5 files changed, 100 insertions, 51 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index da944eca2ca..9c8309ed35c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1192,6 +1192,9 @@ module_init(inet6_init);
 
 static void __exit inet6_exit(void)
 {
+        if (disable_ipv6)
+                return;
+
         /* First of all disallow new sockets creation. */
         sock_unregister(PF_INET6);
         /* Disallow any further netlink messages */
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 385f427beda..ff50a054686 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -293,11 +293,6 @@ static void rpc_make_runnable(struct rpc_task *task)
         rpc_clear_queued(task);
         if (rpc_test_and_set_running(task))
                 return;
-        /* We might have raced */
-        if (RPC_IS_QUEUED(task)) {
-                rpc_clear_running(task);
-                return;
-        }
         if (RPC_IS_ASYNC(task)) {
                 int status;
 
@@ -607,7 +602,9 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
  */
 static void __rpc_execute(struct rpc_task *task)
 {
-        int             status = 0;
+        struct rpc_wait_queue *queue;
+        int task_is_async = RPC_IS_ASYNC(task);
+        int status = 0;
 
         dprintk("RPC: %5u __rpc_execute flags=0x%x\n",
                         task->tk_pid, task->tk_flags);
@@ -647,15 +644,25 @@ static void __rpc_execute(struct rpc_task *task)
                  */
                 if (!RPC_IS_QUEUED(task))
                         continue;
-                rpc_clear_running(task);
-                if (RPC_IS_ASYNC(task)) {
-                        /* Careful! we may have raced... */
-                        if (RPC_IS_QUEUED(task))
-                                return;
-                        if (rpc_test_and_set_running(task))
-                                return;
+                /*
+                 * The queue->lock protects against races with
+                 * rpc_make_runnable().
+                 *
+                 * Note that once we clear RPC_TASK_RUNNING on an asynchronous
+                 * rpc_task, rpc_make_runnable() can assign it to a
+                 * different workqueue. We therefore cannot assume that the
+                 * rpc_task pointer may still be dereferenced.
+                 */
+                queue = task->tk_waitqueue;
+                spin_lock_bh(&queue->lock);
+                if (!RPC_IS_QUEUED(task)) {
+                        spin_unlock_bh(&queue->lock);
                         continue;
                 }
+                rpc_clear_running(task);
+                spin_unlock_bh(&queue->lock);
+                if (task_is_async)
+                        return;
 
                 /* sync task: sleep here */
                 dprintk("RPC: %5u sync task going to sleep\n", task->tk_pid);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 29e401bb612..62098d101a1 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -663,7 +663,7 @@ void xprt_connect(struct rpc_task *task)
                         xprt, (xprt_connected(xprt) ? "is" : "is not"));
 
         if (!xprt_bound(xprt)) {
-                task->tk_status = -EIO;
+                task->tk_status = -EAGAIN;
                 return;
         }
         if (!xprt_lock_write(xprt, task))
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 5cbb404c4cd..29c71e645b2 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -467,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
         int err, sent = 0;
 
         if (unlikely(!sock))
-                return -ENOTCONN;
+                return -ENOTSOCK;
 
         clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
         if (base != 0) {
@@ -577,6 +577,8 @@ static int xs_udp_send_request(struct rpc_task *task)
                                 req->rq_svec->iov_base,
                                 req->rq_svec->iov_len);
 
+        if (!xprt_bound(xprt))
+                return -ENOTCONN;
         status = xs_sendpages(transport->sock,
                               xs_addr(xprt),
                               xprt->addrlen, xdr,
@@ -594,6 +596,10 @@ static int xs_udp_send_request(struct rpc_task *task)
         }
 
         switch (status) {
+        case -ENOTSOCK:
+                status = -ENOTCONN;
+                /* Should we call xs_close() here? */
+                break;
         case -EAGAIN:
                 xs_nospace(task);
                 break;
@@ -693,6 +699,10 @@ static int xs_tcp_send_request(struct rpc_task *task)
         }
 
         switch (status) {
+        case -ENOTSOCK:
+                status = -ENOTCONN;
+                /* Should we call xs_close() here? */
+                break;
         case -EAGAIN:
                 xs_nospace(task);
                 break;
@@ -1523,7 +1533,7 @@ static void xs_udp_connect_worker4(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         /* Start by resetting any existing state */
@@ -1564,7 +1574,7 @@ static void xs_udp_connect_worker6(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         /* Start by resetting any existing state */
@@ -1648,6 +1658,9 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
                 write_unlock_bh(&sk->sk_callback_lock);
         }
 
+        if (!xprt_bound(xprt))
+                return -ENOTCONN;
+
         /* Tell the socket layer to start connecting... */
         xprt->stat.connect_count++;
         xprt->stat.connect_start = jiffies;
@@ -1668,7 +1681,7 @@ static void xs_tcp_connect_worker4(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         if (!sock) {
@@ -1728,7 +1741,7 @@ static void xs_tcp_connect_worker6(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         if (!sock) {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e25ff62ab2a..62a5425cc6a 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -748,12 +748,51 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision)
                 schedule_work(&net->xfrm.state_hash_work);
 }
 
+static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
+                               struct flowi *fl, unsigned short family,
+                               xfrm_address_t *daddr, xfrm_address_t *saddr,
+                               struct xfrm_state **best, int *acq_in_progress,
+                               int *error)
+{
+        /* Resolution logic:
+         * 1. There is a valid state with matching selector. Done.
+         * 2. Valid state with inappropriate selector. Skip.
+         *
+         * Entering area of "sysdeps".
+         *
+         * 3. If state is not valid, selector is temporary, it selects
+         *    only session which triggered previous resolution. Key
+         *    manager will do something to install a state with proper
+         *    selector.
+         */
+        if (x->km.state == XFRM_STATE_VALID) {
+                if ((x->sel.family &&
+                     !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
+                    !security_xfrm_state_pol_flow_match(x, pol, fl))
+                        return;
+
+                if (!*best ||
+                    (*best)->km.dying > x->km.dying ||
+                    ((*best)->km.dying == x->km.dying &&
+                     (*best)->curlft.add_time < x->curlft.add_time))
+                        *best = x;
+        } else if (x->km.state == XFRM_STATE_ACQ) {
+                *acq_in_progress = 1;
+        } else if (x->km.state == XFRM_STATE_ERROR ||
+                   x->km.state == XFRM_STATE_EXPIRED) {
+                if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
+                    security_xfrm_state_pol_flow_match(x, pol, fl))
+                        *error = -ESRCH;
+        }
+}
+
 struct xfrm_state *
 xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
                 struct flowi *fl, struct xfrm_tmpl *tmpl,
                 struct xfrm_policy *pol, int *err,
                 unsigned short family)
 {
+        static xfrm_address_t saddr_wildcard = { };
         struct net *net = xp_net(pol);
         unsigned int h;
         struct hlist_node *entry;
@@ -773,40 +812,27 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
                     xfrm_state_addr_check(x, daddr, saddr, family) &&
                     tmpl->mode == x->props.mode &&
                     tmpl->id.proto == x->id.proto &&
-                    (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) {
-                        /* Resolution logic:
-                           1. There is a valid state with matching selector.
-                              Done.
-                           2. Valid state with inappropriate selector. Skip.
-
-                           Entering area of "sysdeps".
-
-                           3. If state is not valid, selector is temporary,
-                              it selects only session which triggered
-                              previous resolution. Key manager will do
-                              something to install a state with proper
-                              selector.
-                         */
-                        if (x->km.state == XFRM_STATE_VALID) {
-                                if ((x->sel.family && !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
-                                    !security_xfrm_state_pol_flow_match(x, pol, fl))
-                                        continue;
-                                if (!best ||
-                                    best->km.dying > x->km.dying ||
-                                    (best->km.dying == x->km.dying &&
-                                     best->curlft.add_time < x->curlft.add_time))
-                                        best = x;
-                        } else if (x->km.state == XFRM_STATE_ACQ) {
-                                acquire_in_progress = 1;
-                        } else if (x->km.state == XFRM_STATE_ERROR ||
-                                   x->km.state == XFRM_STATE_EXPIRED) {
-                                if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
-                                    security_xfrm_state_pol_flow_match(x, pol, fl))
-                                        error = -ESRCH;
-                        }
-                }
+                    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+                        xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+                                           &best, &acquire_in_progress, &error);
+        }
+        if (best)
+                goto found;
+
+        h = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family);
+        hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
+                if (x->props.family == family &&
+                    x->props.reqid == tmpl->reqid &&
+                    !(x->props.flags & XFRM_STATE_WILDRECV) &&
+                    xfrm_state_addr_check(x, daddr, saddr, family) &&
+                    tmpl->mode == x->props.mode &&
+                    tmpl->id.proto == x->id.proto &&
+                    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+                        xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+                                           &best, &acquire_in_progress, &error);
         }
 
+found:
         x = best;
         if (!x && !error && !acquire_in_progress) {
                 if (tmpl->id.spi &&