seccomp: add "seccomp" syscall
This adds the new "seccomp" syscall with both an "operation" and "flags"
parameter for future expansion. The third argument is a pointer value,
used with the SECCOMP_SET_MODE_FILTER operation. Currently, flags must
be 0. This is functionally equivalent to prctl(PR_SET_SECCOMP, ...).
In addition to the TSYNC flag later in this patch series, there is a
non-zero chance that this syscall could be used for configuring a fixed
argument area for seccomp-tracer-aware processes to pass syscall arguments
in the future. Hence, the use of "seccomp" not simply "seccomp_add_filter"
for this syscall. Additionally, this syscall uses operation, flags,
and user pointer for arguments because strictly passing arguments via
a user pointer would mean seccomp itself would be unable to trivially
filter the seccomp syscall itself.
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Conflicts:
arch/x86/syscalls/syscall_32.tbl
arch/x86/syscalls/syscall_64.tbl
include/linux/syscalls.h
include/uapi/asm-generic/unistd.h
include/uapi/linux/seccomp.h
kernel/seccomp.c
kernel/sys_ni.c
diff --git a/arch/Kconfig b/arch/Kconfig
index 78f9ac2..f9ab2c2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -231,6 +231,7 @@
- secure_computing is called from a ptrace_event()-safe context
- secure_computing return value is checked and a return value of -1
results in the system call being skipped immediately.
+ - seccomp syscall wired up
config SECCOMP_FILTER
def_bool y
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 29f9f05..64e5526 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -355,3 +355,4 @@
346 i386 setns sys_setns
347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
+354 i386 seccomp sys_seccomp
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index dd29a9e..9073c08 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -318,6 +318,8 @@
309 common getcpu sys_getcpu
310 64 process_vm_readv sys_process_vm_readv
311 64 process_vm_writev sys_process_vm_writev
+317 common seccomp sys_seccomp
+
#
# x32-specific system call numbers start at 512 to avoid cache impact
# for native 64-bit operation.
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 991ef01..ae8513b 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -691,9 +691,11 @@
#define __NR_process_vm_writev 271
__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
compat_sys_process_vm_writev)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
#undef __NR_syscalls
-#define __NR_syscalls 272
+#define __NR_syscalls 278
/*
* All syscalls below here should go away really,
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 5818e86..5af7d9b 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -10,6 +10,10 @@
#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+
/*
* All BPF programs must return a 32-bit value.
* The bottom 16-bits are for optional return data.
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index d4e3f6b..ed7d6dd 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -858,4 +858,6 @@
unsigned long riovcnt,
unsigned long flags);
+asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
+ const char __user *uargs);
#endif
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 4a1279c..184a742 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -18,6 +18,7 @@
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
+#include <linux/syscalls.h>
/* #define SECCOMP_DEBUG 1 */
@@ -307,7 +308,7 @@
*
* Returns 0 on success and non-zero otherwise.
*/
-long seccomp_attach_user_filter(char __user *user_filter)
+static long seccomp_attach_user_filter(const char __user *user_filter)
{
struct sock_fprog fprog;
long ret = -EFAULT;
@@ -506,6 +507,7 @@
#ifdef CONFIG_SECCOMP_FILTER
/**
* seccomp_set_mode_filter: internal function for setting seccomp filter
+ * @flags: flags to change filter behavior
* @filter: struct sock_fprog containing filter
*
* This function may be called repeatedly to install additional filters.
@@ -516,11 +518,16 @@
*
* Returns 0 on success or -EINVAL on failure.
*/
-static long seccomp_set_mode_filter(char __user *filter)
+static long seccomp_set_mode_filter(unsigned int flags,
+ const char __user *filter)
{
const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
long ret = -EINVAL;
+ /* Validate flags. */
+ if (flags != 0)
+ goto out;
+
if (!seccomp_may_assign_mode(seccomp_mode))
goto out;
@@ -533,12 +540,35 @@
return ret;
}
#else
-static inline long seccomp_set_mode_filter(char __user *filter)
+static inline long seccomp_set_mode_filter(unsigned int flags,
+ const char __user *filter)
{
return -EINVAL;
}
#endif
+/* Common entry point for both prctl and syscall. */
+static long do_seccomp(unsigned int op, unsigned int flags,
+ const char __user *uargs)
+{
+ switch (op) {
+ case SECCOMP_SET_MODE_STRICT:
+ if (flags != 0 || uargs != NULL)
+ return -EINVAL;
+ return seccomp_set_mode_strict();
+ case SECCOMP_SET_MODE_FILTER:
+ return seccomp_set_mode_filter(flags, uargs);
+ default:
+ return -EINVAL;
+ }
+}
+
+SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags,
+ const char __user *, uargs)
+{
+ return do_seccomp(op, flags, uargs);
+}
+
/**
* prctl_set_seccomp: configures current->seccomp.mode
* @seccomp_mode: requested mode to use
@@ -548,12 +578,27 @@
*/
long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
{
+ unsigned int op;
+ char __user *uargs;
+
switch (seccomp_mode) {
case SECCOMP_MODE_STRICT:
- return seccomp_set_mode_strict();
+ op = SECCOMP_SET_MODE_STRICT;
+ /*
+ * Setting strict mode through prctl always ignored filter,
+ * so make sure it is always NULL here to pass the internal
+ * check in do_seccomp().
+ */
+ uargs = NULL;
+ break;
case SECCOMP_MODE_FILTER:
- return seccomp_set_mode_filter(filter);
+ op = SECCOMP_SET_MODE_FILTER;
+ uargs = filter;
+ break;
default:
return -EINVAL;
}
+
+ /* prctl interface doesn't have flags, so they are always zero. */
+ return do_seccomp(op, 0, uargs);
}
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 47bfa16..026f30a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -203,3 +203,6 @@
cond_syscall(sys_name_to_handle_at);
cond_syscall(sys_open_by_handle_at);
cond_syscall(compat_sys_open_by_handle_at);
+
+/* operate on Secure Computing state */
+cond_syscall(sys_seccomp);