summaryrefslogtreecommitdiffstats
path: root/fs/nsfs.c
diff options
context:
space:
mode:
authorAl Viro <viro@zeniv.linux.org.uk>2014-11-01 10:57:28 -0400
committerAl Viro <viro@zeniv.linux.org.uk>2014-12-10 21:30:20 -0500
commite149ed2b805fefdccf7ccdfc19eca22fdd4514ac (patch)
tree8c9cd88deff8c7309ca2acb8d4cb475aaca47b14 /fs/nsfs.c
parentf77c80142e1afe6d5c16975ca5d7d1fc324b16f9 (diff)
downloadlinux-e149ed2b805fefdccf7ccdfc19eca22fdd4514ac.tar.bz2
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>
Diffstat (limited to 'fs/nsfs.c')
-rw-r--r--fs/nsfs.c161
1 files changed, 161 insertions, 0 deletions
diff --git a/fs/nsfs.c b/fs/nsfs.c
new file mode 100644
index 000000000000..af1b24fa899d
--- /dev/null
+++ b/fs/nsfs.c
@@ -0,0 +1,161 @@
+#include <linux/mount.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/proc_ns.h>
+#include <linux/magic.h>
+#include <linux/ktime.h>
+
+static struct vfsmount *nsfs_mnt;
+
+static const struct file_operations ns_file_operations = {
+ .llseek = no_llseek,
+};
+
+static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ struct inode *inode = dentry->d_inode;
+ const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+
+ return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
+ ns_ops->name, inode->i_ino);
+}
+
+static void ns_prune_dentry(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+ if (inode) {
+ struct ns_common *ns = inode->i_private;
+ atomic_long_set(&ns->stashed, 0);
+ }
+}
+
+const struct dentry_operations ns_dentry_operations =
+{
+ .d_prune = ns_prune_dentry,
+ .d_delete = always_delete_dentry,
+ .d_dname = ns_dname,
+};
+
+static void nsfs_evict(struct inode *inode)
+{
+ struct ns_common *ns = inode->i_private;
+ clear_inode(inode);
+ ns->ops->put(ns);
+}
+
+void *ns_get_path(struct path *path, struct task_struct *task,
+ const struct proc_ns_operations *ns_ops)
+{
+ struct vfsmount *mnt = mntget(nsfs_mnt);
+ struct qstr qname = { .name = "", };
+ struct dentry *dentry;
+ struct inode *inode;
+ struct ns_common *ns;
+ unsigned long d;
+
+again:
+ ns = ns_ops->get(task);
+ if (!ns) {
+ mntput(mnt);
+ return ERR_PTR(-ENOENT);
+ }
+ rcu_read_lock();
+ d = atomic_long_read(&ns->stashed);
+ if (!d)
+ goto slow;
+ dentry = (struct dentry *)d;
+ if (!lockref_get_not_dead(&dentry->d_lockref))
+ goto slow;
+ rcu_read_unlock();
+ ns_ops->put(ns);
+got_it:
+ path->mnt = mnt;
+ path->dentry = dentry;
+ return NULL;
+slow:
+ rcu_read_unlock();
+ inode = new_inode_pseudo(mnt->mnt_sb);
+ if (!inode) {
+ ns_ops->put(ns);
+ mntput(mnt);
+ return ERR_PTR(-ENOMEM);
+ }
+ inode->i_ino = ns->inum;
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode->i_flags |= S_IMMUTABLE;
+ inode->i_mode = S_IFREG | S_IRUGO;
+ inode->i_fop = &ns_file_operations;
+ inode->i_private = ns;
+
+ dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
+ if (!dentry) {
+ iput(inode);
+ mntput(mnt);
+ return ERR_PTR(-ENOMEM);
+ }
+ d_instantiate(dentry, inode);
+ dentry->d_fsdata = (void *)ns_ops;
+ d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
+ if (d) {
+ d_delete(dentry); /* make sure ->d_prune() does nothing */
+ dput(dentry);
+ cpu_relax();
+ goto again;
+ }
+ goto got_it;
+}
+
+int ns_get_name(char *buf, size_t size, struct task_struct *task,
+ const struct proc_ns_operations *ns_ops)
+{
+ struct ns_common *ns;
+ int res = -ENOENT;
+ ns = ns_ops->get(task);
+ if (ns) {
+ res = snprintf(buf, size, "%s:[%u]", ns_ops->name, ns->inum);
+ ns_ops->put(ns);
+ }
+ return res;
+}
+
+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);
+}
+
+static const struct super_operations nsfs_ops = {
+ .statfs = simple_statfs,
+ .evict_inode = nsfs_evict,
+};
+static struct dentry *nsfs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ return mount_pseudo(fs_type, "nsfs:", &nsfs_ops,
+ &ns_dentry_operations, NSFS_MAGIC);
+}
+static struct file_system_type nsfs = {
+ .name = "nsfs",
+ .mount = nsfs_mount,
+ .kill_sb = kill_anon_super,
+};
+
+void __init nsfs_init(void)
+{
+ nsfs_mnt = kern_mount(&nsfs);
+ if (IS_ERR(nsfs_mnt))
+ panic("can't set nsfs up\n");
+ nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
+}