5 files changed, 152 insertions, 64 deletions

diff --git a/kernel/fs/overlayfs/copy_up.c b/kernel/fs/overlayfs/copy_up.c
index eff6319d5..63a0d0ba3 100644
--- a/kernel/fs/overlayfs/copy_up.c
+++ b/kernel/fs/overlayfs/copy_up.c
@@ -25,6 +25,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 	ssize_t list_size, size, value_size = 0;
 	char *buf, *name, *value = NULL;
 	int uninitialized_var(error);
+	size_t slen;
 
 	if (!old->d_inode->i_op->getxattr ||
 	    !new->d_inode->i_op->getxattr)
@@ -47,7 +48,18 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 		goto out;
 	}
 
-	for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+	for (name = buf; list_size; name += slen) {
+		slen = strnlen(name, list_size) + 1;
+
+		/* underlying fs providing us with an broken xattr list? */
+		if (WARN_ON(slen > list_size)) {
+			error = -EIO;
+			break;
+		}
+		list_size -= slen;
+
+		if (ovl_is_private_xattr(name))
+			continue;
 retry:
 		size = vfs_getxattr(old, name, value, value_size);
 		if (size == -ERANGE)
@@ -127,6 +139,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 		len -= bytes;
 	}
 
+	if (!error)
+		error = vfs_fsync(new_file, 0);
 	fput(new_file);
 out_fput:
 	fput(old_file);
diff --git a/kernel/fs/overlayfs/dir.c b/kernel/fs/overlayfs/dir.c
index a2b1d7ce3..327177df0 100644
--- a/kernel/fs/overlayfs/dir.c
+++ b/kernel/fs/overlayfs/dir.c
@@ -12,6 +12,7 @@
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/cred.h>
+#include <linux/atomic.h>
 #include "overlayfs.h"
 
 void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
@@ -35,8 +36,10 @@ struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
 {
 	struct dentry *temp;
 	char name[20];
+	static atomic_t temp_id = ATOMIC_INIT(0);
 
-	snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry);
+	/* counter is allowed to wrap, since temp dentries are ephemeral */
+	snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
 
 	temp = lookup_one_len(name, workdir, strlen(name));
 	if (!IS_ERR(temp) && temp->d_inode) {
@@ -511,6 +514,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	struct dentry *upper;
 	struct dentry *opaquedir = NULL;
 	int err;
+	int flags = 0;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
@@ -540,46 +544,39 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	if (err)
 		goto out_dput;
 
-	whiteout = ovl_whiteout(workdir, dentry);
-	err = PTR_ERR(whiteout);
-	if (IS_ERR(whiteout))
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
 		goto out_unlock;
 
-	upper = ovl_dentry_upper(dentry);
-	if (!upper) {
-		upper = lookup_one_len(dentry->d_name.name, upperdir,
-				       dentry->d_name.len);
-		err = PTR_ERR(upper);
-		if (IS_ERR(upper))
-			goto kill_whiteout;
-
-		err = ovl_do_rename(wdir, whiteout, udir, upper, 0);
-		dput(upper);
-		if (err)
-			goto kill_whiteout;
-	} else {
-		int flags = 0;
+	err = -ESTALE;
+	if ((opaquedir && upper != opaquedir) ||
+	    (!opaquedir && ovl_dentry_upper(dentry) &&
+	     upper != ovl_dentry_upper(dentry))) {
+		goto out_dput_upper;
+	}
 
-		if (opaquedir)
-			upper = opaquedir;
-		err = -ESTALE;
-		if (upper->d_parent != upperdir)
-			goto kill_whiteout;
+	whiteout = ovl_whiteout(workdir, dentry);
+	err = PTR_ERR(whiteout);
+	if (IS_ERR(whiteout))
+		goto out_dput_upper;
 
-		if (is_dir)
-			flags |= RENAME_EXCHANGE;
+	if (d_is_dir(upper))
+		flags = RENAME_EXCHANGE;
 
-		err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
-		if (err)
-			goto kill_whiteout;
+	err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
+	if (err)
+		goto kill_whiteout;
+	if (flags)
+		ovl_cleanup(wdir, upper);
 
-		if (is_dir)
-			ovl_cleanup(wdir, upper);
-	}
 	ovl_dentry_version_inc(dentry->d_parent);
 out_d_drop:
 	d_drop(dentry);
 	dput(whiteout);
+out_dput_upper:
+	dput(upper);
 out_unlock:
 	unlock_rename(workdir, upperdir);
 out_dput:
@@ -596,21 +593,25 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
-	struct dentry *upper = ovl_dentry_upper(dentry);
+	struct dentry *upper;
 	int err;
 
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
+		goto out_unlock;
+
 	err = -ESTALE;
-	if (upper->d_parent == upperdir) {
-		/* Don't let d_delete() think it can reset d_inode */
-		dget(upper);
+	if (upper == ovl_dentry_upper(dentry)) {
 		if (is_dir)
 			err = vfs_rmdir(dir, upper);
 		else
 			err = vfs_unlink(dir, upper, NULL);
-		dput(upper);
 		ovl_dentry_version_inc(dentry->d_parent);
 	}
+	dput(upper);
 
 	/*
 	 * Keeping this dentry hashed would mean having to release
@@ -620,6 +621,7 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 */
 	if (!err)
 		d_drop(dentry);
+out_unlock:
 	mutex_unlock(&dir->i_mutex);
 
 	return err;
@@ -840,29 +842,39 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 	trap = lock_rename(new_upperdir, old_upperdir);
 
-	olddentry = ovl_dentry_upper(old);
-	newdentry = ovl_dentry_upper(new);
-	if (newdentry) {
+
+	olddentry = lookup_one_len(old->d_name.name, old_upperdir,
+				   old->d_name.len);
+	err = PTR_ERR(olddentry);
+	if (IS_ERR(olddentry))
+		goto out_unlock;
+
+	err = -ESTALE;
+	if (olddentry != ovl_dentry_upper(old))
+		goto out_dput_old;
+
+	newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+				   new->d_name.len);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out_dput_old;
+
+	err = -ESTALE;
+	if (ovl_dentry_upper(new)) {
 		if (opaquedir) {
-			newdentry = opaquedir;
-			opaquedir = NULL;
+			if (newdentry != opaquedir)
+				goto out_dput;
 		} else {
-			dget(newdentry);
+			if (newdentry != ovl_dentry_upper(new))
+				goto out_dput;
 		}
 	} else {
 		new_create = true;
-		newdentry = lookup_one_len(new->d_name.name, new_upperdir,
-					   new->d_name.len);
-		err = PTR_ERR(newdentry);
-		if (IS_ERR(newdentry))
-			goto out_unlock;
+		if (!d_is_negative(newdentry) &&
+		    (!new_opaque || !ovl_is_whiteout(newdentry)))
+			goto out_dput;
 	}
 
-	err = -ESTALE;
-	if (olddentry->d_parent != old_upperdir)
-		goto out_dput;
-	if (newdentry->d_parent != new_upperdir)
-		goto out_dput;
 	if (olddentry == trap)
 		goto out_dput;
 	if (newdentry == trap)
@@ -925,6 +937,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 out_dput:
 	dput(newdentry);
+out_dput_old:
+	dput(olddentry);
 out_unlock:
 	unlock_rename(new_upperdir, old_upperdir);
 out_revert_creds:
diff --git a/kernel/fs/overlayfs/inode.c b/kernel/fs/overlayfs/inode.c
index 05ac9a95e..220b04f04 100644
--- a/kernel/fs/overlayfs/inode.c
+++ b/kernel/fs/overlayfs/inode.c
@@ -63,6 +63,9 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	if (!err) {
 		upperdentry = ovl_dentry_upper(dentry);
 
+		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
+			attr->ia_valid &= ~ATTR_MODE;
+
 		mutex_lock(&upperdentry->d_inode->i_mutex);
 		err = notify_change(upperdentry, attr, NULL);
 		if (!err)
@@ -216,7 +219,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
 }
 
 
-static bool ovl_is_private_xattr(const char *name)
+bool ovl_is_private_xattr(const char *name)
 {
 	return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0;
 }
@@ -274,7 +277,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 	struct path realpath;
 	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
 	ssize_t res;
-	int off;
+	size_t len;
+	char *s;
 
 	res = vfs_listxattr(realpath.dentry, list, size);
 	if (res <= 0 || size == 0)
@@ -284,17 +288,19 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 		return res;
 
 	/* filter out private xattrs */
-	for (off = 0; off < res;) {
-		char *s = list + off;
-		size_t slen = strlen(s) + 1;
+	for (s = list, len = res; len;) {
+		size_t slen = strnlen(s, len) + 1;
 
-		BUG_ON(off + slen > res);
+		/* underlying fs providing us with an broken xattr list? */
+		if (WARN_ON(slen > len))
+			return -EIO;
 
+		len -= slen;
 		if (ovl_is_private_xattr(s)) {
 			res -= slen;
-			memmove(s, s + slen, res - off);
+			memmove(s, s + slen, len);
 		} else {
-			off += slen;
+			s += slen;
 		}
 	}
 
@@ -412,12 +418,11 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 	if (!inode)
 		return NULL;
 
-	mode &= S_IFMT;
-
 	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_flags |= S_NOATIME | S_NOCMTIME;
 
+	mode &= S_IFMT;
 	switch (mode) {
 	case S_IFDIR:
 		inode->i_private = oe;
diff --git a/kernel/fs/overlayfs/overlayfs.h b/kernel/fs/overlayfs/overlayfs.h
index e17154aea..c319d5eaa 100644
--- a/kernel/fs/overlayfs/overlayfs.h
+++ b/kernel/fs/overlayfs/overlayfs.h
@@ -174,6 +174,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 int ovl_removexattr(struct dentry *dentry, const char *name);
 struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
+bool ovl_is_private_xattr(const char *name);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 			    struct ovl_entry *oe);
@@ -181,6 +182,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to)
 {
 	to->i_uid = from->i_uid;
 	to->i_gid = from->i_gid;
+	to->i_mode = from->i_mode;
 }
 
 /* dir.c */
diff --git a/kernel/fs/overlayfs/super.c b/kernel/fs/overlayfs/super.c
index 000b2ed05..d70208c0d 100644
--- a/kernel/fs/overlayfs/super.c
+++ b/kernel/fs/overlayfs/super.c
@@ -276,6 +276,37 @@ static void ovl_dentry_release(struct dentry *dentry)
 	}
 }
 
+static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode)
+{
+	struct dentry *real;
+
+	if (d_is_dir(dentry)) {
+		if (!inode || inode == d_inode(dentry))
+			return dentry;
+		goto bug;
+	}
+
+	real = ovl_dentry_upper(dentry);
+	if (real && (!inode || inode == d_inode(real)))
+		return real;
+
+	real = ovl_dentry_lower(dentry);
+	if (!real)
+		goto bug;
+
+	if (!inode || inode == d_inode(real))
+		return real;
+
+	/* Handle recursion */
+	if (real->d_flags & DCACHE_OP_REAL)
+		return real->d_op->d_real(real, inode);
+
+bug:
+	WARN(1, "ovl_d_real(%pd4, %s:%lu\n): real dentry not found\n", dentry,
+	     inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0);
+	return dentry;
+}
+
 static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
@@ -320,11 +351,13 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
 static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
 	.d_select_inode = ovl_d_select_inode,
+	.d_real = ovl_d_real,
 };
 
 static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_release = ovl_dentry_release,
 	.d_select_inode = ovl_d_select_inode,
+	.d_real = ovl_d_real,
 	.d_revalidate = ovl_dentry_revalidate,
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
@@ -343,7 +376,8 @@ static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
 static bool ovl_dentry_remote(struct dentry *dentry)
 {
 	return dentry->d_flags &
-		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE);
+		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
+		 DCACHE_OP_REAL);
 }
 
 static bool ovl_dentry_weird(struct dentry *dentry)
@@ -729,6 +763,10 @@ retry:
 		struct kstat stat = {
 			.mode = S_IFDIR | 0,
 		};
+		struct iattr attr = {
+			.ia_valid = ATTR_MODE,
+			.ia_mode = stat.mode,
+		};
 
 		if (work->d_inode) {
 			err = -EEXIST;
@@ -744,6 +782,21 @@ retry:
 		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
 		if (err)
 			goto out_dput;
+
+		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
+			goto out_dput;
+
+		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
+			goto out_dput;
+
+		/* Clear any inherited mode bits */
+		inode_lock(work->d_inode);
+		err = notify_change(work, &attr, NULL);
+		inode_unlock(work->d_inode);
+		if (err)
+			goto out_dput;
 	}
 out_unlock:
 	mutex_unlock(&dir->i_mutex);