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

Conflicts:
	net/bluetooth/l2cap_core.c

Just two overlapping changes, one added an initialization of
a local variable, and another change added a new local variable.

Signed-off-by: David S. Miller <davem@davemloft.net>

24 files changed, 243 insertions, 78 deletions

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index b328ac611ccd..3fa08dda825e 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -674,7 +674,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
                 goto encrypt;
 
 auth:
-        if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend))
+        if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend))
                 return 0;
 
         if (!hci_conn_auth(conn, sec_level, auth_type))
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 26dc3f6a8346..9bc22e4c4c61 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2372,7 +2372,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi
         void *ptr = req->data;
         int type, olen;
         unsigned long val;
-        struct l2cap_conf_rfc rfc;
+        struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC };
         struct l2cap_conf_efs efs;
 
         BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data);
@@ -2522,6 +2522,16 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len)
                 }
         }
 
+        /* Use sane default values in case a misbehaving remote device
+         * did not send an RFC option.
+         */
+        rfc.mode = chan->mode;
+        rfc.retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO);
+        rfc.monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO);
+        rfc.max_pdu_size = cpu_to_le16(chan->imtu);
+
+        BT_ERR("Expected RFC option was not found, using defaults");
+
 done:
         switch (rfc.mode) {
         case L2CAP_MODE_ERTM:
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index e5ddef081e69..eac849b935a1 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1162,6 +1162,7 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci)
                         if (list_empty(&s->dlcs)) {
                                 s->state = BT_DISCONN;
                                 rfcomm_send_disc(s, 0);
+                                rfcomm_session_clear_timer(s);
                         }
 
                         break;
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 52e44605fb7b..84122472656c 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -114,12 +114,18 @@ static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, const vo
         return NULL;
 }
 
+static unsigned int fake_mtu(const struct dst_entry *dst)
+{
+        return dst->dev->mtu;
+}
+
 static struct dst_ops fake_dst_ops = {
         .family =               AF_INET,
         .protocol =             cpu_to_be16(ETH_P_IP),
         .update_pmtu =          fake_update_pmtu,
         .cow_metrics =          fake_cow_metrics,
         .neigh_lookup =         fake_neigh_lookup,
+        .mtu =                  fake_mtu,
 };
 
 /*
@@ -141,7 +147,7 @@ void br_netfilter_rtable_init(struct net_bridge *br)
         rt->dst.dev = br->dev;
         rt->dst.path = &rt->dst;
         dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
-        rt->dst.flags   = DST_NOXFRM;
+        rt->dst.flags   = DST_NOXFRM | DST_NOPEER;
         rt->dst.ops = &fake_dst_ops;
 }
 
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 42599e31dcad..3a94eae7abe9 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -477,7 +477,6 @@ int crush_do_rule(struct crush_map *map,
         int i, j;
         int numrep;
         int firstn;
-        int rc = -1;
 
         BUG_ON(ruleno >= map->max_rules);
 
@@ -491,23 +490,18 @@ int crush_do_rule(struct crush_map *map,
          * that this may or may not correspond to the specific types
          * referenced by the crush rule.
          */
-        if (force >= 0) {
-                if (force >= map->max_devices ||
-                    map->device_parents[force] == 0) {
-                        /*dprintk("CRUSH: forcefed device dne\n");*/
-                        rc = -1;  /* force fed device dne */
-                        goto out;
-                }
-                if (!is_out(map, weight, force, x)) {
-                        while (1) {
-                                force_context[++force_pos] = force;
-                                if (force >= 0)
-                                        force = map->device_parents[force];
-                                else
-                                        force = map->bucket_parents[-1-force];
-                                if (force == 0)
-                                        break;
-                        }
+        if (force >= 0 &&
+            force < map->max_devices &&
+            map->device_parents[force] != 0 &&
+            !is_out(map, weight, force, x)) {
+                while (1) {
+                        force_context[++force_pos] = force;
+                        if (force >= 0)
+                                force = map->device_parents[force];
+                        else
+                                force = map->bucket_parents[-1-force];
+                        if (force == 0)
+                                break;
                 }
         }
 
@@ -600,10 +594,7 @@ int crush_do_rule(struct crush_map *map,
                         BUG_ON(1);
                 }
         }
-        rc = result_len;
-
-out:
-        return rc;
+        return result_len;
 }
 
 
diff --git a/net/core/flow.c b/net/core/flow.c
index 8ae42de9c79e..e318c7e98042 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -358,6 +358,18 @@ void flow_cache_flush(void)
         put_online_cpus();
 }
 
+static void flow_cache_flush_task(struct work_struct *work)
+{
+        flow_cache_flush();
+}
+
+static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
+
+void flow_cache_flush_deferred(void)
+{
+        schedule_work(&flow_cache_flush_work);
+}
+
 static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
 {
         struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9d134636f87c..4b4d0b0a3543 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -669,11 +669,14 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
         if (count) {
                 int i;
 
-                if (count > 1<<30) {
+                if (count > INT_MAX)
+                        return -EINVAL;
+                count = roundup_pow_of_two(count);
+                if (count > (ULONG_MAX - sizeof(struct rps_dev_flow_table))
+                                / sizeof(struct rps_dev_flow)) {
                         /* Enforce a limit to prevent overflow */
                         return -EINVAL;
                 }
-                count = roundup_pow_of_two(count);
                 table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count));
                 if (!table)
                         return -ENOMEM;
diff --git a/net/core/sock.c b/net/core/sock.c
index 0c67facf42f3..002939cfc069 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -339,11 +339,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
         unsigned long flags;
         struct sk_buff_head *list = &sk->sk_receive_queue;
 
-        /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces
-           number of warnings when compiling with -W --ANK
-         */
-        if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
-            (unsigned)sk->sk_rcvbuf) {
+        if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
                 atomic_inc(&sk->sk_drops);
                 trace_sock_rcvqueue_full(sk, skb);
                 return -ENOMEM;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 915eb5265b2e..7e4ec9fc2cef 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -253,6 +253,10 @@ static int __init ic_open_devs(void)
                 }
         }
 
+        /* no point in waiting if we could not bring up at least one device */
+        if (!ic_first_dev)
+                goto have_carrier;
+
         /* wait for a carrier on at least one device */
         start = jiffies;
         while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f30112f7559a..bcacf54e5418 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -91,6 +91,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -119,6 +120,7 @@
 
 static int ip_rt_max_size;
 static int ip_rt_gc_timeout __read_mostly       = RT_GC_TIMEOUT;
+static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly  = HZ / 2;
 static int ip_rt_redirect_number __read_mostly  = 9;
 static int ip_rt_redirect_load __read_mostly    = HZ / 50;
@@ -132,6 +134,9 @@ static int ip_rt_min_advmss __read_mostly	= 256;
 static int rt_chain_length_max __read_mostly    = 20;
 static int redirect_genid;
 
+static struct delayed_work expires_work;
+static unsigned long expires_ljiffies;
+
 /*
  *      Interface to generic destination cache.
  */
@@ -829,6 +834,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth)
         return ONE;
 }
 
+static void rt_check_expire(void)
+{
+        static unsigned int rover;
+        unsigned int i = rover, goal;
+        struct rtable *rth;
+        struct rtable __rcu **rthp;
+        unsigned long samples = 0;
+        unsigned long sum = 0, sum2 = 0;
+        unsigned long delta;
+        u64 mult;
+
+        delta = jiffies - expires_ljiffies;
+        expires_ljiffies = jiffies;
+        mult = ((u64)delta) << rt_hash_log;
+        if (ip_rt_gc_timeout > 1)
+                do_div(mult, ip_rt_gc_timeout);
+        goal = (unsigned int)mult;
+        if (goal > rt_hash_mask)
+                goal = rt_hash_mask + 1;
+        for (; goal > 0; goal--) {
+                unsigned long tmo = ip_rt_gc_timeout;
+                unsigned long length;
+
+                i = (i + 1) & rt_hash_mask;
+                rthp = &rt_hash_table[i].chain;
+
+                if (need_resched())
+                        cond_resched();
+
+                samples++;
+
+                if (rcu_dereference_raw(*rthp) == NULL)
+                        continue;
+                length = 0;
+                spin_lock_bh(rt_hash_lock_addr(i));
+                while ((rth = rcu_dereference_protected(*rthp,
+                                        lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
+                        prefetch(rth->dst.rt_next);
+                        if (rt_is_expired(rth)) {
+                                *rthp = rth->dst.rt_next;
+                                rt_free(rth);
+                                continue;
+                        }
+                        if (rth->dst.expires) {
+                                /* Entry is expired even if it is in use */
+                                if (time_before_eq(jiffies, rth->dst.expires)) {
+nofree:
+                                        tmo >>= 1;
+                                        rthp = &rth->dst.rt_next;
+                                        /*
+                                         * We only count entries on
+                                         * a chain with equal hash inputs once
+                                         * so that entries for different QOS
+                                         * levels, and other non-hash input
+                                         * attributes don't unfairly skew
+                                         * the length computation
+                                         */
+                                        length += has_noalias(rt_hash_table[i].chain, rth);
+                                        continue;
+                                }
+                        } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+                                goto nofree;
+
+                        /* Cleanup aged off entries. */
+                        *rthp = rth->dst.rt_next;
+                        rt_free(rth);
+                }
+                spin_unlock_bh(rt_hash_lock_addr(i));
+                sum += length;
+                sum2 += length*length;
+        }
+        if (samples) {
+                unsigned long avg = sum / samples;
+                unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
+                rt_chain_length_max = max_t(unsigned long,
+                                        ip_rt_gc_elasticity,
+                                        (avg + 4*sd) >> FRACT_BITS);
+        }
+        rover = i;
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+        rt_check_expire();
+        schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+}
+
 /*
  * Perturbation of rt_genid by a small quantity [1..256]
  * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
@@ -1265,7 +1361,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
 {
         struct rtable *rt = (struct rtable *) dst;
 
-        if (rt) {
+        if (rt && !(rt->dst.flags & DST_NOPEER)) {
                 if (rt->peer == NULL)
                         rt_bind_peer(rt, rt->rt_dst, 1);
 
@@ -1276,7 +1372,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
                         iph->id = htons(inet_getid(rt->peer, more));
                         return;
                 }
-        } else
+        } else if (!rt)
                 printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
                        __builtin_return_address(0));
 
@@ -3173,6 +3269,13 @@ static ctl_table ipv4_route_table[] = {
                 .proc_handler   = proc_dointvec_jiffies,
         },
         {
+                .procname       = "gc_interval",
+                .data           = &ip_rt_gc_interval,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec_jiffies,
+        },
+        {
                 .procname       = "redirect_load",
                 .data           = &ip_rt_redirect_load,
                 .maxlen         = sizeof(int),
@@ -3382,6 +3485,11 @@ int __init ip_rt_init(void)
         devinet_init();
         ip_fib_init();
 
+        INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
+        expires_ljiffies = jiffies;
+        schedule_delayed_work(&expires_work,
+                net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
+
         if (ip_rt_proc_init())
                 printk(KERN_ERR "Unable to create route proc files\n");
 #ifdef CONFIG_XFRM
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 71d26999c955..d97e07183ce9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -604,7 +604,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
         static atomic_t ipv6_fragmentation_id;
         int old, new;
 
-        if (rt) {
+        if (rt && !(rt->dst.flags & DST_NOPEER)) {
                 struct inet_peer *peer;
 
                 if (!rt->rt6i_peer)
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index dfd3a648a551..a18e6c3d36e3 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -833,15 +833,15 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
                 copied += used;
                 len -= used;
 
+                /* For non stream protcols we get one packet per recvmsg call */
+                if (sk->sk_type != SOCK_STREAM)
+                        goto copy_uaddr;
+
                 if (!(flags & MSG_PEEK)) {
                         sk_eat_skb(sk, skb, 0);
                         *seq = 0;
                 }
 
-                /* For non stream protcols we get one packet per recvmsg call */
-                if (sk->sk_type != SOCK_STREAM)
-                        goto copy_uaddr;
-
                 /* Partial read */
                 if (used + offset < skb->len)
                         continue;
@@ -857,6 +857,12 @@ copy_uaddr:
         }
         if (llc_sk(sk)->cmsg_flags)
                 llc_cmsg_rcv(msg, skb);
+
+        if (!(flags & MSG_PEEK)) {
+                        sk_eat_skb(sk, skb, 0);
+                        *seq = 0;
+        }
+
         goto out;
 }
 
diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c
index 5b138506690e..9ddf1c3bfb39 100644
--- a/net/netfilter/xt_connbytes.c
+++ b/net/netfilter/xt_connbytes.c
@@ -87,10 +87,10 @@ connbytes_mt(const struct sk_buff *skb, struct xt_action_param *par)
                 break;
         }
 
-        if (sinfo->count.to)
+        if (sinfo->count.to >= sinfo->count.from)
                 return what <= sinfo->count.to && what >= sinfo->count.from;
-        else
-                return what >= sinfo->count.from;
+        else /* inverted */
+                return what < sinfo->count.to || what > sinfo->count.from;
 }
 
 static int connbytes_mt_check(const struct xt_mtchk_param *par)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0da505c9ac23..e56ca75e3f43 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1631,8 +1631,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
         if (snaplen > res)
                 snaplen = res;
 
-        if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
-            (unsigned)sk->sk_rcvbuf)
+        if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
                 goto drop_n_acct;
 
         if (skb_shared(skb)) {
@@ -1763,8 +1762,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
         if (po->tp_version <= TPACKET_V2) {
                 if (macoff + snaplen > po->rx_ring.frame_size) {
                         if (po->copy_thresh &&
-                                atomic_read(&sk->sk_rmem_alloc) + skb->truesize
-                                < (unsigned)sk->sk_rcvbuf) {
+                            atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
                                 if (skb_shared(skb)) {
                                         copy_skb = skb_clone(skb, GFP_ATOMIC);
                                 } else {
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index f88256cbacbf..28de43092330 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -107,7 +107,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
         if (!netif_is_multiqueue(dev))
                 return -EOPNOTSUPP;
 
-        if (nla_len(opt) < sizeof(*qopt))
+        if (!opt || nla_len(opt) < sizeof(*qopt))
                 return -EINVAL;
 
         qopt = nla_data(opt);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 152b5b3c3fff..acd2edbc073e 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -173,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
         asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0;
         asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay;
         asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =
-                (unsigned long)sp->autoclose * HZ;
+                min_t(unsigned long, sp->autoclose, sctp_max_autoclose) * HZ;
 
         /* Initializes the timers */
         for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i)
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 08b3cead6503..817174eb5f41 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -697,13 +697,7 @@ static void sctp_packet_append_data(struct sctp_packet *packet,
         /* Keep track of how many bytes are in flight to the receiver. */
         asoc->outqueue.outstanding_bytes += datasize;
 
-        /* Update our view of the receiver's rwnd. Include sk_buff overhead
-         * while updating peer.rwnd so that it reduces the chances of a
-         * receiver running out of receive buffer space even when receive
-         * window is still open. This can happen when a sender is sending
-         * sending small messages.
-         */
-        datasize += sizeof(struct sk_buff);
+        /* Update our view of the receiver's rwnd. */
         if (datasize < rwnd)
                 rwnd -= datasize;
         else
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 14c2b06028ff..cfeb1d4a1ee6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -411,8 +411,7 @@ void sctp_retransmit_mark(struct sctp_outq *q,
                                         chunk->transport->flight_size -=
                                                         sctp_data_size(chunk);
                                 q->outstanding_bytes -= sctp_data_size(chunk);
-                                q->asoc->peer.rwnd += (sctp_data_size(chunk) +
-                                                        sizeof(struct sk_buff));
+                                q->asoc->peer.rwnd += sctp_data_size(chunk);
                         }
                         continue;
                 }
@@ -432,8 +431,7 @@ void sctp_retransmit_mark(struct sctp_outq *q,
                          * (Section 7.2.4)), add the data size of those
                          * chunks to the rwnd.
                          */
-                        q->asoc->peer.rwnd += (sctp_data_size(chunk) +
-                                                sizeof(struct sk_buff));
+                        q->asoc->peer.rwnd += sctp_data_size(chunk);
                         q->outstanding_bytes -= sctp_data_size(chunk);
                         if (chunk->transport)
                                 transport->flight_size -= sctp_data_size(chunk);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 544a9b68eb53..5942d27b1444 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1285,6 +1285,9 @@ SCTP_STATIC __init int sctp_init(void)
         sctp_max_instreams              = SCTP_DEFAULT_INSTREAMS;
         sctp_max_outstreams             = SCTP_DEFAULT_OUTSTREAMS;
 
+        /* Initialize maximum autoclose timeout. */
+        sctp_max_autoclose              = INT_MAX / HZ;
+
         /* Initialize handle used for association ids. */
         idr_init(&sctp_assocs_id);
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index db0308344d07..408ebd0e7330 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2200,8 +2200,6 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
                 return -EINVAL;
         if (copy_from_user(&sp->autoclose, optval, optlen))
                 return -EFAULT;
-        /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */
-        sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ);
 
         return 0;
 }
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 6b3952961b85..60ffbd067ff7 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -53,6 +53,10 @@ static int sack_timer_min = 1;
 static int sack_timer_max = 500;
 static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
 static int rwnd_scale_max = 16;
+static unsigned long max_autoclose_min = 0;
+static unsigned long max_autoclose_max =
+        (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
+        ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ;
 
 extern long sysctl_sctp_mem[3];
 extern int sysctl_sctp_rmem[3];
@@ -258,6 +262,15 @@ static ctl_table sctp_table[] = {
                 .extra1         = &one,
                 .extra2         = &rwnd_scale_max,
         },
+        {
+                .procname       = "max_autoclose",
+                .data           = &sctp_max_autoclose,
+                .maxlen         = sizeof(unsigned long),
+                .mode           = 0644,
+                .proc_handler   = &proc_doulongvec_minmax,
+                .extra1         = &max_autoclose_min,
+                .extra2         = &max_autoclose_max,
+        },
 
         { /* sentinel */ }
 };
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index d12ffa545811..00a1a2acd587 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -590,6 +590,27 @@ void rpc_prepare_task(struct rpc_task *task)
         task->tk_ops->rpc_call_prepare(task, task->tk_calldata);
 }
 
+static void
+rpc_init_task_statistics(struct rpc_task *task)
+{
+        /* Initialize retry counters */
+        task->tk_garb_retry = 2;
+        task->tk_cred_retry = 2;
+        task->tk_rebind_retry = 2;
+
+        /* starting timestamp */
+        task->tk_start = ktime_get();
+}
+
+static void
+rpc_reset_task_statistics(struct rpc_task *task)
+{
+        task->tk_timeouts = 0;
+        task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_KILLED|RPC_TASK_SENT);
+
+        rpc_init_task_statistics(task);
+}
+
 /*
  * Helper that calls task->tk_ops->rpc_call_done if it exists
  */
@@ -602,6 +623,7 @@ void rpc_exit_task(struct rpc_task *task)
                         WARN_ON(RPC_ASSASSINATED(task));
                         /* Always release the RPC slot and buffer memory */
                         xprt_release(task);
+                        rpc_reset_task_statistics(task);
                 }
         }
 }
@@ -804,11 +826,6 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
         task->tk_calldata = task_setup_data->callback_data;
         INIT_LIST_HEAD(&task->tk_task);
 
-        /* Initialize retry counters */
-        task->tk_garb_retry = 2;
-        task->tk_cred_retry = 2;
-        task->tk_rebind_retry = 2;
-
         task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW;
         task->tk_owner = current->tgid;
 
@@ -818,8 +835,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
         if (task->tk_ops->rpc_call_prepare != NULL)
                 task->tk_action = rpc_prepare_task;
 
-        /* starting timestamp */
-        task->tk_start = ktime_get();
+        rpc_init_task_statistics(task);
 
         dprintk("RPC:       new task initialized, procpid %u\n",
                                 task_pid_nr(current));
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index f4385e45a5fc..c64c0ef519b5 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -995,13 +995,11 @@ out_init_req:
 
 static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
 {
-        if (xprt_dynamic_free_slot(xprt, req))
-                return;
-
-        memset(req, 0, sizeof(*req));   /* mark unused */
-
         spin_lock(&xprt->reserve_lock);
-        list_add(&req->rq_list, &xprt->free);
+        if (!xprt_dynamic_free_slot(xprt, req)) {
+                memset(req, 0, sizeof(*req));   /* mark unused */
+                list_add(&req->rq_list, &xprt->free);
+        }
         rpc_wake_up_next(&xprt->backlog);
         spin_unlock(&xprt->reserve_lock);
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index eb6b0b7781a5..7661576b6f45 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2276,8 +2276,6 @@ static void __xfrm_garbage_collect(struct net *net)
 {
         struct dst_entry *head, *next;
 
-        flow_cache_flush();
-
         spin_lock_bh(&xfrm_policy_sk_bundle_lock);
         head = xfrm_policy_sk_bundles;
         xfrm_policy_sk_bundles = NULL;
@@ -2290,6 +2288,18 @@ static void __xfrm_garbage_collect(struct net *net)
         }
 }
 
+static void xfrm_garbage_collect(struct net *net)
+{
+        flow_cache_flush();
+        __xfrm_garbage_collect(net);
+}
+
+static void xfrm_garbage_collect_deferred(struct net *net)
+{
+        flow_cache_flush_deferred();
+        __xfrm_garbage_collect(net);
+}
+
 static void xfrm_init_pmtu(struct dst_entry *dst)
 {
         do {
@@ -2422,7 +2432,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
                 if (likely(dst_ops->neigh_lookup == NULL))
                         dst_ops->neigh_lookup = xfrm_neigh_lookup;
                 if (likely(afinfo->garbage_collect == NULL))
-                        afinfo->garbage_collect = __xfrm_garbage_collect;
+                        afinfo->garbage_collect = xfrm_garbage_collect_deferred;
                 xfrm_policy_afinfo[afinfo->family] = afinfo;
         }
         write_unlock_bh(&xfrm_policy_afinfo_lock);
@@ -2516,7 +2526,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 
         switch (event) {
         case NETDEV_DOWN:
-                __xfrm_garbage_collect(dev_net(dev));
+                xfrm_garbage_collect(dev_net(dev));
         }
         return NOTIFY_DONE;
 }