15 files changed, 86 insertions, 62 deletions

diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 3a94eae7abe9..b79747c4b645 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -510,10 +510,15 @@ int crush_do_rule(struct crush_map *map,
                 switch (rule->steps[step].op) {
                 case CRUSH_RULE_TAKE:
                         w[0] = rule->steps[step].arg1;
-                        if (force_pos >= 0) {
-                                BUG_ON(force_context[force_pos] != w[0]);
+
+                        /* find position in force_context/hierarchy */
+                        while (force_pos >= 0 &&
+                               force_context[force_pos] != w[0])
                                 force_pos--;
-                        }
+                        /* and move past it */
+                        if (force_pos >= 0)
+                                force_pos--;
+
                         wsize = 1;
                         break;
 
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 85f3bc0a7062..b780cb7947dd 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -15,10 +15,9 @@ int ceph_crypto_key_clone(struct ceph_crypto_key *dst,
                           const struct ceph_crypto_key *src)
 {
         memcpy(dst, src, sizeof(struct ceph_crypto_key));
-        dst->key = kmalloc(src->len, GFP_NOFS);
+        dst->key = kmemdup(src->key, src->len, GFP_NOFS);
         if (!dst->key)
                 return -ENOMEM;
-        memcpy(dst->key, src->key, src->len);
         return 0;
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index f4f3f58f5234..5e254055c910 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -29,8 +29,8 @@ static void __register_request(struct ceph_osd_client *osdc,
                                struct ceph_osd_request *req);
 static void __unregister_linger_request(struct ceph_osd_client *osdc,
                                         struct ceph_osd_request *req);
-static int __send_request(struct ceph_osd_client *osdc,
-                          struct ceph_osd_request *req);
+static void __send_request(struct ceph_osd_client *osdc,
+                           struct ceph_osd_request *req);
 
 static int op_needs_trail(int op)
 {
@@ -1022,8 +1022,8 @@ out:
 /*
  * caller should hold map_sem (for read) and request_mutex
  */
-static int __send_request(struct ceph_osd_client *osdc,
-                          struct ceph_osd_request *req)
+static void __send_request(struct ceph_osd_client *osdc,
+                           struct ceph_osd_request *req)
 {
         struct ceph_osd_request_head *reqhead;
 
@@ -1041,7 +1041,6 @@ static int __send_request(struct ceph_osd_client *osdc,
         ceph_msg_get(req->r_request); /* send consumes a ref */
         ceph_con_send(&req->r_osd->o_con, req->r_request);
         req->r_sent = req->r_osd->o_incarnation;
-        return 0;
 }
 
 /*
@@ -1726,17 +1725,9 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
                         dout("send_request %p no up osds in pg\n", req);
                         ceph_monc_request_next_osdmap(&osdc->client->monc);
                 } else {
-                        rc = __send_request(osdc, req);
-                        if (rc) {
-                                if (nofail) {
-                                        dout("osdc_start_request failed send, "
-                                             " will retry %lld\n", req->r_tid);
-                                        rc = 0;
-                                } else {
-                                        __unregister_request(osdc, req);
-                                }
-                        }
+                        __send_request(osdc, req);
                 }
+                rc = 0;
         }
 
 out_unlock:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dbf2ddafd52d..f16444bc6cbb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1960,7 +1960,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
         sz_idx = type>>2;
         kind = type&3;
 
-        if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN))
+        if (kind != 2 && !capable(CAP_NET_ADMIN))
                 return -EPERM;
 
         if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 69975e0bcdea..1531135130db 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -108,7 +108,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
         if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
                 return;
 
-        if (security_netlink_recv(skb, CAP_NET_ADMIN))
+        if (!capable(CAP_NET_ADMIN))
                 RCV_SKB_FAIL(-EPERM);
 
         /* Eventually we might send routing messages too */
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index a057fe64debd..94d45e1f8882 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -431,7 +431,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
         if (type <= IPQM_BASE)
                 return;
 
-        if (security_netlink_recv(skb, CAP_NET_ADMIN))
+        if (!capable(CAP_NET_ADMIN))
                 RCV_SKB_FAIL(-EPERM);
 
         spin_lock_bh(&queue_lock);
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index fb80a23c6640..a34c9e4c792c 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -432,7 +432,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
         if (type <= IPQM_BASE)
                 return;
 
-        if (security_netlink_recv(skb, CAP_NET_ADMIN))
+        if (!capable(CAP_NET_ADMIN))
                 RCV_SKB_FAIL(-EPERM);
 
         spin_lock_bh(&queue_lock);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index b4f8d849480c..4d70785b953d 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -130,7 +130,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
         const struct nfnetlink_subsystem *ss;
         int type, err;
 
-        if (security_netlink_recv(skb, CAP_NET_ADMIN))
+        if (!capable(CAP_NET_ADMIN))
                 return -EPERM;
 
         /* All the messages must at least contain nfgenmsg */
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index a403b618faa5..c29d2568c9e0 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -524,7 +524,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
                 return -EOPNOTSUPP;
 
         if ((ops->flags & GENL_ADMIN_PERM) &&
-            security_netlink_recv(skb, CAP_NET_ADMIN))
+            !capable(CAP_NET_ADMIN))
                 return -EPERM;
 
         if (nlh->nlmsg_flags & NLM_F_DUMP) {
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 03b56bc3b659..465df9ae1046 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1641,6 +1641,7 @@ int cache_register_net(struct cache_detail *cd, struct net *net)
                 sunrpc_destroy_cache_detail(cd);
         return ret;
 }
+EXPORT_SYMBOL_GPL(cache_register_net);
 
 int cache_register(struct cache_detail *cd)
 {
@@ -1653,6 +1654,7 @@ void cache_unregister_net(struct cache_detail *cd, struct net *net)
         remove_cache_proc_entries(cd, net);
         sunrpc_destroy_cache_detail(cd);
 }
+EXPORT_SYMBOL_GPL(cache_unregister_net);
 
 void cache_unregister(struct cache_detail *cd)
 {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9d01d46b05f3..e4aabc02368b 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -167,6 +167,7 @@ svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools)
 
 fail_free:
         kfree(m->to_pool);
+        m->to_pool = NULL;
 fail:
         return -ENOMEM;
 }
@@ -285,9 +286,10 @@ svc_pool_map_put(void)
         mutex_lock(&svc_pool_map_mutex);
 
         if (!--m->count) {
-                m->mode = SVC_POOL_DEFAULT;
                 kfree(m->to_pool);
+                m->to_pool = NULL;
                 kfree(m->pool_to);
+                m->pool_to = NULL;
                 m->npools = 0;
         }
 
@@ -527,17 +529,20 @@ svc_destroy(struct svc_serv *serv)
                 printk("svc_destroy: no threads for serv=%p!\n", serv);
 
         del_timer_sync(&serv->sv_temptimer);
-
-        svc_close_all(&serv->sv_tempsocks);
+        /*
+         * The set of xprts (contained in the sv_tempsocks and
+         * sv_permsocks lists) is now constant, since it is modified
+         * only by accepting new sockets (done by service threads in
+         * svc_recv) or aging old ones (done by sv_temptimer), or
+         * configuration changes (excluded by whatever locking the
+         * caller is using--nfsd_mutex in the case of nfsd).  So it's
+         * safe to traverse those lists and shut everything down:
+         */
+        svc_close_all(serv);
 
         if (serv->sv_shutdown)
                 serv->sv_shutdown(serv);
 
-        svc_close_all(&serv->sv_permsocks);
-
-        BUG_ON(!list_empty(&serv->sv_permsocks));
-        BUG_ON(!list_empty(&serv->sv_tempsocks));
-
         cache_clean_deferred(serv);
 
         if (svc_serv_is_pooled(serv))
@@ -683,8 +688,8 @@ found_pool:
  * Create or destroy enough new threads to make the number
  * of threads the given number.  If `pool' is non-NULL, applies
  * only to threads in that pool, otherwise round-robins between
- * all pools.  Must be called with a svc_get() reference and
- * the BKL or another lock to protect access to svc_serv fields.
+ * all pools.  Caller must ensure that mutual exclusion between this and
+ * server startup or shutdown.
  *
  * Destroying threads relies on the service threads filling in
  * rqstp->rq_task, which only the nfs ones do.  Assumes the serv
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 38649cfa4e81..74cb0d8e9ca1 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -22,6 +22,7 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
 static int svc_deferred_recv(struct svc_rqst *rqstp);
 static struct cache_deferred_req *svc_defer(struct cache_req *req);
 static void svc_age_temp_xprts(unsigned long closure);
+static void svc_delete_xprt(struct svc_xprt *xprt);
 
 /* apparently the "standard" is that clients close
  * idle connections after 5 minutes, servers after
@@ -147,8 +148,8 @@ EXPORT_SYMBOL_GPL(svc_xprt_put);
  * Called by transport drivers to initialize the transport independent
  * portion of the transport instance.
  */
-void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
-                   struct svc_serv *serv)
+void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl,
+                   struct svc_xprt *xprt, struct svc_serv *serv)
 {
         memset(xprt, 0, sizeof(*xprt));
         xprt->xpt_class = xcl;
@@ -163,7 +164,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
         spin_lock_init(&xprt->xpt_lock);
         set_bit(XPT_BUSY, &xprt->xpt_flags);
         rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending");
-        xprt->xpt_net = get_net(&init_net);
+        xprt->xpt_net = get_net(net);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
@@ -878,7 +879,7 @@ static void call_xpt_users(struct svc_xprt *xprt)
 /*
  * Remove a dead transport
  */
-void svc_delete_xprt(struct svc_xprt *xprt)
+static void svc_delete_xprt(struct svc_xprt *xprt)
 {
         struct svc_serv *serv = xprt->xpt_server;
         struct svc_deferred_req *dr;
@@ -893,14 +894,7 @@ void svc_delete_xprt(struct svc_xprt *xprt)
         spin_lock_bh(&serv->sv_lock);
         if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags))
                 list_del_init(&xprt->xpt_list);
-        /*
-         * The only time we're called while xpt_ready is still on a list
-         * is while the list itself is about to be destroyed (in
-         * svc_destroy).  BUT svc_xprt_enqueue could still be attempting
-         * to add new entries to the sp_sockets list, so we can't leave
-         * a freed xprt on it.
-         */
-        list_del_init(&xprt->xpt_ready);
+        BUG_ON(!list_empty(&xprt->xpt_ready));
         if (test_bit(XPT_TEMP, &xprt->xpt_flags))
                 serv->sv_tmpcnt--;
         spin_unlock_bh(&serv->sv_lock);
@@ -928,22 +922,48 @@ void svc_close_xprt(struct svc_xprt *xprt)
 }
 EXPORT_SYMBOL_GPL(svc_close_xprt);
 
-void svc_close_all(struct list_head *xprt_list)
+static void svc_close_list(struct list_head *xprt_list)
+{
+        struct svc_xprt *xprt;
+
+        list_for_each_entry(xprt, xprt_list, xpt_list) {
+                set_bit(XPT_CLOSE, &xprt->xpt_flags);
+                set_bit(XPT_BUSY, &xprt->xpt_flags);
+        }
+}
+
+void svc_close_all(struct svc_serv *serv)
 {
+        struct svc_pool *pool;
         struct svc_xprt *xprt;
         struct svc_xprt *tmp;
+        int i;
+
+        svc_close_list(&serv->sv_tempsocks);
+        svc_close_list(&serv->sv_permsocks);
 
+        for (i = 0; i < serv->sv_nrpools; i++) {
+                pool = &serv->sv_pools[i];
+
+                spin_lock_bh(&pool->sp_lock);
+                while (!list_empty(&pool->sp_sockets)) {
+                        xprt = list_first_entry(&pool->sp_sockets, struct svc_xprt, xpt_ready);
+                        list_del_init(&xprt->xpt_ready);
+                }
+                spin_unlock_bh(&pool->sp_lock);
+        }
         /*
-         * The server is shutting down, and no more threads are running.
-         * svc_xprt_enqueue() might still be running, but at worst it
-         * will re-add the xprt to sp_sockets, which will soon get
-         * freed.  So we don't bother with any more locking, and don't
-         * leave the close to the (nonexistent) server threads:
+         * At this point the sp_sockets lists will stay empty, since
+         * svc_enqueue will not add new entries without taking the
+         * sp_lock and checking XPT_BUSY.
          */
-        list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) {
-                set_bit(XPT_CLOSE, &xprt->xpt_flags);
+        list_for_each_entry_safe(xprt, tmp, &serv->sv_tempsocks, xpt_list)
                 svc_delete_xprt(xprt);
-        }
+        list_for_each_entry_safe(xprt, tmp, &serv->sv_permsocks, xpt_list)
+                svc_delete_xprt(xprt);
+
+        BUG_ON(!list_empty(&serv->sv_permsocks));
+        BUG_ON(!list_empty(&serv->sv_tempsocks));
 }
 
 /*
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 4653286fcc9e..464570906f80 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -739,7 +739,8 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
 {
         int err, level, optname, one = 1;
 
-        svc_xprt_init(&svc_udp_class, &svsk->sk_xprt, serv);
+        svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class,
+                      &svsk->sk_xprt, serv);
         clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
         svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
         svsk->sk_sk->sk_write_space = svc_write_space;
@@ -1343,7 +1344,8 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 {
         struct sock     *sk = svsk->sk_sk;
 
-        svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt, serv);
+        svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_tcp_class,
+                      &svsk->sk_xprt, serv);
         set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
         if (sk->sk_state == TCP_LISTEN) {
                 dprintk("setting up TCP socket for listening\n");
@@ -1659,7 +1661,7 @@ static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv,
                 return ERR_PTR(-ENOMEM);
 
         xprt = &svsk->sk_xprt;
-        svc_xprt_init(&svc_tcp_bc_class, xprt, serv);
+        svc_xprt_init(net, &svc_tcp_bc_class, xprt, serv);
 
         serv->sv_bc_xprt = xprt;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index ba1296d88de0..894cb42db91d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -453,7 +453,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 
         if (!cma_xprt)
                 return NULL;
-        svc_xprt_init(&svc_rdma_class, &cma_xprt->sc_xprt, serv);
+        svc_xprt_init(&init_net, &svc_rdma_class, &cma_xprt->sc_xprt, serv);
         INIT_LIST_HEAD(&cma_xprt->sc_accept_q);
         INIT_LIST_HEAD(&cma_xprt->sc_dto_q);
         INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 637f11a1e4df..66b84fbf2746 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2290,7 +2290,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
         link = &xfrm_dispatch[type];
 
         /* All operations require privileges, even GET */
-        if (security_netlink_recv(skb, CAP_NET_ADMIN))
+        if (!capable(CAP_NET_ADMIN))
                 return -EPERM;
 
         if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||