take the targets of /proc/*/ns/* symlinks to separate fs

New pseudo-filesystem: nsfs.  Targets of /proc/*/ns/* live there now.
It's not mountable (not even registered, so it's not in /proc/filesystems,
etc.).  Files on it *are* bindable - we explicitly permit that in do_loopback().

This stuff lives in fs/nsfs.c now; proc_ns_fget() moved there as well.
get_proc_ns() is a macro now (it's simply returning ->i_private; would
have been an inline, if not for header ordering headache).
proc_ns_inode() is an ex-parrot.  The interface used in procfs is
ns_get_path(path, task, ops) and ns_get_name(buf, size, task, ops).

Dentries and inodes are never hashed; a non-counting reference to dentry
is stashed in ns_common (removed by ->d_prune()) and reused by ns_get_path()
if present.  See ns_get_path()/ns_prune_dentry/nsfs_evict() for details
of that mechanism.

As the result, proc_ns_follow_link() has stopped poking in nd->path.mnt;
it does nd_jump_link() on a consistent <vfsmount,dentry> pair it gets
from ns_get_path().

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 20 insertions, 13 deletions

diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index ce23cf4bbe69..85a5c8c16be9 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -4,6 +4,7 @@
 struct proc_ns_operations;
 
 struct ns_common {
+        atomic_long_t stashed;
         const struct proc_ns_operations *ops;
         unsigned int inum;
 };
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 2837ff41cfe3..42dfc615dbf8 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -4,9 +4,11 @@
 #ifndef _LINUX_PROC_NS_H
 #define _LINUX_PROC_NS_H
 
+#include <linux/ns_common.h>
+
 struct pid_namespace;
 struct nsproxy;
-struct ns_common;
+struct path;
 
 struct proc_ns_operations {
         const char *name;
@@ -38,35 +40,38 @@ enum {
 
 extern int pid_ns_prepare_proc(struct pid_namespace *ns);
 extern void pid_ns_release_proc(struct pid_namespace *ns);
-extern struct file *proc_ns_fget(int fd);
-extern struct ns_common *get_proc_ns(struct inode *);
 extern int proc_alloc_inum(unsigned int *pino);
 extern void proc_free_inum(unsigned int inum);
-extern bool proc_ns_inode(struct inode *inode);
 
 #else /* CONFIG_PROC_FS */
 
 static inline int pid_ns_prepare_proc(struct pid_namespace *ns) { return 0; }
 static inline void pid_ns_release_proc(struct pid_namespace *ns) {}
 
-static inline struct file *proc_ns_fget(int fd)
-{
-        return ERR_PTR(-EINVAL);
-}
-
-static inline struct ns_common *get_proc_ns(struct inode *inode) { return NULL; }
-
 static inline int proc_alloc_inum(unsigned int *inum)
 {
         *inum = 1;
         return 0;
 }
 static inline void proc_free_inum(unsigned int inum) {}
-static inline bool proc_ns_inode(struct inode *inode) { return false; }
 
 #endif /* CONFIG_PROC_FS */
 
-#define ns_alloc_inum(ns) proc_alloc_inum(&(ns)->inum)
+static inline int ns_alloc_inum(struct ns_common *ns)
+{
+        atomic_long_set(&ns->stashed, 0);
+        return proc_alloc_inum(&ns->inum);
+}
+
 #define ns_free_inum(ns) proc_free_inum((ns)->inum)
 
+extern struct file *proc_ns_fget(int fd);
+#define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private)
+extern void *ns_get_path(struct path *path, struct task_struct *task,
+                        const struct proc_ns_operations *ns_ops);
+
+extern int ns_get_name(char *buf, size_t size, struct task_struct *task,
+                        const struct proc_ns_operations *ns_ops);
+extern void nsfs_init(void);
+
 #endif /* _LINUX_PROC_NS_H */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 77c60311a6c6..7d664ea85ebd 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -72,5 +72,6 @@
 #define MTD_INODE_FS_MAGIC      0x11307854
 #define ANON_INODE_FS_MAGIC     0x09041934
 #define BTRFS_TEST_MAGIC        0x73727279
+#define NSFS_MAGIC              0x6e736673
 
 #endif /* __LINUX_MAGIC_H__ */