mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC

The new MFD_NOEXEC_SEAL and MFD_EXEC flags allows application to set
executable bit at creation time (memfd_create).

When MFD_NOEXEC_SEAL is set, memfd is created without executable bit
(mode:0666), and sealed with F_SEAL_EXEC, so it can't be chmod to be
executable (mode: 0777) after creation.

when MFD_EXEC flag is set, memfd is created with executable bit
(mode:0777), this is the same as the old behavior of memfd_create.

The new pid namespaced sysctl vm.memfd_noexec has 3 values:
0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like
        MFD_EXEC was set.
1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like
        MFD_NOEXEC_SEAL was set.
2: memfd_create() without MFD_NOEXEC_SEAL will be rejected.

The sysctl allows finer control of memfd_create for old-software that
doesn't set the executable bit, for example, a container with
vm.memfd_noexec=1 means the old-software will create non-executable memfd
by default.  Also, the value of memfd_noexec is passed to child namespace
at creation time.  For example, if the init namespace has
vm.memfd_noexec=2, all its children namespaces will be created with 2.

[akpm@linux-foundation.org: add stub functions to fix build]
[akpm@linux-foundation.org: remove unneeded register_pid_ns_ctl_table_vm() stub, per Jeff]
[akpm@linux-foundation.org: s/pr_warn_ratelimited/pr_warn_once/, per review]
[akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warning]
Link: https://lkml.kernel.org/r/20221215001205.51969-4-jeffxu@google.com
Signed-off-by: Jeff Xu <jeffxu@google.com>
Co-developed-by: Daniel Verkamp <dverkamp@chromium.org>
Signed-off-by: Daniel Verkamp <dverkamp@chromium.org>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: David Herrmann <dh.herrmann@gmail.com>
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: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 23 insertions, 0 deletions

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 07481bb87d4e..c758809d5bcf 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -16,6 +16,21 @@
 
 struct fs_pin;
 
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+/*
+ * sysctl for vm.memfd_noexec
+ * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL
+ *	acts like MFD_EXEC was set.
+ * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL
+ *	acts like MFD_NOEXEC_SEAL was set.
+ * 2: memfd_create() without MFD_NOEXEC_SEAL will be
+ *	rejected.
+ */
+#define MEMFD_NOEXEC_SCOPE_EXEC			0
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL		1
+#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED	2
+#endif
+
 struct pid_namespace {
 	struct idr idr;
 	struct rcu_head rcu;
@@ -31,6 +46,10 @@ struct pid_namespace {
 	struct ucounts *ucounts;
 	int reboot;	/* group exit code if this pidns was rebooted */
 	struct ns_common ns;
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+	/* sysctl for vm.memfd_noexec */
+	int memfd_noexec_scope;
+#endif
 } __randomize_layout;
 
 extern struct pid_namespace init_pid_ns;
diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
index 7a8a26751c23..273a4e15dfcf 100644
--- a/include/uapi/linux/memfd.h
+++ b/include/uapi/linux/memfd.h
@@ -8,6 +8,10 @@
 #define MFD_CLOEXEC		0x0001U
 #define MFD_ALLOW_SEALING	0x0002U
 #define MFD_HUGETLB		0x0004U
+/* not executable and sealed to prevent changing to executable. */
+#define MFD_NOEXEC_SEAL		0x0008U
+/* executable */
+#define MFD_EXEC		0x0010U
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page