VFS: New /proc file /proc/self/mountstats

Create a new file under /proc/self, called mountstats, where mounted file
systems can export information (configuration options, performance counters,
and so on).  Use a mechanism similar to /proc/mounts and s_ops->show_options.

This mechanism does not violate namespace security, and is safe to use while
other processes are unmounting file systems.

Thanks to Mike Waychison for his review and comments.

Test-plan:
Test concurrent mount/unmount operations while cat'ing /proc/self/mountstats.

Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

fs/namespace.c

@@ -399,6 +399,44 @@ struct seq_operations mounts_op = {
 	.show	= show_vfsmnt
 };
 
+static int show_vfsstat(struct seq_file *m, void *v)
+{
+	struct vfsmount *mnt = v;
+	int err = 0;
+
+	/* device */
+	if (mnt->mnt_devname) {
+		seq_puts(m, "device ");
+		mangle(m, mnt->mnt_devname);
+	} else
+		seq_puts(m, "no device");
+
+	/* mount point */
+	seq_puts(m, " mounted on ");
+	seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
+	seq_putc(m, ' ');
+
+	/* file system type */
+	seq_puts(m, "with fstype ");
+	mangle(m, mnt->mnt_sb->s_type->name);
+
+	/* optional statistics */
+	if (mnt->mnt_sb->s_op->show_stats) {
+		seq_putc(m, ' ');
+		err = mnt->mnt_sb->s_op->show_stats(m, mnt);
+	}
+
+	seq_putc(m, '\n');
+	return err;
+}
+
+struct seq_operations mountstats_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_vfsstat,
+};
+
 /**
  * may_umount_tree - check if a mount tree is busy
  * @mnt: root of mount tree

fs/proc/base.c

@@ -104,6 +104,7 @@ enum pid_directory_inos {
 	PROC_TGID_MAPS,
 	PROC_TGID_NUMA_MAPS,
 	PROC_TGID_MOUNTS,
+	PROC_TGID_MOUNTSTATS,
 	PROC_TGID_WCHAN,
 #ifdef CONFIG_MMU
 	PROC_TGID_SMAPS,
@@ -144,6 +145,7 @@ enum pid_directory_inos {
 	PROC_TID_MAPS,
 	PROC_TID_NUMA_MAPS,
 	PROC_TID_MOUNTS,
+	PROC_TID_MOUNTSTATS,
 	PROC_TID_WCHAN,
 #ifdef CONFIG_MMU
 	PROC_TID_SMAPS,
@@ -201,6 +203,7 @@ static struct pid_entry tgid_base_stuff[] = {
 	E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
 	E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
 	E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
+	E(PROC_TGID_MOUNTSTATS, "mountstats", S_IFREG|S_IRUSR),
 #ifdef CONFIG_MMU
 	E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUGO),
 #endif
@@ -732,6 +735,38 @@ static struct file_operations proc_mounts_operations = {
 	.poll		= mounts_poll,
 };
 
+extern struct seq_operations mountstats_op;
+static int mountstats_open(struct inode *inode, struct file *file)
+{
+	struct task_struct *task = proc_task(inode);
+	int ret = seq_open(file, &mountstats_op);
+
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		struct namespace *namespace;
+		task_lock(task);
+		namespace = task->namespace;
+		if (namespace)
+			get_namespace(namespace);
+		task_unlock(task);
+
+		if (namespace)
+			m->private = namespace;
+		else {
+			seq_release(inode, file);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+static struct file_operations proc_mountstats_operations = {
+	.open		= mountstats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= mounts_release,
+};
+
 #define PROC_BLOCK_SIZE	(3*1024)		/* 4K page size but our output routines use some slack for overruns */
 
 static ssize_t proc_info_read(struct file * file, char __user * buf,
@@ -1730,6 +1765,10 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 			inode->i_fop = &proc_smaps_operations;
 			break;
 #endif
+		case PROC_TID_MOUNTSTATS:
+		case PROC_TGID_MOUNTSTATS:
+			inode->i_fop = &proc_mountstats_operations;
+			break;
 #ifdef CONFIG_SECURITY
 		case PROC_TID_ATTR:
 			inode->i_nlink = 2;

include/linux/fs.h

@@ -1086,6 +1086,7 @@ struct super_operations {
 	void (*umount_begin) (struct super_block *);
 
 	int (*show_options)(struct seq_file *, struct vfsmount *);
+	int (*show_stats)(struct seq_file *, struct vfsmount *);
 
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);