6 files changed, 131 insertions, 90 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 5d59155adf2a..9bb8f87c4cda 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1409,14 +1409,34 @@ EXPORT_SYMBOL(register_netdevice_notifier);
  *      register_netdevice_notifier(). The notifier is unlinked into the
  *      kernel structures and may then be reused. A negative errno code
  *      is returned on a failure.
+ *
+ *      After unregistering unregister and down device events are synthesized
+ *      for all devices on the device list to the removed notifier to remove
+ *      the need for special case cleanup code.
  */
 
 int unregister_netdevice_notifier(struct notifier_block *nb)
 {
+        struct net_device *dev;
+        struct net *net;
         int err;
 
         rtnl_lock();
         err = raw_notifier_chain_unregister(&netdev_chain, nb);
+        if (err)
+                goto unlock;
+
+        for_each_net(net) {
+                for_each_netdev(net, dev) {
+                        if (dev->flags & IFF_UP) {
+                                nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+                                nb->notifier_call(nb, NETDEV_DOWN, dev);
+                        }
+                        nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+                        nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
+                }
+        }
+unlock:
         rtnl_unlock();
         return err;
 }
@@ -1596,6 +1616,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
                 kfree_skb(skb);
                 return NET_RX_DROP;
         }
+        skb->skb_iif = 0;
         skb_set_dev(skb, dev);
         skb->tstamp.tv64 = 0;
         skb->pkt_type = PACKET_HOST;
@@ -4027,54 +4048,41 @@ static int dev_ifconf(struct net *net, char __user *arg)
 
 #ifdef CONFIG_PROC_FS
 
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
-
-struct dev_iter_state {
-        struct seq_net_private p;
-        unsigned int pos; /* bucket << BUCKET_SPACE + offset */
-};
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
 
 #define get_bucket(x) ((x) >> BUCKET_SPACE)
 #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
 #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
 
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
 {
-        struct dev_iter_state *state = seq->private;
         struct net *net = seq_file_net(seq);
         struct net_device *dev;
         struct hlist_node *p;
         struct hlist_head *h;
-        unsigned int count, bucket, offset;
+        unsigned int count = 0, offset = get_offset(*pos);
 
-        bucket = get_bucket(state->pos);
-        offset = get_offset(state->pos);
-        h = &net->dev_name_head[bucket];
-        count = 0;
+        h = &net->dev_name_head[get_bucket(*pos)];
         hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
-                if (count++ == offset) {
-                        state->pos = set_bucket_offset(bucket, count);
+                if (++count == offset)
                         return dev;
-                }
         }
 
         return NULL;
 }
 
-static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
 {
-        struct dev_iter_state *state = seq->private;
         struct net_device *dev;
         unsigned int bucket;
 
-        bucket = get_bucket(state->pos);
         do {
-                dev = dev_from_same_bucket(seq);
+                dev = dev_from_same_bucket(seq, pos);
                 if (dev)
                         return dev;
 
-                bucket++;
-                state->pos = set_bucket_offset(bucket, 0);
+                bucket = get_bucket(*pos) + 1;
+                *pos = set_bucket_offset(bucket, 1);
         } while (bucket < NETDEV_HASHENTRIES);
 
         return NULL;
@@ -4087,33 +4095,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
 void *dev_seq_start(struct seq_file *seq, loff_t *pos)
         __acquires(RCU)
 {
-        struct dev_iter_state *state = seq->private;
-
         rcu_read_lock();
         if (!*pos)
                 return SEQ_START_TOKEN;
 
-        /* check for end of the hash */
-        if (state->pos == 0 && *pos > 1)
+        if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
                 return NULL;
 
-        return dev_from_new_bucket(seq);
+        return dev_from_bucket(seq, pos);
 }
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-        struct net_device *dev;
-
         ++*pos;
-
-        if (v == SEQ_START_TOKEN)
-                return dev_from_new_bucket(seq);
-
-        dev = dev_from_same_bucket(seq);
-        if (dev)
-                return dev;
-
-        return dev_from_new_bucket(seq);
+        return dev_from_bucket(seq, pos);
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4212,13 +4207,7 @@ static const struct seq_operations dev_seq_ops = {
 static int dev_seq_open(struct inode *inode, struct file *file)
 {
         return seq_open_net(inode, file, &dev_seq_ops,
-                            sizeof(struct dev_iter_state));
-}
-
-int dev_seq_open_ops(struct inode *inode, struct file *file,
-                     const struct seq_operations *ops)
-{
-        return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+                            sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_seq_fops = {
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 29c07fef9228..626698f0db8b 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -696,7 +696,8 @@ static const struct seq_operations dev_mc_seq_ops = {
 
 static int dev_mc_seq_open(struct inode *inode, struct file *file)
 {
-        return dev_seq_open_ops(inode, file, &dev_mc_seq_ops);
+        return seq_open_net(inode, file, &dev_mc_seq_ops,
+                            sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_mc_seq_fops = {
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 7f36b38e060f..a7cad741df01 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -42,13 +42,14 @@ static void send_dm_alert(struct work_struct *unused);
  * netlink alerts
  */
 static int trace_state = TRACE_OFF;
-static DEFINE_SPINLOCK(trace_state_lock);
+static DEFINE_MUTEX(trace_state_mutex);
 
 struct per_cpu_dm_data {
         struct work_struct dm_alert_work;
-        struct sk_buff *skb;
+        struct sk_buff __rcu *skb;
         atomic_t dm_hit_count;
         struct timer_list send_timer;
+        int cpu;
 };
 
 struct dm_hw_stat_delta {
@@ -79,29 +80,53 @@ static void 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);
 
         al = sizeof(struct net_dm_alert_msg);
         al += dm_hit_limit * sizeof(struct net_dm_drop_point);
         al += sizeof(struct nlattr);
 
-        data->skb = genlmsg_new(al, GFP_KERNEL);
-        genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
-                        0, NET_DM_CMD_ALERT);
-        nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg));
-        msg = nla_data(nla);
-        memset(msg, 0, al);
-        atomic_set(&data->dm_hit_count, dm_hit_limit);
+        skb = genlmsg_new(al, GFP_KERNEL);
+
+        if (skb) {
+                genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+                                0, NET_DM_CMD_ALERT);
+                nla = nla_reserve(skb, NLA_UNSPEC,
+                                  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);
+        }
+
 }
 
 static void send_dm_alert(struct work_struct *unused)
 {
         struct sk_buff *skb;
-        struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+        struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+
+        WARN_ON_ONCE(data->cpu != smp_processor_id());
 
         /*
          * Grab the skb we're about to send
          */
-        skb = data->skb;
+        skb = rcu_dereference_protected(data->skb, 1);
 
         /*
          * Replace it with a new one
@@ -111,8 +136,10 @@ static void send_dm_alert(struct work_struct *unused)
         /*
          * Ship it!
          */
-        genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+        if (skb)
+                genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
 
+        put_cpu_var(dm_cpu_data);
 }
 
 /*
@@ -123,9 +150,11 @@ static void send_dm_alert(struct work_struct *unused)
  */
 static void sched_send_work(unsigned long unused)
 {
-        struct per_cpu_dm_data *data =  &__get_cpu_var(dm_cpu_data);
+        struct per_cpu_dm_data *data =  &get_cpu_var(dm_cpu_data);
+
+        schedule_work_on(smp_processor_id(), &data->dm_alert_work);
 
-        schedule_work(&data->dm_alert_work);
+        put_cpu_var(dm_cpu_data);
 }
 
 static void trace_drop_common(struct sk_buff *skb, void *location)
@@ -134,8 +163,15 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
         struct nlmsghdr *nlh;
         struct nlattr *nla;
         int i;
-        struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+        struct sk_buff *dskb;
+        struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+
+
+        rcu_read_lock();
+        dskb = rcu_dereference(data->skb);
 
+        if (!dskb)
+                goto out;
 
         if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
                 /*
@@ -144,12 +180,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
                 goto out;
         }
 
-        nlh = (struct nlmsghdr *)data->skb->data;
+        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;
                 }
         }
@@ -157,7 +194,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
         /*
          * We need to create a new entry
          */
-        __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
+        __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
         nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
         memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
         msg->points[msg->entries].count = 1;
@@ -169,6 +206,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
         }
 
 out:
+        rcu_read_unlock();
+        put_cpu_var(dm_cpu_data);
         return;
 }
 
@@ -213,7 +252,7 @@ static int set_all_monitor_traces(int state)
         struct dm_hw_stat_delta *new_stat = NULL;
         struct dm_hw_stat_delta *temp;
 
-        spin_lock(&trace_state_lock);
+        mutex_lock(&trace_state_mutex);
 
         if (state == trace_state) {
                 rc = -EAGAIN;
@@ -252,7 +291,7 @@ static int set_all_monitor_traces(int state)
                 rc = -EINPROGRESS;
 
 out_unlock:
-        spin_unlock(&trace_state_lock);
+        mutex_unlock(&trace_state_mutex);
 
         return rc;
 }
@@ -295,12 +334,12 @@ static int dropmon_net_event(struct notifier_block *ev_block,
 
                 new_stat->dev = dev;
                 new_stat->last_rx = jiffies;
-                spin_lock(&trace_state_lock);
+                mutex_lock(&trace_state_mutex);
                 list_add_rcu(&new_stat->list, &hw_stats_list);
-                spin_unlock(&trace_state_lock);
+                mutex_unlock(&trace_state_mutex);
                 break;
         case NETDEV_UNREGISTER:
-                spin_lock(&trace_state_lock);
+                mutex_lock(&trace_state_mutex);
                 list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
                         if (new_stat->dev == dev) {
                                 new_stat->dev = NULL;
@@ -311,7 +350,7 @@ static int dropmon_net_event(struct notifier_block *ev_block,
                                 }
                         }
                 }
-                spin_unlock(&trace_state_lock);
+                mutex_unlock(&trace_state_mutex);
                 break;
         }
 out:
@@ -367,13 +406,15 @@ static int __init init_net_drop_monitor(void)
 
         for_each_present_cpu(cpu) {
                 data = &per_cpu(dm_cpu_data, cpu);
-                reset_per_cpu_data(data);
+                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.function = sched_send_work;
+                reset_per_cpu_data(data);
         }
 
+
         goto out;
 
 out_unreg:
diff --git a/net/core/filter.c b/net/core/filter.c
index cf4989ac503b..6f755cca4520 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -39,8 +39,11 @@
 #include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 
-/* No hurry in this branch */
-static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
+/* No hurry in this branch
+ *
+ * Exported for the bpf jit load helper.
+ */
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
 {
         u8 *ptr = NULL;
 
@@ -59,7 +62,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k,
 {
         if (k >= 0)
                 return skb_header_pointer(skb, k, size, buffer);
-        return __load_pointer(skb, k, size);
+        return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
 /**
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 0e950fda9a0a..31a5ae51a45c 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -83,21 +83,29 @@ assign:
 
 static int ops_init(const struct pernet_operations *ops, struct net *net)
 {
-        int err;
+        int err = -ENOMEM;
+        void *data = NULL;
+
         if (ops->id && ops->size) {
-                void *data = kzalloc(ops->size, GFP_KERNEL);
+                data = kzalloc(ops->size, GFP_KERNEL);
                 if (!data)
-                        return -ENOMEM;
+                        goto out;
 
                 err = net_assign_generic(net, *ops->id, data);
-                if (err) {
-                        kfree(data);
-                        return err;
-                }
+                if (err)
+                        goto cleanup;
         }
+        err = 0;
         if (ops->init)
-                return ops->init(net);
-        return 0;
+                err = ops->init(net);
+        if (!err)
+                return 0;
+
+cleanup:
+        kfree(data);
+
+out:
+        return err;
 }
 
 static void ops_free(const struct pernet_operations *ops, struct net *net)
@@ -448,12 +456,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
 static int __register_pernet_operations(struct list_head *list,
                                         struct pernet_operations *ops)
 {
-        int err = 0;
-        err = ops_init(ops, &init_net);
-        if (err)
-                ops_free(ops, &init_net);
-        return err;
-        
+        return ops_init(ops, &init_net);
 }
 
 static void __unregister_pernet_operations(struct pernet_operations *ops)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f223cdc75da6..e59840010d45 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -952,9 +952,11 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
                 goto adjust_others;
         }
 
-        data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+        data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+                       gfp_mask);
         if (!data)
                 goto nodata;
+        size = SKB_WITH_OVERHEAD(ksize(data));
 
         /* Copy only real data... and, alas, header. This should be
          * optimized for the cases when header is void.
@@ -3161,6 +3163,8 @@ static void sock_rmem_free(struct sk_buff *skb)
  */
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
+        int len = skb->len;
+
         if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
             (unsigned)sk->sk_rcvbuf)
                 return -ENOMEM;
@@ -3175,7 +3179,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
         skb_queue_tail(&sk->sk_error_queue, skb);
         if (!sock_flag(sk, SOCK_DEAD))
-                sk->sk_data_ready(sk, skb->len);
+                sk->sk_data_ready(sk, len);
         return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);