fl6_src = *src,
+		.fl6 = {
+			.flowi6_oif = dev->ifindex,
+			.daddr = *dest,
+			.saddr = *src,
 		},
 	};
 
@@ -1522,7 +1522,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
 	if (rt6_need_strict(dest))
 		flags |= RT6_LOOKUP_F_IFACE;
 
-	return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl,
+	return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6,
 						   flags, __ip6_route_redirect);
 }
 
@@ -2385,7 +2385,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 	struct rt6_info *rt;
 	struct sk_buff *skb;
 	struct rtmsg *rtm;
-	struct flowi fl;
+	struct flowi6 fl6;
 	int err, iif = 0;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
@@ -2393,27 +2393,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 		goto errout;
 
 	err = -EINVAL;
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 
 	if (tb[RTA_SRC]) {
 		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
 			goto errout;
 
-		ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC]));
+		ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC]));
 	}
 
 	if (tb[RTA_DST]) {
 		if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
 			goto errout;
 
-		ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST]));
+		ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST]));
 	}
 
 	if (tb[RTA_IIF])
 		iif = nla_get_u32(tb[RTA_IIF]);
 
 	if (tb[RTA_OIF])
-		fl.flowi_oif = nla_get_u32(tb[RTA_OIF]);
+		fl6.flowi6_oif = nla_get_u32(tb[RTA_OIF]);
 
 	if (iif) {
 		struct net_device *dev;
@@ -2436,10 +2436,10 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 	skb_reset_mac_header(skb);
 	skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
 
-	rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl);
+	rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl6);
 	skb_dst_set(skb, &rt->dst);
 
-	err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
+	err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
 			    RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
 			    nlh->nlmsg_seq, 0, 0, 0);
 	if (err < 0) {
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 5b9eded1432c..97858d5d67e8 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -232,19 +232,19 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	 */
 	{
 		struct in6_addr *final_p, final;
-		struct flowi fl;
-		memset(&fl, 0, sizeof(fl));
-		fl.flowi_proto = IPPROTO_TCP;
-		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
-		final_p = fl6_update_dst(&fl, np->opt, &final);
-		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
-		fl.flowi_oif = sk->sk_bound_dev_if;
-		fl.flowi_mark = sk->sk_mark;
-		fl.fl6_dport = inet_rsk(req)->rmt_port;
-		fl.fl6_sport = inet_sk(sk)->inet_sport;
-		security_req_classify_flow(req, &fl);
-
-		dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+		struct flowi6 fl6;
+		memset(&fl6, 0, sizeof(fl6));
+		fl6.flowi6_proto = IPPROTO_TCP;
+		ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
+		fl6.flowi6_mark = sk->sk_mark;
+		fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
+		fl6.uli.ports.sport = inet_sk(sk)->inet_sport;
+		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 		if (IS_ERR(dst))
 			goto out_free;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c531ad5fbccc..7ed0ba1995f0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -131,7 +131,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
 	struct rt6_info *rt;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
 	int err;
@@ -142,14 +142,14 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (usin->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 
 	if (np->sndflow) {
-		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-		IP6_ECN_flow_init(fl.fl6_flowlabel);
-		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
+		fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+		IP6_ECN_flow_init(fl6.flowlabel);
+		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
 			struct ip6_flowlabel *flowlabel;
-			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
 			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
@@ -195,7 +195,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	}
 
 	ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
-	np->flow_label = fl.fl6_flowlabel;
+	np->flow_label = fl6.flowlabel;
 
 	/*
 	 *	TCP over IPv4
@@ -242,27 +242,27 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (!ipv6_addr_any(&np->rcv_saddr))
 		saddr = &np->rcv_saddr;
 
-	fl.flowi_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-	ipv6_addr_copy(&fl.fl6_src,
+	fl6.flowi6_proto = IPPROTO_TCP;
+	ipv6_addr_copy(&fl6.daddr, &np->daddr);
+	ipv6_addr_copy(&fl6.saddr,
 		       (saddr ? saddr : &np->saddr));
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.flowi_mark = sk->sk_mark;
-	fl.fl6_dport = usin->sin6_port;
-	fl.fl6_sport = inet->inet_sport;
+	fl6.flowi6_oif = sk->sk_bound_dev_if;
+	fl6.flowi6_mark = sk->sk_mark;
+	fl6.uli.ports.dport = usin->sin6_port;
+	fl6.uli.ports.sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl, np->opt, &final);
+	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
-	security_sk_classify_flow(sk, &fl);
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
 	}
 
 	if (saddr == NULL) {
-		saddr = &fl.fl6_src;
+		saddr = &fl6.saddr;
 		ipv6_addr_copy(&np->rcv_saddr, saddr);
 	}
 
@@ -389,23 +389,23 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		if (dst == NULL) {
 			struct inet_sock *inet = inet_sk(sk);
-			struct flowi fl;
+			struct flowi6 fl6;
 
 			/* BUGGG_FUTURE: Again, it is not clear how
 			   to handle rthdr case. Ignore this complexity
 			   for now.
 			 */
-			memset(&fl, 0, sizeof(fl));
-			fl.flowi_proto = IPPROTO_TCP;
-			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
-			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-			fl.flowi_oif = sk->sk_bound_dev_if;
-			fl.flowi_mark = sk->sk_mark;
-			fl.fl6_dport = inet->inet_dport;
-			fl.fl6_sport = inet->inet_sport;
-			security_skb_classify_flow(skb, &fl);
-
-			dst = ip6_dst_lookup_flow(sk, &fl, NULL, false);
+			memset(&fl6, 0, sizeof(fl6));
+			fl6.flowi6_proto = IPPROTO_TCP;
+			ipv6_addr_copy(&fl6.daddr, &np->daddr);
+			ipv6_addr_copy(&fl6.saddr, &np->saddr);
+			fl6.flowi6_oif = sk->sk_bound_dev_if;
+			fl6.flowi6_mark = sk->sk_mark;
+			fl6.uli.ports.dport = inet->inet_dport;
+			fl6.uli.ports.sport = inet->inet_sport;
+			security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+
+			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
 			if (IS_ERR(dst)) {
 				sk->sk_err_soft = -PTR_ERR(dst);
 				goto out;
@@ -482,25 +482,25 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	struct sk_buff * skb;
 	struct ipv6_txoptions *opt = NULL;
 	struct in6_addr * final_p, final;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int err;
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
-	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
-	fl.fl6_flowlabel = 0;
-	fl.flowi_oif = treq->iif;
-	fl.flowi_mark = sk->sk_mark;
-	fl.fl6_dport = inet_rsk(req)->rmt_port;
-	fl.fl6_sport = inet_rsk(req)->loc_port;
-	security_req_classify_flow(req, &fl);
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+	ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
+	fl6.flowlabel = 0;
+	fl6.flowi6_oif = treq->iif;
+	fl6.flowi6_mark = sk->sk_mark;
+	fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
+	fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 	opt = np->opt;
-	final_p = fl6_update_dst(&fl, opt, &final);
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl, final_p, false);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto done;
@@ -510,8 +510,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	if (skb) {
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
-		ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
-		err = ip6_xmit(sk, skb, &fl, opt);
+		ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+		err = ip6_xmit(sk, skb, &fl6, opt);
 		err = net_xmit_eval(err);
 	}
 
@@ -992,7 +992,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 {
 	struct tcphdr *th = tcp_hdr(skb), *t1;
 	struct sk_buff *buff;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	struct sock *ctl_sk = net->ipv6.tcp_sk;
 	unsigned int tot_len = sizeof(struct tcphdr);
@@ -1046,29 +1046,29 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	}
 #endif
 
-	memset(&fl, 0, sizeof(fl));
-	ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr);
-	ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr);
+	memset(&fl6, 0, sizeof(fl6));
+	ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr);
+	ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr);
 
 	buff->ip_summed = CHECKSUM_PARTIAL;
 	buff->csum = 0;
 
-	__tcp_v6_send_check(buff, &fl.fl6_src, &fl.fl6_dst);
+	__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
 
-	fl.flowi_proto = IPPROTO_TCP;
-	fl.flowi_oif = inet6_iif(skb);
-	fl.fl6_dport = t1->dest;
-	fl.fl6_sport = t1->source;
-	security_skb_classify_flow(skb, &fl);
+	fl6.flowi6_proto = IPPROTO_TCP;
+	fl6.flowi6_oif = inet6_iif(skb);
+	fl6.uli.ports.dport = t1->dest;
+	fl6.uli.ports.sport = t1->source;
+	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl, NULL, false);
+	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
-		ip6_xmit(ctl_sk, buff, &fl, NULL);
+		ip6_xmit(ctl_sk, buff, &fl6, NULL);
 		TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 		if (rst)
 			TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index dad035fb0afd..ce4b16fbf81c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -886,7 +886,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	struct udphdr *uh;
 	struct udp_sock  *up = udp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
-	struct flowi *fl = &inet->cork.fl;
+	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
 	__wsum csum = 0;
@@ -899,23 +899,23 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	 * Create a UDP header
 	 */
 	uh = udp_hdr(skb);
-	uh->source = fl->fl6_sport;
-	uh->dest = fl->fl6_dport;
+	uh->source = fl6->uli.ports.sport;
+	uh->dest = fl6->uli.ports.dport;
 	uh->len = htons(up->len);
 	uh->check = 0;
 
 	if (is_udplite)
 		csum = udplite_csum_outgoing(sk, skb);
 	else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
-		udp6_hwcsum_outgoing(sk, skb, &fl->fl6_src, &fl->fl6_dst,
+		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr,
 				     up->len);
 		goto send;
 	} else
 		csum = udp_csum_outgoing(sk, skb);
 
 	/* add protocol-dependent pseudo-header */
-	uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst,
-				    up->len, fl->flowi_proto, csum);
+	uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
+				    up->len, fl6->flowi6_proto, csum);
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
@@ -947,7 +947,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
-	struct flowi fl;
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_len = msg->msg_namelen;
 	int ulen = len;
@@ -1030,19 +1030,19 @@ do_udp_sendmsg:
 	}
 	ulen += sizeof(struct udphdr);
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 
 	if (sin6) {
 		if (sin6->sin6_port == 0)
 			return -EINVAL;
 
-		fl.fl6_dport = sin6->sin6_port;
+		fl6.uli.ports.dport = sin6->sin6_port;
 		daddr = &sin6->sin6_addr;
 
 		if (np->sndflow) {
-			fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-			if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
-				flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+			fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+			if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
+				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 				if (flowlabel == NULL)
 					return -EINVAL;
 				daddr = &flowlabel->dst;
@@ -1060,38 +1060,38 @@ do_udp_sendmsg:
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
 		    ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
-			fl.flowi_oif = sin6->sin6_scope_id;
+			fl6.flowi6_oif = sin6->sin6_scope_id;
 	} else {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
-		fl.fl6_dport = inet->inet_dport;
+		fl6.uli.ports.dport = inet->inet_dport;
 		daddr = &np->daddr;
-		fl.fl6_flowlabel = np->flow_label;
+		fl6.flowlabel = np->flow_label;
 		connected = 1;
 	}
 
-	if (!fl.flowi_oif)
-		fl.flowi_oif = sk->sk_bound_dev_if;
+	if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
-	if (!fl.flowi_oif)
-		fl.flowi_oif = np->sticky_pktinfo.ipi6_ifindex;
+	if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
-	fl.flowi_mark = sk->sk_mark;
+	fl6.flowi6_mark = sk->sk_mark;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(*opt);
 
-		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+		err = datagram_send_ctl(sock_net(sk), msg, &fl6, opt, &hlimit,
 					&tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
 		}
-		if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
-			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+		if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
+			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
 		}
@@ -1105,27 +1105,27 @@ do_udp_sendmsg:
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
 
-	fl.flowi_proto = sk->sk_protocol;
+	fl6.flowi6_proto = sk->sk_protocol;
 	if (!ipv6_addr_any(daddr))
-		ipv6_addr_copy(&fl.fl6_dst, daddr);
+		ipv6_addr_copy(&fl6.daddr, daddr);
 	else
-		fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
-	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
-		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-	fl.fl6_sport = inet->inet_sport;
+		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
+	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
+		ipv6_addr_copy(&fl6.saddr, &np->saddr);
+	fl6.uli.ports.sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl, opt, &final);
+	final_p = fl6_update_dst(&fl6, opt, &final);
 	if (final_p)
 		connected = 0;
 
-	if (!fl.flowi_oif && ipv6_addr_is_multicast(&fl.fl6_dst)) {
-		fl.flowi_oif = np->mcast_oif;
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) {
+		fl6.flowi6_oif = np->mcast_oif;
 		connected = 0;
 	}
 
-	security_sk_classify_flow(sk, &fl);
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_sk_dst_lookup_flow(sk, &fl, final_p, true);
+	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, true);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
@@ -1133,7 +1133,7 @@ do_udp_sendmsg:
 	}
 
 	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl.fl6_dst))
+		if (ipv6_addr_is_multicast(&fl6.daddr))
 			hlimit = np->mcast_hops;
 		else
 			hlimit = np->hop_limit;
@@ -1168,7 +1168,7 @@ do_append_data:
 	up->len += ulen;
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
 	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
-		sizeof(struct udphdr), hlimit, tclass, opt, &fl,
+		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
 		(struct rt6_info*)dst,
 		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
 	if (err)
@@ -1181,10 +1181,10 @@ do_append_data:
 	if (dst) {
 		if (connected) {
 			ip6_dst_store(sk, dst,
-				      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
+				      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
 				      &np->daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
-				      ipv6_addr_equal(&fl.fl6_src, &np->saddr) ?
+				      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
 				      &np->saddr :
 #endif
 				      NULL);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 254aa6d79506..bef62005c0ed 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -39,8 +39,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
 	if (saddr)
 		memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
 
-	dst = ip6_route_output(net, NULL,
-			       flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
 
 	err = dst->error;
 	if (dst->error) {
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d07a32aa07b6..a60b20fa142e 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -75,15 +75,13 @@ static int __ip_vs_addr_is_local_v6(struct net *net,
 				    const struct in6_addr *addr)
 {
 	struct rt6_info *rt;
-	struct flowi fl = {
-		.flowi_oif = 0,
-		.fl6_dst = *addr,
-		.fl6_src = { .s6_addr32 = {0, 0, 0, 0} },
+	struct flowi6 fl6 = {
+		.daddr = *addr,
 	};
 
-	rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl);
+	rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
 	if (rt && rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK))
-			return 1;
+		return 1;
 
 	return 0;
 }
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 7dc00e313611..6132b213eddc 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -198,27 +198,27 @@ __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
 			struct in6_addr *ret_saddr, int do_xfrm)
 {
 	struct dst_entry *dst;
-	struct flowi fl = {
-		.fl6_dst = *daddr,
+	struct flowi6 fl6 = {
+		.daddr = *daddr,
 	};
 
-	dst = ip6_route_output(net, NULL, &fl);
+	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error)
 		goto out_err;
 	if (!ret_saddr)
 		return dst;
-	if (ipv6_addr_any(&fl.fl6_src) &&
+	if (ipv6_addr_any(&fl6.saddr) &&
 	    ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
-			       &fl.fl6_dst, 0, &fl.fl6_src) < 0)
+			       &fl6.daddr, 0, &fl6.saddr) < 0)
 		goto out_err;
 	if (do_xfrm) {
-		dst = xfrm_lookup(net, dst, &fl, NULL, 0);
+		dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 		if (IS_ERR(dst)) {
 			dst = NULL;
 			goto out_err;
 		}
 	}
-	ipv6_addr_copy(ret_saddr, &fl.fl6_src);
+	ipv6_addr_copy(ret_saddr, &fl6.saddr);
 	return dst;
 
 out_err:
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index d8c00f9342ae..5f054a0dbbb1 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -143,18 +143,18 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct net *net = pick_net(skb);
 	struct dst_entry *dst;
-	struct flowi fl;
+	struct flowi6 fl6;
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 	if (info->priv) {
 		if (info->priv->oif == -1)
 			return false;
-		fl.flowi_oif = info->priv->oif;
+		fl6.flowi6_oif = info->priv->oif;
 	}
-	fl.fl6_dst = info->gw.in6;
-	fl.fl6_flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
+	fl6.daddr = info->gw.in6;
+	fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
 			   (iph->flow_lbl[1] << 8) | iph->flow_lbl[2];
-	dst = ip6_route_output(net, NULL, &fl);
+	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst == NULL)
 		return false;
 
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 831627156884..865ce7ba4e14 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -201,40 +201,40 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 {
 	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct flowi fl;
+	struct flowi6 fl6;
 
-	memset(&fl, 0, sizeof(fl));
+	memset(&fl6, 0, sizeof(fl6));
 
-	fl.flowi_proto = sk->sk_protocol;
+	fl6.flowi6_proto = sk->sk_protocol;
 
 	/* Fill in the dest address from the route entry passed with the skb
 	 * and the source address from the transport.
 	 */
-	ipv6_addr_copy(&fl.fl6_dst, &transport->ipaddr.v6.sin6_addr);
-	ipv6_addr_copy(&fl.fl6_src, &transport->saddr.v6.sin6_addr);
+	ipv6_addr_copy(&fl6.daddr, &transport->ipaddr.v6.sin6_addr);
+	ipv6_addr_copy(&fl6.saddr, &transport->saddr.v6.sin6_addr);
 
-	fl.fl6_flowlabel = np->flow_label;
-	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
-	if (ipv6_addr_type(&fl.fl6_src) & IPV6_ADDR_LINKLOCAL)
-		fl.flowi_oif = transport->saddr.v6.sin6_scope_id;
+	fl6.flowlabel = np->flow_label;
+	IP6_ECN_flow_xmit(sk, fl6.flowlabel);
+	if (ipv6_addr_type(&fl6.saddr) & IPV6_ADDR_LINKLOCAL)
+		fl6.flowi6_oif = transport->saddr.v6.sin6_scope_id;
 	else
-		fl.flowi_oif = sk->sk_bound_dev_if;
+		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
 	if (np->opt && np->opt->srcrt) {
 		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
-		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
+		ipv6_addr_copy(&fl6.daddr, rt0->addr);
 	}
 
 	SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n",
 			  __func__, skb, skb->len,
-			  &fl.fl6_src, &fl.fl6_dst);
+			  &fl6.saddr, &fl6.daddr);
 
 	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
 
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
 		skb->local_df = 1;
 
-	return ip6_xmit(sk, skb, &fl, np->opt);
+	return ip6_xmit(sk, skb, &fl6, np->opt);
 }
 
 /* Returns the dst cache entry for the given source and destination ip
@@ -245,22 +245,22 @@ static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc,
 					 union sctp_addr *saddr)
 {
 	struct dst_entry *dst;
-	struct flowi fl;
+	struct flowi6 fl6;
 
-	memset(&fl, 0, sizeof(fl));
-	ipv6_addr_copy(&fl.fl6_dst, &daddr->v6.sin6_addr);
+	memset(&fl6, 0, sizeof(fl6));
+	ipv6_addr_copy(&fl6.daddr, &daddr->v6.sin6_addr);
 	if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
-		fl.flowi_oif = daddr->v6.sin6_scope_id;
+		fl6.flowi6_oif = daddr->v6.sin6_scope_id;
 
 
-	SCTP_DEBUG_PRINTK("%s: DST=%pI6 ", __func__, &fl.fl6_dst);
+	SCTP_DEBUG_PRINTK("%s: DST=%pI6 ", __func__, &fl6.daddr);
 
 	if (saddr) {
-		ipv6_addr_copy(&fl.fl6_src, &saddr->v6.sin6_addr);
-		SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl.fl6_src);
+		ipv6_addr_copy(&fl6.saddr, &saddr->v6.sin6_addr);
+		SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6.saddr);
 	}
 
-	dst = ip6_route_output(&init_net, NULL, &fl);
+	dst = ip6_route_output(&init_net, NULL, &fl6);
 	if (!dst->error) {
 		struct rt6_info *rt;
 		rt = (struct rt6_info *)dst;
-- 
cgit v1.2.3


From 1958b856c1a59c0f1e892b92debb8c9fe4f364dc Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 16:36:19 -0500
Subject: net: Put fl6_* macros to struct flowi6 and use them again.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h               | 17 +++++++----------
 net/dccp/ipv6.c                  | 20 ++++++++++----------
 net/ipv6/af_inet6.c              |  4 ++--
 net/ipv6/datagram.c              |  6 +++---
 net/ipv6/icmp.c                  | 10 +++++-----
 net/ipv6/inet6_connection_sock.c |  8 ++++----
 net/ipv6/mip6.c                  |  2 +-
 net/ipv6/netfilter/ip6t_REJECT.c |  4 ++--
 net/ipv6/raw.c                   |  6 +++---
 net/ipv6/syncookies.c            |  4 ++--
 net/ipv6/tcp_ipv6.c              | 16 ++++++++--------
 net/ipv6/udp.c                   | 10 +++++-----
 net/ipv6/xfrm6_policy.c          | 12 ++++++------
 13 files changed, 58 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 44bd37628f55..172d76dd8731 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -84,6 +84,13 @@ struct flowi6 {
 	struct in6_addr		saddr;
 	__be32			flowlabel;
 	union flowi_uli		uli;
+#define fl6_sport		uli.ports.sport
+#define fl6_dport		uli.ports.dport
+#define fl6_icmp_type		uli.icmpt.type
+#define fl6_icmp_code		uli.icmpt.code
+#define fl6_ipsec_spi		uli.spi
+#define fl6_mh_type		uli.mht.type
+#define fl6_gre_key		uli.gre_key
 };
 
 struct flowidn {
@@ -112,16 +119,6 @@ struct flowi {
 
 #define fld_dst		u.dn.daddr
 #define fld_src		u.dn.saddr
-#define fl6_dst		u.ip6.daddr
-#define fl6_src		u.ip6.saddr
-#define fl6_flowlabel	u.ip6.flowlabel
-#define fl6_sport	u.ip6.uli.ports.sport
-#define fl6_dport	u.ip6.uli.ports.dport
-#define fl6_icmp_type	u.ip6.uli.icmpt.type
-#define fl6_icmp_code	u.ip6.uli.icmpt.code
-#define fl6_ipsec_spi	u.ip6.uli.spi
-#define fl6_mh_type	u.ip6.uli.mht.type
-#define fl6_gre_key	u.ip6.uli.gre_key
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 8d26c122de64..de1b7e37ad5b 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -158,8 +158,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			ipv6_addr_copy(&fl6.daddr, &np->daddr);
 			ipv6_addr_copy(&fl6.saddr, &np->saddr);
 			fl6.flowi6_oif = sk->sk_bound_dev_if;
-			fl6.uli.ports.dport = inet->inet_dport;
-			fl6.uli.ports.sport = inet->inet_sport;
+			fl6.fl6_dport = inet->inet_dport;
+			fl6.fl6_sport = inet->inet_sport;
 			security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
@@ -253,8 +253,8 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 	ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
 	fl6.flowlabel = 0;
 	fl6.flowi6_oif = ireq6->iif;
-	fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
-	fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+	fl6.fl6_dport = inet_rsk(req)->rmt_port;
+	fl6.fl6_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 	opt = np->opt;
@@ -323,8 +323,8 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 
 	fl6.flowi6_proto = IPPROTO_DCCP;
 	fl6.flowi6_oif = inet6_iif(rxskb);
-	fl6.uli.ports.dport = dccp_hdr(skb)->dccph_dport;
-	fl6.uli.ports.sport = dccp_hdr(skb)->dccph_sport;
+	fl6.fl6_dport = dccp_hdr(skb)->dccph_dport;
+	fl6.fl6_sport = dccp_hdr(skb)->dccph_sport;
 	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
@@ -535,8 +535,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		final_p = fl6_update_dst(&fl6, opt, &final);
 		ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
-		fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
-		fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+		fl6.fl6_dport = inet_rsk(req)->rmt_port;
+		fl6.fl6_sport = inet_rsk(req)->loc_port;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
@@ -957,8 +957,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	ipv6_addr_copy(&fl6.daddr, &np->daddr);
 	ipv6_addr_copy(&fl6.saddr, saddr ? saddr : &np->saddr);
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
-	fl6.uli.ports.dport = usin->sin6_port;
-	fl6.uli.ports.sport = inet->inet_sport;
+	fl6.fl6_dport = usin->sin6_port;
+	fl6.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 689eea6553fd..4b13d5d8890e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -661,8 +661,8 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.flowlabel = np->flow_label;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = sk->sk_mark;
-		fl6.uli.ports.dport = inet->inet_dport;
-		fl6.uli.ports.sport = inet->inet_sport;
+		fl6.fl6_dport = inet->inet_dport;
+		fl6.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 04ae676d14ee..16560336eb72 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -151,8 +151,8 @@ ipv4_connected:
 	ipv6_addr_copy(&fl6.saddr, &np->saddr);
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
-	fl6.uli.ports.dport = inet->inet_dport;
-	fl6.uli.ports.sport = inet->inet_sport;
+	fl6.fl6_dport = inet->inet_dport;
+	fl6.fl6_sport = inet->inet_sport;
 
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;
@@ -261,7 +261,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 	serr->ee.ee_info = info;
 	serr->ee.ee_data = 0;
 	serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb);
-	serr->port = fl6->uli.ports.dport;
+	serr->port = fl6->fl6_dport;
 
 	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
 	skb_reset_transport_header(skb);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f7b9041f7845..83cb4f9add81 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -448,8 +448,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	if (saddr)
 		ipv6_addr_copy(&fl6.saddr, saddr);
 	fl6.flowi6_oif = iif;
-	fl6.uli.icmpt.type = type;
-	fl6.uli.icmpt.code = code;
+	fl6.fl6_icmp_type = type;
+	fl6.fl6_icmp_code = code;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
@@ -544,7 +544,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (saddr)
 		ipv6_addr_copy(&fl6.saddr, saddr);
 	fl6.flowi6_oif = skb->dev->ifindex;
-	fl6.uli.icmpt.type = ICMPV6_ECHO_REPLY;
+	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
@@ -794,8 +794,8 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
 	ipv6_addr_copy(&fl6->saddr, saddr);
 	ipv6_addr_copy(&fl6->daddr, daddr);
 	fl6->flowi6_proto 	= IPPROTO_ICMPV6;
-	fl6->uli.icmpt.type	= type;
-	fl6->uli.icmpt.code	= 0;
+	fl6->fl6_icmp_type	= type;
+	fl6->fl6_icmp_code	= 0;
 	fl6->flowi6_oif		= oif;
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 }
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 27d669160ba6..166054650466 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -70,8 +70,8 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
-	fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
-	fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+	fl6.fl6_dport = inet_rsk(req)->rmt_port;
+	fl6.fl6_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
@@ -220,8 +220,8 @@ int inet6_csk_xmit(struct sk_buff *skb)
 	IP6_ECN_flow_xmit(sk, fl6.flowlabel);
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
-	fl6.uli.ports.sport = inet->inet_sport;
-	fl6.uli.ports.dport = inet->inet_dport;
+	fl6.fl6_sport = inet->inet_sport;
+	fl6.fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 6a137355311c..9b210482fb05 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -216,7 +216,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	int err = 0;
 
 	if (unlikely(fl6->flowi6_proto == IPPROTO_MH &&
-		     fl6->uli.mht.type <= IP6_MH_TYPE_MAX))
+		     fl6->fl6_mh_type <= IP6_MH_TYPE_MAX))
 		goto out;
 
 	if (likely(opt->dsthao)) {
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index df05511dea33..28e74488a329 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -93,8 +93,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	fl6.flowi6_proto = IPPROTO_TCP;
 	ipv6_addr_copy(&fl6.saddr, &oip6h->daddr);
 	ipv6_addr_copy(&fl6.daddr, &oip6h->saddr);
-	fl6.uli.ports.sport = otcph.dest;
-	fl6.uli.ports.dport = otcph.source;
+	fl6.fl6_sport = otcph.dest;
+	fl6.fl6_dport = otcph.source;
 	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst == NULL || dst->error) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 259f1b231038..4a1c3b46c56b 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -693,8 +693,8 @@ static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
 				code = iov->iov_base;
 
 			if (type && code) {
-				if (get_user(fl6->uli.icmpt.type, type) ||
-				    get_user(fl6->uli.icmpt.code, code))
+				if (get_user(fl6->fl6_icmp_type, type) ||
+				    get_user(fl6->fl6_icmp_code, code))
 					return -EFAULT;
 				probed = 1;
 			}
@@ -705,7 +705,7 @@ static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
 			/* check if type field is readable or not. */
 			if (iov->iov_len > 2 - len) {
 				u8 __user *p = iov->iov_base;
-				if (get_user(fl6->uli.mht.type, &p[2 - len]))
+				if (get_user(fl6->fl6_mh_type, &p[2 - len]))
 					return -EFAULT;
 				probed = 1;
 			} else
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 97858d5d67e8..352c26081f5d 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -240,8 +240,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = sk->sk_mark;
-		fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
-		fl6.uli.ports.sport = inet_sk(sk)->inet_sport;
+		fl6.fl6_dport = inet_rsk(req)->rmt_port;
+		fl6.fl6_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7ed0ba1995f0..2b0c186862c8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -248,8 +248,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		       (saddr ? saddr : &np->saddr));
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
-	fl6.uli.ports.dport = usin->sin6_port;
-	fl6.uli.ports.sport = inet->inet_sport;
+	fl6.fl6_dport = usin->sin6_port;
+	fl6.fl6_sport = inet->inet_sport;
 
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
@@ -401,8 +401,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			ipv6_addr_copy(&fl6.saddr, &np->saddr);
 			fl6.flowi6_oif = sk->sk_bound_dev_if;
 			fl6.flowi6_mark = sk->sk_mark;
-			fl6.uli.ports.dport = inet->inet_dport;
-			fl6.uli.ports.sport = inet->inet_sport;
+			fl6.fl6_dport = inet->inet_dport;
+			fl6.fl6_sport = inet->inet_sport;
 			security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
@@ -493,8 +493,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	fl6.flowlabel = 0;
 	fl6.flowi6_oif = treq->iif;
 	fl6.flowi6_mark = sk->sk_mark;
-	fl6.uli.ports.dport = inet_rsk(req)->rmt_port;
-	fl6.uli.ports.sport = inet_rsk(req)->loc_port;
+	fl6.fl6_dport = inet_rsk(req)->rmt_port;
+	fl6.fl6_sport = inet_rsk(req)->loc_port;
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 	opt = np->opt;
@@ -1057,8 +1057,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	fl6.flowi6_proto = IPPROTO_TCP;
 	fl6.flowi6_oif = inet6_iif(skb);
-	fl6.uli.ports.dport = t1->dest;
-	fl6.uli.ports.sport = t1->source;
+	fl6.fl6_dport = t1->dest;
+	fl6.fl6_sport = t1->source;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ce4b16fbf81c..d7037c006e13 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -899,8 +899,8 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	 * Create a UDP header
 	 */
 	uh = udp_hdr(skb);
-	uh->source = fl6->uli.ports.sport;
-	uh->dest = fl6->uli.ports.dport;
+	uh->source = fl6->fl6_sport;
+	uh->dest = fl6->fl6_dport;
 	uh->len = htons(up->len);
 	uh->check = 0;
 
@@ -1036,7 +1036,7 @@ do_udp_sendmsg:
 		if (sin6->sin6_port == 0)
 			return -EINVAL;
 
-		fl6.uli.ports.dport = sin6->sin6_port;
+		fl6.fl6_dport = sin6->sin6_port;
 		daddr = &sin6->sin6_addr;
 
 		if (np->sndflow) {
@@ -1065,7 +1065,7 @@ do_udp_sendmsg:
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
-		fl6.uli.ports.dport = inet->inet_dport;
+		fl6.fl6_dport = inet->inet_dport;
 		daddr = &np->daddr;
 		fl6.flowlabel = np->flow_label;
 		connected = 1;
@@ -1112,7 +1112,7 @@ do_udp_sendmsg:
 		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
 	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
 		ipv6_addr_copy(&fl6.saddr, &np->saddr);
-	fl6.uli.ports.sport = inet->inet_sport;
+	fl6.fl6_sport = inet->inet_sport;
 
 	final_p = fl6_update_dst(&fl6, opt, &final);
 	if (final_p)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index bef62005c0ed..05e34c8ec913 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -160,8 +160,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
 				__be16 *ports = (__be16 *)exthdr;
 
-				fl6->uli.ports.sport = ports[!!reverse];
-				fl6->uli.ports.dport = ports[!reverse];
+				fl6->fl6_sport = ports[!!reverse];
+				fl6->fl6_dport = ports[!reverse];
 			}
 			fl6->flowi6_proto = nexthdr;
 			return;
@@ -170,8 +170,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
 				u8 *icmp = (u8 *)exthdr;
 
-				fl6->uli.icmpt.type = icmp[0];
-				fl6->uli.icmpt.code = icmp[1];
+				fl6->fl6_icmp_type = icmp[0];
+				fl6->fl6_icmp_code = icmp[1];
 			}
 			fl6->flowi6_proto = nexthdr;
 			return;
@@ -182,7 +182,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 				struct ip6_mh *mh;
 				mh = (struct ip6_mh *)exthdr;
 
-				fl6->uli.mht.type = mh->ip6mh_type;
+				fl6->fl6_mh_type = mh->ip6mh_type;
 			}
 			fl6->flowi6_proto = nexthdr;
 			return;
@@ -193,7 +193,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 		case IPPROTO_ESP:
 		case IPPROTO_COMP:
 		default:
-			fl6->uli.spi = 0;
+			fl6->fl6_ipsec_spi = 0;
 			fl6->flowi6_proto = nexthdr;
 			return;
 		}
-- 
cgit v1.2.3


From bef55aebd560c5a6f8883c421abccee39978c58c Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 12 Mar 2011 17:17:10 -0500
Subject: decnet: Convert to use flowidn where applicable.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dn.h        |   6 +-
 include/net/dn_fib.h    |   8 +-
 include/net/dn_route.h  |   8 +-
 include/net/flow.h      |  12 ++-
 net/decnet/af_decnet.c  |  16 +--
 net/decnet/dn_fib.c     |  23 +++--
 net/decnet/dn_nsp_out.c |  16 +--
 net/decnet/dn_route.c   | 269 ++++++++++++++++++++++++------------------------
 net/decnet/dn_rules.c   |  17 +--
 net/decnet/dn_table.c   |   6 +-
 10 files changed, 196 insertions(+), 185 deletions(-)

(limited to 'include')

diff --git a/include/net/dn.h b/include/net/dn.h
index 558dc7f93fb3..298521e0d8a2 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -192,10 +192,10 @@ static inline void dn_dn2eth(unsigned char *ethaddr, __le16 addr)
 	ethaddr[5] = (__u8)(a >> 8);
 }
 
-static inline void dn_sk_ports_copy(struct flowi *fl, struct dn_scp *scp)
+static inline void dn_sk_ports_copy(struct flowidn *fld, struct dn_scp *scp)
 {
-	fl->u.dn.uli.ports.sport = scp->addrloc;
-	fl->u.dn.uli.ports.dport = scp->addrrem;
+	fld->fld_sport = scp->addrloc;
+	fld->fld_dport = scp->addrrem;
 }
 
 extern unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu);
diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h
index bbcde3238e58..782ef7cb4930 100644
--- a/include/net/dn_fib.h
+++ b/include/net/dn_fib.h
@@ -98,7 +98,7 @@ struct dn_fib_table {
 	int (*delete)(struct dn_fib_table *t, struct rtmsg *r,
 			struct dn_kern_rta *rta, struct nlmsghdr *n,
 			struct netlink_skb_parms *req);
-	int (*lookup)(struct dn_fib_table *t, const struct flowi *fl,
+	int (*lookup)(struct dn_fib_table *t, const struct flowidn *fld,
 			struct dn_fib_res *res);
 	int (*flush)(struct dn_fib_table *t);
 	int (*dump)(struct dn_fib_table *t, struct sk_buff *skb, struct netlink_callback *cb);
@@ -119,12 +119,12 @@ extern struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r,
 				struct dn_kern_rta *rta, 
 				const struct nlmsghdr *nlh, int *errp);
 extern int dn_fib_semantic_match(int type, struct dn_fib_info *fi, 
-			const struct flowi *fl,
+			const struct flowidn *fld,
 			struct dn_fib_res *res);
 extern void dn_fib_release_info(struct dn_fib_info *fi);
 extern __le16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type);
 extern void dn_fib_flush(void);
-extern void dn_fib_select_multipath(const struct flowi *fl,
+extern void dn_fib_select_multipath(const struct flowidn *fld,
 					struct dn_fib_res *res);
 
 /*
@@ -141,7 +141,7 @@ extern void dn_fib_table_cleanup(void);
 extern void dn_fib_rules_init(void);
 extern void dn_fib_rules_cleanup(void);
 extern unsigned dnet_addr_type(__le16 addr);
-extern int dn_fib_lookup(struct flowi *fl, struct dn_fib_res *res);
+extern int dn_fib_lookup(struct flowidn *fld, struct dn_fib_res *res);
 
 extern int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
diff --git a/include/net/dn_route.h b/include/net/dn_route.h
index 1f59005e4979..81712cfa1ddf 100644
--- a/include/net/dn_route.h
+++ b/include/net/dn_route.h
@@ -16,7 +16,7 @@
 *******************************************************************************/
 
 extern struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri);
-extern int dn_route_output_sock(struct dst_entry **pprt, struct flowi *, struct sock *sk, int flags);
+extern int dn_route_output_sock(struct dst_entry **pprt, struct flowidn *, struct sock *sk, int flags);
 extern int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb);
 extern void dn_rt_cache_flush(int delay);
 
@@ -67,7 +67,7 @@ extern void dn_rt_cache_flush(int delay);
 struct dn_route {
 	struct dst_entry dst;
 
-	struct flowi fl;
+	struct flowidn fld;
 
 	__le16 rt_saddr;
 	__le16 rt_daddr;
@@ -82,12 +82,12 @@ struct dn_route {
 
 static inline bool dn_is_input_route(struct dn_route *rt)
 {
-	return rt->fl.flowi_iif != 0;
+	return rt->fld.flowidn_iif != 0;
 }
 
 static inline bool dn_is_output_route(struct dn_route *rt)
 {
-	return rt->fl.flowi_iif == 0;
+	return rt->fld.flowidn_iif == 0;
 }
 
 extern void dn_route_init(void);
diff --git a/include/net/flow.h b/include/net/flow.h
index 172d76dd8731..7fe5a0f9483a 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -95,9 +95,17 @@ struct flowi6 {
 
 struct flowidn {
 	struct flowi_common	__fl_common;
+#define flowidn_oif		__fl_common.flowic_oif
+#define flowidn_iif		__fl_common.flowic_iif
+#define flowidn_mark		__fl_common.flowic_mark
+#define flowidn_scope		__fl_common.flowic_scope
+#define flowidn_proto		__fl_common.flowic_proto
+#define flowidn_flags		__fl_common.flowic_flags
 	__le16			daddr;
 	__le16			saddr;
 	union flowi_uli		uli;
+#define fld_sport		uli.ports.sport
+#define fld_dport		uli.ports.dport
 };
 
 struct flowi {
@@ -115,10 +123,6 @@ struct flowi {
 #define flowi_proto	u.__fl_common.flowic_proto
 #define flowi_flags	u.__fl_common.flowic_flags
 #define flowi_secid	u.__fl_common.flowic_secid
-#define fld_scope	flowi_scope
-
-#define fld_dst		u.dn.daddr
-#define fld_src		u.dn.saddr
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index aafd15a01575..ea3b6ee21fc9 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -908,7 +908,7 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen,
 	struct socket *sock = sk->sk_socket;
 	struct dn_scp *scp = DN_SK(sk);
 	int err = -EISCONN;
-	struct flowi fl;
+	struct flowidn fld;
 
 	if (sock->state == SS_CONNECTED)
 		goto out;
@@ -947,13 +947,13 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen,
 	memcpy(&scp->peer, addr, sizeof(struct sockaddr_dn));
 
 	err = -EHOSTUNREACH;
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.fld_dst = dn_saddr2dn(&scp->peer);
-	fl.fld_src = dn_saddr2dn(&scp->addr);
-	dn_sk_ports_copy(&fl, scp);
-	fl.flowi_proto = DNPROTO_NSP;
-	if (dn_route_output_sock(&sk->sk_dst_cache, &fl, sk, flags) < 0)
+	memset(&fld, 0, sizeof(fld));
+	fld.flowidn_oif = sk->sk_bound_dev_if;
+	fld.daddr = dn_saddr2dn(&scp->peer);
+	fld.saddr = dn_saddr2dn(&scp->addr);
+	dn_sk_ports_copy(&fld, scp);
+	fld.flowidn_proto = DNPROTO_NSP;
+	if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, flags) < 0)
 		goto out;
 	sk->sk_route_caps = sk->sk_dst_cache->dev->features;
 	sock->state = SS_CONNECTING;
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 4dfffa0b67a8..1c74ed36ce8f 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -201,7 +201,7 @@ static int dn_fib_check_nh(const struct rtmsg *r, struct dn_fib_info *fi, struct
 	int err;
 
 	if (nh->nh_gw) {
-		struct flowi fl;
+		struct flowidn fld;
 		struct dn_fib_res res;
 
 		if (nh->nh_flags&RTNH_F_ONLINK) {
@@ -221,15 +221,15 @@ static int dn_fib_check_nh(const struct rtmsg *r, struct dn_fib_info *fi, struct
 			return 0;
 		}
 
-		memset(&fl, 0, sizeof(fl));
-		fl.fld_dst = nh->nh_gw;
-		fl.flowi_oif = nh->nh_oif;
-		fl.fld_scope = r->rtm_scope + 1;
+		memset(&fld, 0, sizeof(fld));
+		fld.daddr = nh->nh_gw;
+		fld.flowidn_oif = nh->nh_oif;
+		fld.flowidn_scope = r->rtm_scope + 1;
 
-		if (fl.fld_scope < RT_SCOPE_LINK)
-			fl.fld_scope = RT_SCOPE_LINK;
+		if (fld.flowidn_scope < RT_SCOPE_LINK)
+			fld.flowidn_scope = RT_SCOPE_LINK;
 
-		if ((err = dn_fib_lookup(&fl, &res)) != 0)
+		if ((err = dn_fib_lookup(&fld, &res)) != 0)
 			return err;
 
 		err = -EINVAL;
@@ -404,7 +404,7 @@ failure:
 	return NULL;
 }
 
-int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowi *fl, struct dn_fib_res *res)
+int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn *fld, struct dn_fib_res *res)
 {
 	int err = dn_fib_props[type].error;
 
@@ -424,7 +424,8 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowi *
 				for_nexthops(fi) {
 					if (nh->nh_flags & RTNH_F_DEAD)
 						continue;
-					if (!fl->flowi_oif || fl->flowi_oif == nh->nh_oif)
+					if (!fld->flowidn_oif ||
+					    fld->flowidn_oif == nh->nh_oif)
 						break;
 				}
 				if (nhsel < fi->fib_nhs) {
@@ -445,7 +446,7 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowi *
 	return err;
 }
 
-void dn_fib_select_multipath(const struct flowi *fl, struct dn_fib_res *res)
+void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res)
 {
 	struct dn_fib_info *fi = res->fi;
 	int w;
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index b3d66742a01f..bd78836a81eb 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -78,7 +78,7 @@ static void dn_nsp_send(struct sk_buff *skb)
 	struct sock *sk = skb->sk;
 	struct dn_scp *scp = DN_SK(sk);
 	struct dst_entry *dst;
-	struct flowi fl;
+	struct flowidn fld;
 
 	skb_reset_transport_header(skb);
 	scp->stamp = jiffies;
@@ -91,13 +91,13 @@ try_again:
 		return;
 	}
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_oif = sk->sk_bound_dev_if;
-	fl.fld_src = dn_saddr2dn(&scp->addr);
-	fl.fld_dst = dn_saddr2dn(&scp->peer);
-	dn_sk_ports_copy(&fl, scp);
-	fl.flowi_proto = DNPROTO_NSP;
-	if (dn_route_output_sock(&sk->sk_dst_cache, &fl, sk, 0) == 0) {
+	memset(&fld, 0, sizeof(fld));
+	fld.flowidn_oif = sk->sk_bound_dev_if;
+	fld.saddr = dn_saddr2dn(&scp->addr);
+	fld.daddr = dn_saddr2dn(&scp->peer);
+	dn_sk_ports_copy(&fld, scp);
+	fld.flowidn_proto = DNPROTO_NSP;
+	if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, 0) == 0) {
 		dst = sk_dst_get(sk);
 		sk->sk_route_caps = dst->dev->features;
 		goto try_again;
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index d74d34b93f80..9f09d4fc2880 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -282,14 +282,14 @@ static void dn_dst_link_failure(struct sk_buff *skb)
 {
 }
 
-static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
+static inline int compare_keys(struct flowidn *fl1, struct flowidn *fl2)
 {
-	return ((fl1->fld_dst ^ fl2->fld_dst) |
-		(fl1->fld_src ^ fl2->fld_src) |
-		(fl1->flowi_mark ^ fl2->flowi_mark) |
-		(fl1->fld_scope ^ fl2->fld_scope) |
-		(fl1->flowi_oif ^ fl2->flowi_oif) |
-		(fl1->flowi_iif ^ fl2->flowi_iif)) == 0;
+	return ((fl1->daddr ^ fl2->daddr) |
+		(fl1->saddr ^ fl2->saddr) |
+		(fl1->flowidn_mark ^ fl2->flowidn_mark) |
+		(fl1->flowidn_scope ^ fl2->flowidn_scope) |
+		(fl1->flowidn_oif ^ fl2->flowidn_oif) |
+		(fl1->flowidn_iif ^ fl2->flowidn_iif)) == 0;
 }
 
 static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp)
@@ -303,7 +303,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route *
 	spin_lock_bh(&dn_rt_hash_table[hash].lock);
 	while ((rth = rcu_dereference_protected(*rthp,
 						lockdep_is_held(&dn_rt_hash_table[hash].lock))) != NULL) {
-		if (compare_keys(&rth->fl, &rt->fl)) {
+		if (compare_keys(&rth->fld, &rt->fld)) {
 			/* Put it first */
 			*rthp = rth->dst.dn_next;
 			rcu_assign_pointer(rth->dst.dn_next,
@@ -903,15 +903,15 @@ static inline __le16 dn_fib_rules_map_destination(__le16 daddr, struct dn_fib_re
 	return (daddr&~mask)|res->fi->fib_nh->nh_gw;
 }
 
-static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *oldflp, int try_hard)
+static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *oldflp, int try_hard)
 {
-	struct flowi fl = {
-		.fld_dst = oldflp->fld_dst,
-		.fld_src = oldflp->fld_src,
-		.fld_scope = RT_SCOPE_UNIVERSE,
-		.flowi_mark = oldflp->flowi_mark,
-		.flowi_iif = init_net.loopback_dev->ifindex,
-		.flowi_oif = oldflp->flowi_oif,
+	struct flowidn fld = {
+		.daddr = oldflp->daddr,
+		.saddr = oldflp->saddr,
+		.flowidn_scope = RT_SCOPE_UNIVERSE,
+		.flowidn_mark = oldflp->flowidn_mark,
+		.flowidn_iif = init_net.loopback_dev->ifindex,
+		.flowidn_oif = oldflp->flowidn_oif,
 	};
 	struct dn_route *rt = NULL;
 	struct net_device *dev_out = NULL, *dev;
@@ -926,13 +926,14 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old
 	if (decnet_debug_level & 16)
 		printk(KERN_DEBUG
 		       "dn_route_output_slow: dst=%04x src=%04x mark=%d"
-		       " iif=%d oif=%d\n", le16_to_cpu(oldflp->fld_dst),
-		       le16_to_cpu(oldflp->fld_src),
-		       oldflp->flowi_mark, init_net.loopback_dev->ifindex, oldflp->flowi_oif);
+		       " iif=%d oif=%d\n", le16_to_cpu(oldflp->daddr),
+		       le16_to_cpu(oldflp->saddr),
+		       oldflp->flowidn_mark, init_net.loopback_dev->ifindex,
+		       oldflp->flowidn_oif);
 
 	/* If we have an output interface, verify its a DECnet device */
-	if (oldflp->flowi_oif) {
-		dev_out = dev_get_by_index(&init_net, oldflp->flowi_oif);
+	if (oldflp->flowidn_oif) {
+		dev_out = dev_get_by_index(&init_net, oldflp->flowidn_oif);
 		err = -ENODEV;
 		if (dev_out && dev_out->dn_ptr == NULL) {
 			dev_put(dev_out);
@@ -943,11 +944,11 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old
 	}
 
 	/* If we have a source address, verify that its a local address */
-	if (oldflp->fld_src) {
+	if (oldflp->saddr) {
 		err = -EADDRNOTAVAIL;
 
 		if (dev_out) {
-			if (dn_dev_islocal(dev_out, oldflp->fld_src))
+			if (dn_dev_islocal(dev_out, oldflp->saddr))
 				goto source_ok;
 			dev_put(dev_out);
 			goto out;
@@ -956,11 +957,11 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old
 		for_each_netdev_rcu(&init_net, dev) {
 			if (!dev->dn_ptr)
 				continue;
-			if (!dn_dev_islocal(dev, oldflp->fld_src))
+			if (!dn_dev_islocal(dev, oldflp->saddr))
 				continue;
 			if ((dev->flags & IFF_LOOPBACK) &&
-			    oldflp->fld_dst &&
-			    !dn_dev_islocal(dev, oldflp->fld_dst))
+			    oldflp->daddr &&
+			    !dn_dev_islocal(dev, oldflp->daddr))
 				continue;
 
 			dev_out = dev;
@@ -975,22 +976,22 @@ source_ok:
 	}
 
 	/* No destination? Assume its local */
-	if (!fl.fld_dst) {
-		fl.fld_dst = fl.fld_src;
+	if (!fld.daddr) {
+		fld.daddr = fld.saddr;
 
 		err = -EADDRNOTAVAIL;
 		if (dev_out)
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
-		if (!fl.fld_dst) {
-			fl.fld_dst =
-			fl.fld_src = dnet_select_source(dev_out, 0,
+		if (!fld.daddr) {
+			fld.daddr =
+			fld.saddr = dnet_select_source(dev_out, 0,
 						       RT_SCOPE_HOST);
-			if (!fl.fld_dst)
+			if (!fld.daddr)
 				goto out;
 		}
-		fl.flowi_oif = init_net.loopback_dev->ifindex;
+		fld.flowidn_oif = init_net.loopback_dev->ifindex;
 		res.type = RTN_LOCAL;
 		goto make_route;
 	}
@@ -999,8 +1000,8 @@ source_ok:
 		printk(KERN_DEBUG
 		       "dn_route_output_slow: initial checks complete."
 		       " dst=%o4x src=%04x oif=%d try_hard=%d\n",
-		       le16_to_cpu(fl.fld_dst), le16_to_cpu(fl.fld_src),
-		       fl.flowi_oif, try_hard);
+		       le16_to_cpu(fld.daddr), le16_to_cpu(fld.saddr),
+		       fld.flowidn_oif, try_hard);
 
 	/*
 	 * N.B. If the kernel is compiled without router support then
@@ -1008,7 +1009,7 @@ source_ok:
 	 * will always be executed.
 	 */
 	err = -ESRCH;
-	if (try_hard || (err = dn_fib_lookup(&fl, &res)) != 0) {
+	if (try_hard || (err = dn_fib_lookup(&fld, &res)) != 0) {
 		struct dn_dev *dn_db;
 		if (err != -ESRCH)
 			goto out;
@@ -1023,19 +1024,19 @@ source_ok:
 		 * here
 		 */
 		if (!try_hard) {
-			neigh = neigh_lookup_nodev(&dn_neigh_table, &init_net, &fl.fld_dst);
+			neigh = neigh_lookup_nodev(&dn_neigh_table, &init_net, &fld.daddr);
 			if (neigh) {
-				if ((oldflp->flowi_oif &&
-				    (neigh->dev->ifindex != oldflp->flowi_oif)) ||
-				    (oldflp->fld_src &&
+				if ((oldflp->flowidn_oif &&
+				    (neigh->dev->ifindex != oldflp->flowidn_oif)) ||
+				    (oldflp->saddr &&
 				    (!dn_dev_islocal(neigh->dev,
-						      oldflp->fld_src)))) {
+						     oldflp->saddr)))) {
 					neigh_release(neigh);
 					neigh = NULL;
 				} else {
 					if (dev_out)
 						dev_put(dev_out);
-					if (dn_dev_islocal(neigh->dev, fl.fld_dst)) {
+					if (dn_dev_islocal(neigh->dev, fld.daddr)) {
 						dev_out = init_net.loopback_dev;
 						res.type = RTN_LOCAL;
 					} else {
@@ -1055,7 +1056,7 @@ source_ok:
 			goto out;
 		dn_db = rcu_dereference_raw(dev_out->dn_ptr);
 		/* Possible improvement - check all devices for local addr */
-		if (dn_dev_islocal(dev_out, fl.fld_dst)) {
+		if (dn_dev_islocal(dev_out, fld.daddr)) {
 			dev_put(dev_out);
 			dev_out = init_net.loopback_dev;
 			dev_hold(dev_out);
@@ -1071,16 +1072,16 @@ select_source:
 		if (neigh)
 			gateway = ((struct dn_neigh *)neigh)->addr;
 		if (gateway == 0)
-			gateway = fl.fld_dst;
-		if (fl.fld_src == 0) {
-			fl.fld_src = dnet_select_source(dev_out, gateway,
-							 res.type == RTN_LOCAL ?
-							 RT_SCOPE_HOST :
-							 RT_SCOPE_LINK);
-			if (fl.fld_src == 0 && res.type != RTN_LOCAL)
+			gateway = fld.daddr;
+		if (fld.saddr == 0) {
+			fld.saddr = dnet_select_source(dev_out, gateway,
+						       res.type == RTN_LOCAL ?
+						       RT_SCOPE_HOST :
+						       RT_SCOPE_LINK);
+			if (fld.saddr == 0 && res.type != RTN_LOCAL)
 				goto e_addr;
 		}
-		fl.flowi_oif = dev_out->ifindex;
+		fld.flowidn_oif = dev_out->ifindex;
 		goto make_route;
 	}
 	free_res = 1;
@@ -1089,35 +1090,35 @@ select_source:
 		goto e_inval;
 
 	if (res.type == RTN_LOCAL) {
-		if (!fl.fld_src)
-			fl.fld_src = fl.fld_dst;
+		if (!fld.saddr)
+			fld.saddr = fld.daddr;
 		if (dev_out)
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
-		fl.flowi_oif = dev_out->ifindex;
+		fld.flowidn_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
 		res.fi = NULL;
 		goto make_route;
 	}
 
-	if (res.fi->fib_nhs > 1 && fl.flowi_oif == 0)
-		dn_fib_select_multipath(&fl, &res);
+	if (res.fi->fib_nhs > 1 && fld.flowidn_oif == 0)
+		dn_fib_select_multipath(&fld, &res);
 
 	/*
 	 * We could add some logic to deal with default routes here and
 	 * get rid of some of the special casing above.
 	 */
 
-	if (!fl.fld_src)
-		fl.fld_src = DN_FIB_RES_PREFSRC(res);
+	if (!fld.saddr)
+		fld.saddr = DN_FIB_RES_PREFSRC(res);
 
 	if (dev_out)
 		dev_put(dev_out);
 	dev_out = DN_FIB_RES_DEV(res);
 	dev_hold(dev_out);
-	fl.flowi_oif = dev_out->ifindex;
+	fld.flowidn_oif = dev_out->ifindex;
 	gateway = DN_FIB_RES_GW(res);
 
 make_route:
@@ -1131,19 +1132,19 @@ make_route:
 	atomic_set(&rt->dst.__refcnt, 1);
 	rt->dst.flags   = DST_HOST;
 
-	rt->fl.fld_src    = oldflp->fld_src;
-	rt->fl.fld_dst    = oldflp->fld_dst;
-	rt->fl.flowi_oif     = oldflp->flowi_oif;
-	rt->fl.flowi_iif     = 0;
-	rt->fl.flowi_mark    = oldflp->flowi_mark;
+	rt->fld.saddr        = oldflp->saddr;
+	rt->fld.daddr        = oldflp->daddr;
+	rt->fld.flowidn_oif  = oldflp->flowidn_oif;
+	rt->fld.flowidn_iif  = 0;
+	rt->fld.flowidn_mark = oldflp->flowidn_mark;
 
-	rt->rt_saddr      = fl.fld_src;
-	rt->rt_daddr      = fl.fld_dst;
-	rt->rt_gateway    = gateway ? gateway : fl.fld_dst;
-	rt->rt_local_src  = fl.fld_src;
+	rt->rt_saddr      = fld.saddr;
+	rt->rt_daddr      = fld.daddr;
+	rt->rt_gateway    = gateway ? gateway : fld.daddr;
+	rt->rt_local_src  = fld.saddr;
 
-	rt->rt_dst_map    = fl.fld_dst;
-	rt->rt_src_map    = fl.fld_src;
+	rt->rt_dst_map    = fld.daddr;
+	rt->rt_src_map    = fld.saddr;
 
 	rt->dst.dev = dev_out;
 	dev_hold(dev_out);
@@ -1161,7 +1162,7 @@ make_route:
 	if (err)
 		goto e_neighbour;
 
-	hash = dn_hash(rt->fl.fld_src, rt->fl.fld_dst);
+	hash = dn_hash(rt->fld.saddr, rt->fld.daddr);
 	dn_insert_route(rt, hash, (struct dn_route **)pprt);
 
 done:
@@ -1192,20 +1193,20 @@ e_neighbour:
 /*
  * N.B. The flags may be moved into the flowi at some future stage.
  */
-static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *flp, int flags)
+static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn *flp, int flags)
 {
-	unsigned hash = dn_hash(flp->fld_src, flp->fld_dst);
+	unsigned hash = dn_hash(flp->saddr, flp->daddr);
 	struct dn_route *rt = NULL;
 
 	if (!(flags & MSG_TRYHARD)) {
 		rcu_read_lock_bh();
 		for (rt = rcu_dereference_bh(dn_rt_hash_table[hash].chain); rt;
 			rt = rcu_dereference_bh(rt->dst.dn_next)) {
-			if ((flp->fld_dst == rt->fl.fld_dst) &&
-			    (flp->fld_src == rt->fl.fld_src) &&
-			    (flp->flowi_mark == rt->fl.flowi_mark) &&
+			if ((flp->daddr == rt->fld.daddr) &&
+			    (flp->saddr == rt->fld.saddr) &&
+			    (flp->flowidn_mark == rt->fld.flowidn_mark) &&
 			    dn_is_output_route(rt) &&
-			    (rt->fl.flowi_oif == flp->flowi_oif)) {
+			    (rt->fld.flowidn_oif == flp->flowidn_oif)) {
 				dst_use(&rt->dst, jiffies);
 				rcu_read_unlock_bh();
 				*pprt = &rt->dst;
@@ -1218,13 +1219,14 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *fl
 	return dn_route_output_slow(pprt, flp, flags);
 }
 
-static int dn_route_output_key(struct dst_entry **pprt, struct flowi *flp, int flags)
+static int dn_route_output_key(struct dst_entry **pprt, struct flowidn *flp, int flags)
 {
 	int err;
 
 	err = __dn_route_output_key(pprt, flp, flags);
-	if (err == 0 && flp->flowi_proto) {
-		*pprt = xfrm_lookup(&init_net, *pprt, flp, NULL, 0);
+	if (err == 0 && flp->flowidn_proto) {
+		*pprt = xfrm_lookup(&init_net, *pprt,
+				    flowidn_to_flowi(flp), NULL, 0);
 		if (IS_ERR(*pprt)) {
 			err = PTR_ERR(*pprt);
 			*pprt = NULL;
@@ -1233,15 +1235,16 @@ static int dn_route_output_key(struct dst_entry **pprt, struct flowi *flp, int f
 	return err;
 }
 
-int dn_route_output_sock(struct dst_entry **pprt, struct flowi *fl, struct sock *sk, int flags)
+int dn_route_output_sock(struct dst_entry **pprt, struct flowidn *fl, struct sock *sk, int flags)
 {
 	int err;
 
 	err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD);
-	if (err == 0 && fl->flowi_proto) {
+	if (err == 0 && fl->flowidn_proto) {
 		if (!(flags & MSG_DONTWAIT))
-			fl->flowi_flags |= FLOWI_FLAG_CAN_SLEEP;
-		*pprt = xfrm_lookup(&init_net, *pprt, fl, sk, 0);
+			fl->flowidn_flags |= FLOWI_FLAG_CAN_SLEEP;
+		*pprt = xfrm_lookup(&init_net, *pprt,
+				    flowidn_to_flowi(fl), sk, 0);
 		if (IS_ERR(*pprt)) {
 			err = PTR_ERR(*pprt);
 			*pprt = NULL;
@@ -1262,12 +1265,12 @@ static int dn_route_input_slow(struct sk_buff *skb)
 	int flags = 0;
 	__le16 gateway = 0;
 	__le16 local_src = 0;
-	struct flowi fl = {
-		.fld_dst = cb->dst,
-		.fld_src = cb->src,
-		.fld_scope = RT_SCOPE_UNIVERSE,
-		.flowi_mark = skb->mark,
-		.flowi_iif = skb->dev->ifindex,
+	struct flowidn fld = {
+		.daddr = cb->dst,
+		.saddr = cb->src,
+		.flowidn_scope = RT_SCOPE_UNIVERSE,
+		.flowidn_mark = skb->mark,
+		.flowidn_iif = skb->dev->ifindex,
 	};
 	struct dn_fib_res res = { .fi = NULL, .type = RTN_UNREACHABLE };
 	int err = -EINVAL;
@@ -1279,7 +1282,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
 		goto out;
 
 	/* Zero source addresses are not allowed */
-	if (fl.fld_src == 0)
+	if (fld.saddr == 0)
 		goto out;
 
 	/*
@@ -1293,7 +1296,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
 	if (dn_dev_islocal(in_dev, cb->src))
 		goto out;
 
-	err = dn_fib_lookup(&fl, &res);
+	err = dn_fib_lookup(&fld, &res);
 	if (err) {
 		if (err != -ESRCH)
 			goto out;
@@ -1305,7 +1308,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
 
 		res.type = RTN_LOCAL;
 	} else {
-		__le16 src_map = fl.fld_src;
+		__le16 src_map = fld.saddr;
 		free_res = 1;
 
 		out_dev = DN_FIB_RES_DEV(res);
@@ -1318,22 +1321,22 @@ static int dn_route_input_slow(struct sk_buff *skb)
 		dev_hold(out_dev);
 
 		if (res.r)
-			src_map = fl.fld_src; /* no NAT support for now */
+			src_map = fld.saddr; /* no NAT support for now */
 
 		gateway = DN_FIB_RES_GW(res);
 		if (res.type == RTN_NAT) {
-			fl.fld_dst = dn_fib_rules_map_destination(fl.fld_dst, &res);
+			fld.daddr = dn_fib_rules_map_destination(fld.daddr, &res);
 			dn_fib_res_put(&res);
 			free_res = 0;
-			if (dn_fib_lookup(&fl, &res))
+			if (dn_fib_lookup(&fld, &res))
 				goto e_inval;
 			free_res = 1;
 			if (res.type != RTN_UNICAST)
 				goto e_inval;
 			flags |= RTCF_DNAT;
-			gateway = fl.fld_dst;
+			gateway = fld.daddr;
 		}
-		fl.fld_src = src_map;
+		fld.saddr = src_map;
 	}
 
 	switch(res.type) {
@@ -1347,8 +1350,8 @@ static int dn_route_input_slow(struct sk_buff *skb)
 		if (dn_db->parms.forwarding == 0)
 			goto e_inval;
 
-		if (res.fi->fib_nhs > 1 && fl.flowi_oif == 0)
-			dn_fib_select_multipath(&fl, &res);
+		if (res.fi->fib_nhs > 1 && fld.flowidn_oif == 0)
+			dn_fib_select_multipath(&fld, &res);
 
 		/*
 		 * Check for out_dev == in_dev. We use the RTCF_DOREDIRECT
@@ -1366,8 +1369,8 @@ static int dn_route_input_slow(struct sk_buff *skb)
 		break;
 	case RTN_LOCAL:
 		flags |= RTCF_LOCAL;
-		fl.fld_src = cb->dst;
-		fl.fld_dst = cb->src;
+		fld.saddr = cb->dst;
+		fld.daddr = cb->src;
 
 		/* Routing tables gave us a gateway */
 		if (gateway)
@@ -1400,21 +1403,21 @@ make_route:
 	if (rt == NULL)
 		goto e_nobufs;
 
-	rt->rt_saddr      = fl.fld_src;
-	rt->rt_daddr      = fl.fld_dst;
-	rt->rt_gateway    = fl.fld_dst;
+	rt->rt_saddr      = fld.saddr;
+	rt->rt_daddr      = fld.daddr;
+	rt->rt_gateway    = fld.daddr;
 	if (gateway)
 		rt->rt_gateway = gateway;
 	rt->rt_local_src  = local_src ? local_src : rt->rt_saddr;
 
-	rt->rt_dst_map    = fl.fld_dst;
-	rt->rt_src_map    = fl.fld_src;
+	rt->rt_dst_map    = fld.daddr;
+	rt->rt_src_map    = fld.saddr;
 
-	rt->fl.fld_src    = cb->src;
-	rt->fl.fld_dst    = cb->dst;
-	rt->fl.flowi_oif     = 0;
-	rt->fl.flowi_iif     = in_dev->ifindex;
-	rt->fl.flowi_mark    = fl.flowi_mark;
+	rt->fld.saddr        = cb->src;
+	rt->fld.daddr        = cb->dst;
+	rt->fld.flowidn_oif  = 0;
+	rt->fld.flowidn_iif  = in_dev->ifindex;
+	rt->fld.flowidn_mark = fld.flowidn_mark;
 
 	rt->dst.flags = DST_HOST;
 	rt->dst.neighbour = neigh;
@@ -1444,7 +1447,7 @@ make_route:
 	if (err)
 		goto e_neighbour;
 
-	hash = dn_hash(rt->fl.fld_src, rt->fl.fld_dst);
+	hash = dn_hash(rt->fld.saddr, rt->fld.daddr);
 	dn_insert_route(rt, hash, &rt);
 	skb_dst_set(skb, &rt->dst);
 
@@ -1484,11 +1487,11 @@ static int dn_route_input(struct sk_buff *skb)
 	rcu_read_lock();
 	for(rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt != NULL;
 	    rt = rcu_dereference(rt->dst.dn_next)) {
-		if ((rt->fl.fld_src == cb->src) &&
-		    (rt->fl.fld_dst == cb->dst) &&
-		    (rt->fl.flowi_oif == 0) &&
-		    (rt->fl.flowi_mark == skb->mark) &&
-		    (rt->fl.flowi_iif == cb->iif)) {
+		if ((rt->fld.saddr == cb->src) &&
+		    (rt->fld.daddr == cb->dst) &&
+		    (rt->fld.flowidn_oif == 0) &&
+		    (rt->fld.flowidn_mark == skb->mark) &&
+		    (rt->fld.flowidn_iif == cb->iif)) {
 			dst_use(&rt->dst, jiffies);
 			rcu_read_unlock();
 			skb_dst_set(skb, (struct dst_entry *)rt);
@@ -1524,9 +1527,9 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	if (rt->rt_flags & RTCF_NOTIFY)
 		r->rtm_flags |= RTM_F_NOTIFY;
 	RTA_PUT(skb, RTA_DST, 2, &rt->rt_daddr);
-	if (rt->fl.fld_src) {
+	if (rt->fld.saddr) {
 		r->rtm_src_len = 16;
-		RTA_PUT(skb, RTA_SRC, 2, &rt->fl.fld_src);
+		RTA_PUT(skb, RTA_SRC, 2, &rt->fld.saddr);
 	}
 	if (rt->dst.dev)
 		RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->dst.dev->ifindex);
@@ -1545,7 +1548,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 			       rt->dst.error) < 0)
 		goto rtattr_failure;
 	if (dn_is_input_route(rt))
-		RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.flowi_iif);
+		RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fld.flowidn_iif);
 
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	return skb->len;
@@ -1568,13 +1571,13 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 	struct dn_skb_cb *cb;
 	int err;
 	struct sk_buff *skb;
-	struct flowi fl;
+	struct flowidn fld;
 
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	memset(&fl, 0, sizeof(fl));
-	fl.flowi_proto = DNPROTO_NSP;
+	memset(&fld, 0, sizeof(fld));
+	fld.flowidn_proto = DNPROTO_NSP;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb == NULL)
@@ -1583,15 +1586,15 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 	cb = DN_SKB_CB(skb);
 
 	if (rta[RTA_SRC-1])
-		memcpy(&fl.fld_src, RTA_DATA(rta[RTA_SRC-1]), 2);
+		memcpy(&fld.saddr, RTA_DATA(rta[RTA_SRC-1]), 2);
 	if (rta[RTA_DST-1])
-		memcpy(&fl.fld_dst, RTA_DATA(rta[RTA_DST-1]), 2);
+		memcpy(&fld.daddr, RTA_DATA(rta[RTA_DST-1]), 2);
 	if (rta[RTA_IIF-1])
-		memcpy(&fl.flowi_iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));
+		memcpy(&fld.flowidn_iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));
 
-	if (fl.flowi_iif) {
+	if (fld.flowidn_iif) {
 		struct net_device *dev;
-		if ((dev = dev_get_by_index(&init_net, fl.flowi_iif)) == NULL) {
+		if ((dev = dev_get_by_index(&init_net, fld.flowidn_iif)) == NULL) {
 			kfree_skb(skb);
 			return -ENODEV;
 		}
@@ -1602,8 +1605,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 		}
 		skb->protocol = htons(ETH_P_DNA_RT);
 		skb->dev = dev;
-		cb->src = fl.fld_src;
-		cb->dst = fl.fld_dst;
+		cb->src = fld.saddr;
+		cb->dst = fld.daddr;
 		local_bh_disable();
 		err = dn_route_input(skb);
 		local_bh_enable();
@@ -1615,8 +1618,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
 		int oif = 0;
 		if (rta[RTA_OIF - 1])
 			memcpy(&oif, RTA_DATA(rta[RTA_OIF - 1]), sizeof(int));
-		fl.flowi_oif = oif;
-		err = dn_route_output_key((struct dst_entry **)&rt, &fl, 0);
+		fld.flowidn_oif = oif;
+		err = dn_route_output_key((struct dst_entry **)&rt, &fld, 0);
 	}
 
 	if (skb->dev)
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index 6eb91df3c550..f0efb0ccfeca 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -49,14 +49,15 @@ struct dn_fib_rule
 };
 
 
-int dn_fib_lookup(struct flowi *flp, struct dn_fib_res *res)
+int dn_fib_lookup(struct flowidn *flp, struct dn_fib_res *res)
 {
 	struct fib_lookup_arg arg = {
 		.result = res,
 	};
 	int err;
 
-	err = fib_rules_lookup(dn_fib_rules_ops, flp, 0, &arg);
+	err = fib_rules_lookup(dn_fib_rules_ops,
+			       flowidn_to_flowi(flp), 0, &arg);
 	res->r = arg.rule;
 
 	return err;
@@ -65,6 +66,7 @@ int dn_fib_lookup(struct flowi *flp, struct dn_fib_res *res)
 static int dn_fib_rule_action(struct fib_rule *rule, struct flowi *flp,
 			      int flags, struct fib_lookup_arg *arg)
 {
+	struct flowidn *fld = &flp->u.dn;
 	int err = -EAGAIN;
 	struct dn_fib_table *tbl;
 
@@ -90,7 +92,7 @@ static int dn_fib_rule_action(struct fib_rule *rule, struct flowi *flp,
 	if (tbl == NULL)
 		goto errout;
 
-	err = tbl->lookup(tbl, flp, (struct dn_fib_res *)arg->result);
+	err = tbl->lookup(tbl, fld, (struct dn_fib_res *)arg->result);
 	if (err > 0)
 		err = -EAGAIN;
 errout:
@@ -104,8 +106,9 @@ static const struct nla_policy dn_fib_rule_policy[FRA_MAX+1] = {
 static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 {
 	struct dn_fib_rule *r = (struct dn_fib_rule *)rule;
-	__le16 daddr = fl->fld_dst;
-	__le16 saddr = fl->fld_src;
+	struct flowidn *fld = &fl->u.dn;
+	__le16 daddr = fld->daddr;
+	__le16 saddr = fld->saddr;
 
 	if (((saddr ^ r->src) & r->srcmask) ||
 	    ((daddr ^ r->dst) & r->dstmask))
@@ -175,7 +178,7 @@ static int dn_fib_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 
 unsigned dnet_addr_type(__le16 addr)
 {
-	struct flowi fl = { .fld_dst = addr };
+	struct flowidn fld = { .daddr = addr };
 	struct dn_fib_res res;
 	unsigned ret = RTN_UNICAST;
 	struct dn_fib_table *tb = dn_fib_get_table(RT_TABLE_LOCAL, 0);
@@ -183,7 +186,7 @@ unsigned dnet_addr_type(__le16 addr)
 	res.r = NULL;
 
 	if (tb) {
-		if (!tb->lookup(tb, &fl, &res)) {
+		if (!tb->lookup(tb, &fld, &res)) {
 			ret = res.type;
 			dn_fib_res_put(&res);
 		}
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index b66600b3f4b5..99d8d3a40998 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -764,7 +764,7 @@ static int dn_fib_table_flush(struct dn_fib_table *tb)
 	return found;
 }
 
-static int dn_fib_table_lookup(struct dn_fib_table *tb, const struct flowi *flp, struct dn_fib_res *res)
+static int dn_fib_table_lookup(struct dn_fib_table *tb, const struct flowidn *flp, struct dn_fib_res *res)
 {
 	int err;
 	struct dn_zone *dz;
@@ -773,7 +773,7 @@ static int dn_fib_table_lookup(struct dn_fib_table *tb, const struct flowi *flp,
 	read_lock(&dn_fib_tables_lock);
 	for(dz = t->dh_zone_list; dz; dz = dz->dz_next) {
 		struct dn_fib_node *f;
-		dn_fib_key_t k = dz_key(flp->fld_dst, dz);
+		dn_fib_key_t k = dz_key(flp->daddr, dz);
 
 		for(f = dz_chain(k, dz); f; f = f->fn_next) {
 			if (!dn_key_eq(k, f->fn_key)) {
@@ -788,7 +788,7 @@ static int dn_fib_table_lookup(struct dn_fib_table *tb, const struct flowi *flp,
 			if (f->fn_state&DN_S_ZOMBIE)
 				continue;
 
-			if (f->fn_scope < flp->fld_scope)
+			if (f->fn_scope < flp->flowidn_scope)
 				continue;
 
 			err = dn_fib_semantic_match(f->fn_type, DN_FIB_INFO(f), flp, res);
-- 
cgit v1.2.3


From f831c963b5c20bec230edce89e25f369996be5db Mon Sep 17 00:00:00 2001
From: Allan Stephens <Allan.Stephens@windriver.com>
Date: Fri, 25 Feb 2011 14:22:11 -0500
Subject: tipc: Eliminate configuration for maximum number of cluster nodes

Gets rid of the need for users to specify the maximum number of
cluster nodes supported by TIPC. TIPC now automatically provides
support for all 4K nodes allowed by its addressing scheme.

Note: This change sets TIPC's memory usage to the amount used by
a maximum size node table with 4K entries.  An upcoming patch that
converts the node table from a linear array to a hash table will
compact the node table to a more efficient design, but for clarity
it is nice to have all the Kconfig infrastruture go away separately.

Signed-off-by: Allan Stephens <Allan.Stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/tipc_config.h |  4 ++--
 net/tipc/Kconfig            | 12 ------------
 net/tipc/addr.c             | 11 +++--------
 net/tipc/config.c           | 29 +++--------------------------
 net/tipc/core.c             |  6 ------
 net/tipc/core.h             |  1 -
 net/tipc/net.c              |  3 +--
 7 files changed, 9 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h
index 011556fcef04..64aba5a0e9c7 100644
--- a/include/linux/tipc_config.h
+++ b/include/linux/tipc_config.h
@@ -89,7 +89,7 @@
 #define  TIPC_CMD_GET_MAX_SUBSCR    0x4006    /* tx none, rx unsigned */
 #define  TIPC_CMD_GET_MAX_ZONES     0x4007    /* obsoleted */
 #define  TIPC_CMD_GET_MAX_CLUSTERS  0x4008    /* obsoleted */
-#define  TIPC_CMD_GET_MAX_NODES     0x4009    /* tx none, rx unsigned */
+#define  TIPC_CMD_GET_MAX_NODES     0x4009    /* obsoleted */
 #define  TIPC_CMD_GET_MAX_SLAVES    0x400A    /* obsoleted */
 #define  TIPC_CMD_GET_NETID         0x400B    /* tx none, rx unsigned */
 
@@ -115,7 +115,7 @@
 #define  TIPC_CMD_SET_MAX_SUBSCR    0x8006    /* tx unsigned, rx none */
 #define  TIPC_CMD_SET_MAX_ZONES     0x8007    /* obsoleted */
 #define  TIPC_CMD_SET_MAX_CLUSTERS  0x8008    /* obsoleted */
-#define  TIPC_CMD_SET_MAX_NODES     0x8009    /* tx unsigned, rx none */
+#define  TIPC_CMD_SET_MAX_NODES     0x8009    /* obsoleted */
 #define  TIPC_CMD_SET_MAX_SLAVES    0x800A    /* obsoleted */
 #define  TIPC_CMD_SET_NETID         0x800B    /* tx unsigned, rx none */
 
diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig
index 0436927369f3..2c5954b85933 100644
--- a/net/tipc/Kconfig
+++ b/net/tipc/Kconfig
@@ -29,18 +29,6 @@ config TIPC_ADVANCED
 	  Saying Y here will open some advanced configuration for TIPC.
 	  Most users do not need to bother; if unsure, just say N.
 
-config TIPC_NODES
-	int "Maximum number of nodes in a cluster"
-	depends on TIPC_ADVANCED
-	range 8 2047
-	default "255"
-	help
-	  Specifies how many nodes can be supported in a TIPC cluster.
-	  Can range from 8 to 2047 nodes; default is 255.
-
-	  Setting this to a smaller value saves some memory;
-	  setting it to higher allows for more nodes.
-
 config TIPC_PORTS
 	int "Maximum number of ports in a node"
 	depends on TIPC_ADVANCED
diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index 087e399518c1..a6fdab33877e 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -2,7 +2,7 @@
  * net/tipc/addr.c: TIPC address utility routines
  *
  * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2004-2005, Wind River Systems
+ * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -41,7 +41,7 @@
  * tipc_addr_domain_valid - validates a network domain address
  *
  * Accepts <Z.C.N>, <Z.C.0>, <Z.0.0>, and <0.0.0>,
- * where Z, C, and N are non-zero and do not exceed the configured limits.
+ * where Z, C, and N are non-zero.
  *
  * Returns 1 if domain address is valid, otherwise 0
  */
@@ -51,10 +51,6 @@ int tipc_addr_domain_valid(u32 addr)
 	u32 n = tipc_node(addr);
 	u32 c = tipc_cluster(addr);
 	u32 z = tipc_zone(addr);
-	u32 max_nodes = tipc_max_nodes;
-
-	if (n > max_nodes)
-		return 0;
 
 	if (n && (!z || !c))
 		return 0;
@@ -66,8 +62,7 @@ int tipc_addr_domain_valid(u32 addr)
 /**
  * tipc_addr_node_valid - validates a proposed network address for this node
  *
- * Accepts <Z.C.N>, where Z, C, and N are non-zero and do not exceed
- * the configured limits.
+ * Accepts <Z.C.N>, where Z, C, and N are non-zero.
  *
  * Returns 1 if address can be used, otherwise 0
  */
diff --git a/net/tipc/config.c b/net/tipc/config.c
index e16750dcf3c1..fa3d50860055 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -2,7 +2,7 @@
  * net/tipc/config.c: TIPC configuration management code
  *
  * Copyright (c) 2002-2006, Ericsson AB
- * Copyright (c) 2004-2007, Wind River Systems
+ * Copyright (c) 2004-2007, 2010-2011, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -260,25 +260,6 @@ static struct sk_buff *cfg_set_max_ports(void)
 	return tipc_cfg_reply_none();
 }
 
-static struct sk_buff *cfg_set_max_nodes(void)
-{
-	u32 value;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-	value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	if (value == tipc_max_nodes)
-		return tipc_cfg_reply_none();
-	if (value != delimit(value, 8, 2047))
-		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
-						   " (max nodes must be 8-2047)");
-	if (tipc_mode == TIPC_NET_MODE)
-		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
-			" (cannot change max nodes once TIPC has joined a network)");
-	tipc_max_nodes = value;
-	return tipc_cfg_reply_none();
-}
-
 static struct sk_buff *cfg_set_netid(void)
 {
 	u32 value;
@@ -397,9 +378,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 	case TIPC_CMD_SET_MAX_SUBSCR:
 		rep_tlv_buf = cfg_set_max_subscriptions();
 		break;
-	case TIPC_CMD_SET_MAX_NODES:
-		rep_tlv_buf = cfg_set_max_nodes();
-		break;
 	case TIPC_CMD_SET_NETID:
 		rep_tlv_buf = cfg_set_netid();
 		break;
@@ -415,9 +393,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 	case TIPC_CMD_GET_MAX_SUBSCR:
 		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_subscriptions);
 		break;
-	case TIPC_CMD_GET_MAX_NODES:
-		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_nodes);
-		break;
 	case TIPC_CMD_GET_NETID:
 		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_net_id);
 		break;
@@ -431,6 +406,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 	case TIPC_CMD_GET_MAX_SLAVES:
 	case TIPC_CMD_SET_MAX_CLUSTERS:
 	case TIPC_CMD_GET_MAX_CLUSTERS:
+	case TIPC_CMD_SET_MAX_NODES:
+	case TIPC_CMD_GET_MAX_NODES:
 		rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 							  " (obsolete command)");
 		break;
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 2da1fc75ad65..c9a73e7763f6 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -41,10 +41,6 @@
 #include "config.h"
 
 
-#ifndef CONFIG_TIPC_NODES
-#define CONFIG_TIPC_NODES 255
-#endif
-
 #ifndef CONFIG_TIPC_PORTS
 #define CONFIG_TIPC_PORTS 8191
 #endif
@@ -64,7 +60,6 @@ const char tipc_alphabet[] =
 /* configurable TIPC parameters */
 
 u32 tipc_own_addr;
-int tipc_max_nodes;
 int tipc_max_ports;
 int tipc_max_subscriptions;
 int tipc_max_publications;
@@ -192,7 +187,6 @@ static int __init tipc_init(void)
 	tipc_max_publications = 10000;
 	tipc_max_subscriptions = 2000;
 	tipc_max_ports = CONFIG_TIPC_PORTS;
-	tipc_max_nodes = CONFIG_TIPC_NODES;
 	tipc_net_id = 4711;
 
 	res = tipc_core_start();
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 37544d9f73e1..436dda1159d2 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -147,7 +147,6 @@ void tipc_msg_dbg(struct print_buf *, struct tipc_msg *, const char *);
  */
 
 extern u32 tipc_own_addr;
-extern int tipc_max_nodes;
 extern int tipc_max_ports;
 extern int tipc_max_subscriptions;
 extern int tipc_max_publications;
diff --git a/net/tipc/net.c b/net/tipc/net.c
index f6303d79f7f5..b5b337f5516d 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -114,8 +114,7 @@ atomic_t tipc_num_links;
 
 static int net_start(void)
 {
-	tipc_nodes = kcalloc(tipc_max_nodes + 1,
-				 sizeof(*tipc_nodes), GFP_ATOMIC);
+	tipc_nodes = kcalloc(4096, sizeof(*tipc_nodes), GFP_ATOMIC);
 	tipc_highest_node = 0;
 	atomic_set(&tipc_num_links, 0);
 
-- 
cgit v1.2.3


From 50d3e6399a61fca53c5c440a79f71299db66b803 Mon Sep 17 00:00:00 2001
From: Allan Stephens <Allan.Stephens@windriver.com>
Date: Mon, 28 Feb 2011 14:56:15 -0500
Subject: tipc: Correct misnamed references to neighbor discovery domain

Renames items that are improperly labelled as "network scope" items
(which are represented by simple integer values) rather than "network
domain" items (which are represented by <Z.C.N>-type network addresses).
This change is purely cosmetic, and does not affect the operation of TIPC.

Signed-off-by: Allan Stephens <Allan.Stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/tipc_config.h |  2 +-
 net/tipc/bearer.c           | 14 +++++++-------
 net/tipc/bearer.h           |  2 +-
 net/tipc/config.c           |  2 +-
 4 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h
index 64aba5a0e9c7..0db239590b4d 100644
--- a/include/linux/tipc_config.h
+++ b/include/linux/tipc_config.h
@@ -202,7 +202,7 @@ struct tipc_link_info {
 
 struct tipc_bearer_config {
 	__be32 priority;		/* Range [1,31]. Override per link  */
-	__be32 detect_scope;
+	__be32 disc_domain;		/* <Z.C.N> describing desired nodes */
 	char name[TIPC_MAX_BEARER_NAME];
 };
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index f2839b0f6b65..9815797631e7 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -474,7 +474,7 @@ int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct link *l_ptr)
  * tipc_enable_bearer - enable bearer with the given name
  */
 
-int tipc_enable_bearer(const char *name, u32 bcast_scope, u32 priority)
+int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
 {
 	struct tipc_bearer *b_ptr;
 	struct media *m_ptr;
@@ -494,9 +494,9 @@ int tipc_enable_bearer(const char *name, u32 bcast_scope, u32 priority)
 		warn("Bearer <%s> rejected, illegal name\n", name);
 		return -EINVAL;
 	}
-	if (!tipc_addr_domain_valid(bcast_scope) ||
-	    !tipc_in_scope(bcast_scope, tipc_own_addr)) {
-		warn("Bearer <%s> rejected, illegal broadcast scope\n", name);
+	if (!tipc_addr_domain_valid(disc_domain) ||
+	    !tipc_in_scope(disc_domain, tipc_own_addr)) {
+		warn("Bearer <%s> rejected, illegal discovery domain\n", name);
 		return -EINVAL;
 	}
 	if ((priority < TIPC_MIN_LINK_PRI ||
@@ -560,18 +560,18 @@ restart:
 	b_ptr->media = m_ptr;
 	b_ptr->net_plane = bearer_id + 'A';
 	b_ptr->active = 1;
-	b_ptr->detect_scope = bcast_scope;
+	b_ptr->detect_scope = disc_domain;
 	b_ptr->priority = priority;
 	INIT_LIST_HEAD(&b_ptr->cong_links);
 	INIT_LIST_HEAD(&b_ptr->links);
 	if (m_ptr->bcast) {
 		b_ptr->link_req = tipc_disc_init_link_req(b_ptr, &m_ptr->bcast_addr,
-							  bcast_scope);
+							  disc_domain);
 	}
 	spin_lock_init(&b_ptr->lock);
 	write_unlock_bh(&tipc_net_lock);
 	info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
-	     name, tipc_addr_string_fill(addr_string, bcast_scope), priority);
+	     name, tipc_addr_string_fill(addr_string, disc_domain), priority);
 	return 0;
 failed:
 	write_unlock_bh(&tipc_net_lock);
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 255dea64f7bd..adebdaf0d07b 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -167,7 +167,7 @@ void tipc_recv_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr);
 int  tipc_block_bearer(const char *name);
 void tipc_continue(struct tipc_bearer *tb_ptr);
 
-int tipc_enable_bearer(const char *bearer_name, u32 bcast_scope, u32 priority);
+int tipc_enable_bearer(const char *bearer_name, u32 disc_domain, u32 priority);
 int tipc_disable_bearer(const char *name);
 
 /*
diff --git a/net/tipc/config.c b/net/tipc/config.c
index fa3d50860055..b25a396b7e1e 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -148,7 +148,7 @@ static struct sk_buff *cfg_enable_bearer(void)
 
 	args = (struct tipc_bearer_config *)TLV_DATA(req_tlv_area);
 	if (tipc_enable_bearer(args->name,
-			       ntohl(args->detect_scope),
+			       ntohl(args->disc_domain),
 			       ntohl(args->priority)))
 		return tipc_cfg_reply_error_string("unable to enable bearer");
 
-- 
cgit v1.2.3


From da13051cc756756f10b2da8ea97b05bdf84bd7bb Mon Sep 17 00:00:00 2001
From: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Date: Tue, 30 Nov 2010 15:55:51 -0800
Subject: USB: Remove bitmap #define from hcd.h

Using a #define to redefine a common variable name is a bad thing,
especially when the #define is in a header.  include/linux/usb/hcd.h
redefined bitmap to DeviceRemovable to avoid typing a long field in the
hub descriptor.  This has unintended side effects for files like
drivers/usb/core/devio.c that include that file, since another header
included after hcd.h has different variables named bitmap.

Remove the bitmap #define and replace instances of it in the host
controller code.  Cleanup the spaces around function calls and square
brackets while we're at it.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Cc: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Cc: Tony Olech <tony.olech@elandigitalsystems.com>
Cc: "Robert P. J. Day" <rpjday@crashcourse.ca>
Cc: Max Vozeler <mvz@vozeler.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Cc: Rodolfo Giometti <giometti@linux.it>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Anton Vorontsov <avorontsov@mvista.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Lothar Wassmann <LW@KARO-electronics.de>
Cc: Olav Kongas <ok@artecdesign.ee>
Cc: Martin Fuzzey <mfuzzey@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: David Brownell <dbrownell@users.sourceforge.net>
---
 drivers/staging/usbip/vhci_hcd.c |  4 ++--
 drivers/usb/gadget/dummy_hcd.c   |  4 ++--
 drivers/usb/host/ehci-hub.c      |  4 ++--
 drivers/usb/host/imx21-hcd.c     |  4 ++--
 drivers/usb/host/isp116x-hcd.c   |  6 +++---
 drivers/usb/host/isp1362-hcd.c   |  6 +++---
 drivers/usb/host/isp1760-hcd.c   |  6 +++---
 drivers/usb/host/ohci-hub.c      | 12 ++++++------
 drivers/usb/host/oxu210hp-hcd.c  |  6 +++---
 drivers/usb/host/r8a66597-hcd.c  |  4 ++--
 drivers/usb/host/sl811-hcd.c     |  6 +++---
 drivers/usb/host/u132-hcd.c      | 10 +++++-----
 drivers/usb/host/xhci-hub.c      |  1 -
 drivers/usb/wusbcore/rh.c        |  4 ++--
 include/linux/usb/hcd.h          |  7 -------
 15 files changed, 38 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/usbip/vhci_hcd.c b/drivers/staging/usbip/vhci_hcd.c
index a35fe61268de..0fe7e49cdc37 100644
--- a/drivers/staging/usbip/vhci_hcd.c
+++ b/drivers/staging/usbip/vhci_hcd.c
@@ -255,8 +255,8 @@ static inline void hub_descriptor(struct usb_hub_descriptor *desc)
 	desc->wHubCharacteristics = (__force __u16)
 		(__constant_cpu_to_le16(0x0001));
 	desc->bNbrPorts = VHCI_NPORTS;
-	desc->bitmap[0] = 0xff;
-	desc->bitmap[1] = 0xff;
+	desc->DeviceRemovable[0] = 0xff;
+	desc->DeviceRemovable[1] = 0xff;
 }
 
 static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index 13b9f47feecd..f2040e8af8b1 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -1593,8 +1593,8 @@ hub_descriptor (struct usb_hub_descriptor *desc)
 	desc->bDescLength = 9;
 	desc->wHubCharacteristics = cpu_to_le16(0x0001);
 	desc->bNbrPorts = 1;
-	desc->bitmap [0] = 0xff;
-	desc->bitmap [1] = 0xff;
+	desc->DeviceRemovable[0] = 0xff;
+	desc->DeviceRemovable[1] = 0xff;
 }
 
 static int dummy_hub_control (
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index ae0140dd9b9b..dfa1e1d371c8 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -717,8 +717,8 @@ ehci_hub_descriptor (
 	desc->bDescLength = 7 + 2 * temp;
 
 	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset (&desc->bitmap [0], 0, temp);
-	memset (&desc->bitmap [temp], 0xff, temp);
+	memset(&desc->DeviceRemovable[0], 0, temp);
+	memset(&desc->DeviceRemovable[temp], 0xff, temp);
 
 	temp = 0x0008;			/* per-port overcurrent reporting */
 	if (HCS_PPC (ehci->hcs_params))
diff --git a/drivers/usb/host/imx21-hcd.c b/drivers/usb/host/imx21-hcd.c
index b7dfda8a1d51..2f180dfe5371 100644
--- a/drivers/usb/host/imx21-hcd.c
+++ b/drivers/usb/host/imx21-hcd.c
@@ -1472,8 +1472,8 @@ static int get_hub_descriptor(struct usb_hcd *hcd,
 		0x0010 |	/* No over current protection */
 		0);
 
-	desc->bitmap[0] = 1 << 1;
-	desc->bitmap[1] = ~0;
+	desc->DeviceRemovable[0] = 1 << 1;
+	desc->DeviceRemovable[1] = ~0;
 	return 0;
 }
 
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index 0da7fc05f453..2a60a50bc420 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -951,9 +951,9 @@ static void isp116x_hub_descriptor(struct isp116x *isp116x,
 	/* Power switching, device type, overcurrent. */
 	desc->wHubCharacteristics = cpu_to_le16((u16) ((reg >> 8) & 0x1f));
 	desc->bPwrOn2PwrGood = (u8) ((reg >> 24) & 0xff);
-	/* two bitmaps:  ports removable, and legacy PortPwrCtrlMask */
-	desc->bitmap[0] = 0;
-	desc->bitmap[1] = ~0;
+	/* ports removable, and legacy PortPwrCtrlMask */
+	desc->DeviceRemovable[0] = 0;
+	desc->DeviceRemovable[1] = ~0;
 }
 
 /* Perform reset of a given port.
diff --git a/drivers/usb/host/isp1362-hcd.c b/drivers/usb/host/isp1362-hcd.c
index 02b742df332a..6dd94b997d97 100644
--- a/drivers/usb/host/isp1362-hcd.c
+++ b/drivers/usb/host/isp1362-hcd.c
@@ -1552,9 +1552,9 @@ static void isp1362_hub_descriptor(struct isp1362_hcd *isp1362_hcd,
 	desc->wHubCharacteristics = cpu_to_le16((reg >> 8) & 0x1f);
 	DBG(0, "%s: hubcharacteristics = %02x\n", __func__, cpu_to_le16((reg >> 8) & 0x1f));
 	desc->bPwrOn2PwrGood = (reg >> 24) & 0xff;
-	/* two bitmaps:  ports removable, and legacy PortPwrCtrlMask */
-	desc->bitmap[0] = desc->bNbrPorts == 1 ? 1 << 1 : 3 << 1;
-	desc->bitmap[1] = ~0;
+	/* ports removable, and legacy PortPwrCtrlMask */
+	desc->DeviceRemovable[0] = desc->bNbrPorts == 1 ? 1 << 1 : 3 << 1;
+	desc->DeviceRemovable[1] = ~0;
 
 	DBG(3, "%s: exit\n", __func__);
 }
diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c
index c7c1e0aa0b8e..1c8de7666d6a 100644
--- a/drivers/usb/host/isp1760-hcd.c
+++ b/drivers/usb/host/isp1760-hcd.c
@@ -1751,9 +1751,9 @@ static void isp1760_hub_descriptor(struct isp1760_hcd *priv,
 	temp = 1 + (ports / 8);
 	desc->bDescLength = 7 + 2 * temp;
 
-	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&desc->bitmap[0], 0, temp);
-	memset(&desc->bitmap[temp], 0xff, temp);
+	/* ports removable, and usb 1.0 legacy PortPwrCtrlMask */
+	memset(&desc->DeviceRemovable[0], 0, temp);
+	memset(&desc->DeviceRemovable[temp], 0xff, temp);
 
 	/* per-port overcurrent reporting */
 	temp = 0x0008;
diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index cddcda95b579..cd4b74f27d06 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -580,15 +580,15 @@ ohci_hub_descriptor (
 	    temp |= 0x0008;
 	desc->wHubCharacteristics = (__force __u16)cpu_to_hc16(ohci, temp);
 
-	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
+	/* ports removable, and usb 1.0 legacy PortPwrCtrlMask */
 	rh = roothub_b (ohci);
-	memset(desc->bitmap, 0xff, sizeof(desc->bitmap));
-	desc->bitmap [0] = rh & RH_B_DR;
+	memset(desc->DeviceRemovable, 0xff, sizeof(desc->DeviceRemovable));
+	desc->DeviceRemovable[0] = rh & RH_B_DR;
 	if (ohci->num_ports > 7) {
-		desc->bitmap [1] = (rh & RH_B_DR) >> 8;
-		desc->bitmap [2] = 0xff;
+		desc->DeviceRemovable[1] = (rh & RH_B_DR) >> 8;
+		desc->DeviceRemovable[2] = 0xff;
 	} else
-		desc->bitmap [1] = 0xff;
+		desc->DeviceRemovable[1] = 0xff;
 }
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index e0cb12b573f9..ad54a4144756 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -451,9 +451,9 @@ static void ehci_hub_descriptor(struct oxu_hcd *oxu,
 	temp = 1 + (ports / 8);
 	desc->bDescLength = 7 + 2 * temp;
 
-	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&desc->bitmap[0], 0, temp);
-	memset(&desc->bitmap[temp], 0xff, temp);
+	/* ports removable, and usb 1.0 legacy PortPwrCtrlMask */
+	memset(&desc->DeviceRemovable[0], 0, temp);
+	memset(&desc->DeviceRemovable[temp], 0xff, temp);
 
 	temp = 0x0008;			/* per-port overcurrent reporting */
 	if (HCS_PPC(oxu->hcs_params))
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index 3076b1cc05df..98afe75500cc 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -2150,8 +2150,8 @@ static void r8a66597_hub_descriptor(struct r8a66597 *r8a66597,
 	desc->bDescLength = 9;
 	desc->bPwrOn2PwrGood = 0;
 	desc->wHubCharacteristics = cpu_to_le16(0x0011);
-	desc->bitmap[0] = ((1 << r8a66597->max_root_hub) - 1) << 1;
-	desc->bitmap[1] = ~0;
+	desc->DeviceRemovable[0] = ((1 << r8a66597->max_root_hub) - 1) << 1;
+	desc->DeviceRemovable[1] = ~0;
 }
 
 static int r8a66597_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index 2e9602a10e9b..f3899b334c73 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -1111,9 +1111,9 @@ sl811h_hub_descriptor (
 
 	desc->wHubCharacteristics = cpu_to_le16(temp);
 
-	/* two bitmaps:  ports removable, and legacy PortPwrCtrlMask */
-	desc->bitmap[0] = 0 << 1;
-	desc->bitmap[1] = ~0;
+	/* ports removable, and legacy PortPwrCtrlMask */
+	desc->DeviceRemovable[0] = 0 << 1;
+	desc->DeviceRemovable[1] = ~0;
 }
 
 static void
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index fab764946c74..a659e1590bca 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/drivers/usb/host/u132-hcd.c
@@ -2604,13 +2604,13 @@ static int u132_roothub_descriptor(struct u132 *u132,
 	retval = u132_read_pcimem(u132, roothub.b, &rh_b);
 	if (retval)
 		return retval;
-	memset(desc->bitmap, 0xff, sizeof(desc->bitmap));
-	desc->bitmap[0] = rh_b & RH_B_DR;
+	memset(desc->DeviceRemovable, 0xff, sizeof(desc->DeviceRemovable));
+	desc->DeviceRemovable[0] = rh_b & RH_B_DR;
 	if (u132->num_ports > 7) {
-		desc->bitmap[1] = (rh_b & RH_B_DR) >> 8;
-		desc->bitmap[2] = 0xff;
+		desc->DeviceRemovable[1] = (rh_b & RH_B_DR) >> 8;
+		desc->DeviceRemovable[2] = 0xff;
 	} else
-		desc->bitmap[1] = 0xff;
+		desc->DeviceRemovable[1] = 0xff;
 	return 0;
 }
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 5d963e350494..d83c27b9725b 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -45,7 +45,6 @@ static void xhci_hub_descriptor(struct xhci_hcd *xhci,
 	temp = 1 + (ports / 8);
 	desc->bDescLength = 7 + 2 * temp;
 
-	/* Why does core/hcd.h define bitmap?  It's just confusing. */
 	memset(&desc->DeviceRemovable[0], 0, temp);
 	memset(&desc->DeviceRemovable[temp], 0xff, temp);
 
diff --git a/drivers/usb/wusbcore/rh.c b/drivers/usb/wusbcore/rh.c
index 785772e66ed0..cff246b7cb26 100644
--- a/drivers/usb/wusbcore/rh.c
+++ b/drivers/usb/wusbcore/rh.c
@@ -184,8 +184,8 @@ static int wusbhc_rh_get_hub_descr(struct wusbhc *wusbhc, u16 wValue,
 	descr->bPwrOn2PwrGood = 0;
 	descr->bHubContrCurrent = 0;
 	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&descr->bitmap[0], 0, temp);
-	memset(&descr->bitmap[temp], 0xff, temp);
+	memset(&descr->DeviceRemovable[0], 0, temp);
+	memset(&descr->DeviceRemovable[temp], 0xff, temp);
 	return 0;
 }
 
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 8b65068c6af9..0be61970074e 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -639,13 +639,6 @@ static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb,
 
 #endif /* CONFIG_USB_MON || CONFIG_USB_MON_MODULE */
 
-/*-------------------------------------------------------------------------*/
-
-/* hub.h ... DeviceRemovable in 2.4.2-ac11, gone in 2.4.10 */
-/* bleech -- resurfaced in 2.4.11 or 2.4.12 */
-#define bitmap	DeviceRemovable
-
-
 /*-------------------------------------------------------------------------*/
 
 /* random stuff */
-- 
cgit v1.2.3


From dbe79bbe9dcb22cb3651c46f18943477141ca452 Mon Sep 17 00:00:00 2001
From: John Youn <John.Youn@synopsys.com>
Date: Mon, 17 Sep 2001 00:00:00 -0700
Subject: USB 3.0 Hub Changes

Update the USB core to deal with USB 3.0 hubs.  These hubs have a slightly
different hub descriptor than USB 2.0 hubs, with a fixed (rather than
variable length) size.  Change the USB core's hub descriptor to have a
union for the last fields that differ.  Change the host controller drivers
that access those last fields (DeviceRemovable and PortPowerCtrlMask) to
use the union.

Translate the new version of the hub port status field into the old
version that khubd understands.  (Note: we need to fix it to translate the
roothub's port status once we stop converting it to USB 2.0 hub status
internally.)

Add new code to handle link state change status.  Send out new control
messages that are needed for USB 3.0 hubs, like Set Hub Depth.

This patch is a modified version of the original patch submitted by John
Youn.  It's updated to reflect the removal of the "bitmap" #define, and
change the hub descriptor accesses of a couple new host controller
drivers.

Signed-off-by: John Youn <johnyoun@synopsys.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Cc: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Cc: Tony Olech <tony.olech@elandigitalsystems.com>
Cc: "Robert P. J. Day" <rpjday@crashcourse.ca>
Cc: Max Vozeler <mvz@vozeler.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Cc: Rodolfo Giometti <giometti@linux.it>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Anton Vorontsov <avorontsov@mvista.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Lothar Wassmann <LW@KARO-electronics.de>
Cc: Olav Kongas <ok@artecdesign.ee>
Cc: Martin Fuzzey <mfuzzey@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: David Brownell <dbrownell@users.sourceforge.net>
---
 drivers/staging/usbip/vhci_hcd.c |  4 +--
 drivers/usb/core/hub.c           | 73 +++++++++++++++++++++++++++++++++++-----
 drivers/usb/gadget/dummy_hcd.c   |  4 +--
 drivers/usb/host/ehci-hub.c      |  4 +--
 drivers/usb/host/imx21-hcd.c     |  4 +--
 drivers/usb/host/isp116x-hcd.c   |  4 +--
 drivers/usb/host/isp1362-hcd.c   |  4 +--
 drivers/usb/host/isp1760-hcd.c   |  4 +--
 drivers/usb/host/ohci-hub.c      | 11 +++---
 drivers/usb/host/oxu210hp-hcd.c  |  4 +--
 drivers/usb/host/r8a66597-hcd.c  |  5 +--
 drivers/usb/host/sl811-hcd.c     |  4 +--
 drivers/usb/host/u132-hcd.c      | 11 +++---
 drivers/usb/host/xhci-hub.c      |  4 +--
 drivers/usb/musb/musb_virthub.c  |  4 +--
 drivers/usb/wusbcore/rh.c        |  4 +--
 include/linux/usb/ch11.h         | 41 +++++++++++++++++++---
 17 files changed, 141 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/usbip/vhci_hcd.c b/drivers/staging/usbip/vhci_hcd.c
index 0fe7e49cdc37..29ccc0150996 100644
--- a/drivers/staging/usbip/vhci_hcd.c
+++ b/drivers/staging/usbip/vhci_hcd.c
@@ -255,8 +255,8 @@ static inline void hub_descriptor(struct usb_hub_descriptor *desc)
 	desc->wHubCharacteristics = (__force __u16)
 		(__constant_cpu_to_le16(0x0001));
 	desc->bNbrPorts = VHCI_NPORTS;
-	desc->DeviceRemovable[0] = 0xff;
-	desc->DeviceRemovable[1] = 0xff;
+	desc->u.hs.DeviceRemovable[0] = 0xff;
+	desc->u.hs.DeviceRemovable[1] = 0xff;
 }
 
 static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b574f9131b43..feb6e596c7c9 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -82,6 +82,10 @@ struct usb_hub {
 	void			**port_owners;
 };
 
+static inline int hub_is_superspeed(struct usb_device *hdev)
+{
+	return (hdev->descriptor.bDeviceProtocol == 3);
+}
 
 /* Protect struct usb_device->state and ->children members
  * Note: Both are also protected by ->dev.sem, except that ->state can
@@ -172,14 +176,23 @@ static struct usb_hub *hdev_to_hub(struct usb_device *hdev)
 }
 
 /* USB 2.0 spec Section 11.24.4.5 */
-static int get_hub_descriptor(struct usb_device *hdev, void *data, int size)
+static int get_hub_descriptor(struct usb_device *hdev, void *data)
 {
-	int i, ret;
+	int i, ret, size;
+	unsigned dtype;
+
+	if (hub_is_superspeed(hdev)) {
+		dtype = USB_DT_SS_HUB;
+		size = USB_DT_SS_HUB_SIZE;
+	} else {
+		dtype = USB_DT_HUB;
+		size = sizeof(struct usb_hub_descriptor);
+	}
 
 	for (i = 0; i < 3; i++) {
 		ret = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0),
 			USB_REQ_GET_DESCRIPTOR, USB_DIR_IN | USB_RT_HUB,
-			USB_DT_HUB << 8, 0, data, size,
+			dtype << 8, 0, data, size,
 			USB_CTRL_GET_TIMEOUT);
 		if (ret >= (USB_DT_HUB_NONVAR_SIZE + 2))
 			return ret;
@@ -365,6 +378,19 @@ static int hub_port_status(struct usb_hub *hub, int port1,
 	} else {
 		*status = le16_to_cpu(hub->status->port.wPortStatus);
 		*change = le16_to_cpu(hub->status->port.wPortChange);
+
+		if ((hub->hdev->parent != NULL) &&
+				hub_is_superspeed(hub->hdev)) {
+			/* Translate the USB 3 port status */
+			u16 tmp = *status & USB_SS_PORT_STAT_MASK;
+			if (*status & USB_SS_PORT_STAT_POWER)
+				tmp |= USB_PORT_STAT_POWER;
+			if ((*status & USB_SS_PORT_STAT_SPEED) ==
+					USB_PORT_STAT_SPEED_5GBPS)
+				tmp |= USB_PORT_STAT_SUPER_SPEED;
+			*status = tmp;
+		}
+
 		ret = 0;
 	}
 	mutex_unlock(&hub->status_mutex);
@@ -607,7 +633,7 @@ static int hub_port_disable(struct usb_hub *hub, int port1, int set_state)
 	if (hdev->children[port1-1] && set_state)
 		usb_set_device_state(hdev->children[port1-1],
 				USB_STATE_NOTATTACHED);
-	if (!hub->error)
+	if (!hub->error && !hub_is_superspeed(hub->hdev))
 		ret = clear_port_feature(hdev, port1, USB_PORT_FEAT_ENABLE);
 	if (ret)
 		dev_err(hub->intfdev, "cannot disable port %d (err = %d)\n",
@@ -795,6 +821,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			clear_port_feature(hub->hdev, port1,
 					USB_PORT_FEAT_C_ENABLE);
 		}
+		if (portchange & USB_PORT_STAT_C_LINK_STATE) {
+			need_debounce_delay = true;
+			clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_PORT_LINK_STATE);
+		}
 
 		/* We can forget about a "removed" device when there's a
 		 * physical disconnect or the connect status changes.
@@ -964,12 +995,23 @@ static int hub_configure(struct usb_hub *hub,
 		goto fail;
 	}
 
+	if (hub_is_superspeed(hdev) && (hdev->parent != NULL)) {
+		ret = usb_control_msg(hdev, usb_sndctrlpipe(hdev, 0),
+				HUB_SET_DEPTH, USB_RT_HUB,
+				hdev->level - 1, 0, NULL, 0,
+				USB_CTRL_SET_TIMEOUT);
+
+		if (ret < 0) {
+			message = "can't set hub depth";
+			goto fail;
+		}
+	}
+
 	/* Request the entire hub descriptor.
 	 * hub->descriptor can handle USB_MAXCHILDREN ports,
 	 * but the hub can/will return fewer bytes here.
 	 */
-	ret = get_hub_descriptor(hdev, hub->descriptor,
-			sizeof(*hub->descriptor));
+	ret = get_hub_descriptor(hdev, hub->descriptor);
 	if (ret < 0) {
 		message = "can't read hub descriptor";
 		goto fail;
@@ -991,12 +1033,14 @@ static int hub_configure(struct usb_hub *hub,
 
 	wHubCharacteristics = le16_to_cpu(hub->descriptor->wHubCharacteristics);
 
-	if (wHubCharacteristics & HUB_CHAR_COMPOUND) {
+	/* FIXME for USB 3.0, skip for now */
+	if ((wHubCharacteristics & HUB_CHAR_COMPOUND) &&
+			!(hub_is_superspeed(hdev))) {
 		int	i;
 		char	portstr [USB_MAXCHILDREN + 1];
 
 		for (i = 0; i < hdev->maxchild; i++)
-			portstr[i] = hub->descriptor->DeviceRemovable
+			portstr[i] = hub->descriptor->u.hs.DeviceRemovable
 				    [((i + 1) / 8)] & (1 << ((i + 1) % 8))
 				? 'F' : 'R';
 		portstr[hdev->maxchild] = 0;
@@ -2029,6 +2073,8 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1,
 				udev->speed = USB_SPEED_HIGH;
 			else if (portstatus & USB_PORT_STAT_LOW_SPEED)
 				udev->speed = USB_SPEED_LOW;
+			else if (portstatus & USB_PORT_STAT_SUPER_SPEED)
+				udev->speed = USB_SPEED_SUPER;
 			else
 				udev->speed = USB_SPEED_FULL;
 			return 0;
@@ -3430,6 +3476,17 @@ static void hub_events(void)
 				clear_port_feature(hdev, i,
 					USB_PORT_FEAT_C_RESET);
 			}
+			if (portchange & USB_PORT_STAT_C_LINK_STATE) {
+				clear_port_feature(hub->hdev, i,
+						USB_PORT_FEAT_C_PORT_LINK_STATE);
+			}
+			if (portchange & USB_PORT_STAT_C_CONFIG_ERROR) {
+				dev_warn(hub_dev,
+					"config error on port %d\n",
+					i);
+				clear_port_feature(hub->hdev, i,
+						USB_PORT_FEAT_C_PORT_CONFIG_ERROR);
+			}
 
 			if (connect_change)
 				hub_port_connect_change(hub, i,
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index f2040e8af8b1..3214ca375d64 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -1593,8 +1593,8 @@ hub_descriptor (struct usb_hub_descriptor *desc)
 	desc->bDescLength = 9;
 	desc->wHubCharacteristics = cpu_to_le16(0x0001);
 	desc->bNbrPorts = 1;
-	desc->DeviceRemovable[0] = 0xff;
-	desc->DeviceRemovable[1] = 0xff;
+	desc->u.hs.DeviceRemovable[0] = 0xff;
+	desc->u.hs.DeviceRemovable[1] = 0xff;
 }
 
 static int dummy_hub_control (
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index dfa1e1d371c8..d05ea03cfb4d 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -717,8 +717,8 @@ ehci_hub_descriptor (
 	desc->bDescLength = 7 + 2 * temp;
 
 	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&desc->DeviceRemovable[0], 0, temp);
-	memset(&desc->DeviceRemovable[temp], 0xff, temp);
+	memset(&desc->u.hs.DeviceRemovable[0], 0, temp);
+	memset(&desc->u.hs.DeviceRemovable[temp], 0xff, temp);
 
 	temp = 0x0008;			/* per-port overcurrent reporting */
 	if (HCS_PPC (ehci->hcs_params))
diff --git a/drivers/usb/host/imx21-hcd.c b/drivers/usb/host/imx21-hcd.c
index 2f180dfe5371..2562e92e3178 100644
--- a/drivers/usb/host/imx21-hcd.c
+++ b/drivers/usb/host/imx21-hcd.c
@@ -1472,8 +1472,8 @@ static int get_hub_descriptor(struct usb_hcd *hcd,
 		0x0010 |	/* No over current protection */
 		0);
 
-	desc->DeviceRemovable[0] = 1 << 1;
-	desc->DeviceRemovable[1] = ~0;
+	desc->u.hs.DeviceRemovable[0] = 1 << 1;
+	desc->u.hs.DeviceRemovable[1] = ~0;
 	return 0;
 }
 
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index 2a60a50bc420..c0e22f26da19 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -952,8 +952,8 @@ static void isp116x_hub_descriptor(struct isp116x *isp116x,
 	desc->wHubCharacteristics = cpu_to_le16((u16) ((reg >> 8) & 0x1f));
 	desc->bPwrOn2PwrGood = (u8) ((reg >> 24) & 0xff);
 	/* ports removable, and legacy PortPwrCtrlMask */
-	desc->DeviceRemovable[0] = 0;
-	desc->DeviceRemovable[1] = ~0;
+	desc->u.hs.DeviceRemovable[0] = 0;
+	desc->u.hs.DeviceRemovable[1] = ~0;
 }
 
 /* Perform reset of a given port.
diff --git a/drivers/usb/host/isp1362-hcd.c b/drivers/usb/host/isp1362-hcd.c
index 6dd94b997d97..662cd002adfc 100644
--- a/drivers/usb/host/isp1362-hcd.c
+++ b/drivers/usb/host/isp1362-hcd.c
@@ -1553,8 +1553,8 @@ static void isp1362_hub_descriptor(struct isp1362_hcd *isp1362_hcd,
 	DBG(0, "%s: hubcharacteristics = %02x\n", __func__, cpu_to_le16((reg >> 8) & 0x1f));
 	desc->bPwrOn2PwrGood = (reg >> 24) & 0xff;
 	/* ports removable, and legacy PortPwrCtrlMask */
-	desc->DeviceRemovable[0] = desc->bNbrPorts == 1 ? 1 << 1 : 3 << 1;
-	desc->DeviceRemovable[1] = ~0;
+	desc->u.hs.DeviceRemovable[0] = desc->bNbrPorts == 1 ? 1 << 1 : 3 << 1;
+	desc->u.hs.DeviceRemovable[1] = ~0;
 
 	DBG(3, "%s: exit\n", __func__);
 }
diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c
index 1c8de7666d6a..f50e84ac570a 100644
--- a/drivers/usb/host/isp1760-hcd.c
+++ b/drivers/usb/host/isp1760-hcd.c
@@ -1752,8 +1752,8 @@ static void isp1760_hub_descriptor(struct isp1760_hcd *priv,
 	desc->bDescLength = 7 + 2 * temp;
 
 	/* ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&desc->DeviceRemovable[0], 0, temp);
-	memset(&desc->DeviceRemovable[temp], 0xff, temp);
+	memset(&desc->u.hs.DeviceRemovable[0], 0, temp);
+	memset(&desc->u.hs.DeviceRemovable[temp], 0xff, temp);
 
 	/* per-port overcurrent reporting */
 	temp = 0x0008;
diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index cd4b74f27d06..9154615292db 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -582,13 +582,14 @@ ohci_hub_descriptor (
 
 	/* ports removable, and usb 1.0 legacy PortPwrCtrlMask */
 	rh = roothub_b (ohci);
-	memset(desc->DeviceRemovable, 0xff, sizeof(desc->DeviceRemovable));
-	desc->DeviceRemovable[0] = rh & RH_B_DR;
+	memset(desc->u.hs.DeviceRemovable, 0xff,
+			sizeof(desc->u.hs.DeviceRemovable));
+	desc->u.hs.DeviceRemovable[0] = rh & RH_B_DR;
 	if (ohci->num_ports > 7) {
-		desc->DeviceRemovable[1] = (rh & RH_B_DR) >> 8;
-		desc->DeviceRemovable[2] = 0xff;
+		desc->u.hs.DeviceRemovable[1] = (rh & RH_B_DR) >> 8;
+		desc->u.hs.DeviceRemovable[2] = 0xff;
 	} else
-		desc->DeviceRemovable[1] = 0xff;
+		desc->u.hs.DeviceRemovable[1] = 0xff;
 }
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index ad54a4144756..38193f4e980e 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -452,8 +452,8 @@ static void ehci_hub_descriptor(struct oxu_hcd *oxu,
 	desc->bDescLength = 7 + 2 * temp;
 
 	/* ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&desc->DeviceRemovable[0], 0, temp);
-	memset(&desc->DeviceRemovable[temp], 0xff, temp);
+	memset(&desc->u.hs.DeviceRemovable[0], 0, temp);
+	memset(&desc->u.hs.DeviceRemovable[temp], 0xff, temp);
 
 	temp = 0x0008;			/* per-port overcurrent reporting */
 	if (HCS_PPC(oxu->hcs_params))
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index 98afe75500cc..db6f8b9c19b6 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -2150,8 +2150,9 @@ static void r8a66597_hub_descriptor(struct r8a66597 *r8a66597,
 	desc->bDescLength = 9;
 	desc->bPwrOn2PwrGood = 0;
 	desc->wHubCharacteristics = cpu_to_le16(0x0011);
-	desc->DeviceRemovable[0] = ((1 << r8a66597->max_root_hub) - 1) << 1;
-	desc->DeviceRemovable[1] = ~0;
+	desc->u.hs.DeviceRemovable[0] =
+		((1 << r8a66597->max_root_hub) - 1) << 1;
+	desc->u.hs.DeviceRemovable[1] = ~0;
 }
 
 static int r8a66597_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index f3899b334c73..18b7099a8125 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -1112,8 +1112,8 @@ sl811h_hub_descriptor (
 	desc->wHubCharacteristics = cpu_to_le16(temp);
 
 	/* ports removable, and legacy PortPwrCtrlMask */
-	desc->DeviceRemovable[0] = 0 << 1;
-	desc->DeviceRemovable[1] = ~0;
+	desc->u.hs.DeviceRemovable[0] = 0 << 1;
+	desc->u.hs.DeviceRemovable[1] = ~0;
 }
 
 static void
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index a659e1590bca..b4785934e091 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/drivers/usb/host/u132-hcd.c
@@ -2604,13 +2604,14 @@ static int u132_roothub_descriptor(struct u132 *u132,
 	retval = u132_read_pcimem(u132, roothub.b, &rh_b);
 	if (retval)
 		return retval;
-	memset(desc->DeviceRemovable, 0xff, sizeof(desc->DeviceRemovable));
-	desc->DeviceRemovable[0] = rh_b & RH_B_DR;
+	memset(desc->u.hs.DeviceRemovable, 0xff,
+			sizeof(desc->u.hs.DeviceRemovable));
+	desc->u.hs.DeviceRemovable[0] = rh_b & RH_B_DR;
 	if (u132->num_ports > 7) {
-		desc->DeviceRemovable[1] = (rh_b & RH_B_DR) >> 8;
-		desc->DeviceRemovable[2] = 0xff;
+		desc->u.hs.DeviceRemovable[1] = (rh_b & RH_B_DR) >> 8;
+		desc->u.hs.DeviceRemovable[2] = 0xff;
 	} else
-		desc->DeviceRemovable[1] = 0xff;
+		desc->u.hs.DeviceRemovable[1] = 0xff;
 	return 0;
 }
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 43e0a099d634..847b071b6fc9 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -45,8 +45,8 @@ static void xhci_hub_descriptor(struct xhci_hcd *xhci,
 	temp = 1 + (ports / 8);
 	desc->bDescLength = 7 + 2 * temp;
 
-	memset(&desc->DeviceRemovable[0], 0, temp);
-	memset(&desc->DeviceRemovable[temp], 0xff, temp);
+	memset(&desc->u.hs.DeviceRemovable[0], 0, temp);
+	memset(&desc->u.hs.DeviceRemovable[temp], 0xff, temp);
 
 	/* Ugh, these should be #defines, FIXME */
 	/* Using table 11-13 in USB 2.0 spec. */
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index b46d1877e28e..489104a5ae14 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -305,8 +305,8 @@ int musb_hub_control(
 		desc->bHubContrCurrent = 0;
 
 		/* workaround bogus struct definition */
-		desc->DeviceRemovable[0] = 0x02;	/* port 1 */
-		desc->DeviceRemovable[1] = 0xff;
+		desc->u.hs.DeviceRemovable[0] = 0x02;	/* port 1 */
+		desc->u.hs.DeviceRemovable[1] = 0xff;
 		}
 		break;
 	case GetHubStatus:
diff --git a/drivers/usb/wusbcore/rh.c b/drivers/usb/wusbcore/rh.c
index cff246b7cb26..c175b7300c73 100644
--- a/drivers/usb/wusbcore/rh.c
+++ b/drivers/usb/wusbcore/rh.c
@@ -184,8 +184,8 @@ static int wusbhc_rh_get_hub_descr(struct wusbhc *wusbhc, u16 wValue,
 	descr->bPwrOn2PwrGood = 0;
 	descr->bHubContrCurrent = 0;
 	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
-	memset(&descr->DeviceRemovable[0], 0, temp);
-	memset(&descr->DeviceRemovable[temp], 0xff, temp);
+	memset(&descr->u.hs.DeviceRemovable[0], 0, temp);
+	memset(&descr->u.hs.DeviceRemovable[temp], 0xff, temp);
 	return 0;
 }
 
diff --git a/include/linux/usb/ch11.h b/include/linux/usb/ch11.h
index 38c42b013641..22afcd37bc3f 100644
--- a/include/linux/usb/ch11.h
+++ b/include/linux/usb/ch11.h
@@ -26,6 +26,7 @@
 #define HUB_RESET_TT		9
 #define HUB_GET_TT_STATE	10
 #define HUB_STOP_TT		11
+#define HUB_SET_DEPTH		12
 
 /*
  * Hub class additional requests defined by USB 3.0 spec
@@ -61,6 +62,12 @@
 #define USB_PORT_FEAT_TEST              21
 #define USB_PORT_FEAT_INDICATOR         22
 #define USB_PORT_FEAT_C_PORT_L1         23
+#define USB_PORT_FEAT_C_PORT_LINK_STATE	25
+#define USB_PORT_FEAT_C_PORT_CONFIG_ERROR 26
+#define USB_PORT_FEAT_PORT_REMOTE_WAKE_MASK 27
+#define USB_PORT_FEAT_BH_PORT_RESET     28
+#define USB_PORT_FEAT_C_BH_PORT_RESET   29
+#define USB_PORT_FEAT_FORCE_LINKPM_ACCEPT 30
 
 /*
  * Port feature selectors added by USB 3.0 spec.
@@ -110,8 +117,14 @@ struct usb_port_status {
  */
 #define USB_PORT_STAT_LINK_STATE	0x01e0
 #define USB_SS_PORT_STAT_POWER		0x0200
+#define USB_SS_PORT_STAT_SPEED		0x1c00
 #define USB_PORT_STAT_SPEED_5GBPS	0x0000
 /* Valid only if port is enabled */
+/* Bits that are the same from USB 2.0 */
+#define USB_SS_PORT_STAT_MASK (USB_PORT_STAT_CONNECTION |	    \
+				USB_PORT_STAT_ENABLE |	    \
+				USB_PORT_STAT_OVERCURRENT | \
+				USB_PORT_STAT_RESET)
 
 /*
  * Definitions for PORT_LINK_STATE values
@@ -141,6 +154,13 @@ struct usb_port_status {
 #define USB_PORT_STAT_C_OVERCURRENT	0x0008
 #define USB_PORT_STAT_C_RESET		0x0010
 #define USB_PORT_STAT_C_L1		0x0020
+/*
+ * USB 3.0 wPortChange bit fields
+ * See USB 3.0 spec Table 10-11
+ */
+#define USB_PORT_STAT_C_BH_RESET	0x0020
+#define USB_PORT_STAT_C_LINK_STATE	0x0040
+#define USB_PORT_STAT_C_CONFIG_ERROR	0x0080
 
 /*
  * wHubCharacteristics (masks)
@@ -175,7 +195,9 @@ struct usb_hub_status {
  */
 
 #define USB_DT_HUB			(USB_TYPE_CLASS | 0x09)
+#define USB_DT_SS_HUB			(USB_TYPE_CLASS | 0x0a)
 #define USB_DT_HUB_NONVAR_SIZE		7
+#define USB_DT_SS_HUB_SIZE              12
 
 struct usb_hub_descriptor {
 	__u8  bDescLength;
@@ -184,11 +206,22 @@ struct usb_hub_descriptor {
 	__le16 wHubCharacteristics;
 	__u8  bPwrOn2PwrGood;
 	__u8  bHubContrCurrent;
-		/* add 1 bit for hub status change; round to bytes */
-	__u8  DeviceRemovable[(USB_MAXCHILDREN + 1 + 7) / 8];
-	__u8  PortPwrCtrlMask[(USB_MAXCHILDREN + 1 + 7) / 8];
-} __attribute__ ((packed));
 
+	/* 2.0 and 3.0 hubs differ here */
+	union {
+		struct {
+			/* add 1 bit for hub status change; round to bytes */
+			__u8  DeviceRemovable[(USB_MAXCHILDREN + 1 + 7) / 8];
+			__u8  PortPwrCtrlMask[(USB_MAXCHILDREN + 1 + 7) / 8];
+		}  __attribute__ ((packed)) hs;
+
+		struct {
+			__u8 bHubHdrDecLat;
+			__u16 wHubDelay;
+			__u16 DeviceRemovable;
+		}  __attribute__ ((packed)) ss;
+	} u;
+} __attribute__ ((packed));
 
 /* port indicator status selectors, tables 11-7 and 11-25 */
 #define HUB_LED_AUTO	0
-- 
cgit v1.2.3


From d673bfcbfffdeb56064a6b1ee047b85590bed76c Mon Sep 17 00:00:00 2001
From: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Date: Fri, 15 Oct 2010 08:55:24 -0700
Subject: usb: Change usb_hcd->bandwidth_mutex to a pointer.

Change the bandwith_mutex in struct usb_hcd to a pointer.  This will allow
the pointer to be shared across usb_hcds for the upcoming work to split
the xHCI driver roothub into a USB 2.0/1.1 and a USB 3.0 bus.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/hcd.c     | 11 ++++++++++-
 drivers/usb/core/hub.c     |  8 ++++----
 drivers/usb/core/message.c | 22 +++++++++++-----------
 include/linux/usb/hcd.h    |  2 +-
 4 files changed, 26 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 40c7a46ba7d3..3ba27118adc5 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2191,6 +2191,15 @@ struct usb_hcd *usb_create_hcd (const struct hc_driver *driver,
 		dev_dbg (dev, "hcd alloc failed\n");
 		return NULL;
 	}
+	hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex),
+			GFP_KERNEL);
+	if (!hcd->bandwidth_mutex) {
+		kfree(hcd);
+		dev_dbg(dev, "hcd bandwidth mutex alloc failed\n");
+		return NULL;
+	}
+	mutex_init(hcd->bandwidth_mutex);
+
 	dev_set_drvdata(dev, hcd);
 	kref_init(&hcd->kref);
 
@@ -2205,7 +2214,6 @@ struct usb_hcd *usb_create_hcd (const struct hc_driver *driver,
 #ifdef CONFIG_USB_SUSPEND
 	INIT_WORK(&hcd->wakeup_work, hcd_resume_work);
 #endif
-	mutex_init(&hcd->bandwidth_mutex);
 
 	hcd->driver = driver;
 	hcd->product_desc = (driver->product_desc) ? driver->product_desc :
@@ -2218,6 +2226,7 @@ static void hcd_release (struct kref *kref)
 {
 	struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
 
+	kfree(hcd->bandwidth_mutex);
 	kfree(hcd);
 }
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 0eb27006f846..825d803720b3 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -3776,13 +3776,13 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	if (!udev->actconfig)
 		goto done;
 
-	mutex_lock(&hcd->bandwidth_mutex);
+	mutex_lock(hcd->bandwidth_mutex);
 	ret = usb_hcd_alloc_bandwidth(udev, udev->actconfig, NULL, NULL);
 	if (ret < 0) {
 		dev_warn(&udev->dev,
 				"Busted HC?  Not enough HCD resources for "
 				"old configuration.\n");
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		goto re_enumerate;
 	}
 	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
@@ -3793,10 +3793,10 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 		dev_err(&udev->dev,
 			"can't restore configuration #%d (error=%d)\n",
 			udev->actconfig->desc.bConfigurationValue, ret);
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		goto re_enumerate;
   	}
-	mutex_unlock(&hcd->bandwidth_mutex);
+	mutex_unlock(hcd->bandwidth_mutex);
 	usb_set_device_state(udev, USB_STATE_CONFIGURED);
 
 	/* Put interfaces back into the same altsettings as before.
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 832487423826..5701e857392b 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1284,12 +1284,12 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate)
 	/* Make sure we have enough bandwidth for this alternate interface.
 	 * Remove the current alt setting and add the new alt setting.
 	 */
-	mutex_lock(&hcd->bandwidth_mutex);
+	mutex_lock(hcd->bandwidth_mutex);
 	ret = usb_hcd_alloc_bandwidth(dev, NULL, iface->cur_altsetting, alt);
 	if (ret < 0) {
 		dev_info(&dev->dev, "Not enough bandwidth for altsetting %d\n",
 				alternate);
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		return ret;
 	}
 
@@ -1311,10 +1311,10 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate)
 	} else if (ret < 0) {
 		/* Re-instate the old alt setting */
 		usb_hcd_alloc_bandwidth(dev, NULL, alt, iface->cur_altsetting);
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		return ret;
 	}
-	mutex_unlock(&hcd->bandwidth_mutex);
+	mutex_unlock(hcd->bandwidth_mutex);
 
 	/* FIXME drivers shouldn't need to replicate/bugfix the logic here
 	 * when they implement async or easily-killable versions of this or
@@ -1413,7 +1413,7 @@ int usb_reset_configuration(struct usb_device *dev)
 
 	config = dev->actconfig;
 	retval = 0;
-	mutex_lock(&hcd->bandwidth_mutex);
+	mutex_lock(hcd->bandwidth_mutex);
 	/* Make sure we have enough bandwidth for each alternate setting 0 */
 	for (i = 0; i < config->desc.bNumInterfaces; i++) {
 		struct usb_interface *intf = config->interface[i];
@@ -1442,7 +1442,7 @@ reset_old_alts:
 				usb_hcd_alloc_bandwidth(dev, NULL,
 						alt, intf->cur_altsetting);
 		}
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		return retval;
 	}
 	retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
@@ -1451,7 +1451,7 @@ reset_old_alts:
 			NULL, 0, USB_CTRL_SET_TIMEOUT);
 	if (retval < 0)
 		goto reset_old_alts;
-	mutex_unlock(&hcd->bandwidth_mutex);
+	mutex_unlock(hcd->bandwidth_mutex);
 
 	/* re-init hc/hcd interface/endpoint state */
 	for (i = 0; i < config->desc.bNumInterfaces; i++) {
@@ -1739,10 +1739,10 @@ free_interfaces:
 	 * host controller will not allow submissions to dropped endpoints.  If
 	 * this call fails, the device state is unchanged.
 	 */
-	mutex_lock(&hcd->bandwidth_mutex);
+	mutex_lock(hcd->bandwidth_mutex);
 	ret = usb_hcd_alloc_bandwidth(dev, cp, NULL, NULL);
 	if (ret < 0) {
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		usb_autosuspend_device(dev);
 		goto free_interfaces;
 	}
@@ -1761,11 +1761,11 @@ free_interfaces:
 	if (!cp) {
 		usb_set_device_state(dev, USB_STATE_ADDRESS);
 		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
-		mutex_unlock(&hcd->bandwidth_mutex);
+		mutex_unlock(hcd->bandwidth_mutex);
 		usb_autosuspend_device(dev);
 		goto free_interfaces;
 	}
-	mutex_unlock(&hcd->bandwidth_mutex);
+	mutex_unlock(hcd->bandwidth_mutex);
 	usb_set_device_state(dev, USB_STATE_CONFIGURED);
 
 	/* Initialize the new interface structures and the
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 0be61970074e..836aaa91ee15 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -142,7 +142,7 @@ struct usb_hcd {
 	 * bandwidth_mutex should be dropped after a successful control message
 	 * to the device, or resetting the bandwidth after a failed attempt.
 	 */
-	struct mutex		bandwidth_mutex;
+	struct mutex		*bandwidth_mutex;
 
 
 #define HCD_BUFFER_POOLS	4
-- 
cgit v1.2.3


From 83de4b2b90887b5b317d8313864fe4cc5db35280 Mon Sep 17 00:00:00 2001
From: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Date: Thu, 2 Dec 2010 14:45:18 -0800
Subject: usb: Store bus type in usb_hcd, not in driver flags.

The xHCI driver essentially has both a USB 2.0 and a USB 3.0 roothub.  So
setting the HCD_USB3 bits in the hcd->driver->flags is a bit misleading.
Add a new field to usb_hcd, bcdUSB.  Store the result of
hcd->driver->flags & HCD_MASK in it.  Later, when we have the xHCI driver
register the two roothubs, we'll set the usb_hcd->bcdUSB field to HCD_USB2
for the USB 2.0 roothub, and HCD_USB3 for the USB 3.0 roothub.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/hcd.c  | 7 ++++---
 include/linux/usb/hcd.h | 4 ++++
 2 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 3ba27118adc5..a0adcac3da08 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -507,7 +507,7 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
 	case DeviceRequest | USB_REQ_GET_DESCRIPTOR:
 		switch (wValue & 0xff00) {
 		case USB_DT_DEVICE << 8:
-			switch (hcd->driver->flags & HCD_MASK) {
+			switch (hcd->speed) {
 			case HCD_USB3:
 				bufp = usb3_rh_dev_descriptor;
 				break;
@@ -525,7 +525,7 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
 				patch_protocol = 1;
 			break;
 		case USB_DT_CONFIG << 8:
-			switch (hcd->driver->flags & HCD_MASK) {
+			switch (hcd->speed) {
 			case HCD_USB3:
 				bufp = ss_rh_config_descriptor;
 				len = sizeof ss_rh_config_descriptor;
@@ -2216,6 +2216,7 @@ struct usb_hcd *usb_create_hcd (const struct hc_driver *driver,
 #endif
 
 	hcd->driver = driver;
+	hcd->speed = driver->flags & HCD_MASK;
 	hcd->product_desc = (driver->product_desc) ? driver->product_desc :
 			"USB Host Controller";
 	return hcd;
@@ -2325,7 +2326,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	}
 	hcd->self.root_hub = rhdev;
 
-	switch (hcd->driver->flags & HCD_MASK) {
+	switch (hcd->speed) {
 	case HCD_USB11:
 		rhdev->speed = USB_SPEED_FULL;
 		break;
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 836aaa91ee15..b8bb6934f30b 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -76,6 +76,10 @@ struct usb_hcd {
 	struct kref		kref;		/* reference counter */
 
 	const char		*product_desc;	/* product/vendor string */
+	int			speed;		/* Speed for this roothub.
+						 * May be different from
+						 * hcd->driver->flags & HCD_MASK
+						 */
 	char			irq_descr[24];	/* driver + bus # */
 
 	struct timer_list	rh_timer;	/* drives root-hub polling */
-- 
cgit v1.2.3


From c56354378426e550aaf6ddf3983f502a8fddeab5 Mon Sep 17 00:00:00 2001
From: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Date: Thu, 28 Oct 2010 15:40:26 -0700
Subject: usb: Make core allocate resources per PCI-device.

Introduce the notion of a PCI device that may be associated with more than
one USB host controller driver (struct usb_hcd).  This patch is the start
of the work to separate the xHCI host controller into two roothubs: a USB
3.0 roothub with SuperSpeed-only ports, and a USB 2.0 roothub with
HS/FS/LS ports.

One usb_hcd structure is designated to be the "primary HCD", and a pointer
is added to the usb_hcd structure to keep track of that.  A new function
call, usb_hcd_is_primary_hcd() is added to check whether the USB hcd is
marked as the primary HCD (or if it is not part of a roothub pair).  To
allow the USB core and xHCI driver to access either roothub in a pair, a
"shared_hcd" pointer is added to the usb_hcd structure.

Add a new function, usb_create_shared_hcd(), that does roothub allocation
for paired roothubs.  It will act just like usb_create_hcd() did if the
primary_hcd pointer argument is NULL.  If it is passed a non-NULL
primary_hcd pointer, it sets usb_hcd->shared_hcd and usb_hcd->primary_hcd
fields.  It will also skip the bandwidth_mutex allocation, and set the
secondary hcd's bandwidth_mutex pointer to the primary HCD's mutex.

IRQs are only allocated once for the primary roothub.

Introduce a new usb_hcd driver flag that indicates the host controller
driver wants to create two roothubs.  If the HCD_SHARED flag is set, then
the USB core PCI probe methods will allocate a second roothub, and make
sure that second roothub gets freed during rmmod and in initialization
error paths.

When usb_hc_died() is called with the primary HCD, make sure that any
roothubs that share that host controller are also marked as being dead.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/hcd.c  | 108 +++++++++++++++++++++++++++++++++++++++---------
 include/linux/usb/hcd.h |   7 ++++
 2 files changed, 96 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index a0adcac3da08..ba15eeab824e 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2143,7 +2143,9 @@ EXPORT_SYMBOL_GPL(usb_hcd_irq);
  *
  * This is called by bus glue to report a USB host controller that died
  * while operations may still have been pending.  It's called automatically
- * by the PCI glue, so only glue for non-PCI busses should need to call it. 
+ * by the PCI glue, so only glue for non-PCI busses should need to call it.
+ *
+ * Only call this function with the primary HCD.
  */
 void usb_hc_died (struct usb_hcd *hcd)
 {
@@ -2162,17 +2164,31 @@ void usb_hc_died (struct usb_hcd *hcd)
 				USB_STATE_NOTATTACHED);
 		usb_kick_khubd (hcd->self.root_hub);
 	}
+	if (usb_hcd_is_primary_hcd(hcd) && hcd->shared_hcd) {
+		hcd = hcd->shared_hcd;
+		if (hcd->rh_registered) {
+			clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
+
+			/* make khubd clean up old urbs and devices */
+			usb_set_device_state(hcd->self.root_hub,
+					USB_STATE_NOTATTACHED);
+			usb_kick_khubd(hcd->self.root_hub);
+		}
+	}
 	spin_unlock_irqrestore (&hcd_root_hub_lock, flags);
+	/* Make sure that the other roothub is also deallocated. */
 }
 EXPORT_SYMBOL_GPL (usb_hc_died);
 
 /*-------------------------------------------------------------------------*/
 
 /**
- * usb_create_hcd - create and initialize an HCD structure
+ * usb_create_shared_hcd - create and initialize an HCD structure
  * @driver: HC driver that will use this hcd
  * @dev: device for this HC, stored in hcd->self.controller
  * @bus_name: value to store in hcd->self.bus_name
+ * @primary_hcd: a pointer to the usb_hcd structure that is sharing the
+ *              PCI device.  Only allocate certain resources for the primary HCD
  * Context: !in_interrupt()
  *
  * Allocate a struct usb_hcd, with extra space at the end for the
@@ -2181,8 +2197,9 @@ EXPORT_SYMBOL_GPL (usb_hc_died);
  *
  * If memory is unavailable, returns NULL.
  */
-struct usb_hcd *usb_create_hcd (const struct hc_driver *driver,
-		struct device *dev, const char *bus_name)
+struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
+		struct device *dev, const char *bus_name,
+		struct usb_hcd *primary_hcd)
 {
 	struct usb_hcd *hcd;
 
@@ -2191,16 +2208,24 @@ struct usb_hcd *usb_create_hcd (const struct hc_driver *driver,
 		dev_dbg (dev, "hcd alloc failed\n");
 		return NULL;
 	}
-	hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex),
-			GFP_KERNEL);
-	if (!hcd->bandwidth_mutex) {
-		kfree(hcd);
-		dev_dbg(dev, "hcd bandwidth mutex alloc failed\n");
-		return NULL;
+	if (primary_hcd == NULL) {
+		hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex),
+				GFP_KERNEL);
+		if (!hcd->bandwidth_mutex) {
+			kfree(hcd);
+			dev_dbg(dev, "hcd bandwidth mutex alloc failed\n");
+			return NULL;
+		}
+		mutex_init(hcd->bandwidth_mutex);
+		dev_set_drvdata(dev, hcd);
+	} else {
+		hcd->bandwidth_mutex = primary_hcd->bandwidth_mutex;
+		hcd->primary_hcd = primary_hcd;
+		primary_hcd->primary_hcd = primary_hcd;
+		hcd->shared_hcd = primary_hcd;
+		primary_hcd->shared_hcd = hcd;
 	}
-	mutex_init(hcd->bandwidth_mutex);
 
-	dev_set_drvdata(dev, hcd);
 	kref_init(&hcd->kref);
 
 	usb_bus_init(&hcd->self);
@@ -2221,13 +2246,46 @@ struct usb_hcd *usb_create_hcd (const struct hc_driver *driver,
 			"USB Host Controller";
 	return hcd;
 }
+EXPORT_SYMBOL_GPL(usb_create_shared_hcd);
+
+/**
+ * usb_create_hcd - create and initialize an HCD structure
+ * @driver: HC driver that will use this hcd
+ * @dev: device for this HC, stored in hcd->self.controller
+ * @bus_name: value to store in hcd->self.bus_name
+ * Context: !in_interrupt()
+ *
+ * Allocate a struct usb_hcd, with extra space at the end for the
+ * HC driver's private data.  Initialize the generic members of the
+ * hcd structure.
+ *
+ * If memory is unavailable, returns NULL.
+ */
+struct usb_hcd *usb_create_hcd(const struct hc_driver *driver,
+		struct device *dev, const char *bus_name)
+{
+	return usb_create_shared_hcd(driver, dev, bus_name, NULL);
+}
 EXPORT_SYMBOL_GPL(usb_create_hcd);
 
+/*
+ * Roothubs that share one PCI device must also share the bandwidth mutex.
+ * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is
+ * deallocated.
+ *
+ * Make sure to only deallocate the bandwidth_mutex when the primary HCD is
+ * freed.  When hcd_release() is called for the non-primary HCD, set the
+ * primary_hcd's shared_hcd pointer to null (since the non-primary HCD will be
+ * freed shortly).
+ */
 static void hcd_release (struct kref *kref)
 {
 	struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
 
-	kfree(hcd->bandwidth_mutex);
+	if (usb_hcd_is_primary_hcd(hcd))
+		kfree(hcd->bandwidth_mutex);
+	else
+		hcd->shared_hcd->shared_hcd = NULL;
 	kfree(hcd);
 }
 
@@ -2246,6 +2304,14 @@ void usb_put_hcd (struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(usb_put_hcd);
 
+int usb_hcd_is_primary_hcd(struct usb_hcd *hcd)
+{
+	if (!hcd->primary_hcd)
+		return 1;
+	return hcd == hcd->primary_hcd;
+}
+EXPORT_SYMBOL_GPL(usb_hcd_is_primary_hcd);
+
 static int usb_hcd_request_irqs(struct usb_hcd *hcd,
 		unsigned int irqnum, unsigned long irqflags)
 {
@@ -2367,9 +2433,11 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		dev_dbg(hcd->self.controller, "supports USB remote wakeup\n");
 
 	/* enable irqs just before we start the controller */
-	retval = usb_hcd_request_irqs(hcd, irqnum, irqflags);
-	if (retval)
-		goto err_request_irq;
+	if (usb_hcd_is_primary_hcd(hcd)) {
+		retval = usb_hcd_request_irqs(hcd, irqnum, irqflags);
+		if (retval)
+			goto err_request_irq;
+	}
 
 	hcd->state = HC_STATE_RUNNING;
 	retval = hcd->driver->start(hcd);
@@ -2416,7 +2484,7 @@ err_register_root_hub:
 	clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 	del_timer_sync(&hcd->rh_timer);
 err_hcd_driver_start:
-	if (hcd->irq >= 0)
+	if (usb_hcd_is_primary_hcd(hcd) && hcd->irq >= 0)
 		free_irq(irqnum, hcd);
 err_request_irq:
 err_hcd_driver_setup:
@@ -2480,8 +2548,10 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 	del_timer_sync(&hcd->rh_timer);
 
-	if (hcd->irq >= 0)
-		free_irq(hcd->irq, hcd);
+	if (usb_hcd_is_primary_hcd(hcd)) {
+		if (hcd->irq >= 0)
+			free_irq(hcd->irq, hcd);
+	}
 
 	usb_put_dev(hcd->self.root_hub);
 	usb_deregister_bus(&hcd->self);
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index b8bb6934f30b..0097136ba45d 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -147,6 +147,8 @@ struct usb_hcd {
 	 * to the device, or resetting the bandwidth after a failed attempt.
 	 */
 	struct mutex		*bandwidth_mutex;
+	struct usb_hcd		*shared_hcd;
+	struct usb_hcd		*primary_hcd;
 
 
 #define HCD_BUFFER_POOLS	4
@@ -209,6 +211,7 @@ struct hc_driver {
 	int	flags;
 #define	HCD_MEMORY	0x0001		/* HC regs use memory (else I/O) */
 #define	HCD_LOCAL_MEM	0x0002		/* HC needs local memory */
+#define	HCD_SHARED	0x0004		/* Two (or more) usb_hcds share HW */
 #define	HCD_USB11	0x0010		/* USB 1.1 */
 #define	HCD_USB2	0x0020		/* USB 2.0 */
 #define	HCD_USB3	0x0040		/* USB 3.0 */
@@ -370,8 +373,12 @@ extern int usb_hcd_get_frame_number(struct usb_device *udev);
 
 extern struct usb_hcd *usb_create_hcd(const struct hc_driver *driver,
 		struct device *dev, const char *bus_name);
+extern struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
+		struct device *dev, const char *bus_name,
+		struct usb_hcd *shared_hcd);
 extern struct usb_hcd *usb_get_hcd(struct usb_hcd *hcd);
 extern void usb_put_hcd(struct usb_hcd *hcd);
+extern int usb_hcd_is_primary_hcd(struct usb_hcd *hcd);
 extern int usb_add_hcd(struct usb_hcd *hcd,
 		unsigned int irqnum, unsigned long irqflags);
 extern void usb_remove_hcd(struct usb_hcd *hcd);
-- 
cgit v1.2.3


From 131dec344d5e41f01e4791aa4c80eb4bdb1e5274 Mon Sep 17 00:00:00 2001
From: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Date: Mon, 6 Dec 2010 21:00:19 -0800
Subject: USB: Remove bogus USB_PORT_STAT_SUPER_SPEED symbol.

USB_PORT_STAT_SUPER_SPEED is a made up symbol that the USB core used to
track whether USB ports had a SuperSpeed device attached.  This is a
linux-internal symbol that was used when SuperSpeed and non-SuperSpeed
devices would show up under the same xHCI roothub.  This particular
port status is never returned by external USB 3.0 hubs.  (Instead they
have a USB_PORT_STAT_SPEED_5GBPS that uses a completely different speed
mask.)

Now that the xHCI driver registers two roothubs, USB 3.0 devices will only
show up under USB 3.0 hubs.  Rip out USB_PORT_STAT_SUPER_SPEED and replace
it with calls to hub_is_superspeed().

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/hub.c      | 36 ++++++++----------------------------
 drivers/usb/host/xhci-hub.c |  2 --
 include/linux/usb/ch11.h    |  1 -
 3 files changed, 8 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 825d803720b3..13aafd1b45e5 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -155,14 +155,14 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rwsem);
 
 static int usb_reset_and_verify_device(struct usb_device *udev);
 
-static inline char *portspeed(int portstatus)
+static inline char *portspeed(struct usb_hub *hub, int portstatus)
 {
+	if (hub_is_superspeed(hub->hdev))
+		return "5.0 Gb/s";
 	if (portstatus & USB_PORT_STAT_HIGH_SPEED)
     		return "480 Mb/s";
 	else if (portstatus & USB_PORT_STAT_LOW_SPEED)
 		return "1.5 Mb/s";
-	else if (portstatus & USB_PORT_STAT_SUPER_SPEED)
-		return "5.0 Gb/s";
 	else
 		return "12 Mb/s";
 }
@@ -385,9 +385,6 @@ static int hub_port_status(struct usb_hub *hub, int port1,
 			u16 tmp = *status & USB_SS_PORT_STAT_MASK;
 			if (*status & USB_SS_PORT_STAT_POWER)
 				tmp |= USB_PORT_STAT_POWER;
-			if ((*status & USB_SS_PORT_STAT_SPEED) ==
-					USB_PORT_STAT_SPEED_5GBPS)
-				tmp |= USB_PORT_STAT_SUPER_SPEED;
 			*status = tmp;
 		}
 
@@ -795,12 +792,8 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			 * USB3 protocol ports will automatically transition
 			 * to Enabled state when detect an USB3.0 device attach.
 			 * Do not disable USB3 protocol ports.
-			 * FIXME: USB3 root hub and external hubs are treated
-			 * differently here.
 			 */
-			if (hdev->descriptor.bDeviceProtocol != 3 ||
-			    (!hdev->parent &&
-			     !(portstatus & USB_PORT_STAT_SUPER_SPEED))) {
+			if (!hub_is_superspeed(hdev)) {
 				clear_port_feature(hdev, port1,
 						   USB_PORT_FEAT_ENABLE);
 				portstatus &= ~USB_PORT_STAT_ENABLE;
@@ -2067,14 +2060,12 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1,
 		    (portstatus & USB_PORT_STAT_ENABLE)) {
 			if (hub_is_wusb(hub))
 				udev->speed = USB_SPEED_WIRELESS;
-			else if (portstatus & USB_PORT_STAT_SUPER_SPEED)
+			else if (hub_is_superspeed(hub->hdev))
 				udev->speed = USB_SPEED_SUPER;
 			else if (portstatus & USB_PORT_STAT_HIGH_SPEED)
 				udev->speed = USB_SPEED_HIGH;
 			else if (portstatus & USB_PORT_STAT_LOW_SPEED)
 				udev->speed = USB_SPEED_LOW;
-			else if (portstatus & USB_PORT_STAT_SUPER_SPEED)
-				udev->speed = USB_SPEED_SUPER;
 			else
 				udev->speed = USB_SPEED_FULL;
 			return 0;
@@ -3067,7 +3058,7 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1,
 
 	dev_dbg (hub_dev,
 		"port %d, status %04x, change %04x, %s\n",
-		port1, portstatus, portchange, portspeed (portstatus));
+		port1, portstatus, portchange, portspeed(hub, portstatus));
 
 	if (hub->has_indicators) {
 		set_port_led(hub, port1, HUB_LED_AUTO);
@@ -3168,19 +3159,8 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1,
 		udev->level = hdev->level + 1;
 		udev->wusb = hub_is_wusb(hub);
 
-		/*
-		 * USB 3.0 devices are reset automatically before the connect
-		 * port status change appears, and the root hub port status
-		 * shows the correct speed.  We also get port change
-		 * notifications for USB 3.0 devices from the USB 3.0 portion of
-		 * an external USB 3.0 hub, but this isn't handled correctly yet
-		 * FIXME.
-		 */
-
-		if (!(hcd->driver->flags & HCD_USB3))
-			udev->speed = USB_SPEED_UNKNOWN;
-		else if ((hdev->parent == NULL) &&
-				(portstatus & USB_PORT_STAT_SUPER_SPEED))
+		/* Only USB 3.0 devices are connected to SuperSpeed hubs. */
+		if (hub_is_superspeed(hub->hdev))
 			udev->speed = USB_SPEED_SUPER;
 		else
 			udev->speed = USB_SPEED_UNKNOWN;
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 770f84cb7327..a78f2ebd11b7 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -155,8 +155,6 @@ static unsigned int xhci_port_speed(unsigned int port_status)
 		return USB_PORT_STAT_LOW_SPEED;
 	if (DEV_HIGHSPEED(port_status))
 		return USB_PORT_STAT_HIGH_SPEED;
-	if (DEV_SUPERSPEED(port_status))
-		return USB_PORT_STAT_SUPER_SPEED;
 	/*
 	 * FIXME: Yes, we should check for full speed, but the core uses that as
 	 * a default in portspeed() in usb/core/hub.c (which is the only place
diff --git a/include/linux/usb/ch11.h b/include/linux/usb/ch11.h
index 22afcd37bc3f..4ebaf0824179 100644
--- a/include/linux/usb/ch11.h
+++ b/include/linux/usb/ch11.h
@@ -109,7 +109,6 @@ struct usb_port_status {
 #define USB_PORT_STAT_TEST              0x0800
 #define USB_PORT_STAT_INDICATOR         0x1000
 /* bits 13 to 15 are reserved */
-#define USB_PORT_STAT_SUPER_SPEED	0x8000	/* Linux-internal */
 
 /*
  * Additions to wPortStatus bit field from USB 3.0
-- 
cgit v1.2.3


From 500132a0f26ad7d9916102193cbc6c1b1becb373 Mon Sep 17 00:00:00 2001
From: Paul Zimmerman <Paul.Zimmerman@synopsys.com>
Date: Mon, 28 Feb 2011 18:11:27 -0800
Subject: USB: Add support for SuperSpeed isoc endpoints

Use the Mult and bMaxBurst values from the endpoint companion
descriptor to calculate the max length of an isoc transfer.

Add USB_SS_MULT macro to access Mult field of bmAttributes, at
Sarah's suggestion.

This patch should be queued for the 2.6.36 and 2.6.37 stable trees, since
those were the first kernels to have isochronous support for SuperSpeed
devices.

Signed-off-by: Paul Zimmerman <paulz@synopsys.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: stable@kernel.org
---
 drivers/usb/core/urb.c  | 11 ++++++++++-
 include/linux/usb/ch9.h |  2 ++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index c14fc082864f..ae334b067c13 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -366,7 +366,16 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 	if (xfertype == USB_ENDPOINT_XFER_ISOC) {
 		int	n, len;
 
-		/* FIXME SuperSpeed isoc endpoints have up to 16 bursts */
+		/* SuperSpeed isoc endpoints have up to 16 bursts of up to
+		 * 3 packets each
+		 */
+		if (dev->speed == USB_SPEED_SUPER) {
+			int     burst = 1 + ep->ss_ep_comp.bMaxBurst;
+			int     mult = USB_SS_MULT(ep->ss_ep_comp.bmAttributes);
+			max *= burst;
+			max *= mult;
+		}
+
 		/* "high bandwidth" mode, 1-3 packets/uframe? */
 		if (dev->speed == USB_SPEED_HIGH) {
 			int	mult = 1 + ((max >> 11) & 0x03);
diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h
index 34316ba05f29..b72f305ce6bd 100644
--- a/include/linux/usb/ch9.h
+++ b/include/linux/usb/ch9.h
@@ -585,6 +585,8 @@ struct usb_ss_ep_comp_descriptor {
 #define USB_DT_SS_EP_COMP_SIZE		6
 /* Bits 4:0 of bmAttributes if this is a bulk endpoint */
 #define USB_SS_MAX_STREAMS(p)		(1 << ((p) & 0x1f))
+/* Bits 1:0 of bmAttributes if this is an isoc endpoint */
+#define USB_SS_MULT(p)			(1 + ((p) & 0x3))
 
 /*-------------------------------------------------------------------------*/
 
-- 
cgit v1.2.3


From 9736acf395d3608583a7be70f62800b494fa103c Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 8 Mar 2011 00:05:43 +0000
Subject: xfrm: Add basic infrastructure to support IPsec extended sequence
 numbers

This patch adds the struct xfrm_replay_state_esn which will be
used to support IPsec extended sequence numbers and anti replay windows
bigger than 32 packets. Also we add a function that returns the actual
size of the xfrm_replay_state_esn, a xfrm netlink atribute and a xfrm state
flag for the use of extended sequence numbers.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/xfrm.h | 12 ++++++++++++
 include/net/xfrm.h   |  7 +++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
index b93d6f598085..22e61fdf75a2 100644
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -84,6 +84,16 @@ struct xfrm_replay_state {
 	__u32	bitmap;
 };
 
+struct xfrm_replay_state_esn {
+	unsigned int	bmp_len;
+	__u32		oseq;
+	__u32		seq;
+	__u32		oseq_hi;
+	__u32		seq_hi;
+	__u32		replay_window;
+	__u32		bmp[0];
+};
+
 struct xfrm_algo {
 	char		alg_name[64];
 	unsigned int	alg_key_len;    /* in bits */
@@ -284,6 +294,7 @@ enum xfrm_attr_type_t {
 	XFRMA_ALG_AUTH_TRUNC,	/* struct xfrm_algo_auth */
 	XFRMA_MARK,		/* struct xfrm_mark */
 	XFRMA_TFCPAD,		/* __u32 */
+	XFRMA_REPLAY_ESN_VAL,	/* struct xfrm_replay_esn */
 	__XFRMA_MAX
 
 #define XFRMA_MAX (__XFRMA_MAX - 1)
@@ -351,6 +362,7 @@ struct xfrm_usersa_info {
 #define XFRM_STATE_ICMP		16
 #define XFRM_STATE_AF_UNSPEC	32
 #define XFRM_STATE_ALIGN4	64
+#define XFRM_STATE_ESN		128
 };
 
 struct xfrm_usersa_id {
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 8f8bd82606bf..7640822bc515 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -186,9 +186,11 @@ struct xfrm_state {
 
 	/* State for replay detection */
 	struct xfrm_replay_state replay;
+	struct xfrm_replay_state_esn *replay_esn;
 
 	/* Replay detection state at the time we sent the last notification */
 	struct xfrm_replay_state preplay;
+	struct xfrm_replay_state_esn *preplay_esn;
 
 	/* internal flag that only holds state for delayed aevent at the
 	 * moment
@@ -1569,6 +1571,11 @@ static inline int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg)
 	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
 }
 
+static inline int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn)
+{
+	return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32);
+}
+
 #ifdef CONFIG_XFRM_MIGRATE
 static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig)
 {
-- 
cgit v1.2.3


From 1ce3644ade9c865c755bf0f6a4e109b7bb6eb60f Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 8 Mar 2011 00:06:31 +0000
Subject: xfrm: Use separate low and high order bits of the sequence numbers in
 xfrm_skb_cb

To support IPsec extended sequence numbers, we split the
output sequence numbers of xfrm_skb_cb in low and high order 32 bits
and we add the high order 32 bits to the input sequence numbers.
All users are updated accordingly.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     | 10 ++++++++--
 net/ipv4/ah4.c         |  2 +-
 net/ipv4/esp4.c        |  4 ++--
 net/ipv6/ah6.c         |  2 +-
 net/ipv6/esp6.c        |  4 ++--
 net/xfrm/xfrm_input.c  |  4 ++--
 net/xfrm/xfrm_output.c |  2 +-
 7 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 7640822bc515..cb6d9b3fc55e 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -582,8 +582,14 @@ struct xfrm_skb_cb {
 
         /* Sequence number for replay protection. */
 	union {
-		u64 output;
-		__be32 input;
+		struct {
+			__u32 low;
+			__u32 hi;
+		} output;
+		struct {
+			__be32 low;
+			__be32 hi;
+		} input;
 	} seq;
 };
 
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 325053df6e70..4286fd3cc0e2 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -208,7 +208,7 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	ah->reserved = 0;
 	ah->spi = x->id.spi;
-	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output);
+	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg, 0, skb->len);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index e42a905180f0..882dbbb7d799 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -215,7 +215,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	}
 
 	esph->spi = x->id.spi;
-	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output);
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
@@ -227,7 +227,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
 	aead_givcrypt_set_assoc(req, asg, sizeof(*esph));
 	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output);
+			      XFRM_SKB_CB(skb)->seq.output.low);
 
 	ESP_SKB_CB(skb)->tmp = tmp;
 	err = crypto_aead_givencrypt(req);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 1aba54ae53c4..2195ae651923 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -409,7 +409,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	ah->reserved = 0;
 	ah->spi = x->id.spi;
-	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output);
+	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg, 0, skb->len);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 1b5c9825743b..c7b5d5ee0dee 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -204,7 +204,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
 	esph->spi = x->id.spi;
-	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output);
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
@@ -216,7 +216,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
 	aead_givcrypt_set_assoc(req, asg, sizeof(*esph));
 	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output);
+			      XFRM_SKB_CB(skb)->seq.output.low);
 
 	ESP_SKB_CB(skb)->tmp = tmp;
 	err = crypto_aead_givencrypt(req);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 45f1c98d4fce..b173b7fdc433 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -118,7 +118,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	if (encap_type < 0) {
 		async = 1;
 		x = xfrm_input_state(skb);
-		seq = XFRM_SKB_CB(skb)->seq.input;
+		seq = XFRM_SKB_CB(skb)->seq.input.low;
 		goto resume;
 	}
 
@@ -184,7 +184,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		spin_unlock(&x->lock);
 
-		XFRM_SKB_CB(skb)->seq.input = seq;
+		XFRM_SKB_CB(skb)->seq.input.low = seq;
 
 		nexthdr = x->type->input(x, skb);
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 64f2ae1fdc15..4b63776a0264 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -68,7 +68,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 		}
 
 		if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
-			XFRM_SKB_CB(skb)->seq.output = ++x->replay.oseq;
+			XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
 			if (unlikely(x->replay.oseq == 0)) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
 				x->replay.oseq--;
-- 
cgit v1.2.3


From 9fdc4883d92d20842c5acea77a4a21bb1574b495 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 8 Mar 2011 00:08:32 +0000
Subject: xfrm: Move IPsec replay detection functions to a separate file

To support multiple versions of replay detection, we move the replay
detection functions to a separate file and make them accessible
via function pointers contained in the struct xfrm_replay.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     |  24 +++++++--
 net/xfrm/Makefile      |   2 +-
 net/xfrm/xfrm_input.c  |   5 +-
 net/xfrm/xfrm_output.c |  15 ++----
 net/xfrm/xfrm_replay.c | 141 +++++++++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_state.c  | 111 ++------------------------------------
 net/xfrm/xfrm_user.c   |   4 +-
 7 files changed, 174 insertions(+), 128 deletions(-)
 create mode 100644 net/xfrm/xfrm_replay.c

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index cb6d9b3fc55e..41def092b824 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -192,6 +192,9 @@ struct xfrm_state {
 	struct xfrm_replay_state preplay;
 	struct xfrm_replay_state_esn *preplay_esn;
 
+	/* The functions for replay detection. */
+	struct xfrm_replay	*repl;
+
 	/* internal flag that only holds state for delayed aevent at the
 	 * moment
 	*/
@@ -261,6 +264,15 @@ struct km_event {
 	struct net *net;
 };
 
+struct xfrm_replay {
+	void	(*advance)(struct xfrm_state *x, __be32 net_seq);
+	int	(*check)(struct xfrm_state *x,
+			 struct sk_buff *skb,
+			 __be32 net_seq);
+	void	(*notify)(struct xfrm_state *x, int event);
+	int	(*overflow)(struct xfrm_state *x, struct sk_buff *skb);
+};
+
 struct net_device;
 struct xfrm_type;
 struct xfrm_dst;
@@ -693,6 +705,8 @@ extern void xfrm_audit_state_delete(struct xfrm_state *x, int result,
 				    u32 auid, u32 ses, u32 secid);
 extern void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
 					     struct sk_buff *skb);
+extern void xfrm_audit_state_replay(struct xfrm_state *x,
+				    struct sk_buff *skb, __be32 net_seq);
 extern void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family);
 extern void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family,
 				      __be32 net_spi, __be32 net_seq);
@@ -725,6 +739,11 @@ static inline void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
 {
 }
 
+static inline void xfrm_audit_state_replay(struct xfrm_state *x,
+					   struct sk_buff *skb, __be32 net_seq)
+{
+}
+
 static inline void xfrm_audit_state_notfound_simple(struct sk_buff *skb,
 				      u16 family)
 {
@@ -1408,10 +1427,7 @@ extern int xfrm_state_delete(struct xfrm_state *x);
 extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info);
 extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 extern void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
-extern int xfrm_replay_check(struct xfrm_state *x,
-			     struct sk_buff *skb, __be32 seq);
-extern void xfrm_replay_advance(struct xfrm_state *x, __be32 seq);
-extern void xfrm_replay_notify(struct xfrm_state *x, int event);
+extern int xfrm_init_replay(struct xfrm_state *x);
 extern int xfrm_state_mtu(struct xfrm_state *x, int mtu);
 extern int xfrm_init_state(struct xfrm_state *x);
 extern int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index c631047e1b27..aa429eefe919 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
 		      xfrm_input.o xfrm_output.o xfrm_algo.o \
-		      xfrm_sysctl.o
+		      xfrm_sysctl.o xfrm_replay.o
 obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b173b7fdc433..55d5f5c3d119 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -172,7 +172,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			goto drop_unlock;
 		}
 
-		if (x->props.replay_window && xfrm_replay_check(x, skb, seq)) {
+		if (x->props.replay_window && x->repl->check(x, skb, seq)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
 			goto drop_unlock;
 		}
@@ -206,8 +206,7 @@ resume:
 		/* only the first xfrm gets the encap type */
 		encap_type = 0;
 
-		if (x->props.replay_window)
-			xfrm_replay_advance(x, seq);
+		x->repl->advance(x, seq);
 
 		x->curlft.bytes += skb->len;
 		x->curlft.packets++;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 4b63776a0264..1aba03f449cc 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -67,17 +67,10 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 			goto error;
 		}
 
-		if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
-			XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
-			if (unlikely(x->replay.oseq == 0)) {
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
-				x->replay.oseq--;
-				xfrm_audit_state_replay_overflow(x, skb);
-				err = -EOVERFLOW;
-				goto error;
-			}
-			if (xfrm_aevent_is_on(net))
-				xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+		err = x->repl->overflow(x, skb);
+		if (err) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
+			goto error;
 		}
 
 		x->curlft.bytes += skb->len;
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
new file mode 100644
index 000000000000..42d68f324874
--- /dev/null
+++ b/net/xfrm/xfrm_replay.c
@@ -0,0 +1,141 @@
+/*
+ * xfrm_replay.c - xfrm replay detection, derived from xfrm_state.c.
+ */
+
+#include <net/xfrm.h>
+
+static void xfrm_replay_notify(struct xfrm_state *x, int event)
+{
+	struct km_event c;
+	/* we send notify messages in case
+	 *  1. we updated on of the sequence numbers, and the seqno difference
+	 *     is at least x->replay_maxdiff, in this case we also update the
+	 *     timeout of our timer function
+	 *  2. if x->replay_maxage has elapsed since last update,
+	 *     and there were changes
+	 *
+	 *  The state structure must be locked!
+	 */
+
+	switch (event) {
+	case XFRM_REPLAY_UPDATE:
+		if (x->replay_maxdiff &&
+		    (x->replay.seq - x->preplay.seq < x->replay_maxdiff) &&
+		    (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) {
+			if (x->xflags & XFRM_TIME_DEFER)
+				event = XFRM_REPLAY_TIMEOUT;
+			else
+				return;
+		}
+
+		break;
+
+	case XFRM_REPLAY_TIMEOUT:
+		if (memcmp(&x->replay, &x->preplay,
+			   sizeof(struct xfrm_replay_state)) == 0) {
+			x->xflags |= XFRM_TIME_DEFER;
+			return;
+		}
+
+		break;
+	}
+
+	memcpy(&x->preplay, &x->replay, sizeof(struct xfrm_replay_state));
+	c.event = XFRM_MSG_NEWAE;
+	c.data.aevent = event;
+	km_state_notify(x, &c);
+
+	if (x->replay_maxage &&
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+		x->xflags &= ~XFRM_TIME_DEFER;
+}
+
+static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct net *net = xs_net(x);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq;
+		if (unlikely(x->replay.oseq == 0)) {
+			x->replay.oseq--;
+			xfrm_audit_state_replay_overflow(x, skb);
+			err = -EOVERFLOW;
+
+			return err;
+		}
+		if (xfrm_aevent_is_on(net))
+			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_check(struct xfrm_state *x,
+		      struct sk_buff *skb, __be32 net_seq)
+{
+	u32 diff;
+	u32 seq = ntohl(net_seq);
+
+	if (unlikely(seq == 0))
+		goto err;
+
+	if (likely(seq > x->replay.seq))
+		return 0;
+
+	diff = x->replay.seq - seq;
+	if (diff >= min_t(unsigned int, x->props.replay_window,
+			  sizeof(x->replay.bitmap) * 8)) {
+		x->stats.replay_window++;
+		goto err;
+	}
+
+	if (x->replay.bitmap & (1U << diff)) {
+		x->stats.replay++;
+		goto err;
+	}
+	return 0;
+
+err:
+	xfrm_audit_state_replay(x, skb, net_seq);
+	return -EINVAL;
+}
+
+static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
+{
+	u32 diff;
+	u32 seq = ntohl(net_seq);
+
+	if (!x->props.replay_window)
+		return;
+
+	if (seq > x->replay.seq) {
+		diff = seq - x->replay.seq;
+		if (diff < x->props.replay_window)
+			x->replay.bitmap = ((x->replay.bitmap) << diff) | 1;
+		else
+			x->replay.bitmap = 1;
+		x->replay.seq = seq;
+	} else {
+		diff = x->replay.seq - seq;
+		x->replay.bitmap |= (1U << diff);
+	}
+
+	if (xfrm_aevent_is_on(xs_net(x)))
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+}
+
+static struct xfrm_replay xfrm_replay_legacy = {
+	.advance	= xfrm_replay_advance,
+	.check		= xfrm_replay_check,
+	.notify		= xfrm_replay_notify,
+	.overflow	= xfrm_replay_overflow,
+};
+
+int xfrm_init_replay(struct xfrm_state *x)
+{
+	x->repl = &xfrm_replay_legacy;
+
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_init_replay);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index cd6be49f2ae8..23779d19fe02 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -42,13 +42,6 @@ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
 static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
 static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
 
-#ifdef CONFIG_AUDITSYSCALL
-static void xfrm_audit_state_replay(struct xfrm_state *x,
-				    struct sk_buff *skb, __be32 net_seq);
-#else
-#define xfrm_audit_state_replay(x, s, sq)	do { ; } while (0)
-#endif /* CONFIG_AUDITSYSCALL */
-
 static inline unsigned int xfrm_dst_hash(struct net *net,
 					 const xfrm_address_t *daddr,
 					 const xfrm_address_t *saddr,
@@ -1619,54 +1612,6 @@ void xfrm_state_walk_done(struct xfrm_state_walk *walk)
 }
 EXPORT_SYMBOL(xfrm_state_walk_done);
 
-
-void xfrm_replay_notify(struct xfrm_state *x, int event)
-{
-	struct km_event c;
-	/* we send notify messages in case
-	 *  1. we updated on of the sequence numbers, and the seqno difference
-	 *     is at least x->replay_maxdiff, in this case we also update the
-	 *     timeout of our timer function
-	 *  2. if x->replay_maxage has elapsed since last update,
-	 *     and there were changes
-	 *
-	 *  The state structure must be locked!
-	 */
-
-	switch (event) {
-	case XFRM_REPLAY_UPDATE:
-		if (x->replay_maxdiff &&
-		    (x->replay.seq - x->preplay.seq < x->replay_maxdiff) &&
-		    (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) {
-			if (x->xflags & XFRM_TIME_DEFER)
-				event = XFRM_REPLAY_TIMEOUT;
-			else
-				return;
-		}
-
-		break;
-
-	case XFRM_REPLAY_TIMEOUT:
-		if ((x->replay.seq == x->preplay.seq) &&
-		    (x->replay.bitmap == x->preplay.bitmap) &&
-		    (x->replay.oseq == x->preplay.oseq)) {
-			x->xflags |= XFRM_TIME_DEFER;
-			return;
-		}
-
-		break;
-	}
-
-	memcpy(&x->preplay, &x->replay, sizeof(struct xfrm_replay_state));
-	c.event = XFRM_MSG_NEWAE;
-	c.data.aevent = event;
-	km_state_notify(x, &c);
-
-	if (x->replay_maxage &&
-	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
-		x->xflags &= ~XFRM_TIME_DEFER;
-}
-
 static void xfrm_replay_timer_handler(unsigned long data)
 {
 	struct xfrm_state *x = (struct xfrm_state*)data;
@@ -1675,7 +1620,7 @@ static void xfrm_replay_timer_handler(unsigned long data)
 
 	if (x->km.state == XFRM_STATE_VALID) {
 		if (xfrm_aevent_is_on(xs_net(x)))
-			xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
+			x->repl->notify(x, XFRM_REPLAY_TIMEOUT);
 		else
 			x->xflags |= XFRM_TIME_DEFER;
 	}
@@ -1683,57 +1628,6 @@ static void xfrm_replay_timer_handler(unsigned long data)
 	spin_unlock(&x->lock);
 }
 
-int xfrm_replay_check(struct xfrm_state *x,
-		      struct sk_buff *skb, __be32 net_seq)
-{
-	u32 diff;
-	u32 seq = ntohl(net_seq);
-
-	if (unlikely(seq == 0))
-		goto err;
-
-	if (likely(seq > x->replay.seq))
-		return 0;
-
-	diff = x->replay.seq - seq;
-	if (diff >= min_t(unsigned int, x->props.replay_window,
-			  sizeof(x->replay.bitmap) * 8)) {
-		x->stats.replay_window++;
-		goto err;
-	}
-
-	if (x->replay.bitmap & (1U << diff)) {
-		x->stats.replay++;
-		goto err;
-	}
-	return 0;
-
-err:
-	xfrm_audit_state_replay(x, skb, net_seq);
-	return -EINVAL;
-}
-
-void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
-{
-	u32 diff;
-	u32 seq = ntohl(net_seq);
-
-	if (seq > x->replay.seq) {
-		diff = seq - x->replay.seq;
-		if (diff < x->props.replay_window)
-			x->replay.bitmap = ((x->replay.bitmap) << diff) | 1;
-		else
-			x->replay.bitmap = 1;
-		x->replay.seq = seq;
-	} else {
-		diff = x->replay.seq - seq;
-		x->replay.bitmap |= (1U << diff);
-	}
-
-	if (xfrm_aevent_is_on(xs_net(x)))
-		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
-}
-
 static LIST_HEAD(xfrm_km_list);
 static DEFINE_RWLOCK(xfrm_km_lock);
 
@@ -2246,7 +2140,7 @@ void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
 }
 EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow);
 
-static void xfrm_audit_state_replay(struct xfrm_state *x,
+void xfrm_audit_state_replay(struct xfrm_state *x,
 			     struct sk_buff *skb, __be32 net_seq)
 {
 	struct audit_buffer *audit_buf;
@@ -2261,6 +2155,7 @@ static void xfrm_audit_state_replay(struct xfrm_state *x,
 			 spi, spi, ntohl(net_seq));
 	audit_log_end(audit_buf);
 }
+EXPORT_SYMBOL_GPL(xfrm_audit_state_replay);
 
 void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family)
 {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 468ab60d3dc0..f7b3c857c989 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -475,8 +475,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 	x->preplay.seq = x->replay.seq+x->replay_maxdiff;
 	x->preplay.oseq = x->replay.oseq +x->replay_maxdiff;
 
-	/* override default values from above */
+	if ((err = xfrm_init_replay(x)))
+		goto error;
 
+	/* override default values from above */
 	xfrm_update_ae_params(x, attrs);
 
 	return x;
-- 
cgit v1.2.3


From 2cd084678fc1eb75aec4f7ae3d339d232c00ec61 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 8 Mar 2011 00:09:51 +0000
Subject: xfrm: Add support for IPsec extended sequence numbers

This patch adds support for IPsec extended sequence numbers (esn)
as defined in RFC 4303. The bits to manage the anti-replay window
are based on a patch from Alex Badea.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h     |   1 +
 net/xfrm/xfrm_input.c  |   4 ++
 net/xfrm/xfrm_replay.c | 190 ++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 194 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 41def092b824..42a8c32a10e2 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1427,6 +1427,7 @@ extern int xfrm_state_delete(struct xfrm_state *x);
 extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info);
 extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 extern void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
+extern u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
 extern int xfrm_init_replay(struct xfrm_state *x);
 extern int xfrm_state_mtu(struct xfrm_state *x, int mtu);
 extern int xfrm_init_state(struct xfrm_state *x);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 55d5f5c3d119..872065ca7f8c 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -107,6 +107,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	struct net *net = dev_net(skb->dev);
 	int err;
 	__be32 seq;
+	__be32 seq_hi;
 	struct xfrm_state *x;
 	xfrm_address_t *daddr;
 	struct xfrm_mode *inner_mode;
@@ -184,7 +185,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		spin_unlock(&x->lock);
 
+		seq_hi = htonl(xfrm_replay_seqhi(x, seq));
+
 		XFRM_SKB_CB(skb)->seq.input.low = seq;
+		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
 		nexthdr = x->type->input(x, skb);
 
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 50589ea9d6a8..2f5be5b15740 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -20,6 +20,31 @@
 
 #include <net/xfrm.h>
 
+u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq)
+{
+	u32 seq, seq_hi, bottom;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+
+	if (!(x->props.flags & XFRM_STATE_ESN))
+		return 0;
+
+	seq = ntohl(net_seq);
+	seq_hi = replay_esn->seq_hi;
+	bottom = replay_esn->seq - replay_esn->replay_window + 1;
+
+	if (likely(replay_esn->seq >= replay_esn->replay_window - 1)) {
+		/* A. same subspace */
+		if (unlikely(seq < bottom))
+			seq_hi++;
+	} else {
+		/* B. window spans two subspaces */
+		if (unlikely(seq >= bottom))
+			seq_hi--;
+	}
+
+	return seq_hi;
+}
+
 static void xfrm_replay_notify(struct xfrm_state *x, int event)
 {
 	struct km_event c;
@@ -313,6 +338,160 @@ static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event)
 		x->xflags &= ~XFRM_TIME_DEFER;
 }
 
+static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = 0;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	struct net *net = xs_net(x);
+
+	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
+		XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq;
+		XFRM_SKB_CB(skb)->seq.output.hi = replay_esn->oseq_hi;
+
+		if (unlikely(replay_esn->oseq == 0)) {
+			XFRM_SKB_CB(skb)->seq.output.hi = ++replay_esn->oseq_hi;
+
+			if (replay_esn->oseq_hi == 0) {
+				replay_esn->oseq--;
+				replay_esn->oseq_hi--;
+				xfrm_audit_state_replay_overflow(x, skb);
+				err = -EOVERFLOW;
+
+				return err;
+			}
+		}
+		if (xfrm_aevent_is_on(net))
+			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+	}
+
+	return err;
+}
+
+static int xfrm_replay_check_esn(struct xfrm_state *x,
+				 struct sk_buff *skb, __be32 net_seq)
+{
+	unsigned int bitnr, nr;
+	u32 diff;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+	u32 seq = ntohl(net_seq);
+	u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+	u32 wsize = replay_esn->replay_window;
+	u32 top = replay_esn->seq;
+	u32 bottom = top - wsize + 1;
+
+	if (unlikely(seq == 0 && replay_esn->seq_hi == 0 &&
+		     (replay_esn->seq < replay_esn->replay_window - 1)))
+		goto err;
+
+	diff = top - seq;
+
+	if (likely(top >= wsize - 1)) {
+		/* A. same subspace */
+		if (likely(seq > top) || seq < bottom)
+			return 0;
+	} else {
+		/* B. window spans two subspaces */
+		if (likely(seq > top && seq < bottom))
+			return 0;
+		if (seq >= bottom)
+			diff = ~seq + top + 1;
+	}
+
+	if (diff >= replay_esn->replay_window) {
+		x->stats.replay_window++;
+		goto err;
+	}
+
+	if (pos >= diff) {
+		bitnr = (pos - diff) % replay_esn->replay_window;
+		nr = bitnr >> 5;
+		bitnr = bitnr & 0x1F;
+		if (replay_esn->bmp[nr] & (1U << bitnr))
+			goto err_replay;
+	} else {
+		bitnr = replay_esn->replay_window - (diff - pos);
+		nr = bitnr >> 5;
+		bitnr = bitnr & 0x1F;
+		if (replay_esn->bmp[nr] & (1U << bitnr))
+			goto err_replay;
+	}
+	return 0;
+
+err_replay:
+	x->stats.replay++;
+err:
+	xfrm_audit_state_replay(x, skb, net_seq);
+	return -EINVAL;
+}
+
+static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
+{
+	unsigned int bitnr, nr, i;
+	int wrap;
+	u32 diff, pos, seq, seq_hi;
+	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
+
+	if (!replay_esn->replay_window)
+		return;
+
+	seq = ntohl(net_seq);
+	pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+	seq_hi = xfrm_replay_seqhi(x, net_seq);
+	wrap = seq_hi - replay_esn->seq_hi;
+
+	if ((!wrap && seq > replay_esn->seq) || wrap > 0) {
+		if (likely(!wrap))
+			diff = seq - replay_esn->seq;
+		else
+			diff = ~replay_esn->seq + seq + 1;
+
+		if (diff < replay_esn->replay_window) {
+			for (i = 1; i < diff; i++) {
+				bitnr = (pos + i) % replay_esn->replay_window;
+				nr = bitnr >> 5;
+				bitnr = bitnr & 0x1F;
+				replay_esn->bmp[nr] &=  ~(1U << bitnr);
+			}
+
+			bitnr = (pos + diff) % replay_esn->replay_window;
+			nr = bitnr >> 5;
+			bitnr = bitnr & 0x1F;
+			replay_esn->bmp[nr] |= (1U << bitnr);
+		} else {
+			nr = replay_esn->replay_window >> 5;
+			for (i = 0; i <= nr; i++)
+				replay_esn->bmp[i] = 0;
+
+			bitnr = (pos + diff) % replay_esn->replay_window;
+			nr = bitnr >> 5;
+			bitnr = bitnr & 0x1F;
+			replay_esn->bmp[nr] |= (1U << bitnr);
+		}
+
+		replay_esn->seq = seq;
+
+		if (unlikely(wrap > 0))
+			replay_esn->seq_hi++;
+	} else {
+		diff = replay_esn->seq - seq;
+
+		if (pos >= diff) {
+			bitnr = (pos - diff) % replay_esn->replay_window;
+			nr = bitnr >> 5;
+			bitnr = bitnr & 0x1F;
+			replay_esn->bmp[nr] |= (1U << bitnr);
+		} else {
+			bitnr = replay_esn->replay_window - (diff - pos);
+			nr = bitnr >> 5;
+			bitnr = bitnr & 0x1F;
+			replay_esn->bmp[nr] |= (1U << bitnr);
+		}
+	}
+
+	if (xfrm_aevent_is_on(xs_net(x)))
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
+}
+
 static struct xfrm_replay xfrm_replay_legacy = {
 	.advance	= xfrm_replay_advance,
 	.check		= xfrm_replay_check,
@@ -327,6 +506,13 @@ static struct xfrm_replay xfrm_replay_bmp = {
 	.overflow	= xfrm_replay_overflow_bmp,
 };
 
+static struct xfrm_replay xfrm_replay_esn = {
+	.advance	= xfrm_replay_advance_esn,
+	.check		= xfrm_replay_check_esn,
+	.notify		= xfrm_replay_notify_bmp,
+	.overflow	= xfrm_replay_overflow_esn,
+};
+
 int xfrm_init_replay(struct xfrm_state *x)
 {
 	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
@@ -336,11 +522,13 @@ int xfrm_init_replay(struct xfrm_state *x)
 		    replay_esn->bmp_len * sizeof(__u32))
 			return -EINVAL;
 
+	if ((x->props.flags & XFRM_STATE_ESN) && x->replay_esn)
+		x->repl = &xfrm_replay_esn;
+	else
 		x->repl = &xfrm_replay_bmp;
 	} else
 		x->repl = &xfrm_replay_legacy;
 
-
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_init_replay);
-- 
cgit v1.2.3


From 64b97594251bb909d74d64012a2b9e5cc32bb11d Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@st.com>
Date: Tue, 22 Feb 2011 14:32:38 +0530
Subject: libata-sff: add ata_sff_queue_work() & ata_sff_queue_delayed_work()

This patch adds ata_sff_queue_work() & ata_sff_queue_delayed_work() routine in
libata-sff.c file. This routine can be used by ata drivers to use ata_sff_wq.

Signed-off-by: Viresh Kumar <viresh.kumar@st.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
---
 drivers/ata/libata-sff.c | 15 +++++++++++++--
 include/linux/libata.h   |  3 +++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index e75a02d61a8f..cf7acbc0cfcb 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -1302,6 +1302,18 @@ fsm_start:
 }
 EXPORT_SYMBOL_GPL(ata_sff_hsm_move);
 
+void ata_sff_queue_work(struct work_struct *work)
+{
+	queue_work(ata_sff_wq, work);
+}
+EXPORT_SYMBOL_GPL(ata_sff_queue_work);
+
+void ata_sff_queue_delayed_work(struct delayed_work *dwork, unsigned long delay)
+{
+	queue_delayed_work(ata_sff_wq, dwork, delay);
+}
+EXPORT_SYMBOL_GPL(ata_sff_queue_delayed_work);
+
 void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay)
 {
 	struct ata_port *ap = link->ap;
@@ -1311,8 +1323,7 @@ void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay)
 	ap->sff_pio_task_link = link;
 
 	/* may fail if ata_sff_flush_pio_task() in progress */
-	queue_delayed_work(ata_sff_wq, &ap->sff_pio_task,
-			   msecs_to_jiffies(delay));
+	ata_sff_queue_delayed_work(&ap->sff_pio_task, msecs_to_jiffies(delay));
 }
 EXPORT_SYMBOL_GPL(ata_sff_queue_pio_task);
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 71333aa39532..c71f46960f39 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1610,6 +1610,9 @@ extern void ata_sff_irq_on(struct ata_port *ap);
 extern void ata_sff_irq_clear(struct ata_port *ap);
 extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 			    u8 status, int in_wq);
+extern void ata_sff_queue_work(struct work_struct *work);
+extern void ata_sff_queue_delayed_work(struct delayed_work *dwork,
+		unsigned long delay);
 extern void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay);
 extern unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc);
 extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc);
-- 
cgit v1.2.3


From a480167b23ef9b35ec0299bb3e1b11b4ed6b3508 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@st.com>
Date: Tue, 22 Feb 2011 15:46:07 +0530
Subject: pata_arasan_cf: Adding support for arasan compact flash host
 controller

The Arasan CompactFlash Device Controller has three basic modes of
operation: PC card ATA using I/O mode, PC card ATA using memory mode, PC card
ATA using true IDE modes.

Currently driver supports only True IDE mode.

Signed-off-by: Viresh Kumar <viresh.kumar@st.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
---
 MAINTAINERS                         |   7 +
 drivers/ata/Kconfig                 |   6 +
 drivers/ata/Makefile                |   1 +
 drivers/ata/pata_arasan_cf.c        | 977 ++++++++++++++++++++++++++++++++++++
 include/linux/pata_arasan_cf_data.h |  47 ++
 5 files changed, 1038 insertions(+)
 create mode 100644 drivers/ata/pata_arasan_cf.c
 create mode 100644 include/linux/pata_arasan_cf_data.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 8afba6321e24..3f4b3f9edd48 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -557,6 +557,13 @@ S:	Maintained
 F:	drivers/net/appletalk/
 F:	net/appletalk/
 
+ARASAN COMPACT FLASH PATA CONTROLLER
+M:	Viresh Kumar <viresh.kumar@st.com>
+L:	linux-ide@vger.kernel.org
+S:	Maintained
+F:	include/linux/pata_arasan_cf_data.h
+F:	drivers/ata/pata_arasan_cf.c
+
 ARC FRAMEBUFFER DRIVER
 M:	Jaya Kumar <jayalk@intworks.biz>
 S:	Maintained
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 8a1fc396f055..75afa75a515e 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -311,6 +311,12 @@ config PATA_AMD
 
 	  If unsure, say N.
 
+config PATA_ARASAN_CF
+	tristate "ARASAN CompactFlash PATA Controller Support"
+	select DMA_ENGINE
+	help
+	  Say Y here to support the ARASAN CompactFlash PATA controller
+
 config PATA_ARTOP
 	tristate "ARTOP 6210/6260 PATA support"
 	depends on PCI
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 27291aad6ca7..8ac64e1aa051 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_SATA_DWC)		+= sata_dwc_460ex.o
 
 # SFF w/ custom DMA
 obj-$(CONFIG_PDC_ADMA)		+= pdc_adma.o
+obj-$(CONFIG_PATA_ARASAN_CF)	+= pata_arasan_cf.o
 obj-$(CONFIG_PATA_OCTEON_CF)	+= pata_octeon_cf.o
 obj-$(CONFIG_SATA_QSTOR)	+= sata_qstor.o
 obj-$(CONFIG_SATA_SX4)		+= sata_sx4.o
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
new file mode 100644
index 000000000000..b99b3fce307f
--- /dev/null
+++ b/drivers/ata/pata_arasan_cf.c
@@ -0,0 +1,977 @@
+/*
+ * drivers/ata/pata_arasan_cf.c
+ *
+ * Arasan Compact Flash host controller source file
+ *
+ * Copyright (C) 2011 ST Microelectronics
+ * Viresh Kumar <viresh.kumar@st.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/*
+ * The Arasan CompactFlash Device Controller IP core has three basic modes of
+ * operation: PC card ATA using I/O mode, PC card ATA using memory mode, PC card
+ * ATA using true IDE modes. This driver supports only True IDE mode currently.
+ *
+ * Arasan CF Controller shares global irq register with Arasan XD Controller.
+ *
+ * Tested on arch/arm/mach-spear13xx
+ */
+
+#include <linux/ata.h>
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/libata.h>
+#include <linux/module.h>
+#include <linux/pata_arasan_cf_data.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#define DRIVER_NAME	"arasan_cf"
+#define TIMEOUT		msecs_to_jiffies(3000)
+
+/* Registers */
+/* CompactFlash Interface Status */
+#define CFI_STS			0x000
+	#define STS_CHG				(1)
+	#define BIN_AUDIO_OUT			(1 << 1)
+	#define CARD_DETECT1			(1 << 2)
+	#define CARD_DETECT2			(1 << 3)
+	#define INP_ACK				(1 << 4)
+	#define CARD_READY			(1 << 5)
+	#define IO_READY			(1 << 6)
+	#define B16_IO_PORT_SEL			(1 << 7)
+/* IRQ */
+#define IRQ_STS			0x004
+/* Interrupt Enable */
+#define IRQ_EN			0x008
+	#define CARD_DETECT_IRQ			(1)
+	#define STATUS_CHNG_IRQ			(1 << 1)
+	#define MEM_MODE_IRQ			(1 << 2)
+	#define IO_MODE_IRQ			(1 << 3)
+	#define TRUE_IDE_MODE_IRQ		(1 << 8)
+	#define PIO_XFER_ERR_IRQ		(1 << 9)
+	#define BUF_AVAIL_IRQ			(1 << 10)
+	#define XFER_DONE_IRQ			(1 << 11)
+	#define IGNORED_IRQS	(STATUS_CHNG_IRQ | MEM_MODE_IRQ | IO_MODE_IRQ |\
+					TRUE_IDE_MODE_IRQ)
+	#define TRUE_IDE_IRQS	(CARD_DETECT_IRQ | PIO_XFER_ERR_IRQ |\
+					BUF_AVAIL_IRQ | XFER_DONE_IRQ)
+/* Operation Mode */
+#define OP_MODE			0x00C
+	#define CARD_MODE_MASK			(0x3)
+	#define MEM_MODE			(0x0)
+	#define IO_MODE				(0x1)
+	#define TRUE_IDE_MODE			(0x2)
+
+	#define CARD_TYPE_MASK			(1 << 2)
+	#define CF_CARD				(0)
+	#define CF_PLUS_CARD			(1 << 2)
+
+	#define CARD_RESET			(1 << 3)
+	#define CFHOST_ENB			(1 << 4)
+	#define OUTPUTS_TRISTATE		(1 << 5)
+	#define ULTRA_DMA_ENB			(1 << 8)
+	#define MULTI_WORD_DMA_ENB		(1 << 9)
+	#define DRQ_BLOCK_SIZE_MASK		(0x3 << 11)
+	#define DRQ_BLOCK_SIZE_512		(0)
+	#define DRQ_BLOCK_SIZE_1024		(1 << 11)
+	#define DRQ_BLOCK_SIZE_2048		(2 << 11)
+	#define DRQ_BLOCK_SIZE_4096		(3 << 11)
+/* CF Interface Clock Configuration */
+#define CLK_CFG			0x010
+	#define CF_IF_CLK_MASK			(0XF)
+/* CF Timing Mode Configuration */
+#define TM_CFG			0x014
+	#define MEM_MODE_TIMING_MASK		(0x3)
+	#define MEM_MODE_TIMING_250NS		(0x0)
+	#define MEM_MODE_TIMING_120NS		(0x1)
+	#define MEM_MODE_TIMING_100NS		(0x2)
+	#define MEM_MODE_TIMING_80NS		(0x3)
+
+	#define IO_MODE_TIMING_MASK		(0x3 << 2)
+	#define IO_MODE_TIMING_250NS		(0x0 << 2)
+	#define IO_MODE_TIMING_120NS		(0x1 << 2)
+	#define IO_MODE_TIMING_100NS		(0x2 << 2)
+	#define IO_MODE_TIMING_80NS		(0x3 << 2)
+
+	#define TRUEIDE_PIO_TIMING_MASK		(0x7 << 4)
+	#define TRUEIDE_PIO_TIMING_SHIFT	4
+
+	#define TRUEIDE_MWORD_DMA_TIMING_MASK	(0x7 << 7)
+	#define TRUEIDE_MWORD_DMA_TIMING_SHIFT	7
+
+	#define ULTRA_DMA_TIMING_MASK		(0x7 << 10)
+	#define ULTRA_DMA_TIMING_SHIFT		10
+/* CF Transfer Address */
+#define XFER_ADDR		0x014
+	#define XFER_ADDR_MASK			(0x7FF)
+	#define MAX_XFER_COUNT			0x20000u
+/* Transfer Control */
+#define XFER_CTR		0x01C
+	#define XFER_COUNT_MASK			(0x3FFFF)
+	#define ADDR_INC_DISABLE		(1 << 24)
+	#define XFER_WIDTH_MASK			(1 << 25)
+	#define XFER_WIDTH_8B			(0)
+	#define XFER_WIDTH_16B			(1 << 25)
+
+	#define MEM_TYPE_MASK			(1 << 26)
+	#define MEM_TYPE_COMMON			(0)
+	#define MEM_TYPE_ATTRIBUTE		(1 << 26)
+
+	#define MEM_IO_XFER_MASK		(1 << 27)
+	#define MEM_XFER			(0)
+	#define IO_XFER				(1 << 27)
+
+	#define DMA_XFER_MODE			(1 << 28)
+
+	#define AHB_BUS_NORMAL_PIO_OPRTN	(~(1 << 29))
+	#define XFER_DIR_MASK			(1 << 30)
+	#define XFER_READ			(0)
+	#define XFER_WRITE			(1 << 30)
+
+	#define XFER_START			(1 << 31)
+/* Write Data Port */
+#define WRITE_PORT		0x024
+/* Read Data Port */
+#define READ_PORT		0x028
+/* ATA Data Port */
+#define ATA_DATA_PORT		0x030
+	#define ATA_DATA_PORT_MASK		(0xFFFF)
+/* ATA Error/Features */
+#define ATA_ERR_FTR		0x034
+/* ATA Sector Count */
+#define ATA_SC			0x038
+/* ATA Sector Number */
+#define ATA_SN			0x03C
+/* ATA Cylinder Low */
+#define ATA_CL			0x040
+/* ATA Cylinder High */
+#define ATA_CH			0x044
+/* ATA Select Card/Head */
+#define ATA_SH			0x048
+/* ATA Status-Command */
+#define ATA_STS_CMD		0x04C
+/* ATA Alternate Status/Device Control */
+#define ATA_ASTS_DCTR		0x050
+/* Extended Write Data Port 0x200-0x3FC */
+#define EXT_WRITE_PORT		0x200
+/* Extended Read Data Port 0x400-0x5FC */
+#define EXT_READ_PORT		0x400
+	#define FIFO_SIZE	0x200u
+/* Global Interrupt Status */
+#define GIRQ_STS		0x800
+/* Global Interrupt Status enable */
+#define GIRQ_STS_EN		0x804
+/* Global Interrupt Signal enable */
+#define GIRQ_SGN_EN		0x808
+	#define GIRQ_CF		(1)
+	#define GIRQ_XD		(1 << 1)
+
+/* Compact Flash Controller Dev Structure */
+struct arasan_cf_dev {
+	/* pointer to ata_host structure */
+	struct ata_host *host;
+	/* clk structure, only if HAVE_CLK is defined */
+#ifdef CONFIG_HAVE_CLK
+	struct clk *clk;
+#endif
+
+	/* physical base address of controller */
+	dma_addr_t pbase;
+	/* virtual base address of controller */
+	void __iomem *vbase;
+	/* irq number*/
+	int irq;
+
+	/* status to be updated to framework regarding DMA transfer */
+	u8 dma_status;
+	/* Card is present or Not */
+	u8 card_present;
+
+	/* dma specific */
+	/* Completion for transfer complete interrupt from controller */
+	struct completion cf_completion;
+	/* Completion for DMA transfer complete. */
+	struct completion dma_completion;
+	/* Dma channel allocated */
+	struct dma_chan *dma_chan;
+	/* Mask for DMA transfers */
+	dma_cap_mask_t mask;
+	/* DMA transfer work */
+	struct work_struct work;
+	/* DMA delayed finish work */
+	struct delayed_work dwork;
+	/* qc to be transferred using DMA */
+	struct ata_queued_cmd *qc;
+};
+
+static struct scsi_host_template arasan_cf_sht = {
+	ATA_BASE_SHT(DRIVER_NAME),
+	.sg_tablesize = SG_NONE,
+	.dma_boundary = 0xFFFFFFFFUL,
+};
+
+static void cf_dumpregs(struct arasan_cf_dev *acdev)
+{
+	struct device *dev = acdev->host->dev;
+
+	dev_dbg(dev, ": =========== REGISTER DUMP ===========");
+	dev_dbg(dev, ": CFI_STS: %x", readl(acdev->vbase + CFI_STS));
+	dev_dbg(dev, ": IRQ_STS: %x", readl(acdev->vbase + IRQ_STS));
+	dev_dbg(dev, ": IRQ_EN: %x", readl(acdev->vbase + IRQ_EN));
+	dev_dbg(dev, ": OP_MODE: %x", readl(acdev->vbase + OP_MODE));
+	dev_dbg(dev, ": CLK_CFG: %x", readl(acdev->vbase + CLK_CFG));
+	dev_dbg(dev, ": TM_CFG: %x", readl(acdev->vbase + TM_CFG));
+	dev_dbg(dev, ": XFER_CTR: %x", readl(acdev->vbase + XFER_CTR));
+	dev_dbg(dev, ": GIRQ_STS: %x", readl(acdev->vbase + GIRQ_STS));
+	dev_dbg(dev, ": GIRQ_STS_EN: %x", readl(acdev->vbase + GIRQ_STS_EN));
+	dev_dbg(dev, ": GIRQ_SGN_EN: %x", readl(acdev->vbase + GIRQ_SGN_EN));
+	dev_dbg(dev, ": =====================================");
+}
+
+/* Enable/Disable global interrupts shared between CF and XD ctrlr. */
+static void cf_ginterrupt_enable(struct arasan_cf_dev *acdev, bool enable)
+{
+	/* enable should be 0 or 1 */
+	writel(enable, acdev->vbase + GIRQ_STS_EN);
+	writel(enable, acdev->vbase + GIRQ_SGN_EN);
+}
+
+/* Enable/Disable CF interrupts */
+static inline void
+cf_interrupt_enable(struct arasan_cf_dev *acdev, u32 mask, bool enable)
+{
+	u32 val = readl(acdev->vbase + IRQ_EN);
+	/* clear & enable/disable irqs */
+	if (enable) {
+		writel(mask, acdev->vbase + IRQ_STS);
+		writel(val | mask, acdev->vbase + IRQ_EN);
+	} else
+		writel(val & ~mask, acdev->vbase + IRQ_EN);
+}
+
+static inline void cf_card_reset(struct arasan_cf_dev *acdev)
+{
+	u32 val = readl(acdev->vbase + OP_MODE);
+
+	writel(val | CARD_RESET, acdev->vbase + OP_MODE);
+	udelay(200);
+	writel(val & ~CARD_RESET, acdev->vbase + OP_MODE);
+}
+
+static inline void cf_ctrl_reset(struct arasan_cf_dev *acdev)
+{
+	writel(readl(acdev->vbase + OP_MODE) & ~CFHOST_ENB,
+			acdev->vbase + OP_MODE);
+	writel(readl(acdev->vbase + OP_MODE) | CFHOST_ENB,
+			acdev->vbase + OP_MODE);
+}
+
+static void cf_card_detect(struct arasan_cf_dev *acdev, bool hotplugged)
+{
+	struct ata_port *ap = acdev->host->ports[0];
+	struct ata_eh_info *ehi = &ap->link.eh_info;
+	u32 val = readl(acdev->vbase + CFI_STS);
+
+	/* Both CD1 & CD2 should be low if card inserted completely */
+	if (!(val & (CARD_DETECT1 | CARD_DETECT2))) {
+		if (acdev->card_present)
+			return;
+		acdev->card_present = 1;
+		cf_card_reset(acdev);
+	} else {
+		if (!acdev->card_present)
+			return;
+		acdev->card_present = 0;
+	}
+
+	if (hotplugged) {
+		ata_ehi_hotplugged(ehi);
+		ata_port_freeze(ap);
+	}
+}
+
+static int cf_init(struct arasan_cf_dev *acdev)
+{
+	struct arasan_cf_pdata *pdata = dev_get_platdata(acdev->host->dev);
+	unsigned long flags;
+	int ret = 0;
+
+#ifdef CONFIG_HAVE_CLK
+	ret = clk_enable(acdev->clk);
+	if (ret) {
+		dev_dbg(acdev->host->dev, "clock enable failed");
+		return ret;
+	}
+#endif
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	/* configure CF interface clock */
+	writel((pdata->cf_if_clk <= CF_IF_CLK_200M) ? pdata->cf_if_clk :
+			CF_IF_CLK_166M, acdev->vbase + CLK_CFG);
+
+	writel(TRUE_IDE_MODE | CFHOST_ENB, acdev->vbase + OP_MODE);
+	cf_interrupt_enable(acdev, CARD_DETECT_IRQ, 1);
+	cf_ginterrupt_enable(acdev, 1);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+
+	return ret;
+}
+
+static void cf_exit(struct arasan_cf_dev *acdev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	cf_ginterrupt_enable(acdev, 0);
+	cf_interrupt_enable(acdev, TRUE_IDE_IRQS, 0);
+	cf_card_reset(acdev);
+	writel(readl(acdev->vbase + OP_MODE) & ~CFHOST_ENB,
+			acdev->vbase + OP_MODE);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+#ifdef CONFIG_HAVE_CLK
+	clk_disable(acdev->clk);
+#endif
+}
+
+static void dma_callback(void *dev)
+{
+	struct arasan_cf_dev *acdev = (struct arasan_cf_dev *) dev;
+
+	complete(&acdev->dma_completion);
+}
+
+static bool filter(struct dma_chan *chan, void *slave)
+{
+	return true;
+}
+
+static inline void dma_complete(struct arasan_cf_dev *acdev)
+{
+	struct ata_queued_cmd *qc = acdev->qc;
+	unsigned long flags;
+
+	acdev->qc = NULL;
+	ata_sff_interrupt(acdev->irq, acdev->host);
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	if (unlikely(qc->err_mask) && ata_is_dma(qc->tf.protocol))
+		ata_ehi_push_desc(&qc->ap->link.eh_info, "DMA Failed: Timeout");
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+}
+
+static inline int wait4buf(struct arasan_cf_dev *acdev)
+{
+	if (!wait_for_completion_timeout(&acdev->cf_completion, TIMEOUT)) {
+		u32 rw = acdev->qc->tf.flags & ATA_TFLAG_WRITE;
+
+		dev_err(acdev->host->dev, "%s TimeOut", rw ? "write" : "read");
+		return -ETIMEDOUT;
+	}
+
+	/* Check if PIO Error interrupt has occured */
+	if (acdev->dma_status & ATA_DMA_ERR)
+		return -EAGAIN;
+
+	return 0;
+}
+
+static int
+dma_xfer(struct arasan_cf_dev *acdev, dma_addr_t src, dma_addr_t dest, u32 len)
+{
+	struct dma_async_tx_descriptor *tx;
+	struct dma_chan *chan = acdev->dma_chan;
+	dma_cookie_t cookie;
+	unsigned long flags = DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
+		DMA_COMPL_SKIP_DEST_UNMAP;
+	int ret = 0;
+
+	tx = chan->device->device_prep_dma_memcpy(chan, dest, src, len, flags);
+	if (!tx) {
+		dev_err(acdev->host->dev, "device_prep_dma_memcpy failed\n");
+		return -EAGAIN;
+	}
+
+	tx->callback = dma_callback;
+	tx->callback_param = acdev;
+	cookie = tx->tx_submit(tx);
+
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(acdev->host->dev, "dma_submit_error\n");
+		return ret;
+	}
+
+	chan->device->device_issue_pending(chan);
+
+	/* Wait for DMA to complete */
+	if (!wait_for_completion_timeout(&acdev->dma_completion, TIMEOUT)) {
+		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dev_err(acdev->host->dev, "wait_for_completion_timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	return ret;
+}
+
+static int sg_xfer(struct arasan_cf_dev *acdev, struct scatterlist *sg)
+{
+	dma_addr_t dest = 0, src = 0;
+	u32 xfer_cnt, sglen, dma_len, xfer_ctr;
+	u32 write = acdev->qc->tf.flags & ATA_TFLAG_WRITE;
+	unsigned long flags;
+	int ret = 0;
+
+	sglen = sg_dma_len(sg);
+	if (write) {
+		src = sg_dma_address(sg);
+		dest = acdev->pbase + EXT_WRITE_PORT;
+	} else {
+		dest = sg_dma_address(sg);
+		src = acdev->pbase + EXT_READ_PORT;
+	}
+
+	/*
+	 * For each sg:
+	 * MAX_XFER_COUNT data will be transferred before we get transfer
+	 * complete interrupt. Inbetween after FIFO_SIZE data
+	 * buffer available interrupt will be generated. At this time we will
+	 * fill FIFO again: max FIFO_SIZE data.
+	 */
+	while (sglen) {
+		xfer_cnt = min(sglen, MAX_XFER_COUNT);
+		spin_lock_irqsave(&acdev->host->lock, flags);
+		xfer_ctr = readl(acdev->vbase + XFER_CTR) &
+			~XFER_COUNT_MASK;
+		writel(xfer_ctr | xfer_cnt | XFER_START,
+				acdev->vbase + XFER_CTR);
+		spin_unlock_irqrestore(&acdev->host->lock, flags);
+
+		/* continue dma xfers untill current sg is completed */
+		while (xfer_cnt) {
+			/* wait for read to complete */
+			if (!write) {
+				ret = wait4buf(acdev);
+				if (ret)
+					goto fail;
+			}
+
+			/* read/write FIFO in chunk of FIFO_SIZE */
+			dma_len = min(xfer_cnt, FIFO_SIZE);
+			ret = dma_xfer(acdev, src, dest, dma_len);
+			if (ret) {
+				dev_err(acdev->host->dev, "dma failed");
+				goto fail;
+			}
+
+			if (write)
+				src += dma_len;
+			else
+				dest += dma_len;
+
+			sglen -= dma_len;
+			xfer_cnt -= dma_len;
+
+			/* wait for write to complete */
+			if (write) {
+				ret = wait4buf(acdev);
+				if (ret)
+					goto fail;
+			}
+		}
+	}
+
+fail:
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	writel(readl(acdev->vbase + XFER_CTR) & ~XFER_START,
+			acdev->vbase + XFER_CTR);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+
+	return ret;
+}
+
+/*
+ * This routine uses External DMA controller to read/write data to FIFO of CF
+ * controller. There are two xfer related interrupt supported by CF controller:
+ * - buf_avail: This interrupt is generated as soon as we have buffer of 512
+ *	bytes available for reading or empty buffer available for writing.
+ * - xfer_done: This interrupt is generated on transfer of "xfer_size" amount of
+ *	data to/from FIFO. xfer_size is programmed in XFER_CTR register.
+ *
+ * Max buffer size = FIFO_SIZE = 512 Bytes.
+ * Max xfer_size = MAX_XFER_COUNT = 256 KB.
+ */
+static void data_xfer(struct work_struct *work)
+{
+	struct arasan_cf_dev *acdev = container_of(work, struct arasan_cf_dev,
+			work);
+	struct ata_queued_cmd *qc = acdev->qc;
+	struct scatterlist *sg;
+	unsigned long flags;
+	u32 temp;
+	int ret = 0;
+
+	/* request dma channels */
+	/* dma_request_channel may sleep, so calling from process context */
+	acdev->dma_chan = dma_request_channel(acdev->mask, filter, NULL);
+	if (!acdev->dma_chan) {
+		dev_err(acdev->host->dev, "Unable to get dma_chan\n");
+		goto chan_request_fail;
+	}
+
+	for_each_sg(qc->sg, sg, qc->n_elem, temp) {
+		ret = sg_xfer(acdev, sg);
+		if (ret)
+			break;
+	}
+
+	dma_release_channel(acdev->dma_chan);
+
+	/* data xferred successfully */
+	if (!ret) {
+		u32 status;
+
+		spin_lock_irqsave(&acdev->host->lock, flags);
+		status = ioread8(qc->ap->ioaddr.altstatus_addr);
+		spin_unlock_irqrestore(&acdev->host->lock, flags);
+		if (status & (ATA_BUSY | ATA_DRQ)) {
+			ata_sff_queue_delayed_work(&acdev->dwork, 1);
+			return;
+		}
+
+		goto sff_intr;
+	}
+
+	cf_dumpregs(acdev);
+
+chan_request_fail:
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	/* error when transfering data to/from memory */
+	qc->err_mask |= AC_ERR_HOST_BUS;
+	qc->ap->hsm_task_state = HSM_ST_ERR;
+
+	cf_ctrl_reset(acdev);
+	spin_unlock_irqrestore(qc->ap->lock, flags);
+sff_intr:
+	dma_complete(acdev);
+}
+
+static void delayed_finish(struct work_struct *work)
+{
+	struct arasan_cf_dev *acdev = container_of(work, struct arasan_cf_dev,
+			dwork.work);
+	struct ata_queued_cmd *qc = acdev->qc;
+	unsigned long flags;
+	u8 status;
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	status = ioread8(qc->ap->ioaddr.altstatus_addr);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+
+	if (status & (ATA_BUSY | ATA_DRQ))
+		ata_sff_queue_delayed_work(&acdev->dwork, 1);
+	else
+		dma_complete(acdev);
+}
+
+static irqreturn_t arasan_cf_interrupt(int irq, void *dev)
+{
+	struct arasan_cf_dev *acdev = ((struct ata_host *)dev)->private_data;
+	unsigned long flags;
+	u32 irqsts;
+
+	irqsts = readl(acdev->vbase + GIRQ_STS);
+	if (!(irqsts & GIRQ_CF))
+		return IRQ_NONE;
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	irqsts = readl(acdev->vbase + IRQ_STS);
+	writel(irqsts, acdev->vbase + IRQ_STS);		/* clear irqs */
+	writel(GIRQ_CF, acdev->vbase + GIRQ_STS);	/* clear girqs */
+
+	/* handle only relevant interrupts */
+	irqsts &= ~IGNORED_IRQS;
+
+	if (irqsts & CARD_DETECT_IRQ) {
+		cf_card_detect(acdev, 1);
+		spin_unlock_irqrestore(&acdev->host->lock, flags);
+		return IRQ_HANDLED;
+	}
+
+	if (irqsts & PIO_XFER_ERR_IRQ) {
+		acdev->dma_status = ATA_DMA_ERR;
+		writel(readl(acdev->vbase + XFER_CTR) & ~XFER_START,
+				acdev->vbase + XFER_CTR);
+		spin_unlock_irqrestore(&acdev->host->lock, flags);
+		complete(&acdev->cf_completion);
+		dev_err(acdev->host->dev, "pio xfer err irq\n");
+		return IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+
+	if (irqsts & BUF_AVAIL_IRQ) {
+		complete(&acdev->cf_completion);
+		return IRQ_HANDLED;
+	}
+
+	if (irqsts & XFER_DONE_IRQ) {
+		struct ata_queued_cmd *qc = acdev->qc;
+
+		/* Send Complete only for write */
+		if (qc->tf.flags & ATA_TFLAG_WRITE)
+			complete(&acdev->cf_completion);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void arasan_cf_freeze(struct ata_port *ap)
+{
+	struct arasan_cf_dev *acdev = ap->host->private_data;
+
+	/* stop transfer and reset controller */
+	writel(readl(acdev->vbase + XFER_CTR) & ~XFER_START,
+			acdev->vbase + XFER_CTR);
+	cf_ctrl_reset(acdev);
+	acdev->dma_status = ATA_DMA_ERR;
+
+	ata_sff_dma_pause(ap);
+	ata_sff_freeze(ap);
+}
+
+void arasan_cf_error_handler(struct ata_port *ap)
+{
+	struct arasan_cf_dev *acdev = ap->host->private_data;
+
+	/*
+	 * DMA transfers using an external DMA controller may be scheduled.
+	 * Abort them before handling error. Refer data_xfer() for further
+	 * details.
+	 */
+	cancel_work_sync(&acdev->work);
+	cancel_delayed_work_sync(&acdev->dwork);
+	return ata_sff_error_handler(ap);
+}
+
+static void arasan_cf_dma_start(struct arasan_cf_dev *acdev)
+{
+	u32 xfer_ctr = readl(acdev->vbase + XFER_CTR) & ~XFER_DIR_MASK;
+	u32 write = acdev->qc->tf.flags & ATA_TFLAG_WRITE;
+
+	xfer_ctr |= write ? XFER_WRITE : XFER_READ;
+	writel(xfer_ctr, acdev->vbase + XFER_CTR);
+
+	acdev->qc->ap->ops->sff_exec_command(acdev->qc->ap, &acdev->qc->tf);
+	ata_sff_queue_work(&acdev->work);
+}
+
+unsigned int arasan_cf_qc_issue(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct arasan_cf_dev *acdev = ap->host->private_data;
+
+	/* defer PIO handling to sff_qc_issue */
+	if (!ata_is_dma(qc->tf.protocol))
+		return ata_sff_qc_issue(qc);
+
+	/* select the device */
+	ata_wait_idle(ap);
+	ata_sff_dev_select(ap, qc->dev->devno);
+	ata_wait_idle(ap);
+
+	/* start the command */
+	switch (qc->tf.protocol) {
+	case ATA_PROT_DMA:
+		WARN_ON_ONCE(qc->tf.flags & ATA_TFLAG_POLLING);
+
+		ap->ops->sff_tf_load(ap, &qc->tf);
+		acdev->dma_status = 0;
+		acdev->qc = qc;
+		arasan_cf_dma_start(acdev);
+		ap->hsm_task_state = HSM_ST_LAST;
+		break;
+
+	default:
+		WARN_ON(1);
+		return AC_ERR_SYSTEM;
+	}
+
+	return 0;
+}
+
+static void arasan_cf_set_piomode(struct ata_port *ap, struct ata_device *adev)
+{
+	struct arasan_cf_dev *acdev = ap->host->private_data;
+	u8 pio = adev->pio_mode - XFER_PIO_0;
+	unsigned long flags;
+	u32 val;
+
+	/* Arasan ctrl supports Mode0 -> Mode6 */
+	if (pio > 6) {
+		dev_err(ap->dev, "Unknown PIO mode\n");
+		return;
+	}
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	val = readl(acdev->vbase + OP_MODE) &
+		~(ULTRA_DMA_ENB | MULTI_WORD_DMA_ENB | DRQ_BLOCK_SIZE_MASK);
+	writel(val, acdev->vbase + OP_MODE);
+	val = readl(acdev->vbase + TM_CFG) & ~TRUEIDE_PIO_TIMING_MASK;
+	val |= pio << TRUEIDE_PIO_TIMING_SHIFT;
+	writel(val, acdev->vbase + TM_CFG);
+
+	cf_interrupt_enable(acdev, BUF_AVAIL_IRQ | XFER_DONE_IRQ, 0);
+	cf_interrupt_enable(acdev, PIO_XFER_ERR_IRQ, 1);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+}
+
+static void arasan_cf_set_dmamode(struct ata_port *ap, struct ata_device *adev)
+{
+	struct arasan_cf_dev *acdev = ap->host->private_data;
+	u32 opmode, tmcfg, dma_mode = adev->dma_mode;
+	unsigned long flags;
+
+	spin_lock_irqsave(&acdev->host->lock, flags);
+	opmode = readl(acdev->vbase + OP_MODE) &
+		~(MULTI_WORD_DMA_ENB | ULTRA_DMA_ENB);
+	tmcfg = readl(acdev->vbase + TM_CFG);
+
+	if ((dma_mode >= XFER_UDMA_0) && (dma_mode <= XFER_UDMA_6)) {
+		opmode |= ULTRA_DMA_ENB;
+		tmcfg &= ~ULTRA_DMA_TIMING_MASK;
+		tmcfg |= (dma_mode - XFER_UDMA_0) << ULTRA_DMA_TIMING_SHIFT;
+	} else if ((dma_mode >= XFER_MW_DMA_0) && (dma_mode <= XFER_MW_DMA_4)) {
+		opmode |= MULTI_WORD_DMA_ENB;
+		tmcfg &= ~TRUEIDE_MWORD_DMA_TIMING_MASK;
+		tmcfg |= (dma_mode - XFER_MW_DMA_0) <<
+			TRUEIDE_MWORD_DMA_TIMING_SHIFT;
+	} else {
+		dev_err(ap->dev, "Unknown DMA mode\n");
+		spin_unlock_irqrestore(&acdev->host->lock, flags);
+		return;
+	}
+
+	writel(opmode, acdev->vbase + OP_MODE);
+	writel(tmcfg, acdev->vbase + TM_CFG);
+	writel(DMA_XFER_MODE, acdev->vbase + XFER_CTR);
+
+	cf_interrupt_enable(acdev, PIO_XFER_ERR_IRQ, 0);
+	cf_interrupt_enable(acdev, BUF_AVAIL_IRQ | XFER_DONE_IRQ, 1);
+	spin_unlock_irqrestore(&acdev->host->lock, flags);
+}
+
+static struct ata_port_operations arasan_cf_ops = {
+	.inherits = &ata_sff_port_ops,
+	.freeze = arasan_cf_freeze,
+	.error_handler = arasan_cf_error_handler,
+	.qc_issue = arasan_cf_qc_issue,
+	.set_piomode = arasan_cf_set_piomode,
+	.set_dmamode = arasan_cf_set_dmamode,
+};
+
+static int __devinit arasan_cf_probe(struct platform_device *pdev)
+{
+	struct arasan_cf_dev *acdev;
+	struct arasan_cf_pdata *pdata = dev_get_platdata(&pdev->dev);
+	struct ata_host *host;
+	struct ata_port *ap;
+	struct resource *res;
+	irq_handler_t irq_handler = NULL;
+	int ret = 0;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
+	if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
+				DRIVER_NAME)) {
+		dev_warn(&pdev->dev, "Failed to get memory region resource\n");
+		return -ENOENT;
+	}
+
+	acdev = devm_kzalloc(&pdev->dev, sizeof(*acdev), GFP_KERNEL);
+	if (!acdev) {
+		dev_warn(&pdev->dev, "kzalloc fail\n");
+		return -ENOMEM;
+	}
+
+	/* if irq is 0, support only PIO */
+	acdev->irq = platform_get_irq(pdev, 0);
+	if (acdev->irq)
+		irq_handler = arasan_cf_interrupt;
+	else
+		pdata->quirk |= CF_BROKEN_MWDMA | CF_BROKEN_UDMA;
+
+	acdev->pbase = res->start;
+	acdev->vbase = devm_ioremap_nocache(&pdev->dev, res->start,
+			resource_size(res));
+	if (!acdev->vbase) {
+		dev_warn(&pdev->dev, "ioremap fail\n");
+		return -ENOMEM;
+	}
+
+#ifdef CONFIG_HAVE_CLK
+	acdev->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(acdev->clk)) {
+		dev_warn(&pdev->dev, "Clock not found\n");
+		return PTR_ERR(acdev->clk);
+	}
+#endif
+
+	/* allocate host */
+	host = ata_host_alloc(&pdev->dev, 1);
+	if (!host) {
+		ret = -ENOMEM;
+		dev_warn(&pdev->dev, "alloc host fail\n");
+		goto free_clk;
+	}
+
+	ap = host->ports[0];
+	host->private_data = acdev;
+	acdev->host = host;
+	ap->ops = &arasan_cf_ops;
+	ap->pio_mask = ATA_PIO6;
+	ap->mwdma_mask = ATA_MWDMA4;
+	ap->udma_mask = ATA_UDMA6;
+
+	init_completion(&acdev->cf_completion);
+	init_completion(&acdev->dma_completion);
+	INIT_WORK(&acdev->work, data_xfer);
+	INIT_DELAYED_WORK(&acdev->dwork, delayed_finish);
+	dma_cap_set(DMA_MEMCPY, acdev->mask);
+
+	/* Handle platform specific quirks */
+	if (pdata->quirk) {
+		if (pdata->quirk & CF_BROKEN_PIO) {
+			ap->ops->set_piomode = NULL;
+			ap->pio_mask = 0;
+		}
+		if (pdata->quirk & CF_BROKEN_MWDMA)
+			ap->mwdma_mask = 0;
+		if (pdata->quirk & CF_BROKEN_UDMA)
+			ap->udma_mask = 0;
+	}
+	ap->flags |= ATA_FLAG_PIO_POLLING | ATA_FLAG_NO_ATAPI;
+
+	ap->ioaddr.cmd_addr = acdev->vbase + ATA_DATA_PORT;
+	ap->ioaddr.data_addr = acdev->vbase + ATA_DATA_PORT;
+	ap->ioaddr.error_addr = acdev->vbase + ATA_ERR_FTR;
+	ap->ioaddr.feature_addr = acdev->vbase + ATA_ERR_FTR;
+	ap->ioaddr.nsect_addr = acdev->vbase + ATA_SC;
+	ap->ioaddr.lbal_addr = acdev->vbase + ATA_SN;
+	ap->ioaddr.lbam_addr = acdev->vbase + ATA_CL;
+	ap->ioaddr.lbah_addr = acdev->vbase + ATA_CH;
+	ap->ioaddr.device_addr = acdev->vbase + ATA_SH;
+	ap->ioaddr.status_addr = acdev->vbase + ATA_STS_CMD;
+	ap->ioaddr.command_addr = acdev->vbase + ATA_STS_CMD;
+	ap->ioaddr.altstatus_addr = acdev->vbase + ATA_ASTS_DCTR;
+	ap->ioaddr.ctl_addr = acdev->vbase + ATA_ASTS_DCTR;
+
+	ata_port_desc(ap, "phy_addr %x virt_addr %p", res->start, acdev->vbase);
+
+	ret = cf_init(acdev);
+	if (ret)
+		goto free_clk;
+
+	cf_card_detect(acdev, 0);
+
+	return ata_host_activate(host, acdev->irq, irq_handler, 0,
+			&arasan_cf_sht);
+
+free_clk:
+#ifdef CONFIG_HAVE_CLK
+	clk_put(acdev->clk);
+#endif
+	return ret;
+}
+
+static int __devexit arasan_cf_remove(struct platform_device *pdev)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	struct arasan_cf_dev *acdev = host->ports[0]->private_data;
+
+	ata_host_detach(host);
+	cf_exit(acdev);
+#ifdef CONFIG_HAVE_CLK
+	clk_put(acdev->clk);
+#endif
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int arasan_cf_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	struct arasan_cf_dev *acdev = host->ports[0]->private_data;
+
+	if (acdev->dma_chan) {
+		acdev->dma_chan->device->device_control(acdev->dma_chan,
+				DMA_TERMINATE_ALL, 0);
+		dma_release_channel(acdev->dma_chan);
+	}
+	cf_exit(acdev);
+	return ata_host_suspend(host, PMSG_SUSPEND);
+}
+
+static int arasan_cf_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+	struct arasan_cf_dev *acdev = host->ports[0]->private_data;
+
+	cf_init(acdev);
+	ata_host_resume(host);
+
+	return 0;
+}
+
+static const struct dev_pm_ops arasan_cf_pm_ops = {
+	.suspend	= arasan_cf_suspend,
+	.resume		= arasan_cf_resume,
+};
+#endif
+
+static struct platform_driver arasan_cf_driver = {
+	.probe		= arasan_cf_probe,
+	.remove		= __devexit_p(arasan_cf_remove),
+	.driver		= {
+		.name	= DRIVER_NAME,
+		.owner	= THIS_MODULE,
+#ifdef CONFIG_PM
+		.pm		= &arasan_cf_pm_ops,
+#endif
+	},
+};
+
+static int __init arasan_cf_init(void)
+{
+	return platform_driver_register(&arasan_cf_driver);
+}
+module_init(arasan_cf_init);
+
+static void __exit arasan_cf_exit(void)
+{
+	platform_driver_unregister(&arasan_cf_driver);
+}
+module_exit(arasan_cf_exit);
+
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@st.com>");
+MODULE_DESCRIPTION("Arasan ATA Compact Flash driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h
new file mode 100644
index 000000000000..d979fe688796
--- /dev/null
+++ b/include/linux/pata_arasan_cf_data.h
@@ -0,0 +1,47 @@
+/*
+ * include/linux/pata_arasan_cf_data.h
+ *
+ * Arasan Compact Flash host controller platform data header file
+ *
+ * Copyright (C) 2011 ST Microelectronics
+ * Viresh Kumar <viresh.kumar@st.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef _PATA_ARASAN_CF_DATA_H
+#define _PATA_ARASAN_CF_DATA_H
+
+#include <linux/platform_device.h>
+
+struct arasan_cf_pdata {
+	u8 cf_if_clk;
+	#define CF_IF_CLK_100M			(0x0)
+	#define CF_IF_CLK_75M			(0x1)
+	#define CF_IF_CLK_66M			(0x2)
+	#define CF_IF_CLK_50M			(0x3)
+	#define CF_IF_CLK_40M			(0x4)
+	#define CF_IF_CLK_33M			(0x5)
+	#define CF_IF_CLK_25M			(0x6)
+	#define CF_IF_CLK_125M			(0x7)
+	#define CF_IF_CLK_150M			(0x8)
+	#define CF_IF_CLK_166M			(0x9)
+	#define CF_IF_CLK_200M			(0xA)
+	/*
+	 * Platform specific incapabilities of CF controller is handled via
+	 * quirks
+	 */
+	u32 quirk;
+	#define CF_BROKEN_PIO			(1)
+	#define CF_BROKEN_MWDMA			(1 << 1)
+	#define CF_BROKEN_UDMA			(1 << 2)
+};
+
+static inline void
+set_arasan_cf_pdata(struct platform_device *pdev, struct arasan_cf_pdata *data)
+{
+	pdev->dev.platform_data = data;
+}
+#endif /* _PATA_ARASAN_CF_DATA_H */
-- 
cgit v1.2.3


From 60a230e4a62be6837335911b09101bd8aeb7c95a Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@st.com>
Date: Fri, 4 Mar 2011 16:39:29 +0530
Subject: ata/pata_arasan_cf: fill dma chan->private from pdata->dma_priv

Some DMA controllers (eg: drivers/dma/dw_dmac*) allow platform specific
configuration for dma transfers. User drivers need to set chan->private field
of channel with pointer to configuration data. This patch takes dma_priv data
from platform data and passes it to chan->private_data, in order to pass
platform specific configuration to DMAC controller.

Signed-off-by: Viresh Kumar <viresh.kumar@st.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
---
 drivers/ata/pata_arasan_cf.c        | 7 ++++++-
 include/linux/pata_arasan_cf_data.h | 2 ++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 8b060c44bbe1..65cee74605b4 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -210,6 +210,8 @@ struct arasan_cf_dev {
 	struct dma_chan *dma_chan;
 	/* Mask for DMA transfers */
 	dma_cap_mask_t mask;
+	/* dma channel private data */
+	void *dma_priv;
 	/* DMA transfer work */
 	struct work_struct work;
 	/* DMA delayed finish work */
@@ -356,6 +358,7 @@ static void dma_callback(void *dev)
 
 static bool filter(struct dma_chan *chan, void *slave)
 {
+	chan->private = slave;
 	return true;
 }
 
@@ -526,7 +529,8 @@ static void data_xfer(struct work_struct *work)
 
 	/* request dma channels */
 	/* dma_request_channel may sleep, so calling from process context */
-	acdev->dma_chan = dma_request_channel(acdev->mask, filter, NULL);
+	acdev->dma_chan = dma_request_channel(acdev->mask, filter,
+			acdev->dma_priv);
 	if (!acdev->dma_chan) {
 		dev_err(acdev->host->dev, "Unable to get dma_chan\n");
 		goto chan_request_fail;
@@ -853,6 +857,7 @@ static int __devinit arasan_cf_probe(struct platform_device *pdev)
 	INIT_WORK(&acdev->work, data_xfer);
 	INIT_DELAYED_WORK(&acdev->dwork, delayed_finish);
 	dma_cap_set(DMA_MEMCPY, acdev->mask);
+	acdev->dma_priv = pdata->dma_priv;
 
 	/* Handle platform specific quirks */
 	if (pdata->quirk) {
diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h
index d979fe688796..a6ee9aa898bb 100644
--- a/include/linux/pata_arasan_cf_data.h
+++ b/include/linux/pata_arasan_cf_data.h
@@ -37,6 +37,8 @@ struct arasan_cf_pdata {
 	#define CF_BROKEN_PIO			(1)
 	#define CF_BROKEN_MWDMA			(1 << 1)
 	#define CF_BROKEN_UDMA			(1 << 2)
+	/* This is platform specific data for the DMA controller */
+	void *dma_priv;
 };
 
 static inline void
-- 
cgit v1.2.3


From 6b3b9d73e08d8939aaf54f85bb47495171f49e20 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 7 Mar 2011 08:56:44 +0100
Subject: libata: Include WWN ID in inquiry VPD emulation

As per SAT-3 the WWN ID should be included in the VPD page 0x83
(device identification) emulation.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
---
 drivers/ata/libata-scsi.c | 11 +++++++++++
 include/linux/ata.h       |  7 +++++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c11675f34b93..a83419991357 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2056,6 +2056,17 @@ static unsigned int ata_scsiop_inq_83(struct ata_scsi_args *args, u8 *rbuf)
 		      ATA_ID_SERNO_LEN);
 	num += ATA_ID_SERNO_LEN;
 
+	if (ata_id_has_wwn(args->id)) {
+		/* SAT defined lu world wide name */
+		/* piv=0, assoc=lu, code_set=binary, designator=NAA */
+		rbuf[num + 0] = 1;
+		rbuf[num + 1] = 3;
+		rbuf[num + 3] = ATA_ID_WWN_LEN;
+		num += 4;
+		ata_id_string(args->id, (unsigned char *) rbuf + num,
+			      ATA_ID_WWN, ATA_ID_WWN_LEN);
+		num += ATA_ID_WWN_LEN;
+	}
 	rbuf[3] = num - 4;    /* page len (assume less than 256 bytes) */
 	return 0;
 }
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 0c4929fa34d3..198e1ea2b2eb 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -89,6 +89,7 @@ enum {
 	ATA_ID_SPG		= 98,
 	ATA_ID_LBA_CAPACITY_2	= 100,
 	ATA_ID_SECTOR_SIZE	= 106,
+	ATA_ID_WWN		= 108,
 	ATA_ID_LOGICAL_SECTOR_SIZE	= 117,	/* and 118 */
 	ATA_ID_LAST_LUN		= 126,
 	ATA_ID_DLF		= 128,
@@ -103,6 +104,7 @@ enum {
 	ATA_ID_SERNO_LEN	= 20,
 	ATA_ID_FW_REV_LEN	= 8,
 	ATA_ID_PROD_LEN		= 40,
+	ATA_ID_WWN_LEN		= 8,
 
 	ATA_PCI_CTL_OFS		= 2,
 
@@ -815,6 +817,11 @@ static inline int ata_id_has_unload(const u16 *id)
 	return 0;
 }
 
+static inline bool ata_id_has_wwn(const u16 *id)
+{
+	return (id[ATA_ID_CSF_DEFAULT] & 0xC100) == 0x4100;
+}
+
 static inline int ata_id_form_factor(const u16 *id)
 {
 	u16 val = id[168];
-- 
cgit v1.2.3


From c9c6cac0c2bdbda42e7b804838648d0bc60ddb13 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 Feb 2011 15:15:47 -0500
Subject: kill path_lookup()

all remaining callers pass LOOKUP_PARENT to it, so
flags argument can die; renamed to kern_path_parent()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/powerpc/platforms/cell/spufs/syscalls.c | 2 +-
 fs/namei.c                                   | 7 +++----
 fs/ocfs2/refcounttree.c                      | 2 +-
 include/linux/namei.h                        | 2 +-
 kernel/audit_watch.c                         | 2 +-
 net/unix/af_unix.c                           | 2 +-
 6 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 187a7d32f86a..a3d2ce54ea2e 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -70,7 +70,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 	if (!IS_ERR(tmp)) {
 		struct nameidata nd;
 
-		ret = path_lookup(tmp, LOOKUP_PARENT, &nd);
+		ret = kern_path_parent(tmp, &nd);
 		if (!ret) {
 			nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE;
 			ret = spufs_create(&nd, flags, mode, neighbor);
diff --git a/fs/namei.c b/fs/namei.c
index a4689eb2df28..1d6bc8151553 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1747,10 +1747,9 @@ static int do_path_lookup(int dfd, const char *name,
 	return retval;
 }
 
-int path_lookup(const char *name, unsigned int flags,
-			struct nameidata *nd)
+int kern_path_parent(const char *name, struct nameidata *nd)
 {
-	return do_path_lookup(AT_FDCWD, name, flags, nd);
+	return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd);
 }
 
 int kern_path(const char *name, unsigned int flags, struct path *path)
@@ -3586,7 +3585,7 @@ EXPORT_SYMBOL(page_readlink);
 EXPORT_SYMBOL(__page_symlink);
 EXPORT_SYMBOL(page_symlink);
 EXPORT_SYMBOL(page_symlink_inode_operations);
-EXPORT_SYMBOL(path_lookup);
+EXPORT_SYMBOL(kern_path_parent);
 EXPORT_SYMBOL(kern_path);
 EXPORT_SYMBOL(vfs_path_lookup);
 EXPORT_SYMBOL(inode_permission);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 19ebc5aad391..29623da133cc 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4379,7 +4379,7 @@ static int ocfs2_user_path_parent(const char __user *path,
 	if (IS_ERR(s))
 		return PTR_ERR(s);
 
-	error = path_lookup(s, LOOKUP_PARENT, nd);
+	error = kern_path_parent(s, nd);
 	if (error)
 		putname(s);
 	else
diff --git a/include/linux/namei.h b/include/linux/namei.h
index f276d4fa01fc..58ce3433d4ec 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -72,7 +72,7 @@ extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
 extern int kern_path(const char *, unsigned, struct path *);
 
-extern int path_lookup(const char *, unsigned, struct nameidata *);
+extern int kern_path_parent(const char *, struct nameidata *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct nameidata *);
 
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 20b9fe6907d0..e683869365d9 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -359,7 +359,7 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 	struct dentry *d;
 	int err;
 
-	err = path_lookup(watch->path, LOOKUP_PARENT, &nd);
+	err = kern_path_parent(watch->path, &nd);
 	if (err)
 		return err;
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index dd419d286204..d8c04a602cf1 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -850,7 +850,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		 * Get the parent directory, calculate the hash for last
 		 * component.
 		 */
-		err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
+		err = kern_path_parent(sunaddr->sun_path, &nd);
 		if (err)
 			goto out_mknod_parent;
 
-- 
cgit v1.2.3


From 16c2cd7179881d5dd87779512ca5a0d657c64f62 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 22 Feb 2011 15:50:10 -0500
Subject: untangle the "need_reval_dot" mess

instead of ad-hackery around need_reval_dot(), do the following:
set a flag (LOOKUP_JUMPED) in the beginning of path, on absolute
symlink traversal, on ".." and on procfs-style symlinks.  Clear on
normal components, leave unchanged on ".".  Non-nested callers of
link_path_walk() call handle_reval_path(), which checks that flag
is set and that fs does want the final revalidate thing, then does
->d_revalidate().  In link_path_walk() all the return_reval stuff
is gone.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 107 +++++++++++++++++++++-----------------------------
 include/linux/namei.h |   2 +
 2 files changed, 46 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 4521b5ff7c93..450b686e9682 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -613,19 +613,8 @@ do_revalidate_rcu(struct dentry *dentry, struct nameidata *nd)
 	return dentry;
 }
 
-static inline int need_reval_dot(struct dentry *dentry)
-{
-	if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
-		return 0;
-
-	if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
-		return 0;
-
-	return 1;
-}
-
 /*
- * force_reval_path - force revalidation of a dentry
+ * handle_reval_path - force revalidation of a dentry
  *
  * In some situations the path walking code will trust dentries without
  * revalidating them. This causes problems for filesystems that depend on
@@ -639,27 +628,28 @@ static inline int need_reval_dot(struct dentry *dentry)
  * invalidate the dentry. It's up to the caller to handle putting references
  * to the path if necessary.
  */
-static int
-force_reval_path(struct path *path, struct nameidata *nd)
+static inline int handle_reval_path(struct nameidata *nd)
 {
+	struct dentry *dentry = nd->path.dentry;
 	int status;
-	struct dentry *dentry = path->dentry;
 
-	/*
-	 * only check on filesystems where it's possible for the dentry to
-	 * become stale.
-	 */
-	if (!need_reval_dot(dentry))
+	if (likely(!(nd->flags & LOOKUP_JUMPED)))
+		return 0;
+
+	if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
 		return 0;
 
+	if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
+		return 0;
+
+	/* Note: we do not d_invalidate() */
 	status = d_revalidate(dentry, nd);
 	if (status > 0)
 		return 0;
 
-	if (!status) {
-		d_invalidate(dentry);
+	if (!status)
 		status = -ESTALE;
-	}
+
 	return status;
 }
 
@@ -728,6 +718,7 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
 		path_put(&nd->path);
 		nd->path = nd->root;
 		path_get(&nd->root);
+		nd->flags |= LOOKUP_JUMPED;
 	}
 	nd->inode = nd->path.dentry->d_inode;
 
@@ -779,11 +770,8 @@ __do_follow_link(const struct path *link, struct nameidata *nd, void **p)
 		error = 0;
 		if (s)
 			error = __vfs_follow_link(nd, s);
-		else if (nd->last_type == LAST_BIND) {
-			error = force_reval_path(&nd->path, nd);
-			if (error)
-				path_put(&nd->path);
-		}
+		else if (nd->last_type == LAST_BIND)
+			nd->flags |= LOOKUP_JUMPED;
 	}
 	return error;
 }
@@ -1351,7 +1339,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 	while (*name=='/')
 		name++;
 	if (!*name)
-		goto return_reval;
+		goto return_base;
 
 	if (nd->depth)
 		lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
@@ -1385,12 +1373,16 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 		type = LAST_NORM;
 		if (this.name[0] == '.') switch (this.len) {
 			case 2:
-				if (this.name[1] == '.')
+				if (this.name[1] == '.') {
 					type = LAST_DOTDOT;
+					nd->flags |= LOOKUP_JUMPED;
+				}
 				break;
 			case 1:
 				type = LAST_DOT;
 		}
+		if (likely(type == LAST_NORM))
+			nd->flags &= ~LOOKUP_JUMPED;
 
 		/* remove trailing slashes? */
 		if (!c)
@@ -1456,7 +1448,7 @@ last_component:
 				} else
 					follow_dotdot(nd);
 			}
-			goto return_reval;
+			goto return_base;
 		}
 		err = do_lookup(nd, &this, &next, &inode);
 		if (err)
@@ -1483,24 +1475,6 @@ last_component:
 lookup_parent:
 		nd->last = this;
 		nd->last_type = type;
-		if (type == LAST_NORM)
-			goto return_base;
-return_reval:
-		/*
-		 * We bypassed the ordinary revalidation routines.
-		 * We may need to check the cached dentry for staleness.
-		 */
-		if (need_reval_dot(nd->path.dentry)) {
-			if (nameidata_drop_rcu_last_maybe(nd))
-				return -ECHILD;
-			/* Note: we do not d_invalidate() */
-			err = d_revalidate(nd->path.dentry, nd);
-			if (!err)
-				err = -ESTALE;
-			if (err < 0)
-				break;
-			return 0;
-		}
 return_base:
 		if (nameidata_drop_rcu_last_maybe(nd))
 			return -ECHILD;
@@ -1523,7 +1497,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct namei
 	struct file *file;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
-	nd->flags = flags;
+	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
 	nd->root.mnt = NULL;
 	nd->file = NULL;
@@ -1630,6 +1604,9 @@ static int path_lookupat(int dfd, const char *name,
 		br_read_unlock(vfsmount_lock);
 	}
 
+	if (!retval)
+		retval = handle_reval_path(nd);
+
 	if (nd->file) {
 		fput(nd->file);
 		nd->file = NULL;
@@ -1690,7 +1667,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 
 	/* same as do_path_lookup */
 	nd->last_type = LAST_ROOT;
-	nd->flags = flags;
+	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
 
 	nd->path.dentry = dentry;
@@ -1703,6 +1680,8 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 	current->total_link_count = 0;
 
 	result = link_path_walk(name, nd);
+	if (!result)
+		result = handle_reval_path(nd);
 	if (result == -ESTALE) {
 		/* nd->path had been dropped */
 		current->total_link_count = 0;
@@ -1710,8 +1689,11 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 		nd->path.mnt = mnt;
 		nd->inode = dentry->d_inode;
 		path_get(&nd->path);
-		nd->flags |= LOOKUP_REVAL;
+		nd->flags = flags | LOOKUP_JUMPED | LOOKUP_REVAL;
+
 		result = link_path_walk(name, nd);
+		if (!result)
+			result = handle_reval_path(nd);
 	}
 	if (unlikely(!result && !audit_dummy_context() && nd->path.dentry &&
 				nd->inode))
@@ -2198,30 +2180,29 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 {
 	struct dentry *dir = nd->path.dentry;
 	struct file *filp;
-	int error = -EISDIR;
+	int error;
 
 	switch (nd->last_type) {
 	case LAST_DOTDOT:
 		follow_dotdot(nd);
 		dir = nd->path.dentry;
 	case LAST_DOT:
-		if (need_reval_dot(dir)) {
-			int status = d_revalidate(nd->path.dentry, nd);
-			if (!status)
-				status = -ESTALE;
-			if (status < 0) {
-				error = status;
-				goto exit;
-			}
-		}
 		/* fallthrough */
 	case LAST_ROOT:
+		error = handle_reval_path(nd);
+		if (error)
+			goto exit;
+		error = -EISDIR;
 		goto exit;
 	case LAST_BIND:
+		error = handle_reval_path(nd);
+		if (error)
+			goto exit;
 		audit_inode(pathname, dir);
 		goto ok;
 	}
 
+	error = -EISDIR;
 	/* trailing slashes? */
 	if (nd->last.name[nd->last.len])
 		goto exit;
@@ -2422,7 +2403,7 @@ reval:
 	/*
 	 * We have the parent and last component.
 	 */
-	nd.flags = flags;
+	nd.flags = (nd.flags & ~LOOKUP_PARENT) | flags;
 	filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
 	while (unlikely(!filp)) { /* trailing symlink */
 		struct path link = path;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 58ce3433d4ec..265378a707bd 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -63,6 +63,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_EXCL		0x0400
 #define LOOKUP_RENAME_TARGET	0x0800
 
+#define LOOKUP_JUMPED		0x1000
+
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
 #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
-- 
cgit v1.2.3


From 47c805dc2d2dff686962f5f0baa6bac2d703ba19 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 23 Feb 2011 17:44:09 -0500
Subject: switch do_filp_open() to struct open_flags

take calculation of open_flags by open(2) arguments into new helper
in fs/open.c, move filp_open() over there, have it and do_sys_open()
use that helper, switch exec.c callers of do_filp_open() to explicit
(and constant) struct open_flags.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/exec.c          | 18 +++++++----
 fs/internal.h      |  8 +++++
 fs/namei.c         | 88 ++++++------------------------------------------------
 fs/open.c          | 73 +++++++++++++++++++++++++++++++++++++++++++-
 include/linux/fs.h |  2 --
 5 files changed, 101 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index 52a447d9b6ab..ba99e1abb1aa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -115,13 +115,16 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	struct file *file;
 	char *tmp = getname(library);
 	int error = PTR_ERR(tmp);
+	static const struct open_flags uselib_flags = {
+		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
+		.intent = LOOKUP_OPEN
+	};
 
 	if (IS_ERR(tmp))
 		goto out;
 
-	file = do_filp_open(AT_FDCWD, tmp,
-				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-				MAY_READ | MAY_EXEC | MAY_OPEN);
+	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
 	putname(tmp);
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
@@ -721,10 +724,13 @@ struct file *open_exec(const char *name)
 {
 	struct file *file;
 	int err;
+	static const struct open_flags open_exec_flags = {
+		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.acc_mode = MAY_EXEC | MAY_OPEN,
+		.intent = LOOKUP_OPEN
+	};
 
-	file = do_filp_open(AT_FDCWD, name,
-				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
-				MAY_EXEC | MAY_OPEN);
+	file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
 	if (IS_ERR(file))
 		goto out;
 
diff --git a/fs/internal.h b/fs/internal.h
index 9b976b57d7fe..6fdbdf2c6047 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -106,6 +106,14 @@ extern void put_super(struct super_block *sb);
 struct nameidata;
 extern struct file *nameidata_to_filp(struct nameidata *);
 extern void release_open_intent(struct nameidata *);
+struct open_flags {
+	int open_flag;
+	int mode;
+	int acc_mode;
+	int intent;
+};
+extern struct file *do_filp_open(int dfd, const char *pathname,
+		const struct open_flags *op, int lookup_flags);
 
 /*
  * inode.c
diff --git a/fs/namei.c b/fs/namei.c
index 5e4206f45371..9c7fa946abe1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2169,13 +2169,6 @@ exit:
 	return ERR_PTR(error);
 }
 
-struct open_flags {
-	int open_flag;
-	int mode;
-	int acc_mode;
-	int intent;
-};
-
 /*
  * Handle O_CREAT case for do_filp_open
  */
@@ -2305,74 +2298,28 @@ exit:
  * open_to_namei_flags() for more details.
  */
 struct file *do_filp_open(int dfd, const char *pathname,
-		int open_flag, int mode, int acc_mode)
+		const struct open_flags *op, int flags)
 {
 	struct file *filp;
 	struct nameidata nd;
 	int error;
 	struct path path;
 	int count = 0;
-	int flag = open_to_namei_flags(open_flag);
-	int flags = 0;
-	struct open_flags op;
-
-	if (!(open_flag & O_CREAT))
-		mode = 0;
-
-	/* Must never be set by userspace */
-	open_flag &= ~FMODE_NONOTIFY;
-
-	/*
-	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
-	 * check for O_DSYNC if the need any syncing at all we enforce it's
-	 * always set instead of having to deal with possibly weird behaviour
-	 * for malicious applications setting only __O_SYNC.
-	 */
-	if (open_flag & __O_SYNC)
-		open_flag |= O_DSYNC;
-
-	op.open_flag = open_flag;
-
-	if (!acc_mode)
-		acc_mode = MAY_OPEN | ACC_MODE(open_flag);
-
-	/* O_TRUNC implies we need access checks for write permissions */
-	if (open_flag & O_TRUNC)
-		acc_mode |= MAY_WRITE;
-
-	/* Allow the LSM permission hook to distinguish append 
-	   access from general write access. */
-	if (open_flag & O_APPEND)
-		acc_mode |= MAY_APPEND;
-
-	op.acc_mode = acc_mode;
-
-	op.intent = LOOKUP_OPEN;
-	if (open_flag & O_CREAT) {
-		op.intent |= LOOKUP_CREATE;
-		if (open_flag & O_EXCL)
-			op.intent |= LOOKUP_EXCL;
-	}
-
-	if (open_flag & O_DIRECTORY)
-		flags |= LOOKUP_DIRECTORY;
-	if (!(open_flag & O_NOFOLLOW))
-		flags |= LOOKUP_FOLLOW;
 
 	filp = get_empty_filp();
 	if (!filp)
 		return ERR_PTR(-ENFILE);
 
-	filp->f_flags = open_flag;
+	filp->f_flags = op->open_flag;
 	nd.intent.open.file = filp;
-	nd.intent.open.flags = flag;
-	nd.intent.open.create_mode = mode;
+	nd.intent.open.flags = open_to_namei_flags(op->open_flag);
+	nd.intent.open.create_mode = op->mode;
 
-	if (open_flag & O_CREAT)
+	if (op->open_flag & O_CREAT)
 		goto creat;
 
 	/* !O_CREAT, simple open */
-	error = do_path_lookup(dfd, pathname, flags | op.intent, &nd);
+	error = do_path_lookup(dfd, pathname, flags | op->intent, &nd);
 	if (unlikely(error))
 		goto out_filp2;
 	error = -ELOOP;
@@ -2386,7 +2333,7 @@ struct file *do_filp_open(int dfd, const char *pathname,
 			goto out_path2;
 	}
 	audit_inode(pathname, nd.path.dentry);
-	filp = finish_open(&nd, open_flag, acc_mode);
+	filp = finish_open(&nd, op->open_flag, op->acc_mode);
 out2:
 	release_open_intent(&nd);
 	return filp;
@@ -2416,7 +2363,7 @@ reval:
 	/*
 	 * We have the parent and last component.
 	 */
-	filp = do_last(&nd, &path, &op, pathname);
+	filp = do_last(&nd, &path, op, pathname);
 	while (unlikely(!filp)) { /* trailing symlink */
 		struct path link = path;
 		struct inode *linki = link.dentry->d_inode;
@@ -2443,7 +2390,7 @@ reval:
 		if (unlikely(error))
 			filp = ERR_PTR(error);
 		else
-			filp = do_last(&nd, &path, &op, pathname);
+			filp = do_last(&nd, &path, op, pathname);
 		if (!IS_ERR(cookie) && linki->i_op->put_link)
 			linki->i_op->put_link(link.dentry, &nd, cookie);
 		path_put(&link);
@@ -2465,23 +2412,6 @@ out_filp:
 	goto out;
 }
 
-/**
- * filp_open - open file and return file pointer
- *
- * @filename:	path to open
- * @flags:	open flags as per the open(2) second argument
- * @mode:	mode for the new file if O_CREAT is set, else ignored
- *
- * This is the helper to open a file from kernelspace if you really
- * have to.  But in generally you should not do this, so please move
- * along, nothing to see here..
- */
-struct file *filp_open(const char *filename, int flags, int mode)
-{
-	return do_filp_open(AT_FDCWD, filename, flags, mode, 0);
-}
-EXPORT_SYMBOL(filp_open);
-
 /**
  * lookup_create - lookup a dentry, creating it if it doesn't exist
  * @nd: nameidata info
diff --git a/fs/open.c b/fs/open.c
index b47aab39c057..d05e18c60bae 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -890,15 +890,86 @@ void fd_install(unsigned int fd, struct file *file)
 
 EXPORT_SYMBOL(fd_install);
 
+static inline int build_open_flags(int flags, int mode, struct open_flags *op)
+{
+	int lookup_flags = 0;
+	int acc_mode;
+
+	if (!(flags & O_CREAT))
+		mode = 0;
+	op->mode = mode;
+
+	/* Must never be set by userspace */
+	flags &= ~FMODE_NONOTIFY;
+
+	/*
+	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
+	 * check for O_DSYNC if the need any syncing at all we enforce it's
+	 * always set instead of having to deal with possibly weird behaviour
+	 * for malicious applications setting only __O_SYNC.
+	 */
+	if (flags & __O_SYNC)
+		flags |= O_DSYNC;
+
+	op->open_flag = flags;
+
+	acc_mode = MAY_OPEN | ACC_MODE(flags);
+
+	/* O_TRUNC implies we need access checks for write permissions */
+	if (flags & O_TRUNC)
+		acc_mode |= MAY_WRITE;
+
+	/* Allow the LSM permission hook to distinguish append
+	   access from general write access. */
+	if (flags & O_APPEND)
+		acc_mode |= MAY_APPEND;
+
+	op->acc_mode = acc_mode;
+
+	op->intent = LOOKUP_OPEN;
+	if (flags & O_CREAT) {
+		op->intent |= LOOKUP_CREATE;
+		if (flags & O_EXCL)
+			op->intent |= LOOKUP_EXCL;
+	}
+
+	if (flags & O_DIRECTORY)
+		lookup_flags |= LOOKUP_DIRECTORY;
+	if (!(flags & O_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	return lookup_flags;
+}
+
+/**
+ * filp_open - open file and return file pointer
+ *
+ * @filename:	path to open
+ * @flags:	open flags as per the open(2) second argument
+ * @mode:	mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to.  But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *filp_open(const char *filename, int flags, int mode)
+{
+	struct open_flags op;
+	int lookup = build_open_flags(flags, mode, &op);
+	return do_filp_open(AT_FDCWD, filename, &op, lookup);
+}
+EXPORT_SYMBOL(filp_open);
+
 long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
 {
+	struct open_flags op;
+	int lookup = build_open_flags(flags, mode, &op);
 	char *tmp = getname(filename);
 	int fd = PTR_ERR(tmp);
 
 	if (!IS_ERR(tmp)) {
 		fd = get_unused_fd_flags(flags);
 		if (fd >= 0) {
-			struct file *f = do_filp_open(dfd, tmp, flags, mode, 0);
+			struct file *f = do_filp_open(dfd, tmp, &op, lookup);
 			if (IS_ERR(f)) {
 				put_unused_fd(fd);
 				fd = PTR_ERR(f);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e38b50a4b9d2..9c75714f92c1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2205,8 +2205,6 @@ extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
 extern void free_write_pipe(struct file *);
 
-extern struct file *do_filp_open(int dfd, const char *pathname,
-		int open_flag, int mode, int acc_mode);
 extern int may_open(struct path *, int, int);
 
 extern int kernel_read(struct file *, loff_t, char *, unsigned long);
-- 
cgit v1.2.3


From 70e9b3571107b88674cd55ae4bed33f76261e7d3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 5 Mar 2011 21:12:22 -0500
Subject: get rid of nd->file

Don't stash the struct file * used as starting point of walk in nameidata;
pass file ** to path_init() instead.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 15 +++++++--------
 include/linux/namei.h |  1 -
 2 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 85f6e39b4034..a260a306daf5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1498,7 +1498,8 @@ lookup_parent:
 	return err;
 }
 
-static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
+static int path_init(int dfd, const char *name, unsigned int flags,
+		     struct nameidata *nd, struct file **fp)
 {
 	int retval = 0;
 	int fput_needed;
@@ -1508,7 +1509,6 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct namei
 	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
 	nd->root.mnt = NULL;
-	nd->file = NULL;
 
 	if (*name=='/') {
 		if (flags & LOOKUP_RCU) {
@@ -1557,7 +1557,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct namei
 		nd->path = file->f_path;
 		if (flags & LOOKUP_RCU) {
 			if (fput_needed)
-				nd->file = file;
+				*fp = file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			br_read_lock(vfsmount_lock);
 			rcu_read_lock();
@@ -1580,6 +1580,7 @@ out_fail:
 static int path_lookupat(int dfd, const char *name,
 				unsigned int flags, struct nameidata *nd)
 {
+	struct file *base = NULL;
 	int retval;
 
 	/*
@@ -1596,7 +1597,7 @@ static int path_lookupat(int dfd, const char *name,
 	 * be handled by restarting a traditional ref-walk (which will always
 	 * be able to complete).
 	 */
-	retval = path_init(dfd, name, flags, nd);
+	retval = path_init(dfd, name, flags, nd, &base);
 
 	if (unlikely(retval))
 		return retval;
@@ -1614,10 +1615,8 @@ static int path_lookupat(int dfd, const char *name,
 	if (!retval)
 		retval = handle_reval_path(nd);
 
-	if (nd->file) {
-		fput(nd->file);
-		nd->file = NULL;
-	}
+	if (base)
+		fput(base);
 
 	if (nd->root.mnt) {
 		path_put(&nd->root);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 265378a707bd..72ffd62ac736 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -19,7 +19,6 @@ struct nameidata {
 	struct path	path;
 	struct qstr	last;
 	struct path	root;
-	struct file	*file;
 	struct inode	*inode; /* path.dentry.d_inode */
 	unsigned int	flags;
 	unsigned	seq;
-- 
cgit v1.2.3


From 5b6ca027d85b7438c84b78a54ccdc2e53f2909cd Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 9 Mar 2011 23:04:47 -0500
Subject: reduce vfs_path_lookup() to do_path_lookup()

New lookup flag: LOOKUP_ROOT.  nd->root is set (and held) by caller,
path_init() starts walking from that place and all pathname resolution
machinery never drops nd->root if that flag is set.  That turns
vfs_path_lookup() into a special case of do_path_lookup() *and*
gets us down to 3 callers of link_path_walk(), making it finally
feasible to rip the handling of trailing symlink out of link_path_walk().
That will not only simply the living hell out of it, but make life
much simpler for unionfs merge.  Trailing symlink handling will
become iterative, which is a good thing for stack footprint in
a lot of situations as well.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 95 +++++++++++++++++++++++----------------------------
 include/linux/namei.h |  1 +
 2 files changed, 44 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 0bebd13e5cb7..8ee7785d5642 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -401,9 +401,11 @@ static int nameidata_drop_rcu(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
 	struct dentry *dentry = nd->path.dentry;
+	int want_root = 0;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	if (nd->root.mnt) {
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		want_root = 1;
 		spin_lock(&fs->lock);
 		if (nd->root.mnt != fs->root.mnt ||
 				nd->root.dentry != fs->root.dentry)
@@ -414,7 +416,7 @@ static int nameidata_drop_rcu(struct nameidata *nd)
 		goto err;
 	BUG_ON(nd->inode != dentry->d_inode);
 	spin_unlock(&dentry->d_lock);
-	if (nd->root.mnt) {
+	if (want_root) {
 		path_get(&nd->root);
 		spin_unlock(&fs->lock);
 	}
@@ -427,7 +429,7 @@ static int nameidata_drop_rcu(struct nameidata *nd)
 err:
 	spin_unlock(&dentry->d_lock);
 err_root:
-	if (nd->root.mnt)
+	if (want_root)
 		spin_unlock(&fs->lock);
 	return -ECHILD;
 }
@@ -454,9 +456,11 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 {
 	struct fs_struct *fs = current->fs;
 	struct dentry *parent = nd->path.dentry;
+	int want_root = 0;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	if (nd->root.mnt) {
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		want_root = 1;
 		spin_lock(&fs->lock);
 		if (nd->root.mnt != fs->root.mnt ||
 				nd->root.dentry != fs->root.dentry)
@@ -476,7 +480,7 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 	parent->d_count++;
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&parent->d_lock);
-	if (nd->root.mnt) {
+	if (want_root) {
 		path_get(&nd->root);
 		spin_unlock(&fs->lock);
 	}
@@ -490,7 +494,7 @@ err:
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&parent->d_lock);
 err_root:
-	if (nd->root.mnt)
+	if (want_root)
 		spin_unlock(&fs->lock);
 	return -ECHILD;
 }
@@ -501,7 +505,8 @@ static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct d
 	if (nd->flags & LOOKUP_RCU) {
 		if (unlikely(nameidata_dentry_drop_rcu(nd, dentry))) {
 			nd->flags &= ~LOOKUP_RCU;
-			nd->root.mnt = NULL;
+			if (!(nd->flags & LOOKUP_ROOT))
+				nd->root.mnt = NULL;
 			rcu_read_unlock();
 			br_read_unlock(vfsmount_lock);
 			return -ECHILD;
@@ -525,7 +530,8 @@ static int nameidata_drop_rcu_last(struct nameidata *nd)
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 	nd->flags &= ~LOOKUP_RCU;
-	nd->root.mnt = NULL;
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
 	spin_lock(&dentry->d_lock);
 	if (!__d_rcu_to_refcount(dentry, nd->seq))
 		goto err_unlock;
@@ -1053,7 +1059,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 
 failed:
 	nd->flags &= ~LOOKUP_RCU;
-	nd->root.mnt = NULL;
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
 	rcu_read_unlock();
 	br_read_unlock(vfsmount_lock);
 	return -ECHILD;
@@ -1310,7 +1317,8 @@ static void terminate_walk(struct nameidata *nd)
 		path_put(&nd->path);
 	} else {
 		nd->flags &= ~LOOKUP_RCU;
-		nd->root.mnt = NULL;
+		if (!(nd->flags & LOOKUP_ROOT))
+			nd->root.mnt = NULL;
 		rcu_read_unlock();
 		br_read_unlock(vfsmount_lock);
 	}
@@ -1477,6 +1485,25 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
+	if (flags & LOOKUP_ROOT) {
+		struct inode *inode = nd->root.dentry->d_inode;
+		if (!inode->i_op->lookup)
+			return -ENOTDIR;
+		retval = inode_permission(inode, MAY_EXEC);
+		if (retval)
+			return retval;
+		nd->path = nd->root;
+		nd->inode = inode;
+		if (flags & LOOKUP_RCU) {
+			br_read_lock(vfsmount_lock);
+			rcu_read_lock();
+			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+		} else {
+			path_get(&nd->path);
+		}
+		return 0;
+	}
+
 	nd->root.mnt = NULL;
 
 	if (*name=='/') {
@@ -1587,7 +1614,7 @@ static int path_lookupat(int dfd, const char *name,
 	if (base)
 		fput(base);
 
-	if (nd->root.mnt) {
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
 		path_put(&nd->root);
 		nd->root.mnt = NULL;
 	}
@@ -1638,46 +1665,10 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 		    const char *name, unsigned int flags,
 		    struct nameidata *nd)
 {
-	int result;
-
-	/* same as do_path_lookup */
-	nd->last_type = LAST_ROOT;
-	nd->flags = flags | LOOKUP_JUMPED;
-	nd->depth = 0;
-
-	nd->path.dentry = dentry;
-	nd->path.mnt = mnt;
-	path_get(&nd->path);
-	nd->root = nd->path;
-	path_get(&nd->root);
-	nd->inode = nd->path.dentry->d_inode;
-
-	current->total_link_count = 0;
-
-	result = link_path_walk(name, nd);
-	if (!result)
-		result = handle_reval_path(nd);
-	if (result == -ESTALE) {
-		/* nd->path had been dropped */
-		current->total_link_count = 0;
-		nd->path.dentry = dentry;
-		nd->path.mnt = mnt;
-		nd->inode = dentry->d_inode;
-		path_get(&nd->path);
-		nd->flags = flags | LOOKUP_JUMPED | LOOKUP_REVAL;
-
-		result = link_path_walk(name, nd);
-		if (!result)
-			result = handle_reval_path(nd);
-	}
-	if (unlikely(!result && !audit_dummy_context() && nd->path.dentry &&
-				nd->inode))
-		audit_inode(name, nd->path.dentry);
-
-	path_put(&nd->root);
-	nd->root.mnt = NULL;
-
-	return result;
+	nd->root.dentry = dentry;
+	nd->root.mnt = mnt;
+	/* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */
+	return do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, nd);
 }
 
 static struct dentry *__lookup_hash(struct qstr *name,
@@ -2320,7 +2311,7 @@ static struct file *path_openat(int dfd, const char *pathname,
 		path_put(&link);
 	}
 out:
-	if (nd.root.mnt)
+	if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
 		path_put(&nd.root);
 	if (base)
 		fput(base);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 72ffd62ac736..83cd6e5cd7dc 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -63,6 +63,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_RENAME_TARGET	0x0800
 
 #define LOOKUP_JUMPED		0x1000
+#define LOOKUP_ROOT		0x2000
 
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
-- 
cgit v1.2.3


From 73d049a40fc6269189c4e2ba6792cb5dd054883c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 11 Mar 2011 12:08:24 -0500
Subject: open-style analog of vfs_path_lookup()

new function: file_open_root(dentry, mnt, name, flags) opens the file
vfs_path_lookup would arrive to.

Note that name can be empty; in that case the usual requirement that
dentry should be a directory is lifted.

open-coded equivalents switched to it, may_open() got down exactly
one caller and became static.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/um/drivers/mconsole_kern.c | 21 ++---------
 fs/internal.h                   |  2 ++
 fs/namei.c                      | 80 ++++++++++++++++++++++++++---------------
 fs/nfsctl.c                     | 21 +++--------
 fs/open.c                       | 14 ++++++++
 include/linux/fs.h              |  4 +--
 kernel/sysctl_binary.c          | 19 +---------
 7 files changed, 77 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 975613b23dcf..c70e047eed72 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -124,35 +124,18 @@ void mconsole_log(struct mc_request *req)
 #if 0
 void mconsole_proc(struct mc_request *req)
 {
-	struct nameidata nd;
 	struct vfsmount *mnt = current->nsproxy->pid_ns->proc_mnt;
 	struct file *file;
-	int n, err;
+	int n;
 	char *ptr = req->request.data, *buf;
 	mm_segment_t old_fs = get_fs();
 
 	ptr += strlen("proc");
 	ptr = skip_spaces(ptr);
 
-	err = vfs_path_lookup(mnt->mnt_root, mnt, ptr, LOOKUP_FOLLOW, &nd);
-	if (err) {
-		mconsole_reply(req, "Failed to look up file", 1, 0);
-		goto out;
-	}
-
-	err = may_open(&nd.path, MAY_READ, O_RDONLY);
-	if (result) {
-		mconsole_reply(req, "Failed to open file", 1, 0);
-		path_put(&nd.path);
-		goto out;
-	}
-
-	file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY,
-			   current_cred());
-	err = PTR_ERR(file);
+	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY);
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
-		path_put(&nd.path);
 		goto out;
 	}
 
diff --git a/fs/internal.h b/fs/internal.h
index 6fdbdf2c6047..52abc5287f50 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -114,6 +114,8 @@ struct open_flags {
 };
 extern struct file *do_filp_open(int dfd, const char *pathname,
 		const struct open_flags *op, int lookup_flags);
+extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
+		const char *, const struct open_flags *, int lookup_flags);
 
 /*
  * inode.c
diff --git a/fs/namei.c b/fs/namei.c
index 8ee7785d5642..abc8d2df121c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1487,11 +1487,13 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	nd->depth = 0;
 	if (flags & LOOKUP_ROOT) {
 		struct inode *inode = nd->root.dentry->d_inode;
-		if (!inode->i_op->lookup)
-			return -ENOTDIR;
-		retval = inode_permission(inode, MAY_EXEC);
-		if (retval)
-			return retval;
+		if (*name) {
+			if (!inode->i_op->lookup)
+				return -ENOTDIR;
+			retval = inode_permission(inode, MAY_EXEC);
+			if (retval)
+				return retval;
+		}
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
@@ -1937,7 +1939,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	return error;
 }
 
-int may_open(struct path *path, int acc_mode, int flag)
+static int may_open(struct path *path, int acc_mode, int flag)
 {
 	struct dentry *dentry = path->dentry;
 	struct inode *inode = dentry->d_inode;
@@ -2250,11 +2252,10 @@ exit:
 }
 
 static struct file *path_openat(int dfd, const char *pathname,
-		const struct open_flags *op, int flags)
+		struct nameidata *nd, const struct open_flags *op, int flags)
 {
 	struct file *base = NULL;
 	struct file *filp;
-	struct nameidata nd;
 	struct path path;
 	int count = 0;
 	int error;
@@ -2264,27 +2265,27 @@ static struct file *path_openat(int dfd, const char *pathname,
 		return ERR_PTR(-ENFILE);
 
 	filp->f_flags = op->open_flag;
-	nd.intent.open.file = filp;
-	nd.intent.open.flags = open_to_namei_flags(op->open_flag);
-	nd.intent.open.create_mode = op->mode;
+	nd->intent.open.file = filp;
+	nd->intent.open.flags = open_to_namei_flags(op->open_flag);
+	nd->intent.open.create_mode = op->mode;
 
-	error = path_init(dfd, pathname, flags | LOOKUP_PARENT, &nd, &base);
+	error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
 	if (unlikely(error))
 		goto out_filp;
 
 	current->total_link_count = 0;
-	error = link_path_walk(pathname, &nd);
+	error = link_path_walk(pathname, nd);
 	if (unlikely(error))
 		goto out_filp;
 
-	filp = do_last(&nd, &path, op, pathname);
+	filp = do_last(nd, &path, op, pathname);
 	while (unlikely(!filp)) { /* trailing symlink */
 		struct path link = path;
 		struct inode *linki = link.dentry->d_inode;
 		void *cookie;
-		if (!(nd.flags & LOOKUP_FOLLOW) || count++ == 32) {
-			path_put_conditional(&path, &nd);
-			path_put(&nd.path);
+		if (!(nd->flags & LOOKUP_FOLLOW) || count++ == 32) {
+			path_put_conditional(&path, nd);
+			path_put(&nd->path);
 			filp = ERR_PTR(-ELOOP);
 			break;
 		}
@@ -2299,23 +2300,23 @@ static struct file *path_openat(int dfd, const char *pathname,
 		 * have to putname() it when we are done. Procfs-like symlinks
 		 * just set LAST_BIND.
 		 */
-		nd.flags |= LOOKUP_PARENT;
-		nd.flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
-		error = __do_follow_link(&link, &nd, &cookie);
+		nd->flags |= LOOKUP_PARENT;
+		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+		error = __do_follow_link(&link, nd, &cookie);
 		if (unlikely(error))
 			filp = ERR_PTR(error);
 		else
-			filp = do_last(&nd, &path, op, pathname);
+			filp = do_last(nd, &path, op, pathname);
 		if (!IS_ERR(cookie) && linki->i_op->put_link)
-			linki->i_op->put_link(link.dentry, &nd, cookie);
+			linki->i_op->put_link(link.dentry, nd, cookie);
 		path_put(&link);
 	}
 out:
-	if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
-		path_put(&nd.root);
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT))
+		path_put(&nd->root);
 	if (base)
 		fput(base);
-	release_open_intent(&nd);
+	release_open_intent(nd);
 	return filp;
 
 out_filp:
@@ -2326,16 +2327,39 @@ out_filp:
 struct file *do_filp_open(int dfd, const char *pathname,
 		const struct open_flags *op, int flags)
 {
+	struct nameidata nd;
 	struct file *filp;
 
-	filp = path_openat(dfd, pathname, op, flags | LOOKUP_RCU);
+	filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU);
 	if (unlikely(filp == ERR_PTR(-ECHILD)))
-		filp = path_openat(dfd, pathname, op, flags);
+		filp = path_openat(dfd, pathname, &nd, op, flags);
 	if (unlikely(filp == ERR_PTR(-ESTALE)))
-		filp = path_openat(dfd, pathname, op, flags | LOOKUP_REVAL);
+		filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL);
 	return filp;
 }
 
+struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+		const char *name, const struct open_flags *op, int flags)
+{
+	struct nameidata nd;
+	struct file *file;
+
+	nd.root.mnt = mnt;
+	nd.root.dentry = dentry;
+
+	flags |= LOOKUP_ROOT;
+
+	if (dentry->d_inode->i_op->follow_link)
+		return ERR_PTR(-ELOOP);
+
+	file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU);
+	if (unlikely(file == ERR_PTR(-ECHILD)))
+		file = path_openat(-1, name, &nd, op, flags);
+	if (unlikely(file == ERR_PTR(-ESTALE)))
+		file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL);
+	return file;
+}
+
 /**
  * lookup_create - lookup a dentry, creating it if it doesn't exist
  * @nd: nameidata info
diff --git a/fs/nfsctl.c b/fs/nfsctl.c
index bf9cbd242ddd..124e8fcb0dd6 100644
--- a/fs/nfsctl.c
+++ b/fs/nfsctl.c
@@ -22,30 +22,17 @@
 
 static struct file *do_open(char *name, int flags)
 {
-	struct nameidata nd;
 	struct vfsmount *mnt;
-	int error;
+	struct file *file;
 
 	mnt = do_kern_mount("nfsd", 0, "nfsd", NULL);
 	if (IS_ERR(mnt))
 		return (struct file *)mnt;
 
-	error = vfs_path_lookup(mnt->mnt_root, mnt, name, 0, &nd);
-	mntput(mnt);	/* drop do_kern_mount reference */
-	if (error)
-		return ERR_PTR(error);
-
-	if (flags == O_RDWR)
-		error = may_open(&nd.path, MAY_READ|MAY_WRITE, flags);
-	else
-		error = may_open(&nd.path, MAY_WRITE, flags);
+	file = file_open_root(mnt->mnt_root, mnt, name, flags);
 
-	if (!error)
-		return dentry_open(nd.path.dentry, nd.path.mnt, flags,
-				   current_cred());
-
-	path_put(&nd.path);
-	return ERR_PTR(error);
+	mntput(mnt);	/* drop do_kern_mount reference */
+	return file;
 }
 
 static struct {
diff --git a/fs/open.c b/fs/open.c
index d05e18c60bae..48afc5c139d2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -959,6 +959,20 @@ struct file *filp_open(const char *filename, int flags, int mode)
 }
 EXPORT_SYMBOL(filp_open);
 
+struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+			    const char *filename, int flags)
+{
+	struct open_flags op;
+	int lookup = build_open_flags(flags, 0, &op);
+	if (flags & O_CREAT)
+		return ERR_PTR(-EINVAL);
+	if (!filename && (flags & O_DIRECTORY))
+		if (!dentry->d_inode->i_op->lookup)
+			return ERR_PTR(-ENOTDIR);
+	return do_file_open_root(dentry, mnt, filename, &op, lookup);
+}
+EXPORT_SYMBOL(file_open_root);
+
 long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
 {
 	struct open_flags op;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9c75714f92c1..bf5c3c896072 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1990,6 +1990,8 @@ extern int do_fallocate(struct file *file, int mode, loff_t offset,
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			int mode);
 extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+				   const char *, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
 				 const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
@@ -2205,8 +2207,6 @@ extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
 extern void free_write_pipe(struct file *);
 
-extern int may_open(struct path *, int, int);
-
 extern int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
  
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b875bedf7c9a..3b8e028b9601 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1321,13 +1321,11 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
 {
 	const struct bin_table *table = NULL;
-	struct nameidata nd;
 	struct vfsmount *mnt;
 	struct file *file;
 	ssize_t result;
 	char *pathname;
 	int flags;
-	int acc_mode;
 
 	pathname = sysctl_getname(name, nlen, &table);
 	result = PTR_ERR(pathname);
@@ -1337,28 +1335,17 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	/* How should the sysctl be accessed? */
 	if (oldval && oldlen && newval && newlen) {
 		flags = O_RDWR;
-		acc_mode = MAY_READ | MAY_WRITE;
 	} else if (newval && newlen) {
 		flags = O_WRONLY;
-		acc_mode = MAY_WRITE;
 	} else if (oldval && oldlen) {
 		flags = O_RDONLY;
-		acc_mode = MAY_READ;
 	} else {
 		result = 0;
 		goto out_putname;
 	}
 
 	mnt = current->nsproxy->pid_ns->proc_mnt;
-	result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
-	if (result)
-		goto out_putname;
-
-	result = may_open(&nd.path, acc_mode, flags);
-	if (result)
-		goto out_putpath;
-
-	file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+	file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
 	result = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_putname;
@@ -1370,10 +1357,6 @@ out_putname:
 	putname(pathname);
 out:
 	return result;
-
-out_putpath:
-	path_put(&nd.path);
-	goto out_putname;
 }
 
 
-- 
cgit v1.2.3


From c8b91accfa1059d5565443193d89572eca2f5dd6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 12 Mar 2011 10:41:39 -0500
Subject: clean statfs-like syscalls up

New helpers: user_statfs() and fd_statfs(), taking userland pathname and
descriptor resp. and filling struct kstatfs.  Syscalls of statfs family
(native, compat and foreign - osf and hpux on alpha and parisc resp.)
switched to those.  Removes some boilerplate code, simplifies cleanup
on errors...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/osf_sys.c |  36 ++-------
 arch/parisc/hpux/sys_hpux.c |  65 ++++++----------
 fs/compat.c                 |  48 +++---------
 fs/statfs.c                 | 176 ++++++++++++++++++++------------------------
 include/linux/fs.h          |   2 +
 5 files changed, 123 insertions(+), 204 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index fe698b5045e9..376f22130791 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -230,44 +230,24 @@ linux_to_osf_statfs(struct kstatfs *linux_stat, struct osf_statfs __user *osf_st
 	return copy_to_user(osf_stat, &tmp_stat, bufsiz) ? -EFAULT : 0;
 }
 
-static int
-do_osf_statfs(struct path *path, struct osf_statfs __user *buffer,
-	      unsigned long bufsiz)
+SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
+		struct osf_statfs __user *, buffer, unsigned long, bufsiz)
 {
 	struct kstatfs linux_stat;
-	int error = vfs_statfs(path, &linux_stat);
+	int error = user_statfs(pathname, &linux_stat);
 	if (!error)
 		error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
 	return error;	
 }
 
-SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname,
-		struct osf_statfs __user *, buffer, unsigned long, bufsiz)
-{
-	struct path path;
-	int retval;
-
-	retval = user_path(pathname, &path);
-	if (!retval) {
-		retval = do_osf_statfs(&path, buffer, bufsiz);
-		path_put(&path);
-	}
-	return retval;
-}
-
 SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd,
 		struct osf_statfs __user *, buffer, unsigned long, bufsiz)
 {
-	struct file *file;
-	int retval;
-
-	retval = -EBADF;
-	file = fget(fd);
-	if (file) {
-		retval = do_osf_statfs(&file->f_path, buffer, bufsiz);
-		fput(file);
-	}
-	return retval;
+	struct kstatfs linux_stat;
+	int error = fd_statfs(fd, &linux_stat);
+	if (!error)
+		error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz);
+	return error;
 }
 
 /*
diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c
index 30394081d9b6..6ab9580b0b00 100644
--- a/arch/parisc/hpux/sys_hpux.c
+++ b/arch/parisc/hpux/sys_hpux.c
@@ -185,26 +185,21 @@ struct hpux_statfs {
      int16_t f_pad;
 };
 
-static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf)
+static int do_statfs_hpux(struct kstatfs *st, struct hpux_statfs __user *p)
 {
-	struct kstatfs st;
-	int retval;
-	
-	retval = vfs_statfs(path, &st);
-	if (retval)
-		return retval;
-
-	memset(buf, 0, sizeof(*buf));
-	buf->f_type = st.f_type;
-	buf->f_bsize = st.f_bsize;
-	buf->f_blocks = st.f_blocks;
-	buf->f_bfree = st.f_bfree;
-	buf->f_bavail = st.f_bavail;
-	buf->f_files = st.f_files;
-	buf->f_ffree = st.f_ffree;
-	buf->f_fsid[0] = st.f_fsid.val[0];
-	buf->f_fsid[1] = st.f_fsid.val[1];
-
+	struct hpux_statfs buf;
+	memset(&buf, 0, sizeof(buf));
+	buf.f_type = st->f_type;
+	buf.f_bsize = st->f_bsize;
+	buf.f_blocks = st->f_blocks;
+	buf.f_bfree = st->f_bfree;
+	buf.f_bavail = st->f_bavail;
+	buf.f_files = st->f_files;
+	buf.f_ffree = st->f_ffree;
+	buf.f_fsid[0] = st->f_fsid.val[0];
+	buf.f_fsid[1] = st->f_fsid.val[1];
+	if (copy_to_user(p, &buf, sizeof(buf)))
+		return -EFAULT;
 	return 0;
 }
 
@@ -212,35 +207,19 @@ static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf)
 asmlinkage long hpux_statfs(const char __user *pathname,
 						struct hpux_statfs __user *buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct hpux_statfs tmp;
-		error = do_statfs_hpux(&path, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
+	struct kstatfs st;
+	int error = user_statfs(pathname, &st);
+	if (!error)
+		error = do_statfs_hpux(&st, buf);
 	return error;
 }
 
 asmlinkage long hpux_fstatfs(unsigned int fd, struct hpux_statfs __user * buf)
 {
-	struct file *file;
-	struct hpux_statfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = do_statfs_hpux(&file->f_path, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
- out:
+	struct kstatfs st;
+	int error = fd_statfs(fd, &st);
+	if (!error)
+		error = do_statfs_hpux(&st, buf);
 	return error;
 }
 
diff --git a/fs/compat.c b/fs/compat.c
index 691c3fd8ce1d..a071775f3bb3 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -262,35 +262,19 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
  */
 asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct kstatfs tmp;
-		error = vfs_statfs(&path, &tmp);
-		if (!error)
-			error = put_compat_statfs(buf, &tmp);
-		path_put(&path);
-	}
+	struct kstatfs tmp;
+	int error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
 	return error;
 }
 
 asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf)
 {
-	struct file * file;
 	struct kstatfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs(&file->f_path, &tmp);
+	int error = fd_statfs(fd, &tmp);
 	if (!error)
 		error = put_compat_statfs(buf, &tmp);
-	fput(file);
-out:
 	return error;
 }
 
@@ -329,41 +313,29 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
 
 asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-	struct path path;
+	struct kstatfs tmp;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct kstatfs tmp;
-		error = vfs_statfs(&path, &tmp);
-		if (!error)
-			error = put_compat_statfs64(buf, &tmp);
-		path_put(&path);
-	}
+	error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
 	return error;
 }
 
 asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-	struct file * file;
 	struct kstatfs tmp;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = vfs_statfs(&file->f_path, &tmp);
+	error = fd_statfs(fd, &tmp);
 	if (!error)
 		error = put_compat_statfs64(buf, &tmp);
-	fput(file);
-out:
 	return error;
 }
 
diff --git a/fs/statfs.c b/fs/statfs.c
index 30ea8c8a996b..8244924dec55 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -73,149 +73,135 @@ int vfs_statfs(struct path *path, struct kstatfs *buf)
 }
 EXPORT_SYMBOL(vfs_statfs);
 
-static int do_statfs_native(struct path *path, struct statfs *buf)
+int user_statfs(const char __user *pathname, struct kstatfs *st)
 {
-	struct kstatfs st;
-	int retval;
+	struct path path;
+	int error = user_path(pathname, &path);
+	if (!error) {
+		error = vfs_statfs(&path, st);
+		path_put(&path);
+	}
+	return error;
+}
 
-	retval = vfs_statfs(path, &st);
-	if (retval)
-		return retval;
+int fd_statfs(int fd, struct kstatfs *st)
+{
+	struct file *file = fget(fd);
+	int error = -EBADF;
+	if (file) {
+		error = vfs_statfs(&file->f_path, st);
+		fput(file);
+	}
+	return error;
+}
 
-	if (sizeof(*buf) == sizeof(st))
-		memcpy(buf, &st, sizeof(st));
+static int do_statfs_native(struct kstatfs *st, struct statfs __user *p)
+{
+	struct statfs buf;
+
+	if (sizeof(buf) == sizeof(*st))
+		memcpy(&buf, st, sizeof(*st));
 	else {
-		if (sizeof buf->f_blocks == 4) {
-			if ((st.f_blocks | st.f_bfree | st.f_bavail |
-			     st.f_bsize | st.f_frsize) &
+		if (sizeof buf.f_blocks == 4) {
+			if ((st->f_blocks | st->f_bfree | st->f_bavail |
+			     st->f_bsize | st->f_frsize) &
 			    0xffffffff00000000ULL)
 				return -EOVERFLOW;
 			/*
 			 * f_files and f_ffree may be -1; it's okay to stuff
 			 * that into 32 bits
 			 */
-			if (st.f_files != -1 &&
-			    (st.f_files & 0xffffffff00000000ULL))
+			if (st->f_files != -1 &&
+			    (st->f_files & 0xffffffff00000000ULL))
 				return -EOVERFLOW;
-			if (st.f_ffree != -1 &&
-			    (st.f_ffree & 0xffffffff00000000ULL))
+			if (st->f_ffree != -1 &&
+			    (st->f_ffree & 0xffffffff00000000ULL))
 				return -EOVERFLOW;
 		}
 
-		buf->f_type = st.f_type;
-		buf->f_bsize = st.f_bsize;
-		buf->f_blocks = st.f_blocks;
-		buf->f_bfree = st.f_bfree;
-		buf->f_bavail = st.f_bavail;
-		buf->f_files = st.f_files;
-		buf->f_ffree = st.f_ffree;
-		buf->f_fsid = st.f_fsid;
-		buf->f_namelen = st.f_namelen;
-		buf->f_frsize = st.f_frsize;
-		buf->f_flags = st.f_flags;
-		memset(buf->f_spare, 0, sizeof(buf->f_spare));
+		buf.f_type = st->f_type;
+		buf.f_bsize = st->f_bsize;
+		buf.f_blocks = st->f_blocks;
+		buf.f_bfree = st->f_bfree;
+		buf.f_bavail = st->f_bavail;
+		buf.f_files = st->f_files;
+		buf.f_ffree = st->f_ffree;
+		buf.f_fsid = st->f_fsid;
+		buf.f_namelen = st->f_namelen;
+		buf.f_frsize = st->f_frsize;
+		buf.f_flags = st->f_flags;
+		memset(buf.f_spare, 0, sizeof(buf.f_spare));
 	}
+	if (copy_to_user(p, &buf, sizeof(buf)))
+		return -EFAULT;
 	return 0;
 }
 
-static int do_statfs64(struct path *path, struct statfs64 *buf)
+static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p)
 {
-	struct kstatfs st;
-	int retval;
-
-	retval = vfs_statfs(path, &st);
-	if (retval)
-		return retval;
-
-	if (sizeof(*buf) == sizeof(st))
-		memcpy(buf, &st, sizeof(st));
+	struct statfs64 buf;
+	if (sizeof(buf) == sizeof(*st))
+		memcpy(&buf, st, sizeof(*st));
 	else {
-		buf->f_type = st.f_type;
-		buf->f_bsize = st.f_bsize;
-		buf->f_blocks = st.f_blocks;
-		buf->f_bfree = st.f_bfree;
-		buf->f_bavail = st.f_bavail;
-		buf->f_files = st.f_files;
-		buf->f_ffree = st.f_ffree;
-		buf->f_fsid = st.f_fsid;
-		buf->f_namelen = st.f_namelen;
-		buf->f_frsize = st.f_frsize;
-		buf->f_flags = st.f_flags;
-		memset(buf->f_spare, 0, sizeof(buf->f_spare));
+		buf.f_type = st->f_type;
+		buf.f_bsize = st->f_bsize;
+		buf.f_blocks = st->f_blocks;
+		buf.f_bfree = st->f_bfree;
+		buf.f_bavail = st->f_bavail;
+		buf.f_files = st->f_files;
+		buf.f_ffree = st->f_ffree;
+		buf.f_fsid = st->f_fsid;
+		buf.f_namelen = st->f_namelen;
+		buf.f_frsize = st->f_frsize;
+		buf.f_flags = st->f_flags;
+		memset(buf.f_spare, 0, sizeof(buf.f_spare));
 	}
+	if (copy_to_user(p, &buf, sizeof(buf)))
+		return -EFAULT;
 	return 0;
 }
 
 SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf)
 {
-	struct path path;
-	int error;
-
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct statfs tmp;
-		error = do_statfs_native(&path, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
+	struct kstatfs st;
+	int error = user_statfs(pathname, &st);
+	if (!error)
+		error = do_statfs_native(&st, buf);
 	return error;
 }
 
 SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf)
 {
-	struct path path;
-	long error;
-
+	struct kstatfs st;
+	int error;
 	if (sz != sizeof(*buf))
 		return -EINVAL;
-	error = user_path(pathname, &path);
-	if (!error) {
-		struct statfs64 tmp;
-		error = do_statfs64(&path, &tmp);
-		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-			error = -EFAULT;
-		path_put(&path);
-	}
+	error = user_statfs(pathname, &st);
+	if (!error)
+		error = do_statfs64(&st, buf);
 	return error;
 }
 
 SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf)
 {
-	struct file *file;
-	struct statfs tmp;
-	int error;
-
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = do_statfs_native(&file->f_path, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
-out:
+	struct kstatfs st;
+	int error = fd_statfs(fd, &st);
+	if (!error)
+		error = do_statfs_native(&st, buf);
 	return error;
 }
 
 SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf)
 {
-	struct file *file;
-	struct statfs64 tmp;
+	struct kstatfs st;
 	int error;
 
 	if (sz != sizeof(*buf))
 		return -EINVAL;
 
-	error = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	error = do_statfs64(&file->f_path, &tmp);
-	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
-		error = -EFAULT;
-	fput(file);
-out:
+	error = fd_statfs(fd, &st);
+	if (!error)
+		error = do_statfs64(&st, buf);
 	return error;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bf5c3c896072..b7178b05cf3a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1874,6 +1874,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
 			  struct vfsmount *);
 extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, struct kstatfs *);
 extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
-- 
cgit v1.2.3


From 5fe0c2378884e68beb532f5890cc0e3539ac747b Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sat, 29 Jan 2011 18:43:25 +0530
Subject: exportfs: Return the minimum required handle size

The exportfs encode handle function should return the minimum required
handle size. This helps user to find out the handle size by passing 0
handle size in the first step and then redoing to the call again with
the returned handle size value.

Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/btrfs/export.c             | 8 ++++++--
 fs/exportfs/expfs.c           | 9 +++++++--
 fs/fat/inode.c                | 4 +++-
 fs/fuse/inode.c               | 4 +++-
 fs/gfs2/export.c              | 8 ++++++--
 fs/isofs/export.c             | 8 ++++++--
 fs/ocfs2/export.c             | 8 ++++++--
 fs/reiserfs/inode.c           | 7 ++++++-
 fs/udf/namei.c                | 7 ++++++-
 fs/xfs/linux-2.6/xfs_export.c | 4 +++-
 include/linux/exportfs.h      | 6 ++++--
 mm/shmem.c                    | 4 +++-
 12 files changed, 59 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index ff27d7a477b2..b4ffad859adb 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -21,9 +21,13 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	int len = *max_len;
 	int type;
 
-	if ((len < BTRFS_FID_SIZE_NON_CONNECTABLE) ||
-	    (connectable && len < BTRFS_FID_SIZE_CONNECTABLE))
+	if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
+		*max_len = BTRFS_FID_SIZE_CONNECTABLE;
 		return 255;
+	} else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) {
+		*max_len = BTRFS_FID_SIZE_NON_CONNECTABLE;
+		return 255;
+	}
 
 	len  = BTRFS_FID_SIZE_NON_CONNECTABLE;
 	type = FILEID_BTRFS_WITHOUT_PARENT;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 4b6825740dd5..cfe55731b6dc 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -320,9 +320,14 @@ static int export_encode_fh(struct dentry *dentry, struct fid *fid,
 	struct inode * inode = dentry->d_inode;
 	int len = *max_len;
 	int type = FILEID_INO32_GEN;
-	
-	if (len < 2 || (connectable && len < 4))
+
+	if (connectable && (len < 4)) {
+		*max_len = 4;
+		return 255;
+	} else if (len < 2) {
+		*max_len = 2;
 		return 255;
+	}
 
 	len = 2;
 	fid->i32.ino = inode->i_ino;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 86753fe10bd1..0e277ec4b612 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -757,8 +757,10 @@ fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable)
 	struct inode *inode =  de->d_inode;
 	u32 ipos_h, ipos_m, ipos_l;
 
-	if (len < 5)
+	if (len < 5) {
+		*lenp = 5;
 		return 255; /* no room */
+	}
 
 	ipos_h = MSDOS_I(inode)->i_pos >> 8;
 	ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 9e3f68cc1bd1..051b1a084528 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -637,8 +637,10 @@ static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
 	u64 nodeid;
 	u32 generation;
 
-	if (*max_len < len)
+	if (*max_len < len) {
+		*max_len = len;
 		return  255;
+	}
 
 	nodeid = get_fuse_inode(inode)->nodeid;
 	generation = inode->i_generation;
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 9023db8184f9..b5a5e60df0d5 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -36,9 +36,13 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
 	struct super_block *sb = inode->i_sb;
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	if (*len < GFS2_SMALL_FH_SIZE ||
-	    (connectable && *len < GFS2_LARGE_FH_SIZE))
+	if (connectable && (*len < GFS2_LARGE_FH_SIZE)) {
+		*len = GFS2_LARGE_FH_SIZE;
 		return 255;
+	} else if (*len < GFS2_SMALL_FH_SIZE) {
+		*len = GFS2_SMALL_FH_SIZE;
+		return 255;
+	}
 
 	fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
 	fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index ed752cb38474..dd4687ff30d0 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -124,9 +124,13 @@ isofs_export_encode_fh(struct dentry *dentry,
 	 * offset of the inode and the upper 16 bits of fh32[1] to
 	 * hold the offset of the parent.
 	 */
-
-	if (len < 3 || (connectable && len < 5))
+	if (connectable && (len < 5)) {
+		*max_len = 5;
+		return 255;
+	} else if (len < 3) {
+		*max_len = 3;
 		return 255;
+	}
 
 	len = 3;
 	fh32[0] = ei->i_iget5_block;
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 5dbc3062b4fd..254652a9b542 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -197,8 +197,12 @@ static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len,
 		   dentry->d_name.len, dentry->d_name.name,
 		   fh, len, connectable);
 
-	if (len < 3 || (connectable && len < 6)) {
-		mlog(ML_ERROR, "fh buffer is too small for encoding\n");
+	if (connectable && (len < 6)) {
+		*max_len = 6;
+		type = 255;
+		goto bail;
+	} else if (len < 3) {
+		*max_len = 3;
 		type = 255;
 		goto bail;
 	}
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 0bae036831e2..1bba24bad820 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1593,8 +1593,13 @@ int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp,
 	struct inode *inode = dentry->d_inode;
 	int maxlen = *lenp;
 
-	if (maxlen < 3)
+	if (need_parent && (maxlen < 5)) {
+		*lenp = 5;
 		return 255;
+	} else if (maxlen < 3) {
+		*lenp = 3;
+		return 255;
+	}
 
 	data[0] = inode->i_ino;
 	data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index b7c338d5e9df..f1dce848ef96 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1286,8 +1286,13 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp,
 	struct fid *fid = (struct fid *)fh;
 	int type = FILEID_UDF_WITHOUT_PARENT;
 
-	if (len < 3 || (connectable && len < 5))
+	if (connectable && (len < 5)) {
+		*lenp = 5;
+		return 255;
+	} else if (len < 3) {
+		*lenp = 3;
 		return 255;
+	}
 
 	*lenp = 3;
 	fid->udf.block = location.logicalBlockNum;
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index fc0114da7fdd..f4f878fc0083 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -89,8 +89,10 @@ xfs_fs_encode_fh(
 	 * seven combinations work.  The real answer is "don't use v2".
 	 */
 	len = xfs_fileid_length(fileid_type);
-	if (*max_len < len)
+	if (*max_len < len) {
+		*max_len = len;
 		return 255;
+	}
 	*max_len = len;
 
 	switch (fileid_type) {
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 28028988c862..65afdfd31b7b 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -121,8 +121,10 @@ struct fid {
  *    set, the encode_fh() should store sufficient information so that a good
  *    attempt can be made to find not only the file but also it's place in the
  *    filesystem.   This typically means storing a reference to de->d_parent in
- *    the filehandle fragment.  encode_fh() should return the number of bytes
- *    stored or a negative error code such as %-ENOSPC
+ *    the filehandle fragment.  encode_fh() should return the fileid_type on
+ *    success and on error returns 255 (if the space needed to encode fh is
+ *    greater than @max_len*4 bytes). On error @max_len contains the minimum
+ *    size(in 4 byte unit) needed to encode the file handle.
  *
  * fh_to_dentry:
  *    @fh_to_dentry is given a &struct super_block (@sb) and a file handle
diff --git a/mm/shmem.c b/mm/shmem.c
index 5ee67c990602..3437b65d6d6e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2144,8 +2144,10 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
 {
 	struct inode *inode = dentry->d_inode;
 
-	if (*len < 3)
+	if (*len < 3) {
+		*len = 3;
 		return 255;
+	}
 
 	if (inode_unhashed(inode)) {
 		/* Unfortunately insert_inode_hash is not idempotent,
-- 
cgit v1.2.3


From 4fc756bd9dbf6b84fbf751e3bf495277849c5db7 Mon Sep 17 00:00:00 2001
From: Mike Waychison <mikew@google.com>
Date: Fri, 11 Mar 2011 17:43:27 -0800
Subject: efivars: Expose efivars functionality to external drivers.

Signed-off-by: Mike Waychison <mikew@google.com>
Cc: Matt Domsch <Matt_Domsch@dell.com>,
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/firmware/efivars.c | 34 +++++++---------------------------
 include/linux/efi.h        | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index b10b7d7bd7de..ff0c373e3bbf 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -89,28 +89,6 @@ MODULE_DESCRIPTION("sysfs interface to EFI Variables");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(EFIVARS_VERSION);
 
-struct efivar_operations {
-	efi_get_variable_t *get_variable;
-	efi_get_next_variable_t *get_next_variable;
-	efi_set_variable_t *set_variable;
-};
-
-struct efivars {
-	/*
-	 * ->lock protects two things:
-	 * 1) ->list - adds, removals, reads, writes
-	 * 2) ops.[gs]et_variable() calls.
-	 * It must not be held when creating sysfs entries or calling kmalloc.
-	 * ops.get_next_variable() is only called from register_efivars(),
-	 * which is protected by the BKL, so that path is safe.
-	 */
-	spinlock_t lock;
-	struct list_head list;
-	struct kset *kset;
-	struct bin_attribute *new_var, *del_var;
-	const struct efivar_operations *ops;
-};
-
 /*
  * The maximum size of VariableName + Data = 1024
  * Therefore, it's reasonable to save that much
@@ -706,7 +684,7 @@ out_free:
 	return error;
 }
 
-static void unregister_efivars(struct efivars *efivars)
+void unregister_efivars(struct efivars *efivars)
 {
 	struct efivar_entry *entry, *n;
 
@@ -724,10 +702,11 @@ static void unregister_efivars(struct efivars *efivars)
 	kfree(efivars->del_var);
 	kset_unregister(efivars->kset);
 }
+EXPORT_SYMBOL_GPL(unregister_efivars);
 
-static int register_efivars(struct efivars *efivars,
-			    const struct efivar_operations *ops,
-			    struct kobject *parent_kobj)
+int register_efivars(struct efivars *efivars,
+		     const struct efivar_operations *ops,
+		     struct kobject *parent_kobj)
 {
 	efi_status_t status = EFI_NOT_FOUND;
 	efi_guid_t vendor_guid;
@@ -789,6 +768,7 @@ out:
 
 	return error;
 }
+EXPORT_SYMBOL_GPL(register_efivars);
 
 static struct efivars __efivars;
 static struct efivar_operations ops;
@@ -810,7 +790,7 @@ efivars_init(void)
 	       EFIVARS_DATE);
 
 	if (!efi_enabled)
-		return -ENODEV;
+		return 0;
 
 	/* For now we'll register the efi directory at /sys/firmware/efi */
 	efi_kobj = kobject_create_and_add("efi", firmware_kobj);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index fb737bc19a8c..33fa1203024e 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -397,4 +397,41 @@ static inline void memrange_efi_to_native(u64 *addr, u64 *npages)
 	*addr &= PAGE_MASK;
 }
 
+#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
+/*
+ * EFI Variable support.
+ *
+ * Different firmware drivers can expose their EFI-like variables using
+ * the following.
+ */
+
+struct efivar_operations {
+	efi_get_variable_t *get_variable;
+	efi_get_next_variable_t *get_next_variable;
+	efi_set_variable_t *set_variable;
+};
+
+struct efivars {
+	/*
+	 * ->lock protects two things:
+	 * 1) ->list - adds, removals, reads, writes
+	 * 2) ops.[gs]et_variable() calls.
+	 * It must not be held when creating sysfs entries or calling kmalloc.
+	 * ops.get_next_variable() is only called from register_efivars(),
+	 * which is protected by the BKL, so that path is safe.
+	 */
+	spinlock_t lock;
+	struct list_head list;
+	struct kset *kset;
+	struct bin_attribute *new_var, *del_var;
+	const struct efivar_operations *ops;
+};
+
+int register_efivars(struct efivars *efivars,
+		     const struct efivar_operations *ops,
+		     struct kobject *parent_kobj);
+void unregister_efivars(struct efivars *efivars);
+
+#endif /* CONFIG_EFI_VARS */
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v1.2.3


From f52e0c11305aa09ed56cad97ffc8f0cdc3d78b5d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 14 Mar 2011 18:56:51 -0400
Subject: New AT_... flag: AT_EMPTY_PATH

For name_to_handle_at(2) we'll want both ...at()-style syscall that
would be usable for non-directory descriptors (with empty relative
pathname).  Introduce new flag (AT_EMPTY_PATH) to deal with that and
corresponding LOOKUP_EMPTY; teach user_path_at() and path_init() to
deal with the latter.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 29 +++++++++++++++++++----------
 include/linux/fcntl.h |  1 +
 include/linux/namei.h |  1 +
 3 files changed, 21 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index abc8d2df121c..83e92bab79a6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -136,7 +136,7 @@ static int do_getname(const char __user *filename, char *page)
 	return retval;
 }
 
-char * getname(const char __user * filename)
+static char *getname_flags(const char __user * filename, int flags)
 {
 	char *tmp, *result;
 
@@ -147,14 +147,21 @@ char * getname(const char __user * filename)
 
 		result = tmp;
 		if (retval < 0) {
-			__putname(tmp);
-			result = ERR_PTR(retval);
+			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
+				__putname(tmp);
+				result = ERR_PTR(retval);
+			}
 		}
 	}
 	audit_getname(result);
 	return result;
 }
 
+char *getname(const char __user * filename)
+{
+	return getname_flags(filename, 0);
+}
+
 #ifdef CONFIG_AUDITSYSCALL
 void putname(const char *name)
 {
@@ -1544,13 +1551,15 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 
 		dentry = file->f_path.dentry;
 
-		retval = -ENOTDIR;
-		if (!S_ISDIR(dentry->d_inode->i_mode))
-			goto fput_fail;
+		if (*name) {
+			retval = -ENOTDIR;
+			if (!S_ISDIR(dentry->d_inode->i_mode))
+				goto fput_fail;
 
-		retval = file_permission(file, MAY_EXEC);
-		if (retval)
-			goto fput_fail;
+			retval = file_permission(file, MAY_EXEC);
+			if (retval)
+				goto fput_fail;
+		}
 
 		nd->path = file->f_path;
 		if (flags & LOOKUP_RCU) {
@@ -1759,7 +1768,7 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 		 struct path *path)
 {
 	struct nameidata nd;
-	char *tmp = getname(name);
+	char *tmp = getname_flags(name, flags);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index a562fa5fb4e3..f550f894ba15 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -46,6 +46,7 @@
                                            unlinking file.  */
 #define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
 #define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
 
 #ifdef __KERNEL__
 
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 83cd6e5cd7dc..9c8603872c36 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -64,6 +64,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 
 #define LOOKUP_JUMPED		0x1000
 #define LOOKUP_ROOT		0x2000
+#define LOOKUP_EMPTY		0x4000
 
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
-- 
cgit v1.2.3


From cb8f51bdadb7969139c2e39c2defd4cde98c1ea8 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Tue, 8 Feb 2011 23:26:02 +0100
Subject: PM: Do not create wakeup sysfs files for devices that cannot wake up

Currently, wakeup sysfs attributes are created for all devices,
regardless of whether or not they are wakeup-capable.  This is
excessive and complicates wakeup device identification from user
space (i.e. to identify wakeup-capable devices user space has to read
/sys/devices/.../power/wakeup for all devices and see if they are not
empty).

Fix this issue by avoiding to create wakeup sysfs files for devices
that cannot wake up the system from sleep states (i.e. whose
power.can_wakeup flags are unset during registration) and modify
device_set_wakeup_capable() so that it adds (or removes) the relevant
sysfs attributes if a device's wakeup capability status is changed.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
---
 Documentation/ABI/testing/sysfs-devices-power | 20 +++----
 Documentation/power/devices.txt               | 20 +++----
 drivers/base/power/power.h                    | 21 ++++----
 drivers/base/power/sysfs.c                    | 78 +++++++++++++++++----------
 drivers/base/power/wakeup.c                   | 29 ++++++++++
 include/linux/pm_runtime.h                    |  6 +++
 include/linux/pm_wakeup.h                     |  8 +--
 7 files changed, 117 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 7628cd1bc36a..8ffbc25376a0 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -29,9 +29,8 @@ Description:
 		"disabled" to it.
 
 		For the devices that are not capable of generating system wakeup
-		events this file contains "\n".  In that cases the user space
-		cannot modify the contents of this file and the device cannot be
-		enabled to wake up the system.
+		events this file is not present.  In that case the device cannot
+		be enabled to wake up the system from sleep states.
 
 What:		/sys/devices/.../power/control
 Date:		January 2009
@@ -85,7 +84,7 @@ Description:
 		The /sys/devices/.../wakeup_count attribute contains the number
 		of signaled wakeup events associated with the device.  This
 		attribute is read-only.  If the device is not enabled to wake up
-		the system from sleep states, this attribute is empty.
+		the system from sleep states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_active_count
 Date:		September 2010
@@ -95,7 +94,7 @@ Description:
 		number of times the processing of wakeup events associated with
 		the device was completed (at the kernel level).  This attribute
 		is read-only.  If the device is not enabled to wake up the
-		system from sleep states, this attribute is empty.
+		system from sleep states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_hit_count
 Date:		September 2010
@@ -105,7 +104,8 @@ Description:
 		number of times the processing of a wakeup event associated with
 		the device might prevent the system from entering a sleep state.
 		This attribute is read-only.  If the device is not enabled to
-		wake up the system from sleep states, this attribute is empty.
+		wake up the system from sleep states, this attribute is not
+		present.
 
 What:		/sys/devices/.../power/wakeup_active
 Date:		September 2010
@@ -115,7 +115,7 @@ Description:
 		or 0, depending on whether or not a wakeup event associated with
 		the device is being processed (1).  This attribute is read-only.
 		If the device is not enabled to wake up the system from sleep
-		states, this attribute is empty.
+		states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_total_time_ms
 Date:		September 2010
@@ -125,7 +125,7 @@ Description:
 		the total time of processing wakeup events associated with the
 		device, in milliseconds.  This attribute is read-only.  If the
 		device is not enabled to wake up the system from sleep states,
-		this attribute is empty.
+		this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_max_time_ms
 Date:		September 2010
@@ -135,7 +135,7 @@ Description:
 		the maximum time of processing a single wakeup event associated
 		with the device, in milliseconds.  This attribute is read-only.
 		If the device is not enabled to wake up the system from sleep
-		states, this attribute is empty.
+		states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_last_time_ms
 Date:		September 2010
@@ -146,7 +146,7 @@ Description:
 		signaling the last wakeup event associated with the device, in
 		milliseconds.  This attribute is read-only.  If the device is
 		not enabled to wake up the system from sleep states, this
-		attribute is empty.
+		attribute is not present.
 
 What:		/sys/devices/.../power/autosuspend_delay_ms
 Date:		September 2010
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 57080cd74575..dd9b49251db3 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -159,18 +159,18 @@ matter, and the kernel is responsible for keeping track of it.  By contrast,
 whether or not a wakeup-capable device should issue wakeup events is a policy
 decision, and it is managed by user space through a sysfs attribute: the
 power/wakeup file.  User space can write the strings "enabled" or "disabled" to
-set or clear the should_wakeup flag, respectively.  Reads from the file will
-return the corresponding string if can_wakeup is true, but if can_wakeup is
-false then reads will return an empty string, to indicate that the device
-doesn't support wakeup events.  (But even though the file appears empty, writes
-will still affect the should_wakeup flag.)
+set or clear the "should_wakeup" flag, respectively.  This file is only present
+for wakeup-capable devices (i.e. devices whose "can_wakeup" flags are set)
+and is created (or removed) by device_set_wakeup_capable().  Reads from the
+file will return the corresponding string.
 
 The device_may_wakeup() routine returns true only if both flags are set.
-Drivers should check this routine when putting devices in a low-power state
-during a system sleep transition, to see whether or not to enable the devices'
-wakeup mechanisms.  However for runtime power management, wakeup events should
-be enabled whenever the device and driver both support them, regardless of the
-should_wakeup flag.
+This information is used by subsystems, like the PCI bus type code, to see
+whether or not to enable the devices' wakeup mechanisms.  If device wakeup
+mechanisms are enabled or disabled directly by drivers, they also should use
+device_may_wakeup() to decide what to do during a system sleep transition.
+However for runtime power management, wakeup events should be enabled whenever
+the device and driver both support them, regardless of the should_wakeup flag.
 
 
 /sys/devices/.../power/control files
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 698dde742587..f2a25f18fde7 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -58,19 +58,18 @@ static inline void device_pm_move_last(struct device *dev) {}
  * sysfs.c
  */
 
-extern int dpm_sysfs_add(struct device *);
-extern void dpm_sysfs_remove(struct device *);
-extern void rpm_sysfs_remove(struct device *);
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
 
 #else /* CONFIG_PM */
 
-static inline int dpm_sysfs_add(struct device *dev)
-{
-	return 0;
-}
-
-static inline void dpm_sysfs_remove(struct device *dev)
-{
-}
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline void rpm_sysfs_remove(struct device *dev) {}
+static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
+static inline void wakeup_sysfs_remove(struct device *dev) {}
 
 #endif
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 0b1e46bf3e56..fff49bee781d 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -431,26 +431,18 @@ static ssize_t async_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(async, 0644, async_show, async_store);
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 
-static struct attribute * power_attrs[] = {
-	&dev_attr_wakeup.attr,
-#ifdef CONFIG_PM_SLEEP
-	&dev_attr_wakeup_count.attr,
-	&dev_attr_wakeup_active_count.attr,
-	&dev_attr_wakeup_hit_count.attr,
-	&dev_attr_wakeup_active.attr,
-	&dev_attr_wakeup_total_time_ms.attr,
-	&dev_attr_wakeup_max_time_ms.attr,
-	&dev_attr_wakeup_last_time_ms.attr,
-#endif
+static struct attribute *power_attrs[] = {
 #ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
 	&dev_attr_async.attr,
+#endif
 #ifdef CONFIG_PM_RUNTIME
 	&dev_attr_runtime_status.attr,
 	&dev_attr_runtime_usage.attr,
 	&dev_attr_runtime_active_kids.attr,
 	&dev_attr_runtime_enabled.attr,
 #endif
-#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
 	NULL,
 };
 static struct attribute_group pm_attr_group = {
@@ -458,9 +450,26 @@ static struct attribute_group pm_attr_group = {
 	.attrs	= power_attrs,
 };
 
-#ifdef CONFIG_PM_RUNTIME
+static struct attribute *wakeup_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_wakeup.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_hit_count.attr,
+	&dev_attr_wakeup_active.attr,
+	&dev_attr_wakeup_total_time_ms.attr,
+	&dev_attr_wakeup_max_time_ms.attr,
+	&dev_attr_wakeup_last_time_ms.attr,
+#endif
+	NULL,
+};
+static struct attribute_group pm_wakeup_attr_group = {
+	.name	= power_group_name,
+	.attrs	= wakeup_attrs,
+};
 
 static struct attribute *runtime_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
 #ifndef CONFIG_PM_ADVANCED_DEBUG
 	&dev_attr_runtime_status.attr,
 #endif
@@ -468,6 +477,7 @@ static struct attribute *runtime_attrs[] = {
 	&dev_attr_runtime_suspended_time.attr,
 	&dev_attr_runtime_active_time.attr,
 	&dev_attr_autosuspend_delay_ms.attr,
+#endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
 static struct attribute_group pm_runtime_attr_group = {
@@ -480,35 +490,49 @@ int dpm_sysfs_add(struct device *dev)
 	int rc;
 
 	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
-	if (rc == 0 && !dev->power.no_callbacks) {
+	if (rc)
+		return rc;
+
+	if (pm_runtime_callbacks_present(dev)) {
 		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
 		if (rc)
-			sysfs_remove_group(&dev->kobj, &pm_attr_group);
+			goto err_out;
+	}
+
+	if (device_can_wakeup(dev)) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+		if (rc) {
+			if (pm_runtime_callbacks_present(dev))
+				sysfs_unmerge_group(&dev->kobj,
+						    &pm_runtime_attr_group);
+			goto err_out;
+		}
 	}
+	return 0;
+
+ err_out:
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 	return rc;
 }
 
-void rpm_sysfs_remove(struct device *dev)
+int wakeup_sysfs_add(struct device *dev)
 {
-	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+	return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
-void dpm_sysfs_remove(struct device *dev)
+void wakeup_sysfs_remove(struct device *dev)
 {
-	rpm_sysfs_remove(dev);
-	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
-#else /* CONFIG_PM_RUNTIME */
-
-int dpm_sysfs_add(struct device * dev)
+void rpm_sysfs_remove(struct device *dev)
 {
-	return sysfs_create_group(&dev->kobj, &pm_attr_group);
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
 }
 
-void dpm_sysfs_remove(struct device * dev)
+void dpm_sysfs_remove(struct device *dev)
 {
+	rpm_sysfs_remove(dev);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 }
-
-#endif
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 82836383997f..4573c83df6dd 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -241,6 +241,35 @@ int device_wakeup_disable(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(device_wakeup_disable);
 
+/**
+ * device_set_wakeup_capable - Set/reset device wakeup capability flag.
+ * @dev: Device to handle.
+ * @capable: Whether or not @dev is capable of waking up the system from sleep.
+ *
+ * If @capable is set, set the @dev's power.can_wakeup flag and add its
+ * wakeup-related attributes to sysfs.  Otherwise, unset the @dev's
+ * power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
+ *
+ * This function may sleep and it can't be called from any context where
+ * sleeping is not allowed.
+ */
+void device_set_wakeup_capable(struct device *dev, bool capable)
+{
+	if (!!dev->power.can_wakeup == !!capable)
+		return;
+
+	if (device_is_registered(dev)) {
+		if (capable) {
+			if (wakeup_sysfs_add(dev))
+				return;
+		} else {
+			wakeup_sysfs_remove(dev);
+		}
+	}
+	dev->power.can_wakeup = capable;
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
+
 /**
  * device_init_wakeup - Device wakeup initialization.
  * @dev: Device to handle.
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index d34f067e2a7f..8de9aa6e7def 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -87,6 +87,11 @@ static inline bool pm_runtime_enabled(struct device *dev)
 	return !dev->power.disable_depth;
 }
 
+static inline bool pm_runtime_callbacks_present(struct device *dev)
+{
+	return !dev->power.no_callbacks;
+}
+
 static inline void pm_runtime_mark_last_busy(struct device *dev)
 {
 	ACCESS_ONCE(dev->power.last_busy) = jiffies;
@@ -133,6 +138,7 @@ static inline int pm_generic_runtime_resume(struct device *dev) { return 0; }
 static inline void pm_runtime_no_callbacks(struct device *dev) {}
 static inline void pm_runtime_irq_safe(struct device *dev) {}
 
+static inline bool pm_runtime_callbacks_present(struct device *dev) { return false; }
 static inline void pm_runtime_mark_last_busy(struct device *dev) {}
 static inline void __pm_runtime_use_autosuspend(struct device *dev,
 						bool use) {}
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
index 03a67db03d01..a32da962d693 100644
--- a/include/linux/pm_wakeup.h
+++ b/include/linux/pm_wakeup.h
@@ -62,18 +62,11 @@ struct wakeup_source {
  * Changes to device_may_wakeup take effect on the next pm state change.
  */
 
-static inline void device_set_wakeup_capable(struct device *dev, bool capable)
-{
-	dev->power.can_wakeup = capable;
-}
-
 static inline bool device_can_wakeup(struct device *dev)
 {
 	return dev->power.can_wakeup;
 }
 
-
-
 static inline bool device_may_wakeup(struct device *dev)
 {
 	return dev->power.can_wakeup && !!dev->power.wakeup;
@@ -88,6 +81,7 @@ extern struct wakeup_source *wakeup_source_register(const char *name);
 extern void wakeup_source_unregister(struct wakeup_source *ws);
 extern int device_wakeup_enable(struct device *dev);
 extern int device_wakeup_disable(struct device *dev);
+extern void device_set_wakeup_capable(struct device *dev, bool capable);
 extern int device_init_wakeup(struct device *dev, bool val);
 extern int device_set_wakeup_enable(struct device *dev, bool enable);
 extern void __pm_stay_awake(struct wakeup_source *ws);
-- 
cgit v1.2.3


From cd51e61cf4e8b220da37dc35e9c2dc2dc258b4de Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Fri, 11 Feb 2011 00:04:52 +0100
Subject: PM / ACPI: Remove references to pm_flags from bus.c

If direct references to pm_flags are removed from drivers/acpi/bus.c,
CONFIG_ACPI will not need to depend on CONFIG_PM any more.  Make that
happen.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/Kconfig    |  1 -
 drivers/acpi/bus.c      |  7 ++++---
 include/linux/suspend.h |  6 ++++++
 kernel/power/main.c     | 12 +++++++++++-
 4 files changed, 21 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 2aa042a5da6d..3a17ca5fff6f 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -7,7 +7,6 @@ menuconfig ACPI
 	depends on !IA64_HP_SIM
 	depends on IA64 || X86
 	depends on PCI
-	depends on PM
 	select PNP
 	default y
 	help
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 7ced61f39492..973b0709972c 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -40,6 +40,7 @@
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 #include <linux/dmi.h>
+#include <linux/suspend.h>
 
 #include "internal.h"
 
@@ -1025,13 +1026,13 @@ static int __init acpi_init(void)
 
 	if (!result) {
 		pci_mmcfg_late_init();
-		if (!(pm_flags & PM_APM))
-			pm_flags |= PM_ACPI;
-		else {
+		if (pm_apm_enabled()) {
 			printk(KERN_INFO PREFIX
 			       "APM is already active, exiting\n");
 			disable_acpi();
 			result = -ENODEV;
+		} else {
+			pm_set_acpi_flag();
 		}
 	} else
 		disable_acpi();
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 5a89e3612875..5e364db8a56a 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -272,6 +272,9 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 	register_pm_notifier(&fn##_nb);			\
 }
 
+extern bool pm_apm_enabled(void);
+extern void pm_set_acpi_flag(void);
+
 /* drivers/base/power/wakeup.c */
 extern bool events_check_enabled;
 
@@ -292,6 +295,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
+static inline bool pm_apm_enabled(void) { return false; }
+static inline void pm_set_acpi_flag(void) {}
+
 static inline bool pm_wakeup_pending(void) { return false; }
 #endif /* !CONFIG_PM_SLEEP */
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 701853042c28..b5405af48ddb 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -17,10 +17,20 @@
 
 DEFINE_MUTEX(pm_mutex);
 
+#ifdef CONFIG_PM_SLEEP
+
 unsigned int pm_flags;
 EXPORT_SYMBOL(pm_flags);
 
-#ifdef CONFIG_PM_SLEEP
+bool pm_apm_enabled(void)
+{
+	return !!(pm_flags & PM_APM);
+}
+
+void pm_set_acpi_flag(void)
+{
+	pm_flags |= PM_ACPI;
+}
 
 /* Routines for PM-transition notifications */
 
-- 
cgit v1.2.3


From aa33860158114d0df3c7997bc1dd41c0168e1c2a Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Fri, 11 Feb 2011 00:06:54 +0100
Subject: PM: Remove CONFIG_PM_OPS

After redefining CONFIG_PM to depend on (CONFIG_PM_SLEEP ||
CONFIG_PM_RUNTIME) the CONFIG_PM_OPS option is redundant and can be
replaced with CONFIG_PM.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
---
 drivers/acpi/sleep.c               | 4 ++--
 drivers/base/power/Makefile        | 3 +--
 drivers/net/e1000e/netdev.c        | 8 ++++----
 drivers/net/pch_gbe/pch_gbe_main.c | 2 +-
 drivers/pci/pci-driver.c           | 4 ++--
 drivers/scsi/Makefile              | 2 +-
 drivers/scsi/scsi_priv.h           | 2 +-
 drivers/scsi/scsi_sysfs.c          | 2 +-
 drivers/usb/core/hcd-pci.c         | 4 ++--
 include/acpi/acpi_bus.h            | 2 +-
 include/linux/pm.h                 | 2 +-
 kernel/power/Kconfig               | 5 -----
 12 files changed, 17 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index d6a8cd14de2e..8ea092fad3f6 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -585,7 +585,7 @@ int acpi_suspend(u32 acpi_state)
 	return -EINVAL;
 }
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 /**
  *	acpi_pm_device_sleep_state - return preferred power state of ACPI device
  *		in the system sleep state given by %acpi_target_sleep_state
@@ -671,7 +671,7 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p)
 		*d_min_p = d_min;
 	return d_max;
 }
-#endif /* CONFIG_PM_OPS */
+#endif /* CONFIG_PM */
 
 #ifdef CONFIG_PM_SLEEP
 /**
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index abe46edfe5b4..118c1b92a511 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,7 +1,6 @@
-obj-$(CONFIG_PM)	+= sysfs.o
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
-obj-$(CONFIG_PM_OPS)	+= generic_ops.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_OPP)	+= opp.o
 
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 2e5022849f18..6d513a383340 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -5338,7 +5338,7 @@ void e1000e_disable_aspm(struct pci_dev *pdev, u16 state)
 	__e1000e_disable_aspm(pdev, state);
 }
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 static bool e1000e_pm_ready(struct e1000_adapter *adapter)
 {
 	return !!adapter->tx_ring->buffer_info;
@@ -5489,7 +5489,7 @@ static int e1000_runtime_resume(struct device *dev)
 	return __e1000_resume(pdev);
 }
 #endif /* CONFIG_PM_RUNTIME */
-#endif /* CONFIG_PM_OPS */
+#endif /* CONFIG_PM */
 
 static void e1000_shutdown(struct pci_dev *pdev)
 {
@@ -6196,7 +6196,7 @@ static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = {
 };
 MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 static const struct dev_pm_ops e1000_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume)
 	SET_RUNTIME_PM_OPS(e1000_runtime_suspend,
@@ -6210,7 +6210,7 @@ static struct pci_driver e1000_driver = {
 	.id_table = e1000_pci_tbl,
 	.probe    = e1000_probe,
 	.remove   = __devexit_p(e1000_remove),
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 	.driver.pm = &e1000_pm_ops,
 #endif
 	.shutdown = e1000_shutdown,
diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c
index b99e90aca37d..8c66e22c3a0a 100644
--- a/drivers/net/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/pch_gbe/pch_gbe_main.c
@@ -2446,7 +2446,7 @@ static struct pci_driver pch_gbe_pcidev = {
 	.id_table = pch_gbe_pcidev_id,
 	.probe = pch_gbe_probe,
 	.remove = pch_gbe_remove,
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 	.driver.pm = &pch_gbe_pm_ops,
 #endif
 	.shutdown = pch_gbe_shutdown,
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 88246dd46452..d86ea8b01137 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -431,7 +431,7 @@ static void pci_device_shutdown(struct device *dev)
 	pci_msix_shutdown(pci_dev);
 }
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 
 /* Auxiliary functions used for system resume and run-time resume. */
 
@@ -1059,7 +1059,7 @@ static int pci_pm_runtime_idle(struct device *dev)
 
 #endif /* !CONFIG_PM_RUNTIME */
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 
 const struct dev_pm_ops pci_dev_pm_ops = {
 	.prepare = pci_pm_prepare,
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 2e9a87e8e7d8..ef6de669424b 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -165,7 +165,7 @@ scsi_mod-$(CONFIG_SCSI_NETLINK)	+= scsi_netlink.o
 scsi_mod-$(CONFIG_SYSCTL)	+= scsi_sysctl.o
 scsi_mod-$(CONFIG_SCSI_PROC_FS)	+= scsi_proc.o
 scsi_mod-y			+= scsi_trace.o
-scsi_mod-$(CONFIG_PM_OPS)	+= scsi_pm.o
+scsi_mod-$(CONFIG_PM)		+= scsi_pm.o
 
 scsi_tgt-y			+= scsi_tgt_lib.o scsi_tgt_if.o
 
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index b4056d14f812..342ee1a9c41d 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -146,7 +146,7 @@ static inline void scsi_netlink_exit(void) {}
 #endif
 
 /* scsi_pm.c */
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 extern const struct dev_pm_ops scsi_bus_pm_ops;
 #endif
 #ifdef CONFIG_PM_RUNTIME
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 490ce213204e..e44ff64233fd 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -383,7 +383,7 @@ struct bus_type scsi_bus_type = {
         .name		= "scsi",
         .match		= scsi_bus_match,
 	.uevent		= scsi_bus_uevent,
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 	.pm		= &scsi_bus_pm_ops,
 #endif
 };
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index f71e8e307e0f..64a035ba2eab 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -335,7 +335,7 @@ void usb_hcd_pci_shutdown(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(usb_hcd_pci_shutdown);
 
-#ifdef	CONFIG_PM_OPS
+#ifdef	CONFIG_PM
 
 #ifdef	CONFIG_PPC_PMAC
 static void powermac_set_asic(struct pci_dev *pci_dev, int enable)
@@ -580,4 +580,4 @@ const struct dev_pm_ops usb_hcd_pci_pm_ops = {
 };
 EXPORT_SYMBOL_GPL(usb_hcd_pci_pm_ops);
 
-#endif	/* CONFIG_PM_OPS */
+#endif	/* CONFIG_PM */
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 78ca429929f7..ff103ba96b78 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -381,7 +381,7 @@ struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle);
 int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state);
 int acpi_disable_wakeup_device_power(struct acpi_device *dev);
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 int acpi_pm_device_sleep_state(struct device *, int *);
 #else
 static inline int acpi_pm_device_sleep_state(struct device *d, int *p)
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 21415cc91cbb..9279175a4557 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -267,7 +267,7 @@ const struct dev_pm_ops name = { \
  * callbacks provided by device drivers supporting both the system sleep PM and
  * runtime PM, make the pm member point to generic_subsys_pm_ops.
  */
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 extern struct dev_pm_ops generic_subsys_pm_ops;
 #define GENERIC_SUBSYS_PM_OPS	(&generic_subsys_pm_ops)
 #else
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 1e4d9238c5da..0710beead05b 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -220,11 +220,6 @@ config APM_EMULATION
 	  anything, try disabling/enabling this option (or disabling/enabling
 	  APM in your BIOS).
 
-config PM_OPS
-	bool
-	depends on PM_SLEEP || PM_RUNTIME
-	default y
-
 config ARCH_HAS_OPP
 	bool
 
-- 
cgit v1.2.3


From 6831c6edc7b272a08dd2a6c71bb183a48fe98ae6 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Tue, 15 Feb 2011 21:22:24 +0100
Subject: PM: Drop pm_flags that is not necessary

The variable pm_flags is used to prevent APM from being enabled
along with ACPI, which would lead to problems.  However, acpi_init()
is always called before apm_init() and after acpi_init() has
returned, it is known whether or not ACPI will be used.  Namely, if
acpi_disabled is not set after acpi_init() has returned, this means
that ACPI is enabled.  Thus, it is sufficient to check acpi_disabled
in apm_init() to prevent APM from being enabled in parallel with
ACPI.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Len Brown <len.brown@intel.com>
---
 arch/x86/kernel/apm_32.c |  5 ++---
 drivers/acpi/bus.c       | 22 +++++-----------------
 include/linux/pm.h       |  9 ---------
 include/linux/suspend.h  |  6 ------
 kernel/power/main.c      | 13 -------------
 5 files changed, 7 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0e4f24c2a746..15f47f741983 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -227,6 +227,7 @@
 #include <linux/suspend.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
+#include <linux/acpi.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -2331,12 +2332,11 @@ static int __init apm_init(void)
 		apm_info.disabled = 1;
 		return -ENODEV;
 	}
-	if (pm_flags & PM_ACPI) {
+	if (!acpi_disabled) {
 		printk(KERN_NOTICE "apm: overridden by ACPI.\n");
 		apm_info.disabled = 1;
 		return -ENODEV;
 	}
-	pm_flags |= PM_APM;
 
 	/*
 	 * Set up the long jump entry point to the APM BIOS, which is called
@@ -2428,7 +2428,6 @@ static void __exit apm_exit(void)
 		kthread_stop(kapmd_task);
 		kapmd_task = NULL;
 	}
-	pm_flags &= ~PM_APM;
 }
 
 module_init(apm_init);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 973b0709972c..9749980ca6ca 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1007,8 +1007,7 @@ struct kobject *acpi_kobj;
 
 static int __init acpi_init(void)
 {
-	int result = 0;
-
+	int result;
 
 	if (acpi_disabled) {
 		printk(KERN_INFO PREFIX "Interpreter disabled.\n");
@@ -1023,29 +1022,18 @@ static int __init acpi_init(void)
 
 	init_acpi_device_notify();
 	result = acpi_bus_init();
-
-	if (!result) {
-		pci_mmcfg_late_init();
-		if (pm_apm_enabled()) {
-			printk(KERN_INFO PREFIX
-			       "APM is already active, exiting\n");
-			disable_acpi();
-			result = -ENODEV;
-		} else {
-			pm_set_acpi_flag();
-		}
-	} else
+	if (result) {
 		disable_acpi();
-
-	if (acpi_disabled)
 		return result;
+	}
 
+	pci_mmcfg_late_init();
 	acpi_scan_init();
 	acpi_ec_init();
 	acpi_debugfs_init();
 	acpi_sleep_proc_init();
 	acpi_wakeup_device_init();
-	return result;
+	return 0;
 }
 
 subsys_initcall(acpi_init);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 9279175a4557..1f79c98f1e56 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -565,15 +565,6 @@ enum dpm_order {
 	DPM_ORDER_DEV_LAST,
 };
 
-/*
- * Global Power Management flags
- * Used to keep APM and ACPI from both being active
- */
-extern unsigned int	pm_flags;
-
-#define PM_APM	1
-#define PM_ACPI	2
-
 extern int pm_generic_suspend(struct device *dev);
 extern int pm_generic_resume(struct device *dev);
 extern int pm_generic_freeze(struct device *dev);
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 5e364db8a56a..5a89e3612875 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -272,9 +272,6 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 	register_pm_notifier(&fn##_nb);			\
 }
 
-extern bool pm_apm_enabled(void);
-extern void pm_set_acpi_flag(void);
-
 /* drivers/base/power/wakeup.c */
 extern bool events_check_enabled;
 
@@ -295,9 +292,6 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
-static inline bool pm_apm_enabled(void) { return false; }
-static inline void pm_set_acpi_flag(void) {}
-
 static inline bool pm_wakeup_pending(void) { return false; }
 #endif /* !CONFIG_PM_SLEEP */
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b5405af48ddb..8eaba5f27b10 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -19,19 +19,6 @@ DEFINE_MUTEX(pm_mutex);
 
 #ifdef CONFIG_PM_SLEEP
 
-unsigned int pm_flags;
-EXPORT_SYMBOL(pm_flags);
-
-bool pm_apm_enabled(void)
-{
-	return !!(pm_flags & PM_APM);
-}
-
-void pm_set_acpi_flag(void)
-{
-	pm_flags |= PM_ACPI;
-}
-
 /* Routines for PM-transition notifications */
 
 static BLOCKING_NOTIFIER_HEAD(pm_chain_head);
-- 
cgit v1.2.3


From 7538e3db6e015e890825fbd9f8659952896ddd5b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Wed, 16 Feb 2011 21:53:17 +0100
Subject: PM: Add support for device power domains

The platform bus type is often used to handle Systems-on-a-Chip (SoC)
where all devices are represented by objects of type struct
platform_device.  In those cases the same "platform" device driver
may be used with multiple different system configurations, but the
actions needed to put the devices it handles into a low-power state
and back into the full-power state may depend on the design of the
given SoC.  The driver, however, cannot possibly include all the
information necessary for the power management of its device on all
the systems it is used with.  Moreover, the device hierarchy in its
current form also is not suitable for representing this kind of
information.

The patch below attempts to address this problem by introducing
objects of type struct dev_power_domain that can be used for
representing power domains within a SoC.  Every struct
dev_power_domain object provides a sets of device power
management callbacks that can be used to perform what's needed for
device power management in addition to the operations carried out by
the device's driver and subsystem.

Namely, if a struct dev_power_domain object is pointed to by the
pwr_domain field in a struct device, the callbacks provided by its
ops member will be executed in addition to the corresponding
callbacks provided by the device's subsystem and driver during all
power transitions.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Tested-and-acked-by: Kevin Hilman <khilman@ti.com>
---
 Documentation/power/devices.txt | 45 ++++++++++++++++++++++++++++++++++++++++-
 drivers/base/power/main.c       | 37 +++++++++++++++++++++++++++++++++
 drivers/base/power/runtime.c    | 19 +++++++++++++++--
 include/linux/device.h          |  1 +
 include/linux/pm.h              |  8 ++++++++
 5 files changed, 107 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index dd9b49251db3..df1a5cb10c42 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -1,6 +1,6 @@
 Device Power Management
 
-Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+Copyright (c) 2010-2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
 Copyright (c) 2010 Alan Stern <stern@rowland.harvard.edu>
 
 
@@ -507,6 +507,49 @@ routines.  Nevertheless, different callback pointers are used in case there is a
 situation where it actually matters.
 
 
+Device Power Domains
+--------------------
+Sometimes devices share reference clocks or other power resources.  In those
+cases it generally is not possible to put devices into low-power states
+individually.  Instead, a set of devices sharing a power resource can be put
+into a low-power state together at the same time by turning off the shared
+power resource.  Of course, they also need to be put into the full-power state
+together, by turning the shared power resource on.  A set of devices with this
+property is often referred to as a power domain.
+
+Support for power domains is provided through the pwr_domain field of struct
+device.  This field is a pointer to an object of type struct dev_power_domain,
+defined in include/linux/pm.h, providing a set of power management callbacks
+analogous to the subsystem-level and device driver callbacks that are executed
+for the given device during all power transitions, in addition to the respective
+subsystem-level callbacks.  Specifically, the power domain "suspend" callbacks
+(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are
+executed after the analogous subsystem-level callbacks, while the power domain
+"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore,
+etc.) are executed before the analogous subsystem-level callbacks.  Error codes
+returned by the "suspend" and "resume" power domain callbacks are ignored.
+
+Power domain ->runtime_idle() callback is executed before the subsystem-level
+->runtime_idle() callback and the result returned by it is not ignored.  Namely,
+if it returns error code, the subsystem-level ->runtime_idle() callback will not
+be called and the helper function rpm_idle() executing it will return error
+code.  This mechanism is intended to help platforms where saving device state
+is a time consuming operation and should only be carried out if all devices
+in the power domain are idle, before turning off the shared power resource(s).
+Namely, the power domain ->runtime_idle() callback may return error code until
+the pm_runtime_idle() helper (or its asychronous version) has been called for
+all devices in the power domain (it is recommended that the returned error code
+be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle()
+callback from being run prematurely.
+
+The support for device power domains is only relevant to platforms needing to
+use the same subsystem-level (e.g. platform bus type) and device driver power
+management callbacks in many different power domain configurations and wanting
+to avoid incorporating the support for power domains into the subsystem-level
+callbacks.  The other platforms need not implement it or take it into account
+in any way.
+
+
 System Devices
 --------------
 System devices (sysdevs) follow a slightly different API, which can be found in
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index f7a755923751..05b989139b54 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -423,6 +423,11 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 	TRACE_DEVICE(dev);
 	TRACE_RESUME(0);
 
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "EARLY power domain ");
+		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+	}
+
 	if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "EARLY ");
 		error = pm_noirq_op(dev, dev->bus->pm, state);
@@ -518,6 +523,11 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 	dev->power.in_suspend = false;
 
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		pm_op(dev, &dev->pwr_domain->ops, state);
+	}
+
 	if (dev->bus) {
 		if (dev->bus->pm) {
 			pm_dev_dbg(dev, state, "");
@@ -629,6 +639,11 @@ static void device_complete(struct device *dev, pm_message_t state)
 {
 	device_lock(dev);
 
+	if (dev->pwr_domain && dev->pwr_domain->ops.complete) {
+		pm_dev_dbg(dev, state, "completing power domain ");
+		dev->pwr_domain->ops.complete(dev);
+	}
+
 	if (dev->class && dev->class->pm && dev->class->pm->complete) {
 		pm_dev_dbg(dev, state, "completing class ");
 		dev->class->pm->complete(dev);
@@ -745,6 +760,13 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 	if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "LATE ");
 		error = pm_noirq_op(dev, dev->bus->pm, state);
+		if (error)
+			goto End;
+	}
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "LATE power domain ");
+		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
 	}
 
 End:
@@ -864,6 +886,13 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 			pm_dev_dbg(dev, state, "legacy ");
 			error = legacy_suspend(dev, state, dev->bus->suspend);
 		}
+		if (error)
+			goto End;
+	}
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		pm_op(dev, &dev->pwr_domain->ops, state);
 	}
 
  End:
@@ -976,7 +1005,15 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		pm_dev_dbg(dev, state, "preparing class ");
 		error = dev->class->pm->prepare(dev);
 		suspend_report_result(dev->class->pm->prepare, error);
+		if (error)
+			goto End;
+	}
+
+	if (dev->pwr_domain && dev->pwr_domain->ops.prepare) {
+		pm_dev_dbg(dev, state, "preparing power domain ");
+		dev->pwr_domain->ops.prepare(dev);
 	}
+
  End:
 	device_unlock(dev);
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 42615b419dfb..25edc9a3a489 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -168,6 +168,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
 static int rpm_idle(struct device *dev, int rpmflags)
 {
 	int (*callback)(struct device *);
+	int (*domain_callback)(struct device *);
 	int retval;
 
 	retval = rpm_check_suspend_allowed(dev);
@@ -222,10 +223,19 @@ static int rpm_idle(struct device *dev, int rpmflags)
 	else
 		callback = NULL;
 
-	if (callback) {
+	if (dev->pwr_domain)
+		domain_callback = dev->pwr_domain->ops.runtime_idle;
+	else
+		domain_callback = NULL;
+
+	if (callback || domain_callback) {
 		spin_unlock_irq(&dev->power.lock);
 
-		callback(dev);
+		if (domain_callback)
+			retval = domain_callback(dev);
+
+		if (!retval && callback)
+			callback(dev);
 
 		spin_lock_irq(&dev->power.lock);
 	}
@@ -390,6 +400,8 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		else
 			pm_runtime_cancel_pending(dev);
 	} else {
+		if (dev->pwr_domain)
+			rpm_callback(dev->pwr_domain->ops.runtime_suspend, dev);
  no_callback:
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_deactivate_timer(dev);
@@ -569,6 +581,9 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_RESUMING);
 
+	if (dev->pwr_domain)
+		rpm_callback(dev->pwr_domain->ops.runtime_resume, dev);
+
 	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume)
 		callback = dev->bus->pm->runtime_resume;
 	else if (dev->type && dev->type->pm && dev->type->pm->runtime_resume)
diff --git a/include/linux/device.h b/include/linux/device.h
index 1bf5cf0b4513..22e9a8a7e1bc 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -422,6 +422,7 @@ struct device {
 	void		*platform_data;	/* Platform specific data, device
 					   core doesn't touch it */
 	struct dev_pm_info	power;
+	struct dev_power_domain	*pwr_domain;
 
 #ifdef CONFIG_NUMA
 	int		numa_node;	/* NUMA node this device is close to */
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 1f79c98f1e56..6618216bb973 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -465,6 +465,14 @@ struct dev_pm_info {
 
 extern void update_pm_runtime_accounting(struct device *dev);
 
+/*
+ * Power domains provide callbacks that are executed during system suspend,
+ * hibernation, system resume and during runtime PM transitions along with
+ * subsystem-level and driver-level callbacks.
+ */
+struct dev_power_domain {
+	struct dev_pm_ops	ops;
+};
 
 /*
  * The PM_EVENT_ messages are also used by drivers implementing the legacy
-- 
cgit v1.2.3


From 40dc166cb5dddbd36aa4ad11c03915ea538f5a61 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Tue, 15 Mar 2011 00:43:46 +0100
Subject: PM / Core: Introduce struct syscore_ops for core subsystems PM

Some subsystems need to carry out suspend/resume and shutdown
operations with one CPU on-line and interrupts disabled.  The only
way to register such operations is to define a sysdev class and
a sysdev specifically for this purpose which is cumbersome and
inefficient.  Moreover, the arguments taken by sysdev suspend,
resume and shutdown callbacks are practically never necessary.

For this reason, introduce a simpler interface allowing subsystems
to register operations to be executed very late during system suspend
and shutdown and very early during resume in the form of
strcut syscore_ops objects.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/base/Makefile       |   2 +-
 drivers/base/syscore.c      | 117 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/syscore_ops.h |  29 +++++++++++
 kernel/power/hibernate.c    |   9 ++++
 kernel/power/suspend.c      |   4 ++
 kernel/sys.c                |   4 ++
 6 files changed, 164 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/syscore.c
 create mode 100644 include/linux/syscore_ops.h

(limited to 'include')

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 5f51c3b4451e..4c5701c15f53 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -1,6 +1,6 @@
 # Makefile for the Linux device tree
 
-obj-y			:= core.o sys.o bus.o dd.o \
+obj-y			:= core.o sys.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
new file mode 100644
index 000000000000..90af2943f9e4
--- /dev/null
+++ b/drivers/base/syscore.c
@@ -0,0 +1,117 @@
+/*
+ *  syscore.c - Execution of system core operations.
+ *
+ *  Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ *  This file is released under the GPLv2.
+ */
+
+#include <linux/syscore_ops.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+
+static LIST_HEAD(syscore_ops_list);
+static DEFINE_MUTEX(syscore_ops_lock);
+
+/**
+ * register_syscore_ops - Register a set of system core operations.
+ * @ops: System core operations to register.
+ */
+void register_syscore_ops(struct syscore_ops *ops)
+{
+	mutex_lock(&syscore_ops_lock);
+	list_add_tail(&ops->node, &syscore_ops_list);
+	mutex_unlock(&syscore_ops_lock);
+}
+EXPORT_SYMBOL_GPL(register_syscore_ops);
+
+/**
+ * unregister_syscore_ops - Unregister a set of system core operations.
+ * @ops: System core operations to unregister.
+ */
+void unregister_syscore_ops(struct syscore_ops *ops)
+{
+	mutex_lock(&syscore_ops_lock);
+	list_del(&ops->node);
+	mutex_unlock(&syscore_ops_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_syscore_ops);
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * syscore_suspend - Execute all the registered system core suspend callbacks.
+ *
+ * This function is executed with one CPU on-line and disabled interrupts.
+ */
+int syscore_suspend(void)
+{
+	struct syscore_ops *ops;
+	int ret = 0;
+
+	WARN_ONCE(!irqs_disabled(),
+		"Interrupts enabled before system core suspend.\n");
+
+	list_for_each_entry_reverse(ops, &syscore_ops_list, node)
+		if (ops->suspend) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->suspend);
+			ret = ops->suspend();
+			if (ret)
+				goto err_out;
+			WARN_ONCE(!irqs_disabled(),
+				"Interrupts enabled after %pF\n", ops->suspend);
+		}
+
+	return 0;
+
+ err_out:
+	pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend);
+
+	list_for_each_entry_continue(ops, &syscore_ops_list, node)
+		if (ops->resume)
+			ops->resume();
+
+	return ret;
+}
+
+/**
+ * syscore_resume - Execute all the registered system core resume callbacks.
+ *
+ * This function is executed with one CPU on-line and disabled interrupts.
+ */
+void syscore_resume(void)
+{
+	struct syscore_ops *ops;
+
+	WARN_ONCE(!irqs_disabled(),
+		"Interrupts enabled before system core resume.\n");
+
+	list_for_each_entry(ops, &syscore_ops_list, node)
+		if (ops->resume) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->resume);
+			ops->resume();
+			WARN_ONCE(!irqs_disabled(),
+				"Interrupts enabled after %pF\n", ops->resume);
+		}
+}
+#endif /* CONFIG_PM_SLEEP */
+
+/**
+ * syscore_shutdown - Execute all the registered system core shutdown callbacks.
+ */
+void syscore_shutdown(void)
+{
+	struct syscore_ops *ops;
+
+	mutex_lock(&syscore_ops_lock);
+
+	list_for_each_entry_reverse(ops, &syscore_ops_list, node)
+		if (ops->shutdown) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->shutdown);
+			ops->shutdown();
+		}
+
+	mutex_unlock(&syscore_ops_lock);
+}
diff --git a/include/linux/syscore_ops.h b/include/linux/syscore_ops.h
new file mode 100644
index 000000000000..27b3b0bc41a9
--- /dev/null
+++ b/include/linux/syscore_ops.h
@@ -0,0 +1,29 @@
+/*
+ *  syscore_ops.h - System core operations.
+ *
+ *  Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ *  This file is released under the GPLv2.
+ */
+
+#ifndef _LINUX_SYSCORE_OPS_H
+#define _LINUX_SYSCORE_OPS_H
+
+#include <linux/list.h>
+
+struct syscore_ops {
+	struct list_head node;
+	int (*suspend)(void);
+	void (*resume)(void);
+	void (*shutdown)(void);
+};
+
+extern void register_syscore_ops(struct syscore_ops *ops);
+extern void unregister_syscore_ops(struct syscore_ops *ops);
+#ifdef CONFIG_PM_SLEEP
+extern int syscore_suspend(void);
+extern void syscore_resume(void);
+#endif
+extern void syscore_shutdown(void);
+
+#endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 1832bd264219..aeabd26e3342 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/freezer.h>
 #include <linux/gfp.h>
+#include <linux/syscore_ops.h>
 #include <scsi/scsi_scan.h>
 #include <asm/suspend.h>
 
@@ -272,6 +273,8 @@ static int create_image(int platform_mode)
 	local_irq_disable();
 
 	error = sysdev_suspend(PMSG_FREEZE);
+	if (!error)
+		error = syscore_suspend();
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
@@ -295,6 +298,7 @@ static int create_image(int platform_mode)
 	}
 
  Power_up:
+	syscore_resume();
 	sysdev_resume();
 	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
@@ -403,6 +407,8 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_disable();
 
 	error = sysdev_suspend(PMSG_QUIESCE);
+	if (!error)
+		error = syscore_suspend();
 	if (error)
 		goto Enable_irqs;
 
@@ -429,6 +435,7 @@ static int resume_target_kernel(bool platform_mode)
 	restore_processor_state();
 	touch_softlockup_watchdog();
 
+	syscore_resume();
 	sysdev_resume();
 
  Enable_irqs:
@@ -516,6 +523,7 @@ int hibernation_platform_enter(void)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_HIBERNATE);
+	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
 		goto Power_up;
@@ -526,6 +534,7 @@ int hibernation_platform_enter(void)
 	while (1);
 
  Power_up:
+	syscore_resume();
 	sysdev_resume();
 	local_irq_enable();
 	enable_nonboot_cpus();
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index de6f86bfa303..2814c32aed51 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -22,6 +22,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/syscore_ops.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -163,11 +164,14 @@ static int suspend_enter(suspend_state_t state)
 	BUG_ON(!irqs_disabled());
 
 	error = sysdev_suspend(PMSG_SUSPEND);
+	if (!error)
+		error = syscore_suspend();
 	if (!error) {
 		if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
 			error = suspend_ops->enter(state);
 			events_check_enabled = false;
 		}
+		syscore_resume();
 		sysdev_resume();
 	}
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 18da702ec813..1ad48b3b9068 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -37,6 +37,7 @@
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
 #include <linux/gfp.h>
+#include <linux/syscore_ops.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -298,6 +299,7 @@ void kernel_restart_prepare(char *cmd)
 	system_state = SYSTEM_RESTART;
 	device_shutdown();
 	sysdev_shutdown();
+	syscore_shutdown();
 }
 
 /**
@@ -336,6 +338,7 @@ void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
 	sysdev_shutdown();
+	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
 	machine_halt();
@@ -355,6 +358,7 @@ void kernel_power_off(void)
 		pm_power_off_prepare();
 	disable_nonboot_cpus();
 	sysdev_shutdown();
+	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
 	machine_power_off();
-- 
cgit v1.2.3


From 698e1d23cfc15312be2e7665014afd98c49ae9a1 Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Mon, 14 Mar 2011 09:01:02 +0000
Subject: net: dcbnl: Update copyright dates

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dcbnl.h | 2 +-
 net/dcb/dcbnl.c       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index a3680a16718f..97c90b953c31 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008, Intel Corporation.
+ * Copyright (c) 2008-2011, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 118392f3872e..3609eacaf4ce 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008, Intel Corporation.
+ * Copyright (c) 2008-2011, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
-- 
cgit v1.2.3


From 171f20e93b9d44a846bd5a41a583fdae13d26cd7 Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Mon, 14 Mar 2011 09:01:08 +0000
Subject: net: dcbnl: Fix misspellings

Fix a few spelling errors in dcbnl.h.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dcbnl.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 97c90b953c31..eedf79b7ef7e 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -26,13 +26,13 @@
 #define IEEE_8021QAZ_MAX_TCS	8
 
 #define IEEE_8021QAZ_TSA_STRICT		0
-#define IEEE_8021QAZ_TSA_CB_SHABER	1
+#define IEEE_8021QAZ_TSA_CB_SHAPER	1
 #define IEEE_8021QAZ_TSA_ETS		2
 #define IEEE_8021QAZ_TSA_VENDOR		255
 
 /* This structure contains the IEEE 802.1Qaz ETS managed object
  *
- * @willing: willing bit in ETS configuratin TLV
+ * @willing: willing bit in ETS configuration TLV
  * @ets_cap: indicates supported capacity of ets feature
  * @cbs: credit based shaper ets algorithm supported
  * @tc_tx_bw: tc tx bandwidth indexed by traffic class
@@ -92,7 +92,7 @@ struct ieee_pfc {
 #define CEE_DCBX_MAX_PRIO	8
 
 /**
- * struct cee_pg - CEE Prioity-Group managed object
+ * struct cee_pg - CEE Priority-Group managed object
  *
  * @willing: willing bit in the PG tlv
  * @error: error bit in the PG tlv
-- 
cgit v1.2.3


From 0c0217b016ba8a970a6f6ab62ad0d858f39881ca Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Mon, 14 Mar 2011 09:01:15 +0000
Subject: net: dcbnl: Add IEEE app selector value definitions

This adds defines for the app selector values currently
defined in the IEEE 802.1Qaz specification.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dcbnl.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index eedf79b7ef7e..c52280047e2c 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -125,6 +125,11 @@ struct cee_pfc {
 	__u8    tcs_supported;
 };
 
+/* IEEE 802.1Qaz std supported values */
+#define IEEE_8021QAZ_APP_SEL_ETHERTYPE	1
+#define IEEE_8021QAZ_APP_SEL_STREAM	2
+#define IEEE_8021QAZ_APP_SEL_DGRAM	3
+#define IEEE_8021QAZ_APP_SEL_ANY	4
 
 /* This structure contains the IEEE 802.1Qaz APP managed object. This
  * object is also used for the CEE std as well. There is no difference
-- 
cgit v1.2.3


From 06b69390a652bfe4fa7e18e27c938e75ffe86ba0 Mon Sep 17 00:00:00 2001
From: Jesper Juhl <jj@chaosbits.net>
Date: Wed, 9 Mar 2011 22:55:05 +0100
Subject: IPVS: Fix variable assignment in ip_vs_notrack

There's no sense to 'ct = ct = ' in ip_vs_notrack(). Just assign
nf_ct_get()'s return value directly to the pointer variable 'ct' once.

Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index e74da41ebd1b..1dcb75da313d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1190,7 +1190,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
 	if (!ct || !nf_ct_is_untracked(ct)) {
 		nf_reset(skb);
-- 
cgit v1.2.3


From 2553d064ff4bf999f369c8c3dfacaa797dbef1d9 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 4 Mar 2011 12:18:07 +0200
Subject: ipvs: move struct netns_ipvs

 	Remove include/net/netns/ip_vs.h because it depends on
structures from include/net/ip_vs.h. As ipvs is pointer in
struct net it is better to move struct netns_ipvs into
include/net/ip_vs.h, so that we can easily use other structures
in struct netns_ipvs.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h         | 122 +++++++++++++++++++++++++++++++++++++
 include/net/net_namespace.h |   2 +-
 include/net/netns/ip_vs.h   | 143 --------------------------------------------
 3 files changed, 123 insertions(+), 144 deletions(-)
 delete mode 100644 include/net/netns/ip_vs.h

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 1dcb75da313d..091ca1f76e0e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -803,6 +803,128 @@ struct ip_vs_app {
 	void (*timeout_change)(struct ip_vs_app *app, int flags);
 };
 
+/* IPVS in network namespace */
+struct netns_ipvs {
+	int			gen;		/* Generation */
+	/*
+	 *	Hash table: for real service lookups
+	 */
+	#define IP_VS_RTAB_BITS 4
+	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
+	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
+
+	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+	/* ip_vs_app */
+	struct list_head	app_list;
+	struct mutex		app_mutex;
+	struct lock_class_key	app_key;	/* mutex debuging */
+
+	/* ip_vs_proto */
+	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
+	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
+	/* ip_vs_proto_tcp */
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	#define	TCP_APP_TAB_BITS	4
+	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
+	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
+	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
+	spinlock_t		tcp_app_lock;
+#endif
+	/* ip_vs_proto_udp */
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	#define	UDP_APP_TAB_BITS	4
+	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
+	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
+	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
+	spinlock_t		udp_app_lock;
+#endif
+	/* ip_vs_proto_sctp */
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	#define SCTP_APP_TAB_BITS	4
+	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
+	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
+	/* Hash table for SCTP application incarnations	 */
+	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
+	spinlock_t		sctp_app_lock;
+#endif
+	/* ip_vs_conn */
+	atomic_t		conn_count;      /*  connection counter */
+
+	/* ip_vs_ctl */
+	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
+	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
+	seqcount_t			*ustats_seq; /* u64 read retry */
+
+	int			num_services;    /* no of virtual services */
+	/* 1/rate drop and drop-entry variables */
+	struct delayed_work	defense_work;   /* Work handler */
+	int			drop_rate;
+	int			drop_counter;
+	atomic_t		dropentry;
+	/* locks in ctl.c */
+	spinlock_t		dropentry_lock;  /* drop entry handling */
+	spinlock_t		droppacket_lock; /* drop packet handling */
+	spinlock_t		securetcp_lock;  /* state and timeout tables */
+	rwlock_t		rs_lock;         /* real services table */
+	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
+	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* Trash for destinations */
+	struct list_head	dest_trash;
+	/* Service counters */
+	atomic_t		ftpsvc_counter;
+	atomic_t		nullsvc_counter;
+
+	/* sys-ctl struct */
+	struct ctl_table_header	*sysctl_hdr;
+	struct ctl_table	*sysctl_tbl;
+	/* sysctl variables */
+	int			sysctl_amemthresh;
+	int			sysctl_am_droprate;
+	int			sysctl_drop_entry;
+	int			sysctl_drop_packet;
+	int			sysctl_secure_tcp;
+#ifdef CONFIG_IP_VS_NFCT
+	int			sysctl_conntrack;
+#endif
+	int			sysctl_snat_reroute;
+	int			sysctl_sync_ver;
+	int			sysctl_cache_bypass;
+	int			sysctl_expire_nodest_conn;
+	int			sysctl_expire_quiescent_template;
+	int			sysctl_sync_threshold[2];
+	int			sysctl_nat_icmp_send;
+
+	/* ip_vs_lblc */
+	int			sysctl_lblc_expiration;
+	struct ctl_table_header	*lblc_ctl_header;
+	struct ctl_table	*lblc_ctl_table;
+	/* ip_vs_lblcr */
+	int			sysctl_lblcr_expiration;
+	struct ctl_table_header	*lblcr_ctl_header;
+	struct ctl_table	*lblcr_ctl_table;
+	/* ip_vs_est */
+	struct list_head	est_list;	/* estimator list */
+	spinlock_t		est_lock;
+	struct timer_list	est_timer;	/* Estimation timer */
+	/* ip_vs_sync */
+	struct list_head	sync_queue;
+	spinlock_t		sync_lock;
+	struct ip_vs_sync_buff  *sync_buff;
+	spinlock_t		sync_buff_lock;
+	struct sockaddr_in	sync_mcast_addr;
+	struct task_struct	*master_thread;
+	struct task_struct	*backup_thread;
+	int			send_mesg_maxlen;
+	int			recv_mesg_maxlen;
+	volatile int		sync_state;
+	volatile int		master_syncid;
+	volatile int		backup_syncid;
+	/* multicast interface name */
+	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	/* net name space ptr */
+	struct net		*net;            /* Needed by timer routines */
+};
 
 /*
  *      IPVS core functions
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index b3b4a34cb2cc..3ae491932bc8 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -20,7 +20,6 @@
 #include <net/netns/conntrack.h>
 #endif
 #include <net/netns/xfrm.h>
-#include <net/netns/ip_vs.h>
 
 struct proc_dir_entry;
 struct net_device;
@@ -28,6 +27,7 @@ struct sock;
 struct ctl_table_header;
 struct net_generic;
 struct sock;
+struct netns_ipvs;
 
 
 #define NETDEV_HASHBITS    8
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
deleted file mode 100644
index 259ebac904bf..000000000000
--- a/include/net/netns/ip_vs.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- *  IP Virtual Server
- *  Data structure for network namspace
- *
- */
-
-#ifndef IP_VS_H_
-#define IP_VS_H_
-
-#include <linux/list.h>
-#include <linux/mutex.h>
-#include <linux/list_nulls.h>
-#include <linux/ip_vs.h>
-#include <asm/atomic.h>
-#include <linux/in.h>
-
-struct ip_vs_stats;
-struct ip_vs_sync_buff;
-struct ctl_table_header;
-
-struct netns_ipvs {
-	int			gen;		/* Generation */
-	/*
-	 *	Hash table: for real service lookups
-	 */
-	#define IP_VS_RTAB_BITS 4
-	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
-	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
-
-	struct list_head	rs_table[IP_VS_RTAB_SIZE];
-	/* ip_vs_app */
-	struct list_head	app_list;
-	struct mutex		app_mutex;
-	struct lock_class_key	app_key;	/* mutex debuging */
-
-	/* ip_vs_proto */
-	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
-	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
-	/* ip_vs_proto_tcp */
-#ifdef CONFIG_IP_VS_PROTO_TCP
-	#define	TCP_APP_TAB_BITS	4
-	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
-	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
-	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
-	spinlock_t		tcp_app_lock;
-#endif
-	/* ip_vs_proto_udp */
-#ifdef CONFIG_IP_VS_PROTO_UDP
-	#define	UDP_APP_TAB_BITS	4
-	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
-	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
-	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
-	spinlock_t		udp_app_lock;
-#endif
-	/* ip_vs_proto_sctp */
-#ifdef CONFIG_IP_VS_PROTO_SCTP
-	#define SCTP_APP_TAB_BITS	4
-	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
-	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
-	/* Hash table for SCTP application incarnations	 */
-	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
-	spinlock_t		sctp_app_lock;
-#endif
-	/* ip_vs_conn */
-	atomic_t		conn_count;      /*  connection counter */
-
-	/* ip_vs_ctl */
-	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
-	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
-	seqcount_t			*ustats_seq; /* u64 read retry */
-
-	int			num_services;    /* no of virtual services */
-	/* 1/rate drop and drop-entry variables */
-	struct delayed_work	defense_work;   /* Work handler */
-	int			drop_rate;
-	int			drop_counter;
-	atomic_t		dropentry;
-	/* locks in ctl.c */
-	spinlock_t		dropentry_lock;  /* drop entry handling */
-	spinlock_t		droppacket_lock; /* drop packet handling */
-	spinlock_t		securetcp_lock;  /* state and timeout tables */
-	rwlock_t		rs_lock;         /* real services table */
-	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
-	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
-	/* Trash for destinations */
-	struct list_head	dest_trash;
-	/* Service counters */
-	atomic_t		ftpsvc_counter;
-	atomic_t		nullsvc_counter;
-
-	/* sys-ctl struct */
-	struct ctl_table_header	*sysctl_hdr;
-	struct ctl_table	*sysctl_tbl;
-	/* sysctl variables */
-	int			sysctl_amemthresh;
-	int			sysctl_am_droprate;
-	int			sysctl_drop_entry;
-	int			sysctl_drop_packet;
-	int			sysctl_secure_tcp;
-#ifdef CONFIG_IP_VS_NFCT
-	int			sysctl_conntrack;
-#endif
-	int			sysctl_snat_reroute;
-	int			sysctl_sync_ver;
-	int			sysctl_cache_bypass;
-	int			sysctl_expire_nodest_conn;
-	int			sysctl_expire_quiescent_template;
-	int			sysctl_sync_threshold[2];
-	int			sysctl_nat_icmp_send;
-
-	/* ip_vs_lblc */
-	int			sysctl_lblc_expiration;
-	struct ctl_table_header	*lblc_ctl_header;
-	struct ctl_table	*lblc_ctl_table;
-	/* ip_vs_lblcr */
-	int			sysctl_lblcr_expiration;
-	struct ctl_table_header	*lblcr_ctl_header;
-	struct ctl_table	*lblcr_ctl_table;
-	/* ip_vs_est */
-	struct list_head	est_list;	/* estimator list */
-	spinlock_t		est_lock;
-	struct timer_list	est_timer;	/* Estimation timer */
-	/* ip_vs_sync */
-	struct list_head	sync_queue;
-	spinlock_t		sync_lock;
-	struct ip_vs_sync_buff  *sync_buff;
-	spinlock_t		sync_buff_lock;
-	struct sockaddr_in	sync_mcast_addr;
-	struct task_struct	*master_thread;
-	struct task_struct	*backup_thread;
-	int			send_mesg_maxlen;
-	int			recv_mesg_maxlen;
-	volatile int		sync_state;
-	volatile int		master_syncid;
-	volatile int		backup_syncid;
-	/* multicast interface name */
-	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-	/* net name space ptr */
-	struct net		*net;            /* Needed by timer routines */
-};
-
-#endif /* IP_VS_H_ */
-- 
cgit v1.2.3


From 2a0751af09c3099cf2837c623ca5d0436317d02d Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 4 Mar 2011 12:20:35 +0200
Subject: ipvs: reorganize tot_stats

 	The global tot_stats contains cpustats field just like the
stats for dest and svc, so better use it to simplify the usage
in estimation_timer. As tot_stats is registered as estimator
we can remove the special ip_vs_read_cpu_stats call for
tot_stats. Fix ip_vs_read_cpu_stats to be called under
stats lock because it is still used as synchronization between
estimation timer and user context (the stats readers).

 	Also, make sure ip_vs_stats_percpu_show reads properly
the u64 stats from user context.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  3 +--
 net/netfilter/ipvs/ip_vs_core.c |  6 +++---
 net/netfilter/ipvs/ip_vs_ctl.c  | 45 ++++++++++++++++++++++-------------------
 net/netfilter/ipvs/ip_vs_est.c  |  3 +--
 4 files changed, 29 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 091ca1f76e0e..9db750d9082d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -851,8 +851,7 @@ struct netns_ipvs {
 	atomic_t		conn_count;      /*  connection counter */
 
 	/* ip_vs_ctl */
-	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
-	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
+	struct ip_vs_stats		tot_stats;  /* Statistics & est. */
 	seqcount_t			*ustats_seq; /* u64 read retry */
 
 	int			num_services;    /* no of virtual services */
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 2d1f932add46..6f4940e86fc9 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -132,7 +132,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		s->ustats.inbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 
-		s = this_cpu_ptr(ipvs->cpustats);
+		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
 		s->ustats.inpkts++;
 		u64_stats_update_begin(&s->syncp);
 		s->ustats.inbytes += skb->len;
@@ -162,7 +162,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		s->ustats.outbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 
-		s = this_cpu_ptr(ipvs->cpustats);
+		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
 		s->ustats.outpkts++;
 		u64_stats_update_begin(&s->syncp);
 		s->ustats.outbytes += skb->len;
@@ -183,7 +183,7 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 	s = this_cpu_ptr(svc->stats.cpustats);
 	s->ustats.conns++;
 
-	s = this_cpu_ptr(ipvs->cpustats);
+	s = this_cpu_ptr(ipvs->tot_stats.cpustats);
 	s->ustats.conns++;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index f0369d665088..a2a67ad7e094 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1481,7 +1481,7 @@ static int ip_vs_zero_all(struct net *net)
 		}
 	}
 
-	ip_vs_zero_stats(net_ipvs(net)->tot_stats);
+	ip_vs_zero_stats(&net_ipvs(net)->tot_stats);
 	return 0;
 }
 
@@ -1963,7 +1963,7 @@ static const struct file_operations ip_vs_info_fops = {
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -2007,7 +2007,8 @@ static const struct file_operations ip_vs_stats_fops = {
 static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
+	struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats;
 	int i;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2017,11 +2018,20 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 		   "CPU    Conns  Packets  Packets            Bytes            Bytes\n");
 
 	for_each_possible_cpu(i) {
-		struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i);
+		struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
+		unsigned int start;
+		__u64 inbytes, outbytes;
+
+		do {
+			start = u64_stats_fetch_begin_bh(&u->syncp);
+			inbytes = u->ustats.inbytes;
+			outbytes = u->ustats.outbytes;
+		} while (u64_stats_fetch_retry_bh(&u->syncp, start));
+
 		seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
-			    i, u->ustats.conns, u->ustats.inpkts,
-			    u->ustats.outpkts, (__u64)u->ustats.inbytes,
-			    (__u64)u->ustats.outbytes);
+			   i, u->ustats.conns, u->ustats.inpkts,
+			   u->ustats.outpkts, (__u64)inbytes,
+			   (__u64)outbytes);
 	}
 
 	spin_lock_bh(&tot_stats->lock);
@@ -3505,17 +3515,12 @@ int __net_init __ip_vs_control_init(struct net *net)
 	atomic_set(&ipvs->nullsvc_counter, 0);
 
 	/* procfs stats */
-	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
-	if (ipvs->tot_stats == NULL) {
-		pr_err("%s(): no memory.\n", __func__);
-		return -ENOMEM;
-	}
-	ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!ipvs->cpustats) {
+	ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!ipvs->tot_stats.cpustats) {
 		pr_err("%s() alloc_percpu failed\n", __func__);
 		goto err_alloc;
 	}
-	spin_lock_init(&ipvs->tot_stats->lock);
+	spin_lock_init(&ipvs->tot_stats.lock);
 
 	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
 	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
@@ -3563,7 +3568,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 		goto err_dup;
 	}
 #endif
-	ip_vs_new_estimator(net, ipvs->tot_stats);
+	ip_vs_new_estimator(net, &ipvs->tot_stats);
 	ipvs->sysctl_tbl = tbl;
 	/* Schedule defense work */
 	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@@ -3571,9 +3576,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 	return 0;
 
 err_dup:
-	free_percpu(ipvs->cpustats);
+	free_percpu(ipvs->tot_stats.cpustats);
 err_alloc:
-	kfree(ipvs->tot_stats);
 	return -ENOMEM;
 }
 
@@ -3582,7 +3586,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_kill_estimator(net, ipvs->tot_stats);
+	ip_vs_kill_estimator(net, &ipvs->tot_stats);
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 #ifdef CONFIG_SYSCTL
@@ -3591,8 +3595,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
-	free_percpu(ipvs->cpustats);
-	kfree(ipvs->tot_stats);
+	free_percpu(ipvs->tot_stats.cpustats);
 }
 
 static struct pernet_operations ipvs_control_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 88bd71647bf5..b3751cfede2c 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -101,13 +101,12 @@ static void estimation_timer(unsigned long arg)
 	struct netns_ipvs *ipvs;
 
 	ipvs = net_ipvs(net);
-	ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats);
 	spin_lock(&ipvs->est_lock);
 	list_for_each_entry(e, &ipvs->est_list, list) {
 		s = container_of(e, struct ip_vs_stats, est);
 
-		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
 		spin_lock(&s->lock);
+		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
 		n_conns = s->ustats.conns;
 		n_inpkts = s->ustats.inpkts;
 		n_outpkts = s->ustats.outpkts;
-- 
cgit v1.2.3


From 55a3d4e15c7c953ecc55b96b83d2679abf8a7899 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:37:49 +0200
Subject: ipvs: properly zero stats and rates

 	Currently, the new percpu counters are not zeroed and
the zero commands do not work as expected, we still show the old
sum of percpu values. OTOH, we can not reset the percpu counters
from user context without causing the incrementing to use old
and bogus values.

 	So, as Eric Dumazet suggested fix that by moving all overhead
to stats reading in user context. Do not introduce overhead in
timer context (estimator) and incrementing (packet handling in
softirqs).

 	The new ustats0 field holds the zero point for all
counter values, the rates always use 0 as base value as before.
When showing the values to user space just give the difference
between counters and the base values. The only drawback is that
percpu stats are not zeroed, they are accessible only from /proc
and are new interface, so it should not be a compatibility problem
as long as the sum stats are correct after zeroing.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  1 +
 net/netfilter/ipvs/ip_vs_ctl.c | 96 ++++++++++++++++++++++++++----------------
 net/netfilter/ipvs/ip_vs_est.c | 15 ++++---
 3 files changed, 69 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 9db750d9082d..06f5af4b626d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -374,6 +374,7 @@ struct ip_vs_stats {
 	struct ip_vs_estimator	est;		/* estimator */
 	struct ip_vs_cpu_stats	*cpustats;	/* per cpu counters */
 	spinlock_t		lock;		/* spin lock */
+	struct ip_vs_stats_user	ustats0;	/* reset values */
 };
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a2a67ad7e094..804fee7be694 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -711,13 +711,51 @@ static void ip_vs_trash_cleanup(struct net *net)
 	}
 }
 
+static void
+ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
+{
+#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c
+#define IP_VS_SHOW_STATS_RATE(r) dst->r = src->ustats.r
+
+	spin_lock_bh(&src->lock);
+
+	IP_VS_SHOW_STATS_COUNTER(conns);
+	IP_VS_SHOW_STATS_COUNTER(inpkts);
+	IP_VS_SHOW_STATS_COUNTER(outpkts);
+	IP_VS_SHOW_STATS_COUNTER(inbytes);
+	IP_VS_SHOW_STATS_COUNTER(outbytes);
+
+	IP_VS_SHOW_STATS_RATE(cps);
+	IP_VS_SHOW_STATS_RATE(inpps);
+	IP_VS_SHOW_STATS_RATE(outpps);
+	IP_VS_SHOW_STATS_RATE(inbps);
+	IP_VS_SHOW_STATS_RATE(outbps);
+
+	spin_unlock_bh(&src->lock);
+}
 
 static void
 ip_vs_zero_stats(struct ip_vs_stats *stats)
 {
 	spin_lock_bh(&stats->lock);
 
-	memset(&stats->ustats, 0, sizeof(stats->ustats));
+	/* get current counters as zero point, rates are zeroed */
+
+#define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c
+#define IP_VS_ZERO_STATS_RATE(r) stats->ustats.r = 0
+
+	IP_VS_ZERO_STATS_COUNTER(conns);
+	IP_VS_ZERO_STATS_COUNTER(inpkts);
+	IP_VS_ZERO_STATS_COUNTER(outpkts);
+	IP_VS_ZERO_STATS_COUNTER(inbytes);
+	IP_VS_ZERO_STATS_COUNTER(outbytes);
+
+	IP_VS_ZERO_STATS_RATE(cps);
+	IP_VS_ZERO_STATS_RATE(inpps);
+	IP_VS_ZERO_STATS_RATE(outpps);
+	IP_VS_ZERO_STATS_RATE(inbps);
+	IP_VS_ZERO_STATS_RATE(outbps);
+
 	ip_vs_zero_estimator(stats);
 
 	spin_unlock_bh(&stats->lock);
@@ -1963,7 +2001,7 @@ static const struct file_operations ip_vs_info_fops = {
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
+	struct ip_vs_stats_user show;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -1971,22 +2009,18 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 	seq_printf(seq,
 		   "   Conns  Packets  Packets            Bytes            Bytes\n");
 
-	spin_lock_bh(&tot_stats->lock);
-	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns,
-		   tot_stats->ustats.inpkts, tot_stats->ustats.outpkts,
-		   (unsigned long long) tot_stats->ustats.inbytes,
-		   (unsigned long long) tot_stats->ustats.outbytes);
+	ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
+	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", show.conns,
+		   show.inpkts, show.outpkts,
+		   (unsigned long long) show.inbytes,
+		   (unsigned long long) show.outbytes);
 
 /*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		   " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
-	seq_printf(seq,"%8X %8X %8X %16X %16X\n",
-			tot_stats->ustats.cps,
-			tot_stats->ustats.inpps,
-			tot_stats->ustats.outpps,
-			tot_stats->ustats.inbps,
-			tot_stats->ustats.outbps);
-	spin_unlock_bh(&tot_stats->lock);
+	seq_printf(seq, "%8X %8X %8X %16X %16X\n",
+			show.cps, show.inpps, show.outpps,
+			show.inbps, show.outbps);
 
 	return 0;
 }
@@ -2297,14 +2331,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 }
 
 
-static void
-ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
-{
-	spin_lock_bh(&src->lock);
-	memcpy(dst, &src->ustats, sizeof(*dst));
-	spin_unlock_bh(&src->lock);
-}
-
 static void
 ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 {
@@ -2691,31 +2717,29 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
 				 struct ip_vs_stats *stats)
 {
+	struct ip_vs_stats_user ustats;
 	struct nlattr *nl_stats = nla_nest_start(skb, container_type);
 	if (!nl_stats)
 		return -EMSGSIZE;
 
-	spin_lock_bh(&stats->lock);
-
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, stats->ustats.conns);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, stats->ustats.inpkts);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, stats->ustats.outpkts);
-	NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, stats->ustats.inbytes);
-	NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, stats->ustats.outbytes);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, stats->ustats.cps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, stats->ustats.inpps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, stats->ustats.outpps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, stats->ustats.inbps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, stats->ustats.outbps);
+	ip_vs_copy_stats(&ustats, stats);
 
-	spin_unlock_bh(&stats->lock);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts);
+	NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes);
+	NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, ustats.cps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps);
 
 	nla_nest_end(skb, nl_stats);
 
 	return 0;
 
 nla_put_failure:
-	spin_unlock_bh(&stats->lock);
 	nla_nest_cancel(skb, nl_stats);
 	return -EMSGSIZE;
 }
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index b3751cfede2c..a85008796370 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -184,13 +184,14 @@ void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
 void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 {
 	struct ip_vs_estimator *est = &stats->est;
-
-	/* set counters zero, caller must hold the stats->lock lock */
-	est->last_inbytes = 0;
-	est->last_outbytes = 0;
-	est->last_conns = 0;
-	est->last_inpkts = 0;
-	est->last_outpkts = 0;
+	struct ip_vs_stats_user *u = &stats->ustats;
+
+	/* reset counters, caller must hold the stats->lock lock */
+	est->last_inbytes = u->inbytes;
+	est->last_outbytes = u->outbytes;
+	est->last_conns = u->conns;
+	est->last_inpkts = u->inpkts;
+	est->last_outpkts = u->outpkts;
 	est->cps = 0;
 	est->inpps = 0;
 	est->outpps = 0;
-- 
cgit v1.2.3


From 87d68a15e2d5a6bd08e59ec80c7a5073bcabb7c3 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:39:18 +0200
Subject: ipvs: remove unused seqcount stats

 	Remove ustats_seq, IPVS_STAT_INC and IPVS_STAT_ADD
because they are not used. They were replaced with u64_stats.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 06f5af4b626d..cf014abc23fd 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -377,22 +377,6 @@ struct ip_vs_stats {
 	struct ip_vs_stats_user	ustats0;	/* reset values */
 };
 
-/*
- * Helper Macros for per cpu
- * ipvs->tot_stats->ustats.count
- */
-#define IPVS_STAT_INC(ipvs, count)	\
-	__this_cpu_inc((ipvs)->ustats->count)
-
-#define IPVS_STAT_ADD(ipvs, count, value) \
-	do {\
-		write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \
-				     raw_smp_processor_id())); \
-		__this_cpu_add((ipvs)->ustats->count, value); \
-		write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \
-				   raw_smp_processor_id())); \
-	} while (0)
-
 struct dst_entry;
 struct iphdr;
 struct ip_vs_conn;
@@ -853,7 +837,6 @@ struct netns_ipvs {
 
 	/* ip_vs_ctl */
 	struct ip_vs_stats		tot_stats;  /* Statistics & est. */
-	seqcount_t			*ustats_seq; /* u64 read retry */
 
 	int			num_services;    /* no of virtual services */
 	/* 1/rate drop and drop-entry variables */
-- 
cgit v1.2.3


From ea9f22cce9c2530d659f9122819940b69506b2d9 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:41:54 +0200
Subject: ipvs: optimize rates reading

 	Move the estimator reading from estimation_timer to user
context. ip_vs_read_estimator() will be used to decode the rate
values. As the decoded rates are not set by estimation timer
there is no need to reset them in ip_vs_zero_stats.

 	There is no need ip_vs_new_estimator() to encode stats
to rates, if the destination is in trash both the stats and the
rates are inactive.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  2 ++
 net/netfilter/ipvs/ip_vs_ctl.c | 31 ++++++++++++-------------------
 net/netfilter/ipvs/ip_vs_est.c | 33 +++++++++++++--------------------
 3 files changed, 27 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cf014abc23fd..e4a39c4e263b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1179,6 +1179,8 @@ extern void ip_vs_estimator_cleanup(void);
 extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
 extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
 extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
+extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
+				 struct ip_vs_stats *stats);
 
 /*
  *	Various IPVS packet transmitters (from ip_vs_xmit.c)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 804fee7be694..c93d806e73bd 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -715,7 +715,6 @@ static void
 ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
 {
 #define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c
-#define IP_VS_SHOW_STATS_RATE(r) dst->r = src->ustats.r
 
 	spin_lock_bh(&src->lock);
 
@@ -725,11 +724,7 @@ ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
 	IP_VS_SHOW_STATS_COUNTER(inbytes);
 	IP_VS_SHOW_STATS_COUNTER(outbytes);
 
-	IP_VS_SHOW_STATS_RATE(cps);
-	IP_VS_SHOW_STATS_RATE(inpps);
-	IP_VS_SHOW_STATS_RATE(outpps);
-	IP_VS_SHOW_STATS_RATE(inbps);
-	IP_VS_SHOW_STATS_RATE(outbps);
+	ip_vs_read_estimator(dst, src);
 
 	spin_unlock_bh(&src->lock);
 }
@@ -742,7 +737,6 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
 	/* get current counters as zero point, rates are zeroed */
 
 #define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c
-#define IP_VS_ZERO_STATS_RATE(r) stats->ustats.r = 0
 
 	IP_VS_ZERO_STATS_COUNTER(conns);
 	IP_VS_ZERO_STATS_COUNTER(inpkts);
@@ -750,12 +744,6 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
 	IP_VS_ZERO_STATS_COUNTER(inbytes);
 	IP_VS_ZERO_STATS_COUNTER(outbytes);
 
-	IP_VS_ZERO_STATS_RATE(cps);
-	IP_VS_ZERO_STATS_RATE(inpps);
-	IP_VS_ZERO_STATS_RATE(outpps);
-	IP_VS_ZERO_STATS_RATE(inbps);
-	IP_VS_ZERO_STATS_RATE(outbps);
-
 	ip_vs_zero_estimator(stats);
 
 	spin_unlock_bh(&stats->lock);
@@ -2043,6 +2031,7 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 	struct net *net = seq_file_single_net(seq);
 	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
 	struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats;
+	struct ip_vs_stats_user rates;
 	int i;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2069,22 +2058,26 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 	}
 
 	spin_lock_bh(&tot_stats->lock);
+
 	seq_printf(seq, "  ~ %8X %8X %8X %16LX %16LX\n\n",
 		   tot_stats->ustats.conns, tot_stats->ustats.inpkts,
 		   tot_stats->ustats.outpkts,
 		   (unsigned long long) tot_stats->ustats.inbytes,
 		   (unsigned long long) tot_stats->ustats.outbytes);
 
+	ip_vs_read_estimator(&rates, tot_stats);
+
+	spin_unlock_bh(&tot_stats->lock);
+
 /*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		   "     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
 	seq_printf(seq, "    %8X %8X %8X %16X %16X\n",
-			tot_stats->ustats.cps,
-			tot_stats->ustats.inpps,
-			tot_stats->ustats.outpps,
-			tot_stats->ustats.inbps,
-			tot_stats->ustats.outbps);
-	spin_unlock_bh(&tot_stats->lock);
+			rates.cps,
+			rates.inpps,
+			rates.outpps,
+			rates.inbps,
+			rates.outbps);
 
 	return 0;
 }
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index a85008796370..fda75be231e8 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -117,27 +117,22 @@ static void estimation_timer(unsigned long arg)
 		rate = (n_conns - e->last_conns) << 9;
 		e->last_conns = n_conns;
 		e->cps += ((long)rate - (long)e->cps) >> 2;
-		s->ustats.cps = (e->cps + 0x1FF) >> 10;
 
 		rate = (n_inpkts - e->last_inpkts) << 9;
 		e->last_inpkts = n_inpkts;
 		e->inpps += ((long)rate - (long)e->inpps) >> 2;
-		s->ustats.inpps = (e->inpps + 0x1FF) >> 10;
 
 		rate = (n_outpkts - e->last_outpkts) << 9;
 		e->last_outpkts = n_outpkts;
 		e->outpps += ((long)rate - (long)e->outpps) >> 2;
-		s->ustats.outpps = (e->outpps + 0x1FF) >> 10;
 
 		rate = (n_inbytes - e->last_inbytes) << 4;
 		e->last_inbytes = n_inbytes;
 		e->inbps += ((long)rate - (long)e->inbps) >> 2;
-		s->ustats.inbps = (e->inbps + 0xF) >> 5;
 
 		rate = (n_outbytes - e->last_outbytes) << 4;
 		e->last_outbytes = n_outbytes;
 		e->outbps += ((long)rate - (long)e->outbps) >> 2;
-		s->ustats.outbps = (e->outbps + 0xF) >> 5;
 		spin_unlock(&s->lock);
 	}
 	spin_unlock(&ipvs->est_lock);
@@ -151,21 +146,6 @@ void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 
 	INIT_LIST_HEAD(&est->list);
 
-	est->last_conns = stats->ustats.conns;
-	est->cps = stats->ustats.cps<<10;
-
-	est->last_inpkts = stats->ustats.inpkts;
-	est->inpps = stats->ustats.inpps<<10;
-
-	est->last_outpkts = stats->ustats.outpkts;
-	est->outpps = stats->ustats.outpps<<10;
-
-	est->last_inbytes = stats->ustats.inbytes;
-	est->inbps = stats->ustats.inbps<<5;
-
-	est->last_outbytes = stats->ustats.outbytes;
-	est->outbps = stats->ustats.outbps<<5;
-
 	spin_lock_bh(&ipvs->est_lock);
 	list_add(&est->list, &ipvs->est_list);
 	spin_unlock_bh(&ipvs->est_lock);
@@ -199,6 +179,19 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 	est->outbps = 0;
 }
 
+/* Get decoded rates */
+void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
+			  struct ip_vs_stats *stats)
+{
+	struct ip_vs_estimator *e = &stats->est;
+
+	dst->cps = (e->cps + 0x1FF) >> 10;
+	dst->inpps = (e->inpps + 0x1FF) >> 10;
+	dst->outpps = (e->outpps + 0x1FF) >> 10;
+	dst->inbps = (e->inbps + 0xF) >> 5;
+	dst->outbps = (e->outbps + 0xF) >> 5;
+}
+
 static int __net_init __ip_vs_estimator_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
-- 
cgit v1.2.3


From 6ef757f965c9133e82116475eab7f30df391c7fa Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:44:28 +0200
Subject: ipvs: rename estimator functions

 	Rename ip_vs_new_estimator to ip_vs_start_estimator
and ip_vs_kill_estimator to ip_vs_stop_estimator to better
match their logic.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  4 ++--
 net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++------
 net/netfilter/ipvs/ip_vs_est.c |  4 ++--
 3 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index e4a39c4e263b..7ca5be247256 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1176,8 +1176,8 @@ extern void ip_vs_sync_cleanup(void);
  */
 extern int ip_vs_estimator_init(void);
 extern void ip_vs_estimator_cleanup(void);
-extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
-extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
 extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
 				 struct ip_vs_stats *stats);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c93d806e73bd..c5b1234b630e 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -802,7 +802,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	spin_unlock(&dest->dst_lock);
 
 	if (add)
-		ip_vs_new_estimator(svc->net, &dest->stats);
+		ip_vs_start_estimator(svc->net, &dest->stats);
 
 	write_lock_bh(&__ip_vs_svc_lock);
 
@@ -1008,7 +1008,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	ip_vs_kill_estimator(net, &dest->stats);
+	ip_vs_stop_estimator(net, &dest->stats);
 
 	/*
 	 *  Remove it from the d-linked list with the real services.
@@ -1201,7 +1201,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	else if (svc->port == 0)
 		atomic_inc(&ipvs->nullsvc_counter);
 
-	ip_vs_new_estimator(net, &svc->stats);
+	ip_vs_start_estimator(net, &svc->stats);
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
@@ -1353,7 +1353,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	if (svc->af == AF_INET)
 		ipvs->num_services--;
 
-	ip_vs_kill_estimator(svc->net, &svc->stats);
+	ip_vs_stop_estimator(svc->net, &svc->stats);
 
 	/* Unbind scheduler */
 	old_sched = svc->scheduler;
@@ -3585,7 +3585,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 		goto err_dup;
 	}
 #endif
-	ip_vs_new_estimator(net, &ipvs->tot_stats);
+	ip_vs_start_estimator(net, &ipvs->tot_stats);
 	ipvs->sysctl_tbl = tbl;
 	/* Schedule defense work */
 	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@@ -3603,7 +3603,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_kill_estimator(net, &ipvs->tot_stats);
+	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 #ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index fda75be231e8..8c8766ca56ad 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -139,7 +139,7 @@ static void estimation_timer(unsigned long arg)
 	mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
 }
 
-void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
+void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
@@ -151,7 +151,7 @@ void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 	spin_unlock_bh(&ipvs->est_lock);
 }
 
-void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
+void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
-- 
cgit v1.2.3


From 59e0350eada0516a810cb780db37746165f1d516 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add {sysctl_sync_threshold,period}()

In preparation for not including sysctl_sync_threshold in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 29 +++++++++++++++++++++++++++++
 net/netfilter/ipvs/ip_vs_core.c | 10 +++++-----
 net/netfilter/ipvs/ip_vs_ctl.c  |  4 ++--
 net/netfilter/ipvs/ip_vs_sync.c |  4 ++--
 4 files changed, 38 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7ca5be247256..253736db476b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -909,6 +909,35 @@ struct netns_ipvs {
 	struct net		*net;            /* Needed by timer routines */
 };
 
+#define DEFAULT_SYNC_THRESHOLD	3
+#define DEFAULT_SYNC_PERIOD	50
+
+#ifdef CONFIG_SYSCTL
+
+static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_threshold[0];
+}
+
+static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_threshold[1];
+}
+
+#else
+
+static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_THRESHOLD;
+}
+
+static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_PERIOD;
+}
+
+#endif
+
 /*
  *      IPVS core functions
  *      (from ip_vs_core.c)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index c9b83728f3ce..6a0053d91741 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1613,15 +1613,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 */
 
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
-		pkts = ipvs->sysctl_sync_threshold[0];
+		pkts = sysctl_sync_threshold(ipvs);
 	else
 		pkts = atomic_add_return(1, &cp->in_pkts);
 
 	if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
-			(pkts % ipvs->sysctl_sync_threshold[1]
-			 == ipvs->sysctl_sync_threshold[0])) ||
+			(pkts % sysctl_sync_period(ipvs)
+			 == sysctl_sync_threshold(ipvs))) ||
 				(cp->old_state != cp->state &&
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
@@ -1635,8 +1635,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
-	      (pkts % ipvs->sysctl_sync_threshold[1]
-	       == ipvs->sysctl_sync_threshold[0])) ||
+	      (pkts % sysctl_sync_period(ipvs)
+	       == sysctl_sync_threshold(ipvs))) ||
 	     ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
 	      ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE) ||
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c5b1234b630e..364520f66b7a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3569,8 +3569,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 	tbl[idx++].data = &ipvs->sysctl_cache_bypass;
 	tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
 	tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
-	ipvs->sysctl_sync_threshold[0] = 3;
-	ipvs->sysctl_sync_threshold[1] = 50;
+	ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
+	ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
 	tbl[idx].data = &ipvs->sysctl_sync_threshold;
 	tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
 	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c5d13b05275a..e84987fa1bf8 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -650,7 +650,7 @@ control:
 	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
 		int pkts = atomic_add_return(1, &cp->in_pkts);
 
-		if (pkts % ipvs->sysctl_sync_threshold[1] != 1)
+		if (pkts % sysctl_sync_period(ipvs) != 1)
 			return;
 	}
 	goto sloop;
@@ -794,7 +794,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 
 	if (opt)
 		memcpy(&cp->in_seq, opt, sizeof(*opt));
-	atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]);
+	atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs));
 	cp->state = state;
 	cp->old_state = cp->state;
 	/*
-- 
cgit v1.2.3


From 7532e8d40ccfdde6667169eeac4fd7778d6eb462 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add sysctl_sync_ver()

In preparation for not including sysctl_sync_ver in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 11 +++++++++++
 net/netfilter/ipvs/ip_vs_sync.c |  4 ++--
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 253736db476b..687ef18227cd 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -911,6 +911,7 @@ struct netns_ipvs {
 
 #define DEFAULT_SYNC_THRESHOLD	3
 #define DEFAULT_SYNC_PERIOD	50
+#define DEFAULT_SYNC_VER	1
 
 #ifdef CONFIG_SYSCTL
 
@@ -924,6 +925,11 @@ static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 	return ipvs->sysctl_sync_threshold[1];
 }
 
+static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_sync_ver;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -936,6 +942,11 @@ static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
 	return DEFAULT_SYNC_PERIOD;
 }
 
+static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
+{
+	return DEFAULT_SYNC_VER;
+}
+
 #endif
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index e84987fa1bf8..3e7961e85e9c 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -394,7 +394,7 @@ void ip_vs_sync_switch_mode(struct net *net, int mode)
 
 	if (!(ipvs->sync_state & IP_VS_STATE_MASTER))
 		return;
-	if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff)
+	if (mode == sysctl_sync_ver(ipvs) || !ipvs->sync_buff)
 		return;
 
 	spin_lock_bh(&ipvs->sync_buff_lock);
@@ -521,7 +521,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
 	unsigned int len, pe_name_len, pad;
 
 	/* Handle old version of the protocol */
-	if (ipvs->sysctl_sync_ver == 0) {
+	if (sysctl_sync_ver(ipvs) == 0) {
 		ip_vs_sync_conn_v0(net, cp);
 		return;
 	}
-- 
cgit v1.2.3


From 3a1bbf1885e94ecedf1deaaab1ace8409330aa7e Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:02 +0900
Subject: IPVS: ip_vs_todrop() becomes a noop when CONFIG_SYSCTL is undefined

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 687ef18227cd..77ebece7e68c 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1253,6 +1253,7 @@ extern int ip_vs_icmp_xmit_v6
  int offset);
 #endif
 
+#ifdef CONFIG_SYSCTL
 /*
  *	This is a simple mechanism to ignore packets when
  *	we are loaded. Just set ip_vs_drop_rate to 'n' and
@@ -1268,6 +1269,9 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 	ipvs->drop_counter = ipvs->drop_rate;
 	return 1;
 }
+#else
+static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
+#endif
 
 /*
  *      ip_vs_fwd_tag returns the forwarding tag of the connection
-- 
cgit v1.2.3


From a4e2f5a700cb93448b2da0e158149d18dc5290ef Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:02 +0900
Subject: IPVS: Conditional ip_vs_conntrack_enabled()

ip_vs_conntrack_enabled() becomes a noop when CONFIG_SYSCTL is undefined.

In preparation for not including sysctl_conntrack in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 77ebece7e68c..299aeb537899 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1359,7 +1359,11 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
  */
 static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
+#ifdef CONFIG_SYSCTL
 	return ipvs->sysctl_conntrack;
+#else
+	return 0;
+#endif
 }
 
 extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
-- 
cgit v1.2.3


From f2247fbdc41372d64c89505280419ceb45d80a31 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:02 +0900
Subject: IPVS: Conditionally include sysctl members of struct netns_ipvs

There is now no need to include sysctl members of struct netns_ipvs
unless CONFIG_SYSCTL is defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 299aeb537899..272f59336b73 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -839,6 +839,17 @@ struct netns_ipvs {
 	struct ip_vs_stats		tot_stats;  /* Statistics & est. */
 
 	int			num_services;    /* no of virtual services */
+
+	rwlock_t		rs_lock;         /* real services table */
+	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
+	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* Trash for destinations */
+	struct list_head	dest_trash;
+	/* Service counters */
+	atomic_t		ftpsvc_counter;
+	atomic_t		nullsvc_counter;
+
+#ifdef CONFIG_SYSCTL
 	/* 1/rate drop and drop-entry variables */
 	struct delayed_work	defense_work;   /* Work handler */
 	int			drop_rate;
@@ -848,18 +859,12 @@ struct netns_ipvs {
 	spinlock_t		dropentry_lock;  /* drop entry handling */
 	spinlock_t		droppacket_lock; /* drop packet handling */
 	spinlock_t		securetcp_lock;  /* state and timeout tables */
-	rwlock_t		rs_lock;         /* real services table */
-	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
-	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
-	/* Trash for destinations */
-	struct list_head	dest_trash;
-	/* Service counters */
-	atomic_t		ftpsvc_counter;
-	atomic_t		nullsvc_counter;
 
 	/* sys-ctl struct */
 	struct ctl_table_header	*sysctl_hdr;
 	struct ctl_table	*sysctl_tbl;
+#endif
+
 	/* sysctl variables */
 	int			sysctl_amemthresh;
 	int			sysctl_am_droprate;
-- 
cgit v1.2.3


From 990d6c2d7aee921e3bce22b2d6a750fd552262be Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sat, 29 Jan 2011 18:43:26 +0530
Subject: vfs: Add name to file handle conversion support

The syscall also return mount id which can be used
to lookup file system specific information such as uuid
in /proc/<pid>/mountinfo

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/Kconfig               |   2 +-
 fs/Makefile              |   2 +
 fs/fhandle.c             | 107 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/exportfs.h |   3 ++
 include/linux/fs.h       |   7 ++++
 include/linux/syscalls.h |   5 ++-
 init/Kconfig             |  12 ++++++
 kernel/sys_ni.c          |   3 ++
 8 files changed, 139 insertions(+), 2 deletions(-)
 create mode 100644 fs/fhandle.c

(limited to 'include')

diff --git a/fs/Kconfig b/fs/Kconfig
index 3db9caa57edc..7cb53aafac1e 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -47,7 +47,7 @@ config FS_POSIX_ACL
 	def_bool n
 
 config EXPORTFS
-	tristate
+	bool
 
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
diff --git a/fs/Makefile b/fs/Makefile
index a7f7cef0c0c8..ba01202844c5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -48,6 +48,8 @@ obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o xattr_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
 obj-$(CONFIG_GENERIC_ACL)	+= generic_acl.o
 
+obj-$(CONFIG_FHANDLE)		+= fhandle.o
+
 obj-y				+= quota/
 
 obj-$(CONFIG_PROC_FS)		+= proc/
diff --git a/fs/fhandle.c b/fs/fhandle.c
new file mode 100644
index 000000000000..9f79e743a840
--- /dev/null
+++ b/fs/fhandle.c
@@ -0,0 +1,107 @@
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/exportfs.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static long do_sys_name_to_handle(struct path *path,
+				  struct file_handle __user *ufh,
+				  int __user *mnt_id)
+{
+	long retval;
+	struct file_handle f_handle;
+	int handle_dwords, handle_bytes;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * We need t make sure wether the file system
+	 * support decoding of the file handle
+	 */
+	if (!path->mnt->mnt_sb->s_export_op ||
+	    !path->mnt->mnt_sb->s_export_op->fh_to_dentry)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
+		return -EFAULT;
+
+	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
+		return -EINVAL;
+
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	/* convert handle size to  multiple of sizeof(u32) */
+	handle_dwords = f_handle.handle_bytes >> 2;
+
+	/* we ask for a non connected handle */
+	retval = exportfs_encode_fh(path->dentry,
+				    (struct fid *)handle->f_handle,
+				    &handle_dwords,  0);
+	handle->handle_type = retval;
+	/* convert handle size to bytes */
+	handle_bytes = handle_dwords * sizeof(u32);
+	handle->handle_bytes = handle_bytes;
+	if ((handle->handle_bytes > f_handle.handle_bytes) ||
+	    (retval == 255) || (retval == -ENOSPC)) {
+		/* As per old exportfs_encode_fh documentation
+		 * we could return ENOSPC to indicate overflow
+		 * But file system returned 255 always. So handle
+		 * both the values
+		 */
+		/*
+		 * set the handle size to zero so we copy only
+		 * non variable part of the file_handle
+		 */
+		handle_bytes = 0;
+		retval = -EOVERFLOW;
+	} else
+		retval = 0;
+	/* copy the mount id */
+	if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) ||
+	    copy_to_user(ufh, handle,
+			 sizeof(struct file_handle) + handle_bytes))
+		retval = -EFAULT;
+	kfree(handle);
+	return retval;
+}
+
+/**
+ * sys_name_to_handle_at: convert name to handle
+ * @dfd: directory relative to which name is interpreted if not absolute
+ * @name: name that should be converted to handle.
+ * @handle: resulting file handle
+ * @mnt_id: mount id of the file system containing the file
+ * @flag: flag value to indicate whether to follow symlink or not
+ *
+ * @handle->handle_size indicate the space available to store the
+ * variable part of the file handle in bytes. If there is not
+ * enough space, the field is updated to return the minimum
+ * value required.
+ */
+SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
+		struct file_handle __user *, handle, int __user *, mnt_id,
+		int, flag)
+{
+	struct path path;
+	int lookup_flags;
+	int err;
+
+	if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
+	if (flag & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+	err = user_path_at(dfd, name, lookup_flags, &path);
+	if (!err) {
+		err = do_sys_name_to_handle(&path, handle, mnt_id);
+		path_put(&path);
+	}
+	return err;
+}
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 65afdfd31b7b..33a42f24b275 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -8,6 +8,9 @@ struct inode;
 struct super_block;
 struct vfsmount;
 
+/* limit the handle size to NFSv4 handle size now */
+#define MAX_HANDLE_SZ 128
+
 /*
  * The fileid_type identifies how the file within the filesystem is encoded.
  * In theory this is freely set and parsed by the filesystem, but we try to
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b7178b05cf3a..3f64630c0e10 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -978,6 +978,13 @@ struct file {
 #endif
 };
 
+struct file_handle {
+	__u32 handle_bytes;
+	int handle_type;
+	/* file identifier */
+	unsigned char f_handle[0];
+};
+
 #define get_file(x)	atomic_long_inc(&(x)->f_count)
 #define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 98664db1be47..970112613fb4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -62,6 +62,7 @@ struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
+struct file_handle;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -832,5 +833,7 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len,
 			unsigned long prot, unsigned long flags,
 			unsigned long fd, unsigned long pgoff);
 asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
-
+asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
+				      struct file_handle __user *handle,
+				      int __user *mnt_id, int flag);
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index be788c0957d4..e72fa17fe559 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -287,6 +287,18 @@ config BSD_PROCESS_ACCT_V3
 	  for processing it. A preliminary version of these tools is available
 	  at <http://www.gnu.org/software/acct/>.
 
+config FHANDLE
+	bool "open by fhandle syscalls"
+	select EXPORTFS
+	help
+	  If you say Y here, a user level program will be able to map
+	  file names to handle and then later use the handle for
+	  different file system operations. This is useful in implementing
+	  userspace file servers, which now track files using handles instead
+	  of names. The handle would remain the same even if file names
+	  get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+	  syscalls.
+
 config TASKSTATS
 	bool "Export task/process statistics through netlink (EXPERIMENTAL)"
 	depends on NET
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c782fe9924c7..4e013439ac28 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -186,3 +186,6 @@ cond_syscall(sys_perf_event_open);
 /* fanotify! */
 cond_syscall(sys_fanotify_init);
 cond_syscall(sys_fanotify_mark);
+
+/* open by handle */
+cond_syscall(sys_name_to_handle_at);
-- 
cgit v1.2.3


From becfd1f37544798cbdfd788f32c827160fab98c1 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sat, 29 Jan 2011 18:43:26 +0530
Subject: vfs: Add open by file handle support

[AV: duplicate of open() guts removed; file_open_root() used instead]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/compat.c              |  13 ++++
 fs/exportfs/expfs.c      |   2 +
 fs/fhandle.c             | 158 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/internal.h            |   3 +
 include/linux/syscalls.h |   3 +
 kernel/sys_ni.c          |   2 +
 6 files changed, 181 insertions(+)

(limited to 'include')

diff --git a/fs/compat.c b/fs/compat.c
index a071775f3bb3..c6d31a3bab88 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -2284,3 +2284,16 @@ asmlinkage long compat_sys_timerfd_gettime(int ufd,
 }
 
 #endif /* CONFIG_TIMERFD */
+
+#ifdef CONFIG_FHANDLE
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+asmlinkage long
+compat_sys_open_by_handle_at(int mountdirfd,
+			     struct file_handle __user *handle, int flags)
+{
+	return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index cfe55731b6dc..b05acb796135 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -374,6 +374,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	/*
 	 * Try to get any dentry for the given file handle from the filesystem.
 	 */
+	if (!nop || !nop->fh_to_dentry)
+		return ERR_PTR(-ESTALE);
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
 	if (!result)
 		result = ERR_PTR(-ESTALE);
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 9f79e743a840..bf93ad2bee07 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -5,6 +5,8 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/exportfs.h>
+#include <linux/fs_struct.h>
+#include <linux/fsnotify.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -105,3 +107,159 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 	}
 	return err;
 }
+
+static struct vfsmount *get_vfsmount_from_fd(int fd)
+{
+	struct path path;
+
+	if (fd == AT_FDCWD) {
+		struct fs_struct *fs = current->fs;
+		spin_lock(&fs->lock);
+		path = fs->pwd;
+		mntget(path.mnt);
+		spin_unlock(&fs->lock);
+	} else {
+		int fput_needed;
+		struct file *file = fget_light(fd, &fput_needed);
+		if (!file)
+			return ERR_PTR(-EBADF);
+		path = file->f_path;
+		mntget(path.mnt);
+		fput_light(file, fput_needed);
+	}
+	return path.mnt;
+}
+
+static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
+{
+	return 1;
+}
+
+static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
+			     struct path *path)
+{
+	int retval = 0;
+	int handle_dwords;
+
+	path->mnt = get_vfsmount_from_fd(mountdirfd);
+	if (IS_ERR(path->mnt)) {
+		retval = PTR_ERR(path->mnt);
+		goto out_err;
+	}
+	/* change the handle size to multiple of sizeof(u32) */
+	handle_dwords = handle->handle_bytes >> 2;
+	path->dentry = exportfs_decode_fh(path->mnt,
+					  (struct fid *)handle->f_handle,
+					  handle_dwords, handle->handle_type,
+					  vfs_dentry_acceptable, NULL);
+	if (IS_ERR(path->dentry)) {
+		retval = PTR_ERR(path->dentry);
+		goto out_mnt;
+	}
+	return 0;
+out_mnt:
+	mntput(path->mnt);
+out_err:
+	return retval;
+}
+
+static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
+		   struct path *path)
+{
+	int retval = 0;
+	struct file_handle f_handle;
+	struct file_handle *handle = NULL;
+
+	/*
+	 * With handle we don't look at the execute bit on the
+	 * the directory. Ideally we would like CAP_DAC_SEARCH.
+	 * But we don't have that
+	 */
+	if (!capable(CAP_DAC_READ_SEARCH)) {
+		retval = -EPERM;
+		goto out_err;
+	}
+	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
+		retval = -EFAULT;
+		goto out_err;
+	}
+	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
+	    (f_handle.handle_bytes == 0)) {
+		retval = -EINVAL;
+		goto out_err;
+	}
+	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+			 GFP_KERNEL);
+	if (!handle) {
+		retval = -ENOMEM;
+		goto out_err;
+	}
+	/* copy the full handle */
+	if (copy_from_user(handle, ufh,
+			   sizeof(struct file_handle) +
+			   f_handle.handle_bytes)) {
+		retval = -EFAULT;
+		goto out_handle;
+	}
+
+	retval = do_handle_to_path(mountdirfd, handle, path);
+
+out_handle:
+	kfree(handle);
+out_err:
+	return retval;
+}
+
+long do_handle_open(int mountdirfd,
+		    struct file_handle __user *ufh, int open_flag)
+{
+	long retval = 0;
+	struct path path;
+	struct file *file;
+	int fd;
+
+	retval = handle_to_path(mountdirfd, ufh, &path);
+	if (retval)
+		return retval;
+
+	fd = get_unused_fd_flags(open_flag);
+	if (fd < 0) {
+		path_put(&path);
+		return fd;
+	}
+	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		retval =  PTR_ERR(file);
+	} else {
+		retval = fd;
+		fsnotify_open(file);
+		fd_install(fd, file);
+	}
+	path_put(&path);
+	return retval;
+}
+
+/**
+ * sys_open_by_handle_at: Open the file handle
+ * @mountdirfd: directory file descriptor
+ * @handle: file handle to be opened
+ * @flag: open flags.
+ *
+ * @mountdirfd indicate the directory file descriptor
+ * of the mount point. file handle is decoded relative
+ * to the vfsmount pointed by the @mountdirfd. @flags
+ * value is same as the open(2) flags.
+ */
+SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+		struct file_handle __user *, handle,
+		int, flags)
+{
+	long ret;
+
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
+
+	ret = do_handle_open(mountdirfd, handle, flags);
+	return ret;
+}
diff --git a/fs/internal.h b/fs/internal.h
index 52abc5287f50..f3d15de44b15 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -117,6 +117,9 @@ extern struct file *do_filp_open(int dfd, const char *pathname,
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *, int lookup_flags);
 
+extern long do_handle_open(int mountdirfd,
+			   struct file_handle __user *ufh, int open_flag);
+
 /*
  * inode.c
  */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 970112613fb4..2d9b79c0f224 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -836,4 +836,7 @@ asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
 asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
 				      struct file_handle __user *handle,
 				      int __user *mnt_id, int flag);
+asmlinkage long sys_open_by_handle_at(int mountdirfd,
+				      struct file_handle __user *handle,
+				      int flags);
 #endif
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 4e013439ac28..25cc41cd8f33 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -189,3 +189,5 @@ cond_syscall(sys_fanotify_mark);
 
 /* open by handle */
 cond_syscall(sys_name_to_handle_at);
+cond_syscall(sys_open_by_handle_at);
+cond_syscall(compat_sys_open_by_handle_at);
-- 
cgit v1.2.3


From a51571ccb8be1b88aea502ebba8350519682c16d Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sat, 29 Jan 2011 18:43:38 +0530
Subject: unistd.h: Add new syscalls numbers to asm-generic

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/asm-generic/unistd.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index b969770196c2..57af0338d270 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -646,9 +646,13 @@ __SYSCALL(__NR_prlimit64, sys_prlimit64)
 __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 #define __NR_fanotify_mark 263
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at		264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at		265
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
 
 #undef __NR_syscalls
-#define __NR_syscalls 264
+#define __NR_syscalls 266
 
 /*
  * All syscalls below here should go away really,
-- 
cgit v1.2.3


From 93f1c20bc8cdb757be50566eff88d65c3b26881f Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sat, 29 Jan 2011 18:43:38 +0530
Subject: vfs: Export file system uuid via /proc/<pid>/mountinfo

We add a per superblock uuid field. File systems should
update the uuid in the fill_super callback

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c     | 16 ++++++++++++++++
 include/linux/fs.h |  1 +
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index d1edf26025dc..dffe6f49ab93 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1002,6 +1002,18 @@ const struct seq_operations mounts_op = {
 	.show	= show_vfsmnt
 };
 
+static int uuid_is_nil(u8 *uuid)
+{
+	int i;
+	u8  *cp = (u8 *)uuid;
+
+	for (i = 0; i < 16; i++) {
+		if (*cp++)
+			return 0;
+	}
+	return 1;
+}
+
 static int show_mountinfo(struct seq_file *m, void *v)
 {
 	struct proc_mounts *p = m->private;
@@ -1040,6 +1052,10 @@ static int show_mountinfo(struct seq_file *m, void *v)
 	if (IS_MNT_UNBINDABLE(mnt))
 		seq_puts(m, " unbindable");
 
+	if (!uuid_is_nil(mnt->mnt_sb->s_uuid))
+		/* print the uuid */
+		seq_printf(m, " uuid:%pU", mnt->mnt_sb->s_uuid);
+
 	/* Filesystem specific data */
 	seq_puts(m, " - ");
 	show_type(m, sb);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f64630c0e10..f2143e0942c2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1408,6 +1408,7 @@ struct super_block {
 	wait_queue_head_t	s_wait_unfrozen;
 
 	char s_id[32];				/* Informational name */
+	u8 s_uuid[16];				/* UUID */
 
 	void 			*s_fs_info;	/* Filesystem private info */
 	fmode_t			s_mode;
-- 
cgit v1.2.3


From 1abf0c718f15a56a0a435588d1b104c7a37dc9bd Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 13 Mar 2011 03:51:11 -0400
Subject: New kind of open files - "location only".

New flag for open(2) - O_PATH.  Semantics:
	* pathname is resolved, but the file itself is _NOT_ opened
as far as filesystem is concerned.
	* almost all operations on the resulting descriptors shall
fail with -EBADF.  Exceptions are:
	1) operations on descriptors themselves (i.e.
		close(), dup(), dup2(), dup3(), fcntl(fd, F_DUPFD),
		fcntl(fd, F_DUPFD_CLOEXEC, ...), fcntl(fd, F_GETFD),
		fcntl(fd, F_SETFD, ...))
	2) fcntl(fd, F_GETFL), for a common non-destructive way to
		check if descriptor is open
	3) "dfd" arguments of ...at(2) syscalls, i.e. the starting
		points of pathname resolution
	* closing such descriptor does *NOT* affect dnotify or
posix locks.
	* permissions are checked as usual along the way to file;
no permission checks are applied to the file itself.  Of course,
giving such thing to syscall will result in permission checks (at
the moment it means checking that starting point of ....at() is
a directory and caller has exec permissions on it).

fget() and fget_light() return NULL on such descriptors; use of
fget_raw() and fget_raw_light() is needed to get them.  That protects
existing code from dealing with those things.

There are two things still missing (they come in the next commits):
one is handling of symlinks (right now we refuse to open them that
way; see the next commit for semantics related to those) and another
is descriptor passing via SCM_RIGHTS datagrams.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/fcntl.c                  | 37 ++++++++++++++++++++++++++-----
 fs/file_table.c             | 53 ++++++++++++++++++++++++++++++++++++++++-----
 fs/namei.c                  |  2 +-
 fs/open.c                   | 35 +++++++++++++++++++++++++-----
 include/asm-generic/fcntl.h |  4 ++++
 include/linux/file.h        |  2 ++
 include/linux/fs.h          |  3 +++
 7 files changed, 119 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/fcntl.c b/fs/fcntl.c
index cb1026181bdc..6c82e5bac039 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -131,7 +131,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 SYSCALL_DEFINE1(dup, unsigned int, fildes)
 {
 	int ret = -EBADF;
-	struct file *file = fget(fildes);
+	struct file *file = fget_raw(fildes);
 
 	if (file) {
 		ret = get_unused_fd();
@@ -426,15 +426,35 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	return err;
 }
 
+static int check_fcntl_cmd(unsigned cmd)
+{
+	switch (cmd) {
+	case F_DUPFD:
+	case F_DUPFD_CLOEXEC:
+	case F_GETFD:
+	case F_SETFD:
+	case F_GETFL:
+		return 1;
+	}
+	return 0;
+}
+
 SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {	
 	struct file *filp;
 	long err = -EBADF;
 
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -456,10 +476,17 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	long err;
 
 	err = -EBADF;
-	filp = fget(fd);
+	filp = fget_raw(fd);
 	if (!filp)
 		goto out;
 
+	if (unlikely(filp->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd)) {
+			fput(filp);
+			goto out;
+		}
+	}
+
 	err = security_file_fcntl(filp, cmd, arg);
 	if (err) {
 		fput(filp);
@@ -808,14 +835,14 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(18 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC
+		__FMODE_EXEC	| O_PATH
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/file_table.c b/fs/file_table.c
index eb36b6b17e26..3c16e1ca163e 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,11 +276,10 @@ struct file *fget(unsigned int fd)
 	rcu_read_lock();
 	file = fcheck_files(files, fd);
 	if (file) {
-		if (!atomic_long_inc_not_zero(&file->f_count)) {
-			/* File object ref couldn't be taken */
-			rcu_read_unlock();
-			return NULL;
-		}
+		/* File object ref couldn't be taken */
+		if (file->f_mode & FMODE_PATH ||
+		    !atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
 	}
 	rcu_read_unlock();
 
@@ -289,6 +288,23 @@ struct file *fget(unsigned int fd)
 
 EXPORT_SYMBOL(fget);
 
+struct file *fget_raw(unsigned int fd)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file) {
+		/* File object ref couldn't be taken */
+		if (!atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
+	}
+	rcu_read_unlock();
+
+	return file;
+}
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
@@ -310,6 +326,33 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 	struct file *file;
 	struct files_struct *files = current->files;
 
+	*fput_needed = 0;
+	if (atomic_read(&files->count) == 1) {
+		file = fcheck_files(files, fd);
+		if (file && (file->f_mode & FMODE_PATH))
+			file = NULL;
+	} else {
+		rcu_read_lock();
+		file = fcheck_files(files, fd);
+		if (file) {
+			if (!(file->f_mode & FMODE_PATH) &&
+			    atomic_long_inc_not_zero(&file->f_count))
+				*fput_needed = 1;
+			else
+				/* Didn't get the reference, someone's freed */
+				file = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return file;
+}
+
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
 	*fput_needed = 0;
 	if (atomic_read(&files->count) == 1) {
 		file = fcheck_files(files, fd);
diff --git a/fs/namei.c b/fs/namei.c
index 33be51a2ddb7..e1d9f90d9776 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1544,7 +1544,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	} else {
 		struct dentry *dentry;
 
-		file = fget_light(dfd, &fput_needed);
+		file = fget_raw_light(dfd, &fput_needed);
 		retval = -EBADF;
 		if (!file)
 			goto out_fail;
diff --git a/fs/open.c b/fs/open.c
index 48afc5c139d2..14a51de01f54 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -669,11 +669,16 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 					int (*open)(struct inode *, struct file *),
 					const struct cred *cred)
 {
+	static const struct file_operations empty_fops = {};
 	struct inode *inode;
 	int error;
 
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
+
+	if (unlikely(f->f_flags & O_PATH))
+		f->f_mode = FMODE_PATH;
+
 	inode = dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
 		error = __get_file_write_access(inode, mnt);
@@ -687,9 +692,15 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	f->f_path.dentry = dentry;
 	f->f_path.mnt = mnt;
 	f->f_pos = 0;
-	f->f_op = fops_get(inode->i_fop);
 	file_sb_list_add(f, inode->i_sb);
 
+	if (unlikely(f->f_mode & FMODE_PATH)) {
+		f->f_op = &empty_fops;
+		return f;
+	}
+
+	f->f_op = fops_get(inode->i_fop);
+
 	error = security_dentry_open(f, cred);
 	if (error)
 		goto cleanup_all;
@@ -911,9 +922,18 @@ static inline int build_open_flags(int flags, int mode, struct open_flags *op)
 	if (flags & __O_SYNC)
 		flags |= O_DSYNC;
 
-	op->open_flag = flags;
+	/*
+	 * If we have O_PATH in the open flag. Then we
+	 * cannot have anything other than the below set of flags
+	 */
+	if (flags & O_PATH) {
+		flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+		acc_mode = 0;
+	} else {
+		acc_mode = MAY_OPEN | ACC_MODE(flags);
+	}
 
-	acc_mode = MAY_OPEN | ACC_MODE(flags);
+	op->open_flag = flags;
 
 	/* O_TRUNC implies we need access checks for write permissions */
 	if (flags & O_TRUNC)
@@ -926,7 +946,8 @@ static inline int build_open_flags(int flags, int mode, struct open_flags *op)
 
 	op->acc_mode = acc_mode;
 
-	op->intent = LOOKUP_OPEN;
+	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
+
 	if (flags & O_CREAT) {
 		op->intent |= LOOKUP_CREATE;
 		if (flags & O_EXCL)
@@ -1053,8 +1074,10 @@ int filp_close(struct file *filp, fl_owner_t id)
 	if (filp->f_op && filp->f_op->flush)
 		retval = filp->f_op->flush(filp, id);
 
-	dnotify_flush(filp, id);
-	locks_remove_posix(filp, id);
+	if (likely(!(filp->f_mode & FMODE_PATH))) {
+		dnotify_flush(filp, id);
+		locks_remove_posix(filp, id);
+	}
 	fput(filp);
 	return retval;
 }
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index 0fc16e3f0bfc..84793c7025e2 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -80,6 +80,10 @@
 #define O_SYNC		(__O_SYNC|O_DSYNC)
 #endif
 
+#ifndef O_PATH
+#define O_PATH		010000000
+#endif
+
 #ifndef O_NDELAY
 #define O_NDELAY	O_NONBLOCK
 #endif
diff --git a/include/linux/file.h b/include/linux/file.h
index e85baebf6279..21a79958541c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -29,6 +29,8 @@ static inline void fput_light(struct file *file, int fput_needed)
 
 extern struct file *fget(unsigned int fd);
 extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern void put_filp(struct file *);
 extern int alloc_fd(unsigned start, unsigned flags);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f2143e0942c2..13df14e2c42e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -102,6 +102,9 @@ struct inodes_stat_t {
 /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
 #define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)
 
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH		((__force fmode_t)0x4000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
 
-- 
cgit v1.2.3


From 4dce8ba94c751dd25f1d9b2d35c04312b046e5d6 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Mon, 14 Mar 2011 08:54:20 +0100
Subject: libata: Use 'bool' return value for ata_id_XXX

Most ata_id_XXX inlines are simple tests, so we should set
the return value to 'bool' here.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
---
 include/linux/ata.h | 156 +++++++++++++++++++++++++---------------------------
 1 file changed, 75 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/include/linux/ata.h b/include/linux/ata.h
index 198e1ea2b2eb..32df2b6ef0e0 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -600,42 +600,42 @@ static inline bool ata_id_has_dipm(const u16 *id)
 }
 
 
-static inline int ata_id_has_fua(const u16 *id)
+static inline bool ata_id_has_fua(const u16 *id)
 {
 	if ((id[ATA_ID_CFSSE] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_CFSSE] & (1 << 6);
 }
 
-static inline int ata_id_has_flush(const u16 *id)
+static inline bool ata_id_has_flush(const u16 *id)
 {
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_COMMAND_SET_2] & (1 << 12);
 }
 
-static inline int ata_id_flush_enabled(const u16 *id)
+static inline bool ata_id_flush_enabled(const u16 *id)
 {
 	if (ata_id_has_flush(id) == 0)
-		return 0;
+		return false;
 	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_CFS_ENABLE_2] & (1 << 12);
 }
 
-static inline int ata_id_has_flush_ext(const u16 *id)
+static inline bool ata_id_has_flush_ext(const u16 *id)
 {
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_COMMAND_SET_2] & (1 << 13);
 }
 
-static inline int ata_id_flush_ext_enabled(const u16 *id)
+static inline bool ata_id_flush_ext_enabled(const u16 *id)
 {
 	if (ata_id_has_flush_ext(id) == 0)
-		return 0;
+		return false;
 	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	/*
 	 * some Maxtor disks have bit 13 defined incorrectly
 	 * so check bit 10 too
@@ -688,64 +688,64 @@ static inline u16 ata_id_logical_sector_offset(const u16 *id,
 	return 0;
 }
 
-static inline int ata_id_has_lba48(const u16 *id)
+static inline bool ata_id_has_lba48(const u16 *id)
 {
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	if (!ata_id_u64(id, ATA_ID_LBA_CAPACITY_2))
-		return 0;
+		return false;
 	return id[ATA_ID_COMMAND_SET_2] & (1 << 10);
 }
 
-static inline int ata_id_lba48_enabled(const u16 *id)
+static inline bool ata_id_lba48_enabled(const u16 *id)
 {
 	if (ata_id_has_lba48(id) == 0)
-		return 0;
+		return false;
 	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_CFS_ENABLE_2] & (1 << 10);
 }
 
-static inline int ata_id_hpa_enabled(const u16 *id)
+static inline bool ata_id_hpa_enabled(const u16 *id)
 {
 	/* Yes children, word 83 valid bits cover word 82 data */
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	/* And 87 covers 85-87 */
 	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	/* Check command sets enabled as well as supported */
 	if ((id[ATA_ID_CFS_ENABLE_1] & (1 << 10)) == 0)
-		return 0;
+		return false;
 	return id[ATA_ID_COMMAND_SET_1] & (1 << 10);
 }
 
-static inline int ata_id_has_wcache(const u16 *id)
+static inline bool ata_id_has_wcache(const u16 *id)
 {
 	/* Yes children, word 83 valid bits cover word 82 data */
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_COMMAND_SET_1] & (1 << 5);
 }
 
-static inline int ata_id_has_pm(const u16 *id)
+static inline bool ata_id_has_pm(const u16 *id)
 {
 	if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_COMMAND_SET_1] & (1 << 3);
 }
 
-static inline int ata_id_rahead_enabled(const u16 *id)
+static inline bool ata_id_rahead_enabled(const u16 *id)
 {
 	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_CFS_ENABLE_1] & (1 << 6);
 }
 
-static inline int ata_id_wcache_enabled(const u16 *id)
+static inline bool ata_id_wcache_enabled(const u16 *id)
 {
 	if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[ATA_ID_CFS_ENABLE_1] & (1 << 5);
 }
 
@@ -775,7 +775,7 @@ static inline unsigned int ata_id_major_version(const u16 *id)
 	return mver;
 }
 
-static inline int ata_id_is_sata(const u16 *id)
+static inline bool ata_id_is_sata(const u16 *id)
 {
 	/*
 	 * See if word 93 is 0 AND drive is at least ATA-5 compatible
@@ -784,37 +784,35 @@ static inline int ata_id_is_sata(const u16 *id)
 	 * 0x0000 and 0xffff along with the earlier ATA revisions...
 	 */
 	if (id[ATA_ID_HW_CONFIG] == 0 && (short)id[ATA_ID_MAJOR_VER] >= 0x0020)
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 
-static inline int ata_id_has_tpm(const u16 *id)
+static inline bool ata_id_has_tpm(const u16 *id)
 {
 	/* The TPM bits are only valid on ATA8 */
 	if (ata_id_major_version(id) < 8)
-		return 0;
+		return false;
 	if ((id[48] & 0xC000) != 0x4000)
-		return 0;
+		return false;
 	return id[48] & (1 << 0);
 }
 
-static inline int ata_id_has_dword_io(const u16 *id)
+static inline bool ata_id_has_dword_io(const u16 *id)
 {
 	/* ATA 8 reuses this flag for "trusted" computing */
 	if (ata_id_major_version(id) > 7)
-		return 0;
-	if (id[ATA_ID_DWORD_IO] & (1 << 0))
-		return 1;
-	return 0;
+		return false;
+	return id[ATA_ID_DWORD_IO] & (1 << 0);
 }
 
-static inline int ata_id_has_unload(const u16 *id)
+static inline bool ata_id_has_unload(const u16 *id)
 {
 	if (ata_id_major_version(id) >= 7 &&
 	    (id[ATA_ID_CFSSE] & 0xC000) == 0x4000 &&
 	    id[ATA_ID_CFSSE] & (1 << 13))
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 
 static inline bool ata_id_has_wwn(const u16 *id)
@@ -850,25 +848,25 @@ static inline int ata_id_rotation_rate(const u16 *id)
 	return val;
 }
 
-static inline int ata_id_has_trim(const u16 *id)
+static inline bool ata_id_has_trim(const u16 *id)
 {
 	if (ata_id_major_version(id) >= 7 &&
 	    (id[ATA_ID_DATA_SET_MGMT] & 1))
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 
-static inline int ata_id_has_zero_after_trim(const u16 *id)
+static inline bool ata_id_has_zero_after_trim(const u16 *id)
 {
 	/* DSM supported, deterministic read, and read zero after trim set */
 	if (ata_id_has_trim(id) &&
 	    (id[ATA_ID_ADDITIONAL_SUPP] & 0x4020) == 0x4020)
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
-static inline int ata_id_current_chs_valid(const u16 *id)
+static inline bool ata_id_current_chs_valid(const u16 *id)
 {
 	/* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command
 	   has not been issued to the device then the values of
@@ -880,11 +878,11 @@ static inline int ata_id_current_chs_valid(const u16 *id)
 		id[ATA_ID_CUR_SECTORS];    /* sectors in current translation */
 }
 
-static inline int ata_id_is_cfa(const u16 *id)
+static inline bool ata_id_is_cfa(const u16 *id)
 {
 	if ((id[ATA_ID_CONFIG] == 0x848A) ||	/* Traditional CF */
 	    (id[ATA_ID_CONFIG] == 0x844A))	/* Delkin Devices CF */
-		return 1;
+		return true;
 	/*
 	 * CF specs don't require specific value in the word 0 anymore and yet
 	 * they forbid to report the ATA version in the word 80 and require the
@@ -893,44 +891,40 @@ static inline int ata_id_is_cfa(const u16 *id)
 	 * and while those that don't indicate CFA feature support need some
 	 * sort of quirk list, it seems impractical for the ones that do...
 	 */
-	if ((id[ATA_ID_COMMAND_SET_2] & 0xC004) == 0x4004)
-		return 1;
-	return 0;
+	return (id[ATA_ID_COMMAND_SET_2] & 0xC004) == 0x4004;
 }
 
-static inline int ata_id_is_ssd(const u16 *id)
+static inline bool ata_id_is_ssd(const u16 *id)
 {
 	return id[ATA_ID_ROT_SPEED] == 0x01;
 }
 
-static inline int ata_id_pio_need_iordy(const u16 *id, const u8 pio)
+static inline bool ata_id_pio_need_iordy(const u16 *id, const u8 pio)
 {
 	/* CF spec. r4.1 Table 22 says no IORDY on PIO5 and PIO6. */
 	if (pio > 4 && ata_id_is_cfa(id))
-		return 0;
+		return false;
 	/* For PIO3 and higher it is mandatory. */
 	if (pio > 2)
-		return 1;
+		return true;
 	/* Turn it on when possible. */
-	if (ata_id_has_iordy(id))
-		return 1;
-	return 0;
+	return ata_id_has_iordy(id);
 }
 
-static inline int ata_drive_40wire(const u16 *dev_id)
+static inline bool ata_drive_40wire(const u16 *dev_id)
 {
 	if (ata_id_is_sata(dev_id))
-		return 0;	/* SATA */
+		return false;	/* SATA */
 	if ((dev_id[ATA_ID_HW_CONFIG] & 0xE000) == 0x6000)
-		return 0;	/* 80 wire */
-	return 1;
+		return false;	/* 80 wire */
+	return true;
 }
 
-static inline int ata_drive_40wire_relaxed(const u16 *dev_id)
+static inline bool ata_drive_40wire_relaxed(const u16 *dev_id)
 {
 	if ((dev_id[ATA_ID_HW_CONFIG] & 0x2000) == 0x2000)
-		return 0;	/* 80 wire */
-	return 1;
+		return false;	/* 80 wire */
+	return true;
 }
 
 static inline int atapi_cdb_len(const u16 *dev_id)
@@ -943,12 +937,12 @@ static inline int atapi_cdb_len(const u16 *dev_id)
 	}
 }
 
-static inline int atapi_command_packet_set(const u16 *dev_id)
+static inline bool atapi_command_packet_set(const u16 *dev_id)
 {
 	return (dev_id[ATA_ID_CONFIG] >> 8) & 0x1f;
 }
 
-static inline int atapi_id_dmadir(const u16 *dev_id)
+static inline bool atapi_id_dmadir(const u16 *dev_id)
 {
 	return ata_id_major_version(dev_id) >= 7 && (dev_id[62] & 0x8000);
 }
@@ -961,13 +955,13 @@ static inline int atapi_id_dmadir(const u16 *dev_id)
  *
  * It is called only once for each device.
  */
-static inline int ata_id_is_lba_capacity_ok(u16 *id)
+static inline bool ata_id_is_lba_capacity_ok(u16 *id)
 {
 	unsigned long lba_sects, chs_sects, head, tail;
 
 	/* No non-LBA info .. so valid! */
 	if (id[ATA_ID_CYLS] == 0)
-		return 1;
+		return true;
 
 	lba_sects = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
 
@@ -982,13 +976,13 @@ static inline int ata_id_is_lba_capacity_ok(u16 *id)
 	    id[ATA_ID_SECTORS] == 63 &&
 	    (id[ATA_ID_HEADS] == 15 || id[ATA_ID_HEADS] == 16) &&
 	    (lba_sects >= 16383 * 63 * id[ATA_ID_HEADS]))
-		return 1;
+		return true;
 
 	chs_sects = id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * id[ATA_ID_SECTORS];
 
 	/* perform a rough sanity check on lba_sects: within 10% is OK */
 	if (lba_sects - chs_sects < chs_sects/10)
-		return 1;
+		return true;
 
 	/* some drives have the word order reversed */
 	head = (lba_sects >> 16) & 0xffff;
@@ -997,10 +991,10 @@ static inline int ata_id_is_lba_capacity_ok(u16 *id)
 
 	if (lba_sects - chs_sects < chs_sects/10) {
 		*(__le32 *)&id[ATA_ID_LBA_CAPACITY] = __cpu_to_le32(lba_sects);
-		return 1;	/* LBA capacity is (now) good */
+		return true;	/* LBA capacity is (now) good */
 	}
 
-	return 0;	/* LBA capacity value may be bad */
+	return false;	/* LBA capacity value may be bad */
 }
 
 static inline void ata_id_to_hd_driveid(u16 *id)
@@ -1058,19 +1052,19 @@ static inline int is_multi_taskfile(struct ata_taskfile *tf)
 	       (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT);
 }
 
-static inline int ata_ok(u8 status)
+static inline bool ata_ok(u8 status)
 {
 	return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR))
 			== ATA_DRDY);
 }
 
-static inline int lba_28_ok(u64 block, u32 n_block)
+static inline bool lba_28_ok(u64 block, u32 n_block)
 {
 	/* check the ending block number: must be LESS THAN 0x0fffffff */
 	return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= 256);
 }
 
-static inline int lba_48_ok(u64 block, u32 n_block)
+static inline bool lba_48_ok(u64 block, u32 n_block)
 {
 	/* check the ending block number */
 	return ((block + n_block - 1) < ((u64)1 << 48)) && (n_block <= 65536);
-- 
cgit v1.2.3


From 022cae36551ba805bf82084047945b2901d75f36 Mon Sep 17 00:00:00 2001
From: "Venkateswararao Jujjuri (JV)" <jvrao@linux.vnet.ibm.com>
Date: Fri, 28 Jan 2011 14:11:13 -0800
Subject: [net/9p] Preparation and helper functions for zero copy

This patch prepares p9_fcall structure for zero copy. Added
fields send the payload buffer information to the transport layer.
In addition it adds a 'private' field for the transport layer to
store mapped/pinned page information so that it can be freed/unpinned
during req_done.

This patch also creates trans_common.[ch] to house helper functions.
It adds the following helper functions.

p9_release_req_pages - Release pages after the transaction.
p9_nr_pages - Return number of pages needed to accomodate the payload.
payload_gup - Translates user buffer into kernel pages.

Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h   |  8 +++++
 net/9p/Makefile       |  1 +
 net/9p/protocol.c     |  4 +++
 net/9p/trans_common.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++++++
 net/9p/trans_common.h | 29 +++++++++++++++
 5 files changed, 139 insertions(+)
 create mode 100644 net/9p/trans_common.c
 create mode 100644 net/9p/trans_common.h

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index 071fd7a8d781..7aefa6d975ac 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -689,6 +689,10 @@ struct p9_rwstat {
  * @tag: transaction id of the request
  * @offset: used by marshalling routines to track currentposition in buffer
  * @capacity: used by marshalling routines to track total capacity
+ * @pubuf: Payload user buffer given by the caller
+ * @pubuf: Payload kernel buffer given by the caller
+ * @pbuf_size: pubuf/pkbuf(only one will be !NULL) size to be read/write.
+ * @private: For transport layer's use.
  * @sdata: payload
  *
  * &p9_fcall represents the structure for all 9P RPC
@@ -705,6 +709,10 @@ struct p9_fcall {
 
 	size_t offset;
 	size_t capacity;
+	char __user *pubuf;
+	char *pkbuf;
+	size_t pbuf_size;
+	void *private;
 
 	uint8_t *sdata;
 };
diff --git a/net/9p/Makefile b/net/9p/Makefile
index 198a640d53a6..a0874cc1f718 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
 	util.o \
 	protocol.o \
 	trans_fd.o \
+	trans_common.o \
 
 9pnet_virtio-objs := \
 	trans_virtio.o \
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 1e308f210928..d888847db56e 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -606,6 +606,10 @@ void p9pdu_reset(struct p9_fcall *pdu)
 {
 	pdu->offset = 0;
 	pdu->size = 0;
+	pdu->private = NULL;
+	pdu->pubuf = NULL;
+	pdu->pkbuf = NULL;
+	pdu->pbuf_size = 0;
 }
 
 int p9dirent_read(char *buf, int len, struct p9_dirent *dirent,
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
new file mode 100644
index 000000000000..d62b9aa58df8
--- /dev/null
+++ b/net/9p/trans_common.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <linux/scatterlist.h>
+#include "trans_common.h"
+
+/**
+ *  p9_release_req_pages - Release pages after the transaction.
+ *  @*private: PDU's private page of struct trans_rpage_info
+ */
+void
+p9_release_req_pages(struct trans_rpage_info *rpinfo)
+{
+	int i = 0;
+
+	while (rpinfo->rp_data[i] && rpinfo->rp_nr_pages--) {
+		put_page(rpinfo->rp_data[i]);
+		i++;
+	}
+}
+EXPORT_SYMBOL(p9_release_req_pages);
+
+/**
+ * p9_nr_pages - Return number of pages needed to accomodate the payload.
+ */
+int
+p9_nr_pages(struct p9_req_t *req)
+{
+	int start_page, end_page;
+	start_page =  (unsigned long long)req->tc->pubuf >> PAGE_SHIFT;
+	end_page = ((unsigned long long)req->tc->pubuf + req->tc->pbuf_size +
+			PAGE_SIZE - 1) >> PAGE_SHIFT;
+	return end_page - start_page;
+}
+EXPORT_SYMBOL(p9_nr_pages);
+
+/**
+ * payload_gup - Translates user buffer into kernel pages and
+ * pins them either for read/write through get_user_pages_fast().
+ * @req: Request to be sent to server.
+ * @pdata_off: data offset into the first page after translation (gup).
+ * @pdata_len: Total length of the IO. gup may not return requested # of pages.
+ * @nr_pages: number of pages to accomodate the payload
+ * @rw: Indicates if the pages are for read or write.
+ */
+int
+p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len,
+		int nr_pages, u8 rw)
+{
+	uint32_t first_page_bytes = 0;
+	uint32_t pdata_mapped_pages;
+	struct trans_rpage_info  *rpinfo;
+
+	*pdata_off = (size_t)req->tc->pubuf & (PAGE_SIZE-1);
+
+	if (*pdata_off)
+		first_page_bytes = min((PAGE_SIZE - *pdata_off),
+				req->tc->pbuf_size);
+
+	rpinfo = req->tc->private;
+	pdata_mapped_pages = get_user_pages_fast((unsigned long)req->tc->pubuf,
+			nr_pages, rw, &rpinfo->rp_data[0]);
+
+	if (pdata_mapped_pages < 0) {
+		printk(KERN_ERR "get_user_pages_fast failed:%d udata:%p"
+				"nr_pages:%d\n", pdata_mapped_pages,
+				req->tc->pubuf, nr_pages);
+		pdata_mapped_pages = 0;
+		return -EIO;
+	}
+	rpinfo->rp_nr_pages = pdata_mapped_pages;
+	if (*pdata_off) {
+		*pdata_len = first_page_bytes;
+		*pdata_len += min((req->tc->pbuf_size - *pdata_len),
+				((size_t)pdata_mapped_pages - 1) << PAGE_SHIFT);
+	} else {
+		*pdata_len = min(req->tc->pbuf_size,
+				(size_t)pdata_mapped_pages << PAGE_SHIFT);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(p9_payload_gup);
diff --git a/net/9p/trans_common.h b/net/9p/trans_common.h
new file mode 100644
index 000000000000..04977e0ad938
--- /dev/null
+++ b/net/9p/trans_common.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+/**
+ * struct trans_rpage_info - To store mapped page information in PDU.
+ * @rp_alloc:Set if this structure is allocd, not a reuse unused space in pdu.
+ * @rp_nr_pages: Number of mapped pages
+ * @rp_data: Array of page pointers
+ */
+struct trans_rpage_info {
+	u8 rp_alloc;
+	int rp_nr_pages;
+	struct page *rp_data[0];
+};
+
+void p9_release_req_pages(struct trans_rpage_info *);
+int p9_payload_gup(struct p9_req_t *, size_t *, int *, int, u8);
+int p9_nr_pages(struct p9_req_t *);
-- 
cgit v1.2.3


From 6f69c395cefb26ebba2c9bb725296a3a4a9200ec Mon Sep 17 00:00:00 2001
From: "Venkateswararao Jujjuri (JV)" <jvrao@linux.vnet.ibm.com>
Date: Sun, 6 Feb 2011 12:08:01 -0800
Subject: [net/9p] Add preferences to transport layer.

This patch adds preferences field to the p9_trans_module.
Through this, now transport layer can express its preference about the
payload. i.e if payload neds to be part of the PDU or it prefers it
to be sent sepearetly so that the transport layer can handle it in
a better way.

Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/transport.h | 9 +++++++++
 net/9p/trans_virtio.c      | 1 +
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 6d5886efb102..82868f18c573 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -26,11 +26,19 @@
 #ifndef NET_9P_TRANSPORT_H
 #define NET_9P_TRANSPORT_H
 
+#define P9_TRANS_PREF_PAYLOAD_MASK 0x1
+
+/* Default. Add Payload to PDU before sending it down to transport layer */
+#define P9_TRANS_PREF_PAYLOAD_DEF  0x0
+/* Send pay load seperately to transport layer along with PDU.*/
+#define P9_TRANS_PREF_PAYLOAD_SEP  0x1
+
 /**
  * struct p9_trans_module - transport module interface
  * @list: used to maintain a list of currently available transports
  * @name: the human-readable name of the transport
  * @maxsize: transport provided maximum packet size
+ * @pref: Preferences of this transport
  * @def: set if this transport should be considered the default
  * @create: member function to create a new connection on this transport
  * @request: member function to issue a request to the transport
@@ -47,6 +55,7 @@ struct p9_trans_module {
 	struct list_head list;
 	char *name;		/* name of transport */
 	int maxsize;		/* max message size of transport */
+	int pref;               /* Preferences of this transport */
 	int def;		/* this transport should be default */
 	struct module *owner;
 	int (*create)(struct p9_client *, const char *, char *);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 4b236de132da..9b550ed9c711 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -566,6 +566,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	.request = p9_virtio_request,
 	.cancel = p9_virtio_cancel,
 	.maxsize = PAGE_SIZE*16,
+	.pref = P9_TRANS_PREF_PAYLOAD_SEP,
 	.def = 0,
 	.owner = THIS_MODULE,
 };
-- 
cgit v1.2.3


From f735195d51e10b2550097f7b0ac12219060e962b Mon Sep 17 00:00:00 2001
From: "Venkateswararao Jujjuri (JV)" <jvrao@linux.vnet.ibm.com>
Date: Wed, 16 Feb 2011 12:54:22 -0800
Subject: [net/9p] Small non-IO PDUs for zero-copy supporting transports.

If a transport prefers payload to be sent separate from the PDU
(P9_TRANS_PREF_PAYLOAD_SEP), there is no need to allocate msize
PDU buffers(struct p9_fcall).

This patch allocates only upto 4k buffers for this kind of transports
and there won't be any change to the legacy transports.

Hence, this patch on top of zero copy changes allows user to
specify higher msizes through the mount option
without hogging the kernel heap.

Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h |  2 +-
 net/9p/client.c     | 23 +++++++++++++++++------
 2 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index 7aefa6d975ac..eaa45f932970 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -688,7 +688,7 @@ struct p9_rwstat {
  * @id: protocol operating identifier of type &p9_msg_t
  * @tag: transaction id of the request
  * @offset: used by marshalling routines to track currentposition in buffer
- * @capacity: used by marshalling routines to track total capacity
+ * @capacity: used by marshalling routines to track total malloc'd capacity
  * @pubuf: Payload user buffer given by the caller
  * @pubuf: Payload kernel buffer given by the caller
  * @pbuf_size: pubuf/pkbuf(only one will be !NULL) size to be read/write.
diff --git a/net/9p/client.c b/net/9p/client.c
index 251abb1699c4..43ec78af4547 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -229,10 +229,23 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 			return ERR_PTR(-ENOMEM);
 		}
 		init_waitqueue_head(req->wq);
-		req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize,
-								GFP_KERNEL);
-		req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize,
-								GFP_KERNEL);
+		if ((c->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) ==
+				P9_TRANS_PREF_PAYLOAD_SEP) {
+			int alloc_msize = min(c->msize, 4096);
+			req->tc = kmalloc(sizeof(struct p9_fcall)+alloc_msize,
+					GFP_KERNEL);
+			req->tc->capacity = alloc_msize;
+			req->rc = kmalloc(sizeof(struct p9_fcall)+alloc_msize,
+					GFP_KERNEL);
+			req->rc->capacity = alloc_msize;
+		} else {
+			req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize,
+					GFP_KERNEL);
+			req->tc->capacity = c->msize;
+			req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize,
+					GFP_KERNEL);
+			req->rc->capacity = c->msize;
+		}
 		if ((!req->tc) || (!req->rc)) {
 			printk(KERN_ERR "Couldn't grow tag array\n");
 			kfree(req->tc);
@@ -243,9 +256,7 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 			return ERR_PTR(-ENOMEM);
 		}
 		req->tc->sdata = (char *) req->tc + sizeof(struct p9_fcall);
-		req->tc->capacity = c->msize;
 		req->rc->sdata = (char *) req->rc + sizeof(struct p9_fcall);
-		req->rc->capacity = c->msize;
 	}
 
 	p9pdu_reset(req->tc);
-- 
cgit v1.2.3


From c0aa4caf4c8b87fa85c67538974a14b07e81a23f Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 28 Feb 2011 17:03:59 +0530
Subject: net/9p: Implement syncfs 9P operation

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h     |  2 ++
 include/net/9p/client.h |  1 +
 net/9p/client.c         | 21 +++++++++++++++++++++
 3 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index eaa45f932970..6b75a6971346 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -139,6 +139,8 @@ do { \
  */
 
 enum p9_msg_t {
+	P9_TSYNCFS = 0,
+	P9_RSYNCFS,
 	P9_TLERROR = 6,
 	P9_RLERROR,
 	P9_TSTATFS = 8,
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 83ba6a4d58a3..0a30977e3c1f 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -230,6 +230,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
 		gid_t gid, struct p9_qid *qid);
 int p9_client_clunk(struct p9_fid *fid);
 int p9_client_fsync(struct p9_fid *fid, int datasync);
+int p9_client_sync_fs(struct p9_fid *fid);
 int p9_client_remove(struct p9_fid *fid);
 int p9_client_read(struct p9_fid *fid, char *data, char __user *udata,
 							u64 offset, u32 count);
diff --git a/net/9p/client.c b/net/9p/client.c
index 43ec78af4547..347ec0cd2718 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1220,6 +1220,27 @@ error:
 }
 EXPORT_SYMBOL(p9_client_fsync);
 
+int p9_client_sync_fs(struct p9_fid *fid)
+{
+	int err = 0;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TSYNC_FS fid %d\n", fid->fid);
+
+	clnt = fid->clnt;
+	req = p9_client_rpc(clnt, P9_TSYNCFS, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RSYNCFS fid %d\n", fid->fid);
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_sync_fs);
+
 int p9_client_clunk(struct p9_fid *fid)
 {
 	int err;
-- 
cgit v1.2.3


From de81bbea17650769882bc625d6b5df11ee7c4b24 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fwestphal@astaro.com>
Date: Tue, 15 Mar 2011 20:16:20 +0100
Subject: netfilter: ipt_addrtype: rename to xt_addrtype

Followup patch will add ipv6 support.

ipt_addrtype.h is retained for compatibility reasons, but no longer used
by the kernel.

Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 Documentation/feature-removal-schedule.txt |   8 ++
 include/linux/netfilter/Kbuild             |   1 +
 include/linux/netfilter/xt_addrtype.h      |  27 ++++++
 net/ipv4/netfilter/Kconfig                 |  10 ---
 net/ipv4/netfilter/Makefile                |   1 -
 net/ipv4/netfilter/ipt_addrtype.c          | 134 ----------------------------
 net/netfilter/Kconfig                      |  10 +++
 net/netfilter/Makefile                     |   1 +
 net/netfilter/xt_addrtype.c                | 135 +++++++++++++++++++++++++++++
 9 files changed, 182 insertions(+), 145 deletions(-)
 create mode 100644 include/linux/netfilter/xt_addrtype.h
 delete mode 100644 net/ipv4/netfilter/ipt_addrtype.c
 create mode 100644 net/netfilter/xt_addrtype.c

(limited to 'include')

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 05b248aa91f1..a7ee7cf5009e 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -618,3 +618,11 @@ Who:	Jan Engelhardt <jengelh@medozas.de>
 Files:	net/netfilter/xt_connlimit.c
 
 ----------------------------
+
+What:	ipt_addrtype match include file
+When:	2012
+Why:	superseded by xt_addrtype
+Who:	Florian Westphal <fw@strlen.de>
+Files:	include/linux/netfilter_ipv4/ipt_addrtype.h
+
+----------------------------
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 15e83bf3dd58..a1b410c76fc3 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -29,6 +29,7 @@ header-y += xt_TCPMSS.h
 header-y += xt_TCPOPTSTRIP.h
 header-y += xt_TEE.h
 header-y += xt_TPROXY.h
+header-y += xt_addrtype.h
 header-y += xt_cluster.h
 header-y += xt_comment.h
 header-y += xt_connbytes.h
diff --git a/include/linux/netfilter/xt_addrtype.h b/include/linux/netfilter/xt_addrtype.h
new file mode 100644
index 000000000000..b492fc84f737
--- /dev/null
+++ b/include/linux/netfilter/xt_addrtype.h
@@ -0,0 +1,27 @@
+#ifndef _XT_ADDRTYPE_H
+#define _XT_ADDRTYPE_H
+
+#include <linux/types.h>
+
+enum {
+	XT_ADDRTYPE_INVERT_SOURCE	= 0x0001,
+	XT_ADDRTYPE_INVERT_DEST		= 0x0002,
+	XT_ADDRTYPE_LIMIT_IFACE_IN	= 0x0004,
+	XT_ADDRTYPE_LIMIT_IFACE_OUT	= 0x0008,
+};
+
+struct xt_addrtype_info_v1 {
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	flags;
+};
+
+/* revision 0 */
+struct xt_addrtype_info {
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	invert_source;
+	__u32	invert_dest;
+};
+
+#endif
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index f926a310075d..1dfc18a03fd4 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -64,16 +64,6 @@ config IP_NF_IPTABLES
 if IP_NF_IPTABLES
 
 # The matches.
-config IP_NF_MATCH_ADDRTYPE
-	tristate '"addrtype" address type match support'
-	depends on NETFILTER_ADVANCED
-	help
-	  This option allows you to match what routing thinks of an address,
-	  eg. UNICAST, LOCAL, BROADCAST, ...
-
-	  If you want to compile it as a module, say M here and read
-	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
-
 config IP_NF_MATCH_AH
 	tristate '"ah" match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 19eb59d01037..dca2082ec683 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -48,7 +48,6 @@ obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o
 obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o
 
 # matches
-obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o
 obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o
 obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o
 
diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c
deleted file mode 100644
index db8bff0fb86d..000000000000
--- a/net/ipv4/netfilter/ipt_addrtype.c
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- *  iptables module to match inet_addr_type() of an ip.
- *
- *  Copyright (c) 2004 Patrick McHardy <kaber@trash.net>
- *  (C) 2007 Laszlo Attila Toth <panther@balabit.hu>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/ip.h>
-#include <net/route.h>
-
-#include <linux/netfilter_ipv4/ipt_addrtype.h>
-#include <linux/netfilter/x_tables.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_DESCRIPTION("Xtables: address type match for IPv4");
-
-static inline bool match_type(struct net *net, const struct net_device *dev,
-			      __be32 addr, u_int16_t mask)
-{
-	return !!(mask & (1 << inet_dev_addr_type(net, dev, addr)));
-}
-
-static bool
-addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
-{
-	struct net *net = dev_net(par->in ? par->in : par->out);
-	const struct ipt_addrtype_info *info = par->matchinfo;
-	const struct iphdr *iph = ip_hdr(skb);
-	bool ret = true;
-
-	if (info->source)
-		ret &= match_type(net, NULL, iph->saddr, info->source) ^
-		       info->invert_source;
-	if (info->dest)
-		ret &= match_type(net, NULL, iph->daddr, info->dest) ^
-		       info->invert_dest;
-
-	return ret;
-}
-
-static bool
-addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
-{
-	struct net *net = dev_net(par->in ? par->in : par->out);
-	const struct ipt_addrtype_info_v1 *info = par->matchinfo;
-	const struct iphdr *iph = ip_hdr(skb);
-	const struct net_device *dev = NULL;
-	bool ret = true;
-
-	if (info->flags & IPT_ADDRTYPE_LIMIT_IFACE_IN)
-		dev = par->in;
-	else if (info->flags & IPT_ADDRTYPE_LIMIT_IFACE_OUT)
-		dev = par->out;
-
-	if (info->source)
-		ret &= match_type(net, dev, iph->saddr, info->source) ^
-		       (info->flags & IPT_ADDRTYPE_INVERT_SOURCE);
-	if (ret && info->dest)
-		ret &= match_type(net, dev, iph->daddr, info->dest) ^
-		       !!(info->flags & IPT_ADDRTYPE_INVERT_DEST);
-	return ret;
-}
-
-static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
-{
-	struct ipt_addrtype_info_v1 *info = par->matchinfo;
-
-	if (info->flags & IPT_ADDRTYPE_LIMIT_IFACE_IN &&
-	    info->flags & IPT_ADDRTYPE_LIMIT_IFACE_OUT) {
-		pr_info("both incoming and outgoing "
-			"interface limitation cannot be selected\n");
-		return -EINVAL;
-	}
-
-	if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) |
-	    (1 << NF_INET_LOCAL_IN)) &&
-	    info->flags & IPT_ADDRTYPE_LIMIT_IFACE_OUT) {
-		pr_info("output interface limitation "
-			"not valid in PREROUTING and INPUT\n");
-		return -EINVAL;
-	}
-
-	if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) |
-	    (1 << NF_INET_LOCAL_OUT)) &&
-	    info->flags & IPT_ADDRTYPE_LIMIT_IFACE_IN) {
-		pr_info("input interface limitation "
-			"not valid in POSTROUTING and OUTPUT\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static struct xt_match addrtype_mt_reg[] __read_mostly = {
-	{
-		.name		= "addrtype",
-		.family		= NFPROTO_IPV4,
-		.match		= addrtype_mt_v0,
-		.matchsize	= sizeof(struct ipt_addrtype_info),
-		.me		= THIS_MODULE
-	},
-	{
-		.name		= "addrtype",
-		.family		= NFPROTO_IPV4,
-		.revision	= 1,
-		.match		= addrtype_mt_v1,
-		.checkentry	= addrtype_mt_checkentry_v1,
-		.matchsize	= sizeof(struct ipt_addrtype_info_v1),
-		.me		= THIS_MODULE
-	}
-};
-
-static int __init addrtype_mt_init(void)
-{
-	return xt_register_matches(addrtype_mt_reg,
-				   ARRAY_SIZE(addrtype_mt_reg));
-}
-
-static void __exit addrtype_mt_exit(void)
-{
-	xt_unregister_matches(addrtype_mt_reg, ARRAY_SIZE(addrtype_mt_reg));
-}
-
-module_init(addrtype_mt_init);
-module_exit(addrtype_mt_exit);
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 82a6e0d80f05..32bff6d86cb2 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -649,6 +649,16 @@ config NETFILTER_XT_TARGET_TCPOPTSTRIP
 
 comment "Xtables matches"
 
+config NETFILTER_XT_MATCH_ADDRTYPE
+	tristate '"addrtype" address type match support'
+	depends on NETFILTER_ADVANCED
+	---help---
+	  This option allows you to match what routing thinks of an address,
+	  eg. UNICAST, LOCAL, BROADCAST, ...
+
+	  If you want to compile it as a module, say M here and read
+	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
+
 config NETFILTER_XT_MATCH_CLUSTER
 	tristate '"cluster" match support'
 	depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index d57a890eaee5..1a02853df863 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -70,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o
 
 # matches
+obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
new file mode 100644
index 000000000000..e89c0b84583c
--- /dev/null
+++ b/net/netfilter/xt_addrtype.c
@@ -0,0 +1,135 @@
+/*
+ *  iptables module to match inet_addr_type() of an ip.
+ *
+ *  Copyright (c) 2004 Patrick McHardy <kaber@trash.net>
+ *  (C) 2007 Laszlo Attila Toth <panther@balabit.hu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <net/route.h>
+
+#include <linux/netfilter/xt_addrtype.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Xtables: address type match");
+MODULE_ALIAS("ipt_addrtype");
+
+static inline bool match_type(struct net *net, const struct net_device *dev,
+			      __be32 addr, u_int16_t mask)
+{
+	return !!(mask & (1 << inet_dev_addr_type(net, dev, addr)));
+}
+
+static bool
+addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct net *net = dev_net(par->in ? par->in : par->out);
+	const struct xt_addrtype_info *info = par->matchinfo;
+	const struct iphdr *iph = ip_hdr(skb);
+	bool ret = true;
+
+	if (info->source)
+		ret &= match_type(net, NULL, iph->saddr, info->source) ^
+		       info->invert_source;
+	if (info->dest)
+		ret &= match_type(net, NULL, iph->daddr, info->dest) ^
+		       info->invert_dest;
+
+	return ret;
+}
+
+static bool
+addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct net *net = dev_net(par->in ? par->in : par->out);
+	const struct xt_addrtype_info_v1 *info = par->matchinfo;
+	const struct iphdr *iph = ip_hdr(skb);
+	const struct net_device *dev = NULL;
+	bool ret = true;
+
+	if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN)
+		dev = par->in;
+	else if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT)
+		dev = par->out;
+
+	if (info->source)
+		ret &= match_type(net, dev, iph->saddr, info->source) ^
+		       (info->flags & XT_ADDRTYPE_INVERT_SOURCE);
+	if (ret && info->dest)
+		ret &= match_type(net, dev, iph->daddr, info->dest) ^
+		       !!(info->flags & XT_ADDRTYPE_INVERT_DEST);
+	return ret;
+}
+
+static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
+{
+	struct xt_addrtype_info_v1 *info = par->matchinfo;
+
+	if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN &&
+	    info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) {
+		pr_info("both incoming and outgoing "
+			"interface limitation cannot be selected\n");
+		return -EINVAL;
+	}
+
+	if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) |
+	    (1 << NF_INET_LOCAL_IN)) &&
+	    info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT) {
+		pr_info("output interface limitation "
+			"not valid in PREROUTING and INPUT\n");
+		return -EINVAL;
+	}
+
+	if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) |
+	    (1 << NF_INET_LOCAL_OUT)) &&
+	    info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN) {
+		pr_info("input interface limitation "
+			"not valid in POSTROUTING and OUTPUT\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct xt_match addrtype_mt_reg[] __read_mostly = {
+	{
+		.name		= "addrtype",
+		.family		= NFPROTO_IPV4,
+		.match		= addrtype_mt_v0,
+		.matchsize	= sizeof(struct xt_addrtype_info),
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "addrtype",
+		.family		= NFPROTO_IPV4,
+		.revision	= 1,
+		.match		= addrtype_mt_v1,
+		.checkentry	= addrtype_mt_checkentry_v1,
+		.matchsize	= sizeof(struct xt_addrtype_info_v1),
+		.me		= THIS_MODULE
+	}
+};
+
+static int __init addrtype_mt_init(void)
+{
+	return xt_register_matches(addrtype_mt_reg,
+				   ARRAY_SIZE(addrtype_mt_reg));
+}
+
+static void __exit addrtype_mt_exit(void)
+{
+	xt_unregister_matches(addrtype_mt_reg, ARRAY_SIZE(addrtype_mt_reg));
+}
+
+module_init(addrtype_mt_init);
+module_exit(addrtype_mt_exit);
-- 
cgit v1.2.3


From 2f5dc63123905a89d4260ab8ee08d19ec104db04 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fwestphal@astaro.com>
Date: Tue, 15 Mar 2011 20:17:44 +0100
Subject: netfilter: xt_addrtype: ipv6 support

The kernel will refuse certain types that do not work in ipv6 mode.
We can then add these features incrementally without risk of userspace
breakage.

Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_addrtype.h | 17 ++++++
 net/netfilter/Kconfig                 |  1 +
 net/netfilter/xt_addrtype.c           | 98 ++++++++++++++++++++++++++++++++++-
 3 files changed, 114 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_addrtype.h b/include/linux/netfilter/xt_addrtype.h
index b492fc84f737..b156baa9d55e 100644
--- a/include/linux/netfilter/xt_addrtype.h
+++ b/include/linux/netfilter/xt_addrtype.h
@@ -10,6 +10,23 @@ enum {
 	XT_ADDRTYPE_LIMIT_IFACE_OUT	= 0x0008,
 };
 
+
+/* rtn_type enum values from rtnetlink.h, but shifted */
+enum {
+	XT_ADDRTYPE_UNSPEC = 1 << 0,
+	XT_ADDRTYPE_UNICAST = 1 << 1,	/* 1 << RTN_UNICAST */
+	XT_ADDRTYPE_LOCAL  = 1 << 2,	/* 1 << RTN_LOCAL, etc */
+	XT_ADDRTYPE_BROADCAST = 1 << 3,
+	XT_ADDRTYPE_ANYCAST = 1 << 4,
+	XT_ADDRTYPE_MULTICAST = 1 << 5,
+	XT_ADDRTYPE_BLACKHOLE = 1 << 6,
+	XT_ADDRTYPE_UNREACHABLE = 1 << 7,
+	XT_ADDRTYPE_PROHIBIT = 1 << 8,
+	XT_ADDRTYPE_THROW = 1 << 9,
+	XT_ADDRTYPE_NAT = 1 << 10,
+	XT_ADDRTYPE_XRESOLVE = 1 << 11,
+};
+
 struct xt_addrtype_info_v1 {
 	__u16	source;		/* source-type mask */
 	__u16	dest;		/* dest-type mask */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 32bff6d86cb2..c3f988aa1152 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -652,6 +652,7 @@ comment "Xtables matches"
 config NETFILTER_XT_MATCH_ADDRTYPE
 	tristate '"addrtype" address type match support'
 	depends on NETFILTER_ADVANCED
+	depends on (IPV6 || IPV6=n)
 	---help---
 	  This option allows you to match what routing thinks of an address,
 	  eg. UNICAST, LOCAL, BROADCAST, ...
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index e89c0b84583c..2220b85e9519 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -16,6 +16,12 @@
 #include <linux/ip.h>
 #include <net/route.h>
 
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/ip6_fib.h>
+#endif
+
 #include <linux/netfilter/xt_addrtype.h>
 #include <linux/netfilter/x_tables.h>
 
@@ -23,6 +29,73 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
 MODULE_DESCRIPTION("Xtables: address type match");
 MODULE_ALIAS("ipt_addrtype");
+MODULE_ALIAS("ip6t_addrtype");
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt)
+{
+	u32 ret;
+
+	if (!rt)
+		return XT_ADDRTYPE_UNREACHABLE;
+
+	if (rt->rt6i_flags & RTF_REJECT)
+		ret = XT_ADDRTYPE_UNREACHABLE;
+	else
+		ret = 0;
+
+	if (rt->rt6i_flags & RTF_LOCAL)
+		ret |= XT_ADDRTYPE_LOCAL;
+	if (rt->rt6i_flags & RTF_ANYCAST)
+		ret |= XT_ADDRTYPE_ANYCAST;
+	return ret;
+}
+
+static bool match_type6(struct net *net, const struct net_device *dev,
+				const struct in6_addr *addr, u16 mask)
+{
+	int addr_type = ipv6_addr_type(addr);
+
+	if ((mask & XT_ADDRTYPE_MULTICAST) &&
+	    !(addr_type & IPV6_ADDR_MULTICAST))
+		return false;
+	if ((mask & XT_ADDRTYPE_UNICAST) && !(addr_type & IPV6_ADDR_UNICAST))
+		return false;
+	if ((mask & XT_ADDRTYPE_UNSPEC) && addr_type != IPV6_ADDR_ANY)
+		return false;
+
+	if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST |
+	     XT_ADDRTYPE_UNREACHABLE) & mask) {
+		struct rt6_info *rt;
+		u32 type;
+		int ifindex = dev ? dev->ifindex : 0;
+
+		rt = rt6_lookup(net, addr, NULL, ifindex, !!dev);
+
+		type = xt_addrtype_rt6_to_type(rt);
+
+		dst_release(&rt->dst);
+		return !!(mask & type);
+	}
+	return true;
+}
+
+static bool
+addrtype_mt6(struct net *net, const struct net_device *dev,
+	const struct sk_buff *skb, const struct xt_addrtype_info_v1 *info)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	bool ret = true;
+
+	if (info->source)
+		ret &= match_type6(net, dev, &iph->saddr, info->source) ^
+		       (info->flags & XT_ADDRTYPE_INVERT_SOURCE);
+	if (ret && info->dest)
+		ret &= match_type6(net, dev, &iph->daddr, info->dest) ^
+		       !!(info->flags & XT_ADDRTYPE_INVERT_DEST);
+	return ret;
+}
+#endif
 
 static inline bool match_type(struct net *net, const struct net_device *dev,
 			      __be32 addr, u_int16_t mask)
@@ -53,7 +126,7 @@ addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	struct net *net = dev_net(par->in ? par->in : par->out);
 	const struct xt_addrtype_info_v1 *info = par->matchinfo;
-	const struct iphdr *iph = ip_hdr(skb);
+	const struct iphdr *iph;
 	const struct net_device *dev = NULL;
 	bool ret = true;
 
@@ -62,6 +135,11 @@ addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	else if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT)
 		dev = par->out;
 
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+	if (par->family == NFPROTO_IPV6)
+		return addrtype_mt6(net, dev, skb, info);
+#endif
+	iph = ip_hdr(skb);
 	if (info->source)
 		ret &= match_type(net, dev, iph->saddr, info->source) ^
 		       (info->flags & XT_ADDRTYPE_INVERT_SOURCE);
@@ -98,6 +176,22 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	}
 
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+	if (par->family == NFPROTO_IPV6) {
+		if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) {
+			pr_err("ipv6 BLACKHOLE matching not supported\n");
+			return -EINVAL;
+		}
+		if ((info->source | info->dest) >= XT_ADDRTYPE_PROHIBIT) {
+			pr_err("ipv6 PROHIBT (THROW, NAT ..) matching not supported\n");
+			return -EINVAL;
+		}
+		if ((info->source | info->dest) & XT_ADDRTYPE_BROADCAST) {
+			pr_err("ipv6 does not support BROADCAST matching\n");
+			return -EINVAL;
+		}
+	}
+#endif
 	return 0;
 }
 
@@ -111,7 +205,7 @@ static struct xt_match addrtype_mt_reg[] __read_mostly = {
 	},
 	{
 		.name		= "addrtype",
-		.family		= NFPROTO_IPV4,
+		.family		= NFPROTO_UNSPEC,
 		.revision	= 1,
 		.match		= addrtype_mt_v1,
 		.checkentry	= addrtype_mt_checkentry_v1,
-- 
cgit v1.2.3


From f942dc2552b8bfdee607be867b12a8971bb9cd85 Mon Sep 17 00:00:00 2001
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Tue, 15 Mar 2011 00:06:18 +0000
Subject: xen network backend driver

netback is the host side counterpart to the frontend driver in
drivers/net/xen-netfront.c. The PV protocol is also implemented by
frontend drivers in other OSes too, such as the BSDs and even Windows.

The patch is based on the driver from the xen.git pvops kernel tree but
has been put through the checkpatch.pl wringer plus several manual
cleanup passes and review iterations. The driver has been moved from
drivers/xen/netback to drivers/net/xen-netback.

One major change from xen.git is that the guest transmit path (i.e. what
looks like receive to netback) has been significantly reworked to remove
the dependency on the out of tree PageForeign page flag (a core kernel
patch which enables a per page destructor callback on the final
put_page). This page flag was used in order to implement a grant map
based transmit path (where guest pages are mapped directly into SKB
frags). Instead this version of netback uses grant copy operations into
regular memory belonging to the backend domain. Reinstating the grant
map functionality is something which I would like to revisit in the
future.

Note that this driver depends on 2e820f58f7ad "xen/irq: implement
bind_interdomain_evtchn_to_irqhandler for backend drivers" which is in
linux next via the "xen-two" tree and is intended for the 2.6.39 merge
window:
        git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git stable/backends
this branch has only that single commit since 2.6.38-rc2 and is safe for
cross merging into the net branch.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig                 |   38 +-
 drivers/net/Makefile                |    1 +
 drivers/net/xen-netback/Makefile    |    3 +
 drivers/net/xen-netback/common.h    |  161 ++++
 drivers/net/xen-netback/interface.c |  424 +++++++++
 drivers/net/xen-netback/netback.c   | 1745 +++++++++++++++++++++++++++++++++++
 drivers/net/xen-netback/xenbus.c    |  490 ++++++++++
 drivers/net/xen-netfront.c          |   20 +-
 include/xen/interface/io/netif.h    |   80 +-
 9 files changed, 2908 insertions(+), 54 deletions(-)
 create mode 100644 drivers/net/xen-netback/Makefile
 create mode 100644 drivers/net/xen-netback/common.h
 create mode 100644 drivers/net/xen-netback/interface.c
 create mode 100644 drivers/net/xen-netback/netback.c
 create mode 100644 drivers/net/xen-netback/xenbus.c

(limited to 'include')

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 46e1b1a28b80..797d68196728 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2953,12 +2953,38 @@ config XEN_NETDEV_FRONTEND
 	select XEN_XENBUS_FRONTEND
 	default y
 	help
-	  The network device frontend driver allows the kernel to
-	  access network devices exported exported by a virtual
-	  machine containing a physical network device driver. The
-	  frontend driver is intended for unprivileged guest domains;
-	  if you are compiling a kernel for a Xen guest, you almost
-	  certainly want to enable this.
+	  This driver provides support for Xen paravirtual network
+	  devices exported by a Xen network driver domain (often
+	  domain 0).
+
+	  The corresponding Linux backend driver is enabled by the
+	  CONFIG_XEN_NETDEV_BACKEND option.
+
+	  If you are compiling a kernel for use as Xen guest, you
+	  should say Y here. To compile this driver as a module, chose
+	  M here: the module will be called xen-netfront.
+
+config XEN_NETDEV_BACKEND
+	tristate "Xen backend network device"
+	depends on XEN_BACKEND
+	help
+	  This driver allows the kernel to act as a Xen network driver
+	  domain which exports paravirtual network devices to other
+	  Xen domains. These devices can be accessed by any operating
+	  system that implements a compatible front end.
+
+	  The corresponding Linux frontend driver is enabled by the
+	  CONFIG_XEN_NETDEV_FRONTEND configuration option.
+
+	  The backend driver presents a standard network device
+	  endpoint for each paravirtual network device to the driver
+	  domain network stack. These can then be bridged or routed
+	  etc in order to provide full network connectivity.
+
+	  If you are compiling a kernel to run in a Xen network driver
+	  domain (often this is domain 0) you should say Y here. To
+	  compile this driver as a module, chose M here: the module
+	  will be called xen-netback.
 
 config ISERIES_VETH
 	tristate "iSeries Virtual Ethernet driver support"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 7c2171179f97..01b604ad155e 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -172,6 +172,7 @@ obj-$(CONFIG_SLIP) += slip.o
 obj-$(CONFIG_SLHC) += slhc.o
 
 obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o
+obj-$(CONFIG_XEN_NETDEV_BACKEND) += xen-netback/
 
 obj-$(CONFIG_DUMMY) += dummy.o
 obj-$(CONFIG_IFB) += ifb.o
diff --git a/drivers/net/xen-netback/Makefile b/drivers/net/xen-netback/Makefile
new file mode 100644
index 000000000000..e346e8125ef5
--- /dev/null
+++ b/drivers/net/xen-netback/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_XEN_NETDEV_BACKEND) := xen-netback.o
+
+xen-netback-y := netback.o xenbus.o interface.o
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
new file mode 100644
index 000000000000..5d7bbf2b2ee7
--- /dev/null
+++ b/drivers/net/xen-netback/common.h
@@ -0,0 +1,161 @@
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __XEN_NETBACK__COMMON_H__
+#define __XEN_NETBACK__COMMON_H__
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+
+#include <xen/interface/io/netif.h>
+#include <xen/interface/grant_table.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+
+struct xen_netbk;
+
+struct xenvif {
+	/* Unique identifier for this interface. */
+	domid_t          domid;
+	unsigned int     handle;
+
+	/* Reference to netback processing backend. */
+	struct xen_netbk *netbk;
+
+	u8               fe_dev_addr[6];
+
+	/* Physical parameters of the comms window. */
+	grant_handle_t   tx_shmem_handle;
+	grant_ref_t      tx_shmem_ref;
+	grant_handle_t   rx_shmem_handle;
+	grant_ref_t      rx_shmem_ref;
+	unsigned int     irq;
+
+	/* List of frontends to notify after a batch of frames sent. */
+	struct list_head notify_list;
+
+	/* The shared rings and indexes. */
+	struct xen_netif_tx_back_ring tx;
+	struct xen_netif_rx_back_ring rx;
+	struct vm_struct *tx_comms_area;
+	struct vm_struct *rx_comms_area;
+
+	/* Flags that must not be set in dev->features */
+	u32 features_disabled;
+
+	/* Frontend feature information. */
+	u8 can_sg:1;
+	u8 gso:1;
+	u8 gso_prefix:1;
+	u8 csum:1;
+
+	/* Internal feature information. */
+	u8 can_queue:1;	    /* can queue packets for receiver? */
+
+	/*
+	 * Allow xenvif_start_xmit() to peek ahead in the rx request
+	 * ring.  This is a prediction of what rx_req_cons will be
+	 * once all queued skbs are put on the ring.
+	 */
+	RING_IDX rx_req_cons_peek;
+
+	/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
+	unsigned long   credit_bytes;
+	unsigned long   credit_usec;
+	unsigned long   remaining_credit;
+	struct timer_list credit_timeout;
+
+	/* Statistics */
+	unsigned long rx_gso_checksum_fixup;
+
+	/* Miscellaneous private stuff. */
+	struct list_head schedule_list;
+	atomic_t         refcnt;
+	struct net_device *dev;
+
+	wait_queue_head_t waiting_to_free;
+};
+
+#define XEN_NETIF_TX_RING_SIZE __RING_SIZE((struct xen_netif_tx_sring *)0, PAGE_SIZE)
+#define XEN_NETIF_RX_RING_SIZE __RING_SIZE((struct xen_netif_rx_sring *)0, PAGE_SIZE)
+
+struct xenvif *xenvif_alloc(struct device *parent,
+			    domid_t domid,
+			    unsigned int handle);
+
+int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
+		   unsigned long rx_ring_ref, unsigned int evtchn);
+void xenvif_disconnect(struct xenvif *vif);
+
+void xenvif_get(struct xenvif *vif);
+void xenvif_put(struct xenvif *vif);
+
+int xenvif_xenbus_init(void);
+
+int xenvif_schedulable(struct xenvif *vif);
+
+int xen_netbk_rx_ring_full(struct xenvif *vif);
+
+int xen_netbk_must_stop_queue(struct xenvif *vif);
+
+/* (Un)Map communication rings. */
+void xen_netbk_unmap_frontend_rings(struct xenvif *vif);
+int xen_netbk_map_frontend_rings(struct xenvif *vif,
+				 grant_ref_t tx_ring_ref,
+				 grant_ref_t rx_ring_ref);
+
+/* (De)Register a xenvif with the netback backend. */
+void xen_netbk_add_xenvif(struct xenvif *vif);
+void xen_netbk_remove_xenvif(struct xenvif *vif);
+
+/* (De)Schedule backend processing for a xenvif */
+void xen_netbk_schedule_xenvif(struct xenvif *vif);
+void xen_netbk_deschedule_xenvif(struct xenvif *vif);
+
+/* Check for SKBs from frontend and schedule backend processing */
+void xen_netbk_check_rx_xenvif(struct xenvif *vif);
+/* Receive an SKB from the frontend */
+void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb);
+
+/* Queue an SKB for transmission to the frontend */
+void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb);
+/* Notify xenvif that ring now has space to send an skb to the frontend */
+void xenvif_notify_tx_completion(struct xenvif *vif);
+
+/* Returns number of ring slots required to send an skb to the frontend */
+unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
+
+#endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
new file mode 100644
index 000000000000..de569cc19da4
--- /dev/null
+++ b/drivers/net/xen-netback/interface.c
@@ -0,0 +1,424 @@
+/*
+ * Network-device interface management.
+ *
+ * Copyright (c) 2004-2005, Keir Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "common.h"
+
+#include <linux/ethtool.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+
+#include <xen/events.h>
+#include <asm/xen/hypercall.h>
+
+#define XENVIF_QUEUE_LENGTH 32
+
+void xenvif_get(struct xenvif *vif)
+{
+	atomic_inc(&vif->refcnt);
+}
+
+void xenvif_put(struct xenvif *vif)
+{
+	if (atomic_dec_and_test(&vif->refcnt))
+		wake_up(&vif->waiting_to_free);
+}
+
+int xenvif_schedulable(struct xenvif *vif)
+{
+	return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
+}
+
+static int xenvif_rx_schedulable(struct xenvif *vif)
+{
+	return xenvif_schedulable(vif) && !xen_netbk_rx_ring_full(vif);
+}
+
+static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
+{
+	struct xenvif *vif = dev_id;
+
+	if (vif->netbk == NULL)
+		return IRQ_NONE;
+
+	xen_netbk_schedule_xenvif(vif);
+
+	if (xenvif_rx_schedulable(vif))
+		netif_wake_queue(vif->dev);
+
+	return IRQ_HANDLED;
+}
+
+static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+
+	BUG_ON(skb->dev != dev);
+
+	if (vif->netbk == NULL)
+		goto drop;
+
+	/* Drop the packet if the target domain has no receive buffers. */
+	if (!xenvif_rx_schedulable(vif))
+		goto drop;
+
+	/* Reserve ring slots for the worst-case number of fragments. */
+	vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb);
+	xenvif_get(vif);
+
+	if (vif->can_queue && xen_netbk_must_stop_queue(vif))
+		netif_stop_queue(dev);
+
+	xen_netbk_queue_tx_skb(vif, skb);
+
+	return NETDEV_TX_OK;
+
+ drop:
+	vif->dev->stats.tx_dropped++;
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb)
+{
+	netif_rx_ni(skb);
+}
+
+void xenvif_notify_tx_completion(struct xenvif *vif)
+{
+	if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
+		netif_wake_queue(vif->dev);
+}
+
+static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	return &vif->dev->stats;
+}
+
+static void xenvif_up(struct xenvif *vif)
+{
+	xen_netbk_add_xenvif(vif);
+	enable_irq(vif->irq);
+	xen_netbk_check_rx_xenvif(vif);
+}
+
+static void xenvif_down(struct xenvif *vif)
+{
+	disable_irq(vif->irq);
+	xen_netbk_deschedule_xenvif(vif);
+	xen_netbk_remove_xenvif(vif);
+}
+
+static int xenvif_open(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (netif_carrier_ok(dev))
+		xenvif_up(vif);
+	netif_start_queue(dev);
+	return 0;
+}
+
+static int xenvif_close(struct net_device *dev)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (netif_carrier_ok(dev))
+		xenvif_down(vif);
+	netif_stop_queue(dev);
+	return 0;
+}
+
+static int xenvif_change_mtu(struct net_device *dev, int mtu)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	int max = vif->can_sg ? 65535 - VLAN_ETH_HLEN : ETH_DATA_LEN;
+
+	if (mtu > max)
+		return -EINVAL;
+	dev->mtu = mtu;
+	return 0;
+}
+
+static void xenvif_set_features(struct xenvif *vif)
+{
+	struct net_device *dev = vif->dev;
+	u32 features = dev->features;
+
+	if (vif->can_sg)
+		features |= NETIF_F_SG;
+	if (vif->gso || vif->gso_prefix)
+		features |= NETIF_F_TSO;
+	if (vif->csum)
+		features |= NETIF_F_IP_CSUM;
+
+	features &= ~(vif->features_disabled);
+
+	if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN)
+		dev->mtu = ETH_DATA_LEN;
+
+	dev->features = features;
+}
+
+static int xenvif_set_tx_csum(struct net_device *dev, u32 data)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (data) {
+		if (!vif->csum)
+			return -EOPNOTSUPP;
+		vif->features_disabled &= ~NETIF_F_IP_CSUM;
+	} else {
+		vif->features_disabled |= NETIF_F_IP_CSUM;
+	}
+
+	xenvif_set_features(vif);
+	return 0;
+}
+
+static int xenvif_set_sg(struct net_device *dev, u32 data)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (data) {
+		if (!vif->can_sg)
+			return -EOPNOTSUPP;
+		vif->features_disabled &= ~NETIF_F_SG;
+	} else {
+		vif->features_disabled |= NETIF_F_SG;
+	}
+
+	xenvif_set_features(vif);
+	return 0;
+}
+
+static int xenvif_set_tso(struct net_device *dev, u32 data)
+{
+	struct xenvif *vif = netdev_priv(dev);
+	if (data) {
+		if (!vif->gso && !vif->gso_prefix)
+			return -EOPNOTSUPP;
+		vif->features_disabled &= ~NETIF_F_TSO;
+	} else {
+		vif->features_disabled |= NETIF_F_TSO;
+	}
+
+	xenvif_set_features(vif);
+	return 0;
+}
+
+static const struct xenvif_stat {
+	char name[ETH_GSTRING_LEN];
+	u16 offset;
+} xenvif_stats[] = {
+	{
+		"rx_gso_checksum_fixup",
+		offsetof(struct xenvif, rx_gso_checksum_fixup)
+	},
+};
+
+static int xenvif_get_sset_count(struct net_device *dev, int string_set)
+{
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(xenvif_stats);
+	default:
+		return -EINVAL;
+	}
+}
+
+static void xenvif_get_ethtool_stats(struct net_device *dev,
+				     struct ethtool_stats *stats, u64 * data)
+{
+	void *vif = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
+		data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
+}
+
+static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
+{
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
+			memcpy(data + i * ETH_GSTRING_LEN,
+			       xenvif_stats[i].name, ETH_GSTRING_LEN);
+		break;
+	}
+}
+
+static struct ethtool_ops xenvif_ethtool_ops = {
+	.get_tx_csum	= ethtool_op_get_tx_csum,
+	.set_tx_csum	= xenvif_set_tx_csum,
+	.get_sg		= ethtool_op_get_sg,
+	.set_sg		= xenvif_set_sg,
+	.get_tso	= ethtool_op_get_tso,
+	.set_tso	= xenvif_set_tso,
+	.get_link	= ethtool_op_get_link,
+
+	.get_sset_count = xenvif_get_sset_count,
+	.get_ethtool_stats = xenvif_get_ethtool_stats,
+	.get_strings = xenvif_get_strings,
+};
+
+static struct net_device_ops xenvif_netdev_ops = {
+	.ndo_start_xmit	= xenvif_start_xmit,
+	.ndo_get_stats	= xenvif_get_stats,
+	.ndo_open	= xenvif_open,
+	.ndo_stop	= xenvif_close,
+	.ndo_change_mtu	= xenvif_change_mtu,
+};
+
+struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
+			    unsigned int handle)
+{
+	int err;
+	struct net_device *dev;
+	struct xenvif *vif;
+	char name[IFNAMSIZ] = {};
+
+	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
+	dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
+	if (dev == NULL) {
+		pr_warn("Could not allocate netdev\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	SET_NETDEV_DEV(dev, parent);
+
+	vif = netdev_priv(dev);
+	vif->domid  = domid;
+	vif->handle = handle;
+	vif->netbk  = NULL;
+	vif->can_sg = 1;
+	vif->csum = 1;
+	atomic_set(&vif->refcnt, 1);
+	init_waitqueue_head(&vif->waiting_to_free);
+	vif->dev = dev;
+	INIT_LIST_HEAD(&vif->schedule_list);
+	INIT_LIST_HEAD(&vif->notify_list);
+
+	vif->credit_bytes = vif->remaining_credit = ~0UL;
+	vif->credit_usec  = 0UL;
+	init_timer(&vif->credit_timeout);
+	/* Initialize 'expires' now: it's used to track the credit window. */
+	vif->credit_timeout.expires = jiffies;
+
+	dev->netdev_ops	= &xenvif_netdev_ops;
+	xenvif_set_features(vif);
+	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);
+
+	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
+
+	/*
+	 * Initialise a dummy MAC address. We choose the numerically
+	 * largest non-broadcast address to prevent the address getting
+	 * stolen by an Ethernet bridge for STP purposes.
+	 * (FE:FF:FF:FF:FF:FF)
+	 */
+	memset(dev->dev_addr, 0xFF, ETH_ALEN);
+	dev->dev_addr[0] &= ~0x01;
+
+	netif_carrier_off(dev);
+
+	err = register_netdev(dev);
+	if (err) {
+		netdev_warn(dev, "Could not register device: err=%d\n", err);
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
+	netdev_dbg(dev, "Successfully created xenvif\n");
+	return vif;
+}
+
+int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
+		   unsigned long rx_ring_ref, unsigned int evtchn)
+{
+	int err = -ENOMEM;
+
+	/* Already connected through? */
+	if (vif->irq)
+		return 0;
+
+	xenvif_set_features(vif);
+
+	err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
+	if (err < 0)
+		goto err;
+
+	err = bind_interdomain_evtchn_to_irqhandler(
+		vif->domid, evtchn, xenvif_interrupt, 0,
+		vif->dev->name, vif);
+	if (err < 0)
+		goto err_unmap;
+	vif->irq = err;
+	disable_irq(vif->irq);
+
+	xenvif_get(vif);
+
+	rtnl_lock();
+	netif_carrier_on(vif->dev);
+	if (netif_running(vif->dev))
+		xenvif_up(vif);
+	rtnl_unlock();
+
+	return 0;
+err_unmap:
+	xen_netbk_unmap_frontend_rings(vif);
+err:
+	return err;
+}
+
+void xenvif_disconnect(struct xenvif *vif)
+{
+	struct net_device *dev = vif->dev;
+	if (netif_carrier_ok(dev)) {
+		rtnl_lock();
+		netif_carrier_off(dev); /* discard queued packets */
+		if (netif_running(dev))
+			xenvif_down(vif);
+		rtnl_unlock();
+		xenvif_put(vif);
+	}
+
+	atomic_dec(&vif->refcnt);
+	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
+
+	del_timer_sync(&vif->credit_timeout);
+
+	if (vif->irq)
+		unbind_from_irqhandler(vif->irq, vif);
+
+	unregister_netdev(vif->dev);
+
+	xen_netbk_unmap_frontend_rings(vif);
+
+	free_netdev(vif->dev);
+}
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
new file mode 100644
index 000000000000..0e4851b8a773
--- /dev/null
+++ b/drivers/net/xen-netback/netback.c
@@ -0,0 +1,1745 @@
+/*
+ * Back-end of the driver for virtual network devices. This portion of the
+ * driver exports a 'unified' network-device interface that can be accessed
+ * by any operating system that implements a compatible front end. A
+ * reference front-end implementation can be found in:
+ *  drivers/net/xen-netfront.c
+ *
+ * Copyright (c) 2002-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "common.h"
+
+#include <linux/kthread.h>
+#include <linux/if_vlan.h>
+#include <linux/udp.h>
+
+#include <net/tcp.h>
+
+#include <xen/events.h>
+#include <xen/interface/memory.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+struct pending_tx_info {
+	struct xen_netif_tx_request req;
+	struct xenvif *vif;
+};
+typedef unsigned int pending_ring_idx_t;
+
+struct netbk_rx_meta {
+	int id;
+	int size;
+	int gso_size;
+};
+
+#define MAX_PENDING_REQS 256
+
+#define MAX_BUFFER_OFFSET PAGE_SIZE
+
+/* extra field used in struct page */
+union page_ext {
+	struct {
+#if BITS_PER_LONG < 64
+#define IDX_WIDTH   8
+#define GROUP_WIDTH (BITS_PER_LONG - IDX_WIDTH)
+		unsigned int group:GROUP_WIDTH;
+		unsigned int idx:IDX_WIDTH;
+#else
+		unsigned int group, idx;
+#endif
+	} e;
+	void *mapping;
+};
+
+struct xen_netbk {
+	wait_queue_head_t wq;
+	struct task_struct *task;
+
+	struct sk_buff_head rx_queue;
+	struct sk_buff_head tx_queue;
+
+	struct timer_list net_timer;
+
+	struct page *mmap_pages[MAX_PENDING_REQS];
+
+	pending_ring_idx_t pending_prod;
+	pending_ring_idx_t pending_cons;
+	struct list_head net_schedule_list;
+
+	/* Protect the net_schedule_list in netif. */
+	spinlock_t net_schedule_list_lock;
+
+	atomic_t netfront_count;
+
+	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
+	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];
+
+	u16 pending_ring[MAX_PENDING_REQS];
+
+	/*
+	 * Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
+	 * head/fragment page uses 2 copy operations because it
+	 * straddles two buffers in the frontend.
+	 */
+	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
+	struct netbk_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
+};
+
+static struct xen_netbk *xen_netbk;
+static int xen_netbk_group_nr;
+
+void xen_netbk_add_xenvif(struct xenvif *vif)
+{
+	int i;
+	int min_netfront_count;
+	int min_group = 0;
+	struct xen_netbk *netbk;
+
+	min_netfront_count = atomic_read(&xen_netbk[0].netfront_count);
+	for (i = 0; i < xen_netbk_group_nr; i++) {
+		int netfront_count = atomic_read(&xen_netbk[i].netfront_count);
+		if (netfront_count < min_netfront_count) {
+			min_group = i;
+			min_netfront_count = netfront_count;
+		}
+	}
+
+	netbk = &xen_netbk[min_group];
+
+	vif->netbk = netbk;
+	atomic_inc(&netbk->netfront_count);
+}
+
+void xen_netbk_remove_xenvif(struct xenvif *vif)
+{
+	struct xen_netbk *netbk = vif->netbk;
+	vif->netbk = NULL;
+	atomic_dec(&netbk->netfront_count);
+}
+
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx);
+static void make_tx_response(struct xenvif *vif,
+			     struct xen_netif_tx_request *txp,
+			     s8       st);
+static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
+					     u16      id,
+					     s8       st,
+					     u16      offset,
+					     u16      size,
+					     u16      flags);
+
+static inline unsigned long idx_to_pfn(struct xen_netbk *netbk,
+				       unsigned int idx)
+{
+	return page_to_pfn(netbk->mmap_pages[idx]);
+}
+
+static inline unsigned long idx_to_kaddr(struct xen_netbk *netbk,
+					 unsigned int idx)
+{
+	return (unsigned long)pfn_to_kaddr(idx_to_pfn(netbk, idx));
+}
+
+/* extra field used in struct page */
+static inline void set_page_ext(struct page *pg, struct xen_netbk *netbk,
+				unsigned int idx)
+{
+	unsigned int group = netbk - xen_netbk;
+	union page_ext ext = { .e = { .group = group + 1, .idx = idx } };
+
+	BUILD_BUG_ON(sizeof(ext) > sizeof(ext.mapping));
+	pg->mapping = ext.mapping;
+}
+
+static int get_page_ext(struct page *pg,
+			unsigned int *pgroup, unsigned int *pidx)
+{
+	union page_ext ext = { .mapping = pg->mapping };
+	struct xen_netbk *netbk;
+	unsigned int group, idx;
+
+	group = ext.e.group - 1;
+
+	if (group < 0 || group >= xen_netbk_group_nr)
+		return 0;
+
+	netbk = &xen_netbk[group];
+
+	idx = ext.e.idx;
+
+	if ((idx < 0) || (idx >= MAX_PENDING_REQS))
+		return 0;
+
+	if (netbk->mmap_pages[idx] != pg)
+		return 0;
+
+	*pgroup = group;
+	*pidx = idx;
+
+	return 1;
+}
+
+/*
+ * This is the amount of packet we copy rather than map, so that the
+ * guest can't fiddle with the contents of the headers while we do
+ * packet processing on them (netfilter, routing, etc).
+ */
+#define PKT_PROT_LEN    (ETH_HLEN + \
+			 VLAN_HLEN + \
+			 sizeof(struct iphdr) + MAX_IPOPTLEN + \
+			 sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE)
+
+static inline pending_ring_idx_t pending_index(unsigned i)
+{
+	return i & (MAX_PENDING_REQS-1);
+}
+
+static inline pending_ring_idx_t nr_pending_reqs(struct xen_netbk *netbk)
+{
+	return MAX_PENDING_REQS -
+		netbk->pending_prod + netbk->pending_cons;
+}
+
+static void xen_netbk_kick_thread(struct xen_netbk *netbk)
+{
+	wake_up(&netbk->wq);
+}
+
+static int max_required_rx_slots(struct xenvif *vif)
+{
+	int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);
+
+	if (vif->can_sg || vif->gso || vif->gso_prefix)
+		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */
+
+	return max;
+}
+
+int xen_netbk_rx_ring_full(struct xenvif *vif)
+{
+	RING_IDX peek   = vif->rx_req_cons_peek;
+	RING_IDX needed = max_required_rx_slots(vif);
+
+	return ((vif->rx.sring->req_prod - peek) < needed) ||
+	       ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed);
+}
+
+int xen_netbk_must_stop_queue(struct xenvif *vif)
+{
+	if (!xen_netbk_rx_ring_full(vif))
+		return 0;
+
+	vif->rx.sring->req_event = vif->rx_req_cons_peek +
+		max_required_rx_slots(vif);
+	mb(); /* request notification /then/ check the queue */
+
+	return xen_netbk_rx_ring_full(vif);
+}
+
+/*
+ * Returns true if we should start a new receive buffer instead of
+ * adding 'size' bytes to a buffer which currently contains 'offset'
+ * bytes.
+ */
+static bool start_new_rx_buffer(int offset, unsigned long size, int head)
+{
+	/* simple case: we have completely filled the current buffer. */
+	if (offset == MAX_BUFFER_OFFSET)
+		return true;
+
+	/*
+	 * complex case: start a fresh buffer if the current frag
+	 * would overflow the current buffer but only if:
+	 *     (i)   this frag would fit completely in the next buffer
+	 * and (ii)  there is already some data in the current buffer
+	 * and (iii) this is not the head buffer.
+	 *
+	 * Where:
+	 * - (i) stops us splitting a frag into two copies
+	 *   unless the frag is too large for a single buffer.
+	 * - (ii) stops us from leaving a buffer pointlessly empty.
+	 * - (iii) stops us leaving the first buffer
+	 *   empty. Strictly speaking this is already covered
+	 *   by (ii) but is explicitly checked because
+	 *   netfront relies on the first buffer being
+	 *   non-empty and can crash otherwise.
+	 *
+	 * This means we will effectively linearise small
+	 * frags but do not needlessly split large buffers
+	 * into multiple copies tend to give large frags their
+	 * own buffers as before.
+	 */
+	if ((offset + size > MAX_BUFFER_OFFSET) &&
+	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+		return true;
+
+	return false;
+}
+
+/*
+ * Figure out how many ring slots we're going to need to send @skb to
+ * the guest. This function is essentially a dry run of
+ * netbk_gop_frag_copy.
+ */
+unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
+{
+	unsigned int count;
+	int i, copy_off;
+
+	count = DIV_ROUND_UP(
+			offset_in_page(skb->data)+skb_headlen(skb), PAGE_SIZE);
+
+	copy_off = skb_headlen(skb) % PAGE_SIZE;
+
+	if (skb_shinfo(skb)->gso_size)
+		count++;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		unsigned long size = skb_shinfo(skb)->frags[i].size;
+		unsigned long bytes;
+		while (size > 0) {
+			BUG_ON(copy_off > MAX_BUFFER_OFFSET);
+
+			if (start_new_rx_buffer(copy_off, size, 0)) {
+				count++;
+				copy_off = 0;
+			}
+
+			bytes = size;
+			if (copy_off + bytes > MAX_BUFFER_OFFSET)
+				bytes = MAX_BUFFER_OFFSET - copy_off;
+
+			copy_off += bytes;
+			size -= bytes;
+		}
+	}
+	return count;
+}
+
+struct netrx_pending_operations {
+	unsigned copy_prod, copy_cons;
+	unsigned meta_prod, meta_cons;
+	struct gnttab_copy *copy;
+	struct netbk_rx_meta *meta;
+	int copy_off;
+	grant_ref_t copy_gref;
+};
+
+static struct netbk_rx_meta *get_next_rx_buffer(struct xenvif *vif,
+						struct netrx_pending_operations *npo)
+{
+	struct netbk_rx_meta *meta;
+	struct xen_netif_rx_request *req;
+
+	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+
+	meta = npo->meta + npo->meta_prod++;
+	meta->gso_size = 0;
+	meta->size = 0;
+	meta->id = req->id;
+
+	npo->copy_off = 0;
+	npo->copy_gref = req->gref;
+
+	return meta;
+}
+
+/*
+ * Set up the grant operations for this fragment. If it's a flipping
+ * interface, we also set up the unmap request from here.
+ */
+static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
+				struct netrx_pending_operations *npo,
+				struct page *page, unsigned long size,
+				unsigned long offset, int *head)
+{
+	struct gnttab_copy *copy_gop;
+	struct netbk_rx_meta *meta;
+	/*
+	 * These variables a used iff get_page_ext returns true,
+	 * in which case they are guaranteed to be initialized.
+	 */
+	unsigned int uninitialized_var(group), uninitialized_var(idx);
+	int foreign = get_page_ext(page, &group, &idx);
+	unsigned long bytes;
+
+	/* Data must not cross a page boundary. */
+	BUG_ON(size + offset > PAGE_SIZE);
+
+	meta = npo->meta + npo->meta_prod - 1;
+
+	while (size > 0) {
+		BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);
+
+		if (start_new_rx_buffer(npo->copy_off, size, *head)) {
+			/*
+			 * Netfront requires there to be some data in the head
+			 * buffer.
+			 */
+			BUG_ON(*head);
+
+			meta = get_next_rx_buffer(vif, npo);
+		}
+
+		bytes = size;
+		if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
+			bytes = MAX_BUFFER_OFFSET - npo->copy_off;
+
+		copy_gop = npo->copy + npo->copy_prod++;
+		copy_gop->flags = GNTCOPY_dest_gref;
+		if (foreign) {
+			struct xen_netbk *netbk = &xen_netbk[group];
+			struct pending_tx_info *src_pend;
+
+			src_pend = &netbk->pending_tx_info[idx];
+
+			copy_gop->source.domid = src_pend->vif->domid;
+			copy_gop->source.u.ref = src_pend->req.gref;
+			copy_gop->flags |= GNTCOPY_source_gref;
+		} else {
+			void *vaddr = page_address(page);
+			copy_gop->source.domid = DOMID_SELF;
+			copy_gop->source.u.gmfn = virt_to_mfn(vaddr);
+		}
+		copy_gop->source.offset = offset;
+		copy_gop->dest.domid = vif->domid;
+
+		copy_gop->dest.offset = npo->copy_off;
+		copy_gop->dest.u.ref = npo->copy_gref;
+		copy_gop->len = bytes;
+
+		npo->copy_off += bytes;
+		meta->size += bytes;
+
+		offset += bytes;
+		size -= bytes;
+
+		/* Leave a gap for the GSO descriptor. */
+		if (*head && skb_shinfo(skb)->gso_size && !vif->gso_prefix)
+			vif->rx.req_cons++;
+
+		*head = 0; /* There must be something in this buffer now. */
+
+	}
+}
+
+/*
+ * Prepare an SKB to be transmitted to the frontend.
+ *
+ * This function is responsible for allocating grant operations, meta
+ * structures, etc.
+ *
+ * It returns the number of meta structures consumed. The number of
+ * ring slots used is always equal to the number of meta slots used
+ * plus the number of GSO descriptors used. Currently, we use either
+ * zero GSO descriptors (for non-GSO packets) or one descriptor (for
+ * frontend-side LRO).
+ */
+static int netbk_gop_skb(struct sk_buff *skb,
+			 struct netrx_pending_operations *npo)
+{
+	struct xenvif *vif = netdev_priv(skb->dev);
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int i;
+	struct xen_netif_rx_request *req;
+	struct netbk_rx_meta *meta;
+	unsigned char *data;
+	int head = 1;
+	int old_meta_prod;
+
+	old_meta_prod = npo->meta_prod;
+
+	/* Set up a GSO prefix descriptor, if necessary */
+	if (skb_shinfo(skb)->gso_size && vif->gso_prefix) {
+		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+		meta = npo->meta + npo->meta_prod++;
+		meta->gso_size = skb_shinfo(skb)->gso_size;
+		meta->size = 0;
+		meta->id = req->id;
+	}
+
+	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+	meta = npo->meta + npo->meta_prod++;
+
+	if (!vif->gso_prefix)
+		meta->gso_size = skb_shinfo(skb)->gso_size;
+	else
+		meta->gso_size = 0;
+
+	meta->size = 0;
+	meta->id = req->id;
+	npo->copy_off = 0;
+	npo->copy_gref = req->gref;
+
+	data = skb->data;
+	while (data < skb_tail_pointer(skb)) {
+		unsigned int offset = offset_in_page(data);
+		unsigned int len = PAGE_SIZE - offset;
+
+		if (data + len > skb_tail_pointer(skb))
+			len = skb_tail_pointer(skb) - data;
+
+		netbk_gop_frag_copy(vif, skb, npo,
+				    virt_to_page(data), len, offset, &head);
+		data += len;
+	}
+
+	for (i = 0; i < nr_frags; i++) {
+		netbk_gop_frag_copy(vif, skb, npo,
+				    skb_shinfo(skb)->frags[i].page,
+				    skb_shinfo(skb)->frags[i].size,
+				    skb_shinfo(skb)->frags[i].page_offset,
+				    &head);
+	}
+
+	return npo->meta_prod - old_meta_prod;
+}
+
+/*
+ * This is a twin to netbk_gop_skb.  Assume that netbk_gop_skb was
+ * used to set up the operations on the top of
+ * netrx_pending_operations, which have since been done.  Check that
+ * they didn't give any errors and advance over them.
+ */
+static int netbk_check_gop(struct xenvif *vif, int nr_meta_slots,
+			   struct netrx_pending_operations *npo)
+{
+	struct gnttab_copy     *copy_op;
+	int status = XEN_NETIF_RSP_OKAY;
+	int i;
+
+	for (i = 0; i < nr_meta_slots; i++) {
+		copy_op = npo->copy + npo->copy_cons++;
+		if (copy_op->status != GNTST_okay) {
+			netdev_dbg(vif->dev,
+				   "Bad status %d from copy to DOM%d.\n",
+				   copy_op->status, vif->domid);
+			status = XEN_NETIF_RSP_ERROR;
+		}
+	}
+
+	return status;
+}
+
+static void netbk_add_frag_responses(struct xenvif *vif, int status,
+				     struct netbk_rx_meta *meta,
+				     int nr_meta_slots)
+{
+	int i;
+	unsigned long offset;
+
+	/* No fragments used */
+	if (nr_meta_slots <= 1)
+		return;
+
+	nr_meta_slots--;
+
+	for (i = 0; i < nr_meta_slots; i++) {
+		int flags;
+		if (i == nr_meta_slots - 1)
+			flags = 0;
+		else
+			flags = XEN_NETRXF_more_data;
+
+		offset = 0;
+		make_rx_response(vif, meta[i].id, status, offset,
+				 meta[i].size, flags);
+	}
+}
+
+struct skb_cb_overlay {
+	int meta_slots_used;
+};
+
+static void xen_netbk_rx_action(struct xen_netbk *netbk)
+{
+	struct xenvif *vif = NULL, *tmp;
+	s8 status;
+	u16 irq, flags;
+	struct xen_netif_rx_response *resp;
+	struct sk_buff_head rxq;
+	struct sk_buff *skb;
+	LIST_HEAD(notify);
+	int ret;
+	int nr_frags;
+	int count;
+	unsigned long offset;
+	struct skb_cb_overlay *sco;
+
+	struct netrx_pending_operations npo = {
+		.copy  = netbk->grant_copy_op,
+		.meta  = netbk->meta,
+	};
+
+	skb_queue_head_init(&rxq);
+
+	count = 0;
+
+	while ((skb = skb_dequeue(&netbk->rx_queue)) != NULL) {
+		vif = netdev_priv(skb->dev);
+		nr_frags = skb_shinfo(skb)->nr_frags;
+
+		sco = (struct skb_cb_overlay *)skb->cb;
+		sco->meta_slots_used = netbk_gop_skb(skb, &npo);
+
+		count += nr_frags + 1;
+
+		__skb_queue_tail(&rxq, skb);
+
+		/* Filled the batch queue? */
+		if (count + MAX_SKB_FRAGS >= XEN_NETIF_RX_RING_SIZE)
+			break;
+	}
+
+	BUG_ON(npo.meta_prod > ARRAY_SIZE(netbk->meta));
+
+	if (!npo.copy_prod)
+		return;
+
+	BUG_ON(npo.copy_prod > ARRAY_SIZE(netbk->grant_copy_op));
+	ret = HYPERVISOR_grant_table_op(GNTTABOP_copy, &netbk->grant_copy_op,
+					npo.copy_prod);
+	BUG_ON(ret != 0);
+
+	while ((skb = __skb_dequeue(&rxq)) != NULL) {
+		sco = (struct skb_cb_overlay *)skb->cb;
+
+		vif = netdev_priv(skb->dev);
+
+		if (netbk->meta[npo.meta_cons].gso_size && vif->gso_prefix) {
+			resp = RING_GET_RESPONSE(&vif->rx,
+						vif->rx.rsp_prod_pvt++);
+
+			resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data;
+
+			resp->offset = netbk->meta[npo.meta_cons].gso_size;
+			resp->id = netbk->meta[npo.meta_cons].id;
+			resp->status = sco->meta_slots_used;
+
+			npo.meta_cons++;
+			sco->meta_slots_used--;
+		}
+
+
+		vif->dev->stats.tx_bytes += skb->len;
+		vif->dev->stats.tx_packets++;
+
+		status = netbk_check_gop(vif, sco->meta_slots_used, &npo);
+
+		if (sco->meta_slots_used == 1)
+			flags = 0;
+		else
+			flags = XEN_NETRXF_more_data;
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */
+			flags |= XEN_NETRXF_csum_blank | XEN_NETRXF_data_validated;
+		else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
+			/* remote but checksummed. */
+			flags |= XEN_NETRXF_data_validated;
+
+		offset = 0;
+		resp = make_rx_response(vif, netbk->meta[npo.meta_cons].id,
+					status, offset,
+					netbk->meta[npo.meta_cons].size,
+					flags);
+
+		if (netbk->meta[npo.meta_cons].gso_size && !vif->gso_prefix) {
+			struct xen_netif_extra_info *gso =
+				(struct xen_netif_extra_info *)
+				RING_GET_RESPONSE(&vif->rx,
+						  vif->rx.rsp_prod_pvt++);
+
+			resp->flags |= XEN_NETRXF_extra_info;
+
+			gso->u.gso.size = netbk->meta[npo.meta_cons].gso_size;
+			gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
+			gso->u.gso.pad = 0;
+			gso->u.gso.features = 0;
+
+			gso->type = XEN_NETIF_EXTRA_TYPE_GSO;
+			gso->flags = 0;
+		}
+
+		netbk_add_frag_responses(vif, status,
+					 netbk->meta + npo.meta_cons + 1,
+					 sco->meta_slots_used);
+
+		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
+		irq = vif->irq;
+		if (ret && list_empty(&vif->notify_list))
+			list_add_tail(&vif->notify_list, &notify);
+
+		xenvif_notify_tx_completion(vif);
+
+		xenvif_put(vif);
+		npo.meta_cons += sco->meta_slots_used;
+		dev_kfree_skb(skb);
+	}
+
+	list_for_each_entry_safe(vif, tmp, &notify, notify_list) {
+		notify_remote_via_irq(vif->irq);
+		list_del_init(&vif->notify_list);
+	}
+
+	/* More work to do? */
+	if (!skb_queue_empty(&netbk->rx_queue) &&
+			!timer_pending(&netbk->net_timer))
+		xen_netbk_kick_thread(netbk);
+}
+
+void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb)
+{
+	struct xen_netbk *netbk = vif->netbk;
+
+	skb_queue_tail(&netbk->rx_queue, skb);
+
+	xen_netbk_kick_thread(netbk);
+}
+
+static void xen_netbk_alarm(unsigned long data)
+{
+	struct xen_netbk *netbk = (struct xen_netbk *)data;
+	xen_netbk_kick_thread(netbk);
+}
+
+static int __on_net_schedule_list(struct xenvif *vif)
+{
+	return !list_empty(&vif->schedule_list);
+}
+
+/* Must be called with net_schedule_list_lock held */
+static void remove_from_net_schedule_list(struct xenvif *vif)
+{
+	if (likely(__on_net_schedule_list(vif))) {
+		list_del_init(&vif->schedule_list);
+		xenvif_put(vif);
+	}
+}
+
+static struct xenvif *poll_net_schedule_list(struct xen_netbk *netbk)
+{
+	struct xenvif *vif = NULL;
+
+	spin_lock_irq(&netbk->net_schedule_list_lock);
+	if (list_empty(&netbk->net_schedule_list))
+		goto out;
+
+	vif = list_first_entry(&netbk->net_schedule_list,
+			       struct xenvif, schedule_list);
+	if (!vif)
+		goto out;
+
+	xenvif_get(vif);
+
+	remove_from_net_schedule_list(vif);
+out:
+	spin_unlock_irq(&netbk->net_schedule_list_lock);
+	return vif;
+}
+
+void xen_netbk_schedule_xenvif(struct xenvif *vif)
+{
+	unsigned long flags;
+	struct xen_netbk *netbk = vif->netbk;
+
+	if (__on_net_schedule_list(vif))
+		goto kick;
+
+	spin_lock_irqsave(&netbk->net_schedule_list_lock, flags);
+	if (!__on_net_schedule_list(vif) &&
+	    likely(xenvif_schedulable(vif))) {
+		list_add_tail(&vif->schedule_list, &netbk->net_schedule_list);
+		xenvif_get(vif);
+	}
+	spin_unlock_irqrestore(&netbk->net_schedule_list_lock, flags);
+
+kick:
+	smp_mb();
+	if ((nr_pending_reqs(netbk) < (MAX_PENDING_REQS/2)) &&
+	    !list_empty(&netbk->net_schedule_list))
+		xen_netbk_kick_thread(netbk);
+}
+
+void xen_netbk_deschedule_xenvif(struct xenvif *vif)
+{
+	struct xen_netbk *netbk = vif->netbk;
+	spin_lock_irq(&netbk->net_schedule_list_lock);
+	remove_from_net_schedule_list(vif);
+	spin_unlock_irq(&netbk->net_schedule_list_lock);
+}
+
+void xen_netbk_check_rx_xenvif(struct xenvif *vif)
+{
+	int more_to_do;
+
+	RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
+
+	if (more_to_do)
+		xen_netbk_schedule_xenvif(vif);
+}
+
+static void tx_add_credit(struct xenvif *vif)
+{
+	unsigned long max_burst, max_credit;
+
+	/*
+	 * Allow a burst big enough to transmit a jumbo packet of up to 128kB.
+	 * Otherwise the interface can seize up due to insufficient credit.
+	 */
+	max_burst = RING_GET_REQUEST(&vif->tx, vif->tx.req_cons)->size;
+	max_burst = min(max_burst, 131072UL);
+	max_burst = max(max_burst, vif->credit_bytes);
+
+	/* Take care that adding a new chunk of credit doesn't wrap to zero. */
+	max_credit = vif->remaining_credit + vif->credit_bytes;
+	if (max_credit < vif->remaining_credit)
+		max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */
+
+	vif->remaining_credit = min(max_credit, max_burst);
+}
+
+static void tx_credit_callback(unsigned long data)
+{
+	struct xenvif *vif = (struct xenvif *)data;
+	tx_add_credit(vif);
+	xen_netbk_check_rx_xenvif(vif);
+}
+
+static void netbk_tx_err(struct xenvif *vif,
+			 struct xen_netif_tx_request *txp, RING_IDX end)
+{
+	RING_IDX cons = vif->tx.req_cons;
+
+	do {
+		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
+		if (cons >= end)
+			break;
+		txp = RING_GET_REQUEST(&vif->tx, cons++);
+	} while (1);
+	vif->tx.req_cons = cons;
+	xen_netbk_check_rx_xenvif(vif);
+	xenvif_put(vif);
+}
+
+static int netbk_count_requests(struct xenvif *vif,
+				struct xen_netif_tx_request *first,
+				struct xen_netif_tx_request *txp,
+				int work_to_do)
+{
+	RING_IDX cons = vif->tx.req_cons;
+	int frags = 0;
+
+	if (!(first->flags & XEN_NETTXF_more_data))
+		return 0;
+
+	do {
+		if (frags >= work_to_do) {
+			netdev_dbg(vif->dev, "Need more frags\n");
+			return -frags;
+		}
+
+		if (unlikely(frags >= MAX_SKB_FRAGS)) {
+			netdev_dbg(vif->dev, "Too many frags\n");
+			return -frags;
+		}
+
+		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
+		       sizeof(*txp));
+		if (txp->size > first->size) {
+			netdev_dbg(vif->dev, "Frags galore\n");
+			return -frags;
+		}
+
+		first->size -= txp->size;
+		frags++;
+
+		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
+			netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n",
+				 txp->offset, txp->size);
+			return -frags;
+		}
+	} while ((txp++)->flags & XEN_NETTXF_more_data);
+	return frags;
+}
+
+static struct page *xen_netbk_alloc_page(struct xen_netbk *netbk,
+					 struct sk_buff *skb,
+					 unsigned long pending_idx)
+{
+	struct page *page;
+	page = alloc_page(GFP_KERNEL|__GFP_COLD);
+	if (!page)
+		return NULL;
+	set_page_ext(page, netbk, pending_idx);
+	netbk->mmap_pages[pending_idx] = page;
+	return page;
+}
+
+static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
+						  struct xenvif *vif,
+						  struct sk_buff *skb,
+						  struct xen_netif_tx_request *txp,
+						  struct gnttab_copy *gop)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	skb_frag_t *frags = shinfo->frags;
+	unsigned long pending_idx = *((u16 *)skb->data);
+	int i, start;
+
+	/* Skip first skb fragment if it is on same page as header fragment. */
+	start = ((unsigned long)shinfo->frags[0].page == pending_idx);
+
+	for (i = start; i < shinfo->nr_frags; i++, txp++) {
+		struct page *page;
+		pending_ring_idx_t index;
+		struct pending_tx_info *pending_tx_info =
+			netbk->pending_tx_info;
+
+		index = pending_index(netbk->pending_cons++);
+		pending_idx = netbk->pending_ring[index];
+		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
+		if (!page)
+			return NULL;
+
+		netbk->mmap_pages[pending_idx] = page;
+
+		gop->source.u.ref = txp->gref;
+		gop->source.domid = vif->domid;
+		gop->source.offset = txp->offset;
+
+		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
+		gop->dest.domid = DOMID_SELF;
+		gop->dest.offset = txp->offset;
+
+		gop->len = txp->size;
+		gop->flags = GNTCOPY_source_gref;
+
+		gop++;
+
+		memcpy(&pending_tx_info[pending_idx].req, txp, sizeof(*txp));
+		xenvif_get(vif);
+		pending_tx_info[pending_idx].vif = vif;
+		frags[i].page = (void *)pending_idx;
+	}
+
+	return gop;
+}
+
+static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
+				  struct sk_buff *skb,
+				  struct gnttab_copy **gopp)
+{
+	struct gnttab_copy *gop = *gopp;
+	int pending_idx = *((u16 *)skb->data);
+	struct pending_tx_info *pending_tx_info = netbk->pending_tx_info;
+	struct xenvif *vif = pending_tx_info[pending_idx].vif;
+	struct xen_netif_tx_request *txp;
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	int nr_frags = shinfo->nr_frags;
+	int i, err, start;
+
+	/* Check status of header. */
+	err = gop->status;
+	if (unlikely(err)) {
+		pending_ring_idx_t index;
+		index = pending_index(netbk->pending_prod++);
+		txp = &pending_tx_info[pending_idx].req;
+		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
+		netbk->pending_ring[index] = pending_idx;
+		xenvif_put(vif);
+	}
+
+	/* Skip first skb fragment if it is on same page as header fragment. */
+	start = ((unsigned long)shinfo->frags[0].page == pending_idx);
+
+	for (i = start; i < nr_frags; i++) {
+		int j, newerr;
+		pending_ring_idx_t index;
+
+		pending_idx = (unsigned long)shinfo->frags[i].page;
+
+		/* Check error status: if okay then remember grant handle. */
+		newerr = (++gop)->status;
+		if (likely(!newerr)) {
+			/* Had a previous error? Invalidate this fragment. */
+			if (unlikely(err))
+				xen_netbk_idx_release(netbk, pending_idx);
+			continue;
+		}
+
+		/* Error on this fragment: respond to client with an error. */
+		txp = &netbk->pending_tx_info[pending_idx].req;
+		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
+		index = pending_index(netbk->pending_prod++);
+		netbk->pending_ring[index] = pending_idx;
+		xenvif_put(vif);
+
+		/* Not the first error? Preceding frags already invalidated. */
+		if (err)
+			continue;
+
+		/* First error: invalidate header and preceding fragments. */
+		pending_idx = *((u16 *)skb->data);
+		xen_netbk_idx_release(netbk, pending_idx);
+		for (j = start; j < i; j++) {
+			pending_idx = (unsigned long)shinfo->frags[i].page;
+			xen_netbk_idx_release(netbk, pending_idx);
+		}
+
+		/* Remember the error: invalidate all subsequent fragments. */
+		err = newerr;
+	}
+
+	*gopp = gop + 1;
+	return err;
+}
+
+static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	int nr_frags = shinfo->nr_frags;
+	int i;
+
+	for (i = 0; i < nr_frags; i++) {
+		skb_frag_t *frag = shinfo->frags + i;
+		struct xen_netif_tx_request *txp;
+		unsigned long pending_idx;
+
+		pending_idx = (unsigned long)frag->page;
+
+		txp = &netbk->pending_tx_info[pending_idx].req;
+		frag->page = virt_to_page(idx_to_kaddr(netbk, pending_idx));
+		frag->size = txp->size;
+		frag->page_offset = txp->offset;
+
+		skb->len += txp->size;
+		skb->data_len += txp->size;
+		skb->truesize += txp->size;
+
+		/* Take an extra reference to offset xen_netbk_idx_release */
+		get_page(netbk->mmap_pages[pending_idx]);
+		xen_netbk_idx_release(netbk, pending_idx);
+	}
+}
+
+static int xen_netbk_get_extras(struct xenvif *vif,
+				struct xen_netif_extra_info *extras,
+				int work_to_do)
+{
+	struct xen_netif_extra_info extra;
+	RING_IDX cons = vif->tx.req_cons;
+
+	do {
+		if (unlikely(work_to_do-- <= 0)) {
+			netdev_dbg(vif->dev, "Missing extra info\n");
+			return -EBADR;
+		}
+
+		memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons),
+		       sizeof(extra));
+		if (unlikely(!extra.type ||
+			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
+			vif->tx.req_cons = ++cons;
+			netdev_dbg(vif->dev,
+				   "Invalid extra type: %d\n", extra.type);
+			return -EINVAL;
+		}
+
+		memcpy(&extras[extra.type - 1], &extra, sizeof(extra));
+		vif->tx.req_cons = ++cons;
+	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
+
+	return work_to_do;
+}
+
+static int netbk_set_skb_gso(struct xenvif *vif,
+			     struct sk_buff *skb,
+			     struct xen_netif_extra_info *gso)
+{
+	if (!gso->u.gso.size) {
+		netdev_dbg(vif->dev, "GSO size must not be zero.\n");
+		return -EINVAL;
+	}
+
+	/* Currently only TCPv4 S.O. is supported. */
+	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
+		netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		return -EINVAL;
+	}
+
+	skb_shinfo(skb)->gso_size = gso->u.gso.size;
+	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+
+	/* Header must be checked, and gso_segs computed. */
+	skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+	skb_shinfo(skb)->gso_segs = 0;
+
+	return 0;
+}
+
+static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	unsigned char *th;
+	int err = -EPROTO;
+	int recalculate_partial_csum = 0;
+
+	/*
+	 * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
+	 * peers can fail to set NETRXF_csum_blank when sending a GSO
+	 * frame. In this case force the SKB to CHECKSUM_PARTIAL and
+	 * recalculate the partial checksum.
+	 */
+	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
+		vif->rx_gso_checksum_fixup++;
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		recalculate_partial_csum = 1;
+	}
+
+	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		goto out;
+
+	iph = (void *)skb->data;
+	th = skb->data + 4 * iph->ihl;
+	if (th >= skb_tail_pointer(skb))
+		goto out;
+
+	skb->csum_start = th - skb->head;
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+		skb->csum_offset = offsetof(struct tcphdr, check);
+
+		if (recalculate_partial_csum) {
+			struct tcphdr *tcph = (struct tcphdr *)th;
+			tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+							 skb->len - iph->ihl*4,
+							 IPPROTO_TCP, 0);
+		}
+		break;
+	case IPPROTO_UDP:
+		skb->csum_offset = offsetof(struct udphdr, check);
+
+		if (recalculate_partial_csum) {
+			struct udphdr *udph = (struct udphdr *)th;
+			udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+							 skb->len - iph->ihl*4,
+							 IPPROTO_UDP, 0);
+		}
+		break;
+	default:
+		if (net_ratelimit())
+			netdev_err(vif->dev,
+				   "Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
+				   iph->protocol);
+		goto out;
+	}
+
+	if ((th + skb->csum_offset + 2) > skb_tail_pointer(skb))
+		goto out;
+
+	err = 0;
+
+out:
+	return err;
+}
+
+static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
+{
+	unsigned long now = jiffies;
+	unsigned long next_credit =
+		vif->credit_timeout.expires +
+		msecs_to_jiffies(vif->credit_usec / 1000);
+
+	/* Timer could already be pending in rare cases. */
+	if (timer_pending(&vif->credit_timeout))
+		return true;
+
+	/* Passed the point where we can replenish credit? */
+	if (time_after_eq(now, next_credit)) {
+		vif->credit_timeout.expires = now;
+		tx_add_credit(vif);
+	}
+
+	/* Still too big to send right now? Set a callback. */
+	if (size > vif->remaining_credit) {
+		vif->credit_timeout.data     =
+			(unsigned long)vif;
+		vif->credit_timeout.function =
+			tx_credit_callback;
+		mod_timer(&vif->credit_timeout,
+			  next_credit);
+
+		return true;
+	}
+
+	return false;
+}
+
+static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
+{
+	struct gnttab_copy *gop = netbk->tx_copy_ops, *request_gop;
+	struct sk_buff *skb;
+	int ret;
+
+	while (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) &&
+		!list_empty(&netbk->net_schedule_list)) {
+		struct xenvif *vif;
+		struct xen_netif_tx_request txreq;
+		struct xen_netif_tx_request txfrags[MAX_SKB_FRAGS];
+		struct page *page;
+		struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
+		u16 pending_idx;
+		RING_IDX idx;
+		int work_to_do;
+		unsigned int data_len;
+		pending_ring_idx_t index;
+
+		/* Get a netif from the list with work to do. */
+		vif = poll_net_schedule_list(netbk);
+		if (!vif)
+			continue;
+
+		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do);
+		if (!work_to_do) {
+			xenvif_put(vif);
+			continue;
+		}
+
+		idx = vif->tx.req_cons;
+		rmb(); /* Ensure that we see the request before we copy it. */
+		memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq));
+
+		/* Credit-based scheduling. */
+		if (txreq.size > vif->remaining_credit &&
+		    tx_credit_exceeded(vif, txreq.size)) {
+			xenvif_put(vif);
+			continue;
+		}
+
+		vif->remaining_credit -= txreq.size;
+
+		work_to_do--;
+		vif->tx.req_cons = ++idx;
+
+		memset(extras, 0, sizeof(extras));
+		if (txreq.flags & XEN_NETTXF_extra_info) {
+			work_to_do = xen_netbk_get_extras(vif, extras,
+							  work_to_do);
+			idx = vif->tx.req_cons;
+			if (unlikely(work_to_do < 0)) {
+				netbk_tx_err(vif, &txreq, idx);
+				continue;
+			}
+		}
+
+		ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do);
+		if (unlikely(ret < 0)) {
+			netbk_tx_err(vif, &txreq, idx - ret);
+			continue;
+		}
+		idx += ret;
+
+		if (unlikely(txreq.size < ETH_HLEN)) {
+			netdev_dbg(vif->dev,
+				   "Bad packet size: %d\n", txreq.size);
+			netbk_tx_err(vif, &txreq, idx);
+			continue;
+		}
+
+		/* No crossing a page as the payload mustn't fragment. */
+		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
+			netdev_dbg(vif->dev,
+				   "txreq.offset: %x, size: %u, end: %lu\n",
+				   txreq.offset, txreq.size,
+				   (txreq.offset&~PAGE_MASK) + txreq.size);
+			netbk_tx_err(vif, &txreq, idx);
+			continue;
+		}
+
+		index = pending_index(netbk->pending_cons);
+		pending_idx = netbk->pending_ring[index];
+
+		data_len = (txreq.size > PKT_PROT_LEN &&
+			    ret < MAX_SKB_FRAGS) ?
+			PKT_PROT_LEN : txreq.size;
+
+		skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN,
+				GFP_ATOMIC | __GFP_NOWARN);
+		if (unlikely(skb == NULL)) {
+			netdev_dbg(vif->dev,
+				   "Can't allocate a skb in start_xmit.\n");
+			netbk_tx_err(vif, &txreq, idx);
+			break;
+		}
+
+		/* Packets passed to netif_rx() must have some headroom. */
+		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+
+		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
+			struct xen_netif_extra_info *gso;
+			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
+
+			if (netbk_set_skb_gso(vif, skb, gso)) {
+				kfree_skb(skb);
+				netbk_tx_err(vif, &txreq, idx);
+				continue;
+			}
+		}
+
+		/* XXX could copy straight to head */
+		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
+		if (!page) {
+			kfree_skb(skb);
+			netbk_tx_err(vif, &txreq, idx);
+			continue;
+		}
+
+		netbk->mmap_pages[pending_idx] = page;
+
+		gop->source.u.ref = txreq.gref;
+		gop->source.domid = vif->domid;
+		gop->source.offset = txreq.offset;
+
+		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
+		gop->dest.domid = DOMID_SELF;
+		gop->dest.offset = txreq.offset;
+
+		gop->len = txreq.size;
+		gop->flags = GNTCOPY_source_gref;
+
+		gop++;
+
+		memcpy(&netbk->pending_tx_info[pending_idx].req,
+		       &txreq, sizeof(txreq));
+		netbk->pending_tx_info[pending_idx].vif = vif;
+		*((u16 *)skb->data) = pending_idx;
+
+		__skb_put(skb, data_len);
+
+		skb_shinfo(skb)->nr_frags = ret;
+		if (data_len < txreq.size) {
+			skb_shinfo(skb)->nr_frags++;
+			skb_shinfo(skb)->frags[0].page =
+				(void *)(unsigned long)pending_idx;
+		} else {
+			/* Discriminate from any valid pending_idx value. */
+			skb_shinfo(skb)->frags[0].page = (void *)~0UL;
+		}
+
+		__skb_queue_tail(&netbk->tx_queue, skb);
+
+		netbk->pending_cons++;
+
+		request_gop = xen_netbk_get_requests(netbk, vif,
+						     skb, txfrags, gop);
+		if (request_gop == NULL) {
+			kfree_skb(skb);
+			netbk_tx_err(vif, &txreq, idx);
+			continue;
+		}
+		gop = request_gop;
+
+		vif->tx.req_cons = idx;
+		xen_netbk_check_rx_xenvif(vif);
+
+		if ((gop-netbk->tx_copy_ops) >= ARRAY_SIZE(netbk->tx_copy_ops))
+			break;
+	}
+
+	return gop - netbk->tx_copy_ops;
+}
+
+static void xen_netbk_tx_submit(struct xen_netbk *netbk)
+{
+	struct gnttab_copy *gop = netbk->tx_copy_ops;
+	struct sk_buff *skb;
+
+	while ((skb = __skb_dequeue(&netbk->tx_queue)) != NULL) {
+		struct xen_netif_tx_request *txp;
+		struct xenvif *vif;
+		u16 pending_idx;
+		unsigned data_len;
+
+		pending_idx = *((u16 *)skb->data);
+		vif = netbk->pending_tx_info[pending_idx].vif;
+		txp = &netbk->pending_tx_info[pending_idx].req;
+
+		/* Check the remap error code. */
+		if (unlikely(xen_netbk_tx_check_gop(netbk, skb, &gop))) {
+			netdev_dbg(vif->dev, "netback grant failed.\n");
+			skb_shinfo(skb)->nr_frags = 0;
+			kfree_skb(skb);
+			continue;
+		}
+
+		data_len = skb->len;
+		memcpy(skb->data,
+		       (void *)(idx_to_kaddr(netbk, pending_idx)|txp->offset),
+		       data_len);
+		if (data_len < txp->size) {
+			/* Append the packet payload as a fragment. */
+			txp->offset += data_len;
+			txp->size -= data_len;
+		} else {
+			/* Schedule a response immediately. */
+			xen_netbk_idx_release(netbk, pending_idx);
+		}
+
+		if (txp->flags & XEN_NETTXF_csum_blank)
+			skb->ip_summed = CHECKSUM_PARTIAL;
+		else if (txp->flags & XEN_NETTXF_data_validated)
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		xen_netbk_fill_frags(netbk, skb);
+
+		/*
+		 * If the initial fragment was < PKT_PROT_LEN then
+		 * pull through some bytes from the other fragments to
+		 * increase the linear region to PKT_PROT_LEN bytes.
+		 */
+		if (skb_headlen(skb) < PKT_PROT_LEN && skb_is_nonlinear(skb)) {
+			int target = min_t(int, skb->len, PKT_PROT_LEN);
+			__pskb_pull_tail(skb, target - skb_headlen(skb));
+		}
+
+		skb->dev      = vif->dev;
+		skb->protocol = eth_type_trans(skb, skb->dev);
+
+		if (checksum_setup(vif, skb)) {
+			netdev_dbg(vif->dev,
+				   "Can't setup checksum in net_tx_action\n");
+			kfree_skb(skb);
+			continue;
+		}
+
+		vif->dev->stats.rx_bytes += skb->len;
+		vif->dev->stats.rx_packets++;
+
+		xenvif_receive_skb(vif, skb);
+	}
+}
+
+/* Called after netfront has transmitted */
+static void xen_netbk_tx_action(struct xen_netbk *netbk)
+{
+	unsigned nr_gops;
+	int ret;
+
+	nr_gops = xen_netbk_tx_build_gops(netbk);
+
+	if (nr_gops == 0)
+		return;
+	ret = HYPERVISOR_grant_table_op(GNTTABOP_copy,
+					netbk->tx_copy_ops, nr_gops);
+	BUG_ON(ret);
+
+	xen_netbk_tx_submit(netbk);
+
+}
+
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx)
+{
+	struct xenvif *vif;
+	struct pending_tx_info *pending_tx_info;
+	pending_ring_idx_t index;
+
+	/* Already complete? */
+	if (netbk->mmap_pages[pending_idx] == NULL)
+		return;
+
+	pending_tx_info = &netbk->pending_tx_info[pending_idx];
+
+	vif = pending_tx_info->vif;
+
+	make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY);
+
+	index = pending_index(netbk->pending_prod++);
+	netbk->pending_ring[index] = pending_idx;
+
+	xenvif_put(vif);
+
+	netbk->mmap_pages[pending_idx]->mapping = 0;
+	put_page(netbk->mmap_pages[pending_idx]);
+	netbk->mmap_pages[pending_idx] = NULL;
+}
+
+static void make_tx_response(struct xenvif *vif,
+			     struct xen_netif_tx_request *txp,
+			     s8       st)
+{
+	RING_IDX i = vif->tx.rsp_prod_pvt;
+	struct xen_netif_tx_response *resp;
+	int notify;
+
+	resp = RING_GET_RESPONSE(&vif->tx, i);
+	resp->id     = txp->id;
+	resp->status = st;
+
+	if (txp->flags & XEN_NETTXF_extra_info)
+		RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+
+	vif->tx.rsp_prod_pvt = ++i;
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify);
+	if (notify)
+		notify_remote_via_irq(vif->irq);
+}
+
+static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
+					     u16      id,
+					     s8       st,
+					     u16      offset,
+					     u16      size,
+					     u16      flags)
+{
+	RING_IDX i = vif->rx.rsp_prod_pvt;
+	struct xen_netif_rx_response *resp;
+
+	resp = RING_GET_RESPONSE(&vif->rx, i);
+	resp->offset     = offset;
+	resp->flags      = flags;
+	resp->id         = id;
+	resp->status     = (s16)size;
+	if (st < 0)
+		resp->status = (s16)st;
+
+	vif->rx.rsp_prod_pvt = ++i;
+
+	return resp;
+}
+
+static inline int rx_work_todo(struct xen_netbk *netbk)
+{
+	return !skb_queue_empty(&netbk->rx_queue);
+}
+
+static inline int tx_work_todo(struct xen_netbk *netbk)
+{
+
+	if (((nr_pending_reqs(netbk) + MAX_SKB_FRAGS) < MAX_PENDING_REQS) &&
+			!list_empty(&netbk->net_schedule_list))
+		return 1;
+
+	return 0;
+}
+
+static int xen_netbk_kthread(void *data)
+{
+	struct xen_netbk *netbk = data;
+	while (!kthread_should_stop()) {
+		wait_event_interruptible(netbk->wq,
+				rx_work_todo(netbk) ||
+				tx_work_todo(netbk) ||
+				kthread_should_stop());
+		cond_resched();
+
+		if (kthread_should_stop())
+			break;
+
+		if (rx_work_todo(netbk))
+			xen_netbk_rx_action(netbk);
+
+		if (tx_work_todo(netbk))
+			xen_netbk_tx_action(netbk);
+	}
+
+	return 0;
+}
+
+void xen_netbk_unmap_frontend_rings(struct xenvif *vif)
+{
+	struct gnttab_unmap_grant_ref op;
+
+	if (vif->tx.sring) {
+		gnttab_set_unmap_op(&op, (unsigned long)vif->tx_comms_area->addr,
+				    GNTMAP_host_map, vif->tx_shmem_handle);
+
+		if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
+			BUG();
+	}
+
+	if (vif->rx.sring) {
+		gnttab_set_unmap_op(&op, (unsigned long)vif->rx_comms_area->addr,
+				    GNTMAP_host_map, vif->rx_shmem_handle);
+
+		if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
+			BUG();
+	}
+	if (vif->rx_comms_area)
+		free_vm_area(vif->rx_comms_area);
+	if (vif->tx_comms_area)
+		free_vm_area(vif->tx_comms_area);
+}
+
+int xen_netbk_map_frontend_rings(struct xenvif *vif,
+				 grant_ref_t tx_ring_ref,
+				 grant_ref_t rx_ring_ref)
+{
+	struct gnttab_map_grant_ref op;
+	struct xen_netif_tx_sring *txs;
+	struct xen_netif_rx_sring *rxs;
+
+	int err = -ENOMEM;
+
+	vif->tx_comms_area = alloc_vm_area(PAGE_SIZE);
+	if (vif->tx_comms_area == NULL)
+		goto err;
+
+	vif->rx_comms_area = alloc_vm_area(PAGE_SIZE);
+	if (vif->rx_comms_area == NULL)
+		goto err;
+
+	gnttab_set_map_op(&op, (unsigned long)vif->tx_comms_area->addr,
+			  GNTMAP_host_map, tx_ring_ref, vif->domid);
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
+		BUG();
+
+	if (op.status) {
+		netdev_warn(vif->dev,
+			    "failed to map tx ring. err=%d status=%d\n",
+			    err, op.status);
+		err = op.status;
+		goto err;
+	}
+
+	vif->tx_shmem_ref    = tx_ring_ref;
+	vif->tx_shmem_handle = op.handle;
+
+	txs = (struct xen_netif_tx_sring *)vif->tx_comms_area->addr;
+	BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE);
+
+	gnttab_set_map_op(&op, (unsigned long)vif->rx_comms_area->addr,
+			  GNTMAP_host_map, rx_ring_ref, vif->domid);
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
+		BUG();
+
+	if (op.status) {
+		netdev_warn(vif->dev,
+			    "failed to map rx ring. err=%d status=%d\n",
+			    err, op.status);
+		err = op.status;
+		goto err;
+	}
+
+	vif->rx_shmem_ref     = rx_ring_ref;
+	vif->rx_shmem_handle  = op.handle;
+	vif->rx_req_cons_peek = 0;
+
+	rxs = (struct xen_netif_rx_sring *)vif->rx_comms_area->addr;
+	BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE);
+
+	return 0;
+
+err:
+	xen_netbk_unmap_frontend_rings(vif);
+	return err;
+}
+
+static int __init netback_init(void)
+{
+	int i;
+	int rc = 0;
+	int group;
+
+	if (!xen_pv_domain())
+		return -ENODEV;
+
+	xen_netbk_group_nr = num_online_cpus();
+	xen_netbk = vzalloc(sizeof(struct xen_netbk) * xen_netbk_group_nr);
+	if (!xen_netbk) {
+		printk(KERN_ALERT "%s: out of memory\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (group = 0; group < xen_netbk_group_nr; group++) {
+		struct xen_netbk *netbk = &xen_netbk[group];
+		skb_queue_head_init(&netbk->rx_queue);
+		skb_queue_head_init(&netbk->tx_queue);
+
+		init_timer(&netbk->net_timer);
+		netbk->net_timer.data = (unsigned long)netbk;
+		netbk->net_timer.function = xen_netbk_alarm;
+
+		netbk->pending_cons = 0;
+		netbk->pending_prod = MAX_PENDING_REQS;
+		for (i = 0; i < MAX_PENDING_REQS; i++)
+			netbk->pending_ring[i] = i;
+
+		init_waitqueue_head(&netbk->wq);
+		netbk->task = kthread_create(xen_netbk_kthread,
+					     (void *)netbk,
+					     "netback/%u", group);
+
+		if (IS_ERR(netbk->task)) {
+			printk(KERN_ALERT "kthread_run() fails at netback\n");
+			del_timer(&netbk->net_timer);
+			rc = PTR_ERR(netbk->task);
+			goto failed_init;
+		}
+
+		kthread_bind(netbk->task, group);
+
+		INIT_LIST_HEAD(&netbk->net_schedule_list);
+
+		spin_lock_init(&netbk->net_schedule_list_lock);
+
+		atomic_set(&netbk->netfront_count, 0);
+
+		wake_up_process(netbk->task);
+	}
+
+	rc = xenvif_xenbus_init();
+	if (rc)
+		goto failed_init;
+
+	return 0;
+
+failed_init:
+	while (--group >= 0) {
+		struct xen_netbk *netbk = &xen_netbk[group];
+		for (i = 0; i < MAX_PENDING_REQS; i++) {
+			if (netbk->mmap_pages[i])
+				__free_page(netbk->mmap_pages[i]);
+		}
+		del_timer(&netbk->net_timer);
+		kthread_stop(netbk->task);
+	}
+	vfree(xen_netbk);
+	return rc;
+
+}
+
+module_init(netback_init);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
new file mode 100644
index 000000000000..22b8c3505991
--- /dev/null
+++ b/drivers/net/xen-netback/xenbus.c
@@ -0,0 +1,490 @@
+/*
+ * Xenbus code for netif backend
+ *
+ * Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au>
+ * Copyright (C) 2005 XenSource Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+*/
+
+#include "common.h"
+
+struct backend_info {
+	struct xenbus_device *dev;
+	struct xenvif *vif;
+	enum xenbus_state frontend_state;
+	struct xenbus_watch hotplug_status_watch;
+	int have_hotplug_status_watch:1;
+};
+
+static int connect_rings(struct backend_info *);
+static void connect(struct backend_info *);
+static void backend_create_xenvif(struct backend_info *be);
+static void unregister_hotplug_status_watch(struct backend_info *be);
+
+static int netback_remove(struct xenbus_device *dev)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+	unregister_hotplug_status_watch(be);
+	if (be->vif) {
+		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
+		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
+		xenvif_disconnect(be->vif);
+		be->vif = NULL;
+	}
+	kfree(be);
+	dev_set_drvdata(&dev->dev, NULL);
+	return 0;
+}
+
+
+/**
+ * Entry point to this code when a new device is created.  Allocate the basic
+ * structures and switch to InitWait.
+ */
+static int netback_probe(struct xenbus_device *dev,
+			 const struct xenbus_device_id *id)
+{
+	const char *message;
+	struct xenbus_transaction xbt;
+	int err;
+	int sg;
+	struct backend_info *be = kzalloc(sizeof(struct backend_info),
+					  GFP_KERNEL);
+	if (!be) {
+		xenbus_dev_fatal(dev, -ENOMEM,
+				 "allocating backend structure");
+		return -ENOMEM;
+	}
+
+	be->dev = dev;
+	dev_set_drvdata(&dev->dev, be);
+
+	sg = 1;
+
+	do {
+		err = xenbus_transaction_start(&xbt);
+		if (err) {
+			xenbus_dev_fatal(dev, err, "starting transaction");
+			goto fail;
+		}
+
+		err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", sg);
+		if (err) {
+			message = "writing feature-sg";
+			goto abort_transaction;
+		}
+
+		err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4",
+				    "%d", sg);
+		if (err) {
+			message = "writing feature-gso-tcpv4";
+			goto abort_transaction;
+		}
+
+		/* We support rx-copy path. */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-rx-copy", "%d", 1);
+		if (err) {
+			message = "writing feature-rx-copy";
+			goto abort_transaction;
+		}
+
+		/*
+		 * We don't support rx-flip path (except old guests who don't
+		 * grok this feature flag).
+		 */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-rx-flip", "%d", 0);
+		if (err) {
+			message = "writing feature-rx-flip";
+			goto abort_transaction;
+		}
+
+		err = xenbus_transaction_end(xbt, 0);
+	} while (err == -EAGAIN);
+
+	if (err) {
+		xenbus_dev_fatal(dev, err, "completing transaction");
+		goto fail;
+	}
+
+	err = xenbus_switch_state(dev, XenbusStateInitWait);
+	if (err)
+		goto fail;
+
+	/* This kicks hotplug scripts, so do it immediately. */
+	backend_create_xenvif(be);
+
+	return 0;
+
+abort_transaction:
+	xenbus_transaction_end(xbt, 1);
+	xenbus_dev_fatal(dev, err, "%s", message);
+fail:
+	pr_debug("failed");
+	netback_remove(dev);
+	return err;
+}
+
+
+/*
+ * Handle the creation of the hotplug script environment.  We add the script
+ * and vif variables to the environment, for the benefit of the vif-* hotplug
+ * scripts.
+ */
+static int netback_uevent(struct xenbus_device *xdev,
+			  struct kobj_uevent_env *env)
+{
+	struct backend_info *be = dev_get_drvdata(&xdev->dev);
+	char *val;
+
+	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
+	if (IS_ERR(val)) {
+		int err = PTR_ERR(val);
+		xenbus_dev_fatal(xdev, err, "reading script");
+		return err;
+	} else {
+		if (add_uevent_var(env, "script=%s", val)) {
+			kfree(val);
+			return -ENOMEM;
+		}
+		kfree(val);
+	}
+
+	if (!be || !be->vif)
+		return 0;
+
+	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
+}
+
+
+static void backend_create_xenvif(struct backend_info *be)
+{
+	int err;
+	long handle;
+	struct xenbus_device *dev = be->dev;
+
+	if (be->vif != NULL)
+		return;
+
+	err = xenbus_scanf(XBT_NIL, dev->nodename, "handle", "%li", &handle);
+	if (err != 1) {
+		xenbus_dev_fatal(dev, err, "reading handle");
+		return;
+	}
+
+	be->vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle);
+	if (IS_ERR(be->vif)) {
+		err = PTR_ERR(be->vif);
+		be->vif = NULL;
+		xenbus_dev_fatal(dev, err, "creating interface");
+		return;
+	}
+
+	kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
+}
+
+
+static void disconnect_backend(struct xenbus_device *dev)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+	if (be->vif) {
+		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
+		xenvif_disconnect(be->vif);
+		be->vif = NULL;
+	}
+}
+
+/**
+ * Callback received when the frontend's state changes.
+ */
+static void frontend_changed(struct xenbus_device *dev,
+			     enum xenbus_state frontend_state)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
+
+	pr_debug("frontend state %s", xenbus_strstate(frontend_state));
+
+	be->frontend_state = frontend_state;
+
+	switch (frontend_state) {
+	case XenbusStateInitialising:
+		if (dev->state == XenbusStateClosed) {
+			printk(KERN_INFO "%s: %s: prepare for reconnect\n",
+			       __func__, dev->nodename);
+			xenbus_switch_state(dev, XenbusStateInitWait);
+		}
+		break;
+
+	case XenbusStateInitialised:
+		break;
+
+	case XenbusStateConnected:
+		if (dev->state == XenbusStateConnected)
+			break;
+		backend_create_xenvif(be);
+		if (be->vif)
+			connect(be);
+		break;
+
+	case XenbusStateClosing:
+		if (be->vif)
+			kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
+		disconnect_backend(dev);
+		xenbus_switch_state(dev, XenbusStateClosing);
+		break;
+
+	case XenbusStateClosed:
+		xenbus_switch_state(dev, XenbusStateClosed);
+		if (xenbus_dev_is_online(dev))
+			break;
+		/* fall through if not online */
+	case XenbusStateUnknown:
+		device_unregister(&dev->dev);
+		break;
+
+	default:
+		xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
+				 frontend_state);
+		break;
+	}
+}
+
+
+static void xen_net_read_rate(struct xenbus_device *dev,
+			      unsigned long *bytes, unsigned long *usec)
+{
+	char *s, *e;
+	unsigned long b, u;
+	char *ratestr;
+
+	/* Default to unlimited bandwidth. */
+	*bytes = ~0UL;
+	*usec = 0;
+
+	ratestr = xenbus_read(XBT_NIL, dev->nodename, "rate", NULL);
+	if (IS_ERR(ratestr))
+		return;
+
+	s = ratestr;
+	b = simple_strtoul(s, &e, 10);
+	if ((s == e) || (*e != ','))
+		goto fail;
+
+	s = e + 1;
+	u = simple_strtoul(s, &e, 10);
+	if ((s == e) || (*e != '\0'))
+		goto fail;
+
+	*bytes = b;
+	*usec = u;
+
+	kfree(ratestr);
+	return;
+
+ fail:
+	pr_warn("Failed to parse network rate limit. Traffic unlimited.\n");
+	kfree(ratestr);
+}
+
+static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
+{
+	char *s, *e, *macstr;
+	int i;
+
+	macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL);
+	if (IS_ERR(macstr))
+		return PTR_ERR(macstr);
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac[i] = simple_strtoul(s, &e, 16);
+		if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) {
+			kfree(macstr);
+			return -ENOENT;
+		}
+		s = e+1;
+	}
+
+	kfree(macstr);
+	return 0;
+}
+
+static void unregister_hotplug_status_watch(struct backend_info *be)
+{
+	if (be->have_hotplug_status_watch) {
+		unregister_xenbus_watch(&be->hotplug_status_watch);
+		kfree(be->hotplug_status_watch.node);
+	}
+	be->have_hotplug_status_watch = 0;
+}
+
+static void hotplug_status_changed(struct xenbus_watch *watch,
+				   const char **vec,
+				   unsigned int vec_size)
+{
+	struct backend_info *be = container_of(watch,
+					       struct backend_info,
+					       hotplug_status_watch);
+	char *str;
+	unsigned int len;
+
+	str = xenbus_read(XBT_NIL, be->dev->nodename, "hotplug-status", &len);
+	if (IS_ERR(str))
+		return;
+	if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
+		xenbus_switch_state(be->dev, XenbusStateConnected);
+		/* Not interested in this watch anymore. */
+		unregister_hotplug_status_watch(be);
+	}
+	kfree(str);
+}
+
+static void connect(struct backend_info *be)
+{
+	int err;
+	struct xenbus_device *dev = be->dev;
+
+	err = connect_rings(be);
+	if (err)
+		return;
+
+	err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
+		return;
+	}
+
+	xen_net_read_rate(dev, &be->vif->credit_bytes,
+			  &be->vif->credit_usec);
+	be->vif->remaining_credit = be->vif->credit_bytes;
+
+	unregister_hotplug_status_watch(be);
+	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
+				   hotplug_status_changed,
+				   "%s/%s", dev->nodename, "hotplug-status");
+	if (err) {
+		/* Switch now, since we can't do a watch. */
+		xenbus_switch_state(dev, XenbusStateConnected);
+	} else {
+		be->have_hotplug_status_watch = 1;
+	}
+
+	netif_wake_queue(be->vif->dev);
+}
+
+
+static int connect_rings(struct backend_info *be)
+{
+	struct xenvif *vif = be->vif;
+	struct xenbus_device *dev = be->dev;
+	unsigned long tx_ring_ref, rx_ring_ref;
+	unsigned int evtchn, rx_copy;
+	int err;
+	int val;
+
+	err = xenbus_gather(XBT_NIL, dev->otherend,
+			    "tx-ring-ref", "%lu", &tx_ring_ref,
+			    "rx-ring-ref", "%lu", &rx_ring_ref,
+			    "event-channel", "%u", &evtchn, NULL);
+	if (err) {
+		xenbus_dev_fatal(dev, err,
+				 "reading %s/ring-ref and event-channel",
+				 dev->otherend);
+		return err;
+	}
+
+	err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
+			   &rx_copy);
+	if (err == -ENOENT) {
+		err = 0;
+		rx_copy = 0;
+	}
+	if (err < 0) {
+		xenbus_dev_fatal(dev, err, "reading %s/request-rx-copy",
+				 dev->otherend);
+		return err;
+	}
+	if (!rx_copy)
+		return -EOPNOTSUPP;
+
+	if (vif->dev->tx_queue_len != 0) {
+		if (xenbus_scanf(XBT_NIL, dev->otherend,
+				 "feature-rx-notify", "%d", &val) < 0)
+			val = 0;
+		if (val)
+			vif->can_queue = 1;
+		else
+			/* Must be non-zero for pfifo_fast to work. */
+			vif->dev->tx_queue_len = 1;
+	}
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->can_sg = !!val;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->gso = !!val;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->gso_prefix = !!val;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->csum = !val;
+
+	/* Map the shared frame, irq etc. */
+	err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref, evtchn);
+	if (err) {
+		xenbus_dev_fatal(dev, err,
+				 "mapping shared-frames %lu/%lu port %u",
+				 tx_ring_ref, rx_ring_ref, evtchn);
+		return err;
+	}
+	return 0;
+}
+
+
+/* ** Driver Registration ** */
+
+
+static const struct xenbus_device_id netback_ids[] = {
+	{ "vif" },
+	{ "" }
+};
+
+
+static struct xenbus_driver netback = {
+	.name = "vif",
+	.owner = THIS_MODULE,
+	.ids = netback_ids,
+	.probe = netback_probe,
+	.remove = netback_remove,
+	.uevent = netback_uevent,
+	.otherend_changed = frontend_changed,
+};
+
+int xenvif_xenbus_init(void)
+{
+	return xenbus_register_backend(&netback);
+}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 5b399b54fef7..5c8d9c385be0 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -359,7 +359,7 @@ static void xennet_tx_buf_gc(struct net_device *dev)
 			struct xen_netif_tx_response *txrsp;
 
 			txrsp = RING_GET_RESPONSE(&np->tx, cons);
-			if (txrsp->status == NETIF_RSP_NULL)
+			if (txrsp->status == XEN_NETIF_RSP_NULL)
 				continue;
 
 			id  = txrsp->id;
@@ -416,7 +416,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 	   larger than a page), split it it into page-sized chunks. */
 	while (len > PAGE_SIZE - offset) {
 		tx->size = PAGE_SIZE - offset;
-		tx->flags |= NETTXF_more_data;
+		tx->flags |= XEN_NETTXF_more_data;
 		len -= tx->size;
 		data += tx->size;
 		offset = 0;
@@ -442,7 +442,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
 
-		tx->flags |= NETTXF_more_data;
+		tx->flags |= XEN_NETTXF_more_data;
 
 		id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
 		np->tx_skbs[id].skb = skb_get(skb);
@@ -517,10 +517,10 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx->flags = 0;
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		/* local packet? */
-		tx->flags |= NETTXF_csum_blank | NETTXF_data_validated;
+		tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
 	else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
 		/* remote but checksummed. */
-		tx->flags |= NETTXF_data_validated;
+		tx->flags |= XEN_NETTXF_data_validated;
 
 	if (skb_shinfo(skb)->gso_size) {
 		struct xen_netif_extra_info *gso;
@@ -531,7 +531,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (extra)
 			extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE;
 		else
-			tx->flags |= NETTXF_extra_info;
+			tx->flags |= XEN_NETTXF_extra_info;
 
 		gso->u.gso.size = skb_shinfo(skb)->gso_size;
 		gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
@@ -651,7 +651,7 @@ static int xennet_get_responses(struct netfront_info *np,
 	int err = 0;
 	unsigned long ret;
 
-	if (rx->flags & NETRXF_extra_info) {
+	if (rx->flags & XEN_NETRXF_extra_info) {
 		err = xennet_get_extras(np, extras, rp);
 		cons = np->rx.rsp_cons;
 	}
@@ -688,7 +688,7 @@ static int xennet_get_responses(struct netfront_info *np,
 		__skb_queue_tail(list, skb);
 
 next:
-		if (!(rx->flags & NETRXF_more_data))
+		if (!(rx->flags & XEN_NETRXF_more_data))
 			break;
 
 		if (cons + frags == rp) {
@@ -983,9 +983,9 @@ err:
 		skb->truesize += skb->data_len - (RX_COPY_THRESHOLD - len);
 		skb->len += skb->data_len;
 
-		if (rx->flags & NETRXF_csum_blank)
+		if (rx->flags & XEN_NETRXF_csum_blank)
 			skb->ip_summed = CHECKSUM_PARTIAL;
-		else if (rx->flags & NETRXF_data_validated)
+		else if (rx->flags & XEN_NETRXF_data_validated)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		__skb_queue_tail(&rxq, skb);
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index 518481c95f18..cb94668f6e9f 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -22,50 +22,50 @@
 
 /*
  * This is the 'wire' format for packets:
- *  Request 1: netif_tx_request -- NETTXF_* (any flags)
- * [Request 2: netif_tx_extra]  (only if request 1 has NETTXF_extra_info)
- * [Request 3: netif_tx_extra]  (only if request 2 has XEN_NETIF_EXTRA_MORE)
- *  Request 4: netif_tx_request -- NETTXF_more_data
- *  Request 5: netif_tx_request -- NETTXF_more_data
+ *  Request 1: xen_netif_tx_request  -- XEN_NETTXF_* (any flags)
+ * [Request 2: xen_netif_extra_info]    (only if request 1 has XEN_NETTXF_extra_info)
+ * [Request 3: xen_netif_extra_info]    (only if request 2 has XEN_NETIF_EXTRA_MORE)
+ *  Request 4: xen_netif_tx_request  -- XEN_NETTXF_more_data
+ *  Request 5: xen_netif_tx_request  -- XEN_NETTXF_more_data
  *  ...
- *  Request N: netif_tx_request -- 0
+ *  Request N: xen_netif_tx_request  -- 0
  */
 
 /* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _NETTXF_csum_blank     (0)
-#define  NETTXF_csum_blank     (1U<<_NETTXF_csum_blank)
+#define _XEN_NETTXF_csum_blank		(0)
+#define  XEN_NETTXF_csum_blank		(1U<<_XEN_NETTXF_csum_blank)
 
 /* Packet data has been validated against protocol checksum. */
-#define _NETTXF_data_validated (1)
-#define  NETTXF_data_validated (1U<<_NETTXF_data_validated)
+#define _XEN_NETTXF_data_validated	(1)
+#define  XEN_NETTXF_data_validated	(1U<<_XEN_NETTXF_data_validated)
 
 /* Packet continues in the next request descriptor. */
-#define _NETTXF_more_data      (2)
-#define  NETTXF_more_data      (1U<<_NETTXF_more_data)
+#define _XEN_NETTXF_more_data		(2)
+#define  XEN_NETTXF_more_data		(1U<<_XEN_NETTXF_more_data)
 
 /* Packet to be followed by extra descriptor(s). */
-#define _NETTXF_extra_info     (3)
-#define  NETTXF_extra_info     (1U<<_NETTXF_extra_info)
+#define _XEN_NETTXF_extra_info		(3)
+#define  XEN_NETTXF_extra_info		(1U<<_XEN_NETTXF_extra_info)
 
 struct xen_netif_tx_request {
     grant_ref_t gref;      /* Reference to buffer page */
     uint16_t offset;       /* Offset within buffer page */
-    uint16_t flags;        /* NETTXF_* */
+    uint16_t flags;        /* XEN_NETTXF_* */
     uint16_t id;           /* Echoed in response message. */
     uint16_t size;         /* Packet size in bytes.       */
 };
 
-/* Types of netif_extra_info descriptors. */
-#define XEN_NETIF_EXTRA_TYPE_NONE  (0)  /* Never used - invalid */
-#define XEN_NETIF_EXTRA_TYPE_GSO   (1)  /* u.gso */
-#define XEN_NETIF_EXTRA_TYPE_MAX   (2)
+/* Types of xen_netif_extra_info descriptors. */
+#define XEN_NETIF_EXTRA_TYPE_NONE	(0)  /* Never used - invalid */
+#define XEN_NETIF_EXTRA_TYPE_GSO	(1)  /* u.gso */
+#define XEN_NETIF_EXTRA_TYPE_MAX	(2)
 
-/* netif_extra_info flags. */
-#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
-#define XEN_NETIF_EXTRA_FLAG_MORE  (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
+/* xen_netif_extra_info flags. */
+#define _XEN_NETIF_EXTRA_FLAG_MORE	(0)
+#define  XEN_NETIF_EXTRA_FLAG_MORE	(1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
 
 /* GSO types - only TCPv4 currently supported. */
-#define XEN_NETIF_GSO_TYPE_TCPV4        (1)
+#define XEN_NETIF_GSO_TYPE_TCPV4	(1)
 
 /*
  * This structure needs to fit within both netif_tx_request and
@@ -107,7 +107,7 @@ struct xen_netif_extra_info {
 
 struct xen_netif_tx_response {
 	uint16_t id;
-	int16_t  status;       /* NETIF_RSP_* */
+	int16_t  status;       /* XEN_NETIF_RSP_* */
 };
 
 struct xen_netif_rx_request {
@@ -116,25 +116,29 @@ struct xen_netif_rx_request {
 };
 
 /* Packet data has been validated against protocol checksum. */
-#define _NETRXF_data_validated (0)
-#define  NETRXF_data_validated (1U<<_NETRXF_data_validated)
+#define _XEN_NETRXF_data_validated	(0)
+#define  XEN_NETRXF_data_validated	(1U<<_XEN_NETRXF_data_validated)
 
 /* Protocol checksum field is blank in the packet (hardware offload)? */
-#define _NETRXF_csum_blank     (1)
-#define  NETRXF_csum_blank     (1U<<_NETRXF_csum_blank)
+#define _XEN_NETRXF_csum_blank		(1)
+#define  XEN_NETRXF_csum_blank		(1U<<_XEN_NETRXF_csum_blank)
 
 /* Packet continues in the next request descriptor. */
-#define _NETRXF_more_data      (2)
-#define  NETRXF_more_data      (1U<<_NETRXF_more_data)
+#define _XEN_NETRXF_more_data		(2)
+#define  XEN_NETRXF_more_data		(1U<<_XEN_NETRXF_more_data)
 
 /* Packet to be followed by extra descriptor(s). */
-#define _NETRXF_extra_info     (3)
-#define  NETRXF_extra_info     (1U<<_NETRXF_extra_info)
+#define _XEN_NETRXF_extra_info		(3)
+#define  XEN_NETRXF_extra_info		(1U<<_XEN_NETRXF_extra_info)
+
+/* GSO Prefix descriptor. */
+#define _XEN_NETRXF_gso_prefix		(4)
+#define  XEN_NETRXF_gso_prefix		(1U<<_XEN_NETRXF_gso_prefix)
 
 struct xen_netif_rx_response {
     uint16_t id;
     uint16_t offset;       /* Offset in page of start of received packet  */
-    uint16_t flags;        /* NETRXF_* */
+    uint16_t flags;        /* XEN_NETRXF_* */
     int16_t  status;       /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */
 };
 
@@ -149,10 +153,10 @@ DEFINE_RING_TYPES(xen_netif_rx,
 		  struct xen_netif_rx_request,
 		  struct xen_netif_rx_response);
 
-#define NETIF_RSP_DROPPED         -2
-#define NETIF_RSP_ERROR           -1
-#define NETIF_RSP_OKAY             0
-/* No response: used for auxiliary requests (e.g., netif_tx_extra). */
-#define NETIF_RSP_NULL             1
+#define XEN_NETIF_RSP_DROPPED	-2
+#define XEN_NETIF_RSP_ERROR	-1
+#define XEN_NETIF_RSP_OKAY	 0
+/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */
+#define XEN_NETIF_RSP_NULL	 1
 
 #endif
-- 
cgit v1.2.3


From 8a4eb5734e8d1dc60a8c28576bbbdfdcc643626d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jpirko@redhat.com>
Date: Sat, 12 Mar 2011 03:14:39 +0000
Subject: net: introduce rx_handler results and logic around that
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch allows rx_handlers to better signalize what to do next to
it's caller. That makes skb->deliver_no_wcard no longer needed.

kernel-doc for rx_handler_result is taken from Nicolas' patch.

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Reviewed-by: Nicolas de Pesloüan <nicolas.2p.debian@free.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 22 +++++++++---------
 drivers/net/macvlan.c           | 11 ++++-----
 include/linux/netdevice.h       | 50 ++++++++++++++++++++++++++++++++++++++++-
 include/linux/skbuff.h          |  5 +----
 net/bridge/br_input.c           | 25 ++++++++++++---------
 net/bridge/br_private.h         |  2 +-
 net/core/dev.c                  | 21 +++++++++++------
 net/core/skbuff.c               |  1 -
 8 files changed, 98 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 04119b1e7cdb..27c413aa15da 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1480,20 +1480,23 @@ static bool bond_should_deliver_exact_match(struct sk_buff *skb,
 	return false;
 }
 
-static struct sk_buff *bond_handle_frame(struct sk_buff *skb)
+static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 {
+	struct sk_buff *skb = *pskb;
 	struct slave *slave;
 	struct net_device *bond_dev;
 	struct bonding *bond;
 
-	skb = skb_share_check(skb, GFP_ATOMIC);
-	if (unlikely(!skb))
-		return NULL;
-
 	slave = bond_slave_get_rcu(skb->dev);
 	bond_dev = ACCESS_ONCE(slave->dev->master);
 	if (unlikely(!bond_dev))
-		return skb;
+		return RX_HANDLER_PASS;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return RX_HANDLER_CONSUMED;
+
+	*pskb = skb;
 
 	bond = netdev_priv(bond_dev);
 
@@ -1501,8 +1504,7 @@ static struct sk_buff *bond_handle_frame(struct sk_buff *skb)
 		slave->dev->last_rx = jiffies;
 
 	if (bond_should_deliver_exact_match(skb, slave, bond)) {
-		skb->deliver_no_wcard = 1;
-		return skb;
+		return RX_HANDLER_EXACT;
 	}
 
 	skb->dev = bond_dev;
@@ -1514,12 +1516,12 @@ static struct sk_buff *bond_handle_frame(struct sk_buff *skb)
 		if (unlikely(skb_cow_head(skb,
 					  skb->data - skb_mac_header(skb)))) {
 			kfree_skb(skb);
-			return NULL;
+			return RX_HANDLER_CONSUMED;
 		}
 		memcpy(eth_hdr(skb)->h_dest, bond_dev->dev_addr, ETH_ALEN);
 	}
 
-	return skb;
+	return RX_HANDLER_ANOTHER;
 }
 
 /* enslave device <slave> to bond device <master> */
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 497991bd3b64..5b37d3c191e4 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -152,9 +152,10 @@ static void macvlan_broadcast(struct sk_buff *skb,
 }
 
 /* called under rcu_read_lock() from netif_receive_skb */
-static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
+static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 {
 	struct macvlan_port *port;
+	struct sk_buff *skb = *pskb;
 	const struct ethhdr *eth = eth_hdr(skb);
 	const struct macvlan_dev *vlan;
 	const struct macvlan_dev *src;
@@ -184,7 +185,7 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
 			 */
 			macvlan_broadcast(skb, port, src->dev,
 					  MACVLAN_MODE_VEPA);
-		return skb;
+		return RX_HANDLER_PASS;
 	}
 
 	if (port->passthru)
@@ -192,12 +193,12 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
 	else
 		vlan = macvlan_hash_lookup(port, eth->h_dest);
 	if (vlan == NULL)
-		return skb;
+		return RX_HANDLER_PASS;
 
 	dev = vlan->dev;
 	if (unlikely(!(dev->flags & IFF_UP))) {
 		kfree_skb(skb);
-		return NULL;
+		return RX_HANDLER_CONSUMED;
 	}
 	len = skb->len + ETH_HLEN;
 	skb = skb_share_check(skb, GFP_ATOMIC);
@@ -211,7 +212,7 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
 
 out:
 	macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0);
-	return NULL;
+	return RX_HANDLER_CONSUMED;
 }
 
 static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 604dbf5051d3..5eeb2cd3631c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -390,7 +390,55 @@ enum gro_result {
 };
 typedef enum gro_result gro_result_t;
 
-typedef struct sk_buff *rx_handler_func_t(struct sk_buff *skb);
+/*
+ * enum rx_handler_result - Possible return values for rx_handlers.
+ * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it
+ * further.
+ * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in
+ * case skb->dev was changed by rx_handler.
+ * @RX_HANDLER_EXACT: Force exact delivery, no wildcard.
+ * @RX_HANDLER_PASS: Do nothing, passe the skb as if no rx_handler was called.
+ *
+ * rx_handlers are functions called from inside __netif_receive_skb(), to do
+ * special processing of the skb, prior to delivery to protocol handlers.
+ *
+ * Currently, a net_device can only have a single rx_handler registered. Trying
+ * to register a second rx_handler will return -EBUSY.
+ *
+ * To register a rx_handler on a net_device, use netdev_rx_handler_register().
+ * To unregister a rx_handler on a net_device, use
+ * netdev_rx_handler_unregister().
+ *
+ * Upon return, rx_handler is expected to tell __netif_receive_skb() what to
+ * do with the skb.
+ *
+ * If the rx_handler consumed to skb in some way, it should return
+ * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for
+ * the skb to be delivered in some other ways.
+ *
+ * If the rx_handler changed skb->dev, to divert the skb to another
+ * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the
+ * new device will be called if it exists.
+ *
+ * If the rx_handler consider the skb should be ignored, it should return
+ * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that
+ * are registred on exact device (ptype->dev == skb->dev).
+ *
+ * If the rx_handler didn't changed skb->dev, but want the skb to be normally
+ * delivered, it should return RX_HANDLER_PASS.
+ *
+ * A device without a registered rx_handler will behave as if rx_handler
+ * returned RX_HANDLER_PASS.
+ */
+
+enum rx_handler_result {
+	RX_HANDLER_CONSUMED,
+	RX_HANDLER_ANOTHER,
+	RX_HANDLER_EXACT,
+	RX_HANDLER_PASS,
+};
+typedef enum rx_handler_result rx_handler_result_t;
+typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
 
 extern void __napi_schedule(struct napi_struct *n);
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 31f02d0b46a7..24cfa626931e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -388,10 +388,7 @@ struct sk_buff {
 	kmemcheck_bitfield_begin(flags2);
 	__u16			queue_mapping:16;
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
-	__u8			ndisc_nodetype:2,
-				deliver_no_wcard:1;
-#else
-	__u8			deliver_no_wcard:1;
+	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ooo_okay:1;
 	kmemcheck_bitfield_end(flags2);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 88e4aa9cb1f9..e2160792e1bc 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -139,21 +139,22 @@ static inline int is_link_local(const unsigned char *dest)
  * Return NULL if skb is handled
  * note: already called with rcu_read_lock
  */
-struct sk_buff *br_handle_frame(struct sk_buff *skb)
+rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 {
 	struct net_bridge_port *p;
+	struct sk_buff *skb = *pskb;
 	const unsigned char *dest = eth_hdr(skb)->h_dest;
 	br_should_route_hook_t *rhook;
 
 	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
-		return skb;
+		return RX_HANDLER_PASS;
 
 	if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
 		goto drop;
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (!skb)
-		return NULL;
+		return RX_HANDLER_CONSUMED;
 
 	p = br_port_get_rcu(skb->dev);
 
@@ -167,10 +168,12 @@ struct sk_buff *br_handle_frame(struct sk_buff *skb)
 			goto forward;
 
 		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev,
-			    NULL, br_handle_local_finish))
-			return NULL;	/* frame consumed by filter */
-		else
-			return skb;	/* continue processing */
+			    NULL, br_handle_local_finish)) {
+			return RX_HANDLER_CONSUMED; /* consumed by filter */
+		} else {
+			*pskb = skb;
+			return RX_HANDLER_PASS;	/* continue processing */
+		}
 	}
 
 forward:
@@ -178,8 +181,10 @@ forward:
 	case BR_STATE_FORWARDING:
 		rhook = rcu_dereference(br_should_route_hook);
 		if (rhook) {
-			if ((*rhook)(skb))
-				return skb;
+			if ((*rhook)(skb)) {
+				*pskb = skb;
+				return RX_HANDLER_PASS;
+			}
 			dest = eth_hdr(skb)->h_dest;
 		}
 		/* fall through */
@@ -194,5 +199,5 @@ forward:
 drop:
 		kfree_skb(skb);
 	}
-	return NULL;
+	return RX_HANDLER_CONSUMED;
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index f7afc364d777..19e2f46ed086 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -379,7 +379,7 @@ extern void br_features_recompute(struct net_bridge *br);
 
 /* br_input.c */
 extern int br_handle_frame_finish(struct sk_buff *skb);
-extern struct sk_buff *br_handle_frame(struct sk_buff *skb);
+extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
 
 /* br_ioctl.c */
 extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
diff --git a/net/core/dev.c b/net/core/dev.c
index 0d39032e9621..0b88eba97dab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3070,6 +3070,8 @@ out:
  *	on a failure.
  *
  *	The caller must hold the rtnl_mutex.
+ *
+ *	For a general description of rx_handler, see enum rx_handler_result.
  */
 int netdev_rx_handler_register(struct net_device *dev,
 			       rx_handler_func_t *rx_handler,
@@ -3129,6 +3131,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	rx_handler_func_t *rx_handler;
 	struct net_device *orig_dev;
 	struct net_device *null_or_dev;
+	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
 	__be16 type;
 
@@ -3181,18 +3184,22 @@ ncls:
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (rx_handler) {
-		struct net_device *prev_dev;
-
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = NULL;
 		}
-		prev_dev = skb->dev;
-		skb = rx_handler(skb);
-		if (!skb)
+		switch (rx_handler(&skb)) {
+		case RX_HANDLER_CONSUMED:
 			goto out;
-		if (skb->dev != prev_dev)
+		case RX_HANDLER_ANOTHER:
 			goto another_round;
+		case RX_HANDLER_EXACT:
+			deliver_exact = true;
+		case RX_HANDLER_PASS:
+			break;
+		default:
+			BUG();
+		}
 	}
 
 	if (vlan_tx_tag_present(skb)) {
@@ -3210,7 +3217,7 @@ ncls:
 	vlan_on_bond_hook(skb);
 
 	/* deliver only exact match when indicated */
-	null_or_dev = skb->deliver_no_wcard ? skb->dev : NULL;
+	null_or_dev = deliver_exact ? skb->dev : NULL;
 
 	type = skb->protocol;
 	list_for_each_entry_rcu(ptype,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1eb526a848ff..801dd08908f9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -523,7 +523,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->ip_summed		= old->ip_summed;
 	skb_copy_queue_mapping(new, old);
 	new->priority		= old->priority;
-	new->deliver_no_wcard	= old->deliver_no_wcard;
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	new->ipvs_property	= old->ipvs_property;
 #endif
-- 
cgit v1.2.3


From c7f404b40a3665d9f4e9a927cc5c1ee0479ed8f9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 Mar 2011 06:59:40 -0400
Subject: vfs: new superblock methods to override /proc/*/mount{s,info}

a) ->show_devname(m, mnt) - what to put into devname columns in mounts,
mountinfo and mountstats
b) ->show_path(m, mnt) - what to put into relative path column in mountinfo

Leaving those NULL gives old behaviour.  NFS switched to using those.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c     | 39 ++++++++++++++++++++++++++++++---------
 fs/nfs/super.c     | 28 ++++++++++++++++++++++++++++
 include/linux/fs.h |  2 ++
 3 files changed, 60 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index dffe6f49ab93..75d843ae46d2 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -978,7 +978,13 @@ static int show_vfsmnt(struct seq_file *m, void *v)
 	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 
-	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	if (mnt->mnt_sb->s_op->show_devname) {
+		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+		if (err)
+			goto out;
+	} else {
+		mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	}
 	seq_putc(m, ' ');
 	seq_path(m, &mnt_path, " \t\n\\");
 	seq_putc(m, ' ');
@@ -1025,7 +1031,12 @@ static int show_mountinfo(struct seq_file *m, void *v)
 
 	seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id,
 		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
-	seq_dentry(m, mnt->mnt_root, " \t\n\\");
+	if (sb->s_op->show_path)
+		err = sb->s_op->show_path(m, mnt);
+	else
+		seq_dentry(m, mnt->mnt_root, " \t\n\\");
+	if (err)
+		goto out;
 	seq_putc(m, ' ');
 	seq_path_root(m, &mnt_path, &root, " \t\n\\");
 	if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
@@ -1060,7 +1071,12 @@ static int show_mountinfo(struct seq_file *m, void *v)
 	seq_puts(m, " - ");
 	show_type(m, sb);
 	seq_putc(m, ' ');
-	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	if (sb->s_op->show_devname)
+		err = sb->s_op->show_devname(m, mnt);
+	else
+		mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	if (err)
+		goto out;
 	seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
 	err = show_sb_opts(m, sb);
 	if (err)
@@ -1086,11 +1102,15 @@ static int show_vfsstat(struct seq_file *m, void *v)
 	int err = 0;
 
 	/* device */
-	if (mnt->mnt_devname) {
-		seq_puts(m, "device ");
-		mangle(m, mnt->mnt_devname);
-	} else
-		seq_puts(m, "no device");
+	if (mnt->mnt_sb->s_op->show_devname) {
+		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+	} else {
+		if (mnt->mnt_devname) {
+			seq_puts(m, "device ");
+			mangle(m, mnt->mnt_devname);
+		} else
+			seq_puts(m, "no device");
+	}
 
 	/* mount point */
 	seq_puts(m, " mounted on ");
@@ -1104,7 +1124,8 @@ static int show_vfsstat(struct seq_file *m, void *v)
 	/* optional statistics */
 	if (mnt->mnt_sb->s_op->show_stats) {
 		seq_putc(m, ' ');
-		err = mnt->mnt_sb->s_op->show_stats(m, mnt);
+		if (!err)
+			err = mnt->mnt_sb->s_op->show_stats(m, mnt);
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index a6ab483c9ad0..79bc61fe2868 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -263,6 +263,8 @@ static match_table_t nfs_local_lock_tokens = {
 static void nfs_umount_begin(struct super_block *);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
 static int  nfs_show_options(struct seq_file *, struct vfsmount *);
+static int  nfs_show_devname(struct seq_file *, struct vfsmount *);
+static int  nfs_show_path(struct seq_file *, struct vfsmount *);
 static int  nfs_show_stats(struct seq_file *, struct vfsmount *);
 static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *);
 static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
@@ -296,6 +298,8 @@ static const struct super_operations nfs_sops = {
 	.evict_inode	= nfs_evict_inode,
 	.umount_begin	= nfs_umount_begin,
 	.show_options	= nfs_show_options,
+	.show_devname	= nfs_show_devname,
+	.show_path	= nfs_show_path,
 	.show_stats	= nfs_show_stats,
 	.remount_fs	= nfs_remount,
 };
@@ -366,6 +370,8 @@ static const struct super_operations nfs4_sops = {
 	.evict_inode	= nfs4_evict_inode,
 	.umount_begin	= nfs_umount_begin,
 	.show_options	= nfs_show_options,
+	.show_devname	= nfs_show_devname,
+	.show_path	= nfs_show_path,
 	.show_stats	= nfs_show_stats,
 	.remount_fs	= nfs_remount,
 };
@@ -726,6 +732,28 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
 	return 0;
 }
 
+static int nfs_show_devname(struct seq_file *m, struct vfsmount *mnt)
+{
+	char *page = (char *) __get_free_page(GFP_KERNEL);
+	char *devname, *dummy;
+	int err = 0;
+	if (!page)
+		return -ENOMEM;
+	devname = nfs_path(&dummy, mnt->mnt_root, page, PAGE_SIZE);
+	if (IS_ERR(devname))
+		err = PTR_ERR(devname);
+	else
+		seq_escape(m, devname, " \t\n\\");
+	free_page((unsigned long)page);
+	return err;
+}
+
+static int nfs_show_path(struct seq_file *m, struct vfsmount *mnt)
+{
+	seq_puts(m, "/");
+	return 0;
+}
+
 /*
  * Present statistical information for this VFS mountpoint
  */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 13df14e2c42e..e6d3fe45981b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1632,6 +1632,8 @@ struct super_operations {
 	void (*umount_begin) (struct super_block *);
 
 	int (*show_options)(struct seq_file *, struct vfsmount *);
+	int (*show_devname)(struct seq_file *, struct vfsmount *);
+	int (*show_path)(struct seq_file *, struct vfsmount *);
 	int (*show_stats)(struct seq_file *, struct vfsmount *);
 #ifdef CONFIG_QUOTA
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
-- 
cgit v1.2.3


From 1a102ff92579edeff5e3d5d3c76ca49977898f00 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 Mar 2011 09:07:58 -0400
Subject: vfs: bury ->get_sb()

This is an ex-parrot.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/Locking |  6 ++--
 Documentation/filesystems/porting |  7 ++++
 Documentation/filesystems/vfs.txt | 56 ++++++++++++++++++--------------
 fs/super.c                        | 67 ++++-----------------------------------
 include/linux/fs.h                | 14 --------
 5 files changed, 47 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 4471a416c274..2e994efe12cb 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -166,13 +166,11 @@ prototypes:
 	void (*kill_sb) (struct super_block *);
 locking rules:
 		may block
-get_sb		yes
 mount		yes
 kill_sb		yes
 
-->get_sb() returns error or 0 with locked superblock attached to the vfsmount
-(exclusive on ->s_umount).
-->mount() returns ERR_PTR or the root dentry.
+->mount() returns ERR_PTR or the root dentry; its superblock should be locked
+on return.
 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 unlocks and drops the reference.
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index dfbcd1b00b0a..0c986c9e8519 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -394,3 +394,10 @@ file) you must return -EOPNOTSUPP if FALLOC_FL_PUNCH_HOLE is set in mode.
 Currently you can only have FALLOC_FL_PUNCH_HOLE with FALLOC_FL_KEEP_SIZE set,
 so the i_size should not change when hole punching, even when puching the end of
 a file off.
+
+--
+[mandatory]
+	->get_sb() is gone.  Switch to use of ->mount().  Typically it's just
+a matter of switching from calling get_sb_... to mount_... and changing the
+function type.  If you were doing it manually, just switch from setting ->mnt_root
+to some pointer to returning that pointer.  On errors return ERR_PTR(...).
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 94cf97b901d7..ef0714aa8e40 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -95,10 +95,11 @@ functions:
    extern int unregister_filesystem(struct file_system_type *);
 
 The passed struct file_system_type describes your filesystem. When a
-request is made to mount a device onto a directory in your filespace,
-the VFS will call the appropriate get_sb() method for the specific
-filesystem. The dentry for the mount point will then be updated to
-point to the root inode for the new filesystem.
+request is made to mount a filesystem onto a directory in your namespace,
+the VFS will call the appropriate mount() method for the specific
+filesystem.  New vfsmount refering to the tree returned by ->mount()
+will be attached to the mountpoint, so that when pathname resolution
+reaches the mountpoint it will jump into the root of that vfsmount.
 
 You can see all filesystems that are registered to the kernel in the
 file /proc/filesystems.
@@ -107,14 +108,14 @@ file /proc/filesystems.
 struct file_system_type
 -----------------------
 
-This describes the filesystem. As of kernel 2.6.22, the following
+This describes the filesystem. As of kernel 2.6.39, the following
 members are defined:
 
 struct file_system_type {
 	const char *name;
 	int fs_flags;
-        int (*get_sb) (struct file_system_type *, int,
-                       const char *, void *, struct vfsmount *);
+        struct dentry (*mount) (struct file_system_type *, int,
+                       const char *, void *);
         void (*kill_sb) (struct super_block *);
         struct module *owner;
         struct file_system_type * next;
@@ -128,11 +129,11 @@ struct file_system_type {
 
   fs_flags: various flags (i.e. FS_REQUIRES_DEV, FS_NO_DCACHE, etc.)
 
-  get_sb: the method to call when a new instance of this
+  mount: the method to call when a new instance of this
 	filesystem should be mounted
 
   kill_sb: the method to call when an instance of this filesystem
-	should be unmounted
+	should be shut down
 
   owner: for internal VFS use: you should initialize this to THIS_MODULE in
   	most cases.
@@ -141,7 +142,7 @@ struct file_system_type {
 
   s_lock_key, s_umount_key: lockdep-specific
 
-The get_sb() method has the following arguments:
+The mount() method has the following arguments:
 
   struct file_system_type *fs_type: describes the filesystem, partly initialized
   	by the specific filesystem code
@@ -153,32 +154,39 @@ The get_sb() method has the following arguments:
   void *data: arbitrary mount options, usually comes as an ASCII
 	string (see "Mount Options" section)
 
-  struct vfsmount *mnt: a vfs-internal representation of a mount point
+The mount() method must return the root dentry of the tree requested by
+caller.  An active reference to its superblock must be grabbed and the
+superblock must be locked.  On failure it should return ERR_PTR(error).
 
-The get_sb() method must determine if the block device specified
-in the dev_name and fs_type contains a filesystem of the type the method
-supports. If it succeeds in opening the named block device, it initializes a
-struct super_block descriptor for the filesystem contained by the block device.
-On failure it returns an error.
+The arguments match those of mount(2) and their interpretation
+depends on filesystem type.  E.g. for block filesystems, dev_name is
+interpreted as block device name, that device is opened and if it
+contains a suitable filesystem image the method creates and initializes
+struct super_block accordingly, returning its root dentry to caller.
+
+->mount() may choose to return a subtree of existing filesystem - it
+doesn't have to create a new one.  The main result from the caller's
+point of view is a reference to dentry at the root of (sub)tree to
+be attached; creation of new superblock is a common side effect.
 
 The most interesting member of the superblock structure that the
-get_sb() method fills in is the "s_op" field. This is a pointer to
+mount() method fills in is the "s_op" field. This is a pointer to
 a "struct super_operations" which describes the next level of the
 filesystem implementation.
 
-Usually, a filesystem uses one of the generic get_sb() implementations
-and provides a fill_super() method instead. The generic methods are:
+Usually, a filesystem uses one of the generic mount() implementations
+and provides a fill_super() callback instead. The generic variants are:
 
-  get_sb_bdev: mount a filesystem residing on a block device
+  mount_bdev: mount a filesystem residing on a block device
 
-  get_sb_nodev: mount a filesystem that is not backed by a device
+  mount_nodev: mount a filesystem that is not backed by a device
 
-  get_sb_single: mount a filesystem which shares the instance between
+  mount_single: mount a filesystem which shares the instance between
   	all mounts
 
-A fill_super() method implementation has the following arguments:
+A fill_super() callback implementation has the following arguments:
 
-  struct super_block *sb: the superblock structure. The method fill_super()
+  struct super_block *sb: the superblock structure. The callback
   	must initialize this properly.
 
   void *data: arbitrary mount options, usually comes as an ASCII
diff --git a/fs/super.c b/fs/super.c
index 7e9dd4cc2c01..4bae0ef6110e 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -843,23 +843,6 @@ error:
 }
 EXPORT_SYMBOL(mount_bdev);
 
-int get_sb_bdev(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int),
-	struct vfsmount *mnt)
-{
-	struct dentry *root;
-
-	root = mount_bdev(fs_type, flags, dev_name, data, fill_super);
-	if (IS_ERR(root))
-		return PTR_ERR(root);
-	mnt->mnt_root = root;
-	mnt->mnt_sb = root->d_sb;
-	return 0;
-}
-
-EXPORT_SYMBOL(get_sb_bdev);
-
 void kill_block_super(struct super_block *sb)
 {
 	struct block_device *bdev = sb->s_bdev;
@@ -897,22 +880,6 @@ struct dentry *mount_nodev(struct file_system_type *fs_type,
 }
 EXPORT_SYMBOL(mount_nodev);
 
-int get_sb_nodev(struct file_system_type *fs_type,
-	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int),
-	struct vfsmount *mnt)
-{
-	struct dentry *root;
-
-	root = mount_nodev(fs_type, flags, data, fill_super);
-	if (IS_ERR(root))
-		return PTR_ERR(root);
-	mnt->mnt_root = root;
-	mnt->mnt_sb = root->d_sb;
-	return 0;
-}
-EXPORT_SYMBOL(get_sb_nodev);
-
 static int compare_single(struct super_block *s, void *p)
 {
 	return 1;
@@ -943,22 +910,6 @@ struct dentry *mount_single(struct file_system_type *fs_type,
 }
 EXPORT_SYMBOL(mount_single);
 
-int get_sb_single(struct file_system_type *fs_type,
-	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int),
-	struct vfsmount *mnt)
-{
-	struct dentry *root;
-	root = mount_single(fs_type, flags, data, fill_super);
-	if (IS_ERR(root))
-		return PTR_ERR(root);
-	mnt->mnt_root = root;
-	mnt->mnt_sb = root->d_sb;
-	return 0;
-}
-
-EXPORT_SYMBOL(get_sb_single);
-
 struct vfsmount *
 vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
 {
@@ -988,19 +939,13 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 			goto out_free_secdata;
 	}
 
-	if (type->mount) {
-		root = type->mount(type, flags, name, data);
-		if (IS_ERR(root)) {
-			error = PTR_ERR(root);
-			goto out_free_secdata;
-		}
-		mnt->mnt_root = root;
-		mnt->mnt_sb = root->d_sb;
-	} else {
-		error = type->get_sb(type, flags, name, data, mnt);
-		if (error < 0)
-			goto out_free_secdata;
+	root = type->mount(type, flags, name, data);
+	if (IS_ERR(root)) {
+		error = PTR_ERR(root);
+		goto out_free_secdata;
 	}
+	mnt->mnt_root = root;
+	mnt->mnt_sb = root->d_sb;
 	BUG_ON(!mnt->mnt_sb);
 	WARN_ON(!mnt->mnt_sb->s_bdi);
 	mnt->mnt_sb->s_flags |= MS_BORN;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e6d3fe45981b..ffaa0e4926ed 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1797,8 +1797,6 @@ int sync_inode_metadata(struct inode *inode, int wait);
 struct file_system_type {
 	const char *name;
 	int fs_flags;
-	int (*get_sb) (struct file_system_type *, int,
-		       const char *, void *, struct vfsmount *);
 	struct dentry *(*mount) (struct file_system_type *, int,
 		       const char *, void *);
 	void (*kill_sb) (struct super_block *);
@@ -1821,24 +1819,12 @@ extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
 extern struct dentry *mount_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
-extern int get_sb_bdev(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int),
-	struct vfsmount *mnt);
 extern struct dentry *mount_single(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
-extern int get_sb_single(struct file_system_type *fs_type,
-	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int),
-	struct vfsmount *mnt);
 extern struct dentry *mount_nodev(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
-extern int get_sb_nodev(struct file_system_type *fs_type,
-	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int),
-	struct vfsmount *mnt);
 void generic_shutdown_super(struct super_block *sb);
 void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
-- 
cgit v1.2.3