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

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [BRIDGE]: Unaligned access when comparing ethernet addresses
  [SCTP]: Unmap v4mapped addresses during SCTP_BINDX_REM_ADDR operation.
  [SCTP]: Fix assertion (!atomic_read(&sk->sk_rmem_alloc)) failed message
  [NET]: Set a separate lockdep class for neighbour table's proxy_queue
  [NET]: Fix UDP checksum issue in net poll mode.
  [KEY]: Fix conversion between IPSEC_MODE_xxx and XFRM_MODE_xxx.
  [NET]: Get rid of alloc_skb_from_cache

8 files changed, 150 insertions, 81 deletions

diff --git a/arch/x86_64/kernel/functionlist b/arch/x86_64/kernel/functionlist
index 01fa23580c8..7ae18ec1245 100644
--- a/arch/x86_64/kernel/functionlist
+++ b/arch/x86_64/kernel/functionlist
@@ -514,7 +514,6 @@
 *(.text.dentry_open)
 *(.text.dentry_iput)
 *(.text.bio_alloc)
-*(.text.alloc_skb_from_cache)
 *(.text.wait_on_page_bit)
 *(.text.vfs_readdir)
 *(.text.vfs_lstat)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 82f43ad478c..5992f65b418 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -346,9 +346,6 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 	return __alloc_skb(size, priority, 1, -1);
 }
 
-extern struct sk_buff *alloc_skb_from_cache(struct kmem_cache *cp,
-					    unsigned int size,
-					    gfp_t priority);
 extern void	       kfree_skbmem(struct sk_buff *skb);
 extern struct sk_buff *skb_clone(struct sk_buff *skb,
 				 gfp_t priority);
@@ -622,6 +619,13 @@ static inline void skb_queue_head_init(struct sk_buff_head *list)
 	list->qlen = 0;
 }
 
+static inline void skb_queue_head_init_class(struct sk_buff_head *list,
+		struct lock_class_key *class)
+{
+	skb_queue_head_init(list);
+	lockdep_set_class(&list->lock, class);
+}
+
 /*
  *	Insert an sk_buff at the start of a list.
  *
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 58d13f2bd12..a285897a2fb 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -126,7 +126,9 @@ void br_stp_disable_port(struct net_bridge_port *p)
 /* called under bridge lock */
 void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr)
 {
-	unsigned char oldaddr[6];
+	/* should be aligned on 2 bytes for compare_ether_addr() */
+	unsigned short oldaddr_aligned[ETH_ALEN >> 1];
+	unsigned char *oldaddr = (unsigned char *)oldaddr_aligned;
 	struct net_bridge_port *p;
 	int wasroot;
 
@@ -151,11 +153,14 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr)
 		br_become_root_bridge(br);
 }
 
-static const unsigned char br_mac_zero[6];
+/* should be aligned on 2 bytes for compare_ether_addr() */
+static const unsigned short br_mac_zero_aligned[ETH_ALEN >> 1];
 
 /* called under bridge lock */
 void br_stp_recalculate_bridge_id(struct net_bridge *br)
 {
+	const unsigned char *br_mac_zero =
+			(const unsigned char *)br_mac_zero_aligned;
 	const unsigned char *addr = br_mac_zero;
 	struct net_bridge_port *p;
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index cfc60019cf9..841e3f32cab 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1331,6 +1331,8 @@ void neigh_parms_destroy(struct neigh_parms *parms)
 	kfree(parms);
 }
 
+static struct lock_class_key neigh_table_proxy_queue_class;
+
 void neigh_table_init_no_netlink(struct neigh_table *tbl)
 {
 	unsigned long now = jiffies;
@@ -1379,7 +1381,8 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl)
 	init_timer(&tbl->proxy_timer);
 	tbl->proxy_timer.data	  = (unsigned long)tbl;
 	tbl->proxy_timer.function = neigh_proxy_process;
-	skb_queue_head_init(&tbl->proxy_queue);
+	skb_queue_head_init_class(&tbl->proxy_queue,
+			&neigh_table_proxy_queue_class);
 
 	tbl->last_flush = now;
 	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index da1019451cc..4581ece48bb 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -471,6 +471,13 @@ int __netpoll_rx(struct sk_buff *skb)
 	if (skb->len < len || len < iph->ihl*4)
 		goto out;
 
+	/*
+	 * Our transport medium may have padded the buffer out.
+	 * Now We trim to the true length of the frame.
+	 */
+	if (pskb_trim_rcsum(skb, len))
+		goto out;
+
 	if (iph->protocol != IPPROTO_UDP)
 		goto out;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 87573ae35b0..336958fbbcb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -197,61 +197,6 @@ nodata:
 }
 
 /**
- *	alloc_skb_from_cache	-	allocate a network buffer
- *	@cp: kmem_cache from which to allocate the data area
- *           (object size must be big enough for @size bytes + skb overheads)
- *	@size: size to allocate
- *	@gfp_mask: allocation mask
- *
- *	Allocate a new &sk_buff. The returned buffer has no headroom and
- *	tail room of size bytes. The object has a reference count of one.
- *	The return is the buffer. On a failure the return is %NULL.
- *
- *	Buffers may only be allocated from interrupts using a @gfp_mask of
- *	%GFP_ATOMIC.
- */
-struct sk_buff *alloc_skb_from_cache(struct kmem_cache *cp,
-				     unsigned int size,
-				     gfp_t gfp_mask)
-{
-	struct sk_buff *skb;
-	u8 *data;
-
-	/* Get the HEAD */
-	skb = kmem_cache_alloc(skbuff_head_cache,
-			       gfp_mask & ~__GFP_DMA);
-	if (!skb)
-		goto out;
-
-	/* Get the DATA. */
-	size = SKB_DATA_ALIGN(size);
-	data = kmem_cache_alloc(cp, gfp_mask);
-	if (!data)
-		goto nodata;
-
-	memset(skb, 0, offsetof(struct sk_buff, truesize));
-	skb->truesize = size + sizeof(struct sk_buff);
-	atomic_set(&skb->users, 1);
-	skb->head = data;
-	skb->data = data;
-	skb->tail = data;
-	skb->end  = data + size;
-
-	atomic_set(&(skb_shinfo(skb)->dataref), 1);
-	skb_shinfo(skb)->nr_frags  = 0;
-	skb_shinfo(skb)->gso_size = 0;
-	skb_shinfo(skb)->gso_segs = 0;
-	skb_shinfo(skb)->gso_type = 0;
-	skb_shinfo(skb)->frag_list = NULL;
-out:
-	return skb;
-nodata:
-	kmem_cache_free(skbuff_head_cache, skb);
-	skb = NULL;
-	goto out;
-}
-
-/**
  *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
  *	@dev: network device to receive on
  *	@length: length to allocate
diff --git a/net/key/af_key.c b/net/key/af_key.c
index a4e7e2db0ff..cf77930ee51 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -630,6 +630,35 @@ pfkey_sockaddr_size(sa_family_t family)
 	/* NOTREACHED */
 }
 
+static inline int pfkey_mode_from_xfrm(int mode)
+{
+	switch(mode) {
+	case XFRM_MODE_TRANSPORT:
+		return IPSEC_MODE_TRANSPORT;
+	case XFRM_MODE_TUNNEL:
+		return IPSEC_MODE_TUNNEL;
+	case XFRM_MODE_BEET:
+		return IPSEC_MODE_BEET;
+	default:
+		return -1;
+	}
+}
+
+static inline int pfkey_mode_to_xfrm(int mode)
+{
+	switch(mode) {
+	case IPSEC_MODE_ANY:	/*XXX*/
+	case IPSEC_MODE_TRANSPORT:
+		return XFRM_MODE_TRANSPORT;
+	case IPSEC_MODE_TUNNEL:
+		return XFRM_MODE_TUNNEL;
+	case IPSEC_MODE_BEET:
+		return XFRM_MODE_BEET;
+	default:
+		return -1;
+	}
+}
+
 static struct sk_buff * pfkey_xfrm_state2msg(struct xfrm_state *x, int add_keys, int hsc)
 {
 	struct sk_buff *skb;
@@ -651,6 +680,7 @@ static struct sk_buff * pfkey_xfrm_state2msg(struct xfrm_state *x, int add_keys,
 	int encrypt_key_size = 0;
 	int sockaddr_size;
 	struct xfrm_encap_tmpl *natt = NULL;
+	int mode;
 
 	/* address family check */
 	sockaddr_size = pfkey_sockaddr_size(x->props.family);
@@ -928,7 +958,11 @@ static struct sk_buff * pfkey_xfrm_state2msg(struct xfrm_state *x, int add_keys,
 	sa2 = (struct sadb_x_sa2 *)  skb_put(skb, sizeof(struct sadb_x_sa2));
 	sa2->sadb_x_sa2_len = sizeof(struct sadb_x_sa2)/sizeof(uint64_t);
 	sa2->sadb_x_sa2_exttype = SADB_X_EXT_SA2;
-	sa2->sadb_x_sa2_mode = x->props.mode + 1;
+	if ((mode = pfkey_mode_from_xfrm(x->props.mode)) < 0) {
+		kfree_skb(skb);
+		return ERR_PTR(-EINVAL);
+	}
+	sa2->sadb_x_sa2_mode = mode;
 	sa2->sadb_x_sa2_reserved1 = 0;
 	sa2->sadb_x_sa2_reserved2 = 0;
 	sa2->sadb_x_sa2_sequence = 0;
@@ -1155,9 +1189,12 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 
 	if (ext_hdrs[SADB_X_EXT_SA2-1]) {
 		struct sadb_x_sa2 *sa2 = (void*)ext_hdrs[SADB_X_EXT_SA2-1];
-		x->props.mode = sa2->sadb_x_sa2_mode;
-		if (x->props.mode)
-			x->props.mode--;
+		int mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode);
+		if (mode < 0) {
+			err = -EINVAL;
+			goto out;
+		}
+		x->props.mode = mode;
 		x->props.reqid = sa2->sadb_x_sa2_reqid;
 	}
 
@@ -1218,7 +1255,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 	struct sadb_address *saddr, *daddr;
 	struct sadb_msg *out_hdr;
 	struct xfrm_state *x = NULL;
-	u8 mode;
+	int mode;
 	u32 reqid;
 	u8 proto;
 	unsigned short family;
@@ -1233,7 +1270,9 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 		return -EINVAL;
 
 	if ((sa2 = ext_hdrs[SADB_X_EXT_SA2-1]) != NULL) {
-		mode = sa2->sadb_x_sa2_mode - 1;
+		mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode);
+		if (mode < 0)
+			return -EINVAL;
 		reqid = sa2->sadb_x_sa2_reqid;
 	} else {
 		mode = 0;
@@ -1756,6 +1795,7 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	struct sockaddr_in6 *sin6;
 #endif
+	int mode;
 
 	if (xp->xfrm_nr >= XFRM_MAX_DEPTH)
 		return -ELOOP;
@@ -1764,7 +1804,9 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
 		return -EINVAL;
 
 	t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */
-	t->mode = rq->sadb_x_ipsecrequest_mode-1;
+	if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0)
+		return -EINVAL;
+	t->mode = mode;
 	if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE)
 		t->optional = 1;
 	else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) {
@@ -1877,7 +1919,7 @@ static struct sk_buff * pfkey_xfrm_policy2msg_prep(struct xfrm_policy *xp)
 	return skb;
 }
 
-static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, int dir)
+static int pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, int dir)
 {
 	struct sadb_msg *hdr;
 	struct sadb_address *addr;
@@ -2014,6 +2056,7 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i
 		struct sadb_x_ipsecrequest *rq;
 		struct xfrm_tmpl *t = xp->xfrm_vec + i;
 		int req_size;
+		int mode;
 
 		req_size = sizeof(struct sadb_x_ipsecrequest);
 		if (t->mode == XFRM_MODE_TUNNEL)
@@ -2027,7 +2070,9 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i
 		memset(rq, 0, sizeof(*rq));
 		rq->sadb_x_ipsecrequest_len = req_size;
 		rq->sadb_x_ipsecrequest_proto = t->id.proto;
-		rq->sadb_x_ipsecrequest_mode = t->mode+1;
+		if ((mode = pfkey_mode_from_xfrm(t->mode)) < 0)
+			return -EINVAL;
+		mode = pfkey_mode_from_xfrm(t->mode);
 		rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_REQUIRE;
 		if (t->reqid)
 			rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_UNIQUE;
@@ -2089,6 +2134,8 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i
 
 	hdr->sadb_msg_len = size / sizeof(uint64_t);
 	hdr->sadb_msg_reserved = atomic_read(&xp->refcnt);
+
+	return 0;
 }
 
 static int key_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c)
@@ -2102,7 +2149,9 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c
 		err = PTR_ERR(out_skb);
 		goto out;
 	}
-	pfkey_xfrm_policy2msg(out_skb, xp, dir);
+	err = pfkey_xfrm_policy2msg(out_skb, xp, dir);
+	if (err < 0)
+		return err;
 
 	out_hdr = (struct sadb_msg *) out_skb->data;
 	out_hdr->sadb_msg_version = PF_KEY_V2;
@@ -2327,7 +2376,9 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, struct sadb
 		err =  PTR_ERR(out_skb);
 		goto out;
 	}
-	pfkey_xfrm_policy2msg(out_skb, xp, dir);
+	err = pfkey_xfrm_policy2msg(out_skb, xp, dir);
+	if (err < 0)
+		goto out;
 
 	out_hdr = (struct sadb_msg *) out_skb->data;
 	out_hdr->sadb_msg_version = hdr->sadb_msg_version;
@@ -2409,6 +2460,7 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 {
 	int err;
 	struct sadb_x_ipsecrequest *rq2;
+	int mode;
 
 	if (len <= sizeof(struct sadb_x_ipsecrequest) ||
 	    len < rq1->sadb_x_ipsecrequest_len)
@@ -2439,7 +2491,9 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 		return -EINVAL;
 
 	m->proto = rq1->sadb_x_ipsecrequest_proto;
-	m->mode = rq1->sadb_x_ipsecrequest_mode - 1;
+	if ((mode = pfkey_mode_to_xfrm(rq1->sadb_x_ipsecrequest_mode)) < 0)
+		return -EINVAL;
+	m->mode = mode;
 	m->reqid = rq1->sadb_x_ipsecrequest_reqid;
 
 	return ((int)(rq1->sadb_x_ipsecrequest_len +
@@ -2579,12 +2633,15 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr)
 	struct pfkey_dump_data *data = ptr;
 	struct sk_buff *out_skb;
 	struct sadb_msg *out_hdr;
+	int err;
 
 	out_skb = pfkey_xfrm_policy2msg_prep(xp);
 	if (IS_ERR(out_skb))
 		return PTR_ERR(out_skb);
 
-	pfkey_xfrm_policy2msg(out_skb, xp, dir);
+	err = pfkey_xfrm_policy2msg(out_skb, xp, dir);
+	if (err < 0)
+		return err;
 
 	out_hdr = (struct sadb_msg *) out_skb->data;
 	out_hdr->sadb_msg_version = data->hdr->sadb_msg_version;
@@ -3513,7 +3570,10 @@ static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
 
 	for (i = 0, mp = m; i < num_bundles; i++, mp++) {
 		/* old ipsecrequest */
-		if (set_ipsecrequest(skb, mp->proto, mp->mode + 1,
+		int mode = pfkey_mode_from_xfrm(mp->mode);
+		if (mode < 0)
+			return -EINVAL;
+		if (set_ipsecrequest(skb, mp->proto, mode,
 				     (mp->reqid ?  IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE),
 				     mp->reqid, mp->old_family,
 				     &mp->old_saddr, &mp->old_daddr) < 0) {
@@ -3521,7 +3581,7 @@ static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type,
 		}
 
 		/* new ipsecrequest */
-		if (set_ipsecrequest(skb, mp->proto, mp->mode + 1,
+		if (set_ipsecrequest(skb, mp->proto, mode,
 				     (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE),
 				     mp->reqid, mp->new_family,
 				     &mp->new_saddr, &mp->new_daddr) < 0) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 536298c2eda..a1d026f12b0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -627,6 +627,12 @@ int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt)
 			retval = -EINVAL;
 			goto err_bindx_rem;
 		}
+
+		if (!af->addr_valid(sa_addr, sp, NULL)) {
+			retval = -EADDRNOTAVAIL;
+			goto err_bindx_rem;
+		}
+
 		if (sa_addr->v4.sin_port != htons(bp->port)) {
 			retval = -EINVAL;
 			goto err_bindx_rem;
@@ -5638,6 +5644,36 @@ void sctp_wait_for_close(struct sock *sk, long timeout)
 	finish_wait(sk->sk_sleep, &wait);
 }
 
+static void sctp_sock_rfree_frag(struct sk_buff *skb)
+{
+	struct sk_buff *frag;
+
+	if (!skb->data_len)
+		goto done;
+
+	/* Don't forget the fragments. */
+	for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next)
+		sctp_sock_rfree_frag(frag);
+
+done:
+	sctp_sock_rfree(skb);
+}
+
+static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk)
+{
+	struct sk_buff *frag;
+
+	if (!skb->data_len)
+		goto done;
+
+	/* Don't forget the fragments. */
+	for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next)
+		sctp_skb_set_owner_r_frag(frag, sk);
+
+done:
+	sctp_skb_set_owner_r(skb, sk);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -5692,10 +5728,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) {
 		event = sctp_skb2event(skb);
 		if (event->asoc == assoc) {
-			sctp_sock_rfree(skb);
+			sctp_sock_rfree_frag(skb);
 			__skb_unlink(skb, &oldsk->sk_receive_queue);
 			__skb_queue_tail(&newsk->sk_receive_queue, skb);
-			sctp_skb_set_owner_r(skb, newsk);
+			sctp_skb_set_owner_r_frag(skb, newsk);
 		}
 	}
 
@@ -5723,10 +5759,10 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 		sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) {
 			event = sctp_skb2event(skb);
 			if (event->asoc == assoc) {
-				sctp_sock_rfree(skb);
+				sctp_sock_rfree_frag(skb);
 				__skb_unlink(skb, &oldsp->pd_lobby);
 				__skb_queue_tail(queue, skb);
-				sctp_skb_set_owner_r(skb, newsk);
+				sctp_skb_set_owner_r_frag(skb, newsk);
 			}
 		}
 
@@ -5738,6 +5774,16 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 
 	}
 
+	sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) {
+		sctp_sock_rfree_frag(skb);
+		sctp_skb_set_owner_r_frag(skb, newsk);
+	}
+
+	sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) {
+		sctp_sock_rfree_frag(skb);
+		sctp_skb_set_owner_r_frag(skb, newsk);
+	}
+
 	/* Set the type of socket to indicate that it is peeled off from the
 	 * original UDP-style socket or created with the accept() call on a
 	 * TCP-style socket..