1 files changed, 59 insertions, 35 deletions

diff --git a/net/socket.c b/net/socket.c
index 088fb3fd45e0..937d0fcf74bc 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -156,7 +156,7 @@ static const struct file_operations socket_file_ops = {
  */
 
 static DEFINE_SPINLOCK(net_family_lock);
-static const struct net_proto_family *net_families[NPROTO] __read_mostly;
+static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly;
 
 /*
  *      Statistics counters of the socket lists
@@ -240,17 +240,19 @@ static struct kmem_cache *sock_inode_cachep __read_mostly;
 static struct inode *sock_alloc_inode(struct super_block *sb)
 {
         struct socket_alloc *ei;
+        struct socket_wq *wq;
 
         ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
         if (!ei)
                 return NULL;
-        ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL);
-        if (!ei->socket.wq) {
+        wq = kmalloc(sizeof(*wq), GFP_KERNEL);
+        if (!wq) {
                 kmem_cache_free(sock_inode_cachep, ei);
                 return NULL;
         }
-        init_waitqueue_head(&ei->socket.wq->wait);
-        ei->socket.wq->fasync_list = NULL;
+        init_waitqueue_head(&wq->wait);
+        wq->fasync_list = NULL;
+        RCU_INIT_POINTER(ei->socket.wq, wq);
 
         ei->socket.state = SS_UNCONNECTED;
         ei->socket.flags = 0;
@@ -262,6 +264,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 }
 
 
+
 static void wq_free_rcu(struct rcu_head *head)
 {
         struct socket_wq *wq = container_of(head, struct socket_wq, rcu);
@@ -272,9 +275,11 @@ static void wq_free_rcu(struct rcu_head *head)
 static void sock_destroy_inode(struct inode *inode)
 {
         struct socket_alloc *ei;
+        struct socket_wq *wq;
 
         ei = container_of(inode, struct socket_alloc, vfs_inode);
-        call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
+        wq = rcu_dereference_protected(ei->socket.wq, 1);
+        call_rcu(&wq->rcu, wq_free_rcu);
         kmem_cache_free(sock_inode_cachep, ei);
 }
 
@@ -305,20 +310,6 @@ static const struct super_operations sockfs_ops = {
         .statfs         = simple_statfs,
 };
 
-static struct dentry *sockfs_mount(struct file_system_type *fs_type,
-                         int flags, const char *dev_name, void *data)
-{
-        return mount_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC);
-}
-
-static struct vfsmount *sock_mnt __read_mostly;
-
-static struct file_system_type sock_fs_type = {
-        .name =         "sockfs",
-        .mount =        sockfs_mount,
-        .kill_sb =      kill_anon_super,
-};
-
 /*
  * sockfs_dname() is called from d_path().
  */
@@ -332,6 +323,21 @@ static const struct dentry_operations sockfs_dentry_operations = {
         .d_dname  = sockfs_dname,
 };
 
+static struct dentry *sockfs_mount(struct file_system_type *fs_type,
+                         int flags, const char *dev_name, void *data)
+{
+        return mount_pseudo(fs_type, "socket:", &sockfs_ops,
+                &sockfs_dentry_operations, SOCKFS_MAGIC);
+}
+
+static struct vfsmount *sock_mnt __read_mostly;
+
+static struct file_system_type sock_fs_type = {
+        .name =         "sockfs",
+        .mount =        sockfs_mount,
+        .kill_sb =      kill_anon_super,
+};
+
 /*
  *      Obtains the first available file descriptor and sets it up for use.
  *
@@ -360,14 +366,13 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags)
         if (unlikely(fd < 0))
                 return fd;
 
-        path.dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name);
+        path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
         if (unlikely(!path.dentry)) {
                 put_unused_fd(fd);
                 return -ENOMEM;
         }
         path.mnt = mntget(sock_mnt);
 
-        path.dentry->d_op = &sockfs_dentry_operations;
         d_instantiate(path.dentry, SOCK_INODE(sock));
         SOCK_INODE(sock)->i_fop = &socket_file_ops;
 
@@ -523,7 +528,7 @@ void sock_release(struct socket *sock)
                 module_put(owner);
         }
 
-        if (sock->wq->fasync_list)
+        if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
                 printk(KERN_ERR "sock_release: fasync list not empty!\n");
 
         percpu_sub(sockets_in_use, 1);
@@ -1107,15 +1112,16 @@ static int sock_fasync(int fd, struct file *filp, int on)
 {
         struct socket *sock = filp->private_data;
         struct sock *sk = sock->sk;
+        struct socket_wq *wq;
 
         if (sk == NULL)
                 return -EINVAL;
 
         lock_sock(sk);
+        wq = rcu_dereference_protected(sock->wq, sock_owned_by_user(sk));
+        fasync_helper(fd, filp, on, &wq->fasync_list);
 
-        fasync_helper(fd, filp, on, &sock->wq->fasync_list);
-
-        if (!sock->wq->fasync_list)
+        if (!wq->fasync_list)
                 sock_reset_flag(sk, SOCK_FASYNC);
         else
                 sock_set_flag(sk, SOCK_FASYNC);
@@ -1215,7 +1221,7 @@ int __sock_create(struct net *net, int family, int type, int protocol,
          * requested real, full-featured networking support upon configuration.
          * Otherwise module support will break!
          */
-        if (net_families[family] == NULL)
+        if (rcu_access_pointer(net_families[family]) == NULL)
                 request_module("net-pf-%d", family);
 #endif
 
@@ -2347,10 +2353,11 @@ int sock_register(const struct net_proto_family *ops)
         }
 
         spin_lock(&net_family_lock);
-        if (net_families[ops->family])
+        if (rcu_dereference_protected(net_families[ops->family],
+                                      lockdep_is_held(&net_family_lock)))
                 err = -EEXIST;
         else {
-                net_families[ops->family] = ops;
+                rcu_assign_pointer(net_families[ops->family], ops);
                 err = 0;
         }
         spin_unlock(&net_family_lock);
@@ -2378,7 +2385,7 @@ void sock_unregister(int family)
         BUG_ON(family < 0 || family >= NPROTO);
 
         spin_lock(&net_family_lock);
-        net_families[family] = NULL;
+        rcu_assign_pointer(net_families[family], NULL);
         spin_unlock(&net_family_lock);
 
         synchronize_rcu();
@@ -2389,6 +2396,8 @@ EXPORT_SYMBOL(sock_unregister);
 
 static int __init sock_init(void)
 {
+        int err;
+
         /*
          *      Initialize sock SLAB cache.
          */
@@ -2405,8 +2414,15 @@ static int __init sock_init(void)
          */
 
         init_inodecache();
-        register_filesystem(&sock_fs_type);
+
+        err = register_filesystem(&sock_fs_type);
+        if (err)
+                goto out_fs;
         sock_mnt = kern_mount(&sock_fs_type);
+        if (IS_ERR(sock_mnt)) {
+                err = PTR_ERR(sock_mnt);
+                goto out_mount;
+        }
 
         /* The real protocol initialization is performed in later initcalls.
          */
@@ -2419,7 +2435,13 @@ static int __init sock_init(void)
         skb_timestamping_init();
 #endif
 
-        return 0;
+out:
+        return err;
+
+out_mount:
+        unregister_filesystem(&sock_fs_type);
+out_fs:
+        goto out;
 }
 
 core_initcall(sock_init);       /* early initcall */
@@ -2626,7 +2648,8 @@ static int bond_ioctl(struct net *net, unsigned int cmd,
 
                 old_fs = get_fs();
                 set_fs(KERNEL_DS);
-                err = dev_ioctl(net, cmd, &kifr);
+                err = dev_ioctl(net, cmd,
+                                (struct ifreq __user __force *) &kifr);
                 set_fs(old_fs);
 
                 return err;
@@ -2735,7 +2758,7 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
 
         old_fs = get_fs();
         set_fs(KERNEL_DS);
-        err = dev_ioctl(net, cmd, (void __user *)&ifr);
+        err = dev_ioctl(net, cmd, (void  __user __force *)&ifr);
         set_fs(old_fs);
 
         if (cmd == SIOCGIFMAP && !err) {
@@ -2840,7 +2863,8 @@ static int routing_ioctl(struct net *net, struct socket *sock,
                 ret |= __get_user(rtdev, &(ur4->rt_dev));
                 if (rtdev) {
                         ret |= copy_from_user(devname, compat_ptr(rtdev), 15);
-                        r4.rt_dev = devname; devname[15] = 0;
+                        r4.rt_dev = (char __user __force *)devname;
+                        devname[15] = 0;
                 } else
                         r4.rt_dev = NULL;