Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  [patch 7/7] vfs: mountinfo: show dominating group id
  [patch 6/7] vfs: mountinfo: add /proc/<pid>/mountinfo
  [patch 5/7] vfs: mountinfo: allow using process root
  [patch 4/7] vfs: mountinfo: add mount peer group ID
  [patch 3/7] vfs: mountinfo: add mount ID
  [patch 2/7] vfs: mountinfo: add seq_file_root()
  [patch 1/7] vfs: mountinfo: add dentry_path()
  [PATCH] remove unused label in xattr.c (noise from ro-bind)

Documentation/filesystems/proc.txt

@@ -43,6 +43,7 @@ Table of Contents
   2.13	/proc/<pid>/oom_score - Display current oom-killer score
   2.14	/proc/<pid>/io - Display the IO accounting fields
   2.15	/proc/<pid>/coredump_filter - Core dump filtering settings
+  2.16	/proc/<pid>/mountinfo - Information about mounts
 
 ------------------------------------------------------------------------------
 Preface
@@ -2348,4 +2349,41 @@ For example:
   $ echo 0x7 > /proc/self/coredump_filter
   $ ./some_program
 
+2.16	/proc/<pid>/mountinfo - Information about mounts
+--------------------------------------------------------
+
+This file contains lines of the form:
+
+36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
+(1)(2)(3)   (4)   (5)      (6)      (7)   (8) (9)   (10)         (11)
+
+(1) mount ID:  unique identifier of the mount (may be reused after umount)
+(2) parent ID:  ID of parent (or of self for the top of the mount tree)
+(3) major:minor:  value of st_dev for files on filesystem
+(4) root:  root of the mount within the filesystem
+(5) mount point:  mount point relative to the process's root
+(6) mount options:  per mount options
+(7) optional fields:  zero or more fields of the form "tag[:value]"
+(8) separator:  marks the end of the optional fields
+(9) filesystem type:  name of filesystem of the form "type[.subtype]"
+(10) mount source:  filesystem specific information or "none"
+(11) super options:  per super block options
+
+Parsers should ignore all unrecognised optional fields.  Currently the
+possible optional fields are:
+
+shared:X  mount is shared in peer group X
+master:X  mount is slave to peer group X
+propagate_from:X  mount is slave and receives propagation from peer group X (*)
+unbindable  mount is unbindable
+
+(*) X is the closest dominant peer group under the process's root.  If
+X is the immediate master of the mount, or if there's no dominant peer
+group under the same root, then only the "master:X" field is present
+and not the "propagate_from:X" field.
+
+For more information on mount propagation see:
+
+  Documentation/filesystems/sharedsubtree.txt
+
 ------------------------------------------------------------------------------

fs/dcache.c

@@ -1746,12 +1746,21 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 	goto shouldnt_be_hashed;
 }
 
+static int prepend(char **buffer, int *buflen, const char *str,
+			  int namelen)
+{
+	*buflen -= namelen;
+	if (*buflen < 0)
+		return -ENAMETOOLONG;
+	*buffer -= namelen;
+	memcpy(*buffer, str, namelen);
+	return 0;
+}
+
 /**
  * d_path - return the path of a dentry
- * @dentry: dentry to report
- * @vfsmnt: vfsmnt to which the dentry belongs
- * @root: root dentry
- * @rootmnt: vfsmnt to which the root dentry belongs
+ * @path: the dentry/vfsmount to report
+ * @root: root vfsmnt/dentry (may be modified by this function)
  * @buffer: buffer to return value in
  * @buflen: buffer length
  *
@@ -1761,23 +1770,22 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
  * Returns the buffer or an error code if the path was too long.
  *
  * "buflen" should be positive. Caller holds the dcache_lock.
+ *
+ * If path is not reachable from the supplied root, then the value of
+ * root is changed (without modifying refcounts).
  */
-static char *__d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
-		       struct path *root, char *buffer, int buflen)
+char *__d_path(const struct path *path, struct path *root,
+	       char *buffer, int buflen)
 {
+	struct dentry *dentry = path->dentry;
+	struct vfsmount *vfsmnt = path->mnt;
 	char * end = buffer+buflen;
 	char * retval;
-	int namelen;
-
-	*--end = '\0';
-	buflen--;
-	if (!IS_ROOT(dentry) && d_unhashed(dentry)) {
-		buflen -= 10;
-		end -= 10;
-		if (buflen < 0)
+
+	prepend(&end, &buflen, "\0", 1);
+	if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
+		(prepend(&end, &buflen, " (deleted)", 10) != 0))
 			goto Elong;
-		memcpy(end, " (deleted)", 10);
-	}
 
 	if (buflen < 1)
 		goto Elong;
@@ -1804,13 +1812,10 @@ static char *__d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
 		}
 		parent = dentry->d_parent;
 		prefetch(parent);
-		namelen = dentry->d_name.len;
-		buflen -= namelen + 1;
-		if (buflen < 0)
+		if ((prepend(&end, &buflen, dentry->d_name.name,
+				dentry->d_name.len) != 0) ||
+		    (prepend(&end, &buflen, "/", 1) != 0))
 			goto Elong;
-		end -= namelen;
-		memcpy(end, dentry->d_name.name, namelen);
-		*--end = '/';
 		retval = end;
 		dentry = parent;
 	}
@@ -1818,12 +1823,12 @@ static char *__d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
 	return retval;
 
 global_root:
-	namelen = dentry->d_name.len;
-	buflen -= namelen;
-	if (buflen < 0)
+	retval += 1;	/* hit the slash */
+	if (prepend(&retval, &buflen, dentry->d_name.name,
+		    dentry->d_name.len) != 0)
 		goto Elong;
-	retval -= namelen-1;	/* hit the slash */
-	memcpy(retval, dentry->d_name.name, namelen);
+	root->mnt = vfsmnt;
+	root->dentry = dentry;
 	return retval;
 Elong:
 	return ERR_PTR(-ENAMETOOLONG);
@@ -1846,6 +1851,7 @@ char *d_path(struct path *path, char *buf, int buflen)
 {
 	char *res;
 	struct path root;
+	struct path tmp;
 
 	/*
 	 * We have various synthetic filesystems that never get mounted.  On
@@ -1859,10 +1865,11 @@ char *d_path(struct path *path, char *buf, int buflen)
 
 	read_lock(&current->fs->lock);
 	root = current->fs->root;
-	path_get(&current->fs->root);
+	path_get(&root);
 	read_unlock(&current->fs->lock);
 	spin_lock(&dcache_lock);
-	res = __d_path(path->dentry, path->mnt, &root, buf, buflen);
+	tmp = root;
+	res = __d_path(path, &tmp, buf, buflen);
 	spin_unlock(&dcache_lock);
 	path_put(&root);
 	return res;
@@ -1889,6 +1896,48 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
 	return memcpy(buffer, temp, sz);
 }
 
+/*
+ * Write full pathname from the root of the filesystem into the buffer.
+ */
+char *dentry_path(struct dentry *dentry, char *buf, int buflen)
+{
+	char *end = buf + buflen;
+	char *retval;
+
+	spin_lock(&dcache_lock);
+	prepend(&end, &buflen, "\0", 1);
+	if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
+		(prepend(&end, &buflen, "//deleted", 9) != 0))
+			goto Elong;
+	if (buflen < 1)
+		goto Elong;
+	/* Get '/' right */
+	retval = end-1;
+	*retval = '/';
+
+	for (;;) {
+		struct dentry *parent;
+		if (IS_ROOT(dentry))
+			break;
+
+		parent = dentry->d_parent;
+		prefetch(parent);
+
+		if ((prepend(&end, &buflen, dentry->d_name.name,
+				dentry->d_name.len) != 0) ||
+		    (prepend(&end, &buflen, "/", 1) != 0))
+			goto Elong;
+
+		retval = end;
+		dentry = parent;
+	}
+	spin_unlock(&dcache_lock);
+	return retval;
+Elong:
+	spin_unlock(&dcache_lock);
+	return ERR_PTR(-ENAMETOOLONG);
+}
+
 /*
  * NOTE! The user-level library version returns a
  * character pointer. The kernel system call just
@@ -1918,9 +1967,9 @@ asmlinkage long sys_getcwd(char __user *buf, unsigned long size)
 
 	read_lock(&current->fs->lock);
 	pwd = current->fs->pwd;
-	path_get(&current->fs->pwd);
+	path_get(&pwd);
 	root = current->fs->root;
-	path_get(&current->fs->root);
+	path_get(&root);
 	read_unlock(&current->fs->lock);
 
 	error = -ENOENT;
@@ -1928,9 +1977,10 @@ asmlinkage long sys_getcwd(char __user *buf, unsigned long size)
 	spin_lock(&dcache_lock);
 	if (pwd.dentry->d_parent == pwd.dentry || !d_unhashed(pwd.dentry)) {
 		unsigned long len;
+		struct path tmp = root;
 		char * cwd;
 
-		cwd = __d_path(pwd.dentry, pwd.mnt, &root, page, PAGE_SIZE);
+		cwd = __d_path(&pwd, &tmp, page, PAGE_SIZE);
 		spin_unlock(&dcache_lock);
 
 		error = PTR_ERR(cwd);

fs/namespace.c

@@ -27,6 +27,7 @@
 #include <linux/mount.h>
 #include <linux/ramfs.h>
 #include <linux/log2.h>
+#include <linux/idr.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include "pnode.h"
@@ -39,6 +40,8 @@
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
 
 static int event;
+static DEFINE_IDA(mnt_id_ida);
+static DEFINE_IDA(mnt_group_ida);
 
 static struct list_head *mount_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
@@ -58,10 +61,63 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
 
 #define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16)
 
+/* allocation is serialized by namespace_sem */
+static int mnt_alloc_id(struct vfsmount *mnt)
+{
+	int res;
+
+retry:
+	ida_pre_get(&mnt_id_ida, GFP_KERNEL);
+	spin_lock(&vfsmount_lock);
+	res = ida_get_new(&mnt_id_ida, &mnt->mnt_id);
+	spin_unlock(&vfsmount_lock);
+	if (res == -EAGAIN)
+		goto retry;
+
+	return res;
+}
+
+static void mnt_free_id(struct vfsmount *mnt)
+{
+	spin_lock(&vfsmount_lock);
+	ida_remove(&mnt_id_ida, mnt->mnt_id);
+	spin_unlock(&vfsmount_lock);
+}
+
+/*
+ * Allocate a new peer group ID
+ *
+ * mnt_group_ida is protected by namespace_sem
+ */
+static int mnt_alloc_group_id(struct vfsmount *mnt)
+{
+	if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	return ida_get_new_above(&mnt_group_ida, 1, &mnt->mnt_group_id);
+}
+
+/*
+ * Release a peer group ID
+ */
+void mnt_release_group_id(struct vfsmount *mnt)
+{
+	ida_remove(&mnt_group_ida, mnt->mnt_group_id);
+	mnt->mnt_group_id = 0;
+}
+
 struct vfsmount *alloc_vfsmnt(const char *name)
 {
 	struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
 	if (mnt) {
+		int err;
+
+		err = mnt_alloc_id(mnt);
+		if (err) {
+			kmem_cache_free(mnt_cache, mnt);
+			return NULL;
+		}
+
 		atomic_set(&mnt->mnt_count, 1);
 		INIT_LIST_HEAD(&mnt->mnt_hash);
 		INIT_LIST_HEAD(&mnt->mnt_child);
@@ -353,6 +409,7 @@ EXPORT_SYMBOL(simple_set_mnt);
 void free_vfsmnt(struct vfsmount *mnt)
 {
 	kfree(mnt->mnt_devname);
+	mnt_free_id(mnt);
 	kmem_cache_free(mnt_cache, mnt);
 }
 
@@ -499,6 +556,17 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 	struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname);
 
 	if (mnt) {
+		if (flag & (CL_SLAVE | CL_PRIVATE))
+			mnt->mnt_group_id = 0; /* not a peer of original */
+		else
+			mnt->mnt_group_id = old->mnt_group_id;
+
+		if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
+			int err = mnt_alloc_group_id(mnt);
+			if (err)
+				goto out_free;
+		}
+
 		mnt->mnt_flags = old->mnt_flags;
 		atomic_inc(&sb->s_active);
 		mnt->mnt_sb = sb;
@@ -528,6 +596,10 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 		}
 	}
 	return mnt;
+
+ out_free:
+	free_vfsmnt(mnt);
+	return NULL;
 }
 
 static inline void __mntput(struct vfsmount *mnt)
@@ -652,20 +724,21 @@ void save_mount_options(struct super_block *sb, char *options)
 }
 EXPORT_SYMBOL(save_mount_options);
 
+#ifdef CONFIG_PROC_FS
 /* iterator */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
-	struct mnt_namespace *n = m->private;
+	struct proc_mounts *p = m->private;
 
 	down_read(&namespace_sem);
-	return seq_list_start(&n->list, *pos);
+	return seq_list_start(&p->ns->list, *pos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct mnt_namespace *n = m->private;
+	struct proc_mounts *p = m->private;
 
-	return seq_list_next(v, &n->list, pos);
+	return seq_list_next(v, &p->ns->list, pos);
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -673,20 +746,30 @@ static void m_stop(struct seq_file *m, void *v)
 	up_read(&namespace_sem);
 }
 
-static int show_vfsmnt(struct seq_file *m, void *v)
+struct proc_fs_info {
+	int flag;
+	const char *str;
+};
+
+static void show_sb_opts(struct seq_file *m, struct super_block *sb)
 {
-	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
-	int err = 0;
-	static struct proc_fs_info {
-		int flag;
-		char *str;
-	} fs_info[] = {
+	static const struct proc_fs_info fs_info[] = {
 		{ MS_SYNCHRONOUS, ",sync" },
 		{ MS_DIRSYNC, ",dirsync" },
 		{ MS_MANDLOCK, ",mand" },
 		{ 0, NULL }
 	};
-	static struct proc_fs_info mnt_info[] = {
+	const struct proc_fs_info *fs_infop;
+
+	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
+		if (sb->s_flags & fs_infop->flag)
+			seq_puts(m, fs_infop->str);
+	}
+}
+
+static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
+{
+	static const struct proc_fs_info mnt_info[] = {
 		{ MNT_NOSUID, ",nosuid" },
 		{ MNT_NODEV, ",nodev" },
 		{ MNT_NOEXEC, ",noexec" },
@@ -695,40 +778,108 @@ static int show_vfsmnt(struct seq_file *m, void *v)
 		{ MNT_RELATIME, ",relatime" },
 		{ 0, NULL }
 	};
-	struct proc_fs_info *fs_infop;
+	const struct proc_fs_info *fs_infop;
+
+	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
+		if (mnt->mnt_flags & fs_infop->flag)
+			seq_puts(m, fs_infop->str);
+	}
+}
+
+static void show_type(struct seq_file *m, struct super_block *sb)
+{
+	mangle(m, sb->s_type->name);
+	if (sb->s_subtype && sb->s_subtype[0]) {
+		seq_putc(m, '.');
+		mangle(m, sb->s_subtype);
+	}
+}
+
+static int show_vfsmnt(struct seq_file *m, void *v)
+{
+	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
+	int err = 0;
 	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
 
 	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
 	seq_putc(m, ' ');
 	seq_path(m, &mnt_path, " \t\n\\");
 	seq_putc(m, ' ');
-	mangle(m, mnt->mnt_sb->s_type->name);
-	if (mnt->mnt_sb->s_subtype && mnt->mnt_sb->s_subtype[0]) {
-		seq_putc(m, '.');
-		mangle(m, mnt->mnt_sb->s_subtype);
-	}
+	show_type(m, mnt->mnt_sb);
 	seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
-	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
-		if (mnt->mnt_sb->s_flags & fs_infop->flag)
-			seq_puts(m, fs_infop->str);
-	}
-	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
-		if (mnt->mnt_flags & fs_infop->flag)
-			seq_puts(m, fs_infop->str);
-	}
+	show_sb_opts(m, mnt->mnt_sb);
+	show_mnt_opts(m, mnt);
 	if (mnt->mnt_sb->s_op->show_options)
 		err = mnt->mnt_sb->s_op->show_options(m, mnt);
 	seq_puts(m, " 0 0\n");
 	return err;
 }
 
-struct seq_operations mounts_op = {
+const struct seq_operations mounts_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
 	.show	= show_vfsmnt
 };
 
+static int show_mountinfo(struct seq_file *m, void *v)
+{
+	struct proc_mounts *p = m->private;
+	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
+	struct super_block *sb = mnt->mnt_sb;
+	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+	struct path root = p->root;
+	int err = 0;
+
+	seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id,
+		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
+	seq_dentry(m, mnt->mnt_root, " \t\n\\");
+	seq_putc(m, ' ');
+	seq_path_root(m, &mnt_path, &root, " \t\n\\");
+	if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
+		/*
+		 * Mountpoint is outside root, discard that one.  Ugly,
+		 * but less so than trying to do that in iterator in a
+		 * race-free way (due to renames).
+		 */
+		return SEQ_SKIP;
+	}
+	seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
+	show_mnt_opts(m, mnt);
+
+	/* Tagged fields ("foo:X" or "bar") */
+	if (IS_MNT_SHARED(mnt))
+		seq_printf(m, " shared:%i", mnt->mnt_group_id);
+	if (IS_MNT_SLAVE(mnt)) {
+		int master = mnt->mnt_master->mnt_group_id;
+		int dom = get_dominating_id(mnt, &p->root);
+		seq_printf(m, " master:%i", master);
+		if (dom && dom != master)
+			seq_printf(m, " propagate_from:%i", dom);
+	}
+	if (IS_MNT_UNBINDABLE(mnt))
+		seq_puts(m, " unbindable");
+
+	/* Filesystem specific data */
+	seq_puts(m, " - ");
+	show_type(m, sb);
+	seq_putc(m, ' ');
+	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+	seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
+	show_sb_opts(m, sb);
+	if (sb->s_op->show_options)
+		err = sb->s_op->show_options(m, mnt);
+	seq_putc(m, '\n');
+	return err;
+}
+
+const struct seq_operations mountinfo_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_mountinfo,
+};
+
 static int show_vfsstat(struct seq_file *m, void *v)
 {
 	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
@@ -749,7 +900,7 @@ static int show_vfsstat(struct seq_file *m, void *v)
 
 	/* file system type */
 	seq_puts(m, "with fstype ");
-	mangle(m, mnt->mnt_sb->s_type->name);
+	show_type(m, mnt->mnt_sb);
 
 	/* optional statistics */
 	if (mnt->mnt_sb->s_op->show_stats) {
@@ -761,12 +912,13 @@ static int show_vfsstat(struct seq_file *m, void *v)
 	return err;
 }
 
-struct seq_operations mountstats_op = {
+const struct seq_operations mountstats_op = {
 	.start	= m_start,
 	.next	= m_next,
 	.stop	= m_stop,
 	.show	= show_vfsstat,
 };
+#endif  /* CONFIG_PROC_FS */
 
 /**
  * may_umount_tree - check if a mount tree is busy
@@ -1108,6 +1260,33 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	release_mounts(&umount_list);
 }
 
+static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end)
+{
+	struct vfsmount *p;
+
+	for (p = mnt; p != end; p = next_mnt(p, mnt)) {
+		if (p->mnt_group_id && !IS_MNT_SHARED(p))
+			mnt_release_group_id(p);
+	}
+}
+
+static int invent_group_ids(struct vfsmount *mnt, bool recurse)
+{
+	struct vfsmount *p;
+
+	for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
+		if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
+			int err = mnt_alloc_group_id(p);
+			if (err) {
+				cleanup_group_ids(mnt, p);
+				return err;
+			}
+		}
+	}
+
+	return 0;
+}
+
 /*
  *  @source_mnt : mount tree to be attached
  *  @nd         : place the mount tree @source_mnt is attached
@@ -1178,9 +1357,16 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	struct vfsmount *dest_mnt = path->mnt;
 	struct dentry *dest_dentry = path->dentry;
 	struct vfsmount *child, *p;
+	int err;
 
-	if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list))
-		return -EINVAL;
+	if (IS_MNT_SHARED(dest_mnt)) {
+		err = invent_group_ids(source_mnt, true);
+		if (err)
+			goto out;
+	}
+	err = propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list);
+	if (err)
+		goto out_cleanup_ids;
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
@@ -1203,6 +1389,12 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	}
 	spin_unlock(&vfsmount_lock);
 	return 0;
+
+ out_cleanup_ids:
+	if (IS_MNT_SHARED(dest_mnt))
+		cleanup_group_ids(source_mnt, NULL);
+ out:
+	return err;
 }
 
 static int graft_tree(struct vfsmount *mnt, struct path *path)
@@ -1243,6 +1435,7 @@ static noinline int do_change_type(struct nameidata *nd, int flag)
 	struct vfsmount *m, *mnt = nd->path.mnt;
 	int recurse = flag & MS_REC;
 	int type = flag & ~MS_REC;
+	int err = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1251,12 +1444,20 @@ static noinline int do_change_type(struct nameidata *nd, int flag)
 		return -EINVAL;
 
 	down_write(&namespace_sem);
+	if (type == MS_SHARED) {
+		err = invent_group_ids(mnt, recurse);
+		if (err)
+			goto out_unlock;
+	}
+
 	spin_lock(&vfsmount_lock);
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
 	spin_unlock(&vfsmount_lock);
+
+ out_unlock:
 	up_write(&namespace_sem);
-	return 0;
+	return err;
 }
 
 /*

fs/pnode.c

@@ -28,6 +28,57 @@ static inline struct vfsmount *next_slave(struct vfsmount *p)
 	return list_entry(p->mnt_slave.next, struct vfsmount, mnt_slave);
 }
 
+/*
+ * Return true if path is reachable from root
+ *
+ * namespace_sem is held, and mnt is attached
+ */
+static bool is_path_reachable(struct vfsmount *mnt, struct dentry *dentry,
+			 const struct path *root)
+{
+	while (mnt != root->mnt && mnt->mnt_parent != mnt) {
+		dentry = mnt->mnt_mountpoint;
+		mnt = mnt->mnt_parent;
+	}
+	return mnt == root->mnt && is_subdir(dentry, root->dentry);
+}
+
+static struct vfsmount *get_peer_under_root(struct vfsmount *mnt,
+					    struct mnt_namespace *ns,
+					    const struct path *root)
+{
+	struct vfsmount *m = mnt;
+
+	do {
+		/* Check the namespace first for optimization */
+		if (m->mnt_ns == ns && is_path_reachable(m, m->mnt_root, root))
+			return m;
+
+		m = next_peer(m);
+	} while (m != mnt);
+
+	return NULL;
+}
+
+/*
+ * Get ID of closest dominating peer group having a representative
+ * under the given root.
+ *
+ * Caller must hold namespace_sem
+ */
+int get_dominating_id(struct vfsmount *mnt, const struct path *root)
+{
+	struct vfsmount *m;
+
+	for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) {
+		struct vfsmount *d = get_peer_under_root(m, mnt->mnt_ns, root);
+		if (d)
+			return d->mnt_group_id;
+	}
+
+	return 0;
+}
+
 static int do_make_slave(struct vfsmount *mnt)
 {
 	struct vfsmount *peer_mnt = mnt, *master = mnt->mnt_master;
@@ -46,7 +97,11 @@ static int do_make_slave(struct vfsmount *mnt)
 		if (peer_mnt == mnt)
 			peer_mnt = NULL;
 	}
+	if (IS_MNT_SHARED(mnt) && list_empty(&mnt->mnt_share))
+		mnt_release_group_id(mnt);
+
 	list_del_init(&mnt->mnt_share);
+	mnt->mnt_group_id = 0;
 
 	if (peer_mnt)
 		master = peer_mnt;
@@ -68,7 +123,6 @@ static int do_make_slave(struct vfsmount *mnt)
 	}
 	mnt->mnt_master = master;
 	CLEAR_MNT_SHARED(mnt);
-	INIT_LIST_HEAD(&mnt->mnt_slave_list);
 	return 0;
 }
 

fs/pnode.h

@@ -36,4 +36,5 @@ int propagate_mnt(struct vfsmount *, struct dentry *, struct vfsmount *,
 int propagate_umount(struct list_head *);
 int propagate_mount_busy(struct vfsmount *, int);
 void mnt_release_group_id(struct vfsmount *);
+int get_dominating_id(struct vfsmount *mnt, const struct path *root);
 #endif /* _LINUX_PNODE_H */

fs/proc/base.c

@@ -502,17 +502,14 @@ static const struct inode_operations proc_def_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-extern const struct seq_operations mounts_op;
-struct proc_mounts {
-	struct seq_file m;
-	int event;
-};
-
-static int mounts_open(struct inode *inode, struct file *file)
+static int mounts_open_common(struct inode *inode, struct file *file,
+			      const struct seq_operations *op)
 {
 	struct task_struct *task = get_proc_task(inode);
 	struct nsproxy *nsp;
 	struct mnt_namespace *ns = NULL;
+	struct fs_struct *fs = NULL;
+	struct path root;
 	struct proc_mounts *p;
 	int ret = -EINVAL;
 
@@ -525,40 +522,61 @@ static int mounts_open(struct inode *inode, struct file *file)
 				get_mnt_ns(ns);
 		}
 		rcu_read_unlock();
-
+		if (ns)
+			fs = get_fs_struct(task);
 		put_task_struct(task);
 	}
 
-	if (ns) {
-		ret = -ENOMEM;
-		p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
-		if (p) {
-			file->private_data = &p->m;
-			ret = seq_open(file, &mounts_op);
-			if (!ret) {
-				p->m.private = ns;
-				p->event = ns->event;
-				return 0;
-			}
-			kfree(p);
-		}
-		put_mnt_ns(ns);
-	}
+	if (!ns)
+		goto err;
+	if (!fs)
+		goto err_put_ns;
+
+	read_lock(&fs->lock);
+	root = fs->root;
+	path_get(&root);
+	read_unlock(&fs->lock);
+	put_fs_struct(fs);
+
+	ret = -ENOMEM;
+	p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
+	if (!p)
+		goto err_put_path;
+
+	file->private_data = &p->m;
+	ret = seq_open(file, op);
+	if (ret)
+		goto err_free;
+
+	p->m.private = p;
+	p->ns = ns;
+	p->root = root;
+	p->event = ns->event;
+
+	return 0;
+
+ err_free:
+	kfree(p);
+ err_put_path:
+	path_put(&root);
+ err_put_ns:
+	put_mnt_ns(ns);
+ err:
 	return ret;
 }
 
 static int mounts_release(struct inode *inode, struct file *file)
 {
-	struct seq_file *m = file->private_data;
-	struct mnt_namespace *ns = m->private;
-	put_mnt_ns(ns);
+	struct proc_mounts *p = file->private_data;
+	path_put(&p->root);
+	put_mnt_ns(p->ns);
 	return seq_release(inode, file);
 }
 
 static unsigned mounts_poll(struct file *file, poll_table *wait)
 {
 	struct proc_mounts *p = file->private_data;
-	struct mnt_namespace *ns = p->m.private;
+	struct mnt_namespace *ns = p->ns;
 	unsigned res = 0;
 
 	poll_wait(file, &ns->poll, wait);
@@ -573,6 +591,11 @@ static unsigned mounts_poll(struct file *file, poll_table *wait)
 	return res;
 }
 
+static int mounts_open(struct inode *inode, struct file *file)
+{
+	return mounts_open_common(inode, file, &mounts_op);
+}
+
 static const struct file_operations proc_mounts_operations = {
 	.open		= mounts_open,
 	.read		= seq_read,
@@ -581,38 +604,22 @@ static const struct file_operations proc_mounts_operations = {
 	.poll		= mounts_poll,
 };
 
-extern const struct seq_operations mountstats_op;
-static int mountstats_open(struct inode *inode, struct file *file)
+static int mountinfo_open(struct inode *inode, struct file *file)
 {
-	int ret = seq_open(file, &mountstats_op);
-
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		struct nsproxy *nsp;
-		struct mnt_namespace *mnt_ns = NULL;
-		struct task_struct *task = get_proc_task(inode);
-
-		if (task) {
-			rcu_read_lock();
-			nsp = task_nsproxy(task);
-			if (nsp) {
-				mnt_ns = nsp->mnt_ns;
-				if (mnt_ns)
-					get_mnt_ns(mnt_ns);
-			}
-			rcu_read_unlock();
+	return mounts_open_common(inode, file, &mountinfo_op);
+}
 
-			put_task_struct(task);
-		}
+static const struct file_operations proc_mountinfo_operations = {
+	.open		= mountinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= mounts_release,
+	.poll		= mounts_poll,
+};
 
-		if (mnt_ns)
-			m->private = mnt_ns;
-		else {
-			seq_release(inode, file);
-			ret = -EINVAL;
-		}
-	}
-	return ret;
+static int mountstats_open(struct inode *inode, struct file *file)
+{
+	return mounts_open_common(inode, file, &mountstats_op);
 }
 
 static const struct file_operations proc_mountstats_operations = {
@@ -2309,6 +2316,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	LNK("root",       root),
 	LNK("exe",        exe),
 	REG("mounts",     S_IRUGO, mounts),
+	REG("mountinfo",  S_IRUGO, mountinfo),
 	REG("mountstats", S_IRUSR, mountstats),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, clear_refs),
@@ -2641,6 +2649,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	LNK("root",      root),
 	LNK("exe",       exe),
 	REG("mounts",    S_IRUGO, mounts),
+	REG("mountinfo",  S_IRUGO, mountinfo),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, clear_refs),
 	REG("smaps",     S_IRUGO, smaps),

fs/seq_file.c

@@ -350,28 +350,40 @@ int seq_printf(struct seq_file *m, const char *f, ...)
 }
 EXPORT_SYMBOL(seq_printf);
 
+static char *mangle_path(char *s, char *p, char *esc)
+{
+	while (s <= p) {
+		char c = *p++;
+		if (!c) {
+			return s;
+		} else if (!strchr(esc, c)) {
+			*s++ = c;
+		} else if (s + 4 > p) {
+			break;
+		} else {
+			*s++ = '\\';
+			*s++ = '0' + ((c & 0300) >> 6);
+			*s++ = '0' + ((c & 070) >> 3);
+			*s++ = '0' + (c & 07);
+		}
+	}
+	return NULL;
+}
+
+/*
+ * return the absolute path of 'dentry' residing in mount 'mnt'.
+ */
 int seq_path(struct seq_file *m, struct path *path, char *esc)
 {
 	if (m->count < m->size) {
 		char *s = m->buf + m->count;
 		char *p = d_path(path, s, m->size - m->count);
 		if (!IS_ERR(p)) {
-			while (s <= p) {
-				char c = *p++;
-				if (!c) {
-					p = m->buf + m->count;
-					m->count = s - m->buf;
-					return s - p;
-				} else if (!strchr(esc, c)) {
-					*s++ = c;
-				} else if (s + 4 > p) {
-					break;
-				} else {
-					*s++ = '\\';
-					*s++ = '0' + ((c & 0300) >> 6);
-					*s++ = '0' + ((c & 070) >> 3);
-					*s++ = '0' + (c & 07);
-				}
+			s = mangle_path(s, p, esc);
+			if (s) {
+				p = m->buf + m->count;
+				m->count = s - m->buf;
+				return s - p;
 			}
 		}
 	}
@@ -380,6 +392,57 @@ int seq_path(struct seq_file *m, struct path *path, char *esc)
 }
 EXPORT_SYMBOL(seq_path);
 
+/*
+ * Same as seq_path, but relative to supplied root.
+ *
+ * root may be changed, see __d_path().
+ */
+int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
+		  char *esc)
+{
+	int err = -ENAMETOOLONG;
+	if (m->count < m->size) {
+		char *s = m->buf + m->count;
+		char *p;
+
+		spin_lock(&dcache_lock);
+		p = __d_path(path, root, s, m->size - m->count);
+		spin_unlock(&dcache_lock);
+		err = PTR_ERR(p);
+		if (!IS_ERR(p)) {
+			s = mangle_path(s, p, esc);
+			if (s) {
+				p = m->buf + m->count;
+				m->count = s - m->buf;
+				return 0;
+			}
+		}
+	}
+	m->count = m->size;
+	return err;
+}
+
+/*
+ * returns the path of the 'dentry' from the root of its filesystem.
+ */
+int seq_dentry(struct seq_file *m, struct dentry *dentry, char *esc)
+{
+	if (m->count < m->size) {
+		char *s = m->buf + m->count;
+		char *p = dentry_path(dentry, s, m->size - m->count);
+		if (!IS_ERR(p)) {
+			s = mangle_path(s, p, esc);
+			if (s) {
+				p = m->buf + m->count;
+				m->count = s - m->buf;
+				return s - p;
+			}
+		}
+	}
+	m->count = m->size;
+	return -1;
+}
+
 static void *single_start(struct seq_file *p, loff_t *pos)
 {
 	return NULL + (*pos == 0);

fs/xattr.c

@@ -307,7 +307,6 @@ sys_fsetxattr(int fd, char __user *name, void __user *value,
 		error = setxattr(dentry, name, value, size, flags);
 		mnt_drop_write(f->f_path.mnt);
 	}
-out_fput:
 	fput(f);
 	return error;
 }

include/linux/dcache.h

@@ -301,7 +301,9 @@ extern int d_validate(struct dentry *, struct dentry *);
  */
 extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
 
+extern char *__d_path(const struct path *path, struct path *root, char *, int);
 extern char *d_path(struct path *, char *, int);
+extern char *dentry_path(struct dentry *, char *, int);
 
 /* Allocation counts.. */
 

include/linux/mnt_namespace.h

@@ -5,6 +5,7 @@
 #include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/nsproxy.h>
+#include <linux/seq_file.h>
 
 struct mnt_namespace {
 	atomic_t		count;
@@ -14,6 +15,13 @@ struct mnt_namespace {
 	int event;
 };
 
+struct proc_mounts {
+	struct seq_file m; /* must be the first element */
+	struct mnt_namespace *ns;
+	struct path root;
+	int event;
+};
+
 extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
 		struct fs_struct *);
 extern void __put_mnt_ns(struct mnt_namespace *ns);
@@ -37,5 +45,9 @@ static inline void get_mnt_ns(struct mnt_namespace *ns)
 	atomic_inc(&ns->count);
 }
 
+extern const struct seq_operations mounts_op;
+extern const struct seq_operations mountinfo_op;
+extern const struct seq_operations mountstats_op;
+
 #endif
 #endif

include/linux/mount.h

@@ -56,6 +56,8 @@ struct vfsmount {
 	struct list_head mnt_slave;	/* slave list entry */
 	struct vfsmount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
+	int mnt_id;			/* mount identifier */
+	int mnt_group_id;		/* peer group identifier */
 	/*
 	 * We put mnt_count & mnt_expiry_mark at the end of struct vfsmount
 	 * to let these frequently modified fields in a separate cache line

include/linux/seq_file.h

@@ -10,6 +10,7 @@ struct seq_operations;
 struct file;
 struct path;
 struct inode;
+struct dentry;
 
 struct seq_file {
 	char *buf;
@@ -44,6 +45,9 @@ int seq_printf(struct seq_file *, const char *, ...)
 	__attribute__ ((format (printf,2,3)));
 
 int seq_path(struct seq_file *, struct path *, char *);
+int seq_dentry(struct seq_file *, struct dentry *, char *);
+int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
+		  char *esc);
 
 int single_open(struct file *, int (*)(struct seq_file *, void *), void *);
 int single_release(struct inode *, struct file *);