1 files changed, 346 insertions, 36 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 94f026ec990..1bf302d0478 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -17,6 +17,7 @@
 #include <linux/quotaops.h>
 #include <linux/acct.h>
 #include <linux/capability.h>
+#include <linux/cpumask.h>
 #include <linux/module.h>
 #include <linux/sysfs.h>
 #include <linux/seq_file.h>
@@ -55,6 +56,8 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
 	return tmp & (HASH_SIZE - 1);
 }
 
+#define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16)
+
 struct vfsmount *alloc_vfsmnt(const char *name)
 {
 	struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
@@ -68,6 +71,7 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_share);
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
+		atomic_set(&mnt->__mnt_writers, 0);
 		if (name) {
 			int size = strlen(name) + 1;
 			char *newname = kmalloc(size, GFP_KERNEL);
@@ -80,6 +84,263 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 	return mnt;
 }
 
+/*
+ * Most r/o checks on a fs are for operations that take
+ * discrete amounts of time, like a write() or unlink().
+ * We must keep track of when those operations start
+ * (for permission checks) and when they end, so that
+ * we can determine when writes are able to occur to
+ * a filesystem.
+ */
+/*
+ * __mnt_is_readonly: check whether a mount is read-only
+ * @mnt: the mount to check for its write status
+ *
+ * This shouldn't be used directly ouside of the VFS.
+ * It does not guarantee that the filesystem will stay
+ * r/w, just that it is right *now*.  This can not and
+ * should not be used in place of IS_RDONLY(inode).
+ * mnt_want/drop_write() will _keep_ the filesystem
+ * r/w.
+ */
+int __mnt_is_readonly(struct vfsmount *mnt)
+{
+	if (mnt->mnt_flags & MNT_READONLY)
+		return 1;
+	if (mnt->mnt_sb->s_flags & MS_RDONLY)
+		return 1;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__mnt_is_readonly);
+
+struct mnt_writer {
+	/*
+	 * If holding multiple instances of this lock, they
+	 * must be ordered by cpu number.
+	 */
+	spinlock_t lock;
+	struct lock_class_key lock_class; /* compiles out with !lockdep */
+	unsigned long count;
+	struct vfsmount *mnt;
+} ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(struct mnt_writer, mnt_writers);
+
+static int __init init_mnt_writers(void)
+{
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		struct mnt_writer *writer = &per_cpu(mnt_writers, cpu);
+		spin_lock_init(&writer->lock);
+		lockdep_set_class(&writer->lock, &writer->lock_class);
+		writer->count = 0;
+	}
+	return 0;
+}
+fs_initcall(init_mnt_writers);
+
+static void unlock_mnt_writers(void)
+{
+	int cpu;
+	struct mnt_writer *cpu_writer;
+
+	for_each_possible_cpu(cpu) {
+		cpu_writer = &per_cpu(mnt_writers, cpu);
+		spin_unlock(&cpu_writer->lock);
+	}
+}
+
+static inline void __clear_mnt_count(struct mnt_writer *cpu_writer)
+{
+	if (!cpu_writer->mnt)
+		return;
+	/*
+	 * This is in case anyone ever leaves an invalid,
+	 * old ->mnt and a count of 0.
+	 */
+	if (!cpu_writer->count)
+		return;
+	atomic_add(cpu_writer->count, &cpu_writer->mnt->__mnt_writers);
+	cpu_writer->count = 0;
+}
+ /*
+ * must hold cpu_writer->lock
+ */
+static inline void use_cpu_writer_for_mount(struct mnt_writer *cpu_writer,
+					  struct vfsmount *mnt)
+{
+	if (cpu_writer->mnt == mnt)
+		return;
+	__clear_mnt_count(cpu_writer);
+	cpu_writer->mnt = mnt;
+}
+
+/*
+ * Most r/o checks on a fs are for operations that take
+ * discrete amounts of time, like a write() or unlink().
+ * We must keep track of when those operations start
+ * (for permission checks) and when they end, so that
+ * we can determine when writes are able to occur to
+ * a filesystem.
+ */
+/**
+ * mnt_want_write - get write access to a mount
+ * @mnt: the mount on which to take a write
+ *
+ * This tells the low-level filesystem that a write is
+ * about to be performed to it, and makes sure that
+ * writes are allowed before returning success.  When
+ * the write operation is finished, mnt_drop_write()
+ * must be called.  This is effectively a refcount.
+ */
+int mnt_want_write(struct vfsmount *mnt)
+{
+	int ret = 0;
+	struct mnt_writer *cpu_writer;
+
+	cpu_writer = &get_cpu_var(mnt_writers);
+	spin_lock(&cpu_writer->lock);
+	if (__mnt_is_readonly(mnt)) {
+		ret = -EROFS;
+		goto out;
+	}
+	use_cpu_writer_for_mount(cpu_writer, mnt);
+	cpu_writer->count++;
+out:
+	spin_unlock(&cpu_writer->lock);
+	put_cpu_var(mnt_writers);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mnt_want_write);
+
+static void lock_mnt_writers(void)
+{
+	int cpu;
+	struct mnt_writer *cpu_writer;
+
+	for_each_possible_cpu(cpu) {
+		cpu_writer = &per_cpu(mnt_writers, cpu);
+		spin_lock(&cpu_writer->lock);
+		__clear_mnt_count(cpu_writer);
+		cpu_writer->mnt = NULL;
+	}
+}
+
+/*
+ * These per-cpu write counts are not guaranteed to have
+ * matched increments and decrements on any given cpu.
+ * A file open()ed for write on one cpu and close()d on
+ * another cpu will imbalance this count.  Make sure it
+ * does not get too far out of whack.
+ */
+static void handle_write_count_underflow(struct vfsmount *mnt)
+{
+	if (atomic_read(&mnt->__mnt_writers) >=
+	    MNT_WRITER_UNDERFLOW_LIMIT)
+		return;
+	/*
+	 * It isn't necessary to hold all of the locks
+	 * at the same time, but doing it this way makes
+	 * us share a lot more code.
+	 */
+	lock_mnt_writers();
+	/*
+	 * vfsmount_lock is for mnt_flags.
+	 */
+	spin_lock(&vfsmount_lock);
+	/*
+	 * If coalescing the per-cpu writer counts did not
+	 * get us back to a positive writer count, we have
+	 * a bug.
+	 */
+	if ((atomic_read(&mnt->__mnt_writers) < 0) &&
+	    !(mnt->mnt_flags & MNT_IMBALANCED_WRITE_COUNT)) {
+		printk(KERN_DEBUG "leak detected on mount(%p) writers "
+				"count: %d\n",
+			mnt, atomic_read(&mnt->__mnt_writers));
+		WARN_ON(1);
+		/* use the flag to keep the dmesg spam down */
+		mnt->mnt_flags |= MNT_IMBALANCED_WRITE_COUNT;
+	}
+	spin_unlock(&vfsmount_lock);
+	unlock_mnt_writers();
+}
+
+/**
+ * mnt_drop_write - give up write access to a mount
+ * @mnt: the mount on which to give up write access
+ *
+ * Tells the low-level filesystem that we are done
+ * performing writes to it.  Must be matched with
+ * mnt_want_write() call above.
+ */
+void mnt_drop_write(struct vfsmount *mnt)
+{
+	int must_check_underflow = 0;
+	struct mnt_writer *cpu_writer;
+
+	cpu_writer = &get_cpu_var(mnt_writers);
+	spin_lock(&cpu_writer->lock);
+
+	use_cpu_writer_for_mount(cpu_writer, mnt);
+	if (cpu_writer->count > 0) {
+		cpu_writer->count--;
+	} else {
+		must_check_underflow = 1;
+		atomic_dec(&mnt->__mnt_writers);
+	}
+
+	spin_unlock(&cpu_writer->lock);
+	/*
+	 * Logically, we could call this each time,
+	 * but the __mnt_writers cacheline tends to
+	 * be cold, and makes this expensive.
+	 */
+	if (must_check_underflow)
+		handle_write_count_underflow(mnt);
+	/*
+	 * This could be done right after the spinlock
+	 * is taken because the spinlock keeps us on
+	 * the cpu, and disables preemption.  However,
+	 * putting it here bounds the amount that
+	 * __mnt_writers can underflow.  Without it,
+	 * we could theoretically wrap __mnt_writers.
+	 */
+	put_cpu_var(mnt_writers);
+}
+EXPORT_SYMBOL_GPL(mnt_drop_write);
+
+static int mnt_make_readonly(struct vfsmount *mnt)
+{
+	int ret = 0;
+
+	lock_mnt_writers();
+	/*
+	 * With all the locks held, this value is stable
+	 */
+	if (atomic_read(&mnt->__mnt_writers) > 0) {
+		ret = -EBUSY;
+		goto out;
+	}
+	/*
+	 * nobody can do a successful mnt_want_write() with all
+	 * of the counts in MNT_DENIED_WRITE and the locks held.
+	 */
+	spin_lock(&vfsmount_lock);
+	if (!ret)
+		mnt->mnt_flags |= MNT_READONLY;
+	spin_unlock(&vfsmount_lock);
+out:
+	unlock_mnt_writers();
+	return ret;
+}
+
+static void __mnt_unmake_readonly(struct vfsmount *mnt)
+{
+	spin_lock(&vfsmount_lock);
+	mnt->mnt_flags &= ~MNT_READONLY;
+	spin_unlock(&vfsmount_lock);
+}
+
 int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
 {
 	mnt->mnt_sb = sb;
@@ -271,7 +532,36 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 
 static inline void __mntput(struct vfsmount *mnt)
 {
+	int cpu;
 	struct super_block *sb = mnt->mnt_sb;
+	/*
+	 * We don't have to hold all of the locks at the
+	 * same time here because we know that we're the
+	 * last reference to mnt and that no new writers
+	 * can come in.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct mnt_writer *cpu_writer = &per_cpu(mnt_writers, cpu);
+		if (cpu_writer->mnt != mnt)
+			continue;
+		spin_lock(&cpu_writer->lock);
+		atomic_add(cpu_writer->count, &mnt->__mnt_writers);
+		cpu_writer->count = 0;
+		/*
+		 * Might as well do this so that no one
+		 * ever sees the pointer and expects
+		 * it to be valid.
+		 */
+		cpu_writer->mnt = NULL;
+		spin_unlock(&cpu_writer->lock);
+	}
+	/*
+	 * This probably indicates that somebody messed
+	 * up a mnt_want/drop_write() pair.  If this
+	 * happens, the filesystem was probably unable
+	 * to make r/w->r/o transitions.
+	 */
+	WARN_ON(atomic_read(&mnt->__mnt_writers));
 	dput(mnt->mnt_root);
 	free_vfsmnt(mnt);
 	deactivate_super(sb);
@@ -417,7 +707,7 @@ static int show_vfsmnt(struct seq_file *m, void *v)
 		seq_putc(m, '.');
 		mangle(m, mnt->mnt_sb->s_subtype);
 	}
-	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
+	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);
@@ -801,20 +1091,20 @@ Enomem:
 struct vfsmount *collect_mounts(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct vfsmount *tree;
-	down_read(&namespace_sem);
+	down_write(&namespace_sem);
 	tree = copy_tree(mnt, dentry, CL_COPY_ALL | CL_PRIVATE);
-	up_read(&namespace_sem);
+	up_write(&namespace_sem);
 	return tree;
 }
 
 void drop_collected_mounts(struct vfsmount *mnt)
 {
 	LIST_HEAD(umount_list);
-	down_read(&namespace_sem);
+	down_write(&namespace_sem);
 	spin_lock(&vfsmount_lock);
 	umount_tree(mnt, 0, &umount_list);
 	spin_unlock(&vfsmount_lock);
-	up_read(&namespace_sem);
+	up_write(&namespace_sem);
 	release_mounts(&umount_list);
 }
 
@@ -915,32 +1205,32 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	return 0;
 }
 
-static int graft_tree(struct vfsmount *mnt, struct nameidata *nd)
+static int graft_tree(struct vfsmount *mnt, struct path *path)
 {
 	int err;
 	if (mnt->mnt_sb->s_flags & MS_NOUSER)
 		return -EINVAL;
 
-	if (S_ISDIR(nd->path.dentry->d_inode->i_mode) !=
+	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
 	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
 		return -ENOTDIR;
 
 	err = -ENOENT;
-	mutex_lock(&nd->path.dentry->d_inode->i_mutex);
-	if (IS_DEADDIR(nd->path.dentry->d_inode))
+	mutex_lock(&path->dentry->d_inode->i_mutex);
+	if (IS_DEADDIR(path->dentry->d_inode))
 		goto out_unlock;
 
-	err = security_sb_check_sb(mnt, nd);
+	err = security_sb_check_sb(mnt, path);
 	if (err)
 		goto out_unlock;
 
 	err = -ENOENT;
-	if (IS_ROOT(nd->path.dentry) || !d_unhashed(nd->path.dentry))
-		err = attach_recursive_mnt(mnt, &nd->path, NULL);
+	if (IS_ROOT(path->dentry) || !d_unhashed(path->dentry))
+		err = attach_recursive_mnt(mnt, path, NULL);
 out_unlock:
-	mutex_unlock(&nd->path.dentry->d_inode->i_mutex);
+	mutex_unlock(&path->dentry->d_inode->i_mutex);
 	if (!err)
-		security_sb_post_addmount(mnt, nd);
+		security_sb_post_addmount(mnt, path);
 	return err;
 }
 
@@ -1004,7 +1294,7 @@ static noinline int do_loopback(struct nameidata *nd, char *old_name,
 	if (!mnt)
 		goto out;
 
-	err = graft_tree(mnt, nd);
+	err = graft_tree(mnt, &nd->path);
 	if (err) {
 		LIST_HEAD(umount_list);
 		spin_lock(&vfsmount_lock);
@@ -1019,6 +1309,23 @@ out:
 	return err;
 }
 
+static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
+{
+	int error = 0;
+	int readonly_request = 0;
+
+	if (ms_flags & MS_RDONLY)
+		readonly_request = 1;
+	if (readonly_request == __mnt_is_readonly(mnt))
+		return 0;
+
+	if (readonly_request)
+		error = mnt_make_readonly(mnt);
+	else
+		__mnt_unmake_readonly(mnt);
+	return error;
+}
+
 /*
  * change filesystem flags. dir should be a physical root of filesystem.
  * If you've mounted a non-root directory somewhere and want to do remount
@@ -1041,7 +1348,10 @@ static noinline int do_remount(struct nameidata *nd, int flags, int mnt_flags,
 		return -EINVAL;
 
 	down_write(&sb->s_umount);
-	err = do_remount_sb(sb, flags, data, 0);
+	if (flags & MS_BIND)
+		err = change_mount_flags(nd->path.mnt, flags);
+	else
+		err = do_remount_sb(sb, flags, data, 0);
 	if (!err)
 		nd->path.mnt->mnt_flags = mnt_flags;
 	up_write(&sb->s_umount);
@@ -1191,7 +1501,7 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
 		goto unlock;
 
 	newmnt->mnt_flags = mnt_flags;
-	if ((err = graft_tree(newmnt, nd)))
+	if ((err = graft_tree(newmnt, &nd->path)))
 		goto unlock;
 
 	if (fslist) /* add to the specified expiration list */
@@ -1425,6 +1735,8 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
 		mnt_flags |= MNT_NODIRATIME;
 	if (flags & MS_RELATIME)
 		mnt_flags |= MNT_RELATIME;
+	if (flags & MS_RDONLY)
+		mnt_flags |= MNT_READONLY;
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT);
@@ -1434,7 +1746,8 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
 	if (retval)
 		return retval;
 
-	retval = security_sb_mount(dev_name, &nd, type_page, flags, data_page);
+	retval = security_sb_mount(dev_name, &nd.path,
+				   type_page, flags, data_page);
 	if (retval)
 		goto dput_out;
 
@@ -1674,15 +1987,13 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
 			       const char __user * put_old)
 {
 	struct vfsmount *tmp;
-	struct nameidata new_nd, old_nd, user_nd;
-	struct path parent_path, root_parent;
+	struct nameidata new_nd, old_nd;
+	struct path parent_path, root_parent, root;
 	int error;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	lock_kernel();
-
 	error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
 			    &new_nd);
 	if (error)
@@ -1695,14 +2006,14 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
 	if (error)
 		goto out1;
 
-	error = security_sb_pivotroot(&old_nd, &new_nd);
+	error = security_sb_pivotroot(&old_nd.path, &new_nd.path);
 	if (error) {
 		path_put(&old_nd.path);
 		goto out1;
 	}
 
 	read_lock(&current->fs->lock);
-	user_nd.path = current->fs->root;
+	root = current->fs->root;
 	path_get(&current->fs->root);
 	read_unlock(&current->fs->lock);
 	down_write(&namespace_sem);
@@ -1710,9 +2021,9 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
 	error = -EINVAL;
 	if (IS_MNT_SHARED(old_nd.path.mnt) ||
 		IS_MNT_SHARED(new_nd.path.mnt->mnt_parent) ||
-		IS_MNT_SHARED(user_nd.path.mnt->mnt_parent))
+		IS_MNT_SHARED(root.mnt->mnt_parent))
 		goto out2;
-	if (!check_mnt(user_nd.path.mnt))
+	if (!check_mnt(root.mnt))
 		goto out2;
 	error = -ENOENT;
 	if (IS_DEADDIR(new_nd.path.dentry->d_inode))
@@ -1722,13 +2033,13 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
 	if (d_unhashed(old_nd.path.dentry) && !IS_ROOT(old_nd.path.dentry))
 		goto out2;
 	error = -EBUSY;
-	if (new_nd.path.mnt == user_nd.path.mnt ||
-	    old_nd.path.mnt == user_nd.path.mnt)
+	if (new_nd.path.mnt == root.mnt ||
+	    old_nd.path.mnt == root.mnt)
 		goto out2; /* loop, on the same file system  */
 	error = -EINVAL;
-	if (user_nd.path.mnt->mnt_root != user_nd.path.dentry)
+	if (root.mnt->mnt_root != root.dentry)
 		goto out2; /* not a mountpoint */
-	if (user_nd.path.mnt->mnt_parent == user_nd.path.mnt)
+	if (root.mnt->mnt_parent == root.mnt)
 		goto out2; /* not attached */
 	if (new_nd.path.mnt->mnt_root != new_nd.path.dentry)
 		goto out2; /* not a mountpoint */
@@ -1750,27 +2061,26 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
 	} else if (!is_subdir(old_nd.path.dentry, new_nd.path.dentry))
 		goto out3;
 	detach_mnt(new_nd.path.mnt, &parent_path);
-	detach_mnt(user_nd.path.mnt, &root_parent);
+	detach_mnt(root.mnt, &root_parent);
 	/* mount old root on put_old */
-	attach_mnt(user_nd.path.mnt, &old_nd.path);
+	attach_mnt(root.mnt, &old_nd.path);
 	/* mount new_root on / */
 	attach_mnt(new_nd.path.mnt, &root_parent);
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	spin_unlock(&vfsmount_lock);
-	chroot_fs_refs(&user_nd.path, &new_nd.path);
-	security_sb_post_pivotroot(&user_nd, &new_nd);
+	chroot_fs_refs(&root, &new_nd.path);
+	security_sb_post_pivotroot(&root, &new_nd.path);
 	error = 0;
 	path_put(&root_parent);
 	path_put(&parent_path);
 out2:
 	mutex_unlock(&old_nd.path.dentry->d_inode->i_mutex);
 	up_write(&namespace_sem);
-	path_put(&user_nd.path);
+	path_put(&root);
 	path_put(&old_nd.path);
 out1:
 	path_put(&new_nd.path);
 out0:
-	unlock_kernel();
 	return error;
 out3:
 	spin_unlock(&vfsmount_lock);