[PATCH stable/linux-5.10.y 0/7] Backport Fix incorrect overlayfs mmap() and mprotect() LSM access controls

[PATCH stable/linux-5.10.y 0/7] Backport Fix incorrect overlayfs mmap() and mprotect() LSM access controls

[Cai Xinchen]

ackport the patch series
"Fix incorrect overlayfs mmap() and mprotect() LSM access controls" [1]
to 5.10 lts

I test selinux-testsuite[2] overlay test, it pass 135 tests.

[1] https://lore.kernel.org/all/20260403030848.731867-5-paul@paul-moore.com/
[2] https://github.com/SELinuxProject/selinux-testsuite

Amir Goldstein (4):
  ovl: pass layer mnt to ovl_open_realfile()
  fs: move kmem_cache_zalloc() into alloc_empty_file*() helpers
  fs: use backing_file container for internal files with "fake" f_path
  fs: prepare for adding LSM blob to backing_file

Khadija Kamran (1):
  lsm: constify the 'file' parameter in security_binder_transfer_file()

Paul Moore (2):
  lsm: add backing_file LSM hooks
  selinux: fix overlayfs mmap() and mprotect() access checks

 fs/file_table.c                   | 125 +++++++++++++--
 fs/internal.h                     |   6 +-
 fs/open.c                         |  46 ++++--
 fs/overlayfs/file.c               |  32 ++--
 fs/overlayfs/overlayfs.h          |   1 +
 fs/overlayfs/util.c               |  14 ++
 include/linux/fs.h                |  46 +++++-
 include/linux/lsm_audit.h         |   2 +-
 include/linux/lsm_hook_defs.h     |   7 +-
 include/linux/lsm_hooks.h         |   1 +
 include/linux/security.h          |  26 ++-
 security/security.c               | 112 ++++++++++++-
 security/selinux/hooks.c          | 252 ++++++++++++++++++++++--------
 security/selinux/include/objsec.h |  11 ++
 14 files changed, 560 insertions(+), 121 deletions(-)

-- 
2.18.0.huawei.25

[PATCH stable/linux-5.10.y 1/7] ovl: pass layer mnt to ovl_open_realfile()

[Cai Xinchen]

From: Amir Goldstein <amir73il@gmail.com>

[ Upstream commit 1248ea4b91bcdafefdb025087e67d58382cfc9eb ]

Ensure that ovl_open_realfile() takes the mount's idmapping into
account. We add a new helper ovl_path_realdata() that can be used to
easily retrieve the relevant path which we can pass down. This is needed
to support idmapped base layers with overlay.

Cc: <linux-unionfs@vger.kernel.org>
Tested-by: Giuseppe Scrivano <gscrivan@redhat.com>
Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 fs/overlayfs/file.c      | 22 +++++++++++++---------
 fs/overlayfs/overlayfs.h |  1 +
 fs/overlayfs/util.c      | 14 ++++++++++++++
 3 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4440ff43cb66..343db8b3ecd6 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -37,8 +37,9 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 #define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY)
 
 static struct file *ovl_open_realfile(const struct file *file,
-				      struct inode *realinode)
+				      struct path *realpath)
 {
+	struct inode *realinode = d_inode(realpath->dentry);
 	struct inode *inode = file_inode(file);
 	struct file *realfile;
 	const struct cred *old_cred;
@@ -103,21 +104,21 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
 			       bool allow_meta)
 {
-	struct inode *inode = file_inode(file);
-	struct inode *realinode;
+	struct dentry *dentry = file_dentry(file);
+	struct path realpath;
 
 	real->flags = 0;
 	real->file = file->private_data;
 
 	if (allow_meta)
-		realinode = ovl_inode_real(inode);
+		ovl_path_real(dentry, &realpath);
 	else
-		realinode = ovl_inode_realdata(inode);
+		ovl_path_realdata(dentry, &realpath);
 
 	/* Has it been copied up since we'd opened it? */
-	if (unlikely(file_inode(real->file) != realinode)) {
+	if (unlikely(file_inode(real->file) != d_inode(realpath.dentry))) {
 		real->flags = FDPUT_FPUT;
-		real->file = ovl_open_realfile(file, realinode);
+		real->file = ovl_open_realfile(file, &realpath);
 
 		return PTR_ERR_OR_ZERO(real->file);
 	}
@@ -143,17 +144,20 @@ static int ovl_real_fdget(const struct file *file, struct fd *real)
 
 static int ovl_open(struct inode *inode, struct file *file)
 {
+	struct dentry *dentry = file_dentry(file);
 	struct file *realfile;
+	struct path realpath;
 	int err;
 
-	err = ovl_maybe_copy_up(file_dentry(file), file->f_flags);
+	err = ovl_maybe_copy_up(dentry, file->f_flags);
 	if (err)
 		return err;
 
 	/* No longer need these flags, so don't pass them on to underlying fs */
 	file->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
-	realfile = ovl_open_realfile(file, ovl_inode_realdata(inode));
+	ovl_path_realdata(dentry, &realpath);
+	realfile = ovl_open_realfile(file, &realpath);
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 5ac968f709a4..5b8a1c9bc355 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -274,6 +274,7 @@ void ovl_path_upper(struct dentry *dentry, struct path *path);
 void ovl_path_lower(struct dentry *dentry, struct path *path);
 void ovl_path_lowerdata(struct dentry *dentry, struct path *path);
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
+enum ovl_path_type ovl_path_realdata(struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_lowerdata(struct dentry *dentry);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 26f29a3e5ada..431dfe3db0cc 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -209,6 +209,20 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
 	return type;
 }
 
+enum ovl_path_type ovl_path_realdata(struct dentry *dentry, struct path *path)
+{
+	enum ovl_path_type type = ovl_path_type(dentry);
+
+	WARN_ON_ONCE(d_is_dir(dentry));
+
+	if (!OVL_TYPE_UPPER(type) || OVL_TYPE_MERGE(type))
+		ovl_path_lowerdata(dentry, path);
+	else
+		ovl_path_upper(dentry, path);
+
+	return type;
+}
+
 struct dentry *ovl_dentry_upper(struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 1/7] ovl: pass layer mnt to ovl_open_realfile()

[sashiko-bot]

> From: Amir Goldstein <amir73il@gmail.com>
> 
> [ Upstream commit 1248ea4b91bcdafefdb025087e67d58382cfc9eb ]
> 
> Ensure that ovl_open_realfile() takes the mount's idmapping into
> account. We add a new helper ovl_path_realdata() that can be used to
> easily retrieve the relevant path which we can pass down. This is needed
> to support idmapped base layers with overlay.
> 
> Cc: <linux-unionfs@vger.kernel.org>
> Tested-by: Giuseppe Scrivano <gscrivan@redhat.com>
> Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
> Signed-off-by: Amir Goldstein <amir73il@gmail.com>
> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
> Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=1

[PATCH stable/linux-5.10.y 2/7] fs: move kmem_cache_zalloc() into alloc_empty_file*() helpers

[Cai Xinchen]

From: Amir Goldstein <amir73il@gmail.com>

[ Upstream commit 8a05a8c31d06c5d0d67b273a4a00f87269adde82 ]

Use a common helper init_file() instead of __alloc_file() for
alloc_empty_file*() helpers and improrve the documentation.

This is needed for a follow up patch that allocates a backing_file
container.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Message-Id: <20230615112229.2143178-4-amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 fs/file_table.c | 41 ++++++++++++++++++++++++++---------------
 1 file changed, 26 insertions(+), 15 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 7a3b4a7f6808..be24d724b407 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -93,20 +93,15 @@ int proc_nr_files(struct ctl_table *table, int write,
 }
 #endif
 
-static struct file *__alloc_file(int flags, const struct cred *cred)
+static int init_file(struct file *f, int flags, const struct cred *cred)
 {
-	struct file *f;
 	int error;
 
-	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
-	if (unlikely(!f))
-		return ERR_PTR(-ENOMEM);
-
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
 		file_free_rcu(&f->f_u.fu_rcuhead);
-		return ERR_PTR(error);
+		return error;
 	}
 
 	atomic_long_set(&f->f_count, 1);
@@ -118,7 +113,7 @@ static struct file *__alloc_file(int flags, const struct cred *cred)
 	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
 
-	return f;
+	return 0;
 }
 
 /* Find an unused file structure and return a pointer to it.
@@ -135,6 +130,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
 	static long old_max;
 	struct file *f;
+	int error;
 
 	/*
 	 * Privileged users can go above max_files
@@ -148,9 +144,15 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
 			goto over;
 	}
 
-	f = __alloc_file(flags, cred);
-	if (!IS_ERR(f))
-		percpu_counter_inc(&nr_files);
+	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
+	if (unlikely(!f))
+		return ERR_PTR(-ENOMEM);
+
+	error = init_file(f, flags, cred);
+	if (unlikely(error))
+		return ERR_PTR(error);
+
+	percpu_counter_inc(&nr_files);
 
 	return f;
 
@@ -166,14 +168,23 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
 /*
  * Variant of alloc_empty_file() that doesn't check and modify nr_files.
  *
- * Should not be used unless there's a very good reason to do so.
+ * This is only for kernel internal use, and the allocate file must not be
+ * installed into file tables or such.
  */
 struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 {
-	struct file *f = __alloc_file(flags, cred);
+	struct file *f;
+	int error;
+
+	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
+	if (unlikely(!f))
+		return ERR_PTR(-ENOMEM);
+
+	error = init_file(f, flags, cred);
+	if (unlikely(error))
+		return ERR_PTR(error);
 
-	if (!IS_ERR(f))
-		f->f_mode |= FMODE_NOACCOUNT;
+	f->f_mode |= FMODE_NOACCOUNT;
 
 	return f;
 }
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 2/7] fs: move kmem_cache_zalloc() into alloc_empty_file*() helpers

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] API trap leading to cross-allocator slab corruption when handling errors in `init_file()`.
--

commit 4291ff6cf97e536c82d7fa5b99705d5c988c0fac
Author: Amir Goldstein <amir73il@gmail.com>

fs: move kmem_cache_zalloc() into alloc_empty_file*() helpers

Use a common helper init_file() instead of __alloc_file() for
alloc_empty_file*() helpers and improrve the documentation.

This is needed for a follow up patch that allocates a backing_file
container.

> diff --git a/fs/file_table.c b/fs/file_table.c
> index 7a3b4a7f68086..be24d724b4075 100644
> --- a/fs/file_table.c
> +++ b/fs/file_table.c
> @@ -93,20 +93,15 @@ int proc_nr_files(struct ctl_table *table, int write,
[ ... ]
> -static struct file *__alloc_file(int flags, const struct cred *cred)
> +static int init_file(struct file *f, int flags, const struct cred *cred)
>  {
> -	struct file *f;
>  	int error;
>  
> -	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
> -	if (unlikely(!f))
> -		return ERR_PTR(-ENOMEM);
> -
>  	f->f_cred = get_cred(cred);
>  	error = security_file_alloc(f);
>  	if (unlikely(error)) {
>  		file_free_rcu(&f->f_u.fu_rcuhead);
> -		return ERR_PTR(error);
> +		return error;
>  	}

[Severity: High]
If a follow-up patch allocates a struct backing_file container using kzalloc()
and passes its file field to init_file(), could this error path lead to
cross-allocator slab corruption?

Because file_free_rcu() checks f->f_mode & FMODE_BACKING to decide whether to
use kfree() or kmem_cache_free(filp_cachep, ...), it seems FMODE_BACKING would
need to be set before calling init_file() to ensure safe cleanup if
security_file_alloc() fails.

>  
>  	atomic_long_set(&f->f_count, 1);
>  	rwlock_init(&f->f_owner.lock);
>  	spin_lock_init(&f->f_lock);
>  	mutex_init(&f->f_pos_lock);
>  	eventpoll_init_file(f);
>  	f->f_flags = flags;
>  	f->f_mode = OPEN_FMODE(flags);

[Severity: High]
However, since init_file() unconditionally overwrites f->f_mode here, the
caller cannot safely set FMODE_BACKING beforehand without it being
overwritten upon success.

Could this lead to kzalloc allocated memory being incorrectly freed to
filp_cachep if security_file_alloc() encounters an error (e.g., under
memory pressure or LSM denial)?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=2

[PATCH stable/linux-5.10.y 3/7] fs: use backing_file container for internal files with "fake" f_path

[Cai Xinchen]

From: Amir Goldstein <amir73il@gmail.com>

[ Upstream commit 62d53c4a1dfe347bd87ede46ffad38c9a3870338 ]

Overlayfs uses open_with_fake_path() to allocate internal kernel files,
with a "fake" path - whose f_path is not on the same fs as f_inode.

Allocate a container struct backing_file for those internal files, that
is used to hold the "fake" ovl path along with the real path.

backing_file_real_path() can be used to access the stored real path.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Message-Id: <20230615112229.2143178-5-amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 fs/file_table.c     | 50 +++++++++++++++++++++++++++++++++++++++++++--
 fs/internal.h       |  5 +++--
 fs/open.c           | 45 +++++++++++++++++++++++++++++-----------
 fs/overlayfs/file.c |  4 ++--
 include/linux/fs.h  | 33 +++++++++++++++++++++++++-----
 5 files changed, 114 insertions(+), 23 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index be24d724b407..6daef2e2b2ad 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -42,18 +42,40 @@ static struct kmem_cache *filp_cachep __read_mostly;
 
 static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
+/* Container for backing file with optional real path */
+struct backing_file {
+	struct file file;
+	struct path real_path;
+};
+
+static inline struct backing_file *backing_file(struct file *f)
+{
+	return container_of(f, struct backing_file, file);
+}
+
+struct path *backing_file_real_path(struct file *f)
+{
+	return &backing_file(f)->real_path;
+}
+EXPORT_SYMBOL_GPL(backing_file_real_path);
+
 static void file_free_rcu(struct rcu_head *head)
 {
 	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
 
 	put_cred(f->f_cred);
-	kmem_cache_free(filp_cachep, f);
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		kfree(backing_file(f));
+	else
+		kmem_cache_free(filp_cachep, f);
 }
 
 static inline void file_free(struct file *f)
 {
 	security_file_free(f);
-	if (!(f->f_mode & FMODE_NOACCOUNT))
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		path_put(backing_file_real_path(f));
+	if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
 		percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
@@ -189,6 +211,30 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 	return f;
 }
 
+/*
+ * Variant of alloc_empty_file() that allocates a backing_file container
+ * and doesn't check and modify nr_files.
+ *
+ * This is only for kernel internal use, and the allocate file must not be
+ * installed into file tables or such.
+ */
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
+{
+	struct backing_file *ff;
+	int error;
+
+	ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL);
+	if (unlikely(!ff))
+		return ERR_PTR(-ENOMEM);
+
+	error = init_file(&ff->file, flags, cred);
+	if (unlikely(error))
+		return ERR_PTR(error);
+
+	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
+	return &ff->file;
+}
+
 /**
  * alloc_file - allocate and initialize a 'struct file'
  *
diff --git a/fs/internal.h b/fs/internal.h
index 39193250a4ed..676e8a8da1c7 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -107,8 +107,9 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *alloc_empty_file(int, const struct cred *);
-extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
+struct file *alloc_empty_file(int flags, const struct cred *cred);
+struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
 
 /*
  * super.c
diff --git a/fs/open.c b/fs/open.c
index f081f09e411e..d6d5684dc919 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -997,23 +997,44 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 }
 EXPORT_SYMBOL(dentry_create);
 
-struct file *open_with_fake_path(const struct path *path, int flags,
-				struct inode *inode, const struct cred *cred)
+/**
+ * backing_file_open - open a backing file for kernel internal use
+ * @path:	path of the file to open
+ * @flags:	open flags
+ * @path:	path of the backing file
+ * @cred:	credentials for open
+ *
+ * Open a backing file for a stackable filesystem (e.g., overlayfs).
+ * @path may be on the stackable filesystem and backing inode on the
+ * underlying filesystem. In this case, we want to be able to return
+ * the @real_path of the backing inode. This is done by embedding the
+ * returned file into a container structure that also stores the path of
+ * the backing inode on the underlying filesystem, which can be
+ * retrieved using backing_file_real_path().
+ */
+struct file *backing_file_open(const struct path *path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred)
 {
-	struct file *f = alloc_empty_file_noaccount(flags, cred);
-	if (!IS_ERR(f)) {
-		int error;
+	struct file *f;
+	int error;
 
-		f->f_path = *path;
-		error = do_dentry_open(f, inode, NULL);
-		if (error) {
-			fput(f);
-			f = ERR_PTR(error);
-		}
+	f = alloc_empty_backing_file(flags, cred);
+	if (IS_ERR(f))
+		return f;
+
+	f->f_path = *path;
+	path_get(real_path);
+	*backing_file_real_path(f) = *real_path;
+	error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
+	if (error) {
+		fput(f);
+		f = ERR_PTR(error);
 	}
+
 	return f;
 }
-EXPORT_SYMBOL(open_with_fake_path);
+EXPORT_SYMBOL_GPL(backing_file_open);
 
 #define WILL_CREATE(flags)	(flags & (O_CREAT | __O_TMPFILE))
 #define O_PATH_FLAGS		(O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 343db8b3ecd6..460748b63806 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -58,8 +58,8 @@ static struct file *ovl_open_realfile(const struct file *file,
 		if (!inode_owner_or_capable(realinode))
 			flags &= ~O_NOATIME;
 
-		realfile = open_with_fake_path(&file->f_path, flags, realinode,
-					       current_cred());
+		realfile = backing_file_open(&file->f_path, flags, realpath,
+					     current_cred());
 	}
 	revert_creds(old_cred);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 11294a89a53b..acdc14542cbb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -163,6 +163,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is stream-like */
 #define FMODE_STREAM		((__force fmode_t)0x200000)
 
+/* File is embedded in backing_file object */
+#define FMODE_BACKING		((__force fmode_t)0x2000000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
@@ -2673,11 +2676,31 @@ extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
-extern struct file * dentry_open(const struct path *, int, const struct cred *);
-extern struct file *dentry_create(const struct path *path, int flags,
-				  umode_t mode, const struct cred *cred);
-extern struct file * open_with_fake_path(const struct path *, int,
-					 struct inode*, const struct cred *);
+struct file *dentry_open(const struct path *path, int flags,
+			 const struct cred *creds);
+struct file *dentry_create(const struct path *path, int flags, umode_t mode,
+			   const struct cred *cred);
+struct file *backing_file_open(const struct path *path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred);
+struct path *backing_file_real_path(struct file *f);
+
+/*
+ * file_real_path - get the path corresponding to f_inode
+ *
+ * When opening a backing file for a stackable filesystem (e.g.,
+ * overlayfs) f_path may be on the stackable filesystem and f_inode on
+ * the underlying filesystem.  When the path associated with f_inode is
+ * needed, this helper should be used instead of accessing f_path
+ * directly.
+*/
+static inline const struct path *file_real_path(struct file *f)
+{
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		return backing_file_real_path(f);
+	return &f->f_path;
+}
+
 static inline struct file *file_clone_open(struct file *file)
 {
 	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 3/7] fs: use backing_file container for internal files with "fake" f_path

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] If `init_file()` fails in `alloc_empty_backing_file()`, the `kzalloc`'d memory is incorrectly freed to `filp_cachep`, causing SLUB corruption.
- [Medium] The `backing_file` container allocation lacks `__GFP_ACCOUNT`, bypassing memcg memory accounting.
--

commit 253dd7739e2dba161f4b1907e20e7723d9f6a637
Author: Amir Goldstein <amir73il@gmail.com>

fs: use backing_file container for internal files with "fake" f_path

Overlayfs uses open_with_fake_path() to allocate internal kernel files.
This commit introduces a backing_file container to hold the fake ovl path
along with the real path.

> diff --git a/fs/file_table.c b/fs/file_table.c
> index be24d724b4075..6daef2e2b2ada 100644
> --- a/fs/file_table.c
> +++ b/fs/file_table.c
[ ... ]
> @@ -189,6 +211,30 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
>  	return f;
>  }
>  
> +/*
> + * Variant of alloc_empty_file() that allocates a backing_file container
> + * and doesn't check and modify nr_files.
> + *
> + * This is only for kernel internal use, and the allocate file must not be
> + * installed into file tables or such.
> + */
> +struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
> +{
> +	struct backing_file *ff;
> +	int error;
> +
> +	ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL);

[Severity: Medium]
Since this replaces an allocation that previously came from the filp_cachep
slab cache (which uses SLAB_ACCOUNT), should this kzalloc() include the
__GFP_ACCOUNT flag?

Without __GFP_ACCOUNT, this memory might bypass memcg accounting, allowing a
container to allocate kernel memory without being charged against its limit.

> +	if (unlikely(!ff))
> +		return ERR_PTR(-ENOMEM);
> +
> +	error = init_file(&ff->file, flags, cred);

[Severity: High]
If init_file() fails (for example, due to an error in security_file_alloc()),
it calls file_free_rcu().

Because FMODE_BACKING has not been set in f_mode yet, file_free_rcu() will
evaluate (f->f_mode & FMODE_BACKING) as false:

fs/file_table.c:file_free_rcu() {
    ...
    if (unlikely(f->f_mode & FMODE_BACKING))
        kfree(backing_file(f));
    else
        kmem_cache_free(filp_cachep, f);
}

Will this cause the kzalloc'd ff pointer to be incorrectly freed into the
filp_cachep slab cache, leading to SLUB corruption?

> +	if (unlikely(error))
> +		return ERR_PTR(error);
> +
> +	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
> +	return &ff->file;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=3

[PATCH stable/linux-5.10.y 4/7] lsm: constify the 'file' parameter in security_binder_transfer_file()

[Cai Xinchen]

From: Khadija Kamran <kamrankhadijadj@gmail.com>

[ Upstream commit 8e4672d6f902d5c4db1e87e8aa9f530149d85bc6 ]

SELinux registers the implementation for the "binder_transfer_file"
hook. Looking at the function implementation we observe that the
parameter "file" is not changing.

Mark the "file" parameter of LSM hook security_binder_transfer_file() as
"const" since it will not be changing in the LSM hook.

Signed-off-by: Khadija Kamran <kamrankhadijadj@gmail.com>
[PM: subject line whitespace fix]
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 include/linux/lsm_hook_defs.h | 2 +-
 include/linux/security.h      | 4 ++--
 security/security.c           | 2 +-
 security/selinux/hooks.c      | 8 ++++----
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 35bb13ce1faf..e34b295bc15a 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -32,7 +32,7 @@ LSM_HOOK(int, 0, binder_transaction, const struct cred *from,
 LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from,
 	 const struct cred *to)
 LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from,
-	 const struct cred *to, struct file *file)
+	 const struct cred *to, const struct file *file)
 LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child,
 	 unsigned int mode)
 LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent)
diff --git a/include/linux/security.h b/include/linux/security.h
index 2b8a00118903..f3c9d640b60b 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -264,7 +264,7 @@ int security_binder_transaction(const struct cred *from,
 int security_binder_transfer_binder(const struct cred *from,
 				    const struct cred *to);
 int security_binder_transfer_file(const struct cred *from,
-				  const struct cred *to, struct file *file);
+				  const struct cred *to, const struct file *file);
 int security_ptrace_access_check(struct task_struct *child, unsigned int mode);
 int security_ptrace_traceme(struct task_struct *parent);
 int security_capget(struct task_struct *target,
@@ -518,7 +518,7 @@ static inline int security_binder_transfer_binder(const struct cred *from,
 
 static inline int security_binder_transfer_file(const struct cred *from,
 						const struct cred *to,
-						struct file *file)
+						const struct file *file)
 {
 	return 0;
 }
diff --git a/security/security.c b/security/security.c
index 6de10b6699a4..d6b1b82094b7 100644
--- a/security/security.c
+++ b/security/security.c
@@ -744,7 +744,7 @@ int security_binder_transfer_binder(const struct cred *from,
 }
 
 int security_binder_transfer_file(const struct cred *from,
-				  const struct cred *to, struct file *file)
+				  const struct cred *to, const struct file *file)
 {
 	return call_int_hook(binder_transfer_file, 0, from, to, file);
 }
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 90935ed3d8d8..e1bbdef0bcd3 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1700,7 +1700,7 @@ static inline int file_path_has_perm(const struct cred *cred,
 }
 
 #ifdef CONFIG_BPF_SYSCALL
-static int bpf_fd_pass(struct file *file, u32 sid);
+static int bpf_fd_pass(const struct file *file, u32 sid);
 #endif
 
 /* Check whether a task can use an open file descriptor to
@@ -1972,7 +1972,7 @@ static inline u32 file_mask_to_av(int mode, int mask)
 }
 
 /* Convert a Linux file to an access vector. */
-static inline u32 file_to_av(struct file *file)
+static inline u32 file_to_av(const struct file *file)
 {
 	u32 av = 0;
 
@@ -2050,7 +2050,7 @@ static int selinux_binder_transfer_binder(const struct cred *from,
 
 static int selinux_binder_transfer_file(const struct cred *from,
 					const struct cred *to,
-					struct file *file)
+					const struct file *file)
 {
 	u32 sid = cred_sid(to);
 	struct file_security_struct *fsec = selinux_file(file);
@@ -6799,7 +6799,7 @@ static u32 bpf_map_fmode_to_av(fmode_t fmode)
  * access the bpf object and that's why we have to add this additional check in
  * selinux_file_receive and selinux_binder_transfer_files.
  */
-static int bpf_fd_pass(struct file *file, u32 sid)
+static int bpf_fd_pass(const struct file *file, u32 sid)
 {
 	struct bpf_security_struct *bpfsec;
 	struct bpf_prog *prog;
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 4/7] lsm: constify the 'file' parameter in security_binder_transfer_file()

[sashiko-bot]

> From: Khadija Kamran <kamrankhadijadj@gmail.com>
> 
> [ Upstream commit 8e4672d6f902d5c4db1e87e8aa9f530149d85bc6 ]
> 
> SELinux registers the implementation for the "binder_transfer_file"
> hook. Looking at the function implementation we observe that the
> parameter "file" is not changing.
> 
> Mark the "file" parameter of LSM hook security_binder_transfer_file() as
> "const" since it will not be changing in the LSM hook.
> 
> Signed-off-by: Khadija Kamran <kamrankhadijadj@gmail.com>
> [PM: subject line whitespace fix]
> Signed-off-by: Paul Moore <paul@paul-moore.com>
> Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=4

[PATCH stable/linux-5.10.y 5/7] fs: prepare for adding LSM blob to backing_file

[Cai Xinchen]

From: Amir Goldstein <amir73il@gmail.com>

[ Upstream commit 880bd496ec72a6dcb00cb70c430ef752ba242ae7 ]

In preparation to adding LSM blob to backing_file struct, factor out
helpers init_backing_file() and backing_file_free().

Cc: stable@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-unionfs@vger.kernel.org
Cc: linux-erofs@lists.ozlabs.org
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
[PM: use the term "LSM blob", fix comment style to match file]
Signed-off-by: Paul Moore <paul@paul-moore.com>
[1. The commit def3ae83da02
("fs: store real path instead of fake path in backing file f_path")
is not merged, The 5.10 LTS version accordingly operates on
&ff->real_path instead of &ff->user_path.

2. Mainline's file_free() does both the backing_file cleanup and the
kmem_cache_free() synchronously.  Linux 5.10.y defers the actual kfree()
to file_free_rcu() via call_rcu(), so only path_put() is done
synchronously in file_free().]
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 fs/file_table.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 6daef2e2b2ad..6792d0bce246 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -70,11 +70,16 @@ static void file_free_rcu(struct rcu_head *head)
 		kmem_cache_free(filp_cachep, f);
 }
 
+static inline void backing_file_free(struct backing_file *ff)
+{
+	path_put(&ff->real_path);
+}
+
 static inline void file_free(struct file *f)
 {
 	security_file_free(f);
 	if (unlikely(f->f_mode & FMODE_BACKING))
-		path_put(backing_file_real_path(f));
+		backing_file_free(backing_file(f));
 	if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
 		percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
@@ -211,6 +216,12 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 	return f;
 }
 
+static int init_backing_file(struct backing_file *ff)
+{
+	memset(&ff->real_path, 0, sizeof(ff->real_path));
+	return 0;
+}
+
 /*
  * Variant of alloc_empty_file() that allocates a backing_file container
  * and doesn't check and modify nr_files.
@@ -231,7 +242,14 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 	if (unlikely(error))
 		return ERR_PTR(error);
 
+	/* The f_mode flags must be set before fput(). */
 	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
+	error = init_backing_file(ff);
+	if (unlikely(error)) {
+		fput(&ff->file);
+		return ERR_PTR(error);
+	}
+
 	return &ff->file;
 }
 
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 5/7] fs: prepare for adding LSM blob to backing_file

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Slab allocator corruption and kernel panic when security_file_alloc() fails during backing file initialization.
--

commit 5ea328a29bcb61b7c30ea4dc685a4910998da08f
Author: Amir Goldstein <amir73il@gmail.com>

fs: prepare for adding LSM blob to backing_file

In preparation to adding LSM blob to backing_file struct, factor out
helpers init_backing_file() and backing_file_free().

> diff --git a/fs/file_table.c b/fs/file_table.c
> index 6daef2e2b2ada..6792d0bce2461 100644
> --- a/fs/file_table.c
> +++ b/fs/file_table.c

[ ... ]

> @@ -231,7 +242,14 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
>  	if (unlikely(error))
>  		return ERR_PTR(error);
>  
> +	/* The f_mode flags must be set before fput(). */
>  	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;

[Severity: High]
Can this lead to slab corruption if init_file() fails?

In alloc_empty_backing_file(), the backing_file is allocated via kzalloc():

fs/file_table.c:alloc_empty_backing_file() {
    ...
	ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL);
	if (unlikely(!ff))
		return ERR_PTR(-ENOMEM);

	error = init_file(&ff->file, flags, cred);
    ...
}

If security_file_alloc() fails inside init_file(), it triggers the cleanup
path using file_free_rcu():

fs/file_table.c:init_file() {
    ...
	error = security_file_alloc(f);
	if (unlikely(error)) {
		file_free_rcu(&f->f_u.fu_rcuhead);
		return error;
	}
    ...
}

Because FMODE_BACKING is not set until after init_file() returns,
file_free_rcu() will take the else branch and attempt to free the kzalloc'd
pointer into the filp_cachep kmem cache:

fs/file_table.c:file_free_rcu() {
    ...
	if (unlikely(f->f_mode & FMODE_BACKING))
		kfree(backing_file(f));
	else
		kmem_cache_free(filp_cachep, f);
}

Should FMODE_BACKING be set before calling init_file(), or is there a
different way this cleanup should be handled?

> +	error = init_backing_file(ff);
> +	if (unlikely(error)) {
> +		fput(&ff->file);
> +		return ERR_PTR(error);
> +	}
> +
>  	return &ff->file;
>  }

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=5

[PATCH stable/linux-5.10.y 6/7] lsm: add backing_file LSM hooks

[Cai Xinchen]

From: Paul Moore <paul@paul-moore.com>

[ Upstream commit 6af36aeb147a06dea47c49859cd6ca5659aeb987 ]

Stacked filesystems such as overlayfs do not currently provide the
necessary mechanisms for LSMs to properly enforce access controls on the
mmap() and mprotect() operations.  In order to resolve this gap, a LSM
security blob is being added to the backing_file struct and the following
new LSM hooks are being created:

 security_backing_file_alloc()
 security_backing_file_free()
 security_mmap_backing_file()

The first two hooks are to manage the lifecycle of the LSM security blob
in the backing_file struct, while the third provides a new mmap() access
control point for the underlying backing file.  It is also expected that
LSMs will likely want to update their security_file_mprotect() callback
to address issues with their mprotect() controls, but that does not
require a change to the security_file_mprotect() LSM hook.

There are a three other small changes to support these new LSM hooks:
* Pass the user file associated with a backing file down to
alloc_empty_backing_file() so it can be included in the
security_backing_file_alloc() hook.
* Add getter and setter functions for the backing_file struct LSM blob
as the backing_file struct remains private to fs/file_table.c.
* Constify the file struct field in the LSM common_audit_data struct to
better support LSMs that need to pass a const file struct pointer into
the common LSM audit code.

Thanks to Arnd Bergmann for identifying the missing EXPORT_SYMBOL_GPL()
and supplying a fixup.

Cc: stable@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-unionfs@vger.kernel.org
Cc: linux-erofs@lists.ozlabs.org
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Paul Moore <paul@paul-moore.com>
[1. Mainline uses call_int_hook(FUNC, ...) with the default IRC baked
into the macro. Linux 5.10.y uses call_int_hook(FUNC, IRC, ...)
requiring an explicit default return value.

2. fs/backing-file.c does not exist in LTS
Linux 5.10.y places backing_file_open() in fs/open.c and lacks a
dedicated fs/backing-file.c.  The backing_file_mmap() function and
scoped_with_creds() do not exist in 5.10.y.  Therefore the LTS patch
calls security_mmap_backing_file() directly in ovl_mmap() in
fs/overlayfs/file.c rather than modifying backing_file_mmap().

3. Missing filesystems/modules
Linux 5.10.y does not have backing_tmpfile_open(), fs/fuse/passthrough.c,
or the erofs ishare mmap path that the mainline patch touches. These hunks
are dropped in the 5.10 LTS backport.

4. Use macro backing_file to replace inline function to eliminate the
const warning.

5. Mainline declares lsm_backing_file_cache in security/lsm.h. 5.10.y does
not have security/lsm_init.c or security/lsm.h; the cache variable
is defined locally as static struct kmem_cache *lsm_backing_file_cache
in security/security.c.]
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 fs/file_table.c               |  32 +++++++---
 fs/internal.h                 |   3 +-
 fs/open.c                     |   7 ++-
 fs/overlayfs/file.c           |   8 ++-
 include/linux/fs.h            |  15 ++++-
 include/linux/lsm_audit.h     |   2 +-
 include/linux/lsm_hook_defs.h |   5 ++
 include/linux/lsm_hooks.h     |   1 +
 include/linux/security.h      |  22 +++++++
 security/security.c           | 110 ++++++++++++++++++++++++++++++++++
 10 files changed, 190 insertions(+), 15 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 6792d0bce246..829dfd35365c 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -46,12 +46,12 @@ static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 struct backing_file {
 	struct file file;
 	struct path real_path;
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 };
 
-static inline struct backing_file *backing_file(struct file *f)
-{
-	return container_of(f, struct backing_file, file);
-}
+#define backing_file(f) container_of(f, struct backing_file, file)
 
 struct path *backing_file_real_path(struct file *f)
 {
@@ -70,8 +70,21 @@ static void file_free_rcu(struct rcu_head *head)
 		kmem_cache_free(filp_cachep, f);
 }
 
+#ifdef CONFIG_SECURITY
+void *backing_file_security(const struct file *f)
+{
+	return backing_file(f)->security;
+}
+
+void backing_file_set_security(struct file *f, void *security)
+{
+	backing_file(f)->security = security;
+}
+#endif /* CONFIG_SECURITY */
+
 static inline void backing_file_free(struct backing_file *ff)
 {
+	security_backing_file_free(&ff->file);
 	path_put(&ff->real_path);
 }
 
@@ -216,10 +229,12 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 	return f;
 }
 
-static int init_backing_file(struct backing_file *ff)
+static int init_backing_file(struct backing_file *ff,
+			     const struct file *user_file)
 {
 	memset(&ff->real_path, 0, sizeof(ff->real_path));
-	return 0;
+	backing_file_set_security(&ff->file, NULL);
+	return security_backing_file_alloc(&ff->file, user_file);
 }
 
 /*
@@ -229,7 +244,8 @@ static int init_backing_file(struct backing_file *ff)
  * This is only for kernel internal use, and the allocate file must not be
  * installed into file tables or such.
  */
-struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
+				      const struct file *user_file)
 {
 	struct backing_file *ff;
 	int error;
@@ -244,7 +260,7 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 
 	/* The f_mode flags must be set before fput(). */
 	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
-	error = init_backing_file(ff);
+	error = init_backing_file(ff, user_file);
 	if (unlikely(error)) {
 		fput(&ff->file);
 		return ERR_PTR(error);
diff --git a/fs/internal.h b/fs/internal.h
index 676e8a8da1c7..e74f9b27888e 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -109,7 +109,8 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
  */
 struct file *alloc_empty_file(int flags, const struct cred *cred);
 struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
-struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
+				      const struct file *user_file);
 
 /*
  * super.c
diff --git a/fs/open.c b/fs/open.c
index d6d5684dc919..fbcfdb83c02e 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1012,18 +1012,19 @@ EXPORT_SYMBOL(dentry_create);
  * the backing inode on the underlying filesystem, which can be
  * retrieved using backing_file_real_path().
  */
-struct file *backing_file_open(const struct path *path, int flags,
+struct file *backing_file_open(const struct file *user_file, int flags,
 			       const struct path *real_path,
 			       const struct cred *cred)
 {
+	const struct path *user_path = &user_file->f_path;
 	struct file *f;
 	int error;
 
-	f = alloc_empty_backing_file(flags, cred);
+	f = alloc_empty_backing_file(flags, cred, user_file);
 	if (IS_ERR(f))
 		return f;
 
-	f->f_path = *path;
+	f->f_path = *user_path;
 	path_get(real_path);
 	*backing_file_real_path(f) = *real_path;
 	error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 460748b63806..318ec1d99aa1 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -58,7 +58,7 @@ static struct file *ovl_open_realfile(const struct file *file,
 		if (!inode_owner_or_capable(realinode))
 			flags &= ~O_NOATIME;
 
-		realfile = backing_file_open(&file->f_path, flags, realpath,
+		realfile = backing_file_open(file, flags, realpath,
 					     current_cred());
 	}
 	revert_creds(old_cred);
@@ -491,6 +491,7 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct file *user_file = vma->vm_file;
 	struct file *realfile = file->private_data;
 	const struct cred *old_cred;
 	int ret;
@@ -504,6 +505,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_file = get_file(realfile);
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
+	ret = security_mmap_backing_file(vma, realfile, user_file);
+	if (ret) {
+		revert_creds(old_cred);
+		return ret;
+	}
 	ret = call_mmap(vma->vm_file, vma);
 	revert_creds(old_cred);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index acdc14542cbb..3b1eb8d7d9d7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2680,11 +2680,24 @@ struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *creds);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
-struct file *backing_file_open(const struct path *path, int flags,
+struct file *backing_file_open(const struct file *user_file, int flags,
 			       const struct path *real_path,
 			       const struct cred *cred);
 struct path *backing_file_real_path(struct file *f);
 
+#ifdef CONFIG_SECURITY
+void *backing_file_security(const struct file *f);
+void backing_file_set_security(struct file *f, void *security);
+#else
+static inline void *backing_file_security(const struct file *f)
+{
+	return NULL;
+}
+static inline void backing_file_set_security(struct file *f, void *security)
+{
+}
+#endif /* CONFIG_SECURITY */
+
 /*
  * file_real_path - get the path corresponding to f_inode
  *
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 28f23b341c1c..8b42e110cb26 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -92,7 +92,7 @@ struct common_audit_data {
 #endif
 		char *kmod_name;
 		struct lsm_ioctlop_audit *op;
-		struct file *file;
+		const struct file *file;
 		struct lsm_ibpkey_audit *ibpkey;
 		struct lsm_ibendport_audit *ibendport;
 		int reason;
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index e34b295bc15a..473e4d8dafe3 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -156,6 +156,9 @@ LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir,
 LSM_HOOK(int, 0, file_permission, struct file *file, int mask)
 LSM_HOOK(int, 0, file_alloc_security, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
+LSM_HOOK(int, 0, backing_file_alloc, struct file *backing_file,
+	 const struct file *user_file)
+LSM_HOOK(void, LSM_RET_VOID, backing_file_free, struct file *backing_file)
 LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
 	 unsigned long arg)
 LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
@@ -163,6 +166,8 @@ LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
 LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
 LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
 	 unsigned long prot, unsigned long flags)
+LSM_HOOK(int, 0, mmap_backing_file, struct vm_area_struct *vma,
+	 struct file *backing_file, struct file *user_file)
 LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma,
 	 unsigned long reqprot, unsigned long prot)
 LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index bbf9c8c7bd9c..04f08634e552 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1562,6 +1562,7 @@ struct security_hook_list {
 struct lsm_blob_sizes {
 	int	lbs_cred;
 	int	lbs_file;
+	int	lbs_backing_file;
 	int	lbs_inode;
 	int	lbs_ipc;
 	int	lbs_msg_msg;
diff --git a/include/linux/security.h b/include/linux/security.h
index f3c9d640b60b..c127367026d5 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -369,11 +369,17 @@ int security_kernfs_init_security(struct kernfs_node *kn_dir,
 int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_free(struct file *file);
+int security_backing_file_alloc(struct file *backing_file,
+				const struct file *user_file);
+void security_backing_file_free(struct file *backing_file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int security_file_ioctl_compat(struct file *file, unsigned int cmd,
 			       unsigned long arg);
 int security_mmap_file(struct file *file, unsigned long prot,
 			unsigned long flags);
+int security_mmap_backing_file(struct vm_area_struct *vma,
+			       struct file *backing_file,
+			       struct file *user_file);
 int security_mmap_addr(unsigned long addr);
 int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			   unsigned long prot);
@@ -923,6 +929,15 @@ static inline int security_file_alloc(struct file *file)
 static inline void security_file_free(struct file *file)
 { }
 
+static inline int security_backing_file_alloc(struct file *backing_file,
+					      const struct file *user_file)
+{
+	return 0;
+}
+
+static inline void security_backing_file_free(struct file *backing_file)
+{ }
+
 static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 				      unsigned long arg)
 {
@@ -942,6 +957,13 @@ static inline int security_mmap_file(struct file *file, unsigned long prot,
 	return 0;
 }
 
+static inline int security_mmap_backing_file(struct vm_area_struct *vma,
+					     struct file *backing_file,
+					     struct file *user_file)
+{
+	return 0;
+}
+
 static inline int security_mmap_addr(unsigned long addr)
 {
 	return cap_mmap_addr(addr);
diff --git a/security/security.c b/security/security.c
index d6b1b82094b7..50e781b06eb4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -76,6 +76,7 @@ struct security_hook_heads security_hook_heads __lsm_ro_after_init;
 static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain);
 
 static struct kmem_cache *lsm_file_cache;
+static struct kmem_cache *lsm_backing_file_cache;
 static struct kmem_cache *lsm_inode_cache;
 
 char *lsm_names;
@@ -197,6 +198,8 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed)
 
 	lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred);
 	lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file);
+	lsm_set_blob_size(&needed->lbs_backing_file,
+			     &blob_sizes.lbs_backing_file);
 	/*
 	 * The inode blob gets an rcu_head in addition to
 	 * what the modules might need.
@@ -338,6 +341,7 @@ static void __init ordered_lsm_init(void)
 
 	init_debug("cred blob size     = %d\n", blob_sizes.lbs_cred);
 	init_debug("file blob size     = %d\n", blob_sizes.lbs_file);
+	init_debug("backing_file blob size  = %d\n", blob_sizes.lbs_backing_file);
 	init_debug("inode blob size    = %d\n", blob_sizes.lbs_inode);
 	init_debug("ipc blob size      = %d\n", blob_sizes.lbs_ipc);
 	init_debug("msg_msg blob size  = %d\n", blob_sizes.lbs_msg_msg);
@@ -350,6 +354,11 @@ static void __init ordered_lsm_init(void)
 		lsm_file_cache = kmem_cache_create("lsm_file_cache",
 						   blob_sizes.lbs_file, 0,
 						   SLAB_PANIC, NULL);
+	if (blob_sizes.lbs_backing_file)
+		lsm_backing_file_cache = kmem_cache_create(
+						   "lsm_backing_file_cache",
+						   blob_sizes.lbs_backing_file,
+						   0, SLAB_PANIC, NULL);
 	if (blob_sizes.lbs_inode)
 		lsm_inode_cache = kmem_cache_create("lsm_inode_cache",
 						    blob_sizes.lbs_inode, 0,
@@ -575,6 +584,30 @@ static int lsm_file_alloc(struct file *file)
 	return 0;
 }
 
+/**
+ * lsm_backing_file_alloc - allocate a composite backing file blob
+ * @backing_file: the backing file
+ *
+ * Allocate the backing file blob for all the modules.
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_backing_file_alloc(struct file *backing_file)
+{
+	void *blob;
+
+	if (!lsm_backing_file_cache) {
+		backing_file_set_security(backing_file, NULL);
+		return 0;
+	}
+
+	blob = kmem_cache_zalloc(lsm_backing_file_cache, GFP_KERNEL);
+	backing_file_set_security(backing_file, blob);
+	if (!blob)
+		return -ENOMEM;
+	return 0;
+}
+
 /**
  * lsm_inode_alloc - allocate a composite inode blob
  * @inode: the inode that needs a blob
@@ -1493,6 +1526,57 @@ void security_file_free(struct file *file)
 	}
 }
 
+/**
+ * security_backing_file_alloc() - Allocate and setup a backing file blob
+ * @backing_file: the backing file
+ * @user_file: the associated user visible file
+ *
+ * Allocate a backing file LSM blob and perform any necessary initialization of
+ * the LSM blob.  There will be some operations where the LSM will not have
+ * access to @user_file after this point, so any important state associated
+ * with @user_file that is important to the LSM should be captured in the
+ * backing file's LSM blob.
+ *
+ * LSM's should avoid taking a reference to @user_file in this hook as it will
+ * result in problems later when the system attempts to drop/put the file
+ * references due to a circular dependency.
+ *
+ * Return: Return 0 if the hook is successful, negative values otherwise.
+ */
+int security_backing_file_alloc(struct file *backing_file,
+				const struct file *user_file)
+{
+	int rc;
+
+	rc = lsm_backing_file_alloc(backing_file);
+	if (rc)
+		return rc;
+	rc = call_int_hook(backing_file_alloc, 0, backing_file, user_file);
+	if (unlikely(rc))
+		security_backing_file_free(backing_file);
+
+	return rc;
+}
+
+/**
+ * security_backing_file_free() - Free a backing file blob
+ * @backing_file: the backing file
+ *
+ * Free any LSM state associate with a backing file's LSM blob, including the
+ * blob itself.
+ */
+void security_backing_file_free(struct file *backing_file)
+{
+	void *blob = backing_file_security(backing_file);
+
+	call_void_hook(backing_file_free, backing_file);
+
+	if (blob) {
+		backing_file_set_security(backing_file, NULL);
+		kmem_cache_free(lsm_backing_file_cache, blob);
+	}
+}
+
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	return call_int_hook(file_ioctl, 0, file, cmd, arg);
@@ -1562,6 +1646,32 @@ int security_mmap_file(struct file *file, unsigned long prot,
 	return ima_file_mmap(file, prot, prot_adj, flags);
 }
 
+/**
+ * security_mmap_backing_file - Check if mmap'ing a backing file is allowed
+ * @vma: the vm_area_struct for the mmap'd region
+ * @backing_file: the backing file being mmap'd
+ * @user_file: the user file being mmap'd
+ *
+ * Check permissions for a mmap operation on a stacked filesystem.  This hook
+ * is called after the security_mmap_file() and is responsible for authorizing
+ * the mmap on @backing_file.  It is important to note that the mmap operation
+ * on @user_file has already been authorized and the @vma->vm_file has been
+ * set to @backing_file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_mmap_backing_file(struct vm_area_struct *vma,
+			       struct file *backing_file,
+			       struct file *user_file)
+{
+	/* recommended by the stackable filesystem devs */
+	if (WARN_ON_ONCE(!(backing_file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	return call_int_hook(mmap_backing_file, 0, vma, backing_file, user_file);
+}
+EXPORT_SYMBOL_GPL(security_mmap_backing_file);
+
 int security_mmap_addr(unsigned long addr)
 {
 	return call_int_hook(mmap_addr, 0, addr);
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 6/7] lsm: add backing_file LSM hooks

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

New issues:
- [High] Permanent struct file reference count leak of 'realfile' when `security_mmap_backing_file` fails in `ovl_mmap`.

Pre-existing issues:
- [High] Slab corruption when `init_file` fails in `alloc_empty_backing_file` due to a mismatch between `kzalloc` and `kmem_cache_free`.
--

commit d56daad1df4b9fc063314a1e9538b4eee20fd64d
Author: Paul Moore <paul@paul-moore.com>

lsm: add backing_file LSM hooks

Stacked filesystems such as overlayfs do not currently provide the
necessary mechanisms for LSMs to properly enforce access controls on the
mmap() and mprotect() operations. In order to resolve this gap, a LSM
security blob is being added to the backing_file struct and the following
new LSM hooks are being created.

> diff --git a/fs/file_table.c b/fs/file_table.c
> index 6792d0bce2461..829dfd35365c3 100644
> --- a/fs/file_table.c
> +++ b/fs/file_table.c
[ ... ]
> @@ -229,7 +244,8 @@ static int init_backing_file(struct backing_file *ff)
>   * This is only for kernel internal use, and the allocate file must not be
>   * installed into file tables or such.
>   */
> -struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
> +struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
> +				      const struct file *user_file)
>  {

[Severity: High]
This is a pre-existing issue, but does alloc_empty_backing_file() cause slab
corruption if init_file() fails?

In alloc_empty_backing_file(), we allocate a struct backing_file using
kzalloc(). Then we call init_file(&ff->file, flags, cred).

If init_file() fails (e.g., if security_file_alloc() returns -ENOMEM), it cleans
up by directly calling file_free_rcu():

fs/file_table.c:init_file() {
    ...
	error = security_file_alloc(f);
	if (unlikely(error)) {
		file_free_rcu(&f->f_u.fu_rcuhead);
		return error;
	}
    ...
}

Inside file_free_rcu(), it uses the FMODE_BACKING flag to decide how to free:

fs/file_table.c:file_free_rcu() {
    ...
	if (unlikely(f->f_mode & FMODE_BACKING))
		kfree(backing_file(f));
	else
		kmem_cache_free(filp_cachep, f);
}

Since FMODE_BACKING is only set after init_file() returns successfully, the
flag is missing during the error path, and we end up passing the kzalloc'd
pointer to kmem_cache_free(filp_cachep, f).

>  	struct backing_file *ff;
>  	int error;
[ ... ]
> diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
> index 460748b638063..318ec1d99aa16 100644
> --- a/fs/overlayfs/file.c
> +++ b/fs/overlayfs/file.c
[ ... ]
> @@ -504,6 +505,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
>  	vma->vm_file = get_file(realfile);
>  
>  	old_cred = ovl_override_creds(file_inode(file)->i_sb);
> +	ret = security_mmap_backing_file(vma, realfile, user_file);
> +	if (ret) {
> +		revert_creds(old_cred);
> +		return ret;

[Severity: High]
Does this code leak the realfile reference on error?

When security_mmap_backing_file() fails, we return early without dropping
the reference to realfile acquired just above via get_file(realfile) and
stored in vma->vm_file.

The caller (__mmap_region()) handles the error by clearing vma->vm_file = NULL
and only drops the reference to the original user_file, which orphans the
reference to realfile.

> +	}
>  	ret = call_mmap(vma->vm_file, vma);
>  	revert_creds(old_cred);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=6

[PATCH stable/linux-5.10.y 7/7] selinux: fix overlayfs mmap() and mprotect() access checks

[Cai Xinchen]

From: Paul Moore <paul@paul-moore.com>

[ Upstream commit 82544d36b1729153c8aeb179e84750f0c085d3b1 ]

The existing SELinux security model for overlayfs is to allow access if
the current task is able to access the top level file (the "user" file)
and the mounter's credentials are sufficient to access the lower
level file (the "backing" file).  Unfortunately, the current code does
not properly enforce these access controls for both mmap() and mprotect()
operations on overlayfs filesystems.

This patch makes use of the newly created security_mmap_backing_file()
LSM hook to provide the missing backing file enforcement for mmap()
operations, and leverages the backing file API and new LSM blob to
provide the necessary information to properly enforce the mprotect()
access controls.

Cc: stable@vger.kernel.org
Acked-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
[backing_file_user_path() not available
Mainline uses backing_file_user_path(file) to obtain the user-visible path
from a backing file. The 5.10.y version uses &file->f_path directly]
Signed-off-by: Cai Xinchen <caixinchen1@huawei.com>
---
 security/selinux/hooks.c          | 244 ++++++++++++++++++++++--------
 security/selinux/include/objsec.h |  11 ++
 2 files changed, 190 insertions(+), 65 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index e1bbdef0bcd3..76cc0cbd1fd2 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1703,52 +1703,75 @@ static inline int file_path_has_perm(const struct cred *cred,
 static int bpf_fd_pass(const struct file *file, u32 sid);
 #endif
 
-/* Check whether a task can use an open file descriptor to
-   access an inode in a given way.  Check access to the
-   descriptor itself, and then use dentry_has_perm to
-   check a particular permission to the file.
-   Access to the descriptor is implicitly granted if it
-   has the same SID as the process.  If av is zero, then
-   access to the file is not checked, e.g. for cases
-   where only the descriptor is affected like seek. */
-static int file_has_perm(const struct cred *cred,
-			 struct file *file,
-			 u32 av)
+static int __file_has_perm(const struct cred *cred, const struct file *file,
+			   u32 av, bool bf_user_file)
+
 {
-	struct file_security_struct *fsec = selinux_file(file);
-	struct inode *inode = file_inode(file);
 	struct common_audit_data ad;
-	u32 sid = cred_sid(cred);
+	struct inode *inode;
+	u32 ssid = cred_sid(cred);
+	u32 tsid_fd;
 	int rc;
 
-	ad.type = LSM_AUDIT_DATA_FILE;
-	ad.u.file = file;
+	if (bf_user_file) {
+		struct backing_file_security_struct *bfsec;
+		const struct path *path;
 
-	if (sid != fsec->sid) {
-		rc = avc_has_perm(&selinux_state,
-				  sid, fsec->sid,
-				  SECCLASS_FD,
-				  FD__USE,
-				  &ad);
+		if (WARN_ON(!(file->f_mode & FMODE_BACKING)))
+			return -EIO;
+
+		bfsec = selinux_backing_file(file);
+		path = &file->f_path;
+		tsid_fd = bfsec->uf_sid;
+		inode = d_inode(path->dentry);
+
+		ad.type = LSM_AUDIT_DATA_PATH;
+		ad.u.path = *path;
+	} else {
+		struct file_security_struct *fsec = selinux_file(file);
+
+		tsid_fd = fsec->sid;
+		inode = file_inode(file);
+
+		ad.type = LSM_AUDIT_DATA_FILE;
+		ad.u.file = file;
+	}
+
+	if (ssid != tsid_fd) {
+		rc = avc_has_perm(&selinux_state, ssid, tsid_fd, SECCLASS_FD, FD__USE, &ad);
 		if (rc)
-			goto out;
+			return rc;
 	}
 
 #ifdef CONFIG_BPF_SYSCALL
-	rc = bpf_fd_pass(file, cred_sid(cred));
+	/* regardless of backing vs user file, use the underlying file here */
+	rc = bpf_fd_pass(file, ssid);
 	if (rc)
 		return rc;
 #endif
 
 	/* av is zero if only checking access to the descriptor. */
-	rc = 0;
 	if (av)
-		rc = inode_has_perm(cred, inode, av, &ad);
+		return inode_has_perm(cred, inode, av, &ad);
 
-out:
-	return rc;
+	return 0;
 }
 
+/* Check whether a task can use an open file descriptor to
+   access an inode in a given way.  Check access to the
+   descriptor itself, and then use dentry_has_perm to
+   check a particular permission to the file.
+   Access to the descriptor is implicitly granted if it
+   has the same SID as the process.  If av is zero, then
+   access to the file is not checked, e.g. for cases
+   where only the descriptor is affected like seek. */
+static inline int file_has_perm(const struct cred *cred,
+				const struct file *file, u32 av)
+{
+	return __file_has_perm(cred, file, av, false);
+}
+
+
 /*
  * Determine the label for an inode that might be unioned.
  */
@@ -3572,6 +3595,17 @@ static int selinux_file_alloc_security(struct file *file)
 	return 0;
 }
 
+static int selinux_backing_file_alloc(struct file *backing_file,
+				      const struct file *user_file)
+{
+	struct backing_file_security_struct *bfsec;
+
+	bfsec = selinux_backing_file(backing_file);
+	bfsec->uf_sid = selinux_file(user_file)->sid;
+
+	return 0;
+}
+
 /*
  * Check whether a task has the ioctl permission and cmd
  * operation to an inode.
@@ -3691,43 +3725,55 @@ static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd,
 
 static int default_noexec __ro_after_init;
 
-static int file_map_prot_check(struct file *file, unsigned long prot, int shared)
+static int __file_map_prot_check(const struct cred *cred,
+				 const struct file *file, unsigned long prot,
+				 bool shared, bool bf_user_file)
 {
-	const struct cred *cred = current_cred();
-	u32 sid = cred_sid(cred);
-	int rc = 0;
+	struct inode *inode = NULL;
+	bool prot_exec = prot & PROT_EXEC;
+	bool prot_write = prot & PROT_WRITE;
+
+	if (file) {
+		if (bf_user_file)
+			inode = d_inode(file->f_path.dentry);
+		else
+			inode = file_inode(file);
+	}
+
+	if (default_noexec && prot_exec &&
+	    (!file || IS_PRIVATE(inode) || (!shared && prot_write))) {
+		int rc;
+		u32 sid = cred_sid(cred);
 
-	if (default_noexec &&
-	    (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) ||
-				   (!shared && (prot & PROT_WRITE)))) {
 		/*
-		 * We are making executable an anonymous mapping or a
-		 * private file mapping that will also be writable.
-		 * This has an additional check.
+		 * We are making executable an anonymous mapping or a private
+		 * file mapping that will also be writable.
 		 */
-		rc = avc_has_perm(&selinux_state,
-				  sid, sid, SECCLASS_PROCESS,
-				  PROCESS__EXECMEM, NULL);
+		rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM,
+				  NULL);
 		if (rc)
-			goto error;
+			return rc;
 	}
 
 	if (file) {
-		/* read access is always possible with a mapping */
+		/* "read" always possible, "write" only if shared */
 		u32 av = FILE__READ;
-
-		/* write access only matters if the mapping is shared */
-		if (shared && (prot & PROT_WRITE))
+		if (shared && prot_write)
 			av |= FILE__WRITE;
-
-		if (prot & PROT_EXEC)
+		if (prot_exec)
 			av |= FILE__EXECUTE;
 
-		return file_has_perm(cred, file, av);
+		return __file_has_perm(cred, file, av, bf_user_file);
 	}
 
-error:
-	return rc;
+	return 0;
+}
+
+static inline int file_map_prot_check(const struct cred *cred,
+				      const struct file *file,
+				      unsigned long prot, bool shared)
+{
+	return __file_map_prot_check(cred, file, prot, shared, false);
 }
 
 static int selinux_mmap_addr(unsigned long addr)
@@ -3744,17 +3790,16 @@ static int selinux_mmap_addr(unsigned long addr)
 	return rc;
 }
 
-static int selinux_mmap_file(struct file *file, unsigned long reqprot,
-			     unsigned long prot, unsigned long flags)
+static int selinux_mmap_file_common(const struct cred *cred, struct file *file,
+				    unsigned long reqprot, unsigned long prot, bool shared)
 {
-	struct common_audit_data ad;
-	int rc;
-
 	if (file) {
+		int rc;
+		struct common_audit_data ad;
+
 		ad.type = LSM_AUDIT_DATA_FILE;
 		ad.u.file = file;
-		rc = inode_has_perm(current_cred(), file_inode(file),
-				    FILE__MAP, &ad);
+		rc = inode_has_perm(cred, file_inode(file), FILE__MAP, &ad);
 		if (rc)
 			return rc;
 	}
@@ -3762,36 +3807,86 @@ static int selinux_mmap_file(struct file *file, unsigned long reqprot,
 	if (checkreqprot_get(&selinux_state))
 		prot = reqprot;
 
-	return file_map_prot_check(file, prot,
-				   (flags & MAP_TYPE) == MAP_SHARED);
+	return file_map_prot_check(cred, file, prot, shared);
+}
+
+static int selinux_mmap_file(struct file *file,
+			     unsigned long reqprot,
+			     unsigned long prot, unsigned long flags)
+{
+	return selinux_mmap_file_common(current_cred(), file, reqprot, prot,
+					(flags & MAP_TYPE) == MAP_SHARED);
+}
+
+/**
+ * selinux_mmap_backing_file - Check mmap permissions on a backing file
+ * @vma: memory region
+ * @backing_file: stacked filesystem backing file
+ * @user_file: user visible file
+ *
+ * This is called after selinux_mmap_file() on stacked filesystems, and it
+ * is this function's responsibility to verify access to @backing_file and
+ * setup the SELinux state for possible later use in the mprotect() code path.
+ *
+ * By the time this function is called, mmap() access to @user_file has already
+ * been authorized and @vma->vm_file has been set to point to @backing_file.
+ *
+ * Return zero on success, negative values otherwise.
+ */
+static int selinux_mmap_backing_file(struct vm_area_struct *vma,
+				     struct file *backing_file,
+				     struct file *user_file __always_unused)
+{
+	unsigned long prot = 0;
+
+	/* translate vma->vm_flags perms into PROT perms */
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	return selinux_mmap_file_common(backing_file->f_cred, backing_file,
+					prot, prot, vma->vm_flags & VM_SHARED);
 }
 
 static int selinux_file_mprotect(struct vm_area_struct *vma,
 				 unsigned long reqprot,
 				 unsigned long prot)
 {
+	int rc;
 	const struct cred *cred = current_cred();
 	u32 sid = cred_sid(cred);
+	const struct file *file = vma->vm_file;
+	bool backing_file;
+	bool shared = vma->vm_flags & VM_SHARED;
+
+	/* check if we need to trigger the "backing files are awful" mode */
+	backing_file = file && (file->f_mode & FMODE_BACKING);
 
 	if (checkreqprot_get(&selinux_state))
 		prot = reqprot;
 
 	if (default_noexec &&
 	    (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
-		int rc = 0;
 		if (vma->vm_start >= vma->vm_mm->start_brk &&
 		    vma->vm_end <= vma->vm_mm->brk) {
 			rc = avc_has_perm(&selinux_state,
 					  sid, sid, SECCLASS_PROCESS,
 					  PROCESS__EXECHEAP, NULL);
-		} else if (!vma->vm_file &&
+			if (rc)
+				return rc;
+		} else if (!file &&
 			   ((vma->vm_start <= vma->vm_mm->start_stack &&
 			     vma->vm_end >= vma->vm_mm->start_stack) ||
 			    vma_is_stack_for_current(vma))) {
 			rc = avc_has_perm(&selinux_state,
 					  sid, sid, SECCLASS_PROCESS,
 					  PROCESS__EXECSTACK, NULL);
-		} else if (vma->vm_file && vma->anon_vma) {
+			if (rc)
+				return rc;
+		} else if (file && vma->anon_vma) {
 			/*
 			 * We are making executable a file mapping that has
 			 * had some COW done. Since pages might have been
@@ -3799,13 +3894,29 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
 			 * modified content.  This typically should only
 			 * occur for text relocations.
 			 */
-			rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD);
+			rc = __file_has_perm(cred, file, FILE__EXECMOD,
+					     backing_file);
+			if (rc)
+				return rc;
+			if (backing_file) {
+				rc = file_has_perm(file->f_cred, file,
+						   FILE__EXECMOD);
+				if (rc)
+					return rc;
+			}
 		}
+	}
+
+	rc = __file_map_prot_check(cred, file, prot, shared, backing_file);
+	if (rc)
+		return rc;
+	if (backing_file) {
+		rc = file_map_prot_check(file->f_cred, file, prot, shared);
 		if (rc)
 			return rc;
 	}
 
-	return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED);
+	return 0;
 }
 
 static int selinux_file_lock(struct file *file, unsigned int cmd)
@@ -6924,6 +7035,7 @@ static int selinux_lockdown(enum lockdown_reason what)
 struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = {
 	.lbs_cred = sizeof(struct task_security_struct),
 	.lbs_file = sizeof(struct file_security_struct),
+	.lbs_backing_file = sizeof(struct backing_file_security_struct),
 	.lbs_inode = sizeof(struct inode_security_struct),
 	.lbs_ipc = sizeof(struct ipc_security_struct),
 	.lbs_msg_msg = sizeof(struct msg_security_struct),
@@ -7075,9 +7187,11 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 
 	LSM_HOOK_INIT(file_permission, selinux_file_permission),
 	LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
+	LSM_HOOK_INIT(backing_file_alloc, selinux_backing_file_alloc),
 	LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl),
 	LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat),
 	LSM_HOOK_INIT(mmap_file, selinux_mmap_file),
+	LSM_HOOK_INIT(mmap_backing_file, selinux_mmap_backing_file),
 	LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr),
 	LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect),
 	LSM_HOOK_INIT(file_lock, selinux_file_lock),
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 330b7b6d44e0..b4be6588827c 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -60,6 +60,10 @@ struct file_security_struct {
 	u32 pseqno;		/* Policy seqno at the time of file open */
 };
 
+struct backing_file_security_struct {
+	u32 uf_sid; /* associated user file fsec->sid */
+};
+
 struct superblock_security_struct {
 	struct super_block *sb;		/* back pointer to sb object */
 	u32 sid;			/* SID of file system superblock */
@@ -159,6 +163,13 @@ static inline struct file_security_struct *selinux_file(const struct file *file)
 	return file->f_security + selinux_blob_sizes.lbs_file;
 }
 
+static inline struct backing_file_security_struct *
+selinux_backing_file(const struct file *backing_file)
+{
+	void *blob = backing_file_security(backing_file);
+	return blob + selinux_blob_sizes.lbs_backing_file;
+}
+
 static inline struct inode_security_struct *selinux_inode(
 						const struct inode *inode)
 {
-- 
2.18.0.huawei.25

Re: [PATCH stable/linux-5.10.y 7/7] selinux: fix overlayfs mmap() and mprotect() access checks

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

New issues:
- [High] SELinux inappropriately evaluates process-specific execution permissions (PROCESS__EXECMEM and FILE__EXECMOD) against the mounter's credentials for overlayfs backing files.

Pre-existing issues:
- [High] SELinux uses `!file` as a proxy to classify anonymous vs file-backed VMAs, causing incorrect MAC checks for anonymous `/dev/zero` mappings.
--

commit c8a02c1a6e87f41a5505e0fdbf8fe1977f518031
Author: Paul Moore <paul@paul-moore.com>

selinux: fix overlayfs mmap() and mprotect() access checks

This patch implements backing file enforcement for mmap() and mprotect()
operations on overlayfs filesystems. It uses the new LSM hook and backing
file API to ensure correct access controls.

> diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
> index e1bbdef0bcd39..76cc0cbd1fd2b 100644
> --- a/security/selinux/hooks.c
> +++ b/security/selinux/hooks.c

[ ... ]

> @@ -3762,36 +3807,86 @@ static int selinux_mmap_file(struct file *file, unsigned long reqprot,
>  	if (checkreqprot_get(&selinux_state))
>  		prot = reqprot;
>  
> -	return file_map_prot_check(file, prot,
> -				   (flags & MAP_TYPE) == MAP_SHARED);
> +	return file_map_prot_check(cred, file, prot, shared);
> +}
> +
> +/**
> + * selinux_mmap_backing_file - Check mmap permissions on a backing file
> + * @vma: memory region
> + * @backing_file: stacked filesystem backing file
> + * @user_file: user visible file
> + *
> + * This is called after selinux_mmap_file() on stacked filesystems, and it
> + * is this function's responsibility to verify access to @backing_file and
> + * setup the SELinux state for possible later use in the mprotect() code path.
> + *
> + * By the time this function is called, mmap() access to @user_file has already
> + * been authorized and @vma->vm_file has been set to point to @backing_file.
> + *
> + * Return zero on success, negative values otherwise.
> + */
> +static int selinux_mmap_backing_file(struct vm_area_struct *vma,
> +				     struct file *backing_file,
> +				     struct file *user_file __always_unused)
> +{
> +	unsigned long prot = 0;
> +
> +	/* translate vma->vm_flags perms into PROT perms */
> +	if (vma->vm_flags & VM_READ)
> +		prot |= PROT_READ;
> +	if (vma->vm_flags & VM_WRITE)
> +		prot |= PROT_WRITE;
> +	if (vma->vm_flags & VM_EXEC)
> +		prot |= PROT_EXEC;
> +
> +	return selinux_mmap_file_common(backing_file->f_cred, backing_file,
> +					prot, prot, vma->vm_flags & VM_SHARED);
>  }

[Severity: High]
When selinux_mmap_backing_file() calls selinux_mmap_file_common(), it passes
backing_file->f_cred. This cred propagates down to __file_map_prot_check(),
where it is used to evaluate PROCESS__EXECMEM.

Because this evaluates PROCESS__EXECMEM against the mounter's credentials
rather than the current task mapping the memory, could this result in
spurious EACCES denials if the mounter's policy lacks the EXECMEM privilege?

>  static int selinux_file_mprotect(struct vm_area_struct *vma,
>  				 unsigned long reqprot,
>  				 unsigned long prot)
>  {
> +	int rc;
>  	const struct cred *cred = current_cred();
>  	u32 sid = cred_sid(cred);
> +	const struct file *file = vma->vm_file;
> +	bool backing_file;
> +	bool shared = vma->vm_flags & VM_SHARED;
> +
> +	/* check if we need to trigger the "backing files are awful" mode */
> +	backing_file = file && (file->f_mode & FMODE_BACKING);
>  
>  	if (checkreqprot_get(&selinux_state))
>  		prot = reqprot;
>  
>  	if (default_noexec &&
>  	    (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
> -		int rc = 0;
>  		if (vma->vm_start >= vma->vm_mm->start_brk &&
>  		    vma->vm_end <= vma->vm_mm->brk) {
>  			rc = avc_has_perm(&selinux_state,
>  					  sid, sid, SECCLASS_PROCESS,
>  					  PROCESS__EXECHEAP, NULL);
> -		} else if (!vma->vm_file &&
> +			if (rc)
> +				return rc;
> +		} else if (!file &&
>  			   ((vma->vm_start <= vma->vm_mm->start_stack &&
>  			     vma->vm_end >= vma->vm_mm->start_stack) ||
>  			    vma_is_stack_for_current(vma))) {

[Severity: High]
This is a pre-existing issue, but using !file (which evaluates to
vma->vm_file == NULL) as a proxy for an anonymous VMA misses some anonymous
mappings.

Private mappings of /dev/zero are anonymous but have a non-NULL vma->vm_file.
Can this bypass the PROCESS__EXECSTACK permission check for /dev/zero
executable stacks by incorrectly falling through to the FILE__EXECMOD check?

Should this check use vma_is_anonymous(vma) rather than !file to ensure
all anonymous mappings are correctly evaluated?

>  			rc = avc_has_perm(&selinux_state,
>  					  sid, sid, SECCLASS_PROCESS,
>  					  PROCESS__EXECSTACK, NULL);
> -		} else if (vma->vm_file && vma->anon_vma) {
> +			if (rc)
> +				return rc;
> +		} else if (file && vma->anon_vma) {
>  			/*
>  			 * We are making executable a file mapping that has
>  			 * had some COW done. Since pages might have been
> @@ -3799,13 +3894,29 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
>  			 * modified content.  This typically should only
>  			 * occur for text relocations.
>  			 */
> -			rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD);
> +			rc = __file_has_perm(cred, file, FILE__EXECMOD,
> +					     backing_file);
> +			if (rc)
> +				return rc;
> +			if (backing_file) {
> +				rc = file_has_perm(file->f_cred, file,
> +						   FILE__EXECMOD);

[Severity: High]
Similar to the PROCESS__EXECMEM check in the mmap path, this evaluates
FILE__EXECMOD using the backing file's credentials (file->f_cred).

Is it intended to check EXECMOD against the mounter's credentials here,
or should this process-specific execution permission be evaluated against
the current process modifying the memory?

> +				if (rc)
> +					return rc;
> +			}
>  		}
> +	}
> +
> +	rc = __file_map_prot_check(cred, file, prot, shared, backing_file);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260629070653.580879-1-caixinchen1@huawei.com?part=7