summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorJeff Xu <jeffxu@google.com>2022-12-15 03:12:03 +0300
committerAndrew Morton <akpm@linux-foundation.org>2023-01-19 04:12:37 +0300
commit105ff5339f498af74e60d7662c8f1c4d21f1342d (patch)
treeab42419f8614011b2381abdefc16974a490d31ac /kernel
parent32d118ad50a5afecb74358bcefc5cb6ea6ccfc2b (diff)
downloadlinux-105ff5339f498af74e60d7662c8f1c4d21f1342d.tar.xz
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>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/pid_namespace.c5
-rw-r--r--kernel/pid_sysctl.h60
2 files changed, 65 insertions, 0 deletions
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index f4f8cb0435b4..8a98b1af9376 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -23,6 +23,7 @@
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/idr.h>
+#include "pid_sysctl.h"
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;
@@ -110,6 +111,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
ns->ucounts = ucounts;
ns->pid_allocated = PIDNS_ADDING;
+ initialize_memfd_noexec_scope(ns);
+
return ns;
out_free_idr:
@@ -455,6 +458,8 @@ static __init int pid_namespaces_init(void)
#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
+
+ register_pid_ns_sysctl_table_vm();
return 0;
}
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
new file mode 100644
index 000000000000..e22d072e1e24
--- /dev/null
+++ b/kernel/pid_sysctl.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_PID_SYSCTL_H
+#define LINUX_PID_SYSCTL_H
+
+#include <linux/pid_namespace.h>
+
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
+static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns)
+{
+ ns->memfd_noexec_scope =
+ task_active_pid_ns(current)->memfd_noexec_scope;
+}
+
+static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table,
+ int write, void *buf, size_t *lenp, loff_t *ppos)
+{
+ struct pid_namespace *ns = task_active_pid_ns(current);
+ struct ctl_table table_copy;
+
+ if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ table_copy = *table;
+ if (ns != &init_pid_ns)
+ table_copy.data = &ns->memfd_noexec_scope;
+
+ /*
+ * set minimum to current value, the effect is only bigger
+ * value is accepted.
+ */
+ if (*(int *)table_copy.data > *(int *)table_copy.extra1)
+ table_copy.extra1 = table_copy.data;
+
+ return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos);
+}
+
+static struct ctl_table pid_ns_ctl_table_vm[] = {
+ {
+ .procname = "memfd_noexec",
+ .data = &init_pid_ns.memfd_noexec_scope,
+ .maxlen = sizeof(init_pid_ns.memfd_noexec_scope),
+ .mode = 0644,
+ .proc_handler = pid_mfd_noexec_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_TWO,
+ },
+ { }
+};
+static struct ctl_path vm_path[] = { { .procname = "vm", }, { } };
+static inline void register_pid_ns_sysctl_table_vm(void)
+{
+ register_sysctl_paths(vm_path, pid_ns_ctl_table_vm);
+}
+#else
+static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {}
+static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {}
+static inline void register_pid_ns_sysctl_table_vm(void) {}
+#endif
+
+#endif /* LINUX_PID_SYSCTL_H */