memfd,selinux: call security_inode_init_security_anon()

Prior to this change, no security hooks were called at the creation of a
memfd file. It means that, for SELinux as an example, it will receive
the default type of the filesystem that backs the in-memory inode. In
most cases, that would be tmpfs, but if MFD_HUGETLB is passed, it will
be hugetlbfs. Both can be considered implementation details of memfd.

It also means that it is not possible to differentiate between a file
coming from memfd_create and a file coming from a standard tmpfs mount
point.

Additionally, no permission is validated at creation, which differs from
the similar memfd_secret syscall.

Call security_inode_init_security_anon during creation. This ensures
that the file is setup similarly to other anonymous inodes. On SELinux,
it means that the file will receive the security context of its task.

The ability to limit fexecve on memfd has been of interest to avoid
potential pitfalls where /proc/self/exe or similar would be executed
[1][2]. Reuse the "execute_no_trans" and "entrypoint" access vectors,
similarly to the file class. These access vectors may not make sense for
the existing "anon_inode" class. Therefore, define and assign a new
class "memfd_file" to support such access vectors.

Guard these changes behind a new policy capability named "memfd_class".

[1] https://crbug.com/1305267
[2] https://lore.kernel.org/lkml/20221215001205.51969-1-jeffxu@google.com/

Signed-off-by: Thiébaud Weksteen <tweek@google.com>
Reviewed-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Tested-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
[PM: subj tweak]
Signed-off-by: Paul Moore <paul@paul-moore.com>

Author: tweksteen

include/linux/memfd.h

@@ -4,6 +4,8 @@
 
 #include <linux/file.h>
 
+#define MEMFD_ANON_NAME "[memfd]"
+
 #ifdef CONFIG_MEMFD_CREATE
 extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
 struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);

mm/memfd.c

@@ -433,6 +433,8 @@ static struct file *alloc_file(const char *name, unsigned int flags)
 {
 	unsigned int *file_seals;
 	struct file *file;
+	struct inode *inode;
+	int err = 0;
 
 	if (flags & MFD_HUGETLB) {
 		file = hugetlb_file_setup(name, 0, VM_NORESERVE,
@@ -444,12 +446,20 @@ static struct file *alloc_file(const char *name, unsigned int flags)
 	}
 	if (IS_ERR(file))
 		return file;
+
+	inode = file_inode(file);
+	err = security_inode_init_security_anon(inode,
+			&QSTR(MEMFD_ANON_NAME), NULL);
+	if (err) {
+		fput(file);
+		file = ERR_PTR(err);
+		return file;
+	}
+
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	file->f_flags |= O_LARGEFILE;
 
 	if (flags & MFD_NOEXEC_SEAL) {
-		struct inode *inode = file_inode(file);
-
 		inode->i_mode &= ~0111;
 		file_seals = memfd_file_seals_ptr(file);
 		if (file_seals) {

security/selinux/hooks.c

@@ -93,6 +93,7 @@
 #include <linux/fanotify.h>
 #include <linux/io_uring/cmd.h>
 #include <uapi/linux/lsm.h>
+#include <linux/memfd.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -2319,6 +2320,10 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm)
 	new_tsec = selinux_cred(bprm->cred);
 	isec = inode_security(inode);
 
+	if (WARN_ON(isec->sclass != SECCLASS_FILE &&
+		    isec->sclass != SECCLASS_MEMFD_FILE))
+		return -EACCES;
+
 	/* Default to the current task SID. */
 	new_tsec->sid = old_tsec->sid;
 	new_tsec->osid = old_tsec->sid;
@@ -2371,8 +2376,8 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm)
 	ad.u.file = bprm->file;
 
 	if (new_tsec->sid == old_tsec->sid) {
-		rc = avc_has_perm(old_tsec->sid, isec->sid,
-				  SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad);
+		rc = avc_has_perm(old_tsec->sid, isec->sid, isec->sclass,
+				  FILE__EXECUTE_NO_TRANS, &ad);
 		if (rc)
 			return rc;
 	} else {
@@ -2382,8 +2387,8 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm)
 		if (rc)
 			return rc;
 
-		rc = avc_has_perm(new_tsec->sid, isec->sid,
-				  SECCLASS_FILE, FILE__ENTRYPOINT, &ad);
+		rc = avc_has_perm(new_tsec->sid, isec->sid, isec->sclass,
+				  FILE__ENTRYPOINT, &ad);
 		if (rc)
 			return rc;
 
@@ -2978,10 +2983,18 @@ static int selinux_inode_init_security_anon(struct inode *inode,
 	struct common_audit_data ad;
 	struct inode_security_struct *isec;
 	int rc;
+	bool is_memfd = false;
 
 	if (unlikely(!selinux_initialized()))
 		return 0;
 
+	if (name != NULL && name->name != NULL &&
+	    !strcmp(name->name, MEMFD_ANON_NAME)) {
+		if (!selinux_policycap_memfd_class())
+			return 0;
+		is_memfd = true;
+	}
+
 	isec = selinux_inode(inode);
 
 	/*
@@ -3001,7 +3014,10 @@ static int selinux_inode_init_security_anon(struct inode *inode,
 		isec->sclass = context_isec->sclass;
 		isec->sid = context_isec->sid;
 	} else {
-		isec->sclass = SECCLASS_ANON_INODE;
+		if (is_memfd)
+			isec->sclass = SECCLASS_MEMFD_FILE;
+		else
+			isec->sclass = SECCLASS_ANON_INODE;
 		rc = security_transition_sid(
 			sid, sid,
 			isec->sclass, name, &isec->sid);

security/selinux/include/classmap.h

@@ -179,6 +179,8 @@ const struct security_class_mapping secclass_map[] = {
 	{ "anon_inode", { COMMON_FILE_PERMS, NULL } },
 	{ "io_uring", { "override_creds", "sqpoll", "cmd", "allowed", NULL } },
 	{ "user_namespace", { "create", NULL } },
+	{ "memfd_file",
+	  { COMMON_FILE_PERMS, "execute_no_trans", "entrypoint", NULL } },
 	/* last one */ { NULL, {} }
 };
 

security/selinux/include/policycap.h

@@ -18,6 +18,7 @@ enum {
 	POLICYDB_CAP_NETIF_WILDCARD,
 	POLICYDB_CAP_GENFS_SECLABEL_WILDCARD,
 	POLICYDB_CAP_FUNCTIONFS_SECLABEL,
+	POLICYDB_CAP_MEMFD_CLASS,
 	__POLICYDB_CAP_MAX
 };
 #define POLICYDB_CAP_MAX (__POLICYDB_CAP_MAX - 1)

security/selinux/include/policycap_names.h

@@ -21,6 +21,7 @@ const char *const selinux_policycap_names[__POLICYDB_CAP_MAX] = {
 	"netif_wildcard",
 	"genfs_seclabel_wildcard",
 	"functionfs_seclabel",
+	"memfd_class",
 };
 /* clang-format on */
 

security/selinux/include/security.h

@@ -209,6 +209,11 @@ static inline bool selinux_policycap_functionfs_seclabel(void)
 		selinux_state.policycap[POLICYDB_CAP_FUNCTIONFS_SECLABEL]);
 }
 
+static inline bool selinux_policycap_memfd_class(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_MEMFD_CLASS]);
+}
+
 struct selinux_policy_convert_data;
 
 struct selinux_load_state {