[overlayfs/port] overlayfs: v13 port attempt to kernel 3.5

[Andrew Watts <akwatts@ymail.com>]

[-- Attachment #1: Type: text/plain, Size: 563 bytes --]

Hi.

I am trying to port the recent work of Andy Whitcroft (for kernel 3.4)
to kernel 3.5.

Due to changes in *__dentry_open in fs/open.c and to the inode_operations
struct, overlayfs v13 doesn't apply cleanly.

I am attaching consolidated diffs for both fs/open.c and include/linux/fs.h,
which contain the substantive changes I made to Andy's work, for review. 

Please point out any errors I might have made.

I've not attached the changes I made to the patches against the Locking and
vfs.txt documentation as those weren't substantive.

Many thanks,

~ Andy


[-- Attachment #2: overlayfs-v13-3.5.diff --]
[-- Type: text/plain, Size: 6121 bytes --]

--- a/overlayfs2/fs/open.c	2012-08-16
+++ b/overlayfs2/fs/open.c	2012-08-16
@@ -667,7 +667,7 @@ int open_check_o_direct(struct file *f)
 	return 0;
 }
 
-static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
+static struct file *do_dentry_open(struct path *path,
 				   struct file *f,
 				   int (*open)(struct inode *, struct file *),
 				   const struct cred *cred)
@@ -676,15 +676,16 @@ static struct file *do_dentry_open(struc
 	struct inode *inode;
 	int error;
 
+	path_get(path);
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
 
 	if (unlikely(f->f_flags & O_PATH))
 		f->f_mode = FMODE_PATH;
 
-	inode = dentry->d_inode;
+	inode = path->dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
-		error = __get_file_write_access(inode, mnt);
+		error = __get_file_write_access(inode, path->mnt);
 		if (error)
 			goto cleanup_file;
 		if (!special_file(inode->i_mode))
@@ -692,8 +693,7 @@ static struct file *do_dentry_open(struc
 	}
 
 	f->f_mapping = inode->i_mapping;
-	f->f_path.dentry = dentry;
-	f->f_path.mnt = mnt;
+	f->f_path = *path;
 	f->f_pos = 0;
 	file_sb_list_add(f, inode->i_sb);
 
@@ -740,24 +740,23 @@ cleanup_all:
 			 * here, so just reset the state.
 			 */
 			file_reset_write(f);
-			mnt_drop_write(mnt);
+			mnt_drop_write(path->mnt);
 		}
 	}
 	file_sb_list_del(f);
 	f->f_path.dentry = NULL;
 	f->f_path.mnt = NULL;
 cleanup_file:
-	dput(dentry);
-	mntput(mnt);
+	path_put(path);
 	return ERR_PTR(error);
 }
 
-static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
+static struct file *__dentry_open(struct path *path,
 				struct file *f,
 				int (*open)(struct inode *, struct file *),
 				const struct cred *cred)
 {
-	struct file *res = do_dentry_open(dentry, mnt, f, open, cred);
+	struct file *res = do_dentry_open(path, mnt, f, open, cred);
 	if (!IS_ERR(res)) {
 		int error = open_check_o_direct(f);
 		if (error) {
@@ -792,14 +791,14 @@ static struct file *__dentry_open(struct
 struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
 		int (*open)(struct inode *, struct file *))
 {
+	struct path path = { .dentry = dentry, .mnt = nd->path.mnt };
 	const struct cred *cred = current_cred();
 
 	if (IS_ERR(nd->intent.open.file))
 		goto out;
 	if (IS_ERR(dentry))
 		goto out_err;
-	nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
-					     nd->intent.open.file,
+	nd->intent.open.file = __dentry_open(&path, nd->intent.open.file,
 					     open, cred);
 out:
 	return nd->intent.open.file;
@@ -831,9 +830,7 @@ struct file *nameidata_to_filp(struct na
 	} else {
 		struct file *res;
 
-		path_get(&nd->path);
-		res = do_dentry_open(nd->path.dentry, nd->path.mnt,
-				     filp, NULL, cred);
+		res = vfs_open(&nd->path, filp, cred);
 		if (!IS_ERR(res)) {
 			int error;
 
@@ -860,27 +857,48 @@ struct file *nameidata_to_filp(struct na
 struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
 			 const struct cred *cred)
 {
-	int error;
 	struct file *f;
+	struct file *ret;
+	struct path path = { .dentry = dentry, .mnt = mnt };
 
 	validate_creds(cred);
 
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!mnt);
 
-	error = -ENFILE;
+	ret = ERR_PTR(-ENFILE);
 	f = get_empty_filp();
-	if (f == NULL) {
-		dput(dentry);
-		mntput(mnt);
-		return ERR_PTR(error);
+	if (f != NULL) {
+		f->f_flags = flags;
+		ret = vfs_open(&path, f, cred);
 	}
+	path_put(&path);
 
-	f->f_flags = flags;
-	return __dentry_open(dentry, mnt, f, NULL, cred);
+	return ret;
 }
 EXPORT_SYMBOL(dentry_open);
 
+/**
+ * vfs_open - open the file at the given path
+ * @path: path to open
+ * @filp: newly allocated file with f_flag initialized
+ * @cred: credentials to use
+ *
+ * Open the file.  If successful, the returned file will have acquired
+ * an additional reference for path.
+ */
+struct file *vfs_open(struct path *path, struct file *filp,
+		      const struct cred *cred)
+{
+	struct inode *inode = path->dentry->d_inode;
+
+	if (inode->i_op->open)
+		return inode->i_op->open(path->dentry, filp, cred);
+	else
+		return __dentry_open(path, filp, NULL, cred);
+}
+EXPORT_SYMBOL(vfs_open);
+
 static void __put_unused_fd(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = files_fdtable(files);
--- a/overlayfs2/include/linux/fs.h	2012-08-16
+++ b/overlayfs2/include/linux/fs.h	2012-08-16
@@ -499,6 +499,12 @@ struct iattr {
  */
 #include <linux/quota.h>
 
+/*
+ * Maximum number of layers of fs stack.  Needs to be limited to
+ * prevent kernel stack overflow
+ */
+#define FILESYSTEM_MAX_STACK_DEPTH 2
+
 /** 
  * enum positive_aop_returns - aop return codes with specific semantics
  *
@@ -1542,6 +1548,11 @@ struct super_block {
 
 	/* Being remounted read-only */
 	int s_readonly_remount;
+
+	/*
+	 * Indicates how deep in a filesystem stack this SB is
+	 */
+	int s_stack_depth;
 };
 
 /* superblock cache pruning functions */
@@ -1693,6 +1704,8 @@ struct inode_operations {
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
 	int (*update_time)(struct inode *, struct timespec *, int);
+	struct file *(*open) (struct dentry *, struct file *,
+			      const struct cred *);
 } ____cacheline_aligned;
 
 struct seq_file;
@@ -2057,6 +2070,7 @@ extern long do_sys_open(int dfd, const c
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
+extern struct file *vfs_open(struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
 				 const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
@@ -2249,6 +2263,7 @@ extern sector_t bmap(struct inode *, sec
 #endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int inode_permission(struct inode *, int);
+extern int inode_only_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);
 
 static inline bool execute_ok(struct inode *inode)