15 files changed, 133 insertions, 49 deletions

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 35b36b86d762..05f357828a2f 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 1a040e64c69f..cd9c21df87d1 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 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/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 508f9c18992f..133fd22ea287 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -144,7 +144,7 @@ void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
 
         list_for_each_entry(ha, &from_list->list, list) {
                 type = addr_type ? addr_type : ha->type;
-                __hw_addr_del(to_list, ha->addr, addr_len, addr_type);
+                __hw_addr_del(to_list, ha->addr, addr_len, type);
         }
 }
 EXPORT_SYMBOL(__hw_addr_del_multiple);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index d5074a567289..c44348adba3b 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1193,7 +1193,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb,
                         goto err;
         }
 
-        if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setets) {
+        if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) {
                 struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]);
                 err = ops->ieee_setpfc(netdev, pfc);
                 if (err)
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 8cde009e8b85..4222e7a654b0 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -614,6 +614,9 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
                 /* Caller (dccp_v4_do_rcv) will send Reset */
                 dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
                 return 1;
+        } else if (sk->sk_state == DCCP_CLOSED) {
+                dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
+                return 1;
         }
 
         if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) {
@@ -668,10 +671,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
         }
 
         switch (sk->sk_state) {
-        case DCCP_CLOSED:
-                dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
-                return 1;
-
         case DCCP_REQUESTING:
                 queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len);
                 if (queued >= 0)
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 739435a6af39..cfa7a5e1c5c9 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -67,8 +67,9 @@ dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen)
         size_t result_len = 0;
         const char *data = _data, *end, *opt;
 
-        kenter("%%%d,%s,'%s',%zu",
-               key->serial, key->description, data, datalen);
+        kenter("%%%d,%s,'%*.*s',%zu",
+               key->serial, key->description,
+               (int)datalen, (int)datalen, data, datalen);
 
         if (datalen <= 1 || !data || data[datalen - 1] != '\0')
                 return -EINVAL;
@@ -217,6 +218,19 @@ static void dns_resolver_describe(const struct key *key, struct seq_file *m)
                 seq_printf(m, ": %u", key->datalen);
 }
 
+/*
+ * read the DNS data
+ * - the key's semaphore is read-locked
+ */
+static long dns_resolver_read(const struct key *key,
+                              char __user *buffer, size_t buflen)
+{
+        if (key->type_data.x[0])
+                return key->type_data.x[0];
+
+        return user_read(key, buffer, buflen);
+}
+
 struct key_type key_type_dns_resolver = {
         .name           = "dns_resolver",
         .instantiate    = dns_resolver_instantiate,
@@ -224,7 +238,7 @@ struct key_type key_type_dns_resolver = {
         .revoke         = user_revoke,
         .destroy        = user_destroy,
         .describe       = dns_resolver_describe,
-        .read           = user_read,
+        .read           = dns_resolver_read,
 };
 
 static int __init init_dns_resolver(void)
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/route.c b/net/ipv6/route.c
index a998db6e7895..904312e25a3c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2557,14 +2557,16 @@ static
 int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
                               void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        struct net *net = current->nsproxy->net_ns;
-        int delay = net->ipv6.sysctl.flush_delay;
-        if (write) {
-                proc_dointvec(ctl, write, buffer, lenp, ppos);
-                fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
-                return 0;
-        } else
+        struct net *net;
+        int delay;
+        if (!write)
                 return -EINVAL;
+
+        net = (struct net *)ctl->extra1;
+        delay = net->ipv6.sysctl.flush_delay;
+        proc_dointvec(ctl, write, buffer, lenp, ppos);
+        fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
+        return 0;
 }
 
 ctl_table ipv6_route_table_template[] = {
@@ -2651,6 +2653,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
 
         if (table) {
                 table[0].data = &net->ipv6.sysctl.flush_delay;
+                table[0].extra1 = net;
                 table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh;
                 table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
                 table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
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");
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 22f7ad5101ab..ba98e1308f3c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -808,9 +808,9 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
         dest->u_threshold = udest->u_threshold;
         dest->l_threshold = udest->l_threshold;
 
-        spin_lock(&dest->dst_lock);
+        spin_lock_bh(&dest->dst_lock);
         ip_vs_dst_reset(dest);
-        spin_unlock(&dest->dst_lock);
+        spin_unlock_bh(&dest->dst_lock);
 
         if (add)
                 ip_vs_new_estimator(&dest->stats);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index b07393eab88e..91816998ed86 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -85,6 +85,8 @@ EXPORT_SYMBOL(nf_log_unregister);
 
 int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger)
 {
+        if (pf >= ARRAY_SIZE(nf_loggers))
+                return -EINVAL;
         mutex_lock(&nf_log_mutex);
         if (__find_logger(pf, logger->name) == NULL) {
                 mutex_unlock(&nf_log_mutex);
@@ -98,6 +100,8 @@ EXPORT_SYMBOL(nf_log_bind_pf);
 
 void nf_log_unbind_pf(u_int8_t pf)
 {
+        if (pf >= ARRAY_SIZE(nf_loggers))
+                return;
         mutex_lock(&nf_log_mutex);
         rcu_assign_pointer(nf_loggers[pf], NULL);
         mutex_unlock(&nf_log_mutex);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 478181d53c55..1f924595bdef 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1407,7 +1407,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
         int noblock = flags&MSG_DONTWAIT;
         size_t copied;
         struct sk_buff *skb, *data_skb;
-        int err;
+        int err, ret;
 
         if (flags&MSG_OOB)
                 return -EOPNOTSUPP;
@@ -1470,8 +1470,13 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 
         skb_free_datagram(sk, skb);
 
-        if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2)
-                netlink_dump(sk);
+        if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
+                ret = netlink_dump(sk);
+                if (ret) {
+                        sk->sk_err = ret;
+                        sk->sk_error_report(sk);
+                }
+        }
 
         scm_recv(sock, msg, siocb->scm, flags);
 out:
@@ -1736,6 +1741,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
         struct netlink_callback *cb;
         struct sock *sk;
         struct netlink_sock *nlk;
+        int ret;
 
         cb = kzalloc(sizeof(*cb), GFP_KERNEL);
         if (cb == NULL)
@@ -1764,9 +1770,13 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
         nlk->cb = cb;
         mutex_unlock(nlk->cb_mutex);
 
-        netlink_dump(sk);
+        ret = netlink_dump(sk);
+
         sock_put(sk);
 
+        if (ret)
+                return ret;
+
         /* We successfully started a dump, by returning -EINTR we
          * signal not to send ACK even if it was requested.
          */
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 89315009bab1..1a2b0633fece 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -423,6 +423,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb)
                         goto protocol_error;
                 }
 
+        case RXRPC_PACKET_TYPE_ACKALL:
         case RXRPC_PACKET_TYPE_ACK:
                 /* ACK processing is done in process context */
                 read_lock_bh(&call->state_lock);