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

Conflicts:
	drivers/net/bnx2x/bnx2x_cmn.c

15 files changed, 115 insertions, 43 deletions

diff --git a/net/Makefile b/net/Makefile
index a3330eb..a51d946 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -19,9 +19,7 @@ obj-$(CONFIG_NETFILTER)		+= netfilter/
 obj-$(CONFIG_INET)		+= ipv4/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX)		+= unix/
-ifneq ($(CONFIG_IPV6),)
-obj-y				+= ipv6/
-endif
+obj-$(CONFIG_NET)		+= ipv6/
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig
index 9190ae4..6dee7bf 100644
--- a/net/bridge/Kconfig
+++ b/net/bridge/Kconfig
@@ -6,6 +6,7 @@ config BRIDGE
 	tristate "802.1d Ethernet Bridging"
 	select LLC
 	select STP
+	depends on IPV6 || IPV6=n
 	---help---
 	  If you say Y here, then your Linux box will be able to act as an
 	  Ethernet bridge, which means that the different Ethernet segments it
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 35b36b8..05f3578 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;
 }
@@ -1248,8 +1247,6 @@ static int process_connect(struct ceph_connection *con)
 		     con->auth_retry);
 		if (con->auth_retry == 2) {
 			con->error_msg = "connect authorization failure";
-			reset_connection(con);
-			set_bit(CLOSED, &con->state);
 			return -1;
 		}
 		con->auth_retry = 1;
@@ -1715,14 +1712,6 @@ more:
 
 	/* open the socket first? */
 	if (con->sock == NULL) {
-		/*
-		 * if we were STANDBY and are reconnecting _this_
-		 * connection, bump connect_seq now.  Always bump
-		 * global_seq.
-		 */
-		if (test_and_clear_bit(STANDBY, &con->state))
-			con->connect_seq++;
-
 		prepare_write_banner(msgr, con);
 		prepare_write_connect(msgr, con, 1);
 		prepare_read_banner(con);
@@ -1951,7 +1940,24 @@ 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(STANDBY, &con->state)) {
+		dout("con_work %p STANDBY\n", con);
+		goto done;
+	}
 	if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
 		dout("con_work CLOSED\n");
 		con_close_socket(con);
@@ -2008,10 +2014,12 @@ 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)) {
+		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
+		clear_bit(WRITE_PENDING, &con->state);
 		set_bit(STANDBY, &con->state);
 	} else {
 		/* retry after a delay. */
@@ -2019,11 +2027,24 @@ 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:
@@ -2094,6 +2115,19 @@ void ceph_messenger_destroy(struct ceph_messenger *msgr)
 }
 EXPORT_SYMBOL(ceph_messenger_destroy);
 
+static void clear_standby(struct ceph_connection *con)
+{
+	/* come back from STANDBY? */
+	if (test_and_clear_bit(STANDBY, &con->state)) {
+		mutex_lock(&con->mutex);
+		dout("clear_standby %p and ++connect_seq\n", con);
+		con->connect_seq++;
+		WARN_ON(test_bit(WRITE_PENDING, &con->state));
+		WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state));
+		mutex_unlock(&con->mutex);
+	}
+}
+
 /*
  * Queue up an outgoing message on the given connection.
  */
@@ -2126,6 +2160,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
+	clear_standby(con);
 	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
 		queue_con(con);
 }
@@ -2191,6 +2226,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
  */
 void ceph_con_keepalive(struct ceph_connection *con)
 {
+	dout("con_keepalive %p\n", con);
+	clear_standby(con);
 	if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
 	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
 		queue_con(con);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 1a040e6..cd9c21d 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -16,22 +16,30 @@ struct page **ceph_get_direct_page_vector(const char __user *data,
 					  int num_pages, bool write_page)
 {
 	struct page **pages;
-	int rc;
+	int got = 0;
+	int rc = 0;
 
 	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
 	if (!pages)
 		return ERR_PTR(-ENOMEM);
 
 	down_read(&current->mm->mmap_sem);
-	rc = get_user_pages(current, current->mm, (unsigned long)data,
-			    num_pages, write_page, 0, pages, NULL);
+	while (got < num_pages) {
+		rc = get_user_pages(current, current->mm,
+		    (unsigned long)data + ((unsigned long)got * PAGE_SIZE),
+		    num_pages - got, write_page, 0, pages + got, NULL);
+		if (rc < 0)
+			break;
+		BUG_ON(rc == 0);
+		got += rc;
+	}
 	up_read(&current->mm->mmap_sem);
-	if (rc < num_pages)
+	if (rc < 0)
 		goto fail;
 	return pages;
 
 fail:
-	ceph_put_page_vector(pages, rc > 0 ? rc : 0, false);
+	ceph_put_page_vector(pages, got, false);
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL(ceph_get_direct_page_vector);
diff --git a/net/core/dev.c b/net/core/dev.c
index 9f66de9..0d39032 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1115,13 +1115,21 @@ 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/core/pktgen.c b/net/core/pktgen.c
index d73b77a..f0aec6c 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3271,7 +3271,7 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags)
 				    pkt_dev->started_at);
 	ktime_t idle = ns_to_ktime(pkt_dev->idle_acc);
 
-	p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n",
+	p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n",
 		     (unsigned long long)ktime_to_us(elapsed),
 		     (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)),
 		     (unsigned long long)ktime_to_us(idle),
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ff53860..6d85800d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -741,7 +741,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 			     ifap = &ifa->ifa_next) {
 				if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
 				    sin_orig.sin_addr.s_addr ==
-							ifa->ifa_address) {
+							ifa->ifa_local) {
 					break; /* found */
 				}
 			}
@@ -1112,8 +1112,8 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev,
 		return;
 
 	arp_send(ARPOP_REQUEST, ETH_P_ARP,
-		 ifa->ifa_address, dev,
-		 ifa->ifa_address, NULL,
+		 ifa->ifa_local, dev,
+		 ifa->ifa_local, NULL,
 		 dev->dev_addr, NULL);
 }
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f9af98d..71465955 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1766,4 +1766,4 @@ 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 e1e1757..65008f4 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -914,4 +914,4 @@ 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/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 02730ef..ea8d5e8 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -57,6 +57,7 @@
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETDEV("ip6tnl0");
 
 #ifdef IP6_TNL_DEBUG
 #define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d55d00c..0012760 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -783,8 +783,10 @@ restart:
 
 	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
-	else
+	else if (!(rt->dst.flags & DST_HOST))
 		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
+	else
+		goto out2;
 
 	dst_release(&rt->dst);
 	rt = nrt ? : net->ipv6.ip6_null_entry;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b8c8adb..3534cea 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1295,4 +1295,4 @@ static int __init sit_init(void)
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("sit0");
+MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 71f373c..c47a511 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -551,7 +551,10 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 	if (conn->c_loopback
 	    && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
 		rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
-		return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+		scat = &rm->data.op_sg[sg];
+		ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+		ret = min_t(int, ret, scat->length - conn->c_xmit_data_off);
+		return ret;
 	}
 
 	/* FIXME we may overallocate here */
diff --git a/net/rds/loop.c b/net/rds/loop.c
index aeec1d4..bca6761 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -61,10 +61,15 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm,
 			 unsigned int hdr_off, unsigned int sg,
 			 unsigned int off)
 {
+	struct scatterlist *sgp = &rm->data.op_sg[sg];
+	int ret = sizeof(struct rds_header) +
+			be32_to_cpu(rm->m_inc.i_hdr.h_len);
+
 	/* Do not send cong updates to loopback */
 	if (rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
 		rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
-		return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
+		ret = min_t(int, ret, sgp->length - conn->c_xmit_data_off);
+		goto out;
 	}
 
 	BUG_ON(hdr_off || sg || off);
@@ -80,8 +85,8 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm,
 			    NULL);
 
 	rds_inc_put(&rm->m_inc);
-
-	return sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len);
+out:
+	return ret;
 }
 
 /*
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index df5997d..de87018 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1728,7 +1728,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	msg->msg_namelen = 0;
 
-	mutex_lock(&u->readlock);
+	err = mutex_lock_interruptible(&u->readlock);
+	if (err) {
+		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+		goto out;
+	}
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb) {
@@ -1868,7 +1872,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		memset(&tmp_scm, 0, sizeof(tmp_scm));
 	}
 
-	mutex_lock(&u->readlock);
+	err = mutex_lock_interruptible(&u->readlock);
+	if (err) {
+		err = sock_intr_errno(timeo);
+		goto out;
+	}
 
 	do {
 		int chunk;
@@ -1899,11 +1907,12 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 			timeo = unix_stream_data_wait(sk, timeo);
 
-			if (signal_pending(current)) {
+			if (signal_pending(current)
+			    ||  mutex_lock_interruptible(&u->readlock)) {
 				err = sock_intr_errno(timeo);
 				goto out;
 			}
-			mutex_lock(&u->readlock);
+
 			continue;
  unlock:
 			unix_state_unlock(sk);