Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

5 files changed, 79 insertions, 63 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 07a48e2bf7db..1845b08c624e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1006,15 +1006,10 @@ int dev_change_name(struct net_device *dev, const char *newname)
                 return err;
 
 rollback:
-        /* For now only devices in the initial network namespace
-         * are in sysfs.
-         */
-        if (net_eq(net, &init_net)) {
-                ret = device_rename(&dev->dev, dev->name);
-                if (ret) {
-                        memcpy(dev->name, oldname, IFNAMSIZ);
-                        return ret;
-                }
+        ret = device_rename(&dev->dev, dev->name);
+        if (ret) {
+                memcpy(dev->name, oldname, IFNAMSIZ);
+                return ret;
         }
 
         write_lock_bh(&dev_base_lock);
@@ -4998,8 +4993,6 @@ int register_netdevice(struct net_device *dev)
         if (dev->features & NETIF_F_SG)
                 dev->features |= NETIF_F_GSO;
 
-        netdev_initialize_kobject(dev);
-
         ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
         ret = notifier_to_errno(ret);
         if (ret)
@@ -5551,15 +5544,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
         if (dev->features & NETIF_F_NETNS_LOCAL)
                 goto out;
 
-#ifdef CONFIG_SYSFS
-        /* Don't allow real devices to be moved when sysfs
-         * is enabled.
-         */
-        err = -EINVAL;
-        if (dev->dev.parent)
-                goto out;
-#endif
-
         /* Ensure the device has been registrered */
         err = -EINVAL;
         if (dev->reg_state != NETREG_REGISTERED)
@@ -5610,8 +5594,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
         dev_uc_flush(dev);
         dev_mc_flush(dev);
 
-        netdev_unregister_kobject(dev);
-
         /* Actually switch the network namespace */
         dev_net_set(dev, net);
 
@@ -5624,7 +5606,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
         }
 
         /* Fixup kobjects */
-        err = netdev_register_kobject(dev);
+        err = device_rename(&dev->dev, dev->name);
         WARN_ON(err);
 
         /* Add the device back in the hashes */
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index cf208d8042b1..ad41529fb60f 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -172,12 +172,12 @@ out:
         return;
 }
 
-static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
+static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
 {
         trace_drop_common(skb, location);
 }
 
-static void trace_napi_poll_hit(struct napi_struct *napi)
+static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
 {
         struct dm_hw_stat_delta *new_stat;
 
@@ -225,12 +225,12 @@ static int set_all_monitor_traces(int state)
 
         switch (state) {
         case TRACE_ON:
-                rc |= register_trace_kfree_skb(trace_kfree_skb_hit);
-                rc |= register_trace_napi_poll(trace_napi_poll_hit);
+                rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+                rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
                 break;
         case TRACE_OFF:
-                rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit);
-                rc |= unregister_trace_napi_poll(trace_napi_poll_hit);
+                rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+                rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
 
                 tracepoint_synchronize_unregister();
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index c57c4b228bb5..99e7052d7323 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -14,7 +14,9 @@
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
 #include <linux/slab.h>
+#include <linux/nsproxy.h>
 #include <net/sock.h>
+#include <net/net_namespace.h>
 #include <linux/rtnetlink.h>
 #include <linux/wireless.h>
 #include <linux/vmalloc.h>
@@ -467,6 +469,7 @@ static struct attribute_group wireless_group = {
         .attrs = wireless_attrs,
 };
 #endif
+#endif /* CONFIG_SYSFS */
 
 #ifdef CONFIG_RPS
 /*
@@ -766,7 +769,38 @@ static void rx_queue_remove_kobjects(struct net_device *net)
         kset_unregister(net->queues_kset);
 }
 #endif /* CONFIG_RPS */
-#endif /* CONFIG_SYSFS */
+
+static const void *net_current_ns(void)
+{
+        return current->nsproxy->net_ns;
+}
+
+static const void *net_initial_ns(void)
+{
+        return &init_net;
+}
+
+static const void *net_netlink_ns(struct sock *sk)
+{
+        return sock_net(sk);
+}
+
+static struct kobj_ns_type_operations net_ns_type_operations = {
+        .type = KOBJ_NS_TYPE_NET,
+        .current_ns = net_current_ns,
+        .netlink_ns = net_netlink_ns,
+        .initial_ns = net_initial_ns,
+};
+
+static void net_kobj_ns_exit(struct net *net)
+{
+        kobj_ns_exit(KOBJ_NS_TYPE_NET, net);
+}
+
+static struct pernet_operations kobj_net_ops = {
+        .exit = net_kobj_ns_exit,
+};
+
 
 #ifdef CONFIG_HOTPLUG
 static int netdev_uevent(struct device *d, struct kobj_uevent_env *env)
@@ -774,9 +808,6 @@ static int netdev_uevent(struct device *d, struct kobj_uevent_env *env)
         struct net_device *dev = to_net_dev(d);
         int retval;
 
-        if (!net_eq(dev_net(dev), &init_net))
-                return 0;
-
         /* pass interface to uevent. */
         retval = add_uevent_var(env, "INTERFACE=%s", dev->name);
         if (retval)
@@ -806,6 +837,13 @@ static void netdev_release(struct device *d)
         kfree((char *)dev - dev->padded);
 }
 
+static const void *net_namespace(struct device *d)
+{
+        struct net_device *dev;
+        dev = container_of(d, struct net_device, dev);
+        return dev_net(dev);
+}
+
 static struct class net_class = {
         .name = "net",
         .dev_release = netdev_release,
@@ -815,6 +853,8 @@ static struct class net_class = {
 #ifdef CONFIG_HOTPLUG
         .dev_uevent = netdev_uevent,
 #endif
+        .ns_type = &net_ns_type_operations,
+        .namespace = net_namespace,
 };
 
 /* Delete sysfs entries but hold kobject reference until after all
@@ -826,9 +866,6 @@ void netdev_unregister_kobject(struct net_device * net)
 
         kobject_get(&dev->kobj);
 
-        if (!net_eq(dev_net(net), &init_net))
-                return;
-
 #ifdef CONFIG_RPS
         rx_queue_remove_kobjects(net);
 #endif
@@ -843,6 +880,7 @@ int netdev_register_kobject(struct net_device *net)
         const struct attribute_group **groups = net->sysfs_groups;
         int error = 0;
 
+        device_initialize(dev);
         dev->class = &net_class;
         dev->platform_data = net;
         dev->groups = groups;
@@ -865,9 +903,6 @@ int netdev_register_kobject(struct net_device *net)
 #endif
 #endif /* CONFIG_SYSFS */
 
-        if (!net_eq(dev_net(net), &init_net))
-                return 0;
-
         error = device_add(dev);
         if (error)
                 return error;
@@ -896,13 +931,9 @@ void netdev_class_remove_file(struct class_attribute *class_attr)
 EXPORT_SYMBOL(netdev_class_create_file);
 EXPORT_SYMBOL(netdev_class_remove_file);
 
-void netdev_initialize_kobject(struct net_device *net)
-{
-        struct device *device = &(net->dev);
-        device_initialize(device);
-}
-
 int netdev_kobject_init(void)
 {
+        kobj_ns_type_register(&net_ns_type_operations);
+        register_pernet_subsys(&kobj_net_ops);
         return class_register(&net_class);
 }
diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h
index 14e7524260b3..805555e8b187 100644
--- a/net/core/net-sysfs.h
+++ b/net/core/net-sysfs.h
@@ -4,5 +4,4 @@
 int netdev_kobject_init(void);
 int netdev_register_kobject(struct net_device *);
 void netdev_unregister_kobject(struct net_device *);
-void netdev_initialize_kobject(struct net_device *);
 #endif
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f2913ae2b52c..4e7ac09c281a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1406,12 +1406,13 @@ new_page:
 /*
  * Fill page/offset/length into spd, if it can hold more pages.
  */
-static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
+static inline int spd_fill_page(struct splice_pipe_desc *spd,
+                                struct pipe_inode_info *pipe, struct page *page,
                                 unsigned int *len, unsigned int offset,
                                 struct sk_buff *skb, int linear,
                                 struct sock *sk)
 {
-        if (unlikely(spd->nr_pages == PIPE_BUFFERS))
+        if (unlikely(spd->nr_pages == pipe->buffers))
                 return 1;
 
         if (linear) {
@@ -1447,7 +1448,8 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
                                    unsigned int plen, unsigned int *off,
                                    unsigned int *len, struct sk_buff *skb,
                                    struct splice_pipe_desc *spd, int linear,
-                                   struct sock *sk)
+                                   struct sock *sk,
+                                   struct pipe_inode_info *pipe)
 {
         if (!*len)
                 return 1;
@@ -1470,7 +1472,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
                 /* the linear region may spread across several pages  */
                 flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
 
-                if (spd_fill_page(spd, page, &flen, poff, skb, linear, sk))
+                if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk))
                         return 1;
 
                 __segment_seek(&page, &poff, &plen, flen);
@@ -1485,9 +1487,9 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
  * Map linear and fragment data from the skb to spd. It reports failure if the
  * pipe is full or if we already spliced the requested length.
  */
-static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
-                             unsigned int *len, struct splice_pipe_desc *spd,
-                             struct sock *sk)
+static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
+                             unsigned int *offset, unsigned int *len,
+                             struct splice_pipe_desc *spd, struct sock *sk)
 {
         int seg;
 
@@ -1497,7 +1499,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
         if (__splice_segment(virt_to_page(skb->data),
                              (unsigned long) skb->data & (PAGE_SIZE - 1),
                              skb_headlen(skb),
-                             offset, len, skb, spd, 1, sk))
+                             offset, len, skb, spd, 1, sk, pipe))
                 return 1;
 
         /*
@@ -1507,7 +1509,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
                 const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
 
                 if (__splice_segment(f->page, f->page_offset, f->size,
-                                     offset, len, skb, spd, 0, sk))
+                                     offset, len, skb, spd, 0, sk, pipe))
                         return 1;
         }
 
@@ -1524,8 +1526,8 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
                     struct pipe_inode_info *pipe, unsigned int tlen,
                     unsigned int flags)
 {
-        struct partial_page partial[PIPE_BUFFERS];
-        struct page *pages[PIPE_BUFFERS];
+        struct partial_page partial[PIPE_DEF_BUFFERS];
+        struct page *pages[PIPE_DEF_BUFFERS];
         struct splice_pipe_desc spd = {
                 .pages = pages,
                 .partial = partial,
@@ -1535,12 +1537,16 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
         };
         struct sk_buff *frag_iter;
         struct sock *sk = skb->sk;
+        int ret = 0;
+
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
 
         /*
          * __skb_splice_bits() only fails if the output has no room left,
          * so no point in going over the frag_list for the error case.
          */
-        if (__skb_splice_bits(skb, &offset, &tlen, &spd, sk))
+        if (__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk))
                 goto done;
         else if (!tlen)
                 goto done;
@@ -1551,14 +1557,12 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
         skb_walk_frags(skb, frag_iter) {
                 if (!tlen)
                         break;
-                if (__skb_splice_bits(frag_iter, &offset, &tlen, &spd, sk))
+                if (__skb_splice_bits(frag_iter, pipe, &offset, &tlen, &spd, sk))
                         break;
         }
 
 done:
         if (spd.nr_pages) {
-                int ret;
-
                 /*
                  * Drop the socket lock, otherwise we have reverse
                  * locking dependencies between sk_lock and i_mutex
@@ -1571,10 +1575,10 @@ done:
                 release_sock(sk);
                 ret = splice_to_pipe(pipe, &spd);
                 lock_sock(sk);
-                return ret;
         }
 
-        return 0;
+        splice_shrink_spd(pipe, &spd);
+        return ret;
 }
 
 /**