Merge git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/linux-2.6-nsfd

* git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/linux-2.6-nsfd:
net: fix get_net_ns_by_fd for !CONFIG_NET_NS
ns proc: Return -ENOENT for a nonexistent /proc/self/ns/ entry.
ns: Declare sys_setns in syscalls.h
net: Allow setting the network namespace by fd
ns proc: Add support for the ipc namespace
ns proc: Add support for the uts namespace
ns proc: Add support for the network namespace.
ns: Introduce the setns syscall
ns: proc files for namespace naming policy.

fs/proc/Makefile

···
 proc-y	+= uptime.o
 proc-y	+= version.o
 proc-y	+= softirqs.o
+proc-y	+= namespaces.o
 proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
 proc-$(CONFIG_NET)		+= proc_net.o
 proc-$(CONFIG_PROC_KCORE)	+= kcore.o

fs/proc/base.c

···
 	return allowed;
 }
 
-static int proc_setattr(struct dentry *dentry, struct iattr *attr)
+int proc_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int error;
 	struct inode *inode = dentry->d_inode;
···
 	return 0;
 }
 
-
-static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
+struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
 {
 	struct inode * inode;
 	struct proc_inode *ei;
···
 	return NULL;
 }
 
-static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
 	struct task_struct *task;
···
  * made this apply to all per process world readable and executable
  * directories.
  */
-static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
+int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode;
 	struct task_struct *task;
···
 	return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
 }
 
-static const struct dentry_operations pid_dentry_operations =
+const struct dentry_operations pid_dentry_operations =
 {
 	.d_revalidate	= pid_revalidate,
 	.d_delete	= pid_delete_dentry,
 };
 
 /* Lookups */
-
-typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
-				struct task_struct *, const void *);
 
 /*
  * Fill a directory entry.
···
  * reported by readdir in sync with the inode numbers reported
  * by stat.
  */
-static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
-	char *name, int len,
+int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+	const char *name, int len,
 	instantiate_t instantiate, struct task_struct *task, const void *ptr)
 {
 	struct dentry *child, *dir = filp->f_path.dentry;
···
 	DIR("task",       S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
 	DIR("fd",         S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
 	DIR("fdinfo",     S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+	DIR("ns",	  S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
 #ifdef CONFIG_NET
 	DIR("net",        S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
 #endif
···
 static const struct pid_entry tid_base_stuff[] = {
 	DIR("fd",        S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
 	DIR("fdinfo",    S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+	DIR("ns",	 S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
 	REG("environ",   S_IRUSR, proc_environ_operations),
 	INF("auxv",      S_IRUSR, proc_pid_auxv),
 	ONE("status",    S_IRUGO, proc_pid_status),

fs/proc/inode.c

···
 {
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
+	const struct proc_ns_operations *ns_ops;
 
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
···
 		rcu_assign_pointer(PROC_I(inode)->sysctl, NULL);
 		sysctl_head_put(head);
 	}
+	/* Release any associated namespace */
+	ns_ops = PROC_I(inode)->ns_ops;
+	if (ns_ops && ns_ops->put)
+		ns_ops->put(PROC_I(inode)->ns);
 }
 
 static struct kmem_cache * proc_inode_cachep;
···
 	ei->pde = NULL;
 	ei->sysctl = NULL;
 	ei->sysctl_entry = NULL;
+	ei->ns = NULL;
+	ei->ns_ops = NULL;
 	inode = &ei->vfs_inode;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	return inode;

fs/proc/internal.h

···
  */
 int proc_readdir(struct file *, void *, filldir_t);
 struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
+
+
+
+/* Lookups */
+typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
+				struct task_struct *, const void *);
+int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+	const char *name, int len,
+	instantiate_t instantiate, struct task_struct *task, const void *ptr);
+int pid_revalidate(struct dentry *dentry, struct nameidata *nd);
+struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task);
+extern const struct dentry_operations pid_dentry_operations;
+int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
+int proc_setattr(struct dentry *dentry, struct iattr *attr);
+
+extern const struct inode_operations proc_ns_dir_inode_operations;
+extern const struct file_operations proc_ns_dir_operations;
+

fs/proc/namespaces.c

···
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/fs_struct.h>
+#include <linux/mount.h>
+#include <linux/path.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/mnt_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+};
+
+static const struct file_operations ns_file_operations = {
+	.llseek		= no_llseek,
+};
+
+static struct dentry *proc_ns_instantiate(struct inode *dir,
+	struct dentry *dentry, struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct dentry *error = ERR_PTR(-ENOENT);
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	inode->i_mode = S_IFREG|S_IRUSR;
+	inode->i_fop  = &ns_file_operations;
+	ei->ns_ops    = ns_ops;
+	ei->ns	      = ns_ops->get(task);
+	if (!ei->ns)
+		goto out_iput;
+
+	dentry->d_op = &pid_dentry_operations;
+	d_add(dentry, inode);
+	/* Close the race of the process dying before we return the dentry */
+	if (pid_revalidate(dentry, NULL))
+		error = NULL;
+out:
+	return error;
+out_iput:
+	iput(inode);
+	goto out;
+}
+
+static int proc_ns_fill_cache(struct file *filp, void *dirent,
+	filldir_t filldir, struct task_struct *task,
+	const struct proc_ns_operations *ops)
+{
+	return proc_fill_cache(filp, dirent, filldir,
+				ops->name, strlen(ops->name),
+				proc_ns_instantiate, task, ops);
+}
+
+static int proc_ns_dir_readdir(struct file *filp, void *dirent,
+				filldir_t filldir)
+{
+	int i;
+	struct dentry *dentry = filp->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+	struct task_struct *task = get_proc_task(inode);
+	const struct proc_ns_operations **entry, **last;
+	ino_t ino;
+	int ret;
+
+	ret = -ENOENT;
+	if (!task)
+		goto out_no_task;
+
+	ret = -EPERM;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out;
+
+	ret = 0;
+	i = filp->f_pos;
+	switch (i) {
+	case 0:
+		ino = inode->i_ino;
+		if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
+			goto out;
+		i++;
+		filp->f_pos++;
+		/* fall through */
+	case 1:
+		ino = parent_ino(dentry);
+		if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
+			goto out;
+		i++;
+		filp->f_pos++;
+		/* fall through */
+	default:
+		i -= 2;
+		if (i >= ARRAY_SIZE(ns_entries)) {
+			ret = 1;
+			goto out;
+		}
+		entry = ns_entries + i;
+		last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+		while (entry <= last) {
+			if (proc_ns_fill_cache(filp, dirent, filldir,
+						task, *entry) < 0)
+				goto out;
+			filp->f_pos++;
+			entry++;
+		}
+	}
+
+	ret = 1;
+out:
+	put_task_struct(task);
+out_no_task:
+	return ret;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_ns_dir_readdir,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, struct nameidata *nd)
+{
+	struct dentry *error;
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations **entry, **last;
+	unsigned int len = dentry->d_name.len;
+
+	error = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+
+	error = ERR_PTR(-EPERM);
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out;
+
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	for (entry = ns_entries; entry <= last; entry++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	error = ERR_PTR(-ENOENT);
+	if (entry > last)
+		goto out;
+
+	error = proc_ns_instantiate(dir, dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return error;
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_setattr,
+};
+
+struct file *proc_ns_fget(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
+
+	if (file->f_op != &ns_file_operations)
+		goto out_invalid;
+
+	return file;
+
+out_invalid:
+	fput(file);
+	return ERR_PTR(-EINVAL);
+}
+

include/linux/if_link.h

···
 	IFLA_PORT_SELF,
 	IFLA_AF_SPEC,
 	IFLA_GROUP,		/* Group the device belongs to */
+	IFLA_NET_NS_FD,
 	__IFLA_MAX
 };
 

include/linux/proc_fs.h

···
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm);
 
+extern struct file *proc_ns_fget(int fd);
+
 #else
 
 #define proc_net_fops_create(net, name, mode, fops)  ({ (void)(mode), NULL; })
···
 	       			   struct mm_struct *newmm)
 {}
 
+static inline struct file *proc_ns_fget(int fd)
+{
+	return ERR_PTR(-EINVAL);
+}
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)
···
 #else
 extern void kclist_add(struct kcore_list *, void *, size_t, int type);
 #endif
+
+struct nsproxy;
+struct proc_ns_operations {
+	const char *name;
+	int type;
+	void *(*get)(struct task_struct *task);
+	void (*put)(void *ns);
+	int (*install)(struct nsproxy *nsproxy, void *ns);
+};
+extern const struct proc_ns_operations netns_operations;
+extern const struct proc_ns_operations utsns_operations;
+extern const struct proc_ns_operations ipcns_operations;
 
 union proc_op {
 	int (*proc_get_link)(struct inode *, struct path *);
···
 	struct proc_dir_entry *pde;
 	struct ctl_table_header *sysctl;
 	struct ctl_table *sysctl_entry;
+	void *ns;
+	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
 };
 

include/linux/syscalls.h

···
 asmlinkage long sys_open_by_handle_at(int mountdirfd,
 				      struct file_handle __user *handle,
 				      int flags);
+asmlinkage long sys_setns(int fd, int nstype);
 #endif

include/net/net_namespace.h

···
 extern struct list_head net_namespace_list;
 
 extern struct net *get_net_ns_by_pid(pid_t pid);
+extern struct net *get_net_ns_by_fd(int pid);
 
 #ifdef CONFIG_NET_NS
 extern void __put_net(struct net *net);

ipc/namespace.c

···
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
 
 #include "util.h"
 
···
 		free_ipc_ns(ns);
 	}
 }
+
+static void *ipcns_get(struct task_struct *task)
+{
+	struct ipc_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	rcu_read_lock();
+	nsproxy = task_nsproxy(task);
+	if (nsproxy)
+		ns = get_ipc_ns(nsproxy->ipc_ns);
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void ipcns_put(void *ns)
+{
+	return put_ipc_ns(ns);
+}
+
+static int ipcns_install(struct nsproxy *nsproxy, void *ns)
+{
+	/* Ditch state from the old ipc namespace */
+	exit_sem(current);
+	put_ipc_ns(nsproxy->ipc_ns);
+	nsproxy->ipc_ns = get_ipc_ns(ns);
+	return 0;
+}
+
+const struct proc_ns_operations ipcns_operations = {
+	.name		= "ipc",
+	.type		= CLONE_NEWIPC,
+	.get		= ipcns_get,
+	.put		= ipcns_put,
+	.install	= ipcns_install,
+};

kernel/nsproxy.c

···
 #include <linux/pid_namespace.h>
 #include <net/net_namespace.h>
 #include <linux/ipc_namespace.h>
+#include <linux/proc_fs.h>
+#include <linux/file.h>
+#include <linux/syscalls.h>
 
 static struct kmem_cache *nsproxy_cachep;
 
···
 void exit_task_namespaces(struct task_struct *p)
 {
 	switch_task_namespaces(p, NULL);
+}
+
+SYSCALL_DEFINE2(setns, int, fd, int, nstype)
+{
+	const struct proc_ns_operations *ops;
+	struct task_struct *tsk = current;
+	struct nsproxy *new_nsproxy;
+	struct proc_inode *ei;
+	struct file *file;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	file = proc_ns_fget(fd);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	err = -EINVAL;
+	ei = PROC_I(file->f_dentry->d_inode);
+	ops = ei->ns_ops;
+	if (nstype && (ops->type != nstype))
+		goto out;
+
+	new_nsproxy = create_new_namespaces(0, tsk, tsk->fs);
+	if (IS_ERR(new_nsproxy)) {
+		err = PTR_ERR(new_nsproxy);
+		goto out;
+	}
+
+	err = ops->install(new_nsproxy, ei->ns);
+	if (err) {
+		free_nsproxy(new_nsproxy);
+		goto out;
+	}
+	switch_task_namespaces(tsk, new_nsproxy);
+out:
+	fput(file);
+	return err;
 }
 
 static int __init nsproxy_cache_init(void)

kernel/utsname.c

···
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
 
 static struct uts_namespace *create_uts_ns(void)
 {
···
 	put_user_ns(ns->user_ns);
 	kfree(ns);
 }
+
+static void *utsns_get(struct task_struct *task)
+{
+	struct uts_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	rcu_read_lock();
+	nsproxy = task_nsproxy(task);
+	if (nsproxy) {
+		ns = nsproxy->uts_ns;
+		get_uts_ns(ns);
+	}
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static void utsns_put(void *ns)
+{
+	put_uts_ns(ns);
+}
+
+static int utsns_install(struct nsproxy *nsproxy, void *ns)
+{
+	get_uts_ns(ns);
+	put_uts_ns(nsproxy->uts_ns);
+	nsproxy->uts_ns = ns;
+	return 0;
+}
+
+const struct proc_ns_operations utsns_operations = {
+	.name		= "uts",
+	.type		= CLONE_NEWUTS,
+	.get		= utsns_get,
+	.put		= utsns_put,
+	.install	= utsns_install,
+};
+

net/core/net_namespace.c

···
 #include <linux/idr.h>
 #include <linux/rculist.h>
 #include <linux/nsproxy.h>
+#include <linux/proc_fs.h>
+#include <linux/file.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
···
 }
 EXPORT_SYMBOL_GPL(__put_net);
 
+struct net *get_net_ns_by_fd(int fd)
+{
+	struct proc_inode *ei;
+	struct file *file;
+	struct net *net;
+
+	net = ERR_PTR(-EINVAL);
+	file = proc_ns_fget(fd);
+	if (!file)
+		goto out;
+
+	ei = PROC_I(file->f_dentry->d_inode);
+	if (ei->ns_ops != &netns_operations)
+		goto out;
+
+	net = get_net(ei->ns);
+out:
+	if (file)
+		fput(file);
+	return net;
+}
+
 #else
 struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 {
 	if (flags & CLONE_NEWNET)
 		return ERR_PTR(-EINVAL);
 	return old_net;
+}
+
+struct net *get_net_ns_by_fd(int fd)
+{
+	return ERR_PTR(-EINVAL);
 }
 #endif
 
···
 	mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(unregister_pernet_device);
+
+#ifdef CONFIG_NET_NS
+static void *netns_get(struct task_struct *task)
+{
+	struct net *net = NULL;
+	struct nsproxy *nsproxy;
+
+	rcu_read_lock();
+	nsproxy = task_nsproxy(task);
+	if (nsproxy)
+		net = get_net(nsproxy->net_ns);
+	rcu_read_unlock();
+
+	return net;
+}
+
+static void netns_put(void *ns)
+{
+	put_net(ns);
+}
+
+static int netns_install(struct nsproxy *nsproxy, void *ns)
+{
+	put_net(nsproxy->net_ns);
+	nsproxy->net_ns = get_net(ns);
+	return 0;
+}
+
+const struct proc_ns_operations netns_operations = {
+	.name		= "net",
+	.type		= CLONE_NEWNET,
+	.get		= netns_get,
+	.put		= netns_put,
+	.install	= netns_install,
+};
+#endif

net/core/rtnetlink.c

···
 	[IFLA_LINKMODE]		= { .type = NLA_U8 },
 	[IFLA_LINKINFO]		= { .type = NLA_NESTED },
 	[IFLA_NET_NS_PID]	= { .type = NLA_U32 },
+	[IFLA_NET_NS_FD]	= { .type = NLA_U32 },
 	[IFLA_IFALIAS]	        = { .type = NLA_STRING, .len = IFALIASZ-1 },
 	[IFLA_VFINFO_LIST]	= {. type = NLA_NESTED },
 	[IFLA_VF_PORTS]		= { .type = NLA_NESTED },
···
 	 */
 	if (tb[IFLA_NET_NS_PID])
 		net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID]));
+	else if (tb[IFLA_NET_NS_FD])
+		net = get_net_ns_by_fd(nla_get_u32(tb[IFLA_NET_NS_FD]));
 	else
 		net = get_net(src_net);
 	return net;
···
 	int send_addr_notify = 0;
 	int err;
 
-	if (tb[IFLA_NET_NS_PID]) {
+	if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) {
 		struct net *net = rtnl_link_get_net(dev_net(dev), tb);
 		if (IS_ERR(net)) {
 			err = PTR_ERR(net);