8 files changed, 121 insertions, 134 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index cd0981977f5c..1cb0d8a6aa6c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1136,8 +1136,8 @@ void dev_load(struct net *net, const char *name)
                 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);
+                        pr_warn("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);
@@ -2089,25 +2089,6 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
         return 0;
 }
 
-/*
- * Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested or the sk-reference
- * is needed on driver level for other reasons, e.g. see net/can/raw.c
- */
-static inline void skb_orphan_try(struct sk_buff *skb)
-{
-        struct sock *sk = skb->sk;
-
-        if (sk && !skb_shinfo(skb)->tx_flags) {
-                /* skb_tx_hash() wont be able to get sk.
-                 * We copy sk_hash into skb->rxhash
-                 */
-                if (!skb->rxhash)
-                        skb->rxhash = sk->sk_hash;
-                skb_orphan(skb);
-        }
-}
-
 static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
 {
         return ((features & NETIF_F_GEN_CSUM) ||
@@ -2193,8 +2174,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
                 if (!list_empty(&ptype_all))
                         dev_queue_xmit_nit(skb, dev);
 
-                skb_orphan_try(skb);
-
                 features = netif_skb_features(skb);
 
                 if (vlan_tx_tag_present(skb) &&
@@ -2304,7 +2283,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
         if (skb->sk && skb->sk->sk_hash)
                 hash = skb->sk->sk_hash;
         else
-                hash = (__force u16) skb->protocol ^ skb->rxhash;
+                hash = (__force u16) skb->protocol;
         hash = jhash_1word(hash, hashrnd);
 
         return (u16) (((u64) hash * qcount) >> 32) + qoffset;
@@ -2465,8 +2444,12 @@ static void skb_update_prio(struct sk_buff *skb)
 {
         struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
 
-        if ((!skb->priority) && (skb->sk) && map)
-                skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
+        if (!skb->priority && skb->sk && map) {
+                unsigned int prioidx = skb->sk->sk_cgrp_prioidx;
+
+                if (prioidx < map->priomap_len)
+                        skb->priority = map->priomap[prioidx];
+        }
 }
 #else
 #define skb_update_prio(skb)
@@ -6300,7 +6283,8 @@ static struct hlist_head *netdev_create_hash(void)
 /* Initialize per network namespace state */
 static int __net_init netdev_init(struct net *net)
 {
-        INIT_LIST_HEAD(&net->dev_base_head);
+        if (net != &init_net)
+                INIT_LIST_HEAD(&net->dev_base_head);
 
         net->dev_name_head = netdev_create_hash();
         if (net->dev_name_head == NULL)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index ea5fb9fcc3f5..d23b6682f4e9 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -36,9 +36,6 @@
 #define TRACE_ON 1
 #define TRACE_OFF 0
 
-static void send_dm_alert(struct work_struct *unused);
-
-
 /*
  * Globals, our netlink socket pointer
  * and the work handle that will send up
@@ -48,11 +45,10 @@ static int trace_state = TRACE_OFF;
 static DEFINE_MUTEX(trace_state_mutex);
 
 struct per_cpu_dm_data {
-        struct work_struct dm_alert_work;
-        struct sk_buff __rcu *skb;
-        atomic_t dm_hit_count;
-        struct timer_list send_timer;
-        int cpu;
+        spinlock_t              lock;
+        struct sk_buff          *skb;
+        struct work_struct      dm_alert_work;
+        struct timer_list       send_timer;
 };
 
 struct dm_hw_stat_delta {
@@ -78,13 +74,13 @@ static int dm_delay = 1;
 static unsigned long dm_hw_check_delta = 2*HZ;
 static LIST_HEAD(hw_stats_list);
 
-static void reset_per_cpu_data(struct per_cpu_dm_data *data)
+static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 {
         size_t al;
         struct net_dm_alert_msg *msg;
         struct nlattr *nla;
         struct sk_buff *skb;
-        struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1);
+        unsigned long flags;
 
         al = sizeof(struct net_dm_alert_msg);
         al += dm_hit_limit * sizeof(struct net_dm_drop_point);
@@ -99,65 +95,40 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data)
                                   sizeof(struct net_dm_alert_msg));
                 msg = nla_data(nla);
                 memset(msg, 0, al);
-        } else
-                schedule_work_on(data->cpu, &data->dm_alert_work);
-
-        /*
-         * Don't need to lock this, since we are guaranteed to only
-         * run this on a single cpu at a time.
-         * Note also that we only update data->skb if the old and new skb
-         * pointers don't match.  This ensures that we don't continually call
-         * synchornize_rcu if we repeatedly fail to alloc a new netlink message.
-         */
-        if (skb != oskb) {
-                rcu_assign_pointer(data->skb, skb);
-
-                synchronize_rcu();
-
-                atomic_set(&data->dm_hit_count, dm_hit_limit);
+        } else {
+                mod_timer(&data->send_timer, jiffies + HZ / 10);
         }
 
+        spin_lock_irqsave(&data->lock, flags);
+        swap(data->skb, skb);
+        spin_unlock_irqrestore(&data->lock, flags);
+
+        return skb;
 }
 
-static void send_dm_alert(struct work_struct *unused)
+static void send_dm_alert(struct work_struct *work)
 {
         struct sk_buff *skb;
-        struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+        struct per_cpu_dm_data *data;
 
-        WARN_ON_ONCE(data->cpu != smp_processor_id());
+        data = container_of(work, struct per_cpu_dm_data, dm_alert_work);
 
-        /*
-         * Grab the skb we're about to send
-         */
-        skb = rcu_dereference_protected(data->skb, 1);
-
-        /*
-         * Replace it with a new one
-         */
-        reset_per_cpu_data(data);
+        skb = reset_per_cpu_data(data);
 
-        /*
-         * Ship it!
-         */
         if (skb)
                 genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
-
-        put_cpu_var(dm_cpu_data);
 }
 
 /*
  * This is the timer function to delay the sending of an alert
  * in the event that more drops will arrive during the
- * hysteresis period.  Note that it operates under the timer interrupt
- * so we don't need to disable preemption here
+ * hysteresis period.
  */
-static void sched_send_work(unsigned long unused)
+static void sched_send_work(unsigned long _data)
 {
-        struct per_cpu_dm_data *data =  &get_cpu_var(dm_cpu_data);
-
-        schedule_work_on(smp_processor_id(), &data->dm_alert_work);
+        struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data;
 
-        put_cpu_var(dm_cpu_data);
+        schedule_work(&data->dm_alert_work);
 }
 
 static void trace_drop_common(struct sk_buff *skb, void *location)
@@ -167,33 +138,28 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
         struct nlattr *nla;
         int i;
         struct sk_buff *dskb;
-        struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
-
+        struct per_cpu_dm_data *data;
+        unsigned long flags;
 
-        rcu_read_lock();
-        dskb = rcu_dereference(data->skb);
+        local_irq_save(flags);
+        data = &__get_cpu_var(dm_cpu_data);
+        spin_lock(&data->lock);
+        dskb = data->skb;
 
         if (!dskb)
                 goto out;
 
-        if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
-                /*
-                 * we're already at zero, discard this hit
-                 */
-                goto out;
-        }
-
         nlh = (struct nlmsghdr *)dskb->data;
         nla = genlmsg_data(nlmsg_data(nlh));
         msg = nla_data(nla);
         for (i = 0; i < msg->entries; i++) {
                 if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
                         msg->points[i].count++;
-                        atomic_inc(&data->dm_hit_count);
                         goto out;
                 }
         }
-
+        if (msg->entries == dm_hit_limit)
+                goto out;
         /*
          * We need to create a new entry
          */
@@ -205,13 +171,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 
         if (!timer_pending(&data->send_timer)) {
                 data->send_timer.expires = jiffies + dm_delay * HZ;
-                add_timer_on(&data->send_timer, smp_processor_id());
+                add_timer(&data->send_timer);
         }
 
 out:
-        rcu_read_unlock();
-        put_cpu_var(dm_cpu_data);
-        return;
+        spin_unlock_irqrestore(&data->lock, flags);
 }
 
 static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
@@ -418,11 +382,11 @@ static int __init init_net_drop_monitor(void)
 
         for_each_possible_cpu(cpu) {
                 data = &per_cpu(dm_cpu_data, cpu);
-                data->cpu = cpu;
                 INIT_WORK(&data->dm_alert_work, send_dm_alert);
                 init_timer(&data->send_timer);
-                data->send_timer.data = cpu;
+                data->send_timer.data = (unsigned long)data;
                 data->send_timer.function = sched_send_work;
+                spin_lock_init(&data->lock);
                 reset_per_cpu_data(data);
         }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index a3eddb515d1b..d4ce2dc712e3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -616,9 +616,9 @@ static int __sk_prepare_filter(struct sk_filter *fp)
 /**
  *      sk_unattached_filter_create - create an unattached filter
  *      @fprog: the filter program
- *      @sk: the socket to use
+ *      @pfp: the unattached filter that is created
  *
- * Create a filter independent ofr any socket. We first run some
+ * Create a filter independent of any socket. We first run some
  * sanity checks on it to make sure it does not explode on us later.
  * If an error occurs or there is insufficient memory for the filter
  * a negative errno code is returned. On success the return is zero.
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index eb09f8bbbf07..d81d026138f0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2219,9 +2219,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
         rcu_read_lock_bh();
         nht = rcu_dereference_bh(tbl->nht);
 
-        for (h = 0; h < (1 << nht->hash_shift); h++) {
-                if (h < s_h)
-                        continue;
+        for (h = s_h; h < (1 << nht->hash_shift); h++) {
                 if (h > s_h)
                         s_idx = 0;
                 for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0;
@@ -2260,9 +2258,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 
         read_lock_bh(&tbl->lock);
 
-        for (h = 0; h <= PNEIGH_HASHMASK; h++) {
-                if (h < s_h)
-                        continue;
+        for (h = s_h; h <= PNEIGH_HASHMASK; h++) {
                 if (h > s_h)
                         s_idx = 0;
                 for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
@@ -2297,7 +2293,7 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
         struct neigh_table *tbl;
         int t, family, s_t;
         int proxy = 0;
-        int err = 0;
+        int err;
 
         read_lock(&neigh_tbl_lock);
         family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
@@ -2311,7 +2307,7 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
         s_t = cb->args[0];
 
-        for (tbl = neigh_tables, t = 0; tbl && (err >= 0);
+        for (tbl = neigh_tables, t = 0; tbl;
              tbl = tbl->next, t++) {
                 if (t < s_t || (family && tbl->family != family))
                         continue;
@@ -2322,6 +2318,8 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
                         err = pneigh_dump_table(tbl, skb, cb);
                 else
                         err = neigh_dump_table(tbl, skb, cb);
+                if (err < 0)
+                        break;
         }
         read_unlock(&neigh_tbl_lock);
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index dddbacb8f28c..42f1e1c7514f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -27,7 +27,9 @@ static DEFINE_MUTEX(net_mutex);
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
 
-struct net init_net;
+struct net init_net = {
+        .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
+};
 EXPORT_SYMBOL(init_net);
 
 #define INITIAL_NET_GEN_PTRS    13 /* +1 for len +2 for rcu_head */
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3d84fb9d8873..f9f40b932e4b 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -362,22 +362,23 @@ EXPORT_SYMBOL(netpoll_send_skb_on_dev);
 
 void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 {
-        int total_len, eth_len, ip_len, udp_len;
+        int total_len, ip_len, udp_len;
         struct sk_buff *skb;
         struct udphdr *udph;
         struct iphdr *iph;
         struct ethhdr *eth;
 
         udp_len = len + sizeof(*udph);
-        ip_len = eth_len = udp_len + sizeof(*iph);
-        total_len = eth_len + ETH_HLEN + NET_IP_ALIGN;
+        ip_len = udp_len + sizeof(*iph);
+        total_len = ip_len + LL_RESERVED_SPACE(np->dev);
 
-        skb = find_skb(np, total_len, total_len - len);
+        skb = find_skb(np, total_len + np->dev->needed_tailroom,
+                       total_len - len);
         if (!skb)
                 return;
 
         skb_copy_to_linear_data(skb, msg, len);
-        skb->len += len;
+        skb_put(skb, len);
 
         skb_push(skb, sizeof(*udph));
         skb_reset_transport_header(skb);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 5b8aa2fae48b..b2e9caa1ad1a 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -49,8 +49,9 @@ static int get_prioidx(u32 *prio)
                 return -ENOSPC;
         }
         set_bit(prioidx, prioidx_map);
+        if (atomic_read(&max_prioidx) < prioidx)
+                atomic_set(&max_prioidx, prioidx);
         spin_unlock_irqrestore(&prioidx_map_lock, flags);
-        atomic_set(&max_prioidx, prioidx);
         *prio = prioidx;
         return 0;
 }
@@ -64,7 +65,7 @@ static void put_prioidx(u32 idx)
         spin_unlock_irqrestore(&prioidx_map_lock, flags);
 }
 
-static void extend_netdev_table(struct net_device *dev, u32 new_len)
+static int extend_netdev_table(struct net_device *dev, u32 new_len)
 {
         size_t new_size = sizeof(struct netprio_map) +
                            ((sizeof(u32) * new_len));
@@ -76,7 +77,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
 
         if (!new_priomap) {
                 pr_warn("Unable to alloc new priomap!\n");
-                return;
+                return -ENOMEM;
         }
 
         for (i = 0;
@@ -89,46 +90,79 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
         rcu_assign_pointer(dev->priomap, new_priomap);
         if (old_priomap)
                 kfree_rcu(old_priomap, rcu);
+        return 0;
 }
 
-static void update_netdev_tables(void)
+static int write_update_netdev_table(struct net_device *dev)
 {
+        int ret = 0;
+        u32 max_len;
+        struct netprio_map *map;
+
+        rtnl_lock();
+        max_len = atomic_read(&max_prioidx) + 1;
+        map = rtnl_dereference(dev->priomap);
+        if (!map || map->priomap_len < max_len)
+                ret = extend_netdev_table(dev, max_len);
+        rtnl_unlock();
+
+        return ret;
+}
+
+static int update_netdev_tables(void)
+{
+        int ret = 0;
         struct net_device *dev;
-        u32 max_len = atomic_read(&max_prioidx) + 1;
+        u32 max_len;
         struct netprio_map *map;
 
         rtnl_lock();
+        max_len = atomic_read(&max_prioidx) + 1;
         for_each_netdev(&init_net, dev) {
                 map = rtnl_dereference(dev->priomap);
-                if ((!map) ||
-                    (map->priomap_len < max_len))
-                        extend_netdev_table(dev, max_len);
+                /*
+                 * don't allocate priomap if we didn't
+                 * change net_prio.ifpriomap (map == NULL),
+                 * this will speed up skb_update_prio.
+                 */
+                if (map && map->priomap_len < max_len) {
+                        ret = extend_netdev_table(dev, max_len);
+                        if (ret < 0)
+                                break;
+                }
         }
         rtnl_unlock();
+        return ret;
 }
 
 static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
 {
         struct cgroup_netprio_state *cs;
-        int ret;
+        int ret = -EINVAL;
 
         cs = kzalloc(sizeof(*cs), GFP_KERNEL);
         if (!cs)
                 return ERR_PTR(-ENOMEM);
 
-        if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-                kfree(cs);
-                return ERR_PTR(-EINVAL);
-        }
+        if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+                goto out;
 
         ret = get_prioidx(&cs->prioidx);
-        if (ret != 0) {
+        if (ret < 0) {
                 pr_warn("No space in priority index array\n");
-                kfree(cs);
-                return ERR_PTR(ret);
+                goto out;
+        }
+
+        ret = update_netdev_tables();
+        if (ret < 0) {
+                put_prioidx(cs->prioidx);
+                goto out;
         }
 
         return &cs->css;
+out:
+        kfree(cs);
+        return ERR_PTR(ret);
 }
 
 static void cgrp_destroy(struct cgroup *cgrp)
@@ -141,7 +175,7 @@ static void cgrp_destroy(struct cgroup *cgrp)
         rtnl_lock();
         for_each_netdev(&init_net, dev) {
                 map = rtnl_dereference(dev->priomap);
-                if (map)
+                if (map && cs->prioidx < map->priomap_len)
                         map->priomap[cs->prioidx] = 0;
         }
         rtnl_unlock();
@@ -165,7 +199,7 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft,
         rcu_read_lock();
         for_each_netdev_rcu(&init_net, dev) {
                 map = rcu_dereference(dev->priomap);
-                priority = map ? map->priomap[prioidx] : 0;
+                priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0;
                 cb->fill(cb, dev->name, priority);
         }
         rcu_read_unlock();
@@ -220,13 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
         if (!dev)
                 goto out_free_devname;
 
-        update_netdev_tables();
-        ret = 0;
+        ret = write_update_netdev_table(dev);
+        if (ret < 0)
+                goto out_put_dev;
+
         rcu_read_lock();
         map = rcu_dereference(dev->priomap);
         if (map)
                 map->priomap[prioidx] = priority;
         rcu_read_unlock();
+
+out_put_dev:
         dev_put(dev);
 
 out_free_devname:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bac3c5756d63..d124306b81fd 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -353,7 +353,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
         unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) +
                               SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-        if (fragsz <= PAGE_SIZE && !(gfp_mask & __GFP_WAIT)) {
+        if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
                 void *data = netdev_alloc_frag(fragsz);
 
                 if (likely(data)) {
@@ -3362,7 +3362,7 @@ EXPORT_SYMBOL(kfree_skb_partial);
  * @to: prior buffer
  * @from: buffer to add
  * @fragstolen: pointer to boolean
- *
+ * @delta_truesize: how much more was allocated than was requested
  */
 bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
                       bool *fragstolen, int *delta_truesize)