Merge tag 'lsm-pr-20260410' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm

Pull LSM updates from Paul Moore:
 "We only have five patches in the LSM tree, but three of the five are
  for an important bugfix relating to overlayfs and the mmap() and
  mprotect() access controls for LSMs. Highlights below:

   - Fix problems with the mmap() and mprotect() LSM hooks on overlayfs

     As we are dealing with problems both in mmap() and mprotect() there
     are essentially two components to this fix, spread across three
     patches with all marked for stable.

     The simplest portion of the fix is the creation of a new LSM hook,
     security_mmap_backing_file(), that is used to enforce LSM mmap()
     access controls on backing files in the stacked/overlayfs case. The
     existing security_mmap_file() does not have visibility past the
     user file. You can see from the associated SELinux hook callback
     the code is fairly straightforward.

     The mprotect() fix is a bit more complicated as there is no way in
     the mprotect() code path to inspect both the user and backing
     files, and bolting on a second file reference to vm_area_struct
     wasn't really an option.

     The solution taken here adds a LSM security blob and associated
     hooks to the backing_file struct that LSMs can use to capture and
     store relevant information from the user file. While the necessary
     SELinux information is relatively small, a single u32, I expect
     other LSMs to require more than that, and a dedicated backing_file
     LSM blob provides a storage mechanism without negatively impacting
     other filesystems.

     I want to note that other LSMs beyond SELinux have been involved in
     the discussion of the fixes presented here and they are working on
     their own related changes using these new hooks, but due to other
     issues those patches will be coming at a later date.

   - Use kstrdup_const()/kfree_const() for securityfs symlink targets

   - Resolve a handful of kernel-doc warnings in cred.h"

* tag 'lsm-pr-20260410' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm:
  selinux: fix overlayfs mmap() and mprotect() access checks
  lsm: add backing_file LSM hooks
  fs: prepare for adding LSM blob to backing_file
  securityfs: use kstrdup_const() to manage symlink targets
  cred: fix kernel-doc warnings in cred.h

fs/backing-file.c

@@ -12,6 +12,7 @@
 #include <linux/backing-file.h>
 #include <linux/splice.h>
 #include <linux/mm.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -29,14 +30,15 @@
  * returned file into a container structure that also stores the stacked
  * file's path, which can be retrieved using backing_file_user_path().
  */
-struct file *backing_file_open(const struct path *user_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;
 
@@ -52,15 +54,16 @@ struct file *backing_file_open(const struct path *user_path, int flags,
 }
 EXPORT_SYMBOL_GPL(backing_file_open);
 
-struct file *backing_tmpfile_open(const struct path *user_path, int flags,
+struct file *backing_tmpfile_open(const struct file *user_file, int flags,
 				  const struct path *real_parentpath,
 				  umode_t mode, const struct cred *cred)
 {
 	struct mnt_idmap *real_idmap = mnt_idmap(real_parentpath->mnt);
+	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;
 
@@ -336,8 +339,13 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
 
 	vma_set_file(vma, file);
 
-	scoped_with_creds(ctx->cred)
+	scoped_with_creds(ctx->cred) {
+		ret = security_mmap_backing_file(vma, file, user_file);
+		if (ret)
+			return ret;
+
 		ret = vfs_mmap(vma->vm_file, vma);
+	}
 
 	if (ctx->accessed)
 		ctx->accessed(user_file);

fs/erofs/ishare.c

@@ -4,6 +4,7 @@
  */
 #include <linux/xxhash.h>
 #include <linux/mount.h>
+#include <linux/security.h>
 #include "internal.h"
 #include "xattr.h"
 
@@ -106,7 +107,8 @@ static int erofs_ishare_file_open(struct inode *inode, struct file *file)
 
 	if (file->f_flags & O_DIRECT)
 		return -EINVAL;
-	realfile = alloc_empty_backing_file(O_RDONLY|O_NOATIME, current_cred());
+	realfile = alloc_empty_backing_file(O_RDONLY|O_NOATIME, current_cred(),
+					    file);
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 	ihold(sharedinode);
@@ -150,8 +152,14 @@ static ssize_t erofs_ishare_file_read_iter(struct kiocb *iocb,
 static int erofs_ishare_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct file *realfile = file->private_data;
+	int err;
 
 	vma_set_file(vma, realfile);
+
+	err = security_mmap_backing_file(vma, realfile, file);
+	if (err)
+		return err;
+
 	return generic_file_readonly_mmap(file, vma);
 }
 

fs/file_table.c

@@ -54,6 +54,9 @@ struct backing_file {
 		struct path user_path;
 		freeptr_t bf_freeptr;
 	};
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 };
 
 #define backing_file(f) container_of(f, struct backing_file, file)
@@ -70,6 +73,25 @@ void backing_file_set_user_path(struct file *f, const struct path *path)
 }
 EXPORT_SYMBOL_GPL(backing_file_set_user_path);
 
+#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->user_path);
+	kmem_cache_free(bfilp_cache, ff);
+}
+
 static inline void file_free(struct file *f)
 {
 	security_file_free(f);
@@ -77,8 +99,7 @@ static inline void file_free(struct file *f)
 		percpu_counter_dec(&nr_files);
 	put_cred(f->f_cred);
 	if (unlikely(f->f_mode & FMODE_BACKING)) {
-		path_put(backing_file_user_path(f));
-		kmem_cache_free(bfilp_cache, backing_file(f));
+		backing_file_free(backing_file(f));
 	} else {
 		kmem_cache_free(filp_cache, f);
 	}
@@ -287,6 +308,14 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 	return f;
 }
 
+static int init_backing_file(struct backing_file *ff,
+			     const struct file *user_file)
+{
+	memset(&ff->user_path, 0, sizeof(ff->user_path));
+	backing_file_set_security(&ff->file, NULL);
+	return security_backing_file_alloc(&ff->file, user_file);
+}
+
 /*
  * Variant of alloc_empty_file() that allocates a backing_file container
  * and doesn't check and modify nr_files.
@@ -294,7 +323,8 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
  * 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;
@@ -309,7 +339,14 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 		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, user_file);
+	if (unlikely(error)) {
+		fput(&ff->file);
+		return ERR_PTR(error);
+	}
+
 	return &ff->file;
 }
 EXPORT_SYMBOL_GPL(alloc_empty_backing_file);

fs/fuse/passthrough.c

@@ -167,7 +167,7 @@ struct fuse_backing *fuse_passthrough_open(struct file *file, int backing_id)
 		goto out;
 
 	/* Allocate backing file per fuse file to store fuse path */
-	backing_file = backing_file_open(&file->f_path, file->f_flags,
+	backing_file = backing_file_open(file, file->f_flags,
 					 &fb->file->f_path, fb->cred);
 	err = PTR_ERR(backing_file);
 	if (IS_ERR(backing_file)) {

fs/internal.h

@@ -106,7 +106,8 @@ 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);
 void backing_file_set_user_path(struct file *f, const struct path *path);
 
 static inline void file_put_write_access(struct file *file)

fs/overlayfs/dir.c

@@ -1389,7 +1389,7 @@ static int ovl_create_tmpfile(struct file *file, struct dentry *dentry,
 				return PTR_ERR(cred);
 
 			ovl_path_upper(dentry->d_parent, &realparentpath);
-			realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath,
+			realfile = backing_tmpfile_open(file, flags, &realparentpath,
 							mode, current_cred());
 			err = PTR_ERR_OR_ZERO(realfile);
 			pr_debug("tmpfile/open(%pd2, 0%o) = %i\n", realparentpath.dentry, mode, err);

fs/overlayfs/file.c

@@ -48,7 +48,7 @@ static struct file *ovl_open_realfile(const struct file *file,
 			if (!inode_owner_or_capable(real_idmap, realinode))
 				flags &= ~O_NOATIME;
 
-			realfile = backing_file_open(file_user_path(file),
+			realfile = backing_file_open(file,
 						     flags, realpath, current_cred());
 		}
 	}

include/linux/backing-file.h

@@ -18,10 +18,10 @@ struct backing_file_ctx {
 	void (*end_write)(struct kiocb *iocb, ssize_t);
 };
 
-struct file *backing_file_open(const struct path *user_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 file *backing_tmpfile_open(const struct path *user_path, int flags,
+struct file *backing_tmpfile_open(const struct file *user_file, int flags,
 				  const struct path *real_parentpath,
 				  umode_t mode, const struct cred *cred);
 ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,

include/linux/cred.h

@@ -33,12 +33,14 @@ struct group_info {
 
 /**
  * get_group_info - Get a reference to a group info structure
- * @group_info: The group info to reference
+ * @gi: The group info to reference
  *
  * This gets a reference to a set of supplementary groups.
  *
  * If the caller is accessing a task's credentials, they must hold the RCU read
  * lock when reading.
+ *
+ * Returns: @gi
  */
 static inline struct group_info *get_group_info(struct group_info *gi)
 {
@@ -209,6 +211,8 @@ DEFINE_CLASS(override_creds,
  * usage count.  The purpose of this is to attempt to catch at compile time the
  * accidental alteration of a set of credentials that should be considered
  * immutable.
+ *
+ * Returns: @cred when the references are acquired, NULL otherwise.
  */
 static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
 {
@@ -246,8 +250,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 }
 
 /**
- * put_cred - Release a reference to a set of credentials
- * @cred: The credentials to release
+ * put_cred_many - Release a reference to a set of credentials
+ * @_cred: The credentials to release
  * @nr: Number of references to release
  *
  * Release a reference to a set of credentials, deleting them when the last ref

include/linux/fs.h

@@ -2475,6 +2475,19 @@ struct file *dentry_create(struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
 const struct path *backing_file_user_path(const 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 */
+
 /*
  * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
  * stored in ->vm_file is a backing file whose f_inode is on the underlying

include/linux/lsm_audit.h

@@ -94,7 +94,7 @@ 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;

include/linux/lsm_hook_defs.h

@@ -191,6 +191,9 @@ 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_release, 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,
@@ -198,6 +201,8 @@ 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)

include/linux/lsm_hooks.h

@@ -104,6 +104,7 @@ struct security_hook_list {
 struct lsm_blob_sizes {
 	unsigned int lbs_cred;
 	unsigned int lbs_file;
+	unsigned int lbs_backing_file;
 	unsigned int lbs_ib;
 	unsigned int lbs_inode;
 	unsigned int lbs_sock;

include/linux/security.h

@@ -472,11 +472,17 @@ int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_release(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);
@@ -1141,6 +1147,15 @@ static inline void security_file_release(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)
 {
@@ -1160,6 +1175,13 @@ 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);

security/inode.c

@@ -30,7 +30,7 @@ static int mount_count;
 static void securityfs_free_inode(struct inode *inode)
 {
 	if (S_ISLNK(inode->i_mode))
-		kfree(inode->i_link);
+		kfree_const(inode->i_link);
 	free_inode_nonrcu(inode);
 }
 
@@ -258,17 +258,17 @@ struct dentry *securityfs_create_symlink(const char *name,
 					 const struct inode_operations *iops)
 {
 	struct dentry *dent;
-	char *link = NULL;
+	const char *link = NULL;
 
 	if (target) {
-		link = kstrdup(target, GFP_KERNEL);
+		link = kstrdup_const(target, GFP_KERNEL);
 		if (!link)
 			return ERR_PTR(-ENOMEM);
 	}
 	dent = securityfs_create_dentry(name, S_IFLNK | 0444, parent,
-					link, NULL, iops);
+					(void *)link, NULL, iops);
 	if (IS_ERR(dent))
-		kfree(link);
+		kfree_const(link);
 
 	return dent;
 }

security/lsm.h

@@ -29,6 +29,7 @@ extern struct lsm_blob_sizes blob_sizes;
 
 /* LSM blob caches */
 extern struct kmem_cache *lsm_file_cache;
+extern struct kmem_cache *lsm_backing_file_cache;
 extern struct kmem_cache *lsm_inode_cache;
 
 /* LSM blob allocators */

security/lsm_init.c

@@ -293,6 +293,8 @@ static void __init lsm_prepare(struct lsm_info *lsm)
 	blobs = lsm->blobs;
 	lsm_blob_size_update(&blobs->lbs_cred, &blob_sizes.lbs_cred);
 	lsm_blob_size_update(&blobs->lbs_file, &blob_sizes.lbs_file);
+	lsm_blob_size_update(&blobs->lbs_backing_file,
+			     &blob_sizes.lbs_backing_file);
 	lsm_blob_size_update(&blobs->lbs_ib, &blob_sizes.lbs_ib);
 	/* inode blob gets an rcu_head in addition to LSM blobs. */
 	if (blobs->lbs_inode && blob_sizes.lbs_inode == 0)
@@ -441,6 +443,8 @@ int __init security_init(void)
 	if (lsm_debug) {
 		lsm_pr("blob(cred) size %d\n", blob_sizes.lbs_cred);
 		lsm_pr("blob(file) size %d\n", blob_sizes.lbs_file);
+		lsm_pr("blob(backing_file) size %d\n",
+		       blob_sizes.lbs_backing_file);
 		lsm_pr("blob(ib) size %d\n", blob_sizes.lbs_ib);
 		lsm_pr("blob(inode) size %d\n", blob_sizes.lbs_inode);
 		lsm_pr("blob(ipc) size %d\n", blob_sizes.lbs_ipc);
@@ -462,6 +466,11 @@ int __init security_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,

security/security.c

@@ -82,6 +82,7 @@ const struct lsm_id *lsm_idlist[MAX_LSM_COUNT];
 struct lsm_blob_sizes blob_sizes;
 
 struct kmem_cache *lsm_file_cache;
+struct kmem_cache *lsm_backing_file_cache;
 struct kmem_cache *lsm_inode_cache;
 
 #define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX
@@ -173,6 +174,30 @@ 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_blob_alloc - allocate a composite blob
  * @dest: the destination for the blob
@@ -2418,6 +2443,57 @@ 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, 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);
+	}
+}
+
 /**
  * security_file_ioctl() - Check if an ioctl is allowed
  * @file: associated file
@@ -2506,6 +2582,32 @@ int security_mmap_file(struct file *file, unsigned long prot,
 			     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, vma, backing_file, user_file);
+}
+EXPORT_SYMBOL_GPL(security_mmap_backing_file);
+
 /**
  * security_mmap_addr() - Check if mmap'ing an address is allowed
  * @addr: address

security/selinux/hooks.c

@@ -1745,6 +1745,60 @@ static inline int file_path_has_perm(const struct cred *cred,
 static int bpf_fd_pass(const struct file *file, u32 sid);
 #endif
 
+static int __file_has_perm(const struct cred *cred, const struct file *file,
+			   u32 av, bool bf_user_file)
+
+{
+	struct common_audit_data ad;
+	struct inode *inode;
+	u32 ssid = cred_sid(cred);
+	u32 tsid_fd;
+	int rc;
+
+	if (bf_user_file) {
+		struct backing_file_security_struct *bfsec;
+		const struct path *path;
+
+		if (WARN_ON(!(file->f_mode & FMODE_BACKING)))
+			return -EIO;
+
+		bfsec = selinux_backing_file(file);
+		path = backing_file_user_path(file);
+		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(ssid, tsid_fd, SECCLASS_FD, FD__USE, &ad);
+		if (rc)
+			return rc;
+	}
+
+#ifdef CONFIG_BPF_SYSCALL
+	/* 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. */
+	if (av)
+		return inode_has_perm(cred, inode, av, &ad);
+
+	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
@@ -1753,41 +1807,10 @@ static int bpf_fd_pass(const struct file *file, u32 sid);
    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 inline int file_has_perm(const struct cred *cred,
+				const struct file *file, u32 av)
 {
-	struct file_security_struct *fsec = selinux_file(file);
-	struct inode *inode = file_inode(file);
-	struct common_audit_data ad;
-	u32 sid = cred_sid(cred);
-	int rc;
-
-	ad.type = LSM_AUDIT_DATA_FILE;
-	ad.u.file = file;
-
-	if (sid != fsec->sid) {
-		rc = avc_has_perm(sid, fsec->sid,
-				  SECCLASS_FD,
-				  FD__USE,
-				  &ad);
-		if (rc)
-			goto out;
-	}
-
-#ifdef CONFIG_BPF_SYSCALL
-	rc = bpf_fd_pass(file, cred_sid(cred));
-	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);
-
-out:
-	return rc;
+	return __file_has_perm(cred, file, av, false);
 }
 
 /*
@@ -3825,6 +3848,17 @@ 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.
@@ -3942,42 +3976,55 @@ 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(backing_file_user_path(file)->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(sid, sid, SECCLASS_PROCESS,
-				  PROCESS__EXECMEM, NULL);
+		rc = avc_has_perm(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)
@@ -3993,36 +4040,80 @@ static int selinux_mmap_addr(unsigned long addr)
 	return rc;
 }
 
-static int selinux_mmap_file(struct file *file,
-			     unsigned long reqprot __always_unused,
-			     unsigned long prot, unsigned long flags)
+static int selinux_mmap_file_common(const struct cred *cred, struct file *file,
+				    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;
 	}
 
-	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 __always_unused,
+			     unsigned long prot, unsigned long flags)
+{
+	return selinux_mmap_file_common(current_cred(), file, 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, vma->vm_flags & VM_SHARED);
 }
 
 static int selinux_file_mprotect(struct vm_area_struct *vma,
 				 unsigned long reqprot __always_unused,
 				 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 (default_noexec &&
 	    (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
-		int rc = 0;
 		/*
 		 * We don't use the vma_is_initial_heap() helper as it has
 		 * a history of problems and is currently broken on systems
@@ -4036,11 +4127,15 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
 		    vma->vm_end <= vma->vm_mm->brk) {
 			rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
 					  PROCESS__EXECHEAP, NULL);
-		} else if (!vma->vm_file && (vma_is_initial_stack(vma) ||
+			if (rc)
+				return rc;
+		} else if (!file && (vma_is_initial_stack(vma) ||
 			    vma_is_stack_for_current(vma))) {
 			rc = avc_has_perm(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
@@ -4048,13 +4143,29 @@ 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)
@@ -7393,6 +7504,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = {
 	.lbs_cred = sizeof(struct cred_security_struct),
 	.lbs_task = 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_key = sizeof(struct key_security_struct),
@@ -7498,9 +7610,11 @@ static struct security_hook_list selinux_hooks[] __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),

security/selinux/include/objsec.h

@@ -88,6 +88,10 @@ 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 {
 	u32 sid; /* SID of file system superblock */
 	u32 def_sid; /* default SID for labeling */
@@ -195,6 +199,13 @@ 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)
 {