mm/memfd: sysctl: fix MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED

Patch series "mm/memfd: fix sysctl MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED", v2.

When sysctl vm.memfd_noexec is 2 (MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED),
memfd_create(.., MFD_EXEC) should fail.

This complies with how MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED is defined -
"memfd_create() without MFD_NOEXEC_SEAL will be rejected"

Thanks to Dominique Martinet <asmadeus@codewreck.org> who reported the bug.
see [1] for context.

[1] https://lore.kernel.org/linux-mm/CABi2SkXUX_QqTQ10Yx9bBUGpN1wByOi_=gZU6WEy5a8MaQY3Jw@mail.gmail.com/T/


This patch (of 2):

When vm.memfd_noexec is 2 (MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED),
memfd_create(.., MFD_EXEC) should fail.

This complies with how MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED is
defined - "memfd_create() without MFD_NOEXEC_SEAL will be rejected"

Link: https://lkml.kernel.org/r/20230705063315.3680666-1-jeffxu@google.com
Link: https://lkml.kernel.org/r/20230705063315.3680666-2-jeffxu@google.com
Fixes: 105ff533 ("mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC")
Reported-by: Dominique Martinet <asmadeus@codewreck.org>
Closes: https://lore.kernel.org/linux-mm/CABi2SkXUX_QqTQ10Yx9bBUGpN1wByOi_=gZU6WEy5a8MaQY3Jw@mail.gmail.com/T/Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202306301351.kkbSegQW-lkp@intel.com/Signed-off-by: Jeff Xu <jeffxu@google.com>
Cc: Daniel Verkamp <dverkamp@chromium.org>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jorge Lucangeli Obes <jorgelo@chromium.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/memfd.c

@@ -268,6 +268,36 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
 
 #define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC)
 
+static int check_sysctl_memfd_noexec(unsigned int *flags)
+{
+#ifdef CONFIG_SYSCTL
+	char comm[TASK_COMM_LEN];
+	int sysctl = MEMFD_NOEXEC_SCOPE_EXEC;
+	struct pid_namespace *ns;
+
+	ns = task_active_pid_ns(current);
+	if (ns)
+		sysctl = ns->memfd_noexec_scope;
+
+	if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
+		if (sysctl == MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL)
+			*flags |= MFD_NOEXEC_SEAL;
+		else
+			*flags |= MFD_EXEC;
+	}
+
+	if (*flags & MFD_EXEC && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) {
+		pr_warn_once(
+			"memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n",
+			task_pid_nr(current), get_task_comm(comm, current));
+
+		return -EACCES;
+	}
+#endif
+
+	return 0;
+}
+
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
 		unsigned int, flags)
@@ -294,35 +324,14 @@ SYSCALL_DEFINE2(memfd_create,
 		return -EINVAL;
 
 	if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
-#ifdef CONFIG_SYSCTL
-		int sysctl = MEMFD_NOEXEC_SCOPE_EXEC;
-		struct pid_namespace *ns;
-
-		ns = task_active_pid_ns(current);
-		if (ns)
-			sysctl = ns->memfd_noexec_scope;
-
-		switch (sysctl) {
-		case MEMFD_NOEXEC_SCOPE_EXEC:
-			flags |= MFD_EXEC;
-			break;
-		case MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL:
-			flags |= MFD_NOEXEC_SEAL;
-			break;
-		default:
-			pr_warn_once(
-				"memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n",
-				task_pid_nr(current), get_task_comm(comm, current));
-			return -EINVAL;
-		}
-#else
-		flags |= MFD_EXEC;
-#endif
 		pr_warn_once(
 			"memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL, pid=%d '%s'\n",
 			task_pid_nr(current), get_task_comm(comm, current));
 	}
 
+	if (check_sysctl_memfd_noexec(&flags) < 0)
+		return -EACCES;
+
 	/* length includes terminating zero */
 	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
 	if (len <= 0)