1 files changed, 139 insertions, 93 deletions

diff --git a/fs/namei.c b/fs/namei.c
index bbc15c237558..f3c5b278895a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -24,6 +24,7 @@
 #include <linux/fsnotify.h>
 #include <linux/personality.h>
 #include <linux/security.h>
+#include <linux/ima.h>
 #include <linux/syscalls.h>
 #include <linux/mount.h>
 #include <linux/audit.h>
@@ -31,6 +32,7 @@
 #include <linux/file.h>
 #include <linux/fcntl.h>
 #include <linux/device_cgroup.h>
+#include <linux/fs_struct.h>
 #include <asm/uaccess.h>
 
 #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
@@ -550,6 +552,17 @@ static __always_inline int link_path_walk(const char *name, struct nameidata *nd
 	return result;
 }
 
+static __always_inline void set_root(struct nameidata *nd)
+{
+	if (!nd->root.mnt) {
+		struct fs_struct *fs = current->fs;
+		read_lock(&fs->lock);
+		nd->root = fs->root;
+		path_get(&nd->root);
+		read_unlock(&fs->lock);
+	}
+}
+
 static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
 {
 	int res = 0;
@@ -558,14 +571,10 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
 		goto fail;
 
 	if (*link == '/') {
-		struct fs_struct *fs = current->fs;
-
+		set_root(nd);
 		path_put(&nd->path);
-
-		read_lock(&fs->lock);
-		nd->path = fs->root;
-		path_get(&fs->root);
-		read_unlock(&fs->lock);
+		nd->path = nd->root;
+		path_get(&nd->root);
 	}
 
 	res = link_path_walk(link, nd);
@@ -666,23 +675,23 @@ loop:
 	return err;
 }
 
-int follow_up(struct vfsmount **mnt, struct dentry **dentry)
+int follow_up(struct path *path)
 {
 	struct vfsmount *parent;
 	struct dentry *mountpoint;
 	spin_lock(&vfsmount_lock);
-	parent=(*mnt)->mnt_parent;
-	if (parent == *mnt) {
+	parent = path->mnt->mnt_parent;
+	if (parent == path->mnt) {
 		spin_unlock(&vfsmount_lock);
 		return 0;
 	}
 	mntget(parent);
-	mountpoint=dget((*mnt)->mnt_mountpoint);
+	mountpoint = dget(path->mnt->mnt_mountpoint);
 	spin_unlock(&vfsmount_lock);
-	dput(*dentry);
-	*dentry = mountpoint;
-	mntput(*mnt);
-	*mnt = parent;
+	dput(path->dentry);
+	path->dentry = mountpoint;
+	mntput(path->mnt);
+	path->mnt = parent;
 	return 1;
 }
 
@@ -693,7 +702,7 @@ static int __follow_mount(struct path *path)
 {
 	int res = 0;
 	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted = lookup_mnt(path->mnt, path->dentry);
+		struct vfsmount *mounted = lookup_mnt(path);
 		if (!mounted)
 			break;
 		dput(path->dentry);
@@ -706,32 +715,32 @@ static int __follow_mount(struct path *path)
 	return res;
 }
 
-static void follow_mount(struct vfsmount **mnt, struct dentry **dentry)
+static void follow_mount(struct path *path)
 {
-	while (d_mountpoint(*dentry)) {
-		struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted = lookup_mnt(path);
 		if (!mounted)
 			break;
-		dput(*dentry);
-		mntput(*mnt);
-		*mnt = mounted;
-		*dentry = dget(mounted->mnt_root);
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
 	}
 }
 
 /* no need for dcache_lock, as serialization is taken care in
  * namespace.c
  */
-int follow_down(struct vfsmount **mnt, struct dentry **dentry)
+int follow_down(struct path *path)
 {
 	struct vfsmount *mounted;
 
-	mounted = lookup_mnt(*mnt, *dentry);
+	mounted = lookup_mnt(path);
 	if (mounted) {
-		dput(*dentry);
-		mntput(*mnt);
-		*mnt = mounted;
-		*dentry = dget(mounted->mnt_root);
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
 		return 1;
 	}
 	return 0;
@@ -739,19 +748,16 @@ int follow_down(struct vfsmount **mnt, struct dentry **dentry)
 
 static __always_inline void follow_dotdot(struct nameidata *nd)
 {
-	struct fs_struct *fs = current->fs;
+	set_root(nd);
 
 	while(1) {
 		struct vfsmount *parent;
 		struct dentry *old = nd->path.dentry;
 
-                read_lock(&fs->lock);
-		if (nd->path.dentry == fs->root.dentry &&
-		    nd->path.mnt == fs->root.mnt) {
-                        read_unlock(&fs->lock);
+		if (nd->path.dentry == nd->root.dentry &&
+		    nd->path.mnt == nd->root.mnt) {
 			break;
 		}
-                read_unlock(&fs->lock);
 		spin_lock(&dcache_lock);
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			nd->path.dentry = dget(nd->path.dentry->d_parent);
@@ -773,7 +779,7 @@ static __always_inline void follow_dotdot(struct nameidata *nd)
 		mntput(nd->path.mnt);
 		nd->path.mnt = parent;
 	}
-	follow_mount(&nd->path.mnt, &nd->path.dentry);
+	follow_mount(&nd->path);
 }
 
 /*
@@ -850,6 +856,9 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
 		if (err == -EAGAIN)
 			err = inode_permission(nd->path.dentry->d_inode,
 					       MAY_EXEC);
+		if (!err)
+			err = ima_path_check(&nd->path, MAY_EXEC,
+				             IMA_COUNT_UPDATE);
  		if (err)
 			break;
 
@@ -1012,25 +1021,23 @@ static int path_walk(const char *name, struct nameidata *nd)
 	return link_path_walk(name, nd);
 }
 
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int do_path_lookup(int dfd, const char *name,
-				unsigned int flags, struct nameidata *nd)
+static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
 {
 	int retval = 0;
 	int fput_needed;
 	struct file *file;
-	struct fs_struct *fs = current->fs;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags;
 	nd->depth = 0;
+	nd->root.mnt = NULL;
 
 	if (*name=='/') {
-		read_lock(&fs->lock);
-		nd->path = fs->root;
-		path_get(&fs->root);
-		read_unlock(&fs->lock);
+		set_root(nd);
+		nd->path = nd->root;
+		path_get(&nd->root);
 	} else if (dfd == AT_FDCWD) {
+		struct fs_struct *fs = current->fs;
 		read_lock(&fs->lock);
 		nd->path = fs->pwd;
 		path_get(&fs->pwd);
@@ -1058,17 +1065,29 @@ static int do_path_lookup(int dfd, const char *name,
 
 		fput_light(file, fput_needed);
 	}
+	return 0;
 
-	retval = path_walk(name, nd);
+fput_fail:
+	fput_light(file, fput_needed);
+out_fail:
+	return retval;
+}
+
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+static int do_path_lookup(int dfd, const char *name,
+				unsigned int flags, struct nameidata *nd)
+{
+	int retval = path_init(dfd, name, flags, nd);
+	if (!retval)
+		retval = path_walk(name, nd);
 	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
 				nd->path.dentry->d_inode))
 		audit_inode(name, nd->path.dentry);
-out_fail:
+	if (nd->root.mnt) {
+		path_put(&nd->root);
+		nd->root.mnt = NULL;
+	}
 	return retval;
-
-fput_fail:
-	fput_light(file, fput_needed);
-	goto out_fail;
 }
 
 int path_lookup(const char *name, unsigned int flags,
@@ -1108,14 +1127,18 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 	nd->path.dentry = dentry;
 	nd->path.mnt = mnt;
 	path_get(&nd->path);
+	nd->root = nd->path;
+	path_get(&nd->root);
 
 	retval = path_walk(name, nd);
 	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
 				nd->path.dentry->d_inode))
 		audit_inode(name, nd->path.dentry);
 
-	return retval;
+	path_put(&nd->root);
+	nd->root.mnt = NULL;
 
+	return retval;
 }
 
 /**
@@ -1126,8 +1149,8 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
  * @nd: pointer to nameidata
  * @open_flags: open intent flags
  */
-int path_lookup_open(int dfd, const char *name, unsigned int lookup_flags,
-		struct nameidata *nd, int open_flags)
+static int path_lookup_open(int dfd, const char *name,
+		unsigned int lookup_flags, struct nameidata *nd, int open_flags)
 {
 	struct file *filp = get_empty_filp();
 	int err;
@@ -1244,6 +1267,8 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	int err;
 	struct qstr this;
 
+	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
+
 	err = __lookup_one_len(name, &this, base, len);
 	if (err)
 		return ERR_PTR(err);
@@ -1470,7 +1495,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	error = security_inode_create(dir, dentry, mode);
 	if (error)
 		return error;
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 	error = dir->i_op->create(dir, dentry, mode, nd);
 	if (!error)
 		fsnotify_create(dir, dentry);
@@ -1486,29 +1511,33 @@ int may_open(struct path *path, int acc_mode, int flag)
 	if (!inode)
 		return -ENOENT;
 
-	if (S_ISLNK(inode->i_mode))
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFLNK:
 		return -ELOOP;
-	
-	if (S_ISDIR(inode->i_mode) && (acc_mode & MAY_WRITE))
-		return -EISDIR;
-
-	/*
-	 * FIFO's, sockets and device files are special: they don't
-	 * actually live on the filesystem itself, and as such you
-	 * can write to them even if the filesystem is read-only.
-	 */
-	if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
-	    	flag &= ~O_TRUNC;
-	} else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) {
+	case S_IFDIR:
+		if (acc_mode & MAY_WRITE)
+			return -EISDIR;
+		break;
+	case S_IFBLK:
+	case S_IFCHR:
 		if (path->mnt->mnt_flags & MNT_NODEV)
 			return -EACCES;
-
+		/*FALLTHRU*/
+	case S_IFIFO:
+	case S_IFSOCK:
 		flag &= ~O_TRUNC;
+		break;
 	}
 
 	error = inode_permission(inode, acc_mode);
 	if (error)
 		return error;
+
+	error = ima_path_check(path,
+			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC),
+			       IMA_COUNT_UPDATE);
+	if (error)
+		return error;
 	/*
 	 * An append-only file must be opened in append mode for writing.
 	 */
@@ -1544,7 +1573,7 @@ int may_open(struct path *path, int acc_mode, int flag)
 			error = security_path_truncate(path, 0,
 					       ATTR_MTIME|ATTR_CTIME|ATTR_OPEN);
 		if (!error) {
-			DQUOT_INIT(inode);
+			vfs_dq_init(inode);
 
 			error = do_truncate(dentry, 0,
 					    ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
@@ -1555,7 +1584,7 @@ int may_open(struct path *path, int acc_mode, int flag)
 			return error;
 	} else
 		if (flag & FMODE_WRITE)
-			DQUOT_INIT(inode);
+			vfs_dq_init(inode);
 
 	return 0;
 }
@@ -1572,7 +1601,7 @@ static int __open_namei_create(struct nameidata *nd, struct path *path,
 	struct dentry *dir = nd->path.dentry;
 
 	if (!IS_POSIXACL(dir->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 	error = security_path_mknod(&nd->path, path->dentry, mode, 0);
 	if (error)
 		goto out_unlock;
@@ -1628,18 +1657,19 @@ static int open_will_write_to_fs(int flag, struct inode *inode)
  * open_to_namei_flags() for more details.
  */
 struct file *do_filp_open(int dfd, const char *pathname,
-		int open_flag, int mode)
+		int open_flag, int mode, int acc_mode)
 {
 	struct file *filp;
 	struct nameidata nd;
-	int acc_mode, error;
+	int error;
 	struct path path;
 	struct dentry *dir;
 	int count = 0;
 	int will_write;
 	int flag = open_to_namei_flags(open_flag);
 
-	acc_mode = MAY_OPEN | ACC_MODE(flag);
+	if (!acc_mode)
+		acc_mode = MAY_OPEN | ACC_MODE(flag);
 
 	/* O_TRUNC implies we need access checks for write permissions */
 	if (flag & O_TRUNC)
@@ -1664,9 +1694,17 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	/*
 	 * Create - we need to know the parent.
 	 */
-	error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd);
+	error = path_init(dfd, pathname, LOOKUP_PARENT, &nd);
 	if (error)
 		return ERR_PTR(error);
+	error = path_walk(pathname, &nd);
+	if (error) {
+		if (nd.root.mnt)
+			path_put(&nd.root);
+		return ERR_PTR(error);
+	}
+	if (unlikely(!audit_dummy_context()))
+		audit_inode(pathname, nd.path.dentry);
 
 	/*
 	 * We have the parent and last component. First of all, check
@@ -1723,7 +1761,13 @@ do_last:
 			goto exit;
 		}
 		filp = nameidata_to_filp(&nd, open_flag);
+		if (IS_ERR(filp))
+			ima_counts_put(&nd.path,
+				       acc_mode & (MAY_READ | MAY_WRITE |
+						   MAY_EXEC));
 		mnt_drop_write(nd.path.mnt);
+		if (nd.root.mnt)
+			path_put(&nd.root);
 		return filp;
 	}
 
@@ -1777,6 +1821,9 @@ ok:
 		goto exit;
 	}
 	filp = nameidata_to_filp(&nd, open_flag);
+	if (IS_ERR(filp))
+		ima_counts_put(&nd.path,
+			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
 	/*
 	 * It is now safe to drop the mnt write
 	 * because the filp has had a write taken
@@ -1784,6 +1831,8 @@ ok:
 	 */
 	if (will_write)
 		mnt_drop_write(nd.path.mnt);
+	if (nd.root.mnt)
+		path_put(&nd.root);
 	return filp;
 
 exit_mutex_unlock:
@@ -1794,6 +1843,8 @@ exit:
 	if (!IS_ERR(nd.intent.open.file))
 		release_open_intent(&nd);
 exit_parent:
+	if (nd.root.mnt)
+		path_put(&nd.root);
 	path_put(&nd.path);
 	return ERR_PTR(error);
 
@@ -1822,6 +1873,8 @@ do_link:
 		 * with "intent.open".
 		 */
 		release_open_intent(&nd);
+		if (nd.root.mnt)
+			path_put(&nd.root);
 		return ERR_PTR(error);
 	}
 	nd.flags &= ~LOOKUP_PARENT;
@@ -1860,7 +1913,7 @@ do_link:
  */
 struct file *filp_open(const char *filename, int flags, int mode)
 {
-	return do_filp_open(AT_FDCWD, filename, flags, mode);
+	return do_filp_open(AT_FDCWD, filename, flags, mode, 0);
 }
 EXPORT_SYMBOL(filp_open);
 
@@ -1938,7 +1991,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 	if (error)
 		return error;
 
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 	error = dir->i_op->mknod(dir, dentry, mode, dev);
 	if (!error)
 		fsnotify_create(dir, dentry);
@@ -1983,7 +2036,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, int, mode,
 		goto out_unlock;
 	}
 	if (!IS_POSIXACL(nd.path.dentry->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 	error = may_mknod(mode);
 	if (error)
 		goto out_dput;
@@ -2037,7 +2090,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	if (error)
 		return error;
 
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 	error = dir->i_op->mkdir(dir, dentry, mode);
 	if (!error)
 		fsnotify_mkdir(dir, dentry);
@@ -2061,7 +2114,7 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, int, mode)
 		goto out_unlock;
 
 	if (!IS_POSIXACL(nd.path.dentry->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto out_dput;
@@ -2123,7 +2176,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (!dir->i_op->rmdir)
 		return -EPERM;
 
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 
 	mutex_lock(&dentry->d_inode->i_mutex);
 	dentry_unhash(dentry);
@@ -2210,7 +2263,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dir->i_op->unlink)
 		return -EPERM;
 
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 
 	mutex_lock(&dentry->d_inode->i_mutex);
 	if (d_mountpoint(dentry))
@@ -2321,7 +2374,7 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
 	if (error)
 		return error;
 
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 	error = dir->i_op->symlink(dir, dentry, oldname);
 	if (!error)
 		fsnotify_create(dir, dentry);
@@ -2405,7 +2458,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		return error;
 
 	mutex_lock(&inode->i_mutex);
-	DQUOT_INIT(dir);
+	vfs_dq_init(dir);
 	error = dir->i_op->link(old_dentry, dir, new_dentry);
 	mutex_unlock(&inode->i_mutex);
 	if (!error)
@@ -2604,8 +2657,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (!old_dir->i_op->rename)
 		return -EPERM;
 
-	DQUOT_INIT(old_dir);
-	DQUOT_INIT(new_dir);
+	vfs_dq_init(old_dir);
+	vfs_dq_init(new_dir);
 
 	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
 
@@ -2891,10 +2944,3 @@ EXPORT_SYMBOL(vfs_symlink);
 EXPORT_SYMBOL(vfs_unlink);
 EXPORT_SYMBOL(dentry_unhash);
 EXPORT_SYMBOL(generic_readlink);
-
-/* to be mentioned only in INIT_TASK */
-struct fs_struct init_fs = {
-	.count		= ATOMIC_INIT(1),
-	.lock		= __RW_LOCK_UNLOCKED(init_fs.lock),
-	.umask		= 0022,
-};