debugfs: prevent access to removed files' private data

Upon return of debugfs_remove()/debugfs_remove_recursive(), it might
still be attempted to access associated private file data through
previously opened struct file objects. If that data has been freed by
the caller of debugfs_remove*() in the meanwhile, the reading/writing
process would either encounter a fault or, if the memory address in
question has been reassigned again, unrelated data structures could get
overwritten.

However, since debugfs files are seldomly removed, usually from module
exit handlers only, the impact is very low.

Currently, there are ~1000 call sites of debugfs_create_file() spread
throughout the whole tree and touching all of those struct file_operations
in order to make them file removal aware by means of checking the result of
debugfs_use_file_start() from within their methods is unfeasible.

Instead, wrap the struct file_operations by a lifetime managing proxy at
file open:
- In debugfs_create_file(), the original fops handed in has got stashed
  away in ->d_fsdata already.
- In debugfs_create_file(), install a proxy file_operations factory,
  debugfs_full_proxy_file_operations, at ->i_fop.

This proxy factory has got an ->open() method only. It carries out some
lifetime checks and if successful, dynamically allocates and sets up a new
struct file_operations proxy at ->f_op. Afterwards, it forwards to the
->open() of the original struct file_operations in ->d_fsdata, if any.

The dynamically set up proxy at ->f_op has got a lifetime managing wrapper
set for each of the methods defined in the original struct file_operations
in ->d_fsdata.

Its ->release()er frees the proxy again and forwards to the original
->release(), if any.

In order not to mislead the VFS layer, it is strictly necessary to leave
those fields blank in the proxy that have been NULL in the original
struct file_operations also, i.e. aren't supported. This is why there is a
need for dynamically allocated proxies. The choice made not to allocate a
proxy instance for every dentry at file creation, but for every
struct file object instantiated thereof is justified by the expected usage
pattern of debugfs, namely that in general very few files get opened more
than once at a time.

The wrapper methods set in the struct file_operations implement lifetime
managing by means of the SRCU protection facilities already in place for
debugfs:
They set up a SRCU read side critical section and check whether the dentry
is still alive by means of debugfs_use_file_start(). If so, they forward
the call to the original struct file_operation stored in ->d_fsdata, still
under the protection of the SRCU read side critical section.
This SRCU read side critical section prevents any pending debugfs_remove()
and friends to return to their callers. Since a file's private data must
only be freed after the return of debugfs_remove(), the ongoing proxied
call is guarded against any file removal race.

If, on the other hand, the initial call to debugfs_use_file_start() detects
that the dentry is dead, the wrapper simply returns -EIO and does not
forward the call. Note that the ->poll() wrapper is special in that its
signature does not allow for the return of arbitrary -EXXX values and thus,
POLLHUP is returned here.

In order not to pollute debugfs with wrapper definitions that aren't ever
needed, I chose not to define a wrapper for every struct file_operations
method possible. Instead, a wrapper is defined only for the subset of
methods which are actually set by any debugfs users.
Currently, these are:

  ->llseek()
  ->read()
  ->write()
  ->unlocked_ioctl()
  ->poll()

The ->release() wrapper is special in that it does not protect the original
->release() in any way from dead files in order not to leak resources.
Thus, any ->release() handed to debugfs must implement file lifetime
management manually, if needed.
For only 33 out of a total of 434 releasers handed in to debugfs, it could
not be verified immediately whether they access data structures that might
have been freed upon a debugfs_remove() return in the meanwhile.

Export debugfs_use_file_start() and debugfs_use_file_finish() in order to
allow any ->release() to manually implement file lifetime management.

For a set of common cases of struct file_operations implemented by the
debugfs_core itself, future patches will incorporate file lifetime
management directly within those in order to allow for their unproxied
operation. Rename the original, non-proxying "debugfs_create_file()" to
"debugfs_create_file_unsafe()" and keep it for future internal use by
debugfs itself. Factor out code common to both into the new
__debugfs_create_file().

Signed-off-by: Nicolai Stange <nicstange@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

fs/debugfs/file.c

@@ -23,9 +23,12 @@
 #include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/srcu.h>
+#include <asm/poll.h>
 
 #include "internal.h"
 
+struct poll_table_struct;
+
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
 {
@@ -66,7 +69,7 @@ const struct file_operations debugfs_noop_file_operations = {
  * debugfs_use_file_start() must be followed by a matching call
  * to debugfs_use_file_finish().
  */
-static int debugfs_use_file_start(const struct dentry *dentry, int *srcu_idx)
+int debugfs_use_file_start(const struct dentry *dentry, int *srcu_idx)
 	__acquires(&debugfs_srcu)
 {
 	*srcu_idx = srcu_read_lock(&debugfs_srcu);
@@ -75,6 +78,7 @@ static int debugfs_use_file_start(const struct dentry *dentry, int *srcu_idx)
 		return -EIO;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(debugfs_use_file_start);
 
 /**
  * debugfs_use_file_finish - mark the end of file data access
@@ -85,10 +89,11 @@ static int debugfs_use_file_start(const struct dentry *dentry, int *srcu_idx)
  * debugfs_remove_recursive() blocked by a former call to
  * debugfs_use_file_start() to proceed and return to its caller.
  */
-static void debugfs_use_file_finish(int srcu_idx) __releases(&debugfs_srcu)
+void debugfs_use_file_finish(int srcu_idx) __releases(&debugfs_srcu)
 {
 	srcu_read_unlock(&debugfs_srcu, srcu_idx);
 }
+EXPORT_SYMBOL_GPL(debugfs_use_file_finish);
 
 #define F_DENTRY(filp) ((filp)->f_path.dentry)
 
@@ -131,6 +136,154 @@ const struct file_operations debugfs_open_proxy_file_operations = {
 	.open = open_proxy_open,
 };
 
+#define PROTO(args...) args
+#define ARGS(args...) args
+
+#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args)		\
+static ret_type full_proxy_ ## name(proto)				\
+{									\
+	const struct dentry *dentry = F_DENTRY(filp);			\
+	const struct file_operations *real_fops =			\
+		REAL_FOPS_DEREF(dentry);				\
+	int srcu_idx;							\
+	ret_type r;							\
+									\
+	r = debugfs_use_file_start(dentry, &srcu_idx);			\
+	if (likely(!r))						\
+		r = real_fops->name(args);				\
+	debugfs_use_file_finish(srcu_idx);				\
+	return r;							\
+}
+
+FULL_PROXY_FUNC(llseek, loff_t, filp,
+		PROTO(struct file *filp, loff_t offset, int whence),
+		ARGS(filp, offset, whence));
+
+FULL_PROXY_FUNC(read, ssize_t, filp,
+		PROTO(struct file *filp, char __user *buf, size_t size,
+			loff_t *ppos),
+		ARGS(filp, buf, size, ppos));
+
+FULL_PROXY_FUNC(write, ssize_t, filp,
+		PROTO(struct file *filp, const char __user *buf, size_t size,
+			loff_t *ppos),
+		ARGS(filp, buf, size, ppos));
+
+FULL_PROXY_FUNC(unlocked_ioctl, long, filp,
+		PROTO(struct file *filp, unsigned int cmd, unsigned long arg),
+		ARGS(filp, cmd, arg));
+
+static unsigned int full_proxy_poll(struct file *filp,
+				struct poll_table_struct *wait)
+{
+	const struct dentry *dentry = F_DENTRY(filp);
+	const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry);
+	int srcu_idx;
+	unsigned int r = 0;
+
+	if (debugfs_use_file_start(dentry, &srcu_idx)) {
+		debugfs_use_file_finish(srcu_idx);
+		return POLLHUP;
+	}
+
+	r = real_fops->poll(filp, wait);
+	debugfs_use_file_finish(srcu_idx);
+	return r;
+}
+
+static int full_proxy_release(struct inode *inode, struct file *filp)
+{
+	const struct dentry *dentry = F_DENTRY(filp);
+	const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry);
+	const struct file_operations *proxy_fops = filp->f_op;
+	int r = 0;
+
+	/*
+	 * We must not protect this against removal races here: the
+	 * original releaser should be called unconditionally in order
+	 * not to leak any resources. Releasers must not assume that
+	 * ->i_private is still being meaningful here.
+	 */
+	if (real_fops->release)
+		r = real_fops->release(inode, filp);
+
+	replace_fops(filp, d_inode(dentry)->i_fop);
+	kfree((void *)proxy_fops);
+	fops_put(real_fops);
+	return 0;
+}
+
+static void __full_proxy_fops_init(struct file_operations *proxy_fops,
+				const struct file_operations *real_fops)
+{
+	proxy_fops->release = full_proxy_release;
+	if (real_fops->llseek)
+		proxy_fops->llseek = full_proxy_llseek;
+	if (real_fops->read)
+		proxy_fops->read = full_proxy_read;
+	if (real_fops->write)
+		proxy_fops->write = full_proxy_write;
+	if (real_fops->poll)
+		proxy_fops->poll = full_proxy_poll;
+	if (real_fops->unlocked_ioctl)
+		proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl;
+}
+
+static int full_proxy_open(struct inode *inode, struct file *filp)
+{
+	const struct dentry *dentry = F_DENTRY(filp);
+	const struct file_operations *real_fops = NULL;
+	struct file_operations *proxy_fops = NULL;
+	int srcu_idx, r;
+
+	r = debugfs_use_file_start(dentry, &srcu_idx);
+	if (r) {
+		r = -ENOENT;
+		goto out;
+	}
+
+	real_fops = REAL_FOPS_DEREF(dentry);
+	real_fops = fops_get(real_fops);
+	if (!real_fops) {
+		/* Huh? Module did not cleanup after itself at exit? */
+		WARN(1, "debugfs file owner did not clean up at exit: %pd",
+			dentry);
+		r = -ENXIO;
+		goto out;
+	}
+
+	proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL);
+	if (!proxy_fops) {
+		r = -ENOMEM;
+		goto free_proxy;
+	}
+	__full_proxy_fops_init(proxy_fops, real_fops);
+	replace_fops(filp, proxy_fops);
+
+	if (real_fops->open) {
+		r = real_fops->open(inode, filp);
+
+		if (filp->f_op != proxy_fops) {
+			/* No protection against file removal anymore. */
+			WARN(1, "debugfs file owner replaced proxy fops: %pd",
+				dentry);
+			goto free_proxy;
+		}
+	}
+
+	goto out;
+free_proxy:
+	kfree(proxy_fops);
+	fops_put(real_fops);
+out:
+	debugfs_use_file_finish(srcu_idx);
+	return r;
+}
+
+const struct file_operations debugfs_full_proxy_file_operations = {
+	.open = full_proxy_open,
+};
+
 static struct dentry *debugfs_create_mode(const char *name, umode_t mode,
 					  struct dentry *parent, void *value,
 				          const struct file_operations *fops,

fs/debugfs/inode.c

@@ -300,6 +300,37 @@ static struct dentry *end_creating(struct dentry *dentry)
 	return dentry;
 }
 
+static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
+				struct dentry *parent, void *data,
+				const struct file_operations *proxy_fops,
+				const struct file_operations *real_fops)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	if (!(mode & S_IFMT))
+		mode |= S_IFREG;
+	BUG_ON(!S_ISREG(mode));
+	dentry = start_creating(name, parent);
+
+	if (IS_ERR(dentry))
+		return NULL;
+
+	inode = debugfs_get_inode(dentry->d_sb);
+	if (unlikely(!inode))
+		return failed_creating(dentry);
+
+	inode->i_mode = mode;
+	inode->i_private = data;
+
+	inode->i_fop = proxy_fops;
+	dentry->d_fsdata = (void *)real_fops;
+
+	d_instantiate(dentry, inode);
+	fsnotify_create(d_inode(dentry->d_parent), dentry);
+	return end_creating(dentry);
+}
+
 /**
  * debugfs_create_file - create a file in the debugfs filesystem
  * @name: a pointer to a string containing the name of the file to create.
@@ -330,34 +361,25 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
-	struct dentry *dentry;
-	struct inode *inode;
 
-	if (!(mode & S_IFMT))
+	return __debugfs_create_file(name, mode, parent, data,
-		mode |= S_IFREG;
+				fops ? &debugfs_full_proxy_file_operations :
-	BUG_ON(!S_ISREG(mode));
+					&debugfs_noop_file_operations,
-	dentry = start_creating(name, parent);
+				fops);
-
-	if (IS_ERR(dentry))
-		return NULL;
-
-	inode = debugfs_get_inode(dentry->d_sb);
-	if (unlikely(!inode))
-		return failed_creating(dentry);
-
-	inode->i_mode = mode;
-	inode->i_private = data;
-
-	inode->i_fop = fops ? &debugfs_open_proxy_file_operations
-		: &debugfs_noop_file_operations;
-	dentry->d_fsdata = (void *)fops;
-
-	d_instantiate(dentry, inode);
-	fsnotify_create(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file);
 
+struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
+				   struct dentry *parent, void *data,
+				   const struct file_operations *fops)
+{
+
+	return __debugfs_create_file(name, mode, parent, data,
+				fops ? &debugfs_open_proxy_file_operations :
+					&debugfs_noop_file_operations,
+				fops);
+}
+
 /**
  * debugfs_create_file_size - create a file in the debugfs filesystem
  * @name: a pointer to a string containing the name of the file to create.
@@ -579,6 +601,7 @@ void debugfs_remove(struct dentry *dentry)
 	inode_unlock(d_inode(parent));
 	if (!ret)
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+
 	synchronize_srcu(&debugfs_srcu);
 }
 EXPORT_SYMBOL_GPL(debugfs_remove);
@@ -657,6 +680,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	if (!__debugfs_remove(child, parent))
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	inode_unlock(d_inode(parent));
+
 	synchronize_srcu(&debugfs_srcu);
 }
 EXPORT_SYMBOL_GPL(debugfs_remove_recursive);

fs/debugfs/internal.h

@@ -13,12 +13,14 @@
 #define _DEBUGFS_INTERNAL_H_
 
 struct file_operations;
-struct srcu_struct;
 
 /* declared over in file.c */
 extern const struct file_operations debugfs_noop_file_operations;
 extern const struct file_operations debugfs_open_proxy_file_operations;
+extern const struct file_operations debugfs_full_proxy_file_operations;
 
-extern struct srcu_struct debugfs_srcu;
+struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
+					struct dentry *parent, void *data,
+					const struct file_operations *fops);
 
 #endif /* _DEBUGFS_INTERNAL_H_ */

include/linux/debugfs.h

@@ -19,9 +19,11 @@
 #include <linux/seq_file.h>
 
 #include <linux/types.h>
+#include <linux/compiler.h>
 
 struct device;
 struct file_operations;
+struct srcu_struct;
 
 struct debugfs_blob_wrapper {
 	void *data;
@@ -41,6 +43,8 @@ struct debugfs_regset32 {
 
 extern struct dentry *arch_debugfs_dir;
 
+extern struct srcu_struct debugfs_srcu;
+
 #if defined(CONFIG_DEBUG_FS)
 
 struct dentry *debugfs_create_file(const char *name, umode_t mode,
@@ -65,6 +69,11 @@ struct dentry *debugfs_create_automount(const char *name,
 void debugfs_remove(struct dentry *dentry);
 void debugfs_remove_recursive(struct dentry *dentry);
 
+int debugfs_use_file_start(const struct dentry *dentry, int *srcu_idx)
+	__acquires(&debugfs_srcu);
+
+void debugfs_use_file_finish(int srcu_idx) __releases(&debugfs_srcu);
+
 struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
                 struct dentry *new_dir, const char *new_name);
 
@@ -173,6 +182,17 @@ static inline void debugfs_remove(struct dentry *dentry)
 static inline void debugfs_remove_recursive(struct dentry *dentry)
 { }
 
+static inline int debugfs_use_file_start(const struct dentry *dentry,
+					int *srcu_idx)
+	__acquires(&debugfs_srcu)
+{
+	return 0;
+}
+
+static inline void debugfs_use_file_finish(int srcu_idx)
+	__releases(&debugfs_srcu)
+{ }
+
 static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
                 struct dentry *new_dir, char *new_name)
 {